diff options
| author | Jay Berkenbilt <ejb@ql.org> | 2009-10-10 19:41:30 +0200 |
|---|---|---|
| committer | Jay Berkenbilt <ejb@ql.org> | 2009-10-10 19:41:30 +0200 |
| commit | f3bf8d3110b852b8f338898c3237d16a74360cf3 (patch) | |
| tree | cf291098388c426129f1a9e87dcbe27afc571eb3 /external-libs | |
| parent | eb355c60c1fa9ea93fa6824349c91ed324f4ff14 (diff) | |
| download | qpdf-f3bf8d3110b852b8f338898c3237d16a74360cf3.tar.zst | |
remove files not needed for building
git-svn-id: svn+q:///qpdf/trunk@767 71b93d88-0707-0410-a8cf-f5a4172ac649
Diffstat (limited to 'external-libs')
89 files changed, 0 insertions, 52553 deletions
diff --git a/external-libs/pcre/ChangeLog b/external-libs/pcre/ChangeLog deleted file mode 100644 index edc4aea4..00000000 --- a/external-libs/pcre/ChangeLog +++ /dev/null @@ -1,1475 +0,0 @@ -ChangeLog for PCRE ------------------- - -Version 4.5 01-Dec-03 ---------------------- - - 1. There has been some re-arrangement of the code for the match() function so - that it can be compiled in a version that does not call itself recursively. - Instead, it keeps those local variables that need separate instances for - each "recursion" in a frame on the heap, and gets/frees frames whenever it - needs to "recurse". Keeping track of where control must go is done by means - of setjmp/longjmp. The whole thing is implemented by a set of macros that - hide most of the details from the main code, and operates only if - NO_RECURSE is defined while compiling pcre.c. If PCRE is built using the - "configure" mechanism, "--disable-stack-for-recursion" turns on this way of - operating. - - To make it easier for callers to provide specially tailored get/free - functions for this usage, two new functions, pcre_stack_malloc, and - pcre_stack_free, are used. They are always called in strict stacking order, - and the size of block requested is always the same. - - The PCRE_CONFIG_STACKRECURSE info parameter can be used to find out whether - PCRE has been compiled to use the stack or the heap for recursion. The - -C option of pcretest uses this to show which version is compiled. - - A new data escape \S, is added to pcretest; it causes the amounts of store - obtained and freed by both kinds of malloc/free at match time to be added - to the output. - - 2. Changed the locale test to use "fr_FR" instead of "fr" because that's - what's available on my current Linux desktop machine. - - 3. When matching a UTF-8 string, the test for a valid string at the start has - been extended. If start_offset is not zero, PCRE now checks that it points - to a byte that is the start of a UTF-8 character. If not, it returns - PCRE_ERROR_BADUTF8_OFFSET (-11). Note: the whole string is still checked; - this is necessary because there may be backward assertions in the pattern. - When matching the same subject several times, it may save resources to use - PCRE_NO_UTF8_CHECK on all but the first call if the string is long. - - 4. The code for checking the validity of UTF-8 strings has been tightened so - that it rejects (a) strings containing 0xfe or 0xff bytes and (b) strings - containing "overlong sequences". - - 5. Fixed a bug (appearing twice) that I could not find any way of exploiting! - I had written "if ((digitab[*p++] && chtab_digit) == 0)" where the "&&" - should have been "&", but it just so happened that all the cases this let - through by mistake were picked up later in the function. - - 6. I had used a variable called "isblank" - this is a C99 function, causing - some compilers to warn. To avoid this, I renamed it (as "blankclass"). - - 7. Cosmetic: (a) only output another newline at the end of pcretest if it is - prompting; (b) run "./pcretest /dev/null" at the start of the test script - so the version is shown; (c) stop "make test" echoing "./RunTest". - - 8. Added patches from David Burgess to enable PCRE to run on EBCDIC systems. - - 9. The prototype for memmove() for systems that don't have it was using - size_t, but the inclusion of the header that defines size_t was later. I've - moved the #includes for the C headers earlier to avoid this. - -10. Added some adjustments to the code to make it easier to compiler on certain - special systems: - - (a) Some "const" qualifiers were missing. - (b) Added the macro EXPORT before all exported functions; by default this - is defined to be empty. - (c) Changed the dftables auxiliary program (that builds chartables.c) so - that it reads its output file name as an argument instead of writing - to the standard output and assuming this can be redirected. - -11. In UTF-8 mode, if a recursive reference (e.g. (?1)) followed a character - class containing characters with values greater than 255, PCRE compilation - went into a loop. - -12. A recursive reference to a subpattern that was within another subpattern - that had a minimum quantifier of zero caused PCRE to crash. For example, - (x(y(?2))z)? provoked this bug with a subject that got as far as the - recursion. If the recursively-called subpattern itself had a zero repeat, - that was OK. - -13. In pcretest, the buffer for reading a data line was set at 30K, but the - buffer into which it was copied (for escape processing) was still set at - 1024, so long lines caused crashes. - -14. A pattern such as /[ab]{1,3}+/ failed to compile, giving the error - "internal error: code overflow...". This applied to any character class - that was followed by a possessive quantifier. - -15. Modified the Makefile to add libpcre.la as a prerequisite for - libpcreposix.la because I was told this is needed for a parallel build to - work. - -16. If a pattern that contained .* following optional items at the start was - studied, the wrong optimizing data was generated, leading to matching - errors. For example, studying /[ab]*.*c/ concluded, erroneously, that any - matching string must start with a or b or c. The correct conclusion for - this pattern is that a match can start with any character. - - -Version 4.4 13-Aug-03 ---------------------- - - 1. In UTF-8 mode, a character class containing characters with values between - 127 and 255 was not handled correctly if the compiled pattern was studied. - In fixing this, I have also improved the studying algorithm for such - classes (slightly). - - 2. Three internal functions had redundant arguments passed to them. Removal - might give a very teeny performance improvement. - - 3. Documentation bug: the value of the capture_top field in a callout is *one - more than* the number of the hightest numbered captured substring. - - 4. The Makefile linked pcretest and pcregrep with -lpcre, which could result - in incorrectly linking with a previously installed version. They now link - explicitly with libpcre.la. - - 5. configure.in no longer needs to recognize Cygwin specially. - - 6. A problem in pcre.in for Windows platforms is fixed. - - 7. If a pattern was successfully studied, and the -d (or /D) flag was given to - pcretest, it used to include the size of the study block as part of its - output. Unfortunately, the structure contains a field that has a different - size on different hardware architectures. This meant that the tests that - showed this size failed. As the block is currently always of a fixed size, - this information isn't actually particularly useful in pcretest output, so - I have just removed it. - - 8. Three pre-processor statements accidentally did not start in column 1. - Sadly, there are *still* compilers around that complain, even though - standard C has not required this for well over a decade. Sigh. - - 9. In pcretest, the code for checking callouts passed small integers in the - callout_data field, which is a void * field. However, some picky compilers - complained about the casts involved for this on 64-bit systems. Now - pcretest passes the address of the small integer instead, which should get - rid of the warnings. - -10. By default, when in UTF-8 mode, PCRE now checks for valid UTF-8 strings at - both compile and run time, and gives an error if an invalid UTF-8 sequence - is found. There is a option for disabling this check in cases where the - string is known to be correct and/or the maximum performance is wanted. - -11. In response to a bug report, I changed one line in Makefile.in from - - -Wl,--out-implib,.libs/lib@WIN_PREFIX@pcreposix.dll.a \ - to - -Wl,--out-implib,.libs/@WIN_PREFIX@libpcreposix.dll.a \ - - to look similar to other lines, but I have no way of telling whether this - is the right thing to do, as I do not use Windows. No doubt I'll get told - if it's wrong... - - -Version 4.3 21-May-03 ---------------------- - -1. Two instances of @WIN_PREFIX@ omitted from the Windows targets in the - Makefile. - -2. Some refactoring to improve the quality of the code: - - (i) The utf8_table... variables are now declared "const". - - (ii) The code for \cx, which used the "case flipping" table to upper case - lower case letters, now just substracts 32. This is ASCII-specific, - but the whole concept of \cx is ASCII-specific, so it seems - reasonable. - - (iii) PCRE was using its character types table to recognize decimal and - hexadecimal digits in the pattern. This is silly, because it handles - only 0-9, a-f, and A-F, but the character types table is locale- - specific, which means strange things might happen. A private - table is now used for this - though it costs 256 bytes, a table is - much faster than multiple explicit tests. Of course, the standard - character types table is still used for matching digits in subject - strings against \d. - - (iv) Strictly, the identifier ESC_t is reserved by POSIX (all identifiers - ending in _t are). So I've renamed it as ESC_tee. - -3. The first argument for regexec() in the POSIX wrapper should have been - defined as "const". - -4. Changed pcretest to use malloc() for its buffers so that they can be - Electric Fenced for debugging. - -5. There were several places in the code where, in UTF-8 mode, PCRE would try - to read one or more bytes before the start of the subject string. Often this - had no effect on PCRE's behaviour, but in some circumstances it could - provoke a segmentation fault. - -6. A lookbehind at the start of a pattern in UTF-8 mode could also cause PCRE - to try to read one or more bytes before the start of the subject string. - -7. A lookbehind in a pattern matched in non-UTF-8 mode on a PCRE compiled with - UTF-8 support could misbehave in various ways if the subject string - contained bytes with the 0x80 bit set and the 0x40 bit unset in a lookbehind - area. (PCRE was not checking for the UTF-8 mode flag, and trying to move - back over UTF-8 characters.) - - -Version 4.2 14-Apr-03 ---------------------- - -1. Typo "#if SUPPORT_UTF8" instead of "#ifdef SUPPORT_UTF8" fixed. - -2. Changes to the building process, supplied by Ronald Landheer-Cieslak - [ON_WINDOWS]: new variable, "#" on non-Windows platforms - [NOT_ON_WINDOWS]: new variable, "#" on Windows platforms - [WIN_PREFIX]: new variable, "cyg" for Cygwin - * Makefile.in: use autoconf substitution for OBJEXT, EXEEXT, BUILD_OBJEXT - and BUILD_EXEEXT - Note: automatic setting of the BUILD variables is not yet working - set CPPFLAGS and BUILD_CPPFLAGS (but don't use yet) - should be used at - compile-time but not at link-time - [LINK]: use for linking executables only - make different versions for Windows and non-Windows - [LINKLIB]: new variable, copy of UNIX-style LINK, used for linking - libraries - [LINK_FOR_BUILD]: new variable - [OBJEXT]: use throughout - [EXEEXT]: use throughout - <winshared>: new target - <wininstall>: new target - <dftables.o>: use native compiler - <dftables>: use native linker - <install>: handle Windows platform correctly - <clean>: ditto - <check>: ditto - copy DLL to top builddir before testing - - As part of these changes, -no-undefined was removed again. This was reported - to give trouble on HP-UX 11.0, so getting rid of it seems like a good idea - in any case. - -3. Some tidies to get rid of compiler warnings: - - . In the match_data structure, match_limit was an unsigned long int, whereas - match_call_count was an int. I've made them both unsigned long ints. - - . In pcretest the fact that a const uschar * doesn't automatically cast to - a void * provoked a warning. - - . Turning on some more compiler warnings threw up some "shadow" variables - and a few more missing casts. - -4. If PCRE was complied with UTF-8 support, but called without the PCRE_UTF8 - option, a class that contained a single character with a value between 128 - and 255 (e.g. /[\xFF]/) caused PCRE to crash. - -5. If PCRE was compiled with UTF-8 support, but called without the PCRE_UTF8 - option, a class that contained several characters, but with at least one - whose value was between 128 and 255 caused PCRE to crash. - - -Version 4.1 12-Mar-03 ---------------------- - -1. Compiling with gcc -pedantic found a couple of places where casts were -needed, and a string in dftables.c that was longer than standard compilers are -required to support. - -2. Compiling with Sun's compiler found a few more places where the code could -be tidied up in order to avoid warnings. - -3. The variables for cross-compiling were called HOST_CC and HOST_CFLAGS; the -first of these names is deprecated in the latest Autoconf in favour of the name -CC_FOR_BUILD, because "host" is typically used to mean the system on which the -compiled code will be run. I can't find a reference for HOST_CFLAGS, but by -analogy I have changed it to CFLAGS_FOR_BUILD. - -4. Added -no-undefined to the linking command in the Makefile, because this is -apparently helpful for Windows. To make it work, also added "-L. -lpcre" to the -linking step for the pcreposix library. - -5. PCRE was failing to diagnose the case of two named groups with the same -name. - -6. A problem with one of PCRE's optimizations was discovered. PCRE remembers a -literal character that is needed in the subject for a match, and scans along to -ensure that it is present before embarking on the full matching process. This -saves time in cases of nested unlimited repeats that are never going to match. -Problem: the scan can take a lot of time if the subject is very long (e.g. -megabytes), thus penalizing straightforward matches. It is now done only if the -amount of subject to be scanned is less than 1000 bytes. - -7. A lesser problem with the same optimization is that it was recording the -first character of an anchored pattern as "needed", thus provoking a search -right along the subject, even when the first match of the pattern was going to -fail. The "needed" character is now not set for anchored patterns, unless it -follows something in the pattern that is of non-fixed length. Thus, it still -fulfils its original purpose of finding quick non-matches in cases of nested -unlimited repeats, but isn't used for simple anchored patterns such as /^abc/. - - -Version 4.0 17-Feb-03 ---------------------- - -1. If a comment in an extended regex that started immediately after a meta-item -extended to the end of string, PCRE compiled incorrect data. This could lead to -all kinds of weird effects. Example: /#/ was bad; /()#/ was bad; /a#/ was not. - -2. Moved to autoconf 2.53 and libtool 1.4.2. - -3. Perl 5.8 no longer needs "use utf8" for doing UTF-8 things. Consequently, -the special perltest8 script is no longer needed - all the tests can be run -from a single perltest script. - -4. From 5.004, Perl has not included the VT character (0x0b) in the set defined -by \s. It has now been removed in PCRE. This means it isn't recognized as -whitespace in /x regexes too, which is the same as Perl. Note that the POSIX -class [:space:] *does* include VT, thereby creating a mess. - -5. Added the class [:blank:] (a GNU extension from Perl 5.8) to match only -space and tab. - -6. Perl 5.005 was a long time ago. It's time to amalgamate the tests that use -its new features into the main test script, reducing the number of scripts. - -7. Perl 5.8 has changed the meaning of patterns like /a(?i)b/. Earlier versions -were backward compatible, and made the (?i) apply to the whole pattern, as if -/i were given. Now it behaves more logically, and applies the option setting -only to what follows. PCRE has been changed to follow suit. However, if it -finds options settings right at the start of the pattern, it extracts them into -the global options, as before. Thus, they show up in the info data. - -8. Added support for the \Q...\E escape sequence. Characters in between are -treated as literals. This is slightly different from Perl in that $ and @ are -also handled as literals inside the quotes. In Perl, they will cause variable -interpolation. Note the following examples: - - Pattern PCRE matches Perl matches - - \Qabc$xyz\E abc$xyz abc followed by the contents of $xyz - \Qabc\$xyz\E abc\$xyz abc\$xyz - \Qabc\E\$\Qxyz\E abc$xyz abc$xyz - -For compatibility with Perl, \Q...\E sequences are recognized inside character -classes as well as outside them. - -9. Re-organized 3 code statements in pcretest to avoid "overflow in -floating-point constant arithmetic" warnings from a Microsoft compiler. Added a -(size_t) cast to one statement in pcretest and one in pcreposix to avoid -signed/unsigned warnings. - -10. SunOS4 doesn't have strtoul(). This was used only for unpicking the -o -option for pcretest, so I've replaced it by a simple function that does just -that job. - -11. pcregrep was ending with code 0 instead of 2 for the commands "pcregrep" or -"pcregrep -". - -12. Added "possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's -Java package. This provides some syntactic sugar for simple cases of what my -documentation calls "once-only subpatterns". A pattern such as x*+ is the same -as (?>x*). In other words, if what is inside (?>...) is just a single repeated -item, you can use this simplified notation. Note that only makes sense with -greedy quantifiers. Consequently, the use of the possessive quantifier forces -greediness, whatever the setting of the PCRE_UNGREEDY option. - -13. A change of greediness default within a pattern was not taking effect at -the current level for patterns like /(b+(?U)a+)/. It did apply to parenthesized -subpatterns that followed. Patterns like /b+(?U)a+/ worked because the option -was abstracted outside. - -14. PCRE now supports the \G assertion. It is true when the current matching -position is at the start point of the match. This differs from \A when the -starting offset is non-zero. Used with the /g option of pcretest (or similar -code), it works in the same way as it does for Perl's /g option. If all -alternatives of a regex begin with \G, the expression is anchored to the start -match position, and the "anchored" flag is set in the compiled expression. - -15. Some bugs concerning the handling of certain option changes within patterns -have been fixed. These applied to options other than (?ims). For example, -"a(?x: b c )d" did not match "XabcdY" but did match "Xa b c dY". It should have -been the other way round. Some of this was related to change 7 above. - -16. PCRE now gives errors for /[.x.]/ and /[=x=]/ as unsupported POSIX -features, as Perl does. Previously, PCRE gave the warnings only for /[[.x.]]/ -and /[[=x=]]/. PCRE now also gives an error for /[:name:]/ because it supports -POSIX classes only within a class (e.g. /[[:alpha:]]/). - -17. Added support for Perl's \C escape. This matches one byte, even in UTF8 -mode. Unlike ".", it always matches newline, whatever the setting of -PCRE_DOTALL. However, PCRE does not permit \C to appear in lookbehind -assertions. Perl allows it, but it doesn't (in general) work because it can't -calculate the length of the lookbehind. At least, that's the case for Perl -5.8.0 - I've been told they are going to document that it doesn't work in -future. - -18. Added an error diagnosis for escapes that PCRE does not support: these are -\L, \l, \N, \P, \p, \U, \u, and \X. - -19. Although correctly diagnosing a missing ']' in a character class, PCRE was -reading past the end of the pattern in cases such as /[abcd/. - -20. PCRE was getting more memory than necessary for patterns with classes that -contained both POSIX named classes and other characters, e.g. /[[:space:]abc/. - -21. Added some code, conditional on #ifdef VPCOMPAT, to make life easier for -compiling PCRE for use with Virtual Pascal. - -22. Small fix to the Makefile to make it work properly if the build is done -outside the source tree. - -23. Added a new extension: a condition to go with recursion. If a conditional -subpattern starts with (?(R) the "true" branch is used if recursion has -happened, whereas the "false" branch is used only at the top level. - -24. When there was a very long string of literal characters (over 255 bytes -without UTF support, over 250 bytes with UTF support), the computation of how -much memory was required could be incorrect, leading to segfaults or other -strange effects. - -25. PCRE was incorrectly assuming anchoring (either to start of subject or to -start of line for a non-DOTALL pattern) when a pattern started with (.*) and -there was a subsequent back reference to those brackets. This meant that, for -example, /(.*)\d+\1/ failed to match "abc123bc". Unfortunately, it isn't -possible to check for precisely this case. All we can do is abandon the -optimization if .* occurs inside capturing brackets when there are any back -references whatsoever. (See below for a better fix that came later.) - -26. The handling of the optimization for finding the first character of a -non-anchored pattern, and for finding a character that is required later in the -match were failing in some cases. This didn't break the matching; it just -failed to optimize when it could. The way this is done has been re-implemented. - -27. Fixed typo in error message for invalid (?R item (it said "(?p"). - -28. Added a new feature that provides some of the functionality that Perl -provides with (?{...}). The facility is termed a "callout". The way it is done -in PCRE is for the caller to provide an optional function, by setting -pcre_callout to its entry point. Like pcre_malloc and pcre_free, this is a -global variable. By default it is unset, which disables all calling out. To get -the function called, the regex must include (?C) at appropriate points. This -is, in fact, equivalent to (?C0), and any number <= 255 may be given with (?C). -This provides a means of identifying different callout points. When PCRE -reaches such a point in the regex, if pcre_callout has been set, the external -function is called. It is provided with data in a structure called -pcre_callout_block, which is defined in pcre.h. If the function returns 0, -matching continues; if it returns a non-zero value, the match at the current -point fails. However, backtracking will occur if possible. [This was changed -later and other features added - see item 49 below.] - -29. pcretest is upgraded to test the callout functionality. It provides a -callout function that displays information. By default, it shows the start of -the match and the current position in the text. There are some new data escapes -to vary what happens: - - \C+ in addition, show current contents of captured substrings - \C- do not supply a callout function - \C!n return 1 when callout number n is reached - \C!n!m return 1 when callout number n is reached for the mth time - -30. If pcregrep was called with the -l option and just a single file name, it -output "<stdin>" if a match was found, instead of the file name. - -31. Improve the efficiency of the POSIX API to PCRE. If the number of capturing -slots is less than POSIX_MALLOC_THRESHOLD, use a block on the stack to pass to -pcre_exec(). This saves a malloc/free per call. The default value of -POSIX_MALLOC_THRESHOLD is 10; it can be changed by --with-posix-malloc-threshold -when configuring. - -32. The default maximum size of a compiled pattern is 64K. There have been a -few cases of people hitting this limit. The code now uses macros to handle the -storing of links as offsets within the compiled pattern. It defaults to 2-byte -links, but this can be changed to 3 or 4 bytes by --with-link-size when -configuring. Tests 2 and 5 work only with 2-byte links because they output -debugging information about compiled patterns. - -33. Internal code re-arrangements: - -(a) Moved the debugging function for printing out a compiled regex into - its own source file (printint.c) and used #include to pull it into - pcretest.c and, when DEBUG is defined, into pcre.c, instead of having two - separate copies. - -(b) Defined the list of op-code names for debugging as a macro in - internal.h so that it is next to the definition of the opcodes. - -(c) Defined a table of op-code lengths for simpler skipping along compiled - code. This is again a macro in internal.h so that it is next to the - definition of the opcodes. - -34. Added support for recursive calls to individual subpatterns, along the -lines of Robin Houston's patch (but implemented somewhat differently). - -35. Further mods to the Makefile to help Win32. Also, added code to pcregrep to -allow it to read and process whole directories in Win32. This code was -contributed by Lionel Fourquaux; it has not been tested by me. - -36. Added support for named subpatterns. The Python syntax (?P<name>...) is -used to name a group. Names consist of alphanumerics and underscores, and must -be unique. Back references use the syntax (?P=name) and recursive calls use -(?P>name) which is a PCRE extension to the Python extension. Groups still have -numbers. The function pcre_fullinfo() can be used after compilation to extract -a name/number map. There are three relevant calls: - - PCRE_INFO_NAMEENTRYSIZE yields the size of each entry in the map - PCRE_INFO_NAMECOUNT yields the number of entries - PCRE_INFO_NAMETABLE yields a pointer to the map. - -The map is a vector of fixed-size entries. The size of each entry depends on -the length of the longest name used. The first two bytes of each entry are the -group number, most significant byte first. There follows the corresponding -name, zero terminated. The names are in alphabetical order. - -37. Make the maximum literal string in the compiled code 250 for the non-UTF-8 -case instead of 255. Making it the same both with and without UTF-8 support -means that the same test output works with both. - -38. There was a case of malloc(0) in the POSIX testing code in pcretest. Avoid -calling malloc() with a zero argument. - -39. Change 25 above had to resort to a heavy-handed test for the .* anchoring -optimization. I've improved things by keeping a bitmap of backreferences with -numbers 1-31 so that if .* occurs inside capturing brackets that are not in -fact referenced, the optimization can be applied. It is unlikely that a -relevant occurrence of .* (i.e. one which might indicate anchoring or forcing -the match to follow \n) will appear inside brackets with a number greater than -31, but if it does, any back reference > 31 suppresses the optimization. - -40. Added a new compile-time option PCRE_NO_AUTO_CAPTURE. This has the effect -of disabling numbered capturing parentheses. Any opening parenthesis that is -not followed by ? behaves as if it were followed by ?: but named parentheses -can still be used for capturing (and they will acquire numbers in the usual -way). - -41. Redesigned the return codes from the match() function into yes/no/error so -that errors can be passed back from deep inside the nested calls. A malloc -failure while inside a recursive subpattern call now causes the -PCRE_ERROR_NOMEMORY return instead of quietly going wrong. - -42. It is now possible to set a limit on the number of times the match() -function is called in a call to pcre_exec(). This facility makes it possible to -limit the amount of recursion and backtracking, though not in a directly -obvious way, because the match() function is used in a number of different -circumstances. The count starts from zero for each position in the subject -string (for non-anchored patterns). The default limit is, for compatibility, a -large number, namely 10 000 000. You can change this in two ways: - -(a) When configuring PCRE before making, you can use --with-match-limit=n - to set a default value for the compiled library. - -(b) For each call to pcre_exec(), you can pass a pcre_extra block in which - a different value is set. See 45 below. - -If the limit is exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. - -43. Added a new function pcre_config(int, void *) to enable run-time extraction -of things that can be changed at compile time. The first argument specifies -what is wanted and the second points to where the information is to be placed. -The current list of available information is: - - PCRE_CONFIG_UTF8 - -The output is an integer that is set to one if UTF-8 support is available; -otherwise it is set to zero. - - PCRE_CONFIG_NEWLINE - -The output is an integer that it set to the value of the code that is used for -newline. It is either LF (10) or CR (13). - - PCRE_CONFIG_LINK_SIZE - -The output is an integer that contains the number of bytes used for internal -linkage in compiled expressions. The value is 2, 3, or 4. See item 32 above. - - PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - -The output is an integer that contains the threshold above which the POSIX -interface uses malloc() for output vectors. See item 31 above. - - PCRE_CONFIG_MATCH_LIMIT - -The output is an unsigned integer that contains the default limit of the number -of match() calls in a pcre_exec() execution. See 42 above. - -44. pcretest has been upgraded by the addition of the -C option. This causes it -to extract all the available output from the new pcre_config() function, and to -output it. The program then exits immediately. - -45. A need has arisen to pass over additional data with calls to pcre_exec() in -order to support additional features. One way would have been to define -pcre_exec2() (for example) with extra arguments, but this would not have been -extensible, and would also have required all calls to the original function to -be mapped to the new one. Instead, I have chosen to extend the mechanism that -is used for passing in "extra" data from pcre_study(). - -The pcre_extra structure is now exposed and defined in pcre.h. It currently -contains the following fields: - - flags a bitmap indicating which of the following fields are set - study_data opaque data from pcre_study() - match_limit a way of specifying a limit on match() calls for a specific - call to pcre_exec() - callout_data data for callouts (see 49 below) - -The flag bits are also defined in pcre.h, and are - - PCRE_EXTRA_STUDY_DATA - PCRE_EXTRA_MATCH_LIMIT - PCRE_EXTRA_CALLOUT_DATA - -The pcre_study() function now returns one of these new pcre_extra blocks, with -the actual study data pointed to by the study_data field, and the -PCRE_EXTRA_STUDY_DATA flag set. This can be passed directly to pcre_exec() as -before. That is, this change is entirely upwards-compatible and requires no -change to existing code. - -If you want to pass in additional data to pcre_exec(), you can either place it -in a pcre_extra block provided by pcre_study(), or create your own pcre_extra -block. - -46. pcretest has been extended to test the PCRE_EXTRA_MATCH_LIMIT feature. If a -data string contains the escape sequence \M, pcretest calls pcre_exec() several -times with different match limits, until it finds the minimum value needed for -pcre_exec() to complete. The value is then output. This can be instructive; for -most simple matches the number is quite small, but for pathological cases it -gets very large very quickly. - -47. There's a new option for pcre_fullinfo() called PCRE_INFO_STUDYSIZE. It -returns the size of the data block pointed to by the study_data field in a -pcre_extra block, that is, the value that was passed as the argument to -pcre_malloc() when PCRE was getting memory in which to place the information -created by pcre_study(). The fourth argument should point to a size_t variable. -pcretest has been extended so that this information is shown after a successful -pcre_study() call when information about the compiled regex is being displayed. - -48. Cosmetic change to Makefile: there's no need to have / after $(DESTDIR) -because what follows is always an absolute path. (Later: it turns out that this -is more than cosmetic for MinGW, because it doesn't like empty path -components.) - -49. Some changes have been made to the callout feature (see 28 above): - -(i) A callout function now has three choices for what it returns: - - 0 => success, carry on matching - > 0 => failure at this point, but backtrack if possible - < 0 => serious error, return this value from pcre_exec() - - Negative values should normally be chosen from the set of PCRE_ERROR_xxx - values. In particular, returning PCRE_ERROR_NOMATCH forces a standard - "match failed" error. The error number PCRE_ERROR_CALLOUT is reserved for - use by callout functions. It will never be used by PCRE itself. - -(ii) The pcre_extra structure (see 45 above) has a void * field called - callout_data, with corresponding flag bit PCRE_EXTRA_CALLOUT_DATA. The - pcre_callout_block structure has a field of the same name. The contents of - the field passed in the pcre_extra structure are passed to the callout - function in the corresponding field in the callout block. This makes it - easier to use the same callout-containing regex from multiple threads. For - testing, the pcretest program has a new data escape - - \C*n pass the number n (may be negative) as callout_data - - If the callout function in pcretest receives a non-zero value as - callout_data, it returns that value. - -50. Makefile wasn't handling CFLAGS properly when compiling dftables. Also, -there were some redundant $(CFLAGS) in commands that are now specified as -$(LINK), which already includes $(CFLAGS). - -51. Extensions to UTF-8 support are listed below. These all apply when (a) PCRE -has been compiled with UTF-8 support *and* pcre_compile() has been compiled -with the PCRE_UTF8 flag. Patterns that are compiled without that flag assume -one-byte characters throughout. Note that case-insensitive matching applies -only to characters whose values are less than 256. PCRE doesn't support the -notion of cases for higher-valued characters. - -(i) A character class whose characters are all within 0-255 is handled as - a bit map, and the map is inverted for negative classes. Previously, a - character > 255 always failed to match such a class; however it should - match if the class was a negative one (e.g. [^ab]). This has been fixed. - -(ii) A negated character class with a single character < 255 is coded as - "not this character" (OP_NOT). This wasn't working properly when the test - character was multibyte, either singly or repeated. - -(iii) Repeats of multibyte characters are now handled correctly in UTF-8 - mode, for example: \x{100}{2,3}. - -(iv) The character escapes \b, \B, \d, \D, \s, \S, \w, and \W (either - singly or repeated) now correctly test multibyte characters. However, - PCRE doesn't recognize any characters with values greater than 255 as - digits, spaces, or word characters. Such characters always match \D, \S, - and \W, and never match \d, \s, or \w. - -(v) Classes may now contain characters and character ranges with values - greater than 255. For example: [ab\x{100}-\x{400}]. - -(vi) pcregrep now has a --utf-8 option (synonym -u) which makes it call - PCRE in UTF-8 mode. - -52. The info request value PCRE_INFO_FIRSTCHAR has been renamed -PCRE_INFO_FIRSTBYTE because it is a byte value. However, the old name is -retained for backwards compatibility. (Note that LASTLITERAL is also a byte -value.) - -53. The single man page has become too large. I have therefore split it up into -a number of separate man pages. These also give rise to individual HTML pages; -these are now put in a separate directory, and there is an index.html page that -lists them all. Some hyperlinking between the pages has been installed. - -54. Added convenience functions for handling named capturing parentheses. - -55. Unknown escapes inside character classes (e.g. [\M]) and escapes that -aren't interpreted therein (e.g. [\C]) are literals in Perl. This is now also -true in PCRE, except when the PCRE_EXTENDED option is set, in which case they -are faulted. - -56. Introduced HOST_CC and HOST_CFLAGS which can be set in the environment when -calling configure. These values are used when compiling the dftables.c program -which is run to generate the source of the default character tables. They -default to the values of CC and CFLAGS. If you are cross-compiling PCRE, -you will need to set these values. - -57. Updated the building process for Windows DLL, as provided by Fred Cox. - - -Version 3.9 02-Jan-02 ---------------------- - -1. A bit of extraneous text had somehow crept into the pcregrep documentation. - -2. If --disable-static was given, the building process failed when trying to -build pcretest and pcregrep. (For some reason it was using libtool to compile -them, which is not right, as they aren't part of the library.) - - -Version 3.8 18-Dec-01 ---------------------- - -1. The experimental UTF-8 code was completely screwed up. It was packing the -bytes in the wrong order. How dumb can you get? - - -Version 3.7 29-Oct-01 ---------------------- - -1. In updating pcretest to check change 1 of version 3.6, I screwed up. -This caused pcretest, when used on the test data, to segfault. Unfortunately, -this didn't happen under Solaris 8, where I normally test things. - -2. The Makefile had to be changed to make it work on BSD systems, where 'make' -doesn't seem to recognize that ./xxx and xxx are the same file. (This entry -isn't in ChangeLog distributed with 3.7 because I forgot when I hastily made -this fix an hour or so after the initial 3.7 release.) - - -Version 3.6 23-Oct-01 ---------------------- - -1. Crashed with /(sens|respons)e and \1ibility/ and "sense and sensibility" if -offsets passed as NULL with zero offset count. - -2. The config.guess and config.sub files had not been updated when I moved to -the latest autoconf. - - -Version 3.5 15-Aug-01 ---------------------- - -1. Added some missing #if !defined NOPOSIX conditionals in pcretest.c that -had been forgotten. - -2. By using declared but undefined structures, we can avoid using "void" -definitions in pcre.h while keeping the internal definitions of the structures -private. - -3. The distribution is now built using autoconf 2.50 and libtool 1.4. From a -user point of view, this means that both static and shared libraries are built -by default, but this can be individually controlled. More of the work of -handling this static/shared cases is now inside libtool instead of PCRE's make -file. - -4. The pcretest utility is now installed along with pcregrep because it is -useful for users (to test regexs) and by doing this, it automatically gets -relinked by libtool. The documentation has been turned into a man page, so -there are now .1, .txt, and .html versions in /doc. - -5. Upgrades to pcregrep: - (i) Added long-form option names like gnu grep. - (ii) Added --help to list all options with an explanatory phrase. - (iii) Added -r, --recursive to recurse into sub-directories. - (iv) Added -f, --file to read patterns from a file. - -6. pcre_exec() was referring to its "code" argument before testing that -argument for NULL (and giving an error if it was NULL). - -7. Upgraded Makefile.in to allow for compiling in a different directory from -the source directory. - -8. Tiny buglet in pcretest: when pcre_fullinfo() was called to retrieve the -options bits, the pointer it was passed was to an int instead of to an unsigned -long int. This mattered only on 64-bit systems. - -9. Fixed typo (3.4/1) in pcre.h again. Sigh. I had changed pcre.h (which is -generated) instead of pcre.in, which it its source. Also made the same change -in several of the .c files. - -10. A new release of gcc defines printf() as a macro, which broke pcretest -because it had an ifdef in the middle of a string argument for printf(). Fixed -by using separate calls to printf(). - -11. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure -script, to force use of CR or LF instead of \n in the source. On non-Unix -systems, the value can be set in config.h. - -12. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an -absolute limit. Changed the text of the error message to make this clear, and -likewise updated the man page. - -13. The limit of 99 on the number of capturing subpatterns has been removed. -The new limit is 65535, which I hope will not be a "real" limit. - - -Version 3.4 22-Aug-00 ---------------------- - -1. Fixed typo in pcre.h: unsigned const char * changed to const unsigned char *. - -2. Diagnose condition (?(0) as an error instead of crashing on matching. - - -Version 3.3 01-Aug-00 ---------------------- - -1. If an octal character was given, but the value was greater than \377, it -was not getting masked to the least significant bits, as documented. This could -lead to crashes in some systems. - -2. Perl 5.6 (if not earlier versions) accepts classes like [a-\d] and treats -the hyphen as a literal. PCRE used to give an error; it now behaves like Perl. - -3. Added the functions pcre_free_substring() and pcre_free_substring_list(). -These just pass their arguments on to (pcre_free)(), but they are provided -because some uses of PCRE bind it to non-C systems that can call its functions, -but cannot call free() or pcre_free() directly. - -4. Add "make test" as a synonym for "make check". Corrected some comments in -the Makefile. - -5. Add $(DESTDIR)/ in front of all the paths in the "install" target in the -Makefile. - -6. Changed the name of pgrep to pcregrep, because Solaris has introduced a -command called pgrep for grepping around the active processes. - -7. Added the beginnings of support for UTF-8 character strings. - -8. Arranged for the Makefile to pass over the settings of CC, CFLAGS, and -RANLIB to ./ltconfig so that they are used by libtool. I think these are all -the relevant ones. (AR is not passed because ./ltconfig does its own figuring -out for the ar command.) - - -Version 3.2 12-May-00 ---------------------- - -This is purely a bug fixing release. - -1. If the pattern /((Z)+|A)*/ was matched agained ZABCDEFG it matched Z instead -of ZA. This was just one example of several cases that could provoke this bug, -which was introduced by change 9 of version 2.00. The code for breaking -infinite loops after an iteration that matches an empty string was't working -correctly. - -2. The pcretest program was not imitating Perl correctly for the pattern /a*/g -when matched against abbab (for example). After matching an empty string, it -wasn't forcing anchoring when setting PCRE_NOTEMPTY for the next attempt; this -caused it to match further down the string than it should. - -3. The code contained an inclusion of sys/types.h. It isn't clear why this -was there because it doesn't seem to be needed, and it causes trouble on some -systems, as it is not a Standard C header. It has been removed. - -4. Made 4 silly changes to the source to avoid stupid compiler warnings that -were reported on the Macintosh. The changes were from - - while ((c = *(++ptr)) != 0 && c != '\n'); -to - while ((c = *(++ptr)) != 0 && c != '\n') ; - -Totally extraordinary, but if that's what it takes... - -5. PCRE is being used in one environment where neither memmove() nor bcopy() is -available. Added HAVE_BCOPY and an autoconf test for it; if neither -HAVE_MEMMOVE nor HAVE_BCOPY is set, use a built-in emulation function which -assumes the way PCRE uses memmove() (always moving upwards). - -6. PCRE is being used in one environment where strchr() is not available. There -was only one use in pcre.c, and writing it out to avoid strchr() probably gives -faster code anyway. - - -Version 3.1 09-Feb-00 ---------------------- - -The only change in this release is the fixing of some bugs in Makefile.in for -the "install" target: - -(1) It was failing to install pcreposix.h. - -(2) It was overwriting the pcre.3 man page with the pcreposix.3 man page. - - -Version 3.0 01-Feb-00 ---------------------- - -1. Add support for the /+ modifier to perltest (to output $` like it does in -pcretest). - -2. Add support for the /g modifier to perltest. - -3. Fix pcretest so that it behaves even more like Perl for /g when the pattern -matches null strings. - -4. Fix perltest so that it doesn't do unwanted things when fed an empty -pattern. Perl treats empty patterns specially - it reuses the most recent -pattern, which is not what we want. Replace // by /(?#)/ in order to avoid this -effect. - -5. The POSIX interface was broken in that it was just handing over the POSIX -captured string vector to pcre_exec(), but (since release 2.00) PCRE has -required a bigger vector, with some working space on the end. This means that -the POSIX wrapper now has to get and free some memory, and copy the results. - -6. Added some simple autoconf support, placing the test data and the -documentation in separate directories, re-organizing some of the -information files, and making it build pcre-config (a GNU standard). Also added -libtool support for building PCRE as a shared library, which is now the -default. - -7. Got rid of the leading zero in the definition of PCRE_MINOR because 08 and -09 are not valid octal constants. Single digits will be used for minor values -less than 10. - -8. Defined REG_EXTENDED and REG_NOSUB as zero in the POSIX header, so that -existing programs that set these in the POSIX interface can use PCRE without -modification. - -9. Added a new function, pcre_fullinfo() with an extensible interface. It can -return all that pcre_info() returns, plus additional data. The pcre_info() -function is retained for compatibility, but is considered to be obsolete. - -10. Added experimental recursion feature (?R) to handle one common case that -Perl 5.6 will be able to do with (?p{...}). - -11. Added support for POSIX character classes like [:alpha:], which Perl is -adopting. - - -Version 2.08 31-Aug-99 ----------------------- - -1. When startoffset was not zero and the pattern began with ".*", PCRE was not -trying to match at the startoffset position, but instead was moving forward to -the next newline as if a previous match had failed. - -2. pcretest was not making use of PCRE_NOTEMPTY when repeating for /g and /G, -and could get into a loop if a null string was matched other than at the start -of the subject. - -3. Added definitions of PCRE_MAJOR and PCRE_MINOR to pcre.h so the version can -be distinguished at compile time, and for completeness also added PCRE_DATE. - -5. Added Paul Sokolovsky's minor changes to make it easy to compile a Win32 DLL -in GnuWin32 environments. - - -Version 2.07 29-Jul-99 ----------------------- - -1. The documentation is now supplied in plain text form and HTML as well as in -the form of man page sources. - -2. C++ compilers don't like assigning (void *) values to other pointer types. -In particular this affects malloc(). Although there is no problem in Standard -C, I've put in casts to keep C++ compilers happy. - -3. Typo on pcretest.c; a cast of (unsigned char *) in the POSIX regexec() call -should be (const char *). - -4. If NOPOSIX is defined, pcretest.c compiles without POSIX support. This may -be useful for non-Unix systems who don't want to bother with the POSIX stuff. -However, I haven't made this a standard facility. The documentation doesn't -mention it, and the Makefile doesn't support it. - -5. The Makefile now contains an "install" target, with editable destinations at -the top of the file. The pcretest program is not installed. - -6. pgrep -V now gives the PCRE version number and date. - -7. Fixed bug: a zero repetition after a literal string (e.g. /abcde{0}/) was -causing the entire string to be ignored, instead of just the last character. - -8. If a pattern like /"([^\\"]+|\\.)*"/ is applied in the normal way to a -non-matching string, it can take a very, very long time, even for strings of -quite modest length, because of the nested recursion. PCRE now does better in -some of these cases. It does this by remembering the last required literal -character in the pattern, and pre-searching the subject to ensure it is present -before running the real match. In other words, it applies a heuristic to detect -some types of certain failure quickly, and in the above example, if presented -with a string that has no trailing " it gives "no match" very quickly. - -9. A new runtime option PCRE_NOTEMPTY causes null string matches to be ignored; -other alternatives are tried instead. - - -Version 2.06 09-Jun-99 ----------------------- - -1. Change pcretest's output for amount of store used to show just the code -space, because the remainder (the data block) varies in size between 32-bit and -64-bit systems. - -2. Added an extra argument to pcre_exec() to supply an offset in the subject to -start matching at. This allows lookbehinds to work when searching for multiple -occurrences in a string. - -3. Added additional options to pcretest for testing multiple occurrences: - - /+ outputs the rest of the string that follows a match - /g loops for multiple occurrences, using the new startoffset argument - /G loops for multiple occurrences by passing an incremented pointer - -4. PCRE wasn't doing the "first character" optimization for patterns starting -with \b or \B, though it was doing it for other lookbehind assertions. That is, -it wasn't noticing that a match for a pattern such as /\bxyz/ has to start with -the letter 'x'. On long subject strings, this gives a significant speed-up. - - -Version 2.05 21-Apr-99 ----------------------- - -1. Changed the type of magic_number from int to long int so that it works -properly on 16-bit systems. - -2. Fixed a bug which caused patterns starting with .* not to work correctly -when the subject string contained newline characters. PCRE was assuming -anchoring for such patterns in all cases, which is not correct because .* will -not pass a newline unless PCRE_DOTALL is set. It now assumes anchoring only if -DOTALL is set at top level; otherwise it knows that patterns starting with .* -must be retried after every newline in the subject. - - -Version 2.04 18-Feb-99 ----------------------- - -1. For parenthesized subpatterns with repeats whose minimum was zero, the -computation of the store needed to hold the pattern was incorrect (too large). -If such patterns were nested a few deep, this could multiply and become a real -problem. - -2. Added /M option to pcretest to show the memory requirement of a specific -pattern. Made -m a synonym of -s (which does this globally) for compatibility. - -3. Subpatterns of the form (regex){n,m} (i.e. limited maximum) were being -compiled in such a way that the backtracking after subsequent failure was -pessimal. Something like (a){0,3} was compiled as (a)?(a)?(a)? instead of -((a)((a)(a)?)?)? with disastrous performance if the maximum was of any size. - - -Version 2.03 02-Feb-99 ----------------------- - -1. Fixed typo and small mistake in man page. - -2. Added 4th condition (GPL supersedes if conflict) and created separate -LICENCE file containing the conditions. - -3. Updated pcretest so that patterns such as /abc\/def/ work like they do in -Perl, that is the internal \ allows the delimiter to be included in the -pattern. Locked out the use of \ as a delimiter. If \ immediately follows -the final delimiter, add \ to the end of the pattern (to test the error). - -4. Added the convenience functions for extracting substrings after a successful -match. Updated pcretest to make it able to test these functions. - - -Version 2.02 14-Jan-99 ----------------------- - -1. Initialized the working variables associated with each extraction so that -their saving and restoring doesn't refer to uninitialized store. - -2. Put dummy code into study.c in order to trick the optimizer of the IBM C -compiler for OS/2 into generating correct code. Apparently IBM isn't going to -fix the problem. - -3. Pcretest: the timing code wasn't using LOOPREPEAT for timing execution -calls, and wasn't printing the correct value for compiling calls. Increased the -default value of LOOPREPEAT, and the number of significant figures in the -times. - -4. Changed "/bin/rm" in the Makefile to "-rm" so it works on Windows NT. - -5. Renamed "deftables" as "dftables" to get it down to 8 characters, to avoid -a building problem on Windows NT with a FAT file system. - - -Version 2.01 21-Oct-98 ----------------------- - -1. Changed the API for pcre_compile() to allow for the provision of a pointer -to character tables built by pcre_maketables() in the current locale. If NULL -is passed, the default tables are used. - - -Version 2.00 24-Sep-98 ----------------------- - -1. Since the (>?) facility is in Perl 5.005, don't require PCRE_EXTRA to enable -it any more. - -2. Allow quantification of (?>) groups, and make it work correctly. - -3. The first character computation wasn't working for (?>) groups. - -4. Correct the implementation of \Z (it is permitted to match on the \n at the -end of the subject) and add 5.005's \z, which really does match only at the -very end of the subject. - -5. Remove the \X "cut" facility; Perl doesn't have it, and (?> is neater. - -6. Remove the ability to specify CASELESS, MULTILINE, DOTALL, and -DOLLAR_END_ONLY at runtime, to make it possible to implement the Perl 5.005 -localized options. All options to pcre_study() were also removed. - -7. Add other new features from 5.005: - - $(?<= positive lookbehind - $(?<! negative lookbehind - (?imsx-imsx) added the unsetting capability - such a setting is global if at outer level; local otherwise - (?imsx-imsx:) non-capturing groups with option setting - (?(cond)re|re) conditional pattern matching - - A backreference to itself in a repeated group matches the previous - captured string. - -8. General tidying up of studying (both automatic and via "study") -consequential on the addition of new assertions. - -9. As in 5.005, unlimited repeated groups that could match an empty substring -are no longer faulted at compile time. Instead, the loop is forcibly broken at -runtime if any iteration does actually match an empty substring. - -10. Include the RunTest script in the distribution. - -11. Added tests from the Perl 5.005_02 distribution. This showed up a few -discrepancies, some of which were old and were also with respect to 5.004. They -have now been fixed. - - -Version 1.09 28-Apr-98 ----------------------- - -1. A negated single character class followed by a quantifier with a minimum -value of one (e.g. [^x]{1,6} ) was not compiled correctly. This could lead to -program crashes, or just wrong answers. This did not apply to negated classes -containing more than one character, or to minima other than one. - - -Version 1.08 27-Mar-98 ----------------------- - -1. Add PCRE_UNGREEDY to invert the greediness of quantifiers. - -2. Add (?U) and (?X) to set PCRE_UNGREEDY and PCRE_EXTRA respectively. The -latter must appear before anything that relies on it in the pattern. - - -Version 1.07 16-Feb-98 ----------------------- - -1. A pattern such as /((a)*)*/ was not being diagnosed as in error (unlimited -repeat of a potentially empty string). - - -Version 1.06 23-Jan-98 ----------------------- - -1. Added Markus Oberhumer's little patches for C++. - -2. Literal strings longer than 255 characters were broken. - - -Version 1.05 23-Dec-97 ----------------------- - -1. Negated character classes containing more than one character were failing if -PCRE_CASELESS was set at run time. - - -Version 1.04 19-Dec-97 ----------------------- - -1. Corrected the man page, where some "const" qualifiers had been omitted. - -2. Made debugging output print "{0,xxx}" instead of just "{,xxx}" to agree with -input syntax. - -3. Fixed memory leak which occurred when a regex with back references was -matched with an offsets vector that wasn't big enough. The temporary memory -that is used in this case wasn't being freed if the match failed. - -4. Tidied pcretest to ensure it frees memory that it gets. - -5. Temporary memory was being obtained in the case where the passed offsets -vector was exactly big enough. - -6. Corrected definition of offsetof() from change 5 below. - -7. I had screwed up change 6 below and broken the rules for the use of -setjmp(). Now fixed. - - -Version 1.03 18-Dec-97 ----------------------- - -1. A erroneous regex with a missing opening parenthesis was correctly -diagnosed, but PCRE attempted to access brastack[-1], which could cause crashes -on some systems. - -2. Replaced offsetof(real_pcre, code) by offsetof(real_pcre, code[0]) because -it was reported that one broken compiler failed on the former because "code" is -also an independent variable. - -3. The erroneous regex a[]b caused an array overrun reference. - -4. A regex ending with a one-character negative class (e.g. /[^k]$/) did not -fail on data ending with that character. (It was going on too far, and checking -the next character, typically a binary zero.) This was specific to the -optimized code for single-character negative classes. - -5. Added a contributed patch from the TIN world which does the following: - - + Add an undef for memmove, in case the the system defines a macro for it. - - + Add a definition of offsetof(), in case there isn't one. (I don't know - the reason behind this - offsetof() is part of the ANSI standard - but - it does no harm). - - + Reduce the ifdef's in pcre.c using macro DPRINTF, thereby eliminating - most of the places where whitespace preceded '#'. I have given up and - allowed the remaining 2 cases to be at the margin. - - + Rename some variables in pcre to eliminate shadowing. This seems very - pedantic, but does no harm, of course. - -6. Moved the call to setjmp() into its own function, to get rid of warnings -from gcc -Wall, and avoided calling it at all unless PCRE_EXTRA is used. - -7. Constructs such as \d{8,} were compiling into the equivalent of -\d{8}\d{0,65527} instead of \d{8}\d* which didn't make much difference to the -outcome, but in this particular case used more store than had been allocated, -which caused the bug to be discovered because it threw up an internal error. - -8. The debugging code in both pcre and pcretest for outputting the compiled -form of a regex was going wrong in the case of back references followed by -curly-bracketed repeats. - - -Version 1.02 12-Dec-97 ----------------------- - -1. Typos in pcre.3 and comments in the source fixed. - -2. Applied a contributed patch to get rid of places where it used to remove -'const' from variables, and fixed some signed/unsigned and uninitialized -variable warnings. - -3. Added the "runtest" target to Makefile. - -4. Set default compiler flag to -O2 rather than just -O. - - -Version 1.01 19-Nov-97 ----------------------- - -1. PCRE was failing to diagnose unlimited repeat of empty string for patterns -like /([ab]*)*/, that is, for classes with more than one character in them. - -2. Likewise, it wasn't diagnosing patterns with "once-only" subpatterns, such -as /((?>a*))*/ (a PCRE_EXTRA facility). - - -Version 1.00 18-Nov-97 ----------------------- - -1. Added compile-time macros to support systems such as SunOS4 which don't have -memmove() or strerror() but have other things that can be used instead. - -2. Arranged that "make clean" removes the executables. - - -Version 0.99 27-Oct-97 ----------------------- - -1. Fixed bug in code for optimizing classes with only one character. It was -initializing a 32-byte map regardless, which could cause it to run off the end -of the memory it had got. - -2. Added, conditional on PCRE_EXTRA, the proposed (?>REGEX) construction. - - -Version 0.98 22-Oct-97 ----------------------- - -1. Fixed bug in code for handling temporary memory usage when there are more -back references than supplied space in the ovector. This could cause segfaults. - - -Version 0.97 21-Oct-97 ----------------------- - -1. Added the \X "cut" facility, conditional on PCRE_EXTRA. - -2. Optimized negated single characters not to use a bit map. - -3. Brought error texts together as macro definitions; clarified some of them; -fixed one that was wrong - it said "range out of order" when it meant "invalid -escape sequence". - -4. Changed some char * arguments to const char *. - -5. Added PCRE_NOTBOL and PCRE_NOTEOL (from POSIX). - -6. Added the POSIX-style API wrapper in pcreposix.a and testing facilities in -pcretest. - - -Version 0.96 16-Oct-97 ----------------------- - -1. Added a simple "pgrep" utility to the distribution. - -2. Fixed an incompatibility with Perl: "{" is now treated as a normal character -unless it appears in one of the precise forms "{ddd}", "{ddd,}", or "{ddd,ddd}" -where "ddd" means "one or more decimal digits". - -3. Fixed serious bug. If a pattern had a back reference, but the call to -pcre_exec() didn't supply a large enough ovector to record the related -identifying subpattern, the match always failed. PCRE now remembers the number -of the largest back reference, and gets some temporary memory in which to save -the offsets during matching if necessary, in order to ensure that -backreferences always work. - -4. Increased the compatibility with Perl in a number of ways: - - (a) . no longer matches \n by default; an option PCRE_DOTALL is provided - to request this handling. The option can be set at compile or exec time. - - (b) $ matches before a terminating newline by default; an option - PCRE_DOLLAR_ENDONLY is provided to override this (but not in multiline - mode). The option can be set at compile or exec time. - - (c) The handling of \ followed by a digit other than 0 is now supposed to be - the same as Perl's. If the decimal number it represents is less than 10 - or there aren't that many previous left capturing parentheses, an octal - escape is read. Inside a character class, it's always an octal escape, - even if it is a single digit. - - (d) An escaped but undefined alphabetic character is taken as a literal, - unless PCRE_EXTRA is set. Currently this just reserves the remaining - escapes. - - (e) {0} is now permitted. (The previous item is removed from the compiled - pattern). - -5. Changed all the names of code files so that the basic parts are no longer -than 10 characters, and abolished the teeny "globals.c" file. - -6. Changed the handling of character classes; they are now done with a 32-byte -bit map always. - -7. Added the -d and /D options to pcretest to make it possible to look at the -internals of compilation without having to recompile pcre. - - -Version 0.95 23-Sep-97 ----------------------- - -1. Fixed bug in pre-pass concerning escaped "normal" characters such as \x5c or -\x20 at the start of a run of normal characters. These were being treated as -real characters, instead of the source characters being re-checked. - - -Version 0.94 18-Sep-97 ----------------------- - -1. The functions are now thread-safe, with the caveat that the global variables -containing pointers to malloc() and free() or alternative functions are the -same for all threads. - -2. Get pcre_study() to generate a bitmap of initial characters for non- -anchored patterns when this is possible, and use it if passed to pcre_exec(). - - -Version 0.93 15-Sep-97 ----------------------- - -1. /(b)|(:+)/ was computing an incorrect first character. - -2. Add pcre_study() to the API and the passing of pcre_extra to pcre_exec(), -but not actually doing anything yet. - -3. Treat "-" characters in classes that cannot be part of ranges as literals, -as Perl does (e.g. [-az] or [az-]). - -4. Set the anchored flag if a branch starts with .* or .*? because that tests -all possible positions. - -5. Split up into different modules to avoid including unneeded functions in a -compiled binary. However, compile and exec are still in one module. The "study" -function is split off. - -6. The character tables are now in a separate module whose source is generated -by an auxiliary program - but can then be edited by hand if required. There are -now no calls to isalnum(), isspace(), isdigit(), isxdigit(), tolower() or -toupper() in the code. - -7. Turn the malloc/free funtions variables into pcre_malloc and pcre_free and -make them global. Abolish the function for setting them, as the caller can now -set them directly. - - -Version 0.92 11-Sep-97 ----------------------- - -1. A repeat with a fixed maximum and a minimum of 1 for an ordinary character -(e.g. /a{1,3}/) was broken (I mis-optimized it). - -2. Caseless matching was not working in character classes if the characters in -the pattern were in upper case. - -3. Make ranges like [W-c] work in the same way as Perl for caseless matching. - -4. Make PCRE_ANCHORED public and accept as a compile option. - -5. Add an options word to pcre_exec() and accept PCRE_ANCHORED and -PCRE_CASELESS at run time. Add escapes \A and \I to pcretest to cause it to -pass them. - -6. Give an error if bad option bits passed at compile or run time. - -7. Add PCRE_MULTILINE at compile and exec time, and (?m) as well. Add \M to -pcretest to cause it to pass that flag. - -8. Add pcre_info(), to get the number of identifying subpatterns, the stored -options, and the first character, if set. - -9. Recognize C+ or C{n,m} where n >= 1 as providing a fixed starting character. - - -Version 0.91 10-Sep-97 ----------------------- - -1. PCRE was failing to diagnose unlimited repeats of subpatterns that could -match the empty string as in /(a*)*/. It was looping and ultimately crashing. - -2. PCRE was looping on encountering an indefinitely repeated back reference to -a subpattern that had matched an empty string, e.g. /(a|)\1*/. It now does what -Perl does - treats the match as successful. - -**** diff --git a/external-libs/pcre/INSTALL b/external-libs/pcre/INSTALL deleted file mode 100644 index 08802812..00000000 --- a/external-libs/pcre/INSTALL +++ /dev/null @@ -1,185 +0,0 @@ -Basic Installation -================== - - These are generic installation instructions that apply to systems that -can run the `configure' shell script - Unix systems and any that imitate -it. They are not specific to PCRE. There are PCRE-specific instructions -for non-Unix systems in the file NON-UNIX-USE. - - The `configure' shell script attempts to guess correct values for -various system-dependent variables used during compilation. It uses -those values to create a `Makefile' in each directory of the package. -It may also create one or more `.h' files containing system-dependent -definitions. Finally, it creates a shell script `config.status' that -you can run in the future to recreate the current configuration, a file -`config.cache' that saves the results of its tests to speed up -reconfiguring, and a file `config.log' containing compiler output -(useful mainly for debugging `configure'). - - If you need to do unusual things to compile the package, please try -to figure out how `configure' could check whether to do them, and mail -diffs or instructions to the address given in the `README' so they can -be considered for the next release. If at some point `config.cache' -contains results you don't want to keep, you may remove or edit it. - - The file `configure.in' is used to create `configure' by a program -called `autoconf'. You only need `configure.in' if you want to change -it or regenerate `configure' using a newer version of `autoconf'. - -The simplest way to compile this package is: - - 1. `cd' to the directory containing the package's source code and type - `./configure' to configure the package for your system. If you're - using `csh' on an old version of System V, you might need to type - `sh ./configure' instead to prevent `csh' from trying to execute - `configure' itself. - - Running `configure' takes awhile. While running, it prints some - messages telling which features it is checking for. - - 2. Type `make' to compile the package. - - 3. Optionally, type `make check' to run any self-tests that come with - the package. - - 4. Type `make install' to install the programs and any data files and - documentation. - - 5. You can remove the program binaries and object files from the - source code directory by typing `make clean'. To also remove the - files that `configure' created (so you can compile the package for - a different kind of computer), type `make distclean'. There is - also a `make maintainer-clean' target, but that is intended mainly - for the package's developers. If you use it, you may have to get - all sorts of other programs in order to regenerate files that came - with the distribution. - -Compilers and Options -===================== - - Some systems require unusual options for compilation or linking that -the `configure' script does not know about. You can give `configure' -initial values for variables by setting them in the environment. Using -a Bourne-compatible shell, you can do that on the command line like -this: - CC=c89 CFLAGS=-O2 LIBS=-lposix ./configure - -Or on systems that have the `env' program, you can do it like this: - env CPPFLAGS=-I/usr/local/include LDFLAGS=-s ./configure - -Compiling For Multiple Architectures -==================================== - - You can compile the package for more than one kind of computer at the -same time, by placing the object files for each architecture in their -own directory. To do this, you must use a version of `make' that -supports the `VPATH' variable, such as GNU `make'. `cd' to the -directory where you want the object files and executables to go and run -the `configure' script. `configure' automatically checks for the -source code in the directory that `configure' is in and in `..'. - - If you have to use a `make' that does not supports the `VPATH' -variable, you have to compile the package for one architecture at a time -in the source code directory. After you have installed the package for -one architecture, use `make distclean' before reconfiguring for another -architecture. - -Installation Names -================== - - By default, `make install' will install the package's files in -`/usr/local/bin', `/usr/local/man', etc. You can specify an -installation prefix other than `/usr/local' by giving `configure' the -option `--prefix=PATH'. - - You can specify separate installation prefixes for -architecture-specific files and architecture-independent files. If you -give `configure' the option `--exec-prefix=PATH', the package will use -PATH as the prefix for installing programs and libraries. -Documentation and other data files will still use the regular prefix. - - In addition, if you use an unusual directory layout you can give -options like `--bindir=PATH' to specify different values for particular -kinds of files. Run `configure --help' for a list of the directories -you can set and what kinds of files go in them. - - If the package supports it, you can cause programs to be installed -with an extra prefix or suffix on their names by giving `configure' the -option `--program-prefix=PREFIX' or `--program-suffix=SUFFIX'. - -Optional Features -================= - - Some packages pay attention to `--enable-FEATURE' options to -`configure', where FEATURE indicates an optional part of the package. -They may also pay attention to `--with-PACKAGE' options, where PACKAGE -is something like `gnu-as' or `x' (for the X Window System). The -`README' should mention any `--enable-' and `--with-' options that the -package recognizes. - - For packages that use the X Window System, `configure' can usually -find the X include and library files automatically, but if it doesn't, -you can use the `configure' options `--x-includes=DIR' and -`--x-libraries=DIR' to specify their locations. - -Specifying the System Type -========================== - - There may be some features `configure' can not figure out -automatically, but needs to determine by the type of host the package -will run on. Usually `configure' can figure that out, but if it prints -a message saying it can not guess the host type, give it the -`--host=TYPE' option. TYPE can either be a short name for the system -type, such as `sun4', or a canonical name with three fields: - CPU-COMPANY-SYSTEM - -See the file `config.sub' for the possible values of each field. If -`config.sub' isn't included in this package, then this package doesn't -need to know the host type. - - If you are building compiler tools for cross-compiling, you can also -use the `--target=TYPE' option to select the type of system they will -produce code for and the `--build=TYPE' option to select the type of -system on which you are compiling the package. - -Sharing Defaults -================ - - If you want to set default values for `configure' scripts to share, -you can create a site shell script called `config.site' that gives -default values for variables like `CC', `cache_file', and `prefix'. -`configure' looks for `PREFIX/share/config.site' if it exists, then -`PREFIX/etc/config.site' if it exists. Or, you can set the -`CONFIG_SITE' environment variable to the location of the site script. -A warning: not all `configure' scripts look for a site script. - -Operation Controls -================== - - `configure' recognizes the following options to control how it -operates. - -`--cache-file=FILE' - Use and save the results of the tests in FILE instead of - `./config.cache'. Set FILE to `/dev/null' to disable caching, for - debugging `configure'. - -`--help' - Print a summary of the options to `configure', and exit. - -`--quiet' -`--silent' -`-q' - Do not print messages saying which checks are being made. To - suppress all normal output, redirect it to `/dev/null' (any error - messages will still be shown). - -`--srcdir=DIR' - Look for the package's source code in directory DIR. Usually - `configure' can determine that directory automatically. - -`--version' - Print the version of Autoconf used to generate the `configure' - script, and exit. - -`configure' also accepts some other, not widely useful, options. diff --git a/external-libs/pcre/Makefile.in b/external-libs/pcre/Makefile.in deleted file mode 100644 index 8fd1e1a6..00000000 --- a/external-libs/pcre/Makefile.in +++ /dev/null @@ -1,279 +0,0 @@ - -# Makefile.in for PCRE (Perl-Compatible Regular Expression) library. - - -############################################################################# - -# PCRE is developed on a Unix system. I do not use Windows or Macs, and know -# nothing about building software on them. Although the code of PCRE should -# be very portable, the building system in this Makefile is designed for Unix -# systems. However, there are features that have been supplied to me by various -# people that should make it work on MinGW and Cygwin systems. - -# This setting enables Unix-style directory scanning in pcregrep, triggered -# by the -f option. Maybe one day someone will add code for other systems. - -PCREGREP_OSTYPE=-DIS_UNIX - -############################################################################# - - -#---------------------------------------------------------------------------# -# The following lines are modified by "configure" to insert data that it is # -# given in its arguments, or which it finds out for itself. # -#---------------------------------------------------------------------------# - -SHELL = @SHELL@ -prefix = @prefix@ -exec_prefix = @exec_prefix@ -top_srcdir = @top_srcdir@ - -mkinstalldirs = $(SHELL) $(top_srcdir)/mkinstalldirs - -# NB: top_builddir is not referred to directly below, but it is used in the -# setting of $(LIBTOOL), so don't remove it! - -top_builddir = . - -# BINDIR is the directory in which the pcregrep, pcretest, and pcre-config -# commands are installed. -# INCDIR is the directory in which the public header files pcre.h and -# pcreposix.h are installed. -# LIBDIR is the directory in which the libraries are installed. -# MANDIR is the directory in which the man pages are installed. - -BINDIR = @bindir@ -LIBDIR = @libdir@ -INCDIR = @includedir@ -MANDIR = @mandir@ - -# EXEEXT is set by configure to the extention of an executable file -# OBJEXT is set by configure to the extention of an object file -# The BUILD_* equivalents are the same but for the host we're building on - -EXEEXT = @EXEEXT@ -OBJEXT = @OBJEXT@ -# Note that these are just here to have a convenient place to look at the -# outcome. -BUILD_EXEEXT = @BUILD_EXEEXT@ -BUILD_OBJEXT = @BUILD_OBJEXT@ - -# The compiler, C flags, preprocessor flags, etc - -CC = @CC@ -CFLAGS = @CFLAGS@ -CPPFLAGS = @CPPFLAGS@ - -CC_FOR_BUILD = @CC_FOR_BUILD@ -CFLAGS_FOR_BUILD = @CFLAGS_FOR_BUILD@ -CPPFLAGS_FOR_BUILD = @CPPFLAGS_FOR_BUILD@ - -UTF8 = @UTF8@ -NEWLINE = @NEWLINE@ -POSIX_MALLOC_THRESHOLD = @POSIX_MALLOC_THRESHOLD@ -LINK_SIZE = @LINK_SIZE@ -MATCH_LIMIT = @MATCH_LIMIT@ -NO_RECURSE = @NO_RECURSE@ -EBCDIC = @EBCDIC@ - -INSTALL = @INSTALL@ -INSTALL_DATA = @INSTALL_DATA@ - -# LIBTOOL enables the building of shared and static libraries. It is set up -# to do one or the other or both by ./configure. - -LIBTOOL = @LIBTOOL@ -LTCOMPILE = $(LIBTOOL) --mode=compile $(CC) -c $(CFLAGS) -I. -I$(top_srcdir) $(NEWLINE) $(LINK_SIZE) $(MATCH_LIMIT) $(NO_RECURSE) $(EBCDIC) -@ON_WINDOWS@LINK = $(CC) $(CFLAGS) -I. -I$(top_srcdir) -L.libs -@NOT_ON_WINDOWS@LINK = $(LIBTOOL) --mode=link $(CC) $(CFLAGS) -I. -I$(top_srcdir) -LINKLIB = $(LIBTOOL) --mode=link $(CC) $(CFLAGS) -I. -I$(top_srcdir) -LINK_FOR_BUILD = $(LIBTOOL) --mode=link $(CC_FOR_BUILD) $(CFLAGS_FOR_BUILD) -I. -I$(top_srcdir) - -# These are the version numbers for the shared libraries - -PCRELIBVERSION = @PCRE_LIB_VERSION@ -PCREPOSIXLIBVERSION = @PCRE_POSIXLIB_VERSION@ - -############################################################################## - - -OBJ = maketables.@OBJEXT@ get.@OBJEXT@ study.@OBJEXT@ pcre.@OBJEXT@ @POSIX_OBJ@ -LOBJ = maketables.lo get.lo study.lo pcre.lo @POSIX_LOBJ@ - -all: libpcre.la @POSIX_LIB@ pcretest@EXEEXT@ pcregrep@EXEEXT@ @ON_WINDOWS@ winshared - -pcregrep@EXEEXT@: libpcre.la pcregrep.@OBJEXT@ @ON_WINDOWS@ winshared - $(LINK) -o pcregrep@EXEEXT@ pcregrep.@OBJEXT@ libpcre.la - -pcretest@EXEEXT@: libpcre.la @POSIX_LIB@ pcretest.@OBJEXT@ @ON_WINDOWS@ winshared - $(LINK) $(PURIFY) $(EFENCE) -o pcretest@EXEEXT@ pcretest.@OBJEXT@ \ - libpcre.la @POSIX_LIB@ - -libpcre.la: $(OBJ) - -rm -f libpcre.la - $(LINKLIB) -rpath $(LIBDIR) -version-info \ - '$(PCRELIBVERSION)' -o libpcre.la $(LOBJ) - -libpcreposix.la: libpcre.la pcreposix.@OBJEXT@ - -rm -f libpcreposix.la - $(LINKLIB) -rpath $(LIBDIR) libpcre.la -version-info \ - '$(PCREPOSIXLIBVERSION)' -o libpcreposix.la pcreposix.lo - -pcre.@OBJEXT@: $(top_srcdir)/chartables.c $(top_srcdir)/pcre.c \ - $(top_srcdir)/internal.h $(top_srcdir)/printint.c \ - pcre.h config.h Makefile - $(LTCOMPILE) $(UTF8) $(POSIX_MALLOC_THRESHOLD) $(top_srcdir)/pcre.c - -pcreposix.@OBJEXT@: $(top_srcdir)/pcreposix.c $(top_srcdir)/pcreposix.h \ - $(top_srcdir)/internal.h pcre.h config.h Makefile - $(LTCOMPILE) $(POSIX_MALLOC_THRESHOLD) $(top_srcdir)/pcreposix.c - -maketables.@OBJEXT@: $(top_srcdir)/maketables.c $(top_srcdir)/internal.h \ - pcre.h config.h Makefile - $(LTCOMPILE) $(top_srcdir)/maketables.c - -get.@OBJEXT@: $(top_srcdir)/get.c $(top_srcdir)/internal.h \ - pcre.h config.h Makefile - $(LTCOMPILE) $(top_srcdir)/get.c - -study.@OBJEXT@: $(top_srcdir)/study.c $(top_srcdir)/internal.h \ - pcre.h config.h Makefile - $(LTCOMPILE) $(UTF8) $(top_srcdir)/study.c - -pcretest.@OBJEXT@: $(top_srcdir)/pcretest.c $(top_srcdir)/internal.h \ - $(top_srcdir)/printint.c \ - pcre.h config.h Makefile - $(CC) -c $(CFLAGS) -I. $(UTF8) $(LINK_SIZE) $(top_srcdir)/pcretest.c - -pcregrep.@OBJEXT@: $(top_srcdir)/pcregrep.c pcre.h Makefile config.h - $(CC) -c $(CFLAGS) -I. $(UTF8) $(PCREGREP_OSTYPE) $(top_srcdir)/pcregrep.c - -# Some Windows-specific targets for MinGW. Do not use for Cygwin. - -winshared : .libs/@WIN_PREFIX@pcre.dll .libs/@WIN_PREFIX@pcreposix.dll - -.libs/@WIN_PREFIX@pcre.dll : libpcre.la - $(CC) $(CFLAGS) -shared -o $@ \ - -Wl,--whole-archive .libs/libpcre.a \ - -Wl,--out-implib,.libs/libpcre.dll.a \ - -Wl,--output-def,.libs/@WIN_PREFIX@pcre.dll-def \ - -Wl,--export-all-symbols \ - -Wl,--no-whole-archive - sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcre.dll'#" \ - -e "s#library_names=''#library_names='libpcre.dll.a'#" \ - < .libs/libpcre.lai > .libs/libpcre.lai.tmp && \ - mv .libs/libpcre.lai.tmp .libs/libpcre.lai - sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcre.dll'#" \ - -e "s#library_names=''#library_names='libpcre.dll.a'#" \ - < libpcre.la > libpcre.la.tmp && \ - mv libpcre.la.tmp libpcre.la - - -.libs/@WIN_PREFIX@pcreposix.dll: libpcreposix.la libpcre.la - $(CC) $(CFLAGS) -shared -o $@ \ - -Wl,--whole-archive .libs/libpcreposix.a \ - -Wl,--out-implib,.libs/@WIN_PREFIX@pcreposix.dll.a \ - -Wl,--output-def,.libs/@WIN_PREFIX@libpcreposix.dll-def \ - -Wl,--export-all-symbols \ - -Wl,--no-whole-archive .libs/libpcre.a - sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcreposix.dll'#" \ - -e "s#library_names=''#library_names='libpcreposix.dll.a'#"\ - < .libs/libpcreposix.lai > .libs/libpcreposix.lai.tmp && \ - mv .libs/libpcreposix.lai.tmp .libs/libpcreposix.lai - sed -e "s#dlname=''#dlname='../bin/@WIN_PREFIX@pcreposix.dll'#" \ - -e "s#library_names=''#library_names='libpcreposix.dll.a'#"\ - < libpcreposix.la > libpcreposix.la.tmp && \ - mv libpcreposix.la.tmp libpcreposix.la - - -wininstall : winshared - $(mkinstalldirs) $(DESTDIR)$(LIBDIR) - $(mkinstalldirs) $(DESTDIR)$(BINDIR) - $(INSTALL) .libs/@WIN_PREFIX@pcre.dll $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcre.dll - $(INSTALL) .libs/@WIN_PREFIX@pcreposix.dll $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcreposix.dll - $(INSTALL) .libs/@WIN_PREFIX@libpcreposix.dll.a $(DESTDIR)$(LIBDIR)/@WIN_PREFIX@libpcreposix.dll.a - $(INSTALL) .libs/@WIN_PREFIX@libpcre.dll.a $(DESTDIR)$(LIBDIR)/@WIN_PREFIX@libpcre.dll.a - -strip -g $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcre.dll - -strip -g $(DESTDIR)$(BINDIR)/@WIN_PREFIX@pcreposix.dll - -strip $(DESTDIR)$(BINDIR)/pcregrep@EXEEXT@ - -strip $(DESTDIR)$(BINDIR)/pcretest@EXEEXT@ - -# An auxiliary program makes the default character table source - -$(top_srcdir)/chartables.c: dftables - ./dftables $(top_srcdir)/chartables.c - -dftables.@BUILD_OBJEXT@: $(top_srcdir)/dftables.c $(top_srcdir)/maketables.c \ - $(top_srcdir)/internal.h pcre.h config.h Makefile - $(CC_FOR_BUILD) -c $(CFLAGS_FOR_BUILD) -I. $(top_srcdir)/dftables.c - -dftables: dftables.@BUILD_OBJEXT@ - $(LINK_FOR_BUILD) -o dftables dftables.@OBJEXT@ - -install: all @ON_WINDOWS@ wininstall -@NOT_ON_WINDOWS@ $(mkinstalldirs) $(DESTDIR)$(LIBDIR) -@NOT_ON_WINDOWS@ echo "$(LIBTOOL) --mode=install $(INSTALL) libpcre.la $(DESTDIR)$(LIBDIR)/libpcre.la" -@NOT_ON_WINDOWS@ $(LIBTOOL) --mode=install $(INSTALL) libpcre.la $(DESTDIR)$(LIBDIR)/libpcre.la -@NOT_ON_WINDOWS@ echo "$(LIBTOOL) --mode=install $(INSTALL) libpcreposix.la $(DESTDIR)$(LIBDIR)/libpcreposix.la" -@NOT_ON_WINDOWS@ $(LIBTOOL) --mode=install $(INSTALL) libpcreposix.la $(DESTDIR)$(LIBDIR)/libpcreposix.la -@NOT_ON_WINDOWS@ $(LIBTOOL) --finish $(DESTDIR)$(LIBDIR) - $(mkinstalldirs) $(DESTDIR)$(INCDIR) - $(INSTALL_DATA) pcre.h $(DESTDIR)$(INCDIR)/pcre.h - $(INSTALL_DATA) $(top_srcdir)/pcreposix.h $(DESTDIR)$(INCDIR)/pcreposix.h - $(mkinstalldirs) $(DESTDIR)$(MANDIR)/man3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre.3 $(DESTDIR)$(MANDIR)/man3/pcre.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcreapi.3 $(DESTDIR)$(MANDIR)/man3/pcreapi.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcrebuild.3 $(DESTDIR)$(MANDIR)/man3/pcrebuild.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcrecallout.3 $(DESTDIR)$(MANDIR)/man3/pcrecallout.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcrecompat.3 $(DESTDIR)$(MANDIR)/man3/pcrecompat.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcrepattern.3 $(DESTDIR)$(MANDIR)/man3/pcrepattern.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcreperform.3 $(DESTDIR)$(MANDIR)/man3/pcreperform.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcreposix.3 $(DESTDIR)$(MANDIR)/man3/pcreposix.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcresample.3 $(DESTDIR)$(MANDIR)/man3/pcresample.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_compile.3 $(DESTDIR)$(MANDIR)/man3/pcre_compile.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_config.3 $(DESTDIR)$(MANDIR)/man3/pcre_config.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_copy_named_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_copy_named_substring.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_copy_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_copy_substring.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_exec.3 $(DESTDIR)$(MANDIR)/man3/pcre_exec.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_free_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_free_substring.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_free_substring_list.3 $(DESTDIR)$(MANDIR)/man3/pcre_free_substring_list.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_fullinfo.3 $(DESTDIR)$(MANDIR)/man3/pcre_fullinfo.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_named_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_named_substring.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_stringnumber.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_stringnumber.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_substring.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_substring.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_get_substring_list.3 $(DESTDIR)$(MANDIR)/man3/pcre_get_substring_list.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_info.3 $(DESTDIR)$(MANDIR)/man3/pcre_info.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_maketables.3 $(DESTDIR)$(MANDIR)/man3/pcre_maketables.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_study.3 $(DESTDIR)$(MANDIR)/man3/pcre_study.3 - $(INSTALL_DATA) $(top_srcdir)/doc/pcre_version.3 $(DESTDIR)$(MANDIR)/man3/pcre_version.3 - $(mkinstalldirs) $(DESTDIR)$(MANDIR)/man1 - $(INSTALL_DATA) $(top_srcdir)/doc/pcregrep.1 $(DESTDIR)$(MANDIR)/man1/pcregrep.1 - $(INSTALL_DATA) $(top_srcdir)/doc/pcretest.1 $(DESTDIR)$(MANDIR)/man1/pcretest.1 - $(mkinstalldirs) $(DESTDIR)$(BINDIR) - $(LIBTOOL) --mode=install $(INSTALL) pcregrep@EXEEXT@ $(DESTDIR)$(BINDIR)/pcregrep@EXEEXT@ - $(LIBTOOL) --mode=install $(INSTALL) pcretest@EXEEXT@ $(DESTDIR)$(BINDIR)/pcretest@EXEEXT@ - $(INSTALL) pcre-config $(DESTDIR)$(BINDIR)/pcre-config - -# We deliberately omit dftables and chartables.c from 'make clean'; once made -# chartables.c shouldn't change, and if people have edited the tables by hand, -# you don't want to throw them away. - -clean:; -rm -rf *.@OBJEXT@ *.lo *.a *.la .libs pcretest@EXEEXT@ pcregrep@EXEEXT@ testtry - -# But "make distclean" should get back to a virgin distribution - -distclean: clean - -rm -f chartables.c libtool pcre-config pcre.h \ - Makefile config.h config.status config.log config.cache - -check: runtest - -@WIN_PREFIX@pcre.dll : winshared - cp .libs/@WIN_PREFIX@pcre.dll . - -test: runtest - -runtest: all @ON_WINDOWS@ @WIN_PREFIX@pcre.dll - @./RunTest - -# End diff --git a/external-libs/pcre/NEWS b/external-libs/pcre/NEWS deleted file mode 100644 index 26219749..00000000 --- a/external-libs/pcre/NEWS +++ /dev/null @@ -1,154 +0,0 @@ -News about PCRE releases ------------------------- - -Release 4.5 01-Dec-03 ---------------------- - -Again mainly a bug-fix and tidying release, with only a couple of new features: - -1. It's possible now to compile PCRE so that it does not use recursive -function calls when matching. Instead it gets memory from the heap. This slows -things down, but may be necessary on systems with limited stacks. - -2. UTF-8 string checking has been tightened to reject overlong sequences and to -check that a starting offset points to the start of a character. Failure of the -latter returns a new error code: PCRE_ERROR_BADUTF8_OFFSET. - -3. PCRE can now be compiled for systems that use EBCDIC code. - - -Release 4.4 21-Aug-03 ---------------------- - -This is mainly a bug-fix and tidying release. The only new feature is that PCRE -checks UTF-8 strings for validity by default. There is an option to suppress -this, just in case anybody wants that teeny extra bit of performance. - - -Releases 4.1 - 4.3 ------------------- - -Sorry, I forgot about updating the NEWS file for these releases. Please take a -look at ChangeLog. - - -Release 4.0 17-Feb-03 ---------------------- - -There have been a lot of changes for the 4.0 release, adding additional -functionality and mending bugs. Below is a list of the highlights of the new -functionality. For full details of these features, please consult the -documentation. For a complete list of changes, see the ChangeLog file. - -1. Support for Perl's \Q...\E escapes. - -2. "Possessive quantifiers" ?+, *+, ++, and {,}+ which come from Sun's Java -package. They provide some syntactic sugar for simple cases of "atomic -grouping". - -3. Support for the \G assertion. It is true when the current matching position -is at the start point of the match. - -4. A new feature that provides some of the functionality that Perl provides -with (?{...}). The facility is termed a "callout". The way it is done in PCRE -is for the caller to provide an optional function, by setting pcre_callout to -its entry point. To get the function called, the regex must include (?C) at -appropriate points. - -5. Support for recursive calls to individual subpatterns. This makes it really -easy to get totally confused. - -6. Support for named subpatterns. The Python syntax (?P<name>...) is used to -name a group. - -7. Several extensions to UTF-8 support; it is now fairly complete. There is an -option for pcregrep to make it operate in UTF-8 mode. - -8. The single man page has been split into a number of separate man pages. -These also give rise to individual HTML pages which are put in a separate -directory. There is an index.html page that lists them all. Some hyperlinking -between the pages has been installed. - - -Release 3.5 15-Aug-01 ---------------------- - -1. The configuring system has been upgraded to use later versions of autoconf -and libtool. By default it builds both a shared and a static library if the OS -supports it. You can use --disable-shared or --disable-static on the configure -command if you want only one of them. - -2. The pcretest utility is now installed along with pcregrep because it is -useful for users (to test regexs) and by doing this, it automatically gets -relinked by libtool. The documentation has been turned into a man page, so -there are now .1, .txt, and .html versions in /doc. - -3. Upgrades to pcregrep: - (i) Added long-form option names like gnu grep. - (ii) Added --help to list all options with an explanatory phrase. - (iii) Added -r, --recursive to recurse into sub-directories. - (iv) Added -f, --file to read patterns from a file. - -4. Added --enable-newline-is-cr and --enable-newline-is-lf to the configure -script, to force use of CR or LF instead of \n in the source. On non-Unix -systems, the value can be set in config.h. - -5. The limit of 200 on non-capturing parentheses is a _nesting_ limit, not an -absolute limit. Changed the text of the error message to make this clear, and -likewise updated the man page. - -6. The limit of 99 on the number of capturing subpatterns has been removed. -The new limit is 65535, which I hope will not be a "real" limit. - - -Release 3.3 01-Aug-00 ---------------------- - -There is some support for UTF-8 character strings. This is incomplete and -experimental. The documentation describes what is and what is not implemented. -Otherwise, this is just a bug-fixing release. - - -Release 3.0 01-Feb-00 ---------------------- - -1. A "configure" script is now used to configure PCRE for Unix systems. It -builds a Makefile, a config.h file, and the pcre-config script. - -2. PCRE is built as a shared library by default. - -3. There is support for POSIX classes such as [:alpha:]. - -5. There is an experimental recursion feature. - ----------------------------------------------------------------------------- - IMPORTANT FOR THOSE UPGRADING FROM VERSIONS BEFORE 2.00 - -Please note that there has been a change in the API such that a larger -ovector is required at matching time, to provide some additional workspace. -The new man page has details. This change was necessary in order to support -some of the new functionality in Perl 5.005. - - IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.00 - -Another (I hope this is the last!) change has been made to the API for the -pcre_compile() function. An additional argument has been added to make it -possible to pass over a pointer to character tables built in the current -locale by pcre_maketables(). To use the default tables, this new arguement -should be passed as NULL. - - IMPORTANT FOR THOSE UPGRADING FROM VERSION 2.05 - -Yet another (and again I hope this really is the last) change has been made -to the API for the pcre_exec() function. An additional argument has been -added to make it possible to start the match other than at the start of the -subject string. This is important if there are lookbehinds. The new man -page has the details, but you just want to convert existing programs, all -you need to do is to stick in a new fifth argument to pcre_exec(), with a -value of zero. For example, change - - pcre_exec(pattern, extra, subject, length, options, ovec, ovecsize) -to - pcre_exec(pattern, extra, subject, length, 0, options, ovec, ovecsize) - -**** diff --git a/external-libs/pcre/NON-UNIX-USE b/external-libs/pcre/NON-UNIX-USE deleted file mode 100644 index c015b214..00000000 --- a/external-libs/pcre/NON-UNIX-USE +++ /dev/null @@ -1,122 +0,0 @@ -Compiling PCRE on non-Unix systems ----------------------------------- - -See below for comments on Cygwin or MinGW usage. I (Philip Hazel) have no -knowledge of Windows sytems and how their libraries work. The items in the -PCRE Makefile that relate to anything other than Unix-like systems have been -contributed by PCRE users. There are some other comments and files in the -Contrib directory on the ftp site that you may find useful. - -The following are generic comments about building PCRE: - -If you want to compile PCRE for a non-Unix system (or perhaps, more strictly, -for a system that does not support "configure" and make files), note that PCRE -consists entirely of code written in Standard C, and so should compile -successfully on any machine with a Standard C compiler and library, using -normal compiling commands to do the following: - -(1) Copy or rename the file config.in as config.h, and change the macros that -define HAVE_STRERROR and HAVE_MEMMOVE to define them as 1 rather than 0. -Unfortunately, because of the way Unix autoconf works, the default setting has -to be 0. You may also want to make changes to other macros in config.h. In -particular, if you want to force a specific value for newline, you can define -the NEWLINE macro. The default is to use '\n', thereby using whatever value -your compiler gives to '\n'. - -(2) Copy or rename the file pcre.in as pcre.h, and change the macro definitions -for PCRE_MAJOR, PCRE_MINOR, and PCRE_DATE near its start to the values set in -configure.in. - -(3) Compile dftables.c as a stand-alone program, and then run it with -the single argument "chartables.c". This generates a set of standard -character tables and writes them to that file. - -(4) Compile maketables.c, get.c, study.c and pcre.c and link them all -together into an object library in whichever form your system keeps such -libraries. This is the pcre library (chartables.c is included by means of an -#include directive). If your system has static and shared libraries, you may -have to do this once for each type. - -(5) Similarly, compile pcreposix.c and link it (on its own) as the pcreposix -library. - -(6) Compile the test program pcretest.c. This needs the functions in the -pcre and pcreposix libraries when linking. - -(7) Run pcretest on the testinput files in the testdata directory, and check -that the output matches the corresponding testoutput files. You must use the --i option when checking testinput2. Note that the supplied files are in Unix -format, with just LF characters as line terminators. You may need to edit them -to change this if your system uses a different convention. - -If you have a system without "configure" but where you can use a Makefile, edit -Makefile.in to create Makefile, substituting suitable values for the variables -at the head of the file. - -Some help in building a Win32 DLL of PCRE in GnuWin32 environments was -contributed by Paul Sokolovsky. These environments are Mingw32 -(http://www.xraylith.wisc.edu/~khan/software/gnu-win32/) and CygWin -(http://sourceware.cygnus.com/cygwin/). Paul comments: - - For CygWin, set CFLAGS=-mno-cygwin, and do 'make dll'. You'll get - pcre.dll (containing pcreposix also), libpcre.dll.a, and dynamically - linked pgrep and pcretest. If you have /bin/sh, run RunTest (three - main test go ok, locale not supported). - -Changes to do MinGW with autoconf 2.50 were supplied by Fred Cox -<sailorFred@yahoo.com>, who comments as follows: - - If you are using the PCRE DLL, the normal Unix style configure && make && - make check && make install should just work[*]. If you want to statically - link against the .a file, you must define PCRE_STATIC before including - pcre.h, otherwise the pcre_malloc and pcre_free exported functions will be - declared __declspec(dllimport), with hilarious results. See the configure.in - and pcretest.c for how it is done for the static test. - - Also, there will only be a libpcre.la, not a libpcreposix.la, as you - would expect from the Unix version. The single DLL includes the pcreposix - interface. - -[*] But note that the supplied test files are in Unix format, with just LF -characters as line terminators. You will have to edit them to change to CR LF -terminators. - -A script for building PCRE using Borland's C++ compiler for use with VPASCAL -was contributed by Alexander Tokarev. It is called makevp.bat. - -These are some further comments about Win32 builds from Mark Evans. They -were contributed before Fred Cox's changes were made, so it is possible that -they may no longer be relevant. - -"The documentation for Win32 builds is a bit shy. Under MSVC6 I -followed their instructions to the letter, but there were still -some things missing. - -(1) Must #define STATIC for entire project if linking statically. - (I see no reason to use DLLs for code this compact.) This of - course is a project setting in MSVC under Preprocessor. - -(2) Missing some #ifdefs relating to the function pointers - pcre_malloc and pcre_free. See my solution below. (The stubs - may not be mandatory but they made me feel better.)" - -========================= -#ifdef _WIN32 -#include <malloc.h> - -void* malloc_stub(size_t N) -{ return malloc(N); } -void free_stub(void* p) -{ free(p); } -void *(*pcre_malloc)(size_t) = &malloc_stub; -void (*pcre_free)(void *) = &free_stub; - -#else - -void *(*pcre_malloc)(size_t) = malloc; -void (*pcre_free)(void *) = free; - -#endif -========================= - -**** diff --git a/external-libs/pcre/RunTest.in b/external-libs/pcre/RunTest.in deleted file mode 100644 index f203ac71..00000000 --- a/external-libs/pcre/RunTest.in +++ /dev/null @@ -1,139 +0,0 @@ -#! /bin/sh - -# This file is generated by configure from RunTest.in. Make any changes -# to that file. - -# Run PCRE tests - -cf=diff -testdata=@top_srcdir@/testdata - -# Select which tests to run; if no selection, run all - -do1=no -do2=no -do3=no -do4=no -do5=no - -while [ $# -gt 0 ] ; do - case $1 in - 1) do1=yes;; - 2) do2=yes;; - 3) do3=yes;; - 4) do4=yes;; - 5) do5=yes;; - *) echo "Unknown test number $1"; exit 1;; - esac - shift -done - -if [ "@UTF8@" = "" ] ; then - if [ $do4 = yes ] ; then - echo "Can't run test 4 because UFT8 support is not configured" - exit 1 - fi - if [ $do5 = yes ] ; then - echo "Can't run test 5 because UFT8 support is not configured" - exit 1 - fi -fi - -if [ $do1 = no -a $do2 = no -a $do3 = no -a $do4 = no -a\ - $do5 = no ] ; then - do1=yes - do2=yes - do3=yes - if [ "@UTF8@" != "" ] ; then do4=yes; fi - if [ "@UTF8@" != "" ] ; then do5=yes; fi -fi - -# Show which release - -./pcretest /dev/null - -# Primary test, Perl-compatible - -if [ $do1 = yes ] ; then - echo "Testing main functionality (Perl compatible)" - ./pcretest $testdata/testinput1 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput1 - if [ $? != 0 ] ; then exit 1; fi - echo " " - else exit 1 - fi -fi - -# PCRE tests that are not Perl-compatible - API & error tests, mostly - -if [ $do2 = yes ] ; then - echo "Testing API and error handling (not Perl compatible)" - ./pcretest -i $testdata/testinput2 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput2 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi -fi - -if [ $do1 = yes -a $do2 = yes ] ; then - echo " " - echo "The two main tests ran OK" - echo " " -fi - -# Locale-specific tests, provided the "fr_FR" locale is available - -if [ $do3 = yes ] ; then - locale -a | grep '^fr_FR$' >/dev/null - if [ $? -eq 0 ] ; then - echo "Testing locale-specific features (using 'fr_FR' locale)" - ./pcretest $testdata/testinput3 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput3 - if [ $? != 0 ] ; then - echo " " - echo "Locale test did not run entirely successfully." - echo "This usually means that there is a problem with the locale" - echo "settings rather than a bug in PCRE." - else - echo "Locale test ran OK" - fi - echo " " - else exit 1 - fi - else - echo "Cannot test locale-specific features - 'fr_FR' locale not found," - echo "or the \"locale\" command is not available to check for it." - echo " " - fi -fi - -# Additional tests for UTF8 support - -if [ $do4 = yes ] ; then - echo "Testing UTF-8 support (Perl compatible)" - ./pcretest $testdata/testinput4 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput4 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "UTF8 test ran OK" - echo " " -fi - -if [ $do5 = yes ] ; then - echo "Testing API and internals for UTF-8 support (not Perl compatible)" - ./pcretest $testdata/testinput5 testtry - if [ $? = 0 ] ; then - $cf testtry $testdata/testoutput5 - if [ $? != 0 ] ; then exit 1; fi - else exit 1 - fi - echo "UTF8 internals test ran OK" - echo " " -fi - -# End diff --git a/external-libs/pcre/config.guess b/external-libs/pcre/config.guess deleted file mode 100644 index 9b1384be..00000000 --- a/external-libs/pcre/config.guess +++ /dev/null @@ -1,1400 +0,0 @@ -#! /bin/sh -# Attempt to guess a canonical system name. -# Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, -# 2000, 2001, 2002 Free Software Foundation, Inc. - -timestamp='2002-11-30' - -# This file is free software; you can redistribute it and/or modify it -# under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, but -# WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. -# -# As a special exception to the GNU General Public License, if you -# distribute this file as part of a program that contains a -# configuration script generated by Autoconf, you may include it under -# the same distribution terms that you use for the rest of that program. - -# Originally written by Per Bothner <per@bothner.com>. -# Please send patches to <config-patches@gnu.org>. Submit a context -# diff and a properly formatted ChangeLog entry. -# -# This script attempts to guess a canonical system name similar to -# config.sub. If it succeeds, it prints the system name on stdout, and -# exits with 0. Otherwise, it exits with 1. -# -# The plan is that this can be called by configure scripts if you -# don't specify an explicit build system type. - -me=`echo "$0" | sed -e 's,.*/,,'` - -usage="\ -Usage: $0 [OPTION] - -Output the configuration name of the system \`$me' is run on. - -Operation modes: - -h, --help print this help, then exit - -t, --time-stamp print date of last modification, then exit - -v, --version print version number, then exit - -Report bugs and patches to <config-patches@gnu.org>." - -version="\ -GNU config.guess ($timestamp) - -Originally written by Per Bothner. -Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001 -Free Software Foundation, Inc. - -This is free software; see the source for copying conditions. There is NO -warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE." - -help=" -Try \`$me --help' for more information." - -# Parse command line -while test $# -gt 0 ; do - case $1 in - --time-stamp | --time* | -t ) - echo "$timestamp" ; exit 0 ;; - --version | -v ) - echo "$version" ; exit 0 ;; - --help | --h* | -h ) - echo "$usage"; exit 0 ;; - -- ) # Stop option processing - shift; break ;; - - ) # Use stdin as input. - break ;; - -* ) - echo "$me: invalid option $1$help" >&2 - exit 1 ;; - * ) - break ;; - esac -done - -if test $# != 0; then - echo "$me: too many arguments$help" >&2 - exit 1 -fi - -trap 'exit 1' 1 2 15 - -# CC_FOR_BUILD -- compiler used by this script. Note that the use of a -# compiler to aid in system detection is discouraged as it requires -# temporary files to be created and, as you can see below, it is a -# headache to deal with in a portable fashion. - -# Historically, `CC_FOR_BUILD' used to be named `HOST_CC'. We still -# use `HOST_CC' if defined, but it is deprecated. - -# This shell variable is my proudest work .. or something. --bje - -set_cc_for_build='tmpdir=${TMPDIR-/tmp}/config-guess-$$ ; -(old=`umask` && umask 077 && mkdir $tmpdir && umask $old && unset old) - || (echo "$me: cannot create $tmpdir" >&2 && exit 1) ; -dummy=$tmpdir/dummy ; -files="$dummy.c $dummy.o $dummy.rel $dummy" ; -trap '"'"'rm -f $files; rmdir $tmpdir; exit 1'"'"' 1 2 15 ; -case $CC_FOR_BUILD,$HOST_CC,$CC in - ,,) echo "int x;" > $dummy.c ; - for c in cc gcc c89 c99 ; do - if ($c -c -o $dummy.o $dummy.c) >/dev/null 2>&1 ; then - CC_FOR_BUILD="$c"; break ; - fi ; - done ; - rm -f $files ; - if test x"$CC_FOR_BUILD" = x ; then - CC_FOR_BUILD=no_compiler_found ; - fi - ;; - ,,*) CC_FOR_BUILD=$CC ;; - ,*,*) CC_FOR_BUILD=$HOST_CC ;; -esac ; -unset files' - -# This is needed to find uname on a Pyramid OSx when run in the BSD universe. -# (ghazi@noc.rutgers.edu 1994-08-24) -if (test -f /.attbin/uname) >/dev/null 2>&1 ; then - PATH=$PATH:/.attbin ; export PATH -fi - -UNAME_MACHINE=`(uname -m) 2>/dev/null` || UNAME_MACHINE=unknown -UNAME_RELEASE=`(uname -r) 2>/dev/null` || UNAME_RELEASE=unknown -UNAME_SYSTEM=`(uname -s) 2>/dev/null` || UNAME_SYSTEM=unknown -UNAME_VERSION=`(uname -v) 2>/dev/null` || UNAME_VERSION=unknown - -# Note: order is significant - the case branches are not exclusive. - -case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in - *:NetBSD:*:*) - # NetBSD (nbsd) targets should (where applicable) match one or - # more of the tupples: *-*-netbsdelf*, *-*-netbsdaout*, - # *-*-netbsdecoff* and *-*-netbsd*. For targets that recently - # switched to ELF, *-*-netbsd* would select the old - # object file format. This provides both forward - # compatibility and a consistent mechanism for selecting the - # object file format. - # - # Note: NetBSD doesn't particularly care about the vendor - # portion of the name. We always set it to "unknown". - sysctl="sysctl -n hw.machine_arch" - UNAME_MACHINE_ARCH=`(/sbin/$sysctl 2>/dev/null || \ - /usr/sbin/$sysctl 2>/dev/null || echo unknown)` - case "${UNAME_MACHINE_ARCH}" in - armeb) machine=armeb-unknown ;; - arm*) machine=arm-unknown ;; - sh3el) machine=shl-unknown ;; - sh3eb) machine=sh-unknown ;; - *) machine=${UNAME_MACHINE_ARCH}-unknown ;; - esac - # The Operating System including object format, if it has switched - # to ELF recently, or will in the future. - case "${UNAME_MACHINE_ARCH}" in - arm*|i386|m68k|ns32k|sh3*|sparc|vax) - eval $set_cc_for_build - if echo __ELF__ | $CC_FOR_BUILD -E - 2>/dev/null \ - | grep __ELF__ >/dev/null - then - # Once all utilities can be ECOFF (netbsdecoff) or a.out (netbsdaout). - # Return netbsd for either. FIX? - os=netbsd - else - os=netbsdelf - fi - ;; - *) - os=netbsd - ;; - esac - # The OS release - # Debian GNU/NetBSD machines have a different userland, and - # thus, need a distinct triplet. However, they do not need - # kernel version information, so it can be replaced with a - # suitable tag, in the style of linux-gnu. - case "${UNAME_VERSION}" in - Debian*) - release='-gnu' - ;; - *) - release=`echo ${UNAME_RELEASE}|sed -e 's/[-_].*/\./'` - ;; - esac - # Since CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM: - # contains redundant information, the shorter form: - # CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM is used. - echo "${machine}-${os}${release}" - exit 0 ;; - amiga:OpenBSD:*:*) - echo m68k-unknown-openbsd${UNAME_RELEASE} - exit 0 ;; - arc:OpenBSD:*:*) - echo mipsel-unknown-openbsd${UNAME_RELEASE} - exit 0 ;; - hp300:OpenBSD:*:*) - echo m68k-unknown-openbsd${UNAME_RELEASE} - exit 0 ;; - mac68k:OpenBSD:*:*) - echo m68k-unknown-openbsd${UNAME_RELEASE} - exit 0 ;; - macppc:OpenBSD:*:*) - echo powerpc-unknown-openbsd${UNAME_RELEASE} - exit 0 ;; - mvme68k:OpenBSD:*:*) - echo m68k-unknown-openbsd${UNAME_RELEASE} - exit 0 ;; - mvme88k:OpenBSD:*:*) - echo m88k-unknown-openbsd${UNAME_RELEASE} - exit 0 ;; - mvmeppc:OpenBSD:*:*) - echo powerpc-unknown-openbsd${UNAME_RELEASE} - exit 0 ;; - pmax:OpenBSD:*:*) - echo mipsel-unknown-openbsd${UNAME_RELEASE} - exit 0 ;; - sgi:OpenBSD:*:*) - echo mipseb-unknown-openbsd${UNAME_RELEASE} - exit 0 ;; - sun3:OpenBSD:*:*) - echo m68k-unknown-openbsd${UNAME_RELEASE} - exit 0 ;; - wgrisc:OpenBSD:*:*) - echo mipsel-unknown-openbsd${UNAME_RELEASE} - exit 0 ;; - *:OpenBSD:*:*) - echo ${UNAME_MACHINE}-unknown-openbsd${UNAME_RELEASE} - exit 0 ;; - alpha:OSF1:*:*) - if test $UNAME_RELEASE = "V4.0"; then - UNAME_RELEASE=`/usr/sbin/sizer -v | awk '{print $3}'` - fi - # A Vn.n version is a released version. - # A Tn.n version is a released field test version. - # A Xn.n version is an unreleased experimental baselevel. - # 1.2 uses "1.2" for uname -r. - eval $set_cc_for_build - cat <<EOF >$dummy.s - .data -\$Lformat: - .byte 37,100,45,37,120,10,0 # "%d-%x\n" - - .text - .globl main - .align 4 - .ent main -main: - .frame \$30,16,\$26,0 - ldgp \$29,0(\$27) - .prologue 1 - .long 0x47e03d80 # implver \$0 - lda \$2,-1 - .long 0x47e20c21 # amask \$2,\$1 - lda \$16,\$Lformat - mov \$0,\$17 - not \$1,\$18 - jsr \$26,printf - ldgp \$29,0(\$26) - mov 0,\$16 - jsr \$26,exit - .end main -EOF - $CC_FOR_BUILD -o $dummy $dummy.s 2>/dev/null - if test "$?" = 0 ; then - case `$dummy` in - 0-0) - UNAME_MACHINE="alpha" - ;; - 1-0) - UNAME_MACHINE="alphaev5" - ;; - 1-1) - UNAME_MACHINE="alphaev56" - ;; - 1-101) - UNAME_MACHINE="alphapca56" - ;; - 2-303) - UNAME_MACHINE="alphaev6" - ;; - 2-307) - UNAME_MACHINE="alphaev67" - ;; - 2-1307) - UNAME_MACHINE="alphaev68" - ;; - 3-1307) - UNAME_MACHINE="alphaev7" - ;; - esac - fi - rm -f $dummy.s $dummy && rmdir $tmpdir - echo ${UNAME_MACHINE}-dec-osf`echo ${UNAME_RELEASE} | sed -e 's/^[VTX]//' | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz'` - exit 0 ;; - Alpha\ *:Windows_NT*:*) - # How do we know it's Interix rather than the generic POSIX subsystem? - # Should we change UNAME_MACHINE based on the output of uname instead - # of the specific Alpha model? - echo alpha-pc-interix - exit 0 ;; - 21064:Windows_NT:50:3) - echo alpha-dec-winnt3.5 - exit 0 ;; - Amiga*:UNIX_System_V:4.0:*) - echo m68k-unknown-sysv4 - exit 0;; - *:[Aa]miga[Oo][Ss]:*:*) - echo ${UNAME_MACHINE}-unknown-amigaos - exit 0 ;; - *:[Mm]orph[Oo][Ss]:*:*) - echo ${UNAME_MACHINE}-unknown-morphos - exit 0 ;; - *:OS/390:*:*) - echo i370-ibm-openedition - exit 0 ;; - arm:RISC*:1.[012]*:*|arm:riscix:1.[012]*:*) - echo arm-acorn-riscix${UNAME_RELEASE} - exit 0;; - SR2?01:HI-UX/MPP:*:* | SR8000:HI-UX/MPP:*:*) - echo hppa1.1-hitachi-hiuxmpp - exit 0;; - Pyramid*:OSx*:*:* | MIS*:OSx*:*:* | MIS*:SMP_DC-OSx*:*:*) - # akee@wpdis03.wpafb.af.mil (Earle F. Ake) contributed MIS and NILE. - if test "`(/bin/universe) 2>/dev/null`" = att ; then - echo pyramid-pyramid-sysv3 - else - echo pyramid-pyramid-bsd - fi - exit 0 ;; - NILE*:*:*:dcosx) - echo pyramid-pyramid-svr4 - exit 0 ;; - DRS?6000:UNIX_SV:4.2*:7*) - case `/usr/bin/uname -p` in - sparc) echo sparc-icl-nx7 && exit 0 ;; - esac ;; - sun4H:SunOS:5.*:*) - echo sparc-hal-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` - exit 0 ;; - sun4*:SunOS:5.*:* | tadpole*:SunOS:5.*:*) - echo sparc-sun-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` - exit 0 ;; - i86pc:SunOS:5.*:*) - echo i386-pc-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` - exit 0 ;; - sun4*:SunOS:6*:*) - # According to config.sub, this is the proper way to canonicalize - # SunOS6. Hard to guess exactly what SunOS6 will be like, but - # it's likely to be more like Solaris than SunOS4. - echo sparc-sun-solaris3`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` - exit 0 ;; - sun4*:SunOS:*:*) - case "`/usr/bin/arch -k`" in - Series*|S4*) - UNAME_RELEASE=`uname -v` - ;; - esac - # Japanese Language versions have a version number like `4.1.3-JL'. - echo sparc-sun-sunos`echo ${UNAME_RELEASE}|sed -e 's/-/_/'` - exit 0 ;; - sun3*:SunOS:*:*) - echo m68k-sun-sunos${UNAME_RELEASE} - exit 0 ;; - sun*:*:4.2BSD:*) - UNAME_RELEASE=`(sed 1q /etc/motd | awk '{print substr($5,1,3)}') 2>/dev/null` - test "x${UNAME_RELEASE}" = "x" && UNAME_RELEASE=3 - case "`/bin/arch`" in - sun3) - echo m68k-sun-sunos${UNAME_RELEASE} - ;; - sun4) - echo sparc-sun-sunos${UNAME_RELEASE} - ;; - esac - exit 0 ;; - aushp:SunOS:*:*) - echo sparc-auspex-sunos${UNAME_RELEASE} - exit 0 ;; - # The situation for MiNT is a little confusing. The machine name - # can be virtually everything (everything which is not - # "atarist" or "atariste" at least should have a processor - # > m68000). The system name ranges from "MiNT" over "FreeMiNT" - # to the lowercase version "mint" (or "freemint"). Finally - # the system name "TOS" denotes a system which is actually not - # MiNT. But MiNT is downward compatible to TOS, so this should - # be no problem. - atarist[e]:*MiNT:*:* | atarist[e]:*mint:*:* | atarist[e]:*TOS:*:*) - echo m68k-atari-mint${UNAME_RELEASE} - exit 0 ;; - atari*:*MiNT:*:* | atari*:*mint:*:* | atarist[e]:*TOS:*:*) - echo m68k-atari-mint${UNAME_RELEASE} - exit 0 ;; - *falcon*:*MiNT:*:* | *falcon*:*mint:*:* | *falcon*:*TOS:*:*) - echo m68k-atari-mint${UNAME_RELEASE} - exit 0 ;; - milan*:*MiNT:*:* | milan*:*mint:*:* | *milan*:*TOS:*:*) - echo m68k-milan-mint${UNAME_RELEASE} - exit 0 ;; - hades*:*MiNT:*:* | hades*:*mint:*:* | *hades*:*TOS:*:*) - echo m68k-hades-mint${UNAME_RELEASE} - exit 0 ;; - *:*MiNT:*:* | *:*mint:*:* | *:*TOS:*:*) - echo m68k-unknown-mint${UNAME_RELEASE} - exit 0 ;; - powerpc:machten:*:*) - echo powerpc-apple-machten${UNAME_RELEASE} - exit 0 ;; - RISC*:Mach:*:*) - echo mips-dec-mach_bsd4.3 - exit 0 ;; - RISC*:ULTRIX:*:*) - echo mips-dec-ultrix${UNAME_RELEASE} - exit 0 ;; - VAX*:ULTRIX*:*:*) - echo vax-dec-ultrix${UNAME_RELEASE} - exit 0 ;; - 2020:CLIX:*:* | 2430:CLIX:*:*) - echo clipper-intergraph-clix${UNAME_RELEASE} - exit 0 ;; - mips:*:*:UMIPS | mips:*:*:RISCos) - eval $set_cc_for_build - sed 's/^ //' << EOF >$dummy.c -#ifdef __cplusplus -#include <stdio.h> /* for printf() prototype */ - int main (int argc, char *argv[]) { -#else - int main (argc, argv) int argc; char *argv[]; { -#endif - #if defined (host_mips) && defined (MIPSEB) - #if defined (SYSTYPE_SYSV) - printf ("mips-mips-riscos%ssysv\n", argv[1]); exit (0); - #endif - #if defined (SYSTYPE_SVR4) - printf ("mips-mips-riscos%ssvr4\n", argv[1]); exit (0); - #endif - #if defined (SYSTYPE_BSD43) || defined(SYSTYPE_BSD) - printf ("mips-mips-riscos%sbsd\n", argv[1]); exit (0); - #endif - #endif - exit (-1); - } -EOF - $CC_FOR_BUILD -o $dummy $dummy.c \ - && $dummy `echo "${UNAME_RELEASE}" | sed -n 's/\([0-9]*\).*/\1/p'` \ - && rm -f $dummy.c $dummy && rmdir $tmpdir && exit 0 - rm -f $dummy.c $dummy && rmdir $tmpdir - echo mips-mips-riscos${UNAME_RELEASE} - exit 0 ;; - Motorola:PowerMAX_OS:*:*) - echo powerpc-motorola-powermax - exit 0 ;; - Motorola:*:4.3:PL8-*) - echo powerpc-harris-powermax - exit 0 ;; - Night_Hawk:*:*:PowerMAX_OS | Synergy:PowerMAX_OS:*:*) - echo powerpc-harris-powermax - exit 0 ;; - Night_Hawk:Power_UNIX:*:*) - echo powerpc-harris-powerunix - exit 0 ;; - m88k:CX/UX:7*:*) - echo m88k-harris-cxux7 - exit 0 ;; - m88k:*:4*:R4*) - echo m88k-motorola-sysv4 - exit 0 ;; - m88k:*:3*:R3*) - echo m88k-motorola-sysv3 - exit 0 ;; - AViiON:dgux:*:*) - # DG/UX returns AViiON for all architectures - UNAME_PROCESSOR=`/usr/bin/uname -p` - if [ $UNAME_PROCESSOR = mc88100 ] || [ $UNAME_PROCESSOR = mc88110 ] - then - if [ ${TARGET_BINARY_INTERFACE}x = m88kdguxelfx ] || \ - [ ${TARGET_BINARY_INTERFACE}x = x ] - then - echo m88k-dg-dgux${UNAME_RELEASE} - else - echo m88k-dg-dguxbcs${UNAME_RELEASE} - fi - else - echo i586-dg-dgux${UNAME_RELEASE} - fi - exit 0 ;; - M88*:DolphinOS:*:*) # DolphinOS (SVR3) - echo m88k-dolphin-sysv3 - exit 0 ;; - M88*:*:R3*:*) - # Delta 88k system running SVR3 - echo m88k-motorola-sysv3 - exit 0 ;; - XD88*:*:*:*) # Tektronix XD88 system running UTekV (SVR3) - echo m88k-tektronix-sysv3 - exit 0 ;; - Tek43[0-9][0-9]:UTek:*:*) # Tektronix 4300 system running UTek (BSD) - echo m68k-tektronix-bsd - exit 0 ;; - *:IRIX*:*:*) - echo mips-sgi-irix`echo ${UNAME_RELEASE}|sed -e 's/-/_/g'` - exit 0 ;; - ????????:AIX?:[12].1:2) # AIX 2.2.1 or AIX 2.1.1 is RT/PC AIX. - echo romp-ibm-aix # uname -m gives an 8 hex-code CPU id - exit 0 ;; # Note that: echo "'`uname -s`'" gives 'AIX ' - i*86:AIX:*:*) - echo i386-ibm-aix - exit 0 ;; - ia64:AIX:*:*) - if [ -x /usr/bin/oslevel ] ; then - IBM_REV=`/usr/bin/oslevel` - else - IBM_REV=${UNAME_VERSION}.${UNAME_RELEASE} - fi - echo ${UNAME_MACHINE}-ibm-aix${IBM_REV} - exit 0 ;; - *:AIX:2:3) - if grep bos325 /usr/include/stdio.h >/dev/null 2>&1; then - eval $set_cc_for_build - sed 's/^ //' << EOF >$dummy.c - #include <sys/systemcfg.h> - - main() - { - if (!__power_pc()) - exit(1); - puts("powerpc-ibm-aix3.2.5"); - exit(0); - } -EOF - $CC_FOR_BUILD -o $dummy $dummy.c && $dummy && rm -f $dummy.c $dummy && rmdir $tmpdir && exit 0 - rm -f $dummy.c $dummy && rmdir $tmpdir - echo rs6000-ibm-aix3.2.5 - elif grep bos324 /usr/include/stdio.h >/dev/null 2>&1; then - echo rs6000-ibm-aix3.2.4 - else - echo rs6000-ibm-aix3.2 - fi - exit 0 ;; - *:AIX:*:[45]) - IBM_CPU_ID=`/usr/sbin/lsdev -C -c processor -S available | sed 1q | awk '{ print $1 }'` - if /usr/sbin/lsattr -El ${IBM_CPU_ID} | grep ' POWER' >/dev/null 2>&1; then - IBM_ARCH=rs6000 - else - IBM_ARCH=powerpc - fi - if [ -x /usr/bin/oslevel ] ; then - IBM_REV=`/usr/bin/oslevel` - else - IBM_REV=${UNAME_VERSION}.${UNAME_RELEASE} - fi - echo ${IBM_ARCH}-ibm-aix${IBM_REV} - exit 0 ;; - *:AIX:*:*) - echo rs6000-ibm-aix - exit 0 ;; - ibmrt:4.4BSD:*|romp-ibm:BSD:*) - echo romp-ibm-bsd4.4 - exit 0 ;; - ibmrt:*BSD:*|romp-ibm:BSD:*) # covers RT/PC BSD and - echo romp-ibm-bsd${UNAME_RELEASE} # 4.3 with uname added to - exit 0 ;; # report: romp-ibm BSD 4.3 - *:BOSX:*:*) - echo rs6000-bull-bosx - exit 0 ;; - DPX/2?00:B.O.S.:*:*) - echo m68k-bull-sysv3 - exit 0 ;; - 9000/[34]??:4.3bsd:1.*:*) - echo m68k-hp-bsd - exit 0 ;; - hp300:4.4BSD:*:* | 9000/[34]??:4.3bsd:2.*:*) - echo m68k-hp-bsd4.4 - exit 0 ;; - 9000/[34678]??:HP-UX:*:*) - HPUX_REV=`echo ${UNAME_RELEASE}|sed -e 's/[^.]*.[0B]*//'` - case "${UNAME_MACHINE}" in - 9000/31? ) HP_ARCH=m68000 ;; - 9000/[34]?? ) HP_ARCH=m68k ;; - 9000/[678][0-9][0-9]) - if [ -x /usr/bin/getconf ]; then - sc_cpu_version=`/usr/bin/getconf SC_CPU_VERSION 2>/dev/null` - sc_kernel_bits=`/usr/bin/getconf SC_KERNEL_BITS 2>/dev/null` - case "${sc_cpu_version}" in - 523) HP_ARCH="hppa1.0" ;; # CPU_PA_RISC1_0 - 528) HP_ARCH="hppa1.1" ;; # CPU_PA_RISC1_1 - 532) # CPU_PA_RISC2_0 - case "${sc_kernel_bits}" in - 32) HP_ARCH="hppa2.0n" ;; - 64) HP_ARCH="hppa2.0w" ;; - '') HP_ARCH="hppa2.0" ;; # HP-UX 10.20 - esac ;; - esac - fi - if [ "${HP_ARCH}" = "" ]; then - eval $set_cc_for_build - sed 's/^ //' << EOF >$dummy.c - - #define _HPUX_SOURCE - #include <stdlib.h> - #include <unistd.h> - - int main () - { - #if defined(_SC_KERNEL_BITS) - long bits = sysconf(_SC_KERNEL_BITS); - #endif - long cpu = sysconf (_SC_CPU_VERSION); - - switch (cpu) - { - case CPU_PA_RISC1_0: puts ("hppa1.0"); break; - case CPU_PA_RISC1_1: puts ("hppa1.1"); break; - case CPU_PA_RISC2_0: - #if defined(_SC_KERNEL_BITS) - switch (bits) - { - case 64: puts ("hppa2.0w"); break; - case 32: puts ("hppa2.0n"); break; - default: puts ("hppa2.0"); break; - } break; - #else /* !defined(_SC_KERNEL_BITS) */ - puts ("hppa2.0"); break; - #endif - default: puts ("hppa1.0"); break; - } - exit (0); - } -EOF - (CCOPTS= $CC_FOR_BUILD -o $dummy $dummy.c 2>/dev/null) && HP_ARCH=`$dummy` - if test -z "$HP_ARCH"; then HP_ARCH=hppa; fi - rm -f $dummy.c $dummy && rmdir $tmpdir - fi ;; - esac - echo ${HP_ARCH}-hp-hpux${HPUX_REV} - exit 0 ;; - ia64:HP-UX:*:*) - HPUX_REV=`echo ${UNAME_RELEASE}|sed -e 's/[^.]*.[0B]*//'` - echo ia64-hp-hpux${HPUX_REV} - exit 0 ;; - 3050*:HI-UX:*:*) - eval $set_cc_for_build - sed 's/^ //' << EOF >$dummy.c - #include <unistd.h> - int - main () - { - long cpu = sysconf (_SC_CPU_VERSION); - /* The order matters, because CPU_IS_HP_MC68K erroneously returns - true for CPU_PA_RISC1_0. CPU_IS_PA_RISC returns correct - results, however. */ - if (CPU_IS_PA_RISC (cpu)) - { - switch (cpu) - { - case CPU_PA_RISC1_0: puts ("hppa1.0-hitachi-hiuxwe2"); break; - case CPU_PA_RISC1_1: puts ("hppa1.1-hitachi-hiuxwe2"); break; - case CPU_PA_RISC2_0: puts ("hppa2.0-hitachi-hiuxwe2"); break; - default: puts ("hppa-hitachi-hiuxwe2"); break; - } - } - else if (CPU_IS_HP_MC68K (cpu)) - puts ("m68k-hitachi-hiuxwe2"); - else puts ("unknown-hitachi-hiuxwe2"); - exit (0); - } -EOF - $CC_FOR_BUILD -o $dummy $dummy.c && $dummy && rm -f $dummy.c $dummy && rmdir $tmpdir && exit 0 - rm -f $dummy.c $dummy && rmdir $tmpdir - echo unknown-hitachi-hiuxwe2 - exit 0 ;; - 9000/7??:4.3bsd:*:* | 9000/8?[79]:4.3bsd:*:* ) - echo hppa1.1-hp-bsd - exit 0 ;; - 9000/8??:4.3bsd:*:*) - echo hppa1.0-hp-bsd - exit 0 ;; - *9??*:MPE/iX:*:* | *3000*:MPE/iX:*:*) - echo hppa1.0-hp-mpeix - exit 0 ;; - hp7??:OSF1:*:* | hp8?[79]:OSF1:*:* ) - echo hppa1.1-hp-osf - exit 0 ;; - hp8??:OSF1:*:*) - echo hppa1.0-hp-osf - exit 0 ;; - i*86:OSF1:*:*) - if [ -x /usr/sbin/sysversion ] ; then - echo ${UNAME_MACHINE}-unknown-osf1mk - else - echo ${UNAME_MACHINE}-unknown-osf1 - fi - exit 0 ;; - parisc*:Lites*:*:*) - echo hppa1.1-hp-lites - exit 0 ;; - C1*:ConvexOS:*:* | convex:ConvexOS:C1*:*) - echo c1-convex-bsd - exit 0 ;; - C2*:ConvexOS:*:* | convex:ConvexOS:C2*:*) - if getsysinfo -f scalar_acc - then echo c32-convex-bsd - else echo c2-convex-bsd - fi - exit 0 ;; - C34*:ConvexOS:*:* | convex:ConvexOS:C34*:*) - echo c34-convex-bsd - exit 0 ;; - C38*:ConvexOS:*:* | convex:ConvexOS:C38*:*) - echo c38-convex-bsd - exit 0 ;; - C4*:ConvexOS:*:* | convex:ConvexOS:C4*:*) - echo c4-convex-bsd - exit 0 ;; - CRAY*Y-MP:*:*:*) - echo ymp-cray-unicos${UNAME_RELEASE} | sed -e 's/\.[^.]*$/.X/' - exit 0 ;; - CRAY*[A-Z]90:*:*:*) - echo ${UNAME_MACHINE}-cray-unicos${UNAME_RELEASE} \ - | sed -e 's/CRAY.*\([A-Z]90\)/\1/' \ - -e y/ABCDEFGHIJKLMNOPQRSTUVWXYZ/abcdefghijklmnopqrstuvwxyz/ \ - -e 's/\.[^.]*$/.X/' - exit 0 ;; - CRAY*TS:*:*:*) - echo t90-cray-unicos${UNAME_RELEASE} | sed -e 's/\.[^.]*$/.X/' - exit 0 ;; - CRAY*T3D:*:*:*) - echo alpha-cray-unicosmk${UNAME_RELEASE} | sed -e 's/\.[^.]*$/.X/' - exit 0 ;; - CRAY*T3E:*:*:*) - echo alphaev5-cray-unicosmk${UNAME_RELEASE} | sed -e 's/\.[^.]*$/.X/' - exit 0 ;; - CRAY*SV1:*:*:*) - echo sv1-cray-unicos${UNAME_RELEASE} | sed -e 's/\.[^.]*$/.X/' - exit 0 ;; - F30[01]:UNIX_System_V:*:* | F700:UNIX_System_V:*:*) - FUJITSU_PROC=`uname -m | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz'` - FUJITSU_SYS=`uname -p | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/\///'` - FUJITSU_REL=`echo ${UNAME_RELEASE} | sed -e 's/ /_/'` - echo "${FUJITSU_PROC}-fujitsu-${FUJITSU_SYS}${FUJITSU_REL}" - exit 0 ;; - i*86:BSD/386:*:* | i*86:BSD/OS:*:* | *:Ascend\ Embedded/OS:*:*) - echo ${UNAME_MACHINE}-pc-bsdi${UNAME_RELEASE} - exit 0 ;; - sparc*:BSD/OS:*:*) - echo sparc-unknown-bsdi${UNAME_RELEASE} - exit 0 ;; - *:BSD/OS:*:*) - echo ${UNAME_MACHINE}-unknown-bsdi${UNAME_RELEASE} - exit 0 ;; - *:FreeBSD:*:*) - # Determine whether the default compiler uses glibc. - eval $set_cc_for_build - sed 's/^ //' << EOF >$dummy.c - #include <features.h> - #if __GLIBC__ >= 2 - LIBC=gnu - #else - LIBC= - #endif -EOF - eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep ^LIBC=` - rm -f $dummy.c && rmdir $tmpdir - echo ${UNAME_MACHINE}-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'`${LIBC:+-$LIBC} - exit 0 ;; - i*:CYGWIN*:*) - echo ${UNAME_MACHINE}-pc-cygwin - exit 0 ;; - i*:MINGW*:*) - echo ${UNAME_MACHINE}-pc-mingw32 - exit 0 ;; - i*:PW*:*) - echo ${UNAME_MACHINE}-pc-pw32 - exit 0 ;; - x86:Interix*:3*) - echo i586-pc-interix3 - exit 0 ;; - [345]86:Windows_95:* | [345]86:Windows_98:* | [345]86:Windows_NT:*) - echo i${UNAME_MACHINE}-pc-mks - exit 0 ;; - i*:Windows_NT*:* | Pentium*:Windows_NT*:*) - # How do we know it's Interix rather than the generic POSIX subsystem? - # It also conflicts with pre-2.0 versions of AT&T UWIN. Should we - # UNAME_MACHINE based on the output of uname instead of i386? - echo i586-pc-interix - exit 0 ;; - i*:UWIN*:*) - echo ${UNAME_MACHINE}-pc-uwin - exit 0 ;; - p*:CYGWIN*:*) - echo powerpcle-unknown-cygwin - exit 0 ;; - prep*:SunOS:5.*:*) - echo powerpcle-unknown-solaris2`echo ${UNAME_RELEASE}|sed -e 's/[^.]*//'` - exit 0 ;; - *:GNU:*:*) - echo `echo ${UNAME_MACHINE}|sed -e 's,[-/].*$,,'`-unknown-gnu`echo ${UNAME_RELEASE}|sed -e 's,/.*$,,'` - exit 0 ;; - i*86:Minix:*:*) - echo ${UNAME_MACHINE}-pc-minix - exit 0 ;; - arm*:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-gnu - exit 0 ;; - ia64:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-gnu - exit 0 ;; - m68*:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-gnu - exit 0 ;; - mips:Linux:*:*) - eval $set_cc_for_build - sed 's/^ //' << EOF >$dummy.c - #undef CPU - #undef mips - #undef mipsel - #if defined(__MIPSEL__) || defined(__MIPSEL) || defined(_MIPSEL) || defined(MIPSEL) - CPU=mipsel - #else - #if defined(__MIPSEB__) || defined(__MIPSEB) || defined(_MIPSEB) || defined(MIPSEB) - CPU=mips - #else - CPU= - #endif - #endif -EOF - eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep ^CPU=` - rm -f $dummy.c && rmdir $tmpdir - test x"${CPU}" != x && echo "${CPU}-unknown-linux-gnu" && exit 0 - ;; - mips64:Linux:*:*) - eval $set_cc_for_build - sed 's/^ //' << EOF >$dummy.c - #undef CPU - #undef mips64 - #undef mips64el - #if defined(__MIPSEL__) || defined(__MIPSEL) || defined(_MIPSEL) || defined(MIPSEL) - CPU=mips64el - #else - #if defined(__MIPSEB__) || defined(__MIPSEB) || defined(_MIPSEB) || defined(MIPSEB) - CPU=mips64 - #else - CPU= - #endif - #endif -EOF - eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep ^CPU=` - rm -f $dummy.c && rmdir $tmpdir - test x"${CPU}" != x && echo "${CPU}-unknown-linux-gnu" && exit 0 - ;; - ppc:Linux:*:*) - echo powerpc-unknown-linux-gnu - exit 0 ;; - ppc64:Linux:*:*) - echo powerpc64-unknown-linux-gnu - exit 0 ;; - alpha:Linux:*:*) - case `sed -n '/^cpu model/s/^.*: \(.*\)/\1/p' < /proc/cpuinfo` in - EV5) UNAME_MACHINE=alphaev5 ;; - EV56) UNAME_MACHINE=alphaev56 ;; - PCA56) UNAME_MACHINE=alphapca56 ;; - PCA57) UNAME_MACHINE=alphapca56 ;; - EV6) UNAME_MACHINE=alphaev6 ;; - EV67) UNAME_MACHINE=alphaev67 ;; - EV68*) UNAME_MACHINE=alphaev68 ;; - esac - objdump --private-headers /bin/sh | grep ld.so.1 >/dev/null - if test "$?" = 0 ; then LIBC="libc1" ; else LIBC="" ; fi - echo ${UNAME_MACHINE}-unknown-linux-gnu${LIBC} - exit 0 ;; - parisc:Linux:*:* | hppa:Linux:*:*) - # Look for CPU level - case `grep '^cpu[^a-z]*:' /proc/cpuinfo 2>/dev/null | cut -d' ' -f2` in - PA7*) echo hppa1.1-unknown-linux-gnu ;; - PA8*) echo hppa2.0-unknown-linux-gnu ;; - *) echo hppa-unknown-linux-gnu ;; - esac - exit 0 ;; - parisc64:Linux:*:* | hppa64:Linux:*:*) - echo hppa64-unknown-linux-gnu - exit 0 ;; - s390:Linux:*:* | s390x:Linux:*:*) - echo ${UNAME_MACHINE}-ibm-linux - exit 0 ;; - sh*:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-gnu - exit 0 ;; - sparc:Linux:*:* | sparc64:Linux:*:*) - echo ${UNAME_MACHINE}-unknown-linux-gnu - exit 0 ;; - x86_64:Linux:*:*) - echo x86_64-unknown-linux-gnu - exit 0 ;; - i*86:Linux:*:*) - # The BFD linker knows what the default object file format is, so - # first see if it will tell us. cd to the root directory to prevent - # problems with other programs or directories called `ld' in the path. - # Set LC_ALL=C to ensure ld outputs messages in English. - ld_supported_targets=`cd /; LC_ALL=C ld --help 2>&1 \ - | sed -ne '/supported targets:/!d - s/[ ][ ]*/ /g - s/.*supported targets: *// - s/ .*// - p'` - case "$ld_supported_targets" in - elf32-i386) - TENTATIVE="${UNAME_MACHINE}-pc-linux-gnu" - ;; - a.out-i386-linux) - echo "${UNAME_MACHINE}-pc-linux-gnuaout" - exit 0 ;; - coff-i386) - echo "${UNAME_MACHINE}-pc-linux-gnucoff" - exit 0 ;; - "") - # Either a pre-BFD a.out linker (linux-gnuoldld) or - # one that does not give us useful --help. - echo "${UNAME_MACHINE}-pc-linux-gnuoldld" - exit 0 ;; - esac - # Determine whether the default compiler is a.out or elf - eval $set_cc_for_build - sed 's/^ //' << EOF >$dummy.c - #include <features.h> - #ifdef __ELF__ - # ifdef __GLIBC__ - # if __GLIBC__ >= 2 - LIBC=gnu - # else - LIBC=gnulibc1 - # endif - # else - LIBC=gnulibc1 - # endif - #else - #ifdef __INTEL_COMPILER - LIBC=gnu - #else - LIBC=gnuaout - #endif - #endif -EOF - eval `$CC_FOR_BUILD -E $dummy.c 2>/dev/null | grep ^LIBC=` - rm -f $dummy.c && rmdir $tmpdir - test x"${LIBC}" != x && echo "${UNAME_MACHINE}-pc-linux-${LIBC}" && exit 0 - test x"${TENTATIVE}" != x && echo "${TENTATIVE}" && exit 0 - ;; - i*86:DYNIX/ptx:4*:*) - # ptx 4.0 does uname -s correctly, with DYNIX/ptx in there. - # earlier versions are messed up and put the nodename in both - # sysname and nodename. - echo i386-sequent-sysv4 - exit 0 ;; - i*86:UNIX_SV:4.2MP:2.*) - # Unixware is an offshoot of SVR4, but it has its own version - # number series starting with 2... - # I am not positive that other SVR4 systems won't match this, - # I just have to hope. -- rms. - # Use sysv4.2uw... so that sysv4* matches it. - echo ${UNAME_MACHINE}-pc-sysv4.2uw${UNAME_VERSION} - exit 0 ;; - i*86:OS/2:*:*) - # If we were able to find `uname', then EMX Unix compatibility - # is probably installed. - echo ${UNAME_MACHINE}-pc-os2-emx - exit 0 ;; - i*86:XTS-300:*:STOP) - echo ${UNAME_MACHINE}-unknown-stop - exit 0 ;; - i*86:atheos:*:*) - echo ${UNAME_MACHINE}-unknown-atheos - exit 0 ;; - i*86:LynxOS:2.*:* | i*86:LynxOS:3.[01]*:* | i*86:LynxOS:4.0*:*) - echo i386-unknown-lynxos${UNAME_RELEASE} - exit 0 ;; - i*86:*DOS:*:*) - echo ${UNAME_MACHINE}-pc-msdosdjgpp - exit 0 ;; - i*86:*:4.*:* | i*86:SYSTEM_V:4.*:*) - UNAME_REL=`echo ${UNAME_RELEASE} | sed 's/\/MP$//'` - if grep Novell /usr/include/link.h >/dev/null 2>/dev/null; then - echo ${UNAME_MACHINE}-univel-sysv${UNAME_REL} - else - echo ${UNAME_MACHINE}-pc-sysv${UNAME_REL} - fi - exit 0 ;; - i*86:*:5:[78]*) - case `/bin/uname -X | grep "^Machine"` in - *486*) UNAME_MACHINE=i486 ;; - *Pentium) UNAME_MACHINE=i586 ;; - *Pent*|*Celeron) UNAME_MACHINE=i686 ;; - esac - echo ${UNAME_MACHINE}-unknown-sysv${UNAME_RELEASE}${UNAME_SYSTEM}${UNAME_VERSION} - exit 0 ;; - i*86:*:3.2:*) - if test -f /usr/options/cb.name; then - UNAME_REL=`sed -n 's/.*Version //p' </usr/options/cb.name` - echo ${UNAME_MACHINE}-pc-isc$UNAME_REL - elif /bin/uname -X 2>/dev/null >/dev/null ; then - UNAME_REL=`(/bin/uname -X|grep Release|sed -e 's/.*= //')` - (/bin/uname -X|grep i80486 >/dev/null) && UNAME_MACHINE=i486 - (/bin/uname -X|grep '^Machine.*Pentium' >/dev/null) \ - && UNAME_MACHINE=i586 - (/bin/uname -X|grep '^Machine.*Pent *II' >/dev/null) \ - && UNAME_MACHINE=i686 - (/bin/uname -X|grep '^Machine.*Pentium Pro' >/dev/null) \ - && UNAME_MACHINE=i686 - echo ${UNAME_MACHINE}-pc-sco$UNAME_REL - else - echo ${UNAME_MACHINE}-pc-sysv32 - fi - exit 0 ;; - pc:*:*:*) - # Left here for compatibility: - # uname -m prints for DJGPP always 'pc', but it prints nothing about - # the processor, so we play safe by assuming i386. - echo i386-pc-msdosdjgpp - exit 0 ;; - Intel:Mach:3*:*) - echo i386-pc-mach3 - exit 0 ;; - paragon:*:*:*) - echo i860-intel-osf1 - exit 0 ;; - i860:*:4.*:*) # i860-SVR4 - if grep Stardent /usr/include/sys/uadmin.h >/dev/null 2>&1 ; then - echo i860-stardent-sysv${UNAME_RELEASE} # Stardent Vistra i860-SVR4 - else # Add other i860-SVR4 vendors below as they are discovered. - echo i860-unknown-sysv${UNAME_RELEASE} # Unknown i860-SVR4 - fi - exit 0 ;; - mini*:CTIX:SYS*5:*) - # "miniframe" - echo m68010-convergent-sysv - exit 0 ;; - mc68k:UNIX:SYSTEM5:3.51m) - echo m68k-convergent-sysv - exit 0 ;; - M680?0:D-NIX:5.3:*) - echo m68k-diab-dnix - exit 0 ;; - M68*:*:R3V[567]*:*) - test -r /sysV68 && echo 'm68k-motorola-sysv' && exit 0 ;; - 3[34]??:*:4.0:3.0 | 3[34]??A:*:4.0:3.0 | 3[34]??,*:*:4.0:3.0 | 3[34]??/*:*:4.0:3.0 | 4400:*:4.0:3.0 | 4850:*:4.0:3.0 | SKA40:*:4.0:3.0 | SDS2:*:4.0:3.0) - OS_REL='' - test -r /etc/.relid \ - && OS_REL=.`sed -n 's/[^ ]* [^ ]* \([0-9][0-9]\).*/\1/p' < /etc/.relid` - /bin/uname -p 2>/dev/null | grep 86 >/dev/null \ - && echo i486-ncr-sysv4.3${OS_REL} && exit 0 - /bin/uname -p 2>/dev/null | /bin/grep entium >/dev/null \ - && echo i586-ncr-sysv4.3${OS_REL} && exit 0 ;; - 3[34]??:*:4.0:* | 3[34]??,*:*:4.0:*) - /bin/uname -p 2>/dev/null | grep 86 >/dev/null \ - && echo i486-ncr-sysv4 && exit 0 ;; - m68*:LynxOS:2.*:* | m68*:LynxOS:3.0*:*) - echo m68k-unknown-lynxos${UNAME_RELEASE} - exit 0 ;; - mc68030:UNIX_System_V:4.*:*) - echo m68k-atari-sysv4 - exit 0 ;; - TSUNAMI:LynxOS:2.*:*) - echo sparc-unknown-lynxos${UNAME_RELEASE} - exit 0 ;; - rs6000:LynxOS:2.*:*) - echo rs6000-unknown-lynxos${UNAME_RELEASE} - exit 0 ;; - PowerPC:LynxOS:2.*:* | PowerPC:LynxOS:3.[01]*:* | PowerPC:LynxOS:4.0*:*) - echo powerpc-unknown-lynxos${UNAME_RELEASE} - exit 0 ;; - SM[BE]S:UNIX_SV:*:*) - echo mips-dde-sysv${UNAME_RELEASE} - exit 0 ;; - RM*:ReliantUNIX-*:*:*) - echo mips-sni-sysv4 - exit 0 ;; - RM*:SINIX-*:*:*) - echo mips-sni-sysv4 - exit 0 ;; - *:SINIX-*:*:*) - if uname -p 2>/dev/null >/dev/null ; then - UNAME_MACHINE=`(uname -p) 2>/dev/null` - echo ${UNAME_MACHINE}-sni-sysv4 - else - echo ns32k-sni-sysv - fi - exit 0 ;; - PENTIUM:*:4.0*:*) # Unisys `ClearPath HMP IX 4000' SVR4/MP effort - # says <Richard.M.Bartel@ccMail.Census.GOV> - echo i586-unisys-sysv4 - exit 0 ;; - *:UNIX_System_V:4*:FTX*) - # From Gerald Hewes <hewes@openmarket.com>. - # How about differentiating between stratus architectures? -djm - echo hppa1.1-stratus-sysv4 - exit 0 ;; - *:*:*:FTX*) - # From seanf@swdc.stratus.com. - echo i860-stratus-sysv4 - exit 0 ;; - *:VOS:*:*) - # From Paul.Green@stratus.com. - echo hppa1.1-stratus-vos - exit 0 ;; - mc68*:A/UX:*:*) - echo m68k-apple-aux${UNAME_RELEASE} - exit 0 ;; - news*:NEWS-OS:6*:*) - echo mips-sony-newsos6 - exit 0 ;; - R[34]000:*System_V*:*:* | R4000:UNIX_SYSV:*:* | R*000:UNIX_SV:*:*) - if [ -d /usr/nec ]; then - echo mips-nec-sysv${UNAME_RELEASE} - else - echo mips-unknown-sysv${UNAME_RELEASE} - fi - exit 0 ;; - BeBox:BeOS:*:*) # BeOS running on hardware made by Be, PPC only. - echo powerpc-be-beos - exit 0 ;; - BeMac:BeOS:*:*) # BeOS running on Mac or Mac clone, PPC only. - echo powerpc-apple-beos - exit 0 ;; - BePC:BeOS:*:*) # BeOS running on Intel PC compatible. - echo i586-pc-beos - exit 0 ;; - SX-4:SUPER-UX:*:*) - echo sx4-nec-superux${UNAME_RELEASE} - exit 0 ;; - SX-5:SUPER-UX:*:*) - echo sx5-nec-superux${UNAME_RELEASE} - exit 0 ;; - SX-6:SUPER-UX:*:*) - echo sx6-nec-superux${UNAME_RELEASE} - exit 0 ;; - Power*:Rhapsody:*:*) - echo powerpc-apple-rhapsody${UNAME_RELEASE} - exit 0 ;; - *:Rhapsody:*:*) - echo ${UNAME_MACHINE}-apple-rhapsody${UNAME_RELEASE} - exit 0 ;; - *:Darwin:*:*) - echo `uname -p`-apple-darwin${UNAME_RELEASE} - exit 0 ;; - *:procnto*:*:* | *:QNX:[0123456789]*:*) - UNAME_PROCESSOR=`uname -p` - if test "$UNAME_PROCESSOR" = "x86"; then - UNAME_PROCESSOR=i386 - UNAME_MACHINE=pc - fi - echo ${UNAME_PROCESSOR}-${UNAME_MACHINE}-nto-qnx${UNAME_RELEASE} - exit 0 ;; - *:QNX:*:4*) - echo i386-pc-qnx - exit 0 ;; - NSR-[DGKLNPTVW]:NONSTOP_KERNEL:*:*) - echo nsr-tandem-nsk${UNAME_RELEASE} - exit 0 ;; - *:NonStop-UX:*:*) - echo mips-compaq-nonstopux - exit 0 ;; - BS2000:POSIX*:*:*) - echo bs2000-siemens-sysv - exit 0 ;; - DS/*:UNIX_System_V:*:*) - echo ${UNAME_MACHINE}-${UNAME_SYSTEM}-${UNAME_RELEASE} - exit 0 ;; - *:Plan9:*:*) - # "uname -m" is not consistent, so use $cputype instead. 386 - # is converted to i386 for consistency with other x86 - # operating systems. - if test "$cputype" = "386"; then - UNAME_MACHINE=i386 - else - UNAME_MACHINE="$cputype" - fi - echo ${UNAME_MACHINE}-unknown-plan9 - exit 0 ;; - *:TOPS-10:*:*) - echo pdp10-unknown-tops10 - exit 0 ;; - *:TENEX:*:*) - echo pdp10-unknown-tenex - exit 0 ;; - KS10:TOPS-20:*:* | KL10:TOPS-20:*:* | TYPE4:TOPS-20:*:*) - echo pdp10-dec-tops20 - exit 0 ;; - XKL-1:TOPS-20:*:* | TYPE5:TOPS-20:*:*) - echo pdp10-xkl-tops20 - exit 0 ;; - *:TOPS-20:*:*) - echo pdp10-unknown-tops20 - exit 0 ;; - *:ITS:*:*) - echo pdp10-unknown-its - exit 0 ;; -esac - -#echo '(No uname command or uname output not recognized.)' 1>&2 -#echo "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" 1>&2 - -eval $set_cc_for_build -cat >$dummy.c <<EOF -#ifdef _SEQUENT_ -# include <sys/types.h> -# include <sys/utsname.h> -#endif -main () -{ -#if defined (sony) -#if defined (MIPSEB) - /* BFD wants "bsd" instead of "newsos". Perhaps BFD should be changed, - I don't know.... */ - printf ("mips-sony-bsd\n"); exit (0); -#else -#include <sys/param.h> - printf ("m68k-sony-newsos%s\n", -#ifdef NEWSOS4 - "4" -#else - "" -#endif - ); exit (0); -#endif -#endif - -#if defined (__arm) && defined (__acorn) && defined (__unix) - printf ("arm-acorn-riscix"); exit (0); -#endif - -#if defined (hp300) && !defined (hpux) - printf ("m68k-hp-bsd\n"); exit (0); -#endif - -#if defined (NeXT) -#if !defined (__ARCHITECTURE__) -#define __ARCHITECTURE__ "m68k" -#endif - int version; - version=`(hostinfo | sed -n 's/.*NeXT Mach \([0-9]*\).*/\1/p') 2>/dev/null`; - if (version < 4) - printf ("%s-next-nextstep%d\n", __ARCHITECTURE__, version); - else - printf ("%s-next-openstep%d\n", __ARCHITECTURE__, version); - exit (0); -#endif - -#if defined (MULTIMAX) || defined (n16) -#if defined (UMAXV) - printf ("ns32k-encore-sysv\n"); exit (0); -#else -#if defined (CMU) - printf ("ns32k-encore-mach\n"); exit (0); -#else - printf ("ns32k-encore-bsd\n"); exit (0); -#endif -#endif -#endif - -#if defined (__386BSD__) - printf ("i386-pc-bsd\n"); exit (0); -#endif - -#if defined (sequent) -#if defined (i386) - printf ("i386-sequent-dynix\n"); exit (0); -#endif -#if defined (ns32000) - printf ("ns32k-sequent-dynix\n"); exit (0); -#endif -#endif - -#if defined (_SEQUENT_) - struct utsname un; - - uname(&un); - - if (strncmp(un.version, "V2", 2) == 0) { - printf ("i386-sequent-ptx2\n"); exit (0); - } - if (strncmp(un.version, "V1", 2) == 0) { /* XXX is V1 correct? */ - printf ("i386-sequent-ptx1\n"); exit (0); - } - printf ("i386-sequent-ptx\n"); exit (0); - -#endif - -#if defined (vax) -# if !defined (ultrix) -# include <sys/param.h> -# if defined (BSD) -# if BSD == 43 - printf ("vax-dec-bsd4.3\n"); exit (0); -# else -# if BSD == 199006 - printf ("vax-dec-bsd4.3reno\n"); exit (0); -# else - printf ("vax-dec-bsd\n"); exit (0); -# endif -# endif -# else - printf ("vax-dec-bsd\n"); exit (0); -# endif -# else - printf ("vax-dec-ultrix\n"); exit (0); -# endif -#endif - -#if defined (alliant) && defined (i860) - printf ("i860-alliant-bsd\n"); exit (0); -#endif - - exit (1); -} -EOF - -$CC_FOR_BUILD -o $dummy $dummy.c 2>/dev/null && $dummy && rm -f $dummy.c $dummy && rmdir $tmpdir && exit 0 -rm -f $dummy.c $dummy && rmdir $tmpdir - -# Apollos put the system type in the environment. - -test -d /usr/apollo && { echo ${ISP}-apollo-${SYSTYPE}; exit 0; } - -# Convex versions that predate uname can use getsysinfo(1) - -if [ -x /usr/convex/getsysinfo ] -then - case `getsysinfo -f cpu_type` in - c1*) - echo c1-convex-bsd - exit 0 ;; - c2*) - if getsysinfo -f scalar_acc - then echo c32-convex-bsd - else echo c2-convex-bsd - fi - exit 0 ;; - c34*) - echo c34-convex-bsd - exit 0 ;; - c38*) - echo c38-convex-bsd - exit 0 ;; - c4*) - echo c4-convex-bsd - exit 0 ;; - esac -fi - -cat >&2 <<EOF -$0: unable to guess system type - -This script, last modified $timestamp, has failed to recognize -the operating system you are using. It is advised that you -download the most up to date version of the config scripts from - - ftp://ftp.gnu.org/pub/gnu/config/ - -If the version you run ($0) is already up to date, please -send the following data and any information you think might be -pertinent to <config-patches@gnu.org> in order to provide the needed -information to handle your system. - -config.guess timestamp = $timestamp - -uname -m = `(uname -m) 2>/dev/null || echo unknown` -uname -r = `(uname -r) 2>/dev/null || echo unknown` -uname -s = `(uname -s) 2>/dev/null || echo unknown` -uname -v = `(uname -v) 2>/dev/null || echo unknown` - -/usr/bin/uname -p = `(/usr/bin/uname -p) 2>/dev/null` -/bin/uname -X = `(/bin/uname -X) 2>/dev/null` - -hostinfo = `(hostinfo) 2>/dev/null` -/bin/universe = `(/bin/universe) 2>/dev/null` -/usr/bin/arch -k = `(/usr/bin/arch -k) 2>/dev/null` -/bin/arch = `(/bin/arch) 2>/dev/null` -/usr/bin/oslevel = `(/usr/bin/oslevel) 2>/dev/null` -/usr/convex/getsysinfo = `(/usr/convex/getsysinfo) 2>/dev/null` - -UNAME_MACHINE = ${UNAME_MACHINE} -UNAME_RELEASE = ${UNAME_RELEASE} -UNAME_SYSTEM = ${UNAME_SYSTEM} -UNAME_VERSION = ${UNAME_VERSION} -EOF - -exit 1 - -# Local variables: -# eval: (add-hook 'write-file-hooks 'time-stamp) -# time-stamp-start: "timestamp='" -# time-stamp-format: "%:y-%02m-%02d" -# time-stamp-end: "'" -# End: diff --git a/external-libs/pcre/config.in b/external-libs/pcre/config.in deleted file mode 100644 index cb926a47..00000000 --- a/external-libs/pcre/config.in +++ /dev/null @@ -1,107 +0,0 @@ - -/* On Unix systems config.in is converted by configure into config.h. PCRE is -written in Standard C, but there are a few non-standard things it can cope -with, allowing it to run on SunOS4 and other "close to standard" systems. - -On a non-Unix system you should just copy this file into config.h, and set up -the macros the way you need them. You should normally change the definitions of -HAVE_STRERROR and HAVE_MEMMOVE to 1. Unfortunately, because of the way autoconf -works, these cannot be made the defaults. If your system has bcopy() and not -memmove(), change the definition of HAVE_BCOPY instead of HAVE_MEMMOVE. If your -system has neither bcopy() nor memmove(), leave them both as 0; an emulation -function will be used. */ - -/* If you are compiling for a system that uses EBCDIC instead of ASCII -character codes, define this macro as 1. On systems that can use "configure", -this can be done via --enable-ebcdic. */ - -#ifndef EBCDIC -#define EBCDIC 0 -#endif - -/* If you are compiling for a system that needs some magic to be inserted -before the definition of an exported function, define this macro to contain the -relevant magic. It apears at the start of every exported function. */ - -#define EXPORT - -/* Define to empty if the "const" keyword does not work. */ - -#undef const - -/* Define to "unsigned" if <stddef.h> doesn't define size_t. */ - -#undef size_t - -/* The following two definitions are mainly for the benefit of SunOS4, which -doesn't have the strerror() or memmove() functions that should be present in -all Standard C libraries. The macros HAVE_STRERROR and HAVE_MEMMOVE should -normally be defined with the value 1 for other systems, but unfortunately we -can't make this the default because "configure" files generated by autoconf -will only change 0 to 1; they won't change 1 to 0 if the functions are not -found. */ - -#define HAVE_STRERROR 0 -#define HAVE_MEMMOVE 0 - -/* There are some non-Unix systems that don't even have bcopy(). If this macro -is false, an emulation is used. If HAVE_MEMMOVE is set to 1, the value of -HAVE_BCOPY is not relevant. */ - -#define HAVE_BCOPY 0 - -/* The value of NEWLINE determines the newline character. The default is to -leave it up to the compiler, but some sites want to force a particular value. -On Unix systems, "configure" can be used to override this default. */ - -#ifndef NEWLINE -#define NEWLINE '\n' -#endif - -/* The value of LINK_SIZE determines the number of bytes used to store -links as offsets within the compiled regex. The default is 2, which allows for -compiled patterns up to 64K long. This covers the vast majority of cases. -However, PCRE can also be compiled to use 3 or 4 bytes instead. This allows for -longer patterns in extreme cases. On Unix systems, "configure" can be used to -override this default. */ - -#ifndef LINK_SIZE -#define LINK_SIZE 2 -#endif - -/* The value of MATCH_LIMIT determines the default number of times the match() -function can be called during a single execution of pcre_exec(). (There is a -runtime method of setting a different limit.) The limit exists in order to -catch runaway regular expressions that take for ever to determine that they do -not match. The default is set very large so that it does not accidentally catch -legitimate cases. On Unix systems, "configure" can be used to override this -default default. */ - -#ifndef MATCH_LIMIT -#define MATCH_LIMIT 10000000 -#endif - -/* When calling PCRE via the POSIX interface, additional working storage is -required for holding the pointers to capturing substrings because PCRE requires -three integers per substring, whereas the POSIX interface provides only two. If -the number of expected substrings is small, the wrapper function uses space on -the stack, because this is faster than using malloc() for each call. The -threshold above which the stack is no longer use is defined by POSIX_MALLOC_ -THRESHOLD. On Unix systems, "configure" can be used to override this default. -*/ - -#ifndef POSIX_MALLOC_THRESHOLD -#define POSIX_MALLOC_THRESHOLD 10 -#endif - -/* PCRE uses recursive function calls to handle backtracking while matching. -This can sometimes be a problem on systems that have stacks of limited size. -Define NO_RECURSE to get a version that doesn't use recursion in the match() -function; instead it creates its own stack by steam using pcre_recurse_malloc -to get memory. For more detail, see comments and other stuff just above the -match() function. On Unix systems, "configure" can be used to set this in the -Makefile (use --disable-recursion). */ - -/* #define NO_RECURSE */ - -/* End */ diff --git a/external-libs/pcre/config.sub b/external-libs/pcre/config.sub deleted file mode 100644 index f0675aa6..00000000 --- a/external-libs/pcre/config.sub +++ /dev/null @@ -1,1469 +0,0 @@ -#! /bin/sh -# Configuration validation subroutine script. -# Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, -# 2000, 2001, 2002 Free Software Foundation, Inc. - -timestamp='2002-11-30' - -# This file is (in principle) common to ALL GNU software. -# The presence of a machine in this file suggests that SOME GNU software -# can handle that machine. It does not imply ALL GNU software can. -# -# This file is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 59 Temple Place - Suite 330, -# Boston, MA 02111-1307, USA. - -# As a special exception to the GNU General Public License, if you -# distribute this file as part of a program that contains a -# configuration script generated by Autoconf, you may include it under -# the same distribution terms that you use for the rest of that program. - -# Please send patches to <config-patches@gnu.org>. Submit a context -# diff and a properly formatted ChangeLog entry. -# -# Configuration subroutine to validate and canonicalize a configuration type. -# Supply the specified configuration type as an argument. -# If it is invalid, we print an error message on stderr and exit with code 1. -# Otherwise, we print the canonical config type on stdout and succeed. - -# This file is supposed to be the same for all GNU packages -# and recognize all the CPU types, system types and aliases -# that are meaningful with *any* GNU software. -# Each package is responsible for reporting which valid configurations -# it does not support. The user should be able to distinguish -# a failure to support a valid configuration from a meaningless -# configuration. - -# The goal of this file is to map all the various variations of a given -# machine specification into a single specification in the form: -# CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM -# or in some cases, the newer four-part form: -# CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM -# It is wrong to echo any other type of specification. - -me=`echo "$0" | sed -e 's,.*/,,'` - -usage="\ -Usage: $0 [OPTION] CPU-MFR-OPSYS - $0 [OPTION] ALIAS - -Canonicalize a configuration name. - -Operation modes: - -h, --help print this help, then exit - -t, --time-stamp print date of last modification, then exit - -v, --version print version number, then exit - -Report bugs and patches to <config-patches@gnu.org>." - -version="\ -GNU config.sub ($timestamp) - -Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000, 2001 -Free Software Foundation, Inc. - -This is free software; see the source for copying conditions. There is NO -warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE." - -help=" -Try \`$me --help' for more information." - -# Parse command line -while test $# -gt 0 ; do - case $1 in - --time-stamp | --time* | -t ) - echo "$timestamp" ; exit 0 ;; - --version | -v ) - echo "$version" ; exit 0 ;; - --help | --h* | -h ) - echo "$usage"; exit 0 ;; - -- ) # Stop option processing - shift; break ;; - - ) # Use stdin as input. - break ;; - -* ) - echo "$me: invalid option $1$help" - exit 1 ;; - - *local*) - # First pass through any local machine types. - echo $1 - exit 0;; - - * ) - break ;; - esac -done - -case $# in - 0) echo "$me: missing argument$help" >&2 - exit 1;; - 1) ;; - *) echo "$me: too many arguments$help" >&2 - exit 1;; -esac - -# Separate what the user gave into CPU-COMPANY and OS or KERNEL-OS (if any). -# Here we must recognize all the valid KERNEL-OS combinations. -maybe_os=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\2/'` -case $maybe_os in - nto-qnx* | linux-gnu* | freebsd*-gnu* | netbsd*-gnu* | storm-chaos* | os2-emx* | rtmk-nova*) - os=-$maybe_os - basic_machine=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\1/'` - ;; - *) - basic_machine=`echo $1 | sed 's/-[^-]*$//'` - if [ $basic_machine != $1 ] - then os=`echo $1 | sed 's/.*-/-/'` - else os=; fi - ;; -esac - -### Let's recognize common machines as not being operating systems so -### that things like config.sub decstation-3100 work. We also -### recognize some manufacturers as not being operating systems, so we -### can provide default operating systems below. -case $os in - -sun*os*) - # Prevent following clause from handling this invalid input. - ;; - -dec* | -mips* | -sequent* | -encore* | -pc532* | -sgi* | -sony* | \ - -att* | -7300* | -3300* | -delta* | -motorola* | -sun[234]* | \ - -unicom* | -ibm* | -next | -hp | -isi* | -apollo | -altos* | \ - -convergent* | -ncr* | -news | -32* | -3600* | -3100* | -hitachi* |\ - -c[123]* | -convex* | -sun | -crds | -omron* | -dg | -ultra | -tti* | \ - -harris | -dolphin | -highlevel | -gould | -cbm | -ns | -masscomp | \ - -apple | -axis) - os= - basic_machine=$1 - ;; - -sim | -cisco | -oki | -wec | -winbond) - os= - basic_machine=$1 - ;; - -scout) - ;; - -wrs) - os=-vxworks - basic_machine=$1 - ;; - -chorusos*) - os=-chorusos - basic_machine=$1 - ;; - -chorusrdb) - os=-chorusrdb - basic_machine=$1 - ;; - -hiux*) - os=-hiuxwe2 - ;; - -sco5) - os=-sco3.2v5 - basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` - ;; - -sco4) - os=-sco3.2v4 - basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` - ;; - -sco3.2.[4-9]*) - os=`echo $os | sed -e 's/sco3.2./sco3.2v/'` - basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` - ;; - -sco3.2v[4-9]*) - # Don't forget version if it is 3.2v4 or newer. - basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` - ;; - -sco*) - os=-sco3.2v2 - basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` - ;; - -udk*) - basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` - ;; - -isc) - os=-isc2.2 - basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` - ;; - -clix*) - basic_machine=clipper-intergraph - ;; - -isc*) - basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'` - ;; - -lynx*) - os=-lynxos - ;; - -ptx*) - basic_machine=`echo $1 | sed -e 's/86-.*/86-sequent/'` - ;; - -windowsnt*) - os=`echo $os | sed -e 's/windowsnt/winnt/'` - ;; - -psos*) - os=-psos - ;; - -mint | -mint[0-9]*) - basic_machine=m68k-atari - os=-mint - ;; -esac - -# Decode aliases for certain CPU-COMPANY combinations. -case $basic_machine in - # Recognize the basic CPU types without company name. - # Some are omitted here because they have special meanings below. - 1750a | 580 \ - | a29k \ - | alpha | alphaev[4-8] | alphaev56 | alphaev6[78] | alphapca5[67] \ - | alpha64 | alpha64ev[4-8] | alpha64ev56 | alpha64ev6[78] | alpha64pca5[67] \ - | arc | arm | arm[bl]e | arme[lb] | armv[2345] | armv[345][lb] | avr \ - | clipper \ - | d10v | d30v | dlx | dsp16xx \ - | fr30 | frv \ - | h8300 | h8500 | hppa | hppa1.[01] | hppa2.0 | hppa2.0[nw] | hppa64 \ - | i370 | i860 | i960 | ia64 \ - | ip2k \ - | m32r | m68000 | m68k | m88k | mcore \ - | mips | mipsbe | mipseb | mipsel | mipsle \ - | mips16 \ - | mips64 | mips64el \ - | mips64vr | mips64vrel \ - | mips64orion | mips64orionel \ - | mips64vr4100 | mips64vr4100el \ - | mips64vr4300 | mips64vr4300el \ - | mips64vr5000 | mips64vr5000el \ - | mipsisa32 | mipsisa32el \ - | mipsisa64 | mipsisa64el \ - | mipsisa64sb1 | mipsisa64sb1el \ - | mipsisa64sr71k | mipsisa64sr71kel \ - | mipstx39 | mipstx39el \ - | mn10200 | mn10300 \ - | ns16k | ns32k \ - | openrisc | or32 \ - | pdp10 | pdp11 | pj | pjl \ - | powerpc | powerpc64 | powerpc64le | powerpcle | ppcbe \ - | pyramid \ - | sh | sh[1234] | sh3e | sh[34]eb | shbe | shle | sh[1234]le | sh3ele \ - | sh64 | sh64le \ - | sparc | sparc64 | sparc86x | sparclet | sparclite | sparcv9 | sparcv9b \ - | strongarm \ - | tahoe | thumb | tic80 | tron \ - | v850 | v850e \ - | we32k \ - | x86 | xscale | xstormy16 | xtensa \ - | z8k) - basic_machine=$basic_machine-unknown - ;; - m6811 | m68hc11 | m6812 | m68hc12) - # Motorola 68HC11/12. - basic_machine=$basic_machine-unknown - os=-none - ;; - m88110 | m680[12346]0 | m683?2 | m68360 | m5200 | v70 | w65 | z8k) - ;; - - # We use `pc' rather than `unknown' - # because (1) that's what they normally are, and - # (2) the word "unknown" tends to confuse beginning users. - i*86 | x86_64) - basic_machine=$basic_machine-pc - ;; - # Object if more than one company name word. - *-*-*) - echo Invalid configuration \`$1\': machine \`$basic_machine\' not recognized 1>&2 - exit 1 - ;; - # Recognize the basic CPU types with company name. - 580-* \ - | a29k-* \ - | alpha-* | alphaev[4-8]-* | alphaev56-* | alphaev6[78]-* \ - | alpha64-* | alpha64ev[4-8]-* | alpha64ev56-* | alpha64ev6[78]-* \ - | alphapca5[67]-* | alpha64pca5[67]-* | arc-* \ - | arm-* | armbe-* | armle-* | armeb-* | armv*-* \ - | avr-* \ - | bs2000-* \ - | c[123]* | c30-* | [cjt]90-* | c4x-* | c54x-* \ - | clipper-* | cydra-* \ - | d10v-* | d30v-* | dlx-* \ - | elxsi-* \ - | f30[01]-* | f700-* | fr30-* | frv-* | fx80-* \ - | h8300-* | h8500-* \ - | hppa-* | hppa1.[01]-* | hppa2.0-* | hppa2.0[nw]-* | hppa64-* \ - | i*86-* | i860-* | i960-* | ia64-* \ - | ip2k-* \ - | m32r-* \ - | m68000-* | m680[012346]0-* | m68360-* | m683?2-* | m68k-* \ - | m88110-* | m88k-* | mcore-* \ - | mips-* | mipsbe-* | mipseb-* | mipsel-* | mipsle-* \ - | mips16-* \ - | mips64-* | mips64el-* \ - | mips64vr-* | mips64vrel-* \ - | mips64orion-* | mips64orionel-* \ - | mips64vr4100-* | mips64vr4100el-* \ - | mips64vr4300-* | mips64vr4300el-* \ - | mips64vr5000-* | mips64vr5000el-* \ - | mipsisa32-* | mipsisa32el-* \ - | mipsisa64-* | mipsisa64el-* \ - | mipsisa64sb1-* | mipsisa64sb1el-* \ - | mipsisa64sr71k-* | mipsisa64sr71kel-* \ - | mipstx39 | mipstx39el \ - | none-* | np1-* | ns16k-* | ns32k-* \ - | orion-* \ - | pdp10-* | pdp11-* | pj-* | pjl-* | pn-* | power-* \ - | powerpc-* | powerpc64-* | powerpc64le-* | powerpcle-* | ppcbe-* \ - | pyramid-* \ - | romp-* | rs6000-* \ - | sh-* | sh[1234]-* | sh3e-* | sh[34]eb-* | shbe-* \ - | shle-* | sh[1234]le-* | sh3ele-* | sh64-* | sh64le-* \ - | sparc-* | sparc64-* | sparc86x-* | sparclet-* | sparclite-* \ - | sparcv9-* | sparcv9b-* | strongarm-* | sv1-* | sx?-* \ - | tahoe-* | thumb-* | tic30-* | tic4x-* | tic54x-* | tic80-* | tron-* \ - | v850-* | v850e-* | vax-* \ - | we32k-* \ - | x86-* | x86_64-* | xps100-* | xscale-* | xstormy16-* \ - | xtensa-* \ - | ymp-* \ - | z8k-*) - ;; - # Recognize the various machine names and aliases which stand - # for a CPU type and a company and sometimes even an OS. - 386bsd) - basic_machine=i386-unknown - os=-bsd - ;; - 3b1 | 7300 | 7300-att | att-7300 | pc7300 | safari | unixpc) - basic_machine=m68000-att - ;; - 3b*) - basic_machine=we32k-att - ;; - a29khif) - basic_machine=a29k-amd - os=-udi - ;; - adobe68k) - basic_machine=m68010-adobe - os=-scout - ;; - alliant | fx80) - basic_machine=fx80-alliant - ;; - altos | altos3068) - basic_machine=m68k-altos - ;; - am29k) - basic_machine=a29k-none - os=-bsd - ;; - amdahl) - basic_machine=580-amdahl - os=-sysv - ;; - amiga | amiga-*) - basic_machine=m68k-unknown - ;; - amigaos | amigados) - basic_machine=m68k-unknown - os=-amigaos - ;; - amigaunix | amix) - basic_machine=m68k-unknown - os=-sysv4 - ;; - apollo68) - basic_machine=m68k-apollo - os=-sysv - ;; - apollo68bsd) - basic_machine=m68k-apollo - os=-bsd - ;; - aux) - basic_machine=m68k-apple - os=-aux - ;; - balance) - basic_machine=ns32k-sequent - os=-dynix - ;; - c90) - basic_machine=c90-cray - os=-unicos - ;; - convex-c1) - basic_machine=c1-convex - os=-bsd - ;; - convex-c2) - basic_machine=c2-convex - os=-bsd - ;; - convex-c32) - basic_machine=c32-convex - os=-bsd - ;; - convex-c34) - basic_machine=c34-convex - os=-bsd - ;; - convex-c38) - basic_machine=c38-convex - os=-bsd - ;; - cray | j90) - basic_machine=j90-cray - os=-unicos - ;; - crds | unos) - basic_machine=m68k-crds - ;; - cris | cris-* | etrax*) - basic_machine=cris-axis - ;; - da30 | da30-*) - basic_machine=m68k-da30 - ;; - decstation | decstation-3100 | pmax | pmax-* | pmin | dec3100 | decstatn) - basic_machine=mips-dec - ;; - decsystem10* | dec10*) - basic_machine=pdp10-dec - os=-tops10 - ;; - decsystem20* | dec20*) - basic_machine=pdp10-dec - os=-tops20 - ;; - delta | 3300 | motorola-3300 | motorola-delta \ - | 3300-motorola | delta-motorola) - basic_machine=m68k-motorola - ;; - delta88) - basic_machine=m88k-motorola - os=-sysv3 - ;; - dpx20 | dpx20-*) - basic_machine=rs6000-bull - os=-bosx - ;; - dpx2* | dpx2*-bull) - basic_machine=m68k-bull - os=-sysv3 - ;; - ebmon29k) - basic_machine=a29k-amd - os=-ebmon - ;; - elxsi) - basic_machine=elxsi-elxsi - os=-bsd - ;; - encore | umax | mmax) - basic_machine=ns32k-encore - ;; - es1800 | OSE68k | ose68k | ose | OSE) - basic_machine=m68k-ericsson - os=-ose - ;; - fx2800) - basic_machine=i860-alliant - ;; - genix) - basic_machine=ns32k-ns - ;; - gmicro) - basic_machine=tron-gmicro - os=-sysv - ;; - go32) - basic_machine=i386-pc - os=-go32 - ;; - h3050r* | hiux*) - basic_machine=hppa1.1-hitachi - os=-hiuxwe2 - ;; - h8300hms) - basic_machine=h8300-hitachi - os=-hms - ;; - h8300xray) - basic_machine=h8300-hitachi - os=-xray - ;; - h8500hms) - basic_machine=h8500-hitachi - os=-hms - ;; - harris) - basic_machine=m88k-harris - os=-sysv3 - ;; - hp300-*) - basic_machine=m68k-hp - ;; - hp300bsd) - basic_machine=m68k-hp - os=-bsd - ;; - hp300hpux) - basic_machine=m68k-hp - os=-hpux - ;; - hp3k9[0-9][0-9] | hp9[0-9][0-9]) - basic_machine=hppa1.0-hp - ;; - hp9k2[0-9][0-9] | hp9k31[0-9]) - basic_machine=m68000-hp - ;; - hp9k3[2-9][0-9]) - basic_machine=m68k-hp - ;; - hp9k6[0-9][0-9] | hp6[0-9][0-9]) - basic_machine=hppa1.0-hp - ;; - hp9k7[0-79][0-9] | hp7[0-79][0-9]) - basic_machine=hppa1.1-hp - ;; - hp9k78[0-9] | hp78[0-9]) - # FIXME: really hppa2.0-hp - basic_machine=hppa1.1-hp - ;; - hp9k8[67]1 | hp8[67]1 | hp9k80[24] | hp80[24] | hp9k8[78]9 | hp8[78]9 | hp9k893 | hp893) - # FIXME: really hppa2.0-hp - basic_machine=hppa1.1-hp - ;; - hp9k8[0-9][13679] | hp8[0-9][13679]) - basic_machine=hppa1.1-hp - ;; - hp9k8[0-9][0-9] | hp8[0-9][0-9]) - basic_machine=hppa1.0-hp - ;; - hppa-next) - os=-nextstep3 - ;; - hppaosf) - basic_machine=hppa1.1-hp - os=-osf - ;; - hppro) - basic_machine=hppa1.1-hp - os=-proelf - ;; - i370-ibm* | ibm*) - basic_machine=i370-ibm - ;; -# I'm not sure what "Sysv32" means. Should this be sysv3.2? - i*86v32) - basic_machine=`echo $1 | sed -e 's/86.*/86-pc/'` - os=-sysv32 - ;; - i*86v4*) - basic_machine=`echo $1 | sed -e 's/86.*/86-pc/'` - os=-sysv4 - ;; - i*86v) - basic_machine=`echo $1 | sed -e 's/86.*/86-pc/'` - os=-sysv - ;; - i*86sol2) - basic_machine=`echo $1 | sed -e 's/86.*/86-pc/'` - os=-solaris2 - ;; - i386mach) - basic_machine=i386-mach - os=-mach - ;; - i386-vsta | vsta) - basic_machine=i386-unknown - os=-vsta - ;; - iris | iris4d) - basic_machine=mips-sgi - case $os in - -irix*) - ;; - *) - os=-irix4 - ;; - esac - ;; - isi68 | isi) - basic_machine=m68k-isi - os=-sysv - ;; - m88k-omron*) - basic_machine=m88k-omron - ;; - magnum | m3230) - basic_machine=mips-mips - os=-sysv - ;; - merlin) - basic_machine=ns32k-utek - os=-sysv - ;; - mingw32) - basic_machine=i386-pc - os=-mingw32 - ;; - miniframe) - basic_machine=m68000-convergent - ;; - *mint | -mint[0-9]* | *MiNT | *MiNT[0-9]*) - basic_machine=m68k-atari - os=-mint - ;; - mips3*-*) - basic_machine=`echo $basic_machine | sed -e 's/mips3/mips64/'` - ;; - mips3*) - basic_machine=`echo $basic_machine | sed -e 's/mips3/mips64/'`-unknown - ;; - mmix*) - basic_machine=mmix-knuth - os=-mmixware - ;; - monitor) - basic_machine=m68k-rom68k - os=-coff - ;; - morphos) - basic_machine=powerpc-unknown - os=-morphos - ;; - msdos) - basic_machine=i386-pc - os=-msdos - ;; - mvs) - basic_machine=i370-ibm - os=-mvs - ;; - ncr3000) - basic_machine=i486-ncr - os=-sysv4 - ;; - netbsd386) - basic_machine=i386-unknown - os=-netbsd - ;; - netwinder) - basic_machine=armv4l-rebel - os=-linux - ;; - news | news700 | news800 | news900) - basic_machine=m68k-sony - os=-newsos - ;; - news1000) - basic_machine=m68030-sony - os=-newsos - ;; - news-3600 | risc-news) - basic_machine=mips-sony - os=-newsos - ;; - necv70) - basic_machine=v70-nec - os=-sysv - ;; - next | m*-next ) - basic_machine=m68k-next - case $os in - -nextstep* ) - ;; - -ns2*) - os=-nextstep2 - ;; - *) - os=-nextstep3 - ;; - esac - ;; - nh3000) - basic_machine=m68k-harris - os=-cxux - ;; - nh[45]000) - basic_machine=m88k-harris - os=-cxux - ;; - nindy960) - basic_machine=i960-intel - os=-nindy - ;; - mon960) - basic_machine=i960-intel - os=-mon960 - ;; - nonstopux) - basic_machine=mips-compaq - os=-nonstopux - ;; - np1) - basic_machine=np1-gould - ;; - nsr-tandem) - basic_machine=nsr-tandem - ;; - op50n-* | op60c-*) - basic_machine=hppa1.1-oki - os=-proelf - ;; - or32 | or32-*) - basic_machine=or32-unknown - os=-coff - ;; - OSE68000 | ose68000) - basic_machine=m68000-ericsson - os=-ose - ;; - os68k) - basic_machine=m68k-none - os=-os68k - ;; - pa-hitachi) - basic_machine=hppa1.1-hitachi - os=-hiuxwe2 - ;; - paragon) - basic_machine=i860-intel - os=-osf - ;; - pbd) - basic_machine=sparc-tti - ;; - pbb) - basic_machine=m68k-tti - ;; - pc532 | pc532-*) - basic_machine=ns32k-pc532 - ;; - pentium | p5 | k5 | k6 | nexgen | viac3) - basic_machine=i586-pc - ;; - pentiumpro | p6 | 6x86 | athlon | athlon_*) - basic_machine=i686-pc - ;; - pentiumii | pentium2) - basic_machine=i686-pc - ;; - pentium-* | p5-* | k5-* | k6-* | nexgen-* | viac3-*) - basic_machine=i586-`echo $basic_machine | sed 's/^[^-]*-//'` - ;; - pentiumpro-* | p6-* | 6x86-* | athlon-*) - basic_machine=i686-`echo $basic_machine | sed 's/^[^-]*-//'` - ;; - pentiumii-* | pentium2-*) - basic_machine=i686-`echo $basic_machine | sed 's/^[^-]*-//'` - ;; - pn) - basic_machine=pn-gould - ;; - power) basic_machine=power-ibm - ;; - ppc) basic_machine=powerpc-unknown - ;; - ppc-*) basic_machine=powerpc-`echo $basic_machine | sed 's/^[^-]*-//'` - ;; - ppcle | powerpclittle | ppc-le | powerpc-little) - basic_machine=powerpcle-unknown - ;; - ppcle-* | powerpclittle-*) - basic_machine=powerpcle-`echo $basic_machine | sed 's/^[^-]*-//'` - ;; - ppc64) basic_machine=powerpc64-unknown - ;; - ppc64-*) basic_machine=powerpc64-`echo $basic_machine | sed 's/^[^-]*-//'` - ;; - ppc64le | powerpc64little | ppc64-le | powerpc64-little) - basic_machine=powerpc64le-unknown - ;; - ppc64le-* | powerpc64little-*) - basic_machine=powerpc64le-`echo $basic_machine | sed 's/^[^-]*-//'` - ;; - ps2) - basic_machine=i386-ibm - ;; - pw32) - basic_machine=i586-unknown - os=-pw32 - ;; - rom68k) - basic_machine=m68k-rom68k - os=-coff - ;; - rm[46]00) - basic_machine=mips-siemens - ;; - rtpc | rtpc-*) - basic_machine=romp-ibm - ;; - s390 | s390-*) - basic_machine=s390-ibm - ;; - s390x | s390x-*) - basic_machine=s390x-ibm - ;; - sa29200) - basic_machine=a29k-amd - os=-udi - ;; - sb1) - basic_machine=mipsisa64sb1-unknown - ;; - sb1el) - basic_machine=mipsisa64sb1el-unknown - ;; - sequent) - basic_machine=i386-sequent - ;; - sh) - basic_machine=sh-hitachi - os=-hms - ;; - sparclite-wrs | simso-wrs) - basic_machine=sparclite-wrs - os=-vxworks - ;; - sps7) - basic_machine=m68k-bull - os=-sysv2 - ;; - spur) - basic_machine=spur-unknown - ;; - st2000) - basic_machine=m68k-tandem - ;; - stratus) - basic_machine=i860-stratus - os=-sysv4 - ;; - sun2) - basic_machine=m68000-sun - ;; - sun2os3) - basic_machine=m68000-sun - os=-sunos3 - ;; - sun2os4) - basic_machine=m68000-sun - os=-sunos4 - ;; - sun3os3) - basic_machine=m68k-sun - os=-sunos3 - ;; - sun3os4) - basic_machine=m68k-sun - os=-sunos4 - ;; - sun4os3) - basic_machine=sparc-sun - os=-sunos3 - ;; - sun4os4) - basic_machine=sparc-sun - os=-sunos4 - ;; - sun4sol2) - basic_machine=sparc-sun - os=-solaris2 - ;; - sun3 | sun3-*) - basic_machine=m68k-sun - ;; - sun4) - basic_machine=sparc-sun - ;; - sun386 | sun386i | roadrunner) - basic_machine=i386-sun - ;; - sv1) - basic_machine=sv1-cray - os=-unicos - ;; - symmetry) - basic_machine=i386-sequent - os=-dynix - ;; - t3d) - basic_machine=alpha-cray - os=-unicos - ;; - t3e) - basic_machine=alphaev5-cray - os=-unicos - ;; - t90) - basic_machine=t90-cray - os=-unicos - ;; - tic4x | c4x*) - basic_machine=tic4x-unknown - os=-coff - ;; - tic54x | c54x*) - basic_machine=tic54x-unknown - os=-coff - ;; - tx39) - basic_machine=mipstx39-unknown - ;; - tx39el) - basic_machine=mipstx39el-unknown - ;; - toad1) - basic_machine=pdp10-xkl - os=-tops20 - ;; - tower | tower-32) - basic_machine=m68k-ncr - ;; - udi29k) - basic_machine=a29k-amd - os=-udi - ;; - ultra3) - basic_machine=a29k-nyu - os=-sym1 - ;; - v810 | necv810) - basic_machine=v810-nec - os=-none - ;; - vaxv) - basic_machine=vax-dec - os=-sysv - ;; - vms) - basic_machine=vax-dec - os=-vms - ;; - vpp*|vx|vx-*) - basic_machine=f301-fujitsu - ;; - vxworks960) - basic_machine=i960-wrs - os=-vxworks - ;; - vxworks68) - basic_machine=m68k-wrs - os=-vxworks - ;; - vxworks29k) - basic_machine=a29k-wrs - os=-vxworks - ;; - w65*) - basic_machine=w65-wdc - os=-none - ;; - w89k-*) - basic_machine=hppa1.1-winbond - os=-proelf - ;; - xps | xps100) - basic_machine=xps100-honeywell - ;; - ymp) - basic_machine=ymp-cray - os=-unicos - ;; - z8k-*-coff) - basic_machine=z8k-unknown - os=-sim - ;; - none) - basic_machine=none-none - os=-none - ;; - -# Here we handle the default manufacturer of certain CPU types. It is in -# some cases the only manufacturer, in others, it is the most popular. - w89k) - basic_machine=hppa1.1-winbond - ;; - op50n) - basic_machine=hppa1.1-oki - ;; - op60c) - basic_machine=hppa1.1-oki - ;; - romp) - basic_machine=romp-ibm - ;; - rs6000) - basic_machine=rs6000-ibm - ;; - vax) - basic_machine=vax-dec - ;; - pdp10) - # there are many clones, so DEC is not a safe bet - basic_machine=pdp10-unknown - ;; - pdp11) - basic_machine=pdp11-dec - ;; - we32k) - basic_machine=we32k-att - ;; - sh3 | sh4 | sh3eb | sh4eb | sh[1234]le | sh3ele) - basic_machine=sh-unknown - ;; - sh64) - basic_machine=sh64-unknown - ;; - sparc | sparcv9 | sparcv9b) - basic_machine=sparc-sun - ;; - cydra) - basic_machine=cydra-cydrome - ;; - orion) - basic_machine=orion-highlevel - ;; - orion105) - basic_machine=clipper-highlevel - ;; - mac | mpw | mac-mpw) - basic_machine=m68k-apple - ;; - pmac | pmac-mpw) - basic_machine=powerpc-apple - ;; - *-unknown) - # Make sure to match an already-canonicalized machine name. - ;; - *) - echo Invalid configuration \`$1\': machine \`$basic_machine\' not recognized 1>&2 - exit 1 - ;; -esac - -# Here we canonicalize certain aliases for manufacturers. -case $basic_machine in - *-digital*) - basic_machine=`echo $basic_machine | sed 's/digital.*/dec/'` - ;; - *-commodore*) - basic_machine=`echo $basic_machine | sed 's/commodore.*/cbm/'` - ;; - *) - ;; -esac - -# Decode manufacturer-specific aliases for certain operating systems. - -if [ x"$os" != x"" ] -then -case $os in - # First match some system type aliases - # that might get confused with valid system types. - # -solaris* is a basic system type, with this one exception. - -solaris1 | -solaris1.*) - os=`echo $os | sed -e 's|solaris1|sunos4|'` - ;; - -solaris) - os=-solaris2 - ;; - -svr4*) - os=-sysv4 - ;; - -unixware*) - os=-sysv4.2uw - ;; - -gnu/linux*) - os=`echo $os | sed -e 's|gnu/linux|linux-gnu|'` - ;; - # First accept the basic system types. - # The portable systems comes first. - # Each alternative MUST END IN A *, to match a version number. - # -sysv* is not here because it comes later, after sysvr4. - -gnu* | -bsd* | -mach* | -minix* | -genix* | -ultrix* | -irix* \ - | -*vms* | -sco* | -esix* | -isc* | -aix* | -sunos | -sunos[34]*\ - | -hpux* | -unos* | -osf* | -luna* | -dgux* | -solaris* | -sym* \ - | -amigaos* | -amigados* | -msdos* | -newsos* | -unicos* | -aof* \ - | -aos* \ - | -nindy* | -vxsim* | -vxworks* | -ebmon* | -hms* | -mvs* \ - | -clix* | -riscos* | -uniplus* | -iris* | -rtu* | -xenix* \ - | -hiux* | -386bsd* | -netbsd* | -openbsd* | -freebsd* | -riscix* \ - | -lynxos* | -bosx* | -nextstep* | -cxux* | -aout* | -elf* | -oabi* \ - | -ptx* | -coff* | -ecoff* | -winnt* | -domain* | -vsta* \ - | -udi* | -eabi* | -lites* | -ieee* | -go32* | -aux* \ - | -chorusos* | -chorusrdb* \ - | -cygwin* | -pe* | -psos* | -moss* | -proelf* | -rtems* \ - | -mingw32* | -linux-gnu* | -uxpv* | -beos* | -mpeix* | -udk* \ - | -interix* | -uwin* | -mks* | -rhapsody* | -darwin* | -opened* \ - | -openstep* | -oskit* | -conix* | -pw32* | -nonstopux* \ - | -storm-chaos* | -tops10* | -tenex* | -tops20* | -its* \ - | -os2* | -vos* | -palmos* | -uclinux* | -nucleus* \ - | -morphos* | -superux* | -rtmk* | -rtmk-nova* | -windiss* \ - | -powermax* | -dnix*) - # Remember, each alternative MUST END IN *, to match a version number. - ;; - -qnx*) - case $basic_machine in - x86-* | i*86-*) - ;; - *) - os=-nto$os - ;; - esac - ;; - -nto-qnx*) - ;; - -nto*) - os=`echo $os | sed -e 's|nto|nto-qnx|'` - ;; - -sim | -es1800* | -hms* | -xray | -os68k* | -none* | -v88r* \ - | -windows* | -osx | -abug | -netware* | -os9* | -beos* \ - | -macos* | -mpw* | -magic* | -mmixware* | -mon960* | -lnews*) - ;; - -mac*) - os=`echo $os | sed -e 's|mac|macos|'` - ;; - -linux*) - os=`echo $os | sed -e 's|linux|linux-gnu|'` - ;; - -sunos5*) - os=`echo $os | sed -e 's|sunos5|solaris2|'` - ;; - -sunos6*) - os=`echo $os | sed -e 's|sunos6|solaris3|'` - ;; - -opened*) - os=-openedition - ;; - -wince*) - os=-wince - ;; - -osfrose*) - os=-osfrose - ;; - -osf*) - os=-osf - ;; - -utek*) - os=-bsd - ;; - -dynix*) - os=-bsd - ;; - -acis*) - os=-aos - ;; - -atheos*) - os=-atheos - ;; - -386bsd) - os=-bsd - ;; - -ctix* | -uts*) - os=-sysv - ;; - -nova*) - os=-rtmk-nova - ;; - -ns2 ) - os=-nextstep2 - ;; - -nsk*) - os=-nsk - ;; - # Preserve the version number of sinix5. - -sinix5.*) - os=`echo $os | sed -e 's|sinix|sysv|'` - ;; - -sinix*) - os=-sysv4 - ;; - -triton*) - os=-sysv3 - ;; - -oss*) - os=-sysv3 - ;; - -svr4) - os=-sysv4 - ;; - -svr3) - os=-sysv3 - ;; - -sysvr4) - os=-sysv4 - ;; - # This must come after -sysvr4. - -sysv*) - ;; - -ose*) - os=-ose - ;; - -es1800*) - os=-ose - ;; - -xenix) - os=-xenix - ;; - -*mint | -mint[0-9]* | -*MiNT | -MiNT[0-9]*) - os=-mint - ;; - -none) - ;; - *) - # Get rid of the `-' at the beginning of $os. - os=`echo $os | sed 's/[^-]*-//'` - echo Invalid configuration \`$1\': system \`$os\' not recognized 1>&2 - exit 1 - ;; -esac -else - -# Here we handle the default operating systems that come with various machines. -# The value should be what the vendor currently ships out the door with their -# machine or put another way, the most popular os provided with the machine. - -# Note that if you're going to try to match "-MANUFACTURER" here (say, -# "-sun"), then you have to tell the case statement up towards the top -# that MANUFACTURER isn't an operating system. Otherwise, code above -# will signal an error saying that MANUFACTURER isn't an operating -# system, and we'll never get to this point. - -case $basic_machine in - *-acorn) - os=-riscix1.2 - ;; - arm*-rebel) - os=-linux - ;; - arm*-semi) - os=-aout - ;; - # This must come before the *-dec entry. - pdp10-*) - os=-tops20 - ;; - pdp11-*) - os=-none - ;; - *-dec | vax-*) - os=-ultrix4.2 - ;; - m68*-apollo) - os=-domain - ;; - i386-sun) - os=-sunos4.0.2 - ;; - m68000-sun) - os=-sunos3 - # This also exists in the configure program, but was not the - # default. - # os=-sunos4 - ;; - m68*-cisco) - os=-aout - ;; - mips*-cisco) - os=-elf - ;; - mips*-*) - os=-elf - ;; - or32-*) - os=-coff - ;; - *-tti) # must be before sparc entry or we get the wrong os. - os=-sysv3 - ;; - sparc-* | *-sun) - os=-sunos4.1.1 - ;; - *-be) - os=-beos - ;; - *-ibm) - os=-aix - ;; - *-wec) - os=-proelf - ;; - *-winbond) - os=-proelf - ;; - *-oki) - os=-proelf - ;; - *-hp) - os=-hpux - ;; - *-hitachi) - os=-hiux - ;; - i860-* | *-att | *-ncr | *-altos | *-motorola | *-convergent) - os=-sysv - ;; - *-cbm) - os=-amigaos - ;; - *-dg) - os=-dgux - ;; - *-dolphin) - os=-sysv3 - ;; - m68k-ccur) - os=-rtu - ;; - m88k-omron*) - os=-luna - ;; - *-next ) - os=-nextstep - ;; - *-sequent) - os=-ptx - ;; - *-crds) - os=-unos - ;; - *-ns) - os=-genix - ;; - i370-*) - os=-mvs - ;; - *-next) - os=-nextstep3 - ;; - *-gould) - os=-sysv - ;; - *-highlevel) - os=-bsd - ;; - *-encore) - os=-bsd - ;; - *-sgi) - os=-irix - ;; - *-siemens) - os=-sysv4 - ;; - *-masscomp) - os=-rtu - ;; - f30[01]-fujitsu | f700-fujitsu) - os=-uxpv - ;; - *-rom68k) - os=-coff - ;; - *-*bug) - os=-coff - ;; - *-apple) - os=-macos - ;; - *-atari*) - os=-mint - ;; - *) - os=-none - ;; -esac -fi - -# Here we handle the case where we know the os, and the CPU type, but not the -# manufacturer. We pick the logical manufacturer. -vendor=unknown -case $basic_machine in - *-unknown) - case $os in - -riscix*) - vendor=acorn - ;; - -sunos*) - vendor=sun - ;; - -aix*) - vendor=ibm - ;; - -beos*) - vendor=be - ;; - -hpux*) - vendor=hp - ;; - -mpeix*) - vendor=hp - ;; - -hiux*) - vendor=hitachi - ;; - -unos*) - vendor=crds - ;; - -dgux*) - vendor=dg - ;; - -luna*) - vendor=omron - ;; - -genix*) - vendor=ns - ;; - -mvs* | -opened*) - vendor=ibm - ;; - -ptx*) - vendor=sequent - ;; - -vxsim* | -vxworks* | -windiss*) - vendor=wrs - ;; - -aux*) - vendor=apple - ;; - -hms*) - vendor=hitachi - ;; - -mpw* | -macos*) - vendor=apple - ;; - -*mint | -mint[0-9]* | -*MiNT | -MiNT[0-9]*) - vendor=atari - ;; - -vos*) - vendor=stratus - ;; - esac - basic_machine=`echo $basic_machine | sed "s/unknown/$vendor/"` - ;; -esac - -echo $basic_machine$os -exit 0 - -# Local variables: -# eval: (add-hook 'write-file-hooks 'time-stamp) -# time-stamp-start: "timestamp='" -# time-stamp-format: "%:y-%02m-%02d" -# time-stamp-end: "'" -# End: diff --git a/external-libs/pcre/configure b/external-libs/pcre/configure deleted file mode 100644 index da706e01..00000000 --- a/external-libs/pcre/configure +++ /dev/null @@ -1,8927 +0,0 @@ -#! /bin/sh -# Guess values for system-dependent variables and create Makefiles. -# Generated by GNU Autoconf 2.57. -# -# Copyright 1992, 1993, 1994, 1995, 1996, 1998, 1999, 2000, 2001, 2002 -# Free Software Foundation, Inc. -# This configure script is free software; the Free Software Foundation -# gives unlimited permission to copy, distribute and modify it. -## --------------------- ## -## M4sh Initialization. ## -## --------------------- ## - -# Be Bourne compatible -if test -n "${ZSH_VERSION+set}" && (emulate sh) >/dev/null 2>&1; then - emulate sh - NULLCMD=: - # Zsh 3.x and 4.x performs word splitting on ${1+"$@"}, which - # is contrary to our usage. Disable this feature. - alias -g '${1+"$@"}'='"$@"' -elif test -n "${BASH_VERSION+set}" && (set -o posix) >/dev/null 2>&1; then - set -o posix -fi - -# Support unset when possible. -if (FOO=FOO; unset FOO) >/dev/null 2>&1; then - as_unset=unset -else - as_unset=false -fi - - -# Work around bugs in pre-3.0 UWIN ksh. -$as_unset ENV MAIL MAILPATH -PS1='$ ' -PS2='> ' -PS4='+ ' - -# NLS nuisances. -for as_var in \ - LANG LANGUAGE LC_ADDRESS LC_ALL LC_COLLATE LC_CTYPE LC_IDENTIFICATION \ - LC_MEASUREMENT LC_MESSAGES LC_MONETARY LC_NAME LC_NUMERIC LC_PAPER \ - LC_TELEPHONE LC_TIME -do - if (set +x; test -n "`(eval $as_var=C; export $as_var) 2>&1`"); then - eval $as_var=C; export $as_var - else - $as_unset $as_var - fi -done - -# Required to use basename. -if expr a : '\(a\)' >/dev/null 2>&1; then - as_expr=expr -else - as_expr=false -fi - -if (basename /) >/dev/null 2>&1 && test "X`basename / 2>&1`" = "X/"; then - as_basename=basename -else - as_basename=false -fi - - -# Name of the executable. -as_me=`$as_basename "$0" || -$as_expr X/"$0" : '.*/\([^/][^/]*\)/*$' \| \ - X"$0" : 'X\(//\)$' \| \ - X"$0" : 'X\(/\)$' \| \ - . : '\(.\)' 2>/dev/null || -echo X/"$0" | - sed '/^.*\/\([^/][^/]*\)\/*$/{ s//\1/; q; } - /^X\/\(\/\/\)$/{ s//\1/; q; } - /^X\/\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` - - -# PATH needs CR, and LINENO needs CR and PATH. -# Avoid depending upon Character Ranges. -as_cr_letters='abcdefghijklmnopqrstuvwxyz' -as_cr_LETTERS='ABCDEFGHIJKLMNOPQRSTUVWXYZ' -as_cr_Letters=$as_cr_letters$as_cr_LETTERS -as_cr_digits='0123456789' -as_cr_alnum=$as_cr_Letters$as_cr_digits - -# The user is always right. -if test "${PATH_SEPARATOR+set}" != set; then - echo "#! /bin/sh" >conf$$.sh - echo "exit 0" >>conf$$.sh - chmod +x conf$$.sh - if (PATH="/nonexistent;."; conf$$.sh) >/dev/null 2>&1; then - PATH_SEPARATOR=';' - else - PATH_SEPARATOR=: - fi - rm -f conf$$.sh -fi - - - as_lineno_1=$LINENO - as_lineno_2=$LINENO - as_lineno_3=`(expr $as_lineno_1 + 1) 2>/dev/null` - test "x$as_lineno_1" != "x$as_lineno_2" && - test "x$as_lineno_3" = "x$as_lineno_2" || { - # Find who we are. Look in the path if we contain no path at all - # relative or not. - case $0 in - *[\\/]* ) as_myself=$0 ;; - *) as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - test -r "$as_dir/$0" && as_myself=$as_dir/$0 && break -done - - ;; - esac - # We did not find ourselves, most probably we were run as `sh COMMAND' - # in which case we are not to be found in the path. - if test "x$as_myself" = x; then - as_myself=$0 - fi - if test ! -f "$as_myself"; then - { echo "$as_me: error: cannot find myself; rerun with an absolute path" >&2 - { (exit 1); exit 1; }; } - fi - case $CONFIG_SHELL in - '') - as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in /bin$PATH_SEPARATOR/usr/bin$PATH_SEPARATOR$PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for as_base in sh bash ksh sh5; do - case $as_dir in - /*) - if ("$as_dir/$as_base" -c ' - as_lineno_1=$LINENO - as_lineno_2=$LINENO - as_lineno_3=`(expr $as_lineno_1 + 1) 2>/dev/null` - test "x$as_lineno_1" != "x$as_lineno_2" && - test "x$as_lineno_3" = "x$as_lineno_2" ') 2>/dev/null; then - $as_unset BASH_ENV || test "${BASH_ENV+set}" != set || { BASH_ENV=; export BASH_ENV; } - $as_unset ENV || test "${ENV+set}" != set || { ENV=; export ENV; } - CONFIG_SHELL=$as_dir/$as_base - export CONFIG_SHELL - exec "$CONFIG_SHELL" "$0" ${1+"$@"} - fi;; - esac - done -done -;; - esac - - # Create $as_me.lineno as a copy of $as_myself, but with $LINENO - # uniformly replaced by the line number. The first 'sed' inserts a - # line-number line before each line; the second 'sed' does the real - # work. The second script uses 'N' to pair each line-number line - # with the numbered line, and appends trailing '-' during - # substitution so that $LINENO is not a special case at line end. - # (Raja R Harinath suggested sed '=', and Paul Eggert wrote the - # second 'sed' script. Blame Lee E. McMahon for sed's syntax. :-) - sed '=' <$as_myself | - sed ' - N - s,$,-, - : loop - s,^\(['$as_cr_digits']*\)\(.*\)[$]LINENO\([^'$as_cr_alnum'_]\),\1\2\1\3, - t loop - s,-$,, - s,^['$as_cr_digits']*\n,, - ' >$as_me.lineno && - chmod +x $as_me.lineno || - { echo "$as_me: error: cannot create $as_me.lineno; rerun with a POSIX shell" >&2 - { (exit 1); exit 1; }; } - - # Don't try to exec as it changes $[0], causing all sort of problems - # (the dirname of $[0] is not the place where we might find the - # original and so on. Autoconf is especially sensible to this). - . ./$as_me.lineno - # Exit status is that of the last command. - exit -} - - -case `echo "testing\c"; echo 1,2,3`,`echo -n testing; echo 1,2,3` in - *c*,-n*) ECHO_N= ECHO_C=' -' ECHO_T=' ' ;; - *c*,* ) ECHO_N=-n ECHO_C= ECHO_T= ;; - *) ECHO_N= ECHO_C='\c' ECHO_T= ;; -esac - -if expr a : '\(a\)' >/dev/null 2>&1; then - as_expr=expr -else - as_expr=false -fi - -rm -f conf$$ conf$$.exe conf$$.file -echo >conf$$.file -if ln -s conf$$.file conf$$ 2>/dev/null; then - # We could just check for DJGPP; but this test a) works b) is more generic - # and c) will remain valid once DJGPP supports symlinks (DJGPP 2.04). - if test -f conf$$.exe; then - # Don't use ln at all; we don't have any links - as_ln_s='cp -p' - else - as_ln_s='ln -s' - fi -elif ln conf$$.file conf$$ 2>/dev/null; then - as_ln_s=ln -else - as_ln_s='cp -p' -fi -rm -f conf$$ conf$$.exe conf$$.file - -if mkdir -p . 2>/dev/null; then - as_mkdir_p=: -else - as_mkdir_p=false -fi - -as_executable_p="test -f" - -# Sed expression to map a string onto a valid CPP name. -as_tr_cpp="sed y%*$as_cr_letters%P$as_cr_LETTERS%;s%[^_$as_cr_alnum]%_%g" - -# Sed expression to map a string onto a valid variable name. -as_tr_sh="sed y%*+%pp%;s%[^_$as_cr_alnum]%_%g" - - -# IFS -# We need space, tab and new line, in precisely that order. -as_nl=' -' -IFS=" $as_nl" - -# CDPATH. -$as_unset CDPATH - - -# Find the correct PATH separator. Usually this is `:', but -# DJGPP uses `;' like DOS. -if test "X${PATH_SEPARATOR+set}" != Xset; then - UNAME=${UNAME-`uname 2>/dev/null`} - case X$UNAME in - *-DOS) lt_cv_sys_path_separator=';' ;; - *) lt_cv_sys_path_separator=':' ;; - esac -fi - - -# Check that we are running under the correct shell. -SHELL=${CONFIG_SHELL-/bin/sh} - -case X$ECHO in -X*--fallback-echo) - # Remove one level of quotation (which was required for Make). - ECHO=`echo "$ECHO" | sed 's,\\\\\$\\$0,'$0','` - ;; -esac - -echo=${ECHO-echo} -if test "X$1" = X--no-reexec; then - # Discard the --no-reexec flag, and continue. - shift -elif test "X$1" = X--fallback-echo; then - # Avoid inline document here, it may be left over - : -elif test "X`($echo '\t') 2>/dev/null`" = 'X\t'; then - # Yippee, $echo works! - : -else - # Restart under the correct shell. - exec $SHELL "$0" --no-reexec ${1+"$@"} -fi - -if test "X$1" = X--fallback-echo; then - # used as fallback echo - shift - cat <<EOF - -EOF - exit 0 -fi - -# The HP-UX ksh and POSIX shell print the target directory to stdout -# if CDPATH is set. -if test "X${CDPATH+set}" = Xset; then CDPATH=:; export CDPATH; fi - -if test -z "$ECHO"; then -if test "X${echo_test_string+set}" != Xset; then -# find a string as large as possible, as long as the shell can cope with it - for cmd in 'sed 50q "$0"' 'sed 20q "$0"' 'sed 10q "$0"' 'sed 2q "$0"' 'echo test'; do - # expected sizes: less than 2Kb, 1Kb, 512 bytes, 16 bytes, ... - if (echo_test_string="`eval $cmd`") 2>/dev/null && - echo_test_string="`eval $cmd`" && - (test "X$echo_test_string" = "X$echo_test_string") 2>/dev/null - then - break - fi - done -fi - -if test "X`($echo '\t') 2>/dev/null`" = 'X\t' && - echo_testing_string=`($echo "$echo_test_string") 2>/dev/null` && - test "X$echo_testing_string" = "X$echo_test_string"; then - : -else - # The Solaris, AIX, and Digital Unix default echo programs unquote - # backslashes. This makes it impossible to quote backslashes using - # echo "$something" | sed 's/\\/\\\\/g' - # - # So, first we look for a working echo in the user's PATH. - - IFS="${IFS= }"; save_ifs="$IFS"; IFS="${IFS}${PATH_SEPARATOR}" - for dir in $PATH /usr/ucb; do - if (test -f $dir/echo || test -f $dir/echo$ac_exeext) && - test "X`($dir/echo '\t') 2>/dev/null`" = 'X\t' && - echo_testing_string=`($dir/echo "$echo_test_string") 2>/dev/null` && - test "X$echo_testing_string" = "X$echo_test_string"; then - echo="$dir/echo" - break - fi - done - IFS="$save_ifs" - - if test "X$echo" = Xecho; then - # We didn't find a better echo, so look for alternatives. - if test "X`(print -r '\t') 2>/dev/null`" = 'X\t' && - echo_testing_string=`(print -r "$echo_test_string") 2>/dev/null` && - test "X$echo_testing_string" = "X$echo_test_string"; then - # This shell has a builtin print -r that does the trick. - echo='print -r' - elif (test -f /bin/ksh || test -f /bin/ksh$ac_exeext) && - test "X$CONFIG_SHELL" != X/bin/ksh; then - # If we have ksh, try running configure again with it. - ORIGINAL_CONFIG_SHELL=${CONFIG_SHELL-/bin/sh} - export ORIGINAL_CONFIG_SHELL - CONFIG_SHELL=/bin/ksh - export CONFIG_SHELL - exec $CONFIG_SHELL "$0" --no-reexec ${1+"$@"} - else - # Try using printf. - echo='printf %s\n' - if test "X`($echo '\t') 2>/dev/null`" = 'X\t' && - echo_testing_string=`($echo "$echo_test_string") 2>/dev/null` && - test "X$echo_testing_string" = "X$echo_test_string"; then - # Cool, printf works - : - elif echo_testing_string=`($ORIGINAL_CONFIG_SHELL "$0" --fallback-echo '\t') 2>/dev/null` && - test "X$echo_testing_string" = 'X\t' && - echo_testing_string=`($ORIGINAL_CONFIG_SHELL "$0" --fallback-echo "$echo_test_string") 2>/dev/null` && - test "X$echo_testing_string" = "X$echo_test_string"; then - CONFIG_SHELL=$ORIGINAL_CONFIG_SHELL - export CONFIG_SHELL - SHELL="$CONFIG_SHELL" - export SHELL - echo="$CONFIG_SHELL $0 --fallback-echo" - elif echo_testing_string=`($CONFIG_SHELL "$0" --fallback-echo '\t') 2>/dev/null` && - test "X$echo_testing_string" = 'X\t' && - echo_testing_string=`($CONFIG_SHELL "$0" --fallback-echo "$echo_test_string") 2>/dev/null` && - test "X$echo_testing_string" = "X$echo_test_string"; then - echo="$CONFIG_SHELL $0 --fallback-echo" - else - # maybe with a smaller string... - prev=: - - for cmd in 'echo test' 'sed 2q "$0"' 'sed 10q "$0"' 'sed 20q "$0"' 'sed 50q "$0"'; do - if (test "X$echo_test_string" = "X`eval $cmd`") 2>/dev/null - then - break - fi - prev="$cmd" - done - - if test "$prev" != 'sed 50q "$0"'; then - echo_test_string=`eval $prev` - export echo_test_string - exec ${ORIGINAL_CONFIG_SHELL-${CONFIG_SHELL-/bin/sh}} "$0" ${1+"$@"} - else - # Oops. We lost completely, so just stick with echo. - echo=echo - fi - fi - fi - fi -fi -fi - -# Copy echo and quote the copy suitably for passing to libtool from -# the Makefile, instead of quoting the original, which is used later. -ECHO=$echo -if test "X$ECHO" = "X$CONFIG_SHELL $0 --fallback-echo"; then - ECHO="$CONFIG_SHELL \\\$\$0 --fallback-echo" -fi - - - -# Name of the host. -# hostname on some systems (SVR3.2, Linux) returns a bogus exit status, -# so uname gets run too. -ac_hostname=`(hostname || uname -n) 2>/dev/null | sed 1q` - -exec 6>&1 - -# -# Initializations. -# -ac_default_prefix=/usr/local -ac_config_libobj_dir=. -cross_compiling=no -subdirs= -MFLAGS= -MAKEFLAGS= -SHELL=${CONFIG_SHELL-/bin/sh} - -# Maximum number of lines to put in a shell here document. -# This variable seems obsolete. It should probably be removed, and -# only ac_max_sed_lines should be used. -: ${ac_max_here_lines=38} - -# Identity of this package. -PACKAGE_NAME= -PACKAGE_TARNAME= -PACKAGE_VERSION= -PACKAGE_STRING= -PACKAGE_BUGREPORT= - -ac_unique_file="dftables.c" -# Factoring default headers for most tests. -ac_includes_default="\ -#include <stdio.h> -#if HAVE_SYS_TYPES_H -# include <sys/types.h> -#endif -#if HAVE_SYS_STAT_H -# include <sys/stat.h> -#endif -#if STDC_HEADERS -# include <stdlib.h> -# include <stddef.h> -#else -# if HAVE_STDLIB_H -# include <stdlib.h> -# endif -#endif -#if HAVE_STRING_H -# if !STDC_HEADERS && HAVE_MEMORY_H -# include <memory.h> -# endif -# include <string.h> -#endif -#if HAVE_STRINGS_H -# include <strings.h> -#endif -#if HAVE_INTTYPES_H -# include <inttypes.h> -#else -# if HAVE_STDINT_H -# include <stdint.h> -# endif -#endif -#if HAVE_UNISTD_H -# include <unistd.h> -#endif" - -ac_subst_vars='SHELL PATH_SEPARATOR PACKAGE_NAME PACKAGE_TARNAME PACKAGE_VERSION PACKAGE_STRING PACKAGE_BUGREPORT exec_prefix prefix program_transform_name bindir sbindir libexecdir datadir sysconfdir sharedstatedir localstatedir libdir includedir oldincludedir infodir mandir build_alias host_alias target_alias DEFS ECHO_C ECHO_N ECHO_T LIBS CC CFLAGS LDFLAGS CPPFLAGS ac_ct_CC EXEEXT OBJEXT INSTALL_PROGRAM INSTALL_SCRIPT INSTALL_DATA build build_cpu build_vendor build_os host host_cpu host_vendor host_os LN_S ECHO RANLIB ac_ct_RANLIB STRIP ac_ct_STRIP CPP EGREP LIBTOOL BUILD_EXEEXT BUILD_OBJEXT CC_FOR_BUILD CFLAGS_FOR_BUILD EBCDIC HAVE_MEMMOVE HAVE_STRERROR LINK_SIZE MATCH_LIMIT NEWLINE NO_RECURSE PCRE_MAJOR PCRE_MINOR PCRE_DATE PCRE_VERSION PCRE_LIB_VERSION PCRE_POSIXLIB_VERSION POSIX_MALLOC_THRESHOLD UTF8 WIN_PREFIX ON_WINDOWS NOT_ON_WINDOWS POSIX_OBJ POSIX_LOBJ POSIX_LIB LIBOBJS LTLIBOBJS' -ac_subst_files='' - -# Initialize some variables set by options. -ac_init_help= -ac_init_version=false -# The variables have the same names as the options, with -# dashes changed to underlines. -cache_file=/dev/null -exec_prefix=NONE -no_create= -no_recursion= -prefix=NONE -program_prefix=NONE -program_suffix=NONE -program_transform_name=s,x,x, -silent= -site= -srcdir= -verbose= -x_includes=NONE -x_libraries=NONE - -# Installation directory options. -# These are left unexpanded so users can "make install exec_prefix=/foo" -# and all the variables that are supposed to be based on exec_prefix -# by default will actually change. -# Use braces instead of parens because sh, perl, etc. also accept them. -bindir='${exec_prefix}/bin' -sbindir='${exec_prefix}/sbin' -libexecdir='${exec_prefix}/libexec' -datadir='${prefix}/share' -sysconfdir='${prefix}/etc' -sharedstatedir='${prefix}/com' -localstatedir='${prefix}/var' -libdir='${exec_prefix}/lib' -includedir='${prefix}/include' -oldincludedir='/usr/include' -infodir='${prefix}/info' -mandir='${prefix}/man' - -ac_prev= -for ac_option -do - # If the previous option needs an argument, assign it. - if test -n "$ac_prev"; then - eval "$ac_prev=\$ac_option" - ac_prev= - continue - fi - - ac_optarg=`expr "x$ac_option" : 'x[^=]*=\(.*\)'` - - # Accept the important Cygnus configure options, so we can diagnose typos. - - case $ac_option in - - -bindir | --bindir | --bindi | --bind | --bin | --bi) - ac_prev=bindir ;; - -bindir=* | --bindir=* | --bindi=* | --bind=* | --bin=* | --bi=*) - bindir=$ac_optarg ;; - - -build | --build | --buil | --bui | --bu) - ac_prev=build_alias ;; - -build=* | --build=* | --buil=* | --bui=* | --bu=*) - build_alias=$ac_optarg ;; - - -cache-file | --cache-file | --cache-fil | --cache-fi \ - | --cache-f | --cache- | --cache | --cach | --cac | --ca | --c) - ac_prev=cache_file ;; - -cache-file=* | --cache-file=* | --cache-fil=* | --cache-fi=* \ - | --cache-f=* | --cache-=* | --cache=* | --cach=* | --cac=* | --ca=* | --c=*) - cache_file=$ac_optarg ;; - - --config-cache | -C) - cache_file=config.cache ;; - - -datadir | --datadir | --datadi | --datad | --data | --dat | --da) - ac_prev=datadir ;; - -datadir=* | --datadir=* | --datadi=* | --datad=* | --data=* | --dat=* \ - | --da=*) - datadir=$ac_optarg ;; - - -disable-* | --disable-*) - ac_feature=`expr "x$ac_option" : 'x-*disable-\(.*\)'` - # Reject names that are not valid shell variable names. - expr "x$ac_feature" : ".*[^-_$as_cr_alnum]" >/dev/null && - { echo "$as_me: error: invalid feature name: $ac_feature" >&2 - { (exit 1); exit 1; }; } - ac_feature=`echo $ac_feature | sed 's/-/_/g'` - eval "enable_$ac_feature=no" ;; - - -enable-* | --enable-*) - ac_feature=`expr "x$ac_option" : 'x-*enable-\([^=]*\)'` - # Reject names that are not valid shell variable names. - expr "x$ac_feature" : ".*[^-_$as_cr_alnum]" >/dev/null && - { echo "$as_me: error: invalid feature name: $ac_feature" >&2 - { (exit 1); exit 1; }; } - ac_feature=`echo $ac_feature | sed 's/-/_/g'` - case $ac_option in - *=*) ac_optarg=`echo "$ac_optarg" | sed "s/'/'\\\\\\\\''/g"`;; - *) ac_optarg=yes ;; - esac - eval "enable_$ac_feature='$ac_optarg'" ;; - - -exec-prefix | --exec_prefix | --exec-prefix | --exec-prefi \ - | --exec-pref | --exec-pre | --exec-pr | --exec-p | --exec- \ - | --exec | --exe | --ex) - ac_prev=exec_prefix ;; - -exec-prefix=* | --exec_prefix=* | --exec-prefix=* | --exec-prefi=* \ - | --exec-pref=* | --exec-pre=* | --exec-pr=* | --exec-p=* | --exec-=* \ - | --exec=* | --exe=* | --ex=*) - exec_prefix=$ac_optarg ;; - - -gas | --gas | --ga | --g) - # Obsolete; use --with-gas. - with_gas=yes ;; - - -help | --help | --hel | --he | -h) - ac_init_help=long ;; - -help=r* | --help=r* | --hel=r* | --he=r* | -hr*) - ac_init_help=recursive ;; - -help=s* | --help=s* | --hel=s* | --he=s* | -hs*) - ac_init_help=short ;; - - -host | --host | --hos | --ho) - ac_prev=host_alias ;; - -host=* | --host=* | --hos=* | --ho=*) - host_alias=$ac_optarg ;; - - -includedir | --includedir | --includedi | --included | --include \ - | --includ | --inclu | --incl | --inc) - ac_prev=includedir ;; - -includedir=* | --includedir=* | --includedi=* | --included=* | --include=* \ - | --includ=* | --inclu=* | --incl=* | --inc=*) - includedir=$ac_optarg ;; - - -infodir | --infodir | --infodi | --infod | --info | --inf) - ac_prev=infodir ;; - -infodir=* | --infodir=* | --infodi=* | --infod=* | --info=* | --inf=*) - infodir=$ac_optarg ;; - - -libdir | --libdir | --libdi | --libd) - ac_prev=libdir ;; - -libdir=* | --libdir=* | --libdi=* | --libd=*) - libdir=$ac_optarg ;; - - -libexecdir | --libexecdir | --libexecdi | --libexecd | --libexec \ - | --libexe | --libex | --libe) - ac_prev=libexecdir ;; - -libexecdir=* | --libexecdir=* | --libexecdi=* | --libexecd=* | --libexec=* \ - | --libexe=* | --libex=* | --libe=*) - libexecdir=$ac_optarg ;; - - -localstatedir | --localstatedir | --localstatedi | --localstated \ - | --localstate | --localstat | --localsta | --localst \ - | --locals | --local | --loca | --loc | --lo) - ac_prev=localstatedir ;; - -localstatedir=* | --localstatedir=* | --localstatedi=* | --localstated=* \ - | --localstate=* | --localstat=* | --localsta=* | --localst=* \ - | --locals=* | --local=* | --loca=* | --loc=* | --lo=*) - localstatedir=$ac_optarg ;; - - -mandir | --mandir | --mandi | --mand | --man | --ma | --m) - ac_prev=mandir ;; - -mandir=* | --mandir=* | --mandi=* | --mand=* | --man=* | --ma=* | --m=*) - mandir=$ac_optarg ;; - - -nfp | --nfp | --nf) - # Obsolete; use --without-fp. - with_fp=no ;; - - -no-create | --no-create | --no-creat | --no-crea | --no-cre \ - | --no-cr | --no-c | -n) - no_create=yes ;; - - -no-recursion | --no-recursion | --no-recursio | --no-recursi \ - | --no-recurs | --no-recur | --no-recu | --no-rec | --no-re | --no-r) - no_recursion=yes ;; - - -oldincludedir | --oldincludedir | --oldincludedi | --oldincluded \ - | --oldinclude | --oldinclud | --oldinclu | --oldincl | --oldinc \ - | --oldin | --oldi | --old | --ol | --o) - ac_prev=oldincludedir ;; - -oldincludedir=* | --oldincludedir=* | --oldincludedi=* | --oldincluded=* \ - | --oldinclude=* | --oldinclud=* | --oldinclu=* | --oldincl=* | --oldinc=* \ - | --oldin=* | --oldi=* | --old=* | --ol=* | --o=*) - oldincludedir=$ac_optarg ;; - - -prefix | --prefix | --prefi | --pref | --pre | --pr | --p) - ac_prev=prefix ;; - -prefix=* | --prefix=* | --prefi=* | --pref=* | --pre=* | --pr=* | --p=*) - prefix=$ac_optarg ;; - - -program-prefix | --program-prefix | --program-prefi | --program-pref \ - | --program-pre | --program-pr | --program-p) - ac_prev=program_prefix ;; - -program-prefix=* | --program-prefix=* | --program-prefi=* \ - | --program-pref=* | --program-pre=* | --program-pr=* | --program-p=*) - program_prefix=$ac_optarg ;; - - -program-suffix | --program-suffix | --program-suffi | --program-suff \ - | --program-suf | --program-su | --program-s) - ac_prev=program_suffix ;; - -program-suffix=* | --program-suffix=* | --program-suffi=* \ - | --program-suff=* | --program-suf=* | --program-su=* | --program-s=*) - program_suffix=$ac_optarg ;; - - -program-transform-name | --program-transform-name \ - | --program-transform-nam | --program-transform-na \ - | --program-transform-n | --program-transform- \ - | --program-transform | --program-transfor \ - | --program-transfo | --program-transf \ - | --program-trans | --program-tran \ - | --progr-tra | --program-tr | --program-t) - ac_prev=program_transform_name ;; - -program-transform-name=* | --program-transform-name=* \ - | --program-transform-nam=* | --program-transform-na=* \ - | --program-transform-n=* | --program-transform-=* \ - | --program-transform=* | --program-transfor=* \ - | --program-transfo=* | --program-transf=* \ - | --program-trans=* | --program-tran=* \ - | --progr-tra=* | --program-tr=* | --program-t=*) - program_transform_name=$ac_optarg ;; - - -q | -quiet | --quiet | --quie | --qui | --qu | --q \ - | -silent | --silent | --silen | --sile | --sil) - silent=yes ;; - - -sbindir | --sbindir | --sbindi | --sbind | --sbin | --sbi | --sb) - ac_prev=sbindir ;; - -sbindir=* | --sbindir=* | --sbindi=* | --sbind=* | --sbin=* \ - | --sbi=* | --sb=*) - sbindir=$ac_optarg ;; - - -sharedstatedir | --sharedstatedir | --sharedstatedi \ - | --sharedstated | --sharedstate | --sharedstat | --sharedsta \ - | --sharedst | --shareds | --shared | --share | --shar \ - | --sha | --sh) - ac_prev=sharedstatedir ;; - -sharedstatedir=* | --sharedstatedir=* | --sharedstatedi=* \ - | --sharedstated=* | --sharedstate=* | --sharedstat=* | --sharedsta=* \ - | --sharedst=* | --shareds=* | --shared=* | --share=* | --shar=* \ - | --sha=* | --sh=*) - sharedstatedir=$ac_optarg ;; - - -site | --site | --sit) - ac_prev=site ;; - -site=* | --site=* | --sit=*) - site=$ac_optarg ;; - - -srcdir | --srcdir | --srcdi | --srcd | --src | --sr) - ac_prev=srcdir ;; - -srcdir=* | --srcdir=* | --srcdi=* | --srcd=* | --src=* | --sr=*) - srcdir=$ac_optarg ;; - - -sysconfdir | --sysconfdir | --sysconfdi | --sysconfd | --sysconf \ - | --syscon | --sysco | --sysc | --sys | --sy) - ac_prev=sysconfdir ;; - -sysconfdir=* | --sysconfdir=* | --sysconfdi=* | --sysconfd=* | --sysconf=* \ - | --syscon=* | --sysco=* | --sysc=* | --sys=* | --sy=*) - sysconfdir=$ac_optarg ;; - - -target | --target | --targe | --targ | --tar | --ta | --t) - ac_prev=target_alias ;; - -target=* | --target=* | --targe=* | --targ=* | --tar=* | --ta=* | --t=*) - target_alias=$ac_optarg ;; - - -v | -verbose | --verbose | --verbos | --verbo | --verb) - verbose=yes ;; - - -version | --version | --versio | --versi | --vers | -V) - ac_init_version=: ;; - - -with-* | --with-*) - ac_package=`expr "x$ac_option" : 'x-*with-\([^=]*\)'` - # Reject names that are not valid shell variable names. - expr "x$ac_package" : ".*[^-_$as_cr_alnum]" >/dev/null && - { echo "$as_me: error: invalid package name: $ac_package" >&2 - { (exit 1); exit 1; }; } - ac_package=`echo $ac_package| sed 's/-/_/g'` - case $ac_option in - *=*) ac_optarg=`echo "$ac_optarg" | sed "s/'/'\\\\\\\\''/g"`;; - *) ac_optarg=yes ;; - esac - eval "with_$ac_package='$ac_optarg'" ;; - - -without-* | --without-*) - ac_package=`expr "x$ac_option" : 'x-*without-\(.*\)'` - # Reject names that are not valid shell variable names. - expr "x$ac_package" : ".*[^-_$as_cr_alnum]" >/dev/null && - { echo "$as_me: error: invalid package name: $ac_package" >&2 - { (exit 1); exit 1; }; } - ac_package=`echo $ac_package | sed 's/-/_/g'` - eval "with_$ac_package=no" ;; - - --x) - # Obsolete; use --with-x. - with_x=yes ;; - - -x-includes | --x-includes | --x-include | --x-includ | --x-inclu \ - | --x-incl | --x-inc | --x-in | --x-i) - ac_prev=x_includes ;; - -x-includes=* | --x-includes=* | --x-include=* | --x-includ=* | --x-inclu=* \ - | --x-incl=* | --x-inc=* | --x-in=* | --x-i=*) - x_includes=$ac_optarg ;; - - -x-libraries | --x-libraries | --x-librarie | --x-librari \ - | --x-librar | --x-libra | --x-libr | --x-lib | --x-li | --x-l) - ac_prev=x_libraries ;; - -x-libraries=* | --x-libraries=* | --x-librarie=* | --x-librari=* \ - | --x-librar=* | --x-libra=* | --x-libr=* | --x-lib=* | --x-li=* | --x-l=*) - x_libraries=$ac_optarg ;; - - -*) { echo "$as_me: error: unrecognized option: $ac_option -Try \`$0 --help' for more information." >&2 - { (exit 1); exit 1; }; } - ;; - - *=*) - ac_envvar=`expr "x$ac_option" : 'x\([^=]*\)='` - # Reject names that are not valid shell variable names. - expr "x$ac_envvar" : ".*[^_$as_cr_alnum]" >/dev/null && - { echo "$as_me: error: invalid variable name: $ac_envvar" >&2 - { (exit 1); exit 1; }; } - ac_optarg=`echo "$ac_optarg" | sed "s/'/'\\\\\\\\''/g"` - eval "$ac_envvar='$ac_optarg'" - export $ac_envvar ;; - - *) - # FIXME: should be removed in autoconf 3.0. - echo "$as_me: WARNING: you should use --build, --host, --target" >&2 - expr "x$ac_option" : ".*[^-._$as_cr_alnum]" >/dev/null && - echo "$as_me: WARNING: invalid host type: $ac_option" >&2 - : ${build_alias=$ac_option} ${host_alias=$ac_option} ${target_alias=$ac_option} - ;; - - esac -done - -if test -n "$ac_prev"; then - ac_option=--`echo $ac_prev | sed 's/_/-/g'` - { echo "$as_me: error: missing argument to $ac_option" >&2 - { (exit 1); exit 1; }; } -fi - -# Be sure to have absolute paths. -for ac_var in exec_prefix prefix -do - eval ac_val=$`echo $ac_var` - case $ac_val in - [\\/$]* | ?:[\\/]* | NONE | '' ) ;; - *) { echo "$as_me: error: expected an absolute directory name for --$ac_var: $ac_val" >&2 - { (exit 1); exit 1; }; };; - esac -done - -# Be sure to have absolute paths. -for ac_var in bindir sbindir libexecdir datadir sysconfdir sharedstatedir \ - localstatedir libdir includedir oldincludedir infodir mandir -do - eval ac_val=$`echo $ac_var` - case $ac_val in - [\\/$]* | ?:[\\/]* ) ;; - *) { echo "$as_me: error: expected an absolute directory name for --$ac_var: $ac_val" >&2 - { (exit 1); exit 1; }; };; - esac -done - -# There might be people who depend on the old broken behavior: `$host' -# used to hold the argument of --host etc. -# FIXME: To remove some day. -build=$build_alias -host=$host_alias -target=$target_alias - -# FIXME: To remove some day. -if test "x$host_alias" != x; then - if test "x$build_alias" = x; then - cross_compiling=maybe - echo "$as_me: WARNING: If you wanted to set the --build type, don't use --host. - If a cross compiler is detected then cross compile mode will be used." >&2 - elif test "x$build_alias" != "x$host_alias"; then - cross_compiling=yes - fi -fi - -ac_tool_prefix= -test -n "$host_alias" && ac_tool_prefix=$host_alias- - -test "$silent" = yes && exec 6>/dev/null - - -# Find the source files, if location was not specified. -if test -z "$srcdir"; then - ac_srcdir_defaulted=yes - # Try the directory containing this script, then its parent. - ac_confdir=`(dirname "$0") 2>/dev/null || -$as_expr X"$0" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ - X"$0" : 'X\(//\)[^/]' \| \ - X"$0" : 'X\(//\)$' \| \ - X"$0" : 'X\(/\)' \| \ - . : '\(.\)' 2>/dev/null || -echo X"$0" | - sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } - /^X\(\/\/\)[^/].*/{ s//\1/; q; } - /^X\(\/\/\)$/{ s//\1/; q; } - /^X\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` - srcdir=$ac_confdir - if test ! -r $srcdir/$ac_unique_file; then - srcdir=.. - fi -else - ac_srcdir_defaulted=no -fi -if test ! -r $srcdir/$ac_unique_file; then - if test "$ac_srcdir_defaulted" = yes; then - { echo "$as_me: error: cannot find sources ($ac_unique_file) in $ac_confdir or .." >&2 - { (exit 1); exit 1; }; } - else - { echo "$as_me: error: cannot find sources ($ac_unique_file) in $srcdir" >&2 - { (exit 1); exit 1; }; } - fi -fi -(cd $srcdir && test -r ./$ac_unique_file) 2>/dev/null || - { echo "$as_me: error: sources are in $srcdir, but \`cd $srcdir' does not work" >&2 - { (exit 1); exit 1; }; } -srcdir=`echo "$srcdir" | sed 's%\([^\\/]\)[\\/]*$%\1%'` -ac_env_build_alias_set=${build_alias+set} -ac_env_build_alias_value=$build_alias -ac_cv_env_build_alias_set=${build_alias+set} -ac_cv_env_build_alias_value=$build_alias -ac_env_host_alias_set=${host_alias+set} -ac_env_host_alias_value=$host_alias -ac_cv_env_host_alias_set=${host_alias+set} -ac_cv_env_host_alias_value=$host_alias -ac_env_target_alias_set=${target_alias+set} -ac_env_target_alias_value=$target_alias -ac_cv_env_target_alias_set=${target_alias+set} -ac_cv_env_target_alias_value=$target_alias -ac_env_CC_set=${CC+set} -ac_env_CC_value=$CC -ac_cv_env_CC_set=${CC+set} -ac_cv_env_CC_value=$CC -ac_env_CFLAGS_set=${CFLAGS+set} -ac_env_CFLAGS_value=$CFLAGS -ac_cv_env_CFLAGS_set=${CFLAGS+set} -ac_cv_env_CFLAGS_value=$CFLAGS -ac_env_LDFLAGS_set=${LDFLAGS+set} -ac_env_LDFLAGS_value=$LDFLAGS -ac_cv_env_LDFLAGS_set=${LDFLAGS+set} -ac_cv_env_LDFLAGS_value=$LDFLAGS -ac_env_CPPFLAGS_set=${CPPFLAGS+set} -ac_env_CPPFLAGS_value=$CPPFLAGS -ac_cv_env_CPPFLAGS_set=${CPPFLAGS+set} -ac_cv_env_CPPFLAGS_value=$CPPFLAGS -ac_env_CPP_set=${CPP+set} -ac_env_CPP_value=$CPP -ac_cv_env_CPP_set=${CPP+set} -ac_cv_env_CPP_value=$CPP - -# -# Report the --help message. -# -if test "$ac_init_help" = "long"; then - # Omit some internal or obsolete options to make the list less imposing. - # The list generated by autoconf has been trimmed to remove many - # options that are totally irrelevant to PCRE (e.g. relating to X), - # or are not supported by its Makefile. - # The list generated by autoconf has been trimmed to remove many - # options that are totally irrelevant to PCRE (e.g. relating to X), - # or are not supported by its Makefile. - # The list generated by autoconf has been trimmed to remove many - # options that are totally irrelevant to PCRE (e.g. relating to X), - # or are not supported by its Makefile. - # This message is too long to be a string in the A/UX 3.1 sh. - cat <<_ACEOF -\`configure' configures this package to adapt to many kinds of systems. - -Usage: $0 [OPTION]... [VAR=VALUE]... - -To assign environment variables (e.g., CC, CFLAGS...), specify them as -VAR=VALUE. See below for descriptions of some of the useful variables. - -Defaults for the options are specified in brackets. - -Configuration: - -h, --help display this help and exit - --help=short display options specific to this package - --help=recursive display the short help of all the included packages - -V, --version display version information and exit - -q, --quiet, --silent do not print \`checking...' messages - --cache-file=FILE cache test results in FILE [disabled] - -C, --config-cache alias for \`--cache-file=config.cache' - -n, --no-create do not create output files - --srcdir=DIR find the sources in DIR [configure dir or \`..'] - -_ACEOF - - cat <<_ACEOF -Installation directories: - --prefix=PREFIX install architecture-independent files in PREFIX - [$ac_default_prefix] - --exec-prefix=EPREFIX install architecture-dependent files in EPREFIX - [PREFIX] - -By default, \`make install' will install all the files in -\`$ac_default_prefix/bin', \`$ac_default_prefix/lib' etc. You can specify -an installation prefix other than \`$ac_default_prefix' using \`--prefix', -for instance \`--prefix=\$HOME'. - -For better control, use the options below. - -Fine tuning of the installation directories: - --bindir=DIR user executables [EPREFIX/bin] - --libdir=DIR object code libraries [EPREFIX/lib] - --includedir=DIR C header files [PREFIX/include] - --mandir=DIR man documentation [PREFIX/man] -_ACEOF - - cat <<\_ACEOF - -_ACEOF -fi - -if test -n "$ac_init_help"; then - - cat <<\_ACEOF - -Optional Features: - --disable-FEATURE do not include FEATURE (same as --enable-FEATURE=no) - --enable-FEATURE[=ARG] include FEATURE [ARG=yes] - --enable-shared build shared libraries default=yes - --enable-static build static libraries default=yes - --enable-fast-install optimize for fast installation default=yes - --disable-libtool-lock avoid locking (might break parallel builds) - --enable-utf8 enable UTF8 support - --enable-newline-is-cr use CR as the newline character - --enable-newline-is-lf use LF as the newline character - --enable-ebcdic assume EBCDIC coding rather than ASCII - --disable-stack-for-recursion disable use of stack recursion when matching - -Optional Packages: - --with-gnu-ld assume the C compiler uses GNU ld default=no - --with-pic try to use only PIC/non-PIC objects default=use both - --with-posix-malloc-threshold=5 threshold for POSIX malloc usage - --with-link-size=2 internal link size (2, 3, or 4 allowed) - --with-match-limit=10000000 default limit on internal looping) - -Some influential environment variables: - CC C compiler command - CFLAGS C compiler flags - LDFLAGS linker flags, e.g. -L<lib dir> if you have libraries in a - nonstandard directory <lib dir> - CPPFLAGS C/C++ preprocessor flags, e.g. -I<include dir> if you have - headers in a nonstandard directory <include dir> - CPP C preprocessor - -Use these variables to override the choices made by `configure' or to help -it to find libraries and programs with nonstandard names/locations. - -_ACEOF -fi - -if test "$ac_init_help" = "recursive"; then - # If there are subdirs, report their specific --help. - ac_popdir=`pwd` - for ac_dir in : $ac_subdirs_all; do test "x$ac_dir" = x: && continue - test -d $ac_dir || continue - ac_builddir=. - -if test "$ac_dir" != .; then - ac_dir_suffix=/`echo "$ac_dir" | sed 's,^\.[\\/],,'` - # A "../" for each directory in $ac_dir_suffix. - ac_top_builddir=`echo "$ac_dir_suffix" | sed 's,/[^\\/]*,../,g'` -else - ac_dir_suffix= ac_top_builddir= -fi - -case $srcdir in - .) # No --srcdir option. We are building in place. - ac_srcdir=. - if test -z "$ac_top_builddir"; then - ac_top_srcdir=. - else - ac_top_srcdir=`echo $ac_top_builddir | sed 's,/$,,'` - fi ;; - [\\/]* | ?:[\\/]* ) # Absolute path. - ac_srcdir=$srcdir$ac_dir_suffix; - ac_top_srcdir=$srcdir ;; - *) # Relative path. - ac_srcdir=$ac_top_builddir$srcdir$ac_dir_suffix - ac_top_srcdir=$ac_top_builddir$srcdir ;; -esac -# Don't blindly perform a `cd "$ac_dir"/$ac_foo && pwd` since $ac_foo can be -# absolute. -ac_abs_builddir=`cd "$ac_dir" && cd $ac_builddir && pwd` -ac_abs_top_builddir=`cd "$ac_dir" && cd ${ac_top_builddir}. && pwd` -ac_abs_srcdir=`cd "$ac_dir" && cd $ac_srcdir && pwd` -ac_abs_top_srcdir=`cd "$ac_dir" && cd $ac_top_srcdir && pwd` - - cd $ac_dir - # Check for guested configure; otherwise get Cygnus style configure. - if test -f $ac_srcdir/configure.gnu; then - echo - $SHELL $ac_srcdir/configure.gnu --help=recursive - elif test -f $ac_srcdir/configure; then - echo - $SHELL $ac_srcdir/configure --help=recursive - elif test -f $ac_srcdir/configure.ac || - test -f $ac_srcdir/configure.in; then - echo - $ac_configure --help - else - echo "$as_me: WARNING: no configuration information is in $ac_dir" >&2 - fi - cd $ac_popdir - done -fi - -test -n "$ac_init_help" && exit 0 -if $ac_init_version; then - cat <<\_ACEOF - -Copyright 1992, 1993, 1994, 1995, 1996, 1998, 1999, 2000, 2001, 2002 -Free Software Foundation, Inc. -This configure script is free software; the Free Software Foundation -gives unlimited permission to copy, distribute and modify it. -_ACEOF - exit 0 -fi -exec 5>config.log -cat >&5 <<_ACEOF -This file contains any messages produced by compilers while -running configure, to aid debugging if configure makes a mistake. - -It was created by $as_me, which was -generated by GNU Autoconf 2.57. Invocation command line was - - $ $0 $@ - -_ACEOF -{ -cat <<_ASUNAME -## --------- ## -## Platform. ## -## --------- ## - -hostname = `(hostname || uname -n) 2>/dev/null | sed 1q` -uname -m = `(uname -m) 2>/dev/null || echo unknown` -uname -r = `(uname -r) 2>/dev/null || echo unknown` -uname -s = `(uname -s) 2>/dev/null || echo unknown` -uname -v = `(uname -v) 2>/dev/null || echo unknown` - -/usr/bin/uname -p = `(/usr/bin/uname -p) 2>/dev/null || echo unknown` -/bin/uname -X = `(/bin/uname -X) 2>/dev/null || echo unknown` - -/bin/arch = `(/bin/arch) 2>/dev/null || echo unknown` -/usr/bin/arch -k = `(/usr/bin/arch -k) 2>/dev/null || echo unknown` -/usr/convex/getsysinfo = `(/usr/convex/getsysinfo) 2>/dev/null || echo unknown` -hostinfo = `(hostinfo) 2>/dev/null || echo unknown` -/bin/machine = `(/bin/machine) 2>/dev/null || echo unknown` -/usr/bin/oslevel = `(/usr/bin/oslevel) 2>/dev/null || echo unknown` -/bin/universe = `(/bin/universe) 2>/dev/null || echo unknown` - -_ASUNAME - -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - echo "PATH: $as_dir" -done - -} >&5 - -cat >&5 <<_ACEOF - - -## ----------- ## -## Core tests. ## -## ----------- ## - -_ACEOF - - -# Keep a trace of the command line. -# Strip out --no-create and --no-recursion so they do not pile up. -# Strip out --silent because we don't want to record it for future runs. -# Also quote any args containing shell meta-characters. -# Make two passes to allow for proper duplicate-argument suppression. -ac_configure_args= -ac_configure_args0= -ac_configure_args1= -ac_sep= -ac_must_keep_next=false -for ac_pass in 1 2 -do - for ac_arg - do - case $ac_arg in - -no-create | --no-c* | -n | -no-recursion | --no-r*) continue ;; - -q | -quiet | --quiet | --quie | --qui | --qu | --q \ - | -silent | --silent | --silen | --sile | --sil) - continue ;; - *" "*|*" "*|*[\[\]\~\#\$\^\&\*\(\)\{\}\\\|\;\<\>\?\"\']*) - ac_arg=`echo "$ac_arg" | sed "s/'/'\\\\\\\\''/g"` ;; - esac - case $ac_pass in - 1) ac_configure_args0="$ac_configure_args0 '$ac_arg'" ;; - 2) - ac_configure_args1="$ac_configure_args1 '$ac_arg'" - if test $ac_must_keep_next = true; then - ac_must_keep_next=false # Got value, back to normal. - else - case $ac_arg in - *=* | --config-cache | -C | -disable-* | --disable-* \ - | -enable-* | --enable-* | -gas | --g* | -nfp | --nf* \ - | -q | -quiet | --q* | -silent | --sil* | -v | -verb* \ - | -with-* | --with-* | -without-* | --without-* | --x) - case "$ac_configure_args0 " in - "$ac_configure_args1"*" '$ac_arg' "* ) continue ;; - esac - ;; - -* ) ac_must_keep_next=true ;; - esac - fi - ac_configure_args="$ac_configure_args$ac_sep'$ac_arg'" - # Get rid of the leading space. - ac_sep=" " - ;; - esac - done -done -$as_unset ac_configure_args0 || test "${ac_configure_args0+set}" != set || { ac_configure_args0=; export ac_configure_args0; } -$as_unset ac_configure_args1 || test "${ac_configure_args1+set}" != set || { ac_configure_args1=; export ac_configure_args1; } - -# When interrupted or exit'd, cleanup temporary files, and complete -# config.log. We remove comments because anyway the quotes in there -# would cause problems or look ugly. -# WARNING: Be sure not to use single quotes in there, as some shells, -# such as our DU 5.0 friend, will then `close' the trap. -trap 'exit_status=$? - # Save into config.log some information that might help in debugging. - { - echo - - cat <<\_ASBOX -## ---------------- ## -## Cache variables. ## -## ---------------- ## -_ASBOX - echo - # The following way of writing the cache mishandles newlines in values, -{ - (set) 2>&1 | - case `(ac_space='"'"' '"'"'; set | grep ac_space) 2>&1` in - *ac_space=\ *) - sed -n \ - "s/'"'"'/'"'"'\\\\'"'"''"'"'/g; - s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1='"'"'\\2'"'"'/p" - ;; - *) - sed -n \ - "s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1=\\2/p" - ;; - esac; -} - echo - - cat <<\_ASBOX -## ----------------- ## -## Output variables. ## -## ----------------- ## -_ASBOX - echo - for ac_var in $ac_subst_vars - do - eval ac_val=$`echo $ac_var` - echo "$ac_var='"'"'$ac_val'"'"'" - done | sort - echo - - if test -n "$ac_subst_files"; then - cat <<\_ASBOX -## ------------- ## -## Output files. ## -## ------------- ## -_ASBOX - echo - for ac_var in $ac_subst_files - do - eval ac_val=$`echo $ac_var` - echo "$ac_var='"'"'$ac_val'"'"'" - done | sort - echo - fi - - if test -s confdefs.h; then - cat <<\_ASBOX -## ----------- ## -## confdefs.h. ## -## ----------- ## -_ASBOX - echo - sed "/^$/d" confdefs.h | sort - echo - fi - test "$ac_signal" != 0 && - echo "$as_me: caught signal $ac_signal" - echo "$as_me: exit $exit_status" - } >&5 - rm -f core core.* *.core && - rm -rf conftest* confdefs* conf$$* $ac_clean_files && - exit $exit_status - ' 0 -for ac_signal in 1 2 13 15; do - trap 'ac_signal='$ac_signal'; { (exit 1); exit 1; }' $ac_signal -done -ac_signal=0 - -# confdefs.h avoids OS command line length limits that DEFS can exceed. -rm -rf conftest* confdefs.h -# AIX cpp loses on an empty file, so make sure it contains at least a newline. -echo >confdefs.h - -# Predefined preprocessor variables. - -cat >>confdefs.h <<_ACEOF -#define PACKAGE_NAME "$PACKAGE_NAME" -_ACEOF - - -cat >>confdefs.h <<_ACEOF -#define PACKAGE_TARNAME "$PACKAGE_TARNAME" -_ACEOF - - -cat >>confdefs.h <<_ACEOF -#define PACKAGE_VERSION "$PACKAGE_VERSION" -_ACEOF - - -cat >>confdefs.h <<_ACEOF -#define PACKAGE_STRING "$PACKAGE_STRING" -_ACEOF - - -cat >>confdefs.h <<_ACEOF -#define PACKAGE_BUGREPORT "$PACKAGE_BUGREPORT" -_ACEOF - - -# Let the site file select an alternate cache file if it wants to. -# Prefer explicitly selected file to automatically selected ones. -if test -z "$CONFIG_SITE"; then - if test "x$prefix" != xNONE; then - CONFIG_SITE="$prefix/share/config.site $prefix/etc/config.site" - else - CONFIG_SITE="$ac_default_prefix/share/config.site $ac_default_prefix/etc/config.site" - fi -fi -for ac_site_file in $CONFIG_SITE; do - if test -r "$ac_site_file"; then - { echo "$as_me:$LINENO: loading site script $ac_site_file" >&5 -echo "$as_me: loading site script $ac_site_file" >&6;} - sed 's/^/| /' "$ac_site_file" >&5 - . "$ac_site_file" - fi -done - -if test -r "$cache_file"; then - # Some versions of bash will fail to source /dev/null (special - # files actually), so we avoid doing that. - if test -f "$cache_file"; then - { echo "$as_me:$LINENO: loading cache $cache_file" >&5 -echo "$as_me: loading cache $cache_file" >&6;} - case $cache_file in - [\\/]* | ?:[\\/]* ) . $cache_file;; - *) . ./$cache_file;; - esac - fi -else - { echo "$as_me:$LINENO: creating cache $cache_file" >&5 -echo "$as_me: creating cache $cache_file" >&6;} - >$cache_file -fi - -# Check that the precious variables saved in the cache have kept the same -# value. -ac_cache_corrupted=false -for ac_var in `(set) 2>&1 | - sed -n 's/^ac_env_\([a-zA-Z_0-9]*\)_set=.*/\1/p'`; do - eval ac_old_set=\$ac_cv_env_${ac_var}_set - eval ac_new_set=\$ac_env_${ac_var}_set - eval ac_old_val="\$ac_cv_env_${ac_var}_value" - eval ac_new_val="\$ac_env_${ac_var}_value" - case $ac_old_set,$ac_new_set in - set,) - { echo "$as_me:$LINENO: error: \`$ac_var' was set to \`$ac_old_val' in the previous run" >&5 -echo "$as_me: error: \`$ac_var' was set to \`$ac_old_val' in the previous run" >&2;} - ac_cache_corrupted=: ;; - ,set) - { echo "$as_me:$LINENO: error: \`$ac_var' was not set in the previous run" >&5 -echo "$as_me: error: \`$ac_var' was not set in the previous run" >&2;} - ac_cache_corrupted=: ;; - ,);; - *) - if test "x$ac_old_val" != "x$ac_new_val"; then - { echo "$as_me:$LINENO: error: \`$ac_var' has changed since the previous run:" >&5 -echo "$as_me: error: \`$ac_var' has changed since the previous run:" >&2;} - { echo "$as_me:$LINENO: former value: $ac_old_val" >&5 -echo "$as_me: former value: $ac_old_val" >&2;} - { echo "$as_me:$LINENO: current value: $ac_new_val" >&5 -echo "$as_me: current value: $ac_new_val" >&2;} - ac_cache_corrupted=: - fi;; - esac - # Pass precious variables to config.status. - if test "$ac_new_set" = set; then - case $ac_new_val in - *" "*|*" "*|*[\[\]\~\#\$\^\&\*\(\)\{\}\\\|\;\<\>\?\"\']*) - ac_arg=$ac_var=`echo "$ac_new_val" | sed "s/'/'\\\\\\\\''/g"` ;; - *) ac_arg=$ac_var=$ac_new_val ;; - esac - case " $ac_configure_args " in - *" '$ac_arg' "*) ;; # Avoid dups. Use of quotes ensures accuracy. - *) ac_configure_args="$ac_configure_args '$ac_arg'" ;; - esac - fi -done -if $ac_cache_corrupted; then - { echo "$as_me:$LINENO: error: changes in the environment can compromise the build" >&5 -echo "$as_me: error: changes in the environment can compromise the build" >&2;} - { { echo "$as_me:$LINENO: error: run \`make distclean' and/or \`rm $cache_file' and start over" >&5 -echo "$as_me: error: run \`make distclean' and/or \`rm $cache_file' and start over" >&2;} - { (exit 1); exit 1; }; } -fi - -ac_ext=c -ac_cpp='$CPP $CPPFLAGS' -ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' -ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' -ac_compiler_gnu=$ac_cv_c_compiler_gnu - - - - - - - - - - - - - - - - - - - - - - - - ac_config_headers="$ac_config_headers config.h:config.in" - - - -PCRE_MAJOR=4 -PCRE_MINOR=5 -PCRE_DATE=01-December-2003 -PCRE_VERSION=${PCRE_MAJOR}.${PCRE_MINOR} - - -POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=10 - - -PCRE_LIB_VERSION=0:1:0 -PCRE_POSIXLIB_VERSION=0:0:0 - - -ac_ext=c -ac_cpp='$CPP $CPPFLAGS' -ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' -ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' -ac_compiler_gnu=$ac_cv_c_compiler_gnu -if test -n "$ac_tool_prefix"; then - # Extract the first word of "${ac_tool_prefix}gcc", so it can be a program name with args. -set dummy ${ac_tool_prefix}gcc; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 -if test "${ac_cv_prog_CC+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -n "$CC"; then - ac_cv_prog_CC="$CC" # Let the user override the test. -else -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - ac_cv_prog_CC="${ac_tool_prefix}gcc" - echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 - fi -done -done - -fi -fi -CC=$ac_cv_prog_CC -if test -n "$CC"; then - echo "$as_me:$LINENO: result: $CC" >&5 -echo "${ECHO_T}$CC" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - -fi -if test -z "$ac_cv_prog_CC"; then - ac_ct_CC=$CC - # Extract the first word of "gcc", so it can be a program name with args. -set dummy gcc; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 -if test "${ac_cv_prog_ac_ct_CC+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -n "$ac_ct_CC"; then - ac_cv_prog_ac_ct_CC="$ac_ct_CC" # Let the user override the test. -else -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - ac_cv_prog_ac_ct_CC="gcc" - echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 - fi -done -done - -fi -fi -ac_ct_CC=$ac_cv_prog_ac_ct_CC -if test -n "$ac_ct_CC"; then - echo "$as_me:$LINENO: result: $ac_ct_CC" >&5 -echo "${ECHO_T}$ac_ct_CC" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - - CC=$ac_ct_CC -else - CC="$ac_cv_prog_CC" -fi - -if test -z "$CC"; then - if test -n "$ac_tool_prefix"; then - # Extract the first word of "${ac_tool_prefix}cc", so it can be a program name with args. -set dummy ${ac_tool_prefix}cc; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 -if test "${ac_cv_prog_CC+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -n "$CC"; then - ac_cv_prog_CC="$CC" # Let the user override the test. -else -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - ac_cv_prog_CC="${ac_tool_prefix}cc" - echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 - fi -done -done - -fi -fi -CC=$ac_cv_prog_CC -if test -n "$CC"; then - echo "$as_me:$LINENO: result: $CC" >&5 -echo "${ECHO_T}$CC" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - -fi -if test -z "$ac_cv_prog_CC"; then - ac_ct_CC=$CC - # Extract the first word of "cc", so it can be a program name with args. -set dummy cc; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 -if test "${ac_cv_prog_ac_ct_CC+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -n "$ac_ct_CC"; then - ac_cv_prog_ac_ct_CC="$ac_ct_CC" # Let the user override the test. -else -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - ac_cv_prog_ac_ct_CC="cc" - echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 - fi -done -done - -fi -fi -ac_ct_CC=$ac_cv_prog_ac_ct_CC -if test -n "$ac_ct_CC"; then - echo "$as_me:$LINENO: result: $ac_ct_CC" >&5 -echo "${ECHO_T}$ac_ct_CC" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - - CC=$ac_ct_CC -else - CC="$ac_cv_prog_CC" -fi - -fi -if test -z "$CC"; then - # Extract the first word of "cc", so it can be a program name with args. -set dummy cc; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 -if test "${ac_cv_prog_CC+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -n "$CC"; then - ac_cv_prog_CC="$CC" # Let the user override the test. -else - ac_prog_rejected=no -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - if test "$as_dir/$ac_word$ac_exec_ext" = "/usr/ucb/cc"; then - ac_prog_rejected=yes - continue - fi - ac_cv_prog_CC="cc" - echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 - fi -done -done - -if test $ac_prog_rejected = yes; then - # We found a bogon in the path, so make sure we never use it. - set dummy $ac_cv_prog_CC - shift - if test $# != 0; then - # We chose a different compiler from the bogus one. - # However, it has the same basename, so the bogon will be chosen - # first if we set CC to just the basename; use the full file name. - shift - ac_cv_prog_CC="$as_dir/$ac_word${1+' '}$@" - fi -fi -fi -fi -CC=$ac_cv_prog_CC -if test -n "$CC"; then - echo "$as_me:$LINENO: result: $CC" >&5 -echo "${ECHO_T}$CC" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - -fi -if test -z "$CC"; then - if test -n "$ac_tool_prefix"; then - for ac_prog in cl - do - # Extract the first word of "$ac_tool_prefix$ac_prog", so it can be a program name with args. -set dummy $ac_tool_prefix$ac_prog; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 -if test "${ac_cv_prog_CC+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -n "$CC"; then - ac_cv_prog_CC="$CC" # Let the user override the test. -else -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - ac_cv_prog_CC="$ac_tool_prefix$ac_prog" - echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 - fi -done -done - -fi -fi -CC=$ac_cv_prog_CC -if test -n "$CC"; then - echo "$as_me:$LINENO: result: $CC" >&5 -echo "${ECHO_T}$CC" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - - test -n "$CC" && break - done -fi -if test -z "$CC"; then - ac_ct_CC=$CC - for ac_prog in cl -do - # Extract the first word of "$ac_prog", so it can be a program name with args. -set dummy $ac_prog; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 -if test "${ac_cv_prog_ac_ct_CC+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -n "$ac_ct_CC"; then - ac_cv_prog_ac_ct_CC="$ac_ct_CC" # Let the user override the test. -else -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - ac_cv_prog_ac_ct_CC="$ac_prog" - echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 - fi -done -done - -fi -fi -ac_ct_CC=$ac_cv_prog_ac_ct_CC -if test -n "$ac_ct_CC"; then - echo "$as_me:$LINENO: result: $ac_ct_CC" >&5 -echo "${ECHO_T}$ac_ct_CC" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - - test -n "$ac_ct_CC" && break -done - - CC=$ac_ct_CC -fi - -fi - - -test -z "$CC" && { { echo "$as_me:$LINENO: error: no acceptable C compiler found in \$PATH -See \`config.log' for more details." >&5 -echo "$as_me: error: no acceptable C compiler found in \$PATH -See \`config.log' for more details." >&2;} - { (exit 1); exit 1; }; } - -# Provide some information about the compiler. -echo "$as_me:$LINENO:" \ - "checking for C compiler version" >&5 -ac_compiler=`set X $ac_compile; echo $2` -{ (eval echo "$as_me:$LINENO: \"$ac_compiler --version </dev/null >&5\"") >&5 - (eval $ac_compiler --version </dev/null >&5) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } -{ (eval echo "$as_me:$LINENO: \"$ac_compiler -v </dev/null >&5\"") >&5 - (eval $ac_compiler -v </dev/null >&5) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } -{ (eval echo "$as_me:$LINENO: \"$ac_compiler -V </dev/null >&5\"") >&5 - (eval $ac_compiler -V </dev/null >&5) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } - -cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ - -int -main () -{ - - ; - return 0; -} -_ACEOF -ac_clean_files_save=$ac_clean_files -ac_clean_files="$ac_clean_files a.out a.exe b.out" -# Try to create an executable without -o first, disregard a.out. -# It will help us diagnose broken compilers, and finding out an intuition -# of exeext. -echo "$as_me:$LINENO: checking for C compiler default output" >&5 -echo $ECHO_N "checking for C compiler default output... $ECHO_C" >&6 -ac_link_default=`echo "$ac_link" | sed 's/ -o *conftest[^ ]*//'` -if { (eval echo "$as_me:$LINENO: \"$ac_link_default\"") >&5 - (eval $ac_link_default) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; then - # Find the output, starting from the most likely. This scheme is -# not robust to junk in `.', hence go to wildcards (a.*) only as a last -# resort. - -# Be careful to initialize this variable, since it used to be cached. -# Otherwise an old cache value of `no' led to `EXEEXT = no' in a Makefile. -ac_cv_exeext= -# b.out is created by i960 compilers. -for ac_file in a_out.exe a.exe conftest.exe a.out conftest a.* conftest.* b.out -do - test -f "$ac_file" || continue - case $ac_file in - *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.o | *.obj ) - ;; - conftest.$ac_ext ) - # This is the source file. - ;; - [ab].out ) - # We found the default executable, but exeext='' is most - # certainly right. - break;; - *.* ) - ac_cv_exeext=`expr "$ac_file" : '[^.]*\(\..*\)'` - # FIXME: I believe we export ac_cv_exeext for Libtool, - # but it would be cool to find out if it's true. Does anybody - # maintain Libtool? --akim. - export ac_cv_exeext - break;; - * ) - break;; - esac -done -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -{ { echo "$as_me:$LINENO: error: C compiler cannot create executables -See \`config.log' for more details." >&5 -echo "$as_me: error: C compiler cannot create executables -See \`config.log' for more details." >&2;} - { (exit 77); exit 77; }; } -fi - -ac_exeext=$ac_cv_exeext -echo "$as_me:$LINENO: result: $ac_file" >&5 -echo "${ECHO_T}$ac_file" >&6 - -# Check the compiler produces executables we can run. If not, either -# the compiler is broken, or we cross compile. -echo "$as_me:$LINENO: checking whether the C compiler works" >&5 -echo $ECHO_N "checking whether the C compiler works... $ECHO_C" >&6 -# FIXME: These cross compiler hacks should be removed for Autoconf 3.0 -# If not cross compiling, check that we can run a simple program. -if test "$cross_compiling" != yes; then - if { ac_try='./$ac_file' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - cross_compiling=no - else - if test "$cross_compiling" = maybe; then - cross_compiling=yes - else - { { echo "$as_me:$LINENO: error: cannot run C compiled programs. -If you meant to cross compile, use \`--host'. -See \`config.log' for more details." >&5 -echo "$as_me: error: cannot run C compiled programs. -If you meant to cross compile, use \`--host'. -See \`config.log' for more details." >&2;} - { (exit 1); exit 1; }; } - fi - fi -fi -echo "$as_me:$LINENO: result: yes" >&5 -echo "${ECHO_T}yes" >&6 - -rm -f a.out a.exe conftest$ac_cv_exeext b.out -ac_clean_files=$ac_clean_files_save -# Check the compiler produces executables we can run. If not, either -# the compiler is broken, or we cross compile. -echo "$as_me:$LINENO: checking whether we are cross compiling" >&5 -echo $ECHO_N "checking whether we are cross compiling... $ECHO_C" >&6 -echo "$as_me:$LINENO: result: $cross_compiling" >&5 -echo "${ECHO_T}$cross_compiling" >&6 - -echo "$as_me:$LINENO: checking for suffix of executables" >&5 -echo $ECHO_N "checking for suffix of executables... $ECHO_C" >&6 -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; then - # If both `conftest.exe' and `conftest' are `present' (well, observable) -# catch `conftest.exe'. For instance with Cygwin, `ls conftest' will -# work properly (i.e., refer to `conftest.exe'), while it won't with -# `rm'. -for ac_file in conftest.exe conftest conftest.*; do - test -f "$ac_file" || continue - case $ac_file in - *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg | *.o | *.obj ) ;; - *.* ) ac_cv_exeext=`expr "$ac_file" : '[^.]*\(\..*\)'` - export ac_cv_exeext - break;; - * ) break;; - esac -done -else - { { echo "$as_me:$LINENO: error: cannot compute suffix of executables: cannot compile and link -See \`config.log' for more details." >&5 -echo "$as_me: error: cannot compute suffix of executables: cannot compile and link -See \`config.log' for more details." >&2;} - { (exit 1); exit 1; }; } -fi - -rm -f conftest$ac_cv_exeext -echo "$as_me:$LINENO: result: $ac_cv_exeext" >&5 -echo "${ECHO_T}$ac_cv_exeext" >&6 - -rm -f conftest.$ac_ext -EXEEXT=$ac_cv_exeext -ac_exeext=$EXEEXT -echo "$as_me:$LINENO: checking for suffix of object files" >&5 -echo $ECHO_N "checking for suffix of object files... $ECHO_C" >&6 -if test "${ac_cv_objext+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ - -int -main () -{ - - ; - return 0; -} -_ACEOF -rm -f conftest.o conftest.obj -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; then - for ac_file in `(ls conftest.o conftest.obj; ls conftest.*) 2>/dev/null`; do - case $ac_file in - *.$ac_ext | *.xcoff | *.tds | *.d | *.pdb | *.xSYM | *.bb | *.bbg ) ;; - *) ac_cv_objext=`expr "$ac_file" : '.*\.\(.*\)'` - break;; - esac -done -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -{ { echo "$as_me:$LINENO: error: cannot compute suffix of object files: cannot compile -See \`config.log' for more details." >&5 -echo "$as_me: error: cannot compute suffix of object files: cannot compile -See \`config.log' for more details." >&2;} - { (exit 1); exit 1; }; } -fi - -rm -f conftest.$ac_cv_objext conftest.$ac_ext -fi -echo "$as_me:$LINENO: result: $ac_cv_objext" >&5 -echo "${ECHO_T}$ac_cv_objext" >&6 -OBJEXT=$ac_cv_objext -ac_objext=$OBJEXT -echo "$as_me:$LINENO: checking whether we are using the GNU C compiler" >&5 -echo $ECHO_N "checking whether we are using the GNU C compiler... $ECHO_C" >&6 -if test "${ac_cv_c_compiler_gnu+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ - -int -main () -{ -#ifndef __GNUC__ - choke me -#endif - - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_compiler_gnu=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -ac_compiler_gnu=no -fi -rm -f conftest.$ac_objext conftest.$ac_ext -ac_cv_c_compiler_gnu=$ac_compiler_gnu - -fi -echo "$as_me:$LINENO: result: $ac_cv_c_compiler_gnu" >&5 -echo "${ECHO_T}$ac_cv_c_compiler_gnu" >&6 -GCC=`test $ac_compiler_gnu = yes && echo yes` -ac_test_CFLAGS=${CFLAGS+set} -ac_save_CFLAGS=$CFLAGS -CFLAGS="-g" -echo "$as_me:$LINENO: checking whether $CC accepts -g" >&5 -echo $ECHO_N "checking whether $CC accepts -g... $ECHO_C" >&6 -if test "${ac_cv_prog_cc_g+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ - -int -main () -{ - - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_cv_prog_cc_g=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -ac_cv_prog_cc_g=no -fi -rm -f conftest.$ac_objext conftest.$ac_ext -fi -echo "$as_me:$LINENO: result: $ac_cv_prog_cc_g" >&5 -echo "${ECHO_T}$ac_cv_prog_cc_g" >&6 -if test "$ac_test_CFLAGS" = set; then - CFLAGS=$ac_save_CFLAGS -elif test $ac_cv_prog_cc_g = yes; then - if test "$GCC" = yes; then - CFLAGS="-g -O2" - else - CFLAGS="-g" - fi -else - if test "$GCC" = yes; then - CFLAGS="-O2" - else - CFLAGS= - fi -fi -echo "$as_me:$LINENO: checking for $CC option to accept ANSI C" >&5 -echo $ECHO_N "checking for $CC option to accept ANSI C... $ECHO_C" >&6 -if test "${ac_cv_prog_cc_stdc+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - ac_cv_prog_cc_stdc=no -ac_save_CC=$CC -cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <stdarg.h> -#include <stdio.h> -#include <sys/types.h> -#include <sys/stat.h> -/* Most of the following tests are stolen from RCS 5.7's src/conf.sh. */ -struct buf { int x; }; -FILE * (*rcsopen) (struct buf *, struct stat *, int); -static char *e (p, i) - char **p; - int i; -{ - return p[i]; -} -static char *f (char * (*g) (char **, int), char **p, ...) -{ - char *s; - va_list v; - va_start (v,p); - s = g (p, va_arg (v,int)); - va_end (v); - return s; -} -int test (int i, double x); -struct s1 {int (*f) (int a);}; -struct s2 {int (*f) (double a);}; -int pairnames (int, char **, FILE *(*)(struct buf *, struct stat *, int), int, int); -int argc; -char **argv; -int -main () -{ -return f (e, argv, 0) != argv[0] || f (e, argv, 1) != argv[1]; - ; - return 0; -} -_ACEOF -# Don't try gcc -ansi; that turns off useful extensions and -# breaks some systems' header files. -# AIX -qlanglvl=ansi -# Ultrix and OSF/1 -std1 -# HP-UX 10.20 and later -Ae -# HP-UX older versions -Aa -D_HPUX_SOURCE -# SVR4 -Xc -D__EXTENSIONS__ -for ac_arg in "" -qlanglvl=ansi -std1 -Ae "-Aa -D_HPUX_SOURCE" "-Xc -D__EXTENSIONS__" -do - CC="$ac_save_CC $ac_arg" - rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_cv_prog_cc_stdc=$ac_arg -break -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -fi -rm -f conftest.$ac_objext -done -rm -f conftest.$ac_ext conftest.$ac_objext -CC=$ac_save_CC - -fi - -case "x$ac_cv_prog_cc_stdc" in - x|xno) - echo "$as_me:$LINENO: result: none needed" >&5 -echo "${ECHO_T}none needed" >&6 ;; - *) - echo "$as_me:$LINENO: result: $ac_cv_prog_cc_stdc" >&5 -echo "${ECHO_T}$ac_cv_prog_cc_stdc" >&6 - CC="$CC $ac_cv_prog_cc_stdc" ;; -esac - -# Some people use a C++ compiler to compile C. Since we use `exit', -# in C++ we need to declare it. In case someone uses the same compiler -# for both compiling C and C++ we need to have the C++ compiler decide -# the declaration of exit, since it's the most demanding environment. -cat >conftest.$ac_ext <<_ACEOF -#ifndef __cplusplus - choke me -#endif -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - for ac_declaration in \ - ''\ - '#include <stdlib.h>' \ - 'extern "C" void std::exit (int) throw (); using std::exit;' \ - 'extern "C" void std::exit (int); using std::exit;' \ - 'extern "C" void exit (int) throw ();' \ - 'extern "C" void exit (int);' \ - 'void exit (int);' -do - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <stdlib.h> -$ac_declaration -int -main () -{ -exit (42); - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - : -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -continue -fi -rm -f conftest.$ac_objext conftest.$ac_ext - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -$ac_declaration -int -main () -{ -exit (42); - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - break -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -fi -rm -f conftest.$ac_objext conftest.$ac_ext -done -rm -f conftest* -if test -n "$ac_declaration"; then - echo '#ifdef __cplusplus' >>confdefs.h - echo $ac_declaration >>confdefs.h - echo '#endif' >>confdefs.h -fi - -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -fi -rm -f conftest.$ac_objext conftest.$ac_ext -ac_ext=c -ac_cpp='$CPP $CPPFLAGS' -ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' -ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' -ac_compiler_gnu=$ac_cv_c_compiler_gnu - -ac_aux_dir= -for ac_dir in $srcdir $srcdir/.. $srcdir/../..; do - if test -f $ac_dir/install-sh; then - ac_aux_dir=$ac_dir - ac_install_sh="$ac_aux_dir/install-sh -c" - break - elif test -f $ac_dir/install.sh; then - ac_aux_dir=$ac_dir - ac_install_sh="$ac_aux_dir/install.sh -c" - break - elif test -f $ac_dir/shtool; then - ac_aux_dir=$ac_dir - ac_install_sh="$ac_aux_dir/shtool install -c" - break - fi -done -if test -z "$ac_aux_dir"; then - { { echo "$as_me:$LINENO: error: cannot find install-sh or install.sh in $srcdir $srcdir/.. $srcdir/../.." >&5 -echo "$as_me: error: cannot find install-sh or install.sh in $srcdir $srcdir/.. $srcdir/../.." >&2;} - { (exit 1); exit 1; }; } -fi -ac_config_guess="$SHELL $ac_aux_dir/config.guess" -ac_config_sub="$SHELL $ac_aux_dir/config.sub" -ac_configure="$SHELL $ac_aux_dir/configure" # This should be Cygnus configure. - -# Find a good install program. We prefer a C program (faster), -# so one script is as good as another. But avoid the broken or -# incompatible versions: -# SysV /etc/install, /usr/sbin/install -# SunOS /usr/etc/install -# IRIX /sbin/install -# AIX /bin/install -# AmigaOS /C/install, which installs bootblocks on floppy discs -# AIX 4 /usr/bin/installbsd, which doesn't work without a -g flag -# AFS /usr/afsws/bin/install, which mishandles nonexistent args -# SVR4 /usr/ucb/install, which tries to use the nonexistent group "staff" -# ./install, which can be erroneously created by make from ./install.sh. -echo "$as_me:$LINENO: checking for a BSD-compatible install" >&5 -echo $ECHO_N "checking for a BSD-compatible install... $ECHO_C" >&6 -if test -z "$INSTALL"; then -if test "${ac_cv_path_install+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - # Account for people who put trailing slashes in PATH elements. -case $as_dir/ in - ./ | .// | /cC/* | \ - /etc/* | /usr/sbin/* | /usr/etc/* | /sbin/* | /usr/afsws/bin/* | \ - /usr/ucb/* ) ;; - *) - # OSF1 and SCO ODT 3.0 have their own names for install. - # Don't use installbsd from OSF since it installs stuff as root - # by default. - for ac_prog in ginstall scoinst install; do - for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_prog$ac_exec_ext"; then - if test $ac_prog = install && - grep dspmsg "$as_dir/$ac_prog$ac_exec_ext" >/dev/null 2>&1; then - # AIX install. It has an incompatible calling convention. - : - elif test $ac_prog = install && - grep pwplus "$as_dir/$ac_prog$ac_exec_ext" >/dev/null 2>&1; then - # program-specific install script used by HP pwplus--don't use. - : - else - ac_cv_path_install="$as_dir/$ac_prog$ac_exec_ext -c" - break 3 - fi - fi - done - done - ;; -esac -done - - -fi - if test "${ac_cv_path_install+set}" = set; then - INSTALL=$ac_cv_path_install - else - # As a last resort, use the slow shell script. We don't cache a - # path for INSTALL within a source directory, because that will - # break other packages using the cache if that directory is - # removed, or if the path is relative. - INSTALL=$ac_install_sh - fi -fi -echo "$as_me:$LINENO: result: $INSTALL" >&5 -echo "${ECHO_T}$INSTALL" >&6 - -# Use test -z because SunOS4 sh mishandles braces in ${var-val}. -# It thinks the first close brace ends the variable substitution. -test -z "$INSTALL_PROGRAM" && INSTALL_PROGRAM='${INSTALL}' - -test -z "$INSTALL_SCRIPT" && INSTALL_SCRIPT='${INSTALL}' - -test -z "$INSTALL_DATA" && INSTALL_DATA='${INSTALL} -m 644' - - -# Check whether --enable-shared or --disable-shared was given. -if test "${enable_shared+set}" = set; then - enableval="$enable_shared" - p=${PACKAGE-default} -case $enableval in -yes) enable_shared=yes ;; -no) enable_shared=no ;; -*) - enable_shared=no - # Look at the argument we got. We use all the common list separators. - IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS="${IFS}:," - for pkg in $enableval; do - if test "X$pkg" = "X$p"; then - enable_shared=yes - fi - done - IFS="$ac_save_ifs" - ;; -esac -else - enable_shared=yes -fi; -# Check whether --enable-static or --disable-static was given. -if test "${enable_static+set}" = set; then - enableval="$enable_static" - p=${PACKAGE-default} -case $enableval in -yes) enable_static=yes ;; -no) enable_static=no ;; -*) - enable_static=no - # Look at the argument we got. We use all the common list separators. - IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS="${IFS}:," - for pkg in $enableval; do - if test "X$pkg" = "X$p"; then - enable_static=yes - fi - done - IFS="$ac_save_ifs" - ;; -esac -else - enable_static=yes -fi; -# Check whether --enable-fast-install or --disable-fast-install was given. -if test "${enable_fast_install+set}" = set; then - enableval="$enable_fast_install" - p=${PACKAGE-default} -case $enableval in -yes) enable_fast_install=yes ;; -no) enable_fast_install=no ;; -*) - enable_fast_install=no - # Look at the argument we got. We use all the common list separators. - IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS="${IFS}:," - for pkg in $enableval; do - if test "X$pkg" = "X$p"; then - enable_fast_install=yes - fi - done - IFS="$ac_save_ifs" - ;; -esac -else - enable_fast_install=yes -fi; -# Make sure we can run config.sub. -$ac_config_sub sun4 >/dev/null 2>&1 || - { { echo "$as_me:$LINENO: error: cannot run $ac_config_sub" >&5 -echo "$as_me: error: cannot run $ac_config_sub" >&2;} - { (exit 1); exit 1; }; } - -echo "$as_me:$LINENO: checking build system type" >&5 -echo $ECHO_N "checking build system type... $ECHO_C" >&6 -if test "${ac_cv_build+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - ac_cv_build_alias=$build_alias -test -z "$ac_cv_build_alias" && - ac_cv_build_alias=`$ac_config_guess` -test -z "$ac_cv_build_alias" && - { { echo "$as_me:$LINENO: error: cannot guess build type; you must specify one" >&5 -echo "$as_me: error: cannot guess build type; you must specify one" >&2;} - { (exit 1); exit 1; }; } -ac_cv_build=`$ac_config_sub $ac_cv_build_alias` || - { { echo "$as_me:$LINENO: error: $ac_config_sub $ac_cv_build_alias failed" >&5 -echo "$as_me: error: $ac_config_sub $ac_cv_build_alias failed" >&2;} - { (exit 1); exit 1; }; } - -fi -echo "$as_me:$LINENO: result: $ac_cv_build" >&5 -echo "${ECHO_T}$ac_cv_build" >&6 -build=$ac_cv_build -build_cpu=`echo $ac_cv_build | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\1/'` -build_vendor=`echo $ac_cv_build | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\2/'` -build_os=`echo $ac_cv_build | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\3/'` - - -echo "$as_me:$LINENO: checking host system type" >&5 -echo $ECHO_N "checking host system type... $ECHO_C" >&6 -if test "${ac_cv_host+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - ac_cv_host_alias=$host_alias -test -z "$ac_cv_host_alias" && - ac_cv_host_alias=$ac_cv_build_alias -ac_cv_host=`$ac_config_sub $ac_cv_host_alias` || - { { echo "$as_me:$LINENO: error: $ac_config_sub $ac_cv_host_alias failed" >&5 -echo "$as_me: error: $ac_config_sub $ac_cv_host_alias failed" >&2;} - { (exit 1); exit 1; }; } - -fi -echo "$as_me:$LINENO: result: $ac_cv_host" >&5 -echo "${ECHO_T}$ac_cv_host" >&6 -host=$ac_cv_host -host_cpu=`echo $ac_cv_host | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\1/'` -host_vendor=`echo $ac_cv_host | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\2/'` -host_os=`echo $ac_cv_host | sed 's/^\([^-]*\)-\([^-]*\)-\(.*\)$/\3/'` - - - -# Check whether --with-gnu-ld or --without-gnu-ld was given. -if test "${with_gnu_ld+set}" = set; then - withval="$with_gnu_ld" - test "$withval" = no || with_gnu_ld=yes -else - with_gnu_ld=no -fi; -ac_prog=ld -if test "$GCC" = yes; then - # Check if gcc -print-prog-name=ld gives a path. - echo "$as_me:$LINENO: checking for ld used by GCC" >&5 -echo $ECHO_N "checking for ld used by GCC... $ECHO_C" >&6 - case $host in - *-*-mingw*) - # gcc leaves a trailing carriage return which upsets mingw - ac_prog=`($CC -print-prog-name=ld) 2>&5 | tr -d '\015'` ;; - *) - ac_prog=`($CC -print-prog-name=ld) 2>&5` ;; - esac - case $ac_prog in - # Accept absolute paths. - [\\/]* | [A-Za-z]:[\\/]*) - re_direlt='/[^/][^/]*/\.\./' - # Canonicalize the path of ld - ac_prog=`echo $ac_prog| sed 's%\\\\%/%g'` - while echo $ac_prog | grep "$re_direlt" > /dev/null 2>&1; do - ac_prog=`echo $ac_prog| sed "s%$re_direlt%/%"` - done - test -z "$LD" && LD="$ac_prog" - ;; - "") - # If it fails, then pretend we aren't using GCC. - ac_prog=ld - ;; - *) - # If it is relative, then search for the first ld in PATH. - with_gnu_ld=unknown - ;; - esac -elif test "$with_gnu_ld" = yes; then - echo "$as_me:$LINENO: checking for GNU ld" >&5 -echo $ECHO_N "checking for GNU ld... $ECHO_C" >&6 -else - echo "$as_me:$LINENO: checking for non-GNU ld" >&5 -echo $ECHO_N "checking for non-GNU ld... $ECHO_C" >&6 -fi -if test "${lt_cv_path_LD+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -z "$LD"; then - IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS="${IFS}${PATH_SEPARATOR-:}" - for ac_dir in $PATH; do - test -z "$ac_dir" && ac_dir=. - if test -f "$ac_dir/$ac_prog" || test -f "$ac_dir/$ac_prog$ac_exeext"; then - lt_cv_path_LD="$ac_dir/$ac_prog" - # Check to see if the program is GNU ld. I'd rather use --version, - # but apparently some GNU ld's only accept -v. - # Break only if it was the GNU/non-GNU ld that we prefer. - if "$lt_cv_path_LD" -v 2>&1 < /dev/null | egrep '(GNU|with BFD)' > /dev/null; then - test "$with_gnu_ld" != no && break - else - test "$with_gnu_ld" != yes && break - fi - fi - done - IFS="$ac_save_ifs" -else - lt_cv_path_LD="$LD" # Let the user override the test with a path. -fi -fi - -LD="$lt_cv_path_LD" -if test -n "$LD"; then - echo "$as_me:$LINENO: result: $LD" >&5 -echo "${ECHO_T}$LD" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi -test -z "$LD" && { { echo "$as_me:$LINENO: error: no acceptable ld found in \$PATH" >&5 -echo "$as_me: error: no acceptable ld found in \$PATH" >&2;} - { (exit 1); exit 1; }; } -echo "$as_me:$LINENO: checking if the linker ($LD) is GNU ld" >&5 -echo $ECHO_N "checking if the linker ($LD) is GNU ld... $ECHO_C" >&6 -if test "${lt_cv_prog_gnu_ld+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - # I'd rather use --version here, but apparently some GNU ld's only accept -v. -if $LD -v 2>&1 </dev/null | egrep '(GNU|with BFD)' 1>&5; then - lt_cv_prog_gnu_ld=yes -else - lt_cv_prog_gnu_ld=no -fi -fi -echo "$as_me:$LINENO: result: $lt_cv_prog_gnu_ld" >&5 -echo "${ECHO_T}$lt_cv_prog_gnu_ld" >&6 -with_gnu_ld=$lt_cv_prog_gnu_ld - - -echo "$as_me:$LINENO: checking for $LD option to reload object files" >&5 -echo $ECHO_N "checking for $LD option to reload object files... $ECHO_C" >&6 -if test "${lt_cv_ld_reload_flag+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - lt_cv_ld_reload_flag='-r' -fi -echo "$as_me:$LINENO: result: $lt_cv_ld_reload_flag" >&5 -echo "${ECHO_T}$lt_cv_ld_reload_flag" >&6 -reload_flag=$lt_cv_ld_reload_flag -test -n "$reload_flag" && reload_flag=" $reload_flag" - -echo "$as_me:$LINENO: checking for BSD-compatible nm" >&5 -echo $ECHO_N "checking for BSD-compatible nm... $ECHO_C" >&6 -if test "${lt_cv_path_NM+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -n "$NM"; then - # Let the user override the test. - lt_cv_path_NM="$NM" -else - IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS="${IFS}${PATH_SEPARATOR-:}" - for ac_dir in $PATH /usr/ccs/bin /usr/ucb /bin; do - test -z "$ac_dir" && ac_dir=. - tmp_nm=$ac_dir/${ac_tool_prefix}nm - if test -f $tmp_nm || test -f $tmp_nm$ac_exeext ; then - # Check to see if the nm accepts a BSD-compat flag. - # Adding the `sed 1q' prevents false positives on HP-UX, which says: - # nm: unknown option "B" ignored - # Tru64's nm complains that /dev/null is an invalid object file - if ($tmp_nm -B /dev/null 2>&1 | sed '1q'; exit 0) | egrep '(/dev/null|Invalid file or object type)' >/dev/null; then - lt_cv_path_NM="$tmp_nm -B" - break - elif ($tmp_nm -p /dev/null 2>&1 | sed '1q'; exit 0) | egrep /dev/null >/dev/null; then - lt_cv_path_NM="$tmp_nm -p" - break - else - lt_cv_path_NM=${lt_cv_path_NM="$tmp_nm"} # keep the first match, but - continue # so that we can try to find one that supports BSD flags - fi - fi - done - IFS="$ac_save_ifs" - test -z "$lt_cv_path_NM" && lt_cv_path_NM=nm -fi -fi - -NM="$lt_cv_path_NM" -echo "$as_me:$LINENO: result: $NM" >&5 -echo "${ECHO_T}$NM" >&6 - -echo "$as_me:$LINENO: checking whether ln -s works" >&5 -echo $ECHO_N "checking whether ln -s works... $ECHO_C" >&6 -LN_S=$as_ln_s -if test "$LN_S" = "ln -s"; then - echo "$as_me:$LINENO: result: yes" >&5 -echo "${ECHO_T}yes" >&6 -else - echo "$as_me:$LINENO: result: no, using $LN_S" >&5 -echo "${ECHO_T}no, using $LN_S" >&6 -fi - -echo "$as_me:$LINENO: checking how to recognise dependant libraries" >&5 -echo $ECHO_N "checking how to recognise dependant libraries... $ECHO_C" >&6 -if test "${lt_cv_deplibs_check_method+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - lt_cv_file_magic_cmd='$MAGIC_CMD' -lt_cv_file_magic_test_file= -lt_cv_deplibs_check_method='unknown' -# Need to set the preceding variable on all platforms that support -# interlibrary dependencies. -# 'none' -- dependencies not supported. -# `unknown' -- same as none, but documents that we really don't know. -# 'pass_all' -- all dependencies passed with no checks. -# 'test_compile' -- check by making test program. -# ['file_magic [regex]'] -- check by looking for files in library path -# which responds to the $file_magic_cmd with a given egrep regex. -# If you have `file' or equivalent on your system and you're not sure -# whether `pass_all' will *always* work, you probably want this one. - -case $host_os in -aix4* | aix5*) - lt_cv_deplibs_check_method=pass_all - ;; - -beos*) - lt_cv_deplibs_check_method=pass_all - ;; - -bsdi4*) - lt_cv_deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [ML]SB (shared object|dynamic lib)' - lt_cv_file_magic_cmd='/usr/bin/file -L' - lt_cv_file_magic_test_file=/shlib/libc.so - ;; - -cygwin* | mingw* | pw32*) - lt_cv_deplibs_check_method='file_magic file format pei*-i386(.*architecture: i386)?' - lt_cv_file_magic_cmd='$OBJDUMP -f' - ;; - -darwin* | rhapsody*) - lt_cv_deplibs_check_method='file_magic Mach-O dynamically linked shared library' - lt_cv_file_magic_cmd='/usr/bin/file -L' - case "$host_os" in - rhapsody* | darwin1.012) - lt_cv_file_magic_test_file=`echo /System/Library/Frameworks/System.framework/Versions/*/System | head -1` - ;; - *) # Darwin 1.3 on - lt_cv_file_magic_test_file='/usr/lib/libSystem.dylib' - ;; - esac - ;; - -freebsd*) - if echo __ELF__ | $CC -E - | grep __ELF__ > /dev/null; then - case $host_cpu in - i*86 ) - # Not sure whether the presence of OpenBSD here was a mistake. - # Let's accept both of them until this is cleared up. - lt_cv_deplibs_check_method='file_magic (FreeBSD|OpenBSD)/i[3-9]86 (compact )?demand paged shared library' - lt_cv_file_magic_cmd=/usr/bin/file - lt_cv_file_magic_test_file=`echo /usr/lib/libc.so.*` - ;; - esac - else - lt_cv_deplibs_check_method=pass_all - fi - ;; - -gnu*) - lt_cv_deplibs_check_method=pass_all - ;; - -hpux10.20*|hpux11*) - lt_cv_deplibs_check_method='file_magic (s[0-9][0-9][0-9]|PA-RISC[0-9].[0-9]) shared library' - lt_cv_file_magic_cmd=/usr/bin/file - lt_cv_file_magic_test_file=/usr/lib/libc.sl - ;; - -irix5* | irix6*) - case $host_os in - irix5*) - # this will be overridden with pass_all, but let us keep it just in case - lt_cv_deplibs_check_method="file_magic ELF 32-bit MSB dynamic lib MIPS - version 1" - ;; - *) - case $LD in - *-32|*"-32 ") libmagic=32-bit;; - *-n32|*"-n32 ") libmagic=N32;; - *-64|*"-64 ") libmagic=64-bit;; - *) libmagic=never-match;; - esac - # this will be overridden with pass_all, but let us keep it just in case - lt_cv_deplibs_check_method="file_magic ELF ${libmagic} MSB mips-[1234] dynamic lib MIPS - version 1" - ;; - esac - lt_cv_file_magic_test_file=`echo /lib${libsuff}/libc.so*` - lt_cv_deplibs_check_method=pass_all - ;; - -# This must be Linux ELF. -linux-gnu*) - case $host_cpu in - alpha* | i*86 | powerpc* | sparc* | ia64* ) - lt_cv_deplibs_check_method=pass_all ;; - *) - # glibc up to 2.1.1 does not perform some relocations on ARM - lt_cv_deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [LM]SB (shared object|dynamic lib )' ;; - esac - lt_cv_file_magic_test_file=`echo /lib/libc.so* /lib/libc-*.so` - ;; - -netbsd*) - if echo __ELF__ | $CC -E - | grep __ELF__ > /dev/null; then - lt_cv_deplibs_check_method='match_pattern /lib[^/\.]+\.so\.[0-9]+\.[0-9]+$' - else - lt_cv_deplibs_check_method='match_pattern /lib[^/\.]+\.so$' - fi - ;; - -newos6*) - lt_cv_deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [ML]SB (executable|dynamic lib)' - lt_cv_file_magic_cmd=/usr/bin/file - lt_cv_file_magic_test_file=/usr/lib/libnls.so - ;; - -osf3* | osf4* | osf5*) - # this will be overridden with pass_all, but let us keep it just in case - lt_cv_deplibs_check_method='file_magic COFF format alpha shared library' - lt_cv_file_magic_test_file=/shlib/libc.so - lt_cv_deplibs_check_method=pass_all - ;; - -sco3.2v5*) - lt_cv_deplibs_check_method=pass_all - ;; - -solaris*) - lt_cv_deplibs_check_method=pass_all - lt_cv_file_magic_test_file=/lib/libc.so - ;; - -sysv5uw[78]* | sysv4*uw2*) - lt_cv_deplibs_check_method=pass_all - ;; - -sysv4 | sysv4.2uw2* | sysv4.3* | sysv5*) - case $host_vendor in - motorola) - lt_cv_deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [ML]SB (shared object|dynamic lib) M[0-9][0-9]* Version [0-9]' - lt_cv_file_magic_test_file=`echo /usr/lib/libc.so*` - ;; - ncr) - lt_cv_deplibs_check_method=pass_all - ;; - sequent) - lt_cv_file_magic_cmd='/bin/file' - lt_cv_deplibs_check_method='file_magic ELF [0-9][0-9]*-bit [LM]SB (shared object|dynamic lib )' - ;; - sni) - lt_cv_file_magic_cmd='/bin/file' - lt_cv_deplibs_check_method="file_magic ELF [0-9][0-9]*-bit [LM]SB dynamic lib" - lt_cv_file_magic_test_file=/lib/libc.so - ;; - esac - ;; -esac - -fi -echo "$as_me:$LINENO: result: $lt_cv_deplibs_check_method" >&5 -echo "${ECHO_T}$lt_cv_deplibs_check_method" >&6 -file_magic_cmd=$lt_cv_file_magic_cmd -deplibs_check_method=$lt_cv_deplibs_check_method - - - - - - - - -# Check for command to grab the raw symbol name followed by C symbol from nm. -echo "$as_me:$LINENO: checking command to parse $NM output" >&5 -echo $ECHO_N "checking command to parse $NM output... $ECHO_C" >&6 -if test "${lt_cv_sys_global_symbol_pipe+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - -# These are sane defaults that work on at least a few old systems. -# [They come from Ultrix. What could be older than Ultrix?!! ;)] - -# Character class describing NM global symbol codes. -symcode='[BCDEGRST]' - -# Regexp to match symbols that can be accessed directly from C. -sympat='\([_A-Za-z][_A-Za-z0-9]*\)' - -# Transform the above into a raw symbol and a C symbol. -symxfrm='\1 \2\3 \3' - -# Transform an extracted symbol line into a proper C declaration -lt_cv_global_symbol_to_cdecl="sed -n -e 's/^. .* \(.*\)$/extern char \1;/p'" - -# Define system-specific variables. -case $host_os in -aix*) - symcode='[BCDT]' - ;; -cygwin* | mingw* | pw32*) - symcode='[ABCDGISTW]' - ;; -hpux*) # Its linker distinguishes data from code symbols - lt_cv_global_symbol_to_cdecl="sed -n -e 's/^T .* \(.*\)$/extern char \1();/p' -e 's/^$symcode* .* \(.*\)$/extern char \1;/p'" - ;; -irix*) - symcode='[BCDEGRST]' - ;; -solaris* | sysv5*) - symcode='[BDT]' - ;; -sysv4) - symcode='[DFNSTU]' - ;; -esac - -# Handle CRLF in mingw tool chain -opt_cr= -case $host_os in -mingw*) - opt_cr=`echo 'x\{0,1\}' | tr x '\015'` # option cr in regexp - ;; -esac - -# If we're using GNU nm, then use its standard symbol codes. -if $NM -V 2>&1 | egrep '(GNU|with BFD)' > /dev/null; then - symcode='[ABCDGISTW]' -fi - -# Try without a prefix undercore, then with it. -for ac_symprfx in "" "_"; do - - # Write the raw and C identifiers. -lt_cv_sys_global_symbol_pipe="sed -n -e 's/^.*[ ]\($symcode$symcode*\)[ ][ ]*\($ac_symprfx\)$sympat$opt_cr$/$symxfrm/p'" - - # Check to see that the pipe works correctly. - pipe_works=no - rm -f conftest* - cat > conftest.$ac_ext <<EOF -#ifdef __cplusplus -extern "C" { -#endif -char nm_test_var; -void nm_test_func(){} -#ifdef __cplusplus -} -#endif -int main(){nm_test_var='a';nm_test_func();return(0);} -EOF - - if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; then - # Now try to grab the symbols. - nlist=conftest.nm - if { (eval echo "$as_me:$LINENO: \"$NM conftest.$ac_objext \| $lt_cv_sys_global_symbol_pipe \> $nlist\"") >&5 - (eval $NM conftest.$ac_objext \| $lt_cv_sys_global_symbol_pipe \> $nlist) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && test -s "$nlist"; then - # Try sorting and uniquifying the output. - if sort "$nlist" | uniq > "$nlist"T; then - mv -f "$nlist"T "$nlist" - else - rm -f "$nlist"T - fi - - # Make sure that we snagged all the symbols we need. - if egrep ' nm_test_var$' "$nlist" >/dev/null; then - if egrep ' nm_test_func$' "$nlist" >/dev/null; then - cat <<EOF > conftest.$ac_ext -#ifdef __cplusplus -extern "C" { -#endif - -EOF - # Now generate the symbol file. - eval "$lt_cv_global_symbol_to_cdecl"' < "$nlist" >> conftest.$ac_ext' - - cat <<EOF >> conftest.$ac_ext -#if defined (__STDC__) && __STDC__ -# define lt_ptr_t void * -#else -# define lt_ptr_t char * -# define const -#endif - -/* The mapping between symbol names and symbols. */ -const struct { - const char *name; - lt_ptr_t address; -} -lt_preloaded_symbols[] = -{ -EOF - sed "s/^$symcode$symcode* \(.*\) \(.*\)$/ {\"\2\", (lt_ptr_t) \&\2},/" < "$nlist" >> conftest.$ac_ext - cat <<\EOF >> conftest.$ac_ext - {0, (lt_ptr_t) 0} -}; - -#ifdef __cplusplus -} -#endif -EOF - # Now try linking the two files. - mv conftest.$ac_objext conftstm.$ac_objext - save_LIBS="$LIBS" - save_CFLAGS="$CFLAGS" - LIBS="conftstm.$ac_objext" - CFLAGS="$CFLAGS$no_builtin_flag" - if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && test -s conftest; then - pipe_works=yes - fi - LIBS="$save_LIBS" - CFLAGS="$save_CFLAGS" - else - echo "cannot find nm_test_func in $nlist" >&5 - fi - else - echo "cannot find nm_test_var in $nlist" >&5 - fi - else - echo "cannot run $lt_cv_sys_global_symbol_pipe" >&5 - fi - else - echo "$progname: failed program was:" >&5 - cat conftest.$ac_ext >&5 - fi - rm -f conftest* conftst* - - # Do not use the global_symbol_pipe unless it works. - if test "$pipe_works" = yes; then - break - else - lt_cv_sys_global_symbol_pipe= - fi -done - -fi - -global_symbol_pipe="$lt_cv_sys_global_symbol_pipe" -if test -z "$lt_cv_sys_global_symbol_pipe"; then - global_symbol_to_cdecl= -else - global_symbol_to_cdecl="$lt_cv_global_symbol_to_cdecl" -fi -if test -z "$global_symbol_pipe$global_symbol_to_cdecl"; then - echo "$as_me:$LINENO: result: failed" >&5 -echo "${ECHO_T}failed" >&6 -else - echo "$as_me:$LINENO: result: ok" >&5 -echo "${ECHO_T}ok" >&6 -fi - -ac_ext=c -ac_cpp='$CPP $CPPFLAGS' -ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' -ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' -ac_compiler_gnu=$ac_cv_c_compiler_gnu -echo "$as_me:$LINENO: checking how to run the C preprocessor" >&5 -echo $ECHO_N "checking how to run the C preprocessor... $ECHO_C" >&6 -# On Suns, sometimes $CPP names a directory. -if test -n "$CPP" && test -d "$CPP"; then - CPP= -fi -if test -z "$CPP"; then - if test "${ac_cv_prog_CPP+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - # Double quotes because CPP needs to be expanded - for CPP in "$CC -E" "$CC -E -traditional-cpp" "/lib/cpp" - do - ac_preproc_ok=false -for ac_c_preproc_warn_flag in '' yes -do - # Use a header file that comes with gcc, so configuring glibc - # with a fresh cross-compiler works. - # Prefer <limits.h> to <assert.h> if __STDC__ is defined, since - # <limits.h> exists even on freestanding compilers. - # On the NeXT, cc -E runs the code through the compiler's parser, - # not just through cpp. "Syntax error" is here to catch this case. - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#ifdef __STDC__ -# include <limits.h> -#else -# include <assert.h> -#endif - Syntax error -_ACEOF -if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 - (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 - ac_status=$? - grep -v '^ *+' conftest.er1 >conftest.err - rm -f conftest.er1 - cat conftest.err >&5 - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } >/dev/null; then - if test -s conftest.err; then - ac_cpp_err=$ac_c_preproc_warn_flag - else - ac_cpp_err= - fi -else - ac_cpp_err=yes -fi -if test -z "$ac_cpp_err"; then - : -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - - # Broken: fails on valid input. -continue -fi -rm -f conftest.err conftest.$ac_ext - - # OK, works on sane cases. Now check whether non-existent headers - # can be detected and how. - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <ac_nonexistent.h> -_ACEOF -if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 - (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 - ac_status=$? - grep -v '^ *+' conftest.er1 >conftest.err - rm -f conftest.er1 - cat conftest.err >&5 - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } >/dev/null; then - if test -s conftest.err; then - ac_cpp_err=$ac_c_preproc_warn_flag - else - ac_cpp_err= - fi -else - ac_cpp_err=yes -fi -if test -z "$ac_cpp_err"; then - # Broken: success on invalid input. -continue -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - - # Passes both tests. -ac_preproc_ok=: -break -fi -rm -f conftest.err conftest.$ac_ext - -done -# Because of `break', _AC_PREPROC_IFELSE's cleaning code was skipped. -rm -f conftest.err conftest.$ac_ext -if $ac_preproc_ok; then - break -fi - - done - ac_cv_prog_CPP=$CPP - -fi - CPP=$ac_cv_prog_CPP -else - ac_cv_prog_CPP=$CPP -fi -echo "$as_me:$LINENO: result: $CPP" >&5 -echo "${ECHO_T}$CPP" >&6 -ac_preproc_ok=false -for ac_c_preproc_warn_flag in '' yes -do - # Use a header file that comes with gcc, so configuring glibc - # with a fresh cross-compiler works. - # Prefer <limits.h> to <assert.h> if __STDC__ is defined, since - # <limits.h> exists even on freestanding compilers. - # On the NeXT, cc -E runs the code through the compiler's parser, - # not just through cpp. "Syntax error" is here to catch this case. - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#ifdef __STDC__ -# include <limits.h> -#else -# include <assert.h> -#endif - Syntax error -_ACEOF -if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 - (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 - ac_status=$? - grep -v '^ *+' conftest.er1 >conftest.err - rm -f conftest.er1 - cat conftest.err >&5 - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } >/dev/null; then - if test -s conftest.err; then - ac_cpp_err=$ac_c_preproc_warn_flag - else - ac_cpp_err= - fi -else - ac_cpp_err=yes -fi -if test -z "$ac_cpp_err"; then - : -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - - # Broken: fails on valid input. -continue -fi -rm -f conftest.err conftest.$ac_ext - - # OK, works on sane cases. Now check whether non-existent headers - # can be detected and how. - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <ac_nonexistent.h> -_ACEOF -if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 - (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 - ac_status=$? - grep -v '^ *+' conftest.er1 >conftest.err - rm -f conftest.er1 - cat conftest.err >&5 - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } >/dev/null; then - if test -s conftest.err; then - ac_cpp_err=$ac_c_preproc_warn_flag - else - ac_cpp_err= - fi -else - ac_cpp_err=yes -fi -if test -z "$ac_cpp_err"; then - # Broken: success on invalid input. -continue -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - - # Passes both tests. -ac_preproc_ok=: -break -fi -rm -f conftest.err conftest.$ac_ext - -done -# Because of `break', _AC_PREPROC_IFELSE's cleaning code was skipped. -rm -f conftest.err conftest.$ac_ext -if $ac_preproc_ok; then - : -else - { { echo "$as_me:$LINENO: error: C preprocessor \"$CPP\" fails sanity check -See \`config.log' for more details." >&5 -echo "$as_me: error: C preprocessor \"$CPP\" fails sanity check -See \`config.log' for more details." >&2;} - { (exit 1); exit 1; }; } -fi - -ac_ext=c -ac_cpp='$CPP $CPPFLAGS' -ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' -ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' -ac_compiler_gnu=$ac_cv_c_compiler_gnu - - -echo "$as_me:$LINENO: checking for egrep" >&5 -echo $ECHO_N "checking for egrep... $ECHO_C" >&6 -if test "${ac_cv_prog_egrep+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if echo a | (grep -E '(a|b)') >/dev/null 2>&1 - then ac_cv_prog_egrep='grep -E' - else ac_cv_prog_egrep='egrep' - fi -fi -echo "$as_me:$LINENO: result: $ac_cv_prog_egrep" >&5 -echo "${ECHO_T}$ac_cv_prog_egrep" >&6 - EGREP=$ac_cv_prog_egrep - - -echo "$as_me:$LINENO: checking for ANSI C header files" >&5 -echo $ECHO_N "checking for ANSI C header files... $ECHO_C" >&6 -if test "${ac_cv_header_stdc+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <stdlib.h> -#include <stdarg.h> -#include <string.h> -#include <float.h> - -int -main () -{ - - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_cv_header_stdc=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -ac_cv_header_stdc=no -fi -rm -f conftest.$ac_objext conftest.$ac_ext - -if test $ac_cv_header_stdc = yes; then - # SunOS 4.x string.h does not declare mem*, contrary to ANSI. - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <string.h> - -_ACEOF -if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | - $EGREP "memchr" >/dev/null 2>&1; then - : -else - ac_cv_header_stdc=no -fi -rm -f conftest* - -fi - -if test $ac_cv_header_stdc = yes; then - # ISC 2.0.2 stdlib.h does not declare free, contrary to ANSI. - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <stdlib.h> - -_ACEOF -if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | - $EGREP "free" >/dev/null 2>&1; then - : -else - ac_cv_header_stdc=no -fi -rm -f conftest* - -fi - -if test $ac_cv_header_stdc = yes; then - # /bin/cc in Irix-4.0.5 gets non-ANSI ctype macros unless using -ansi. - if test "$cross_compiling" = yes; then - : -else - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <ctype.h> -#if ((' ' & 0x0FF) == 0x020) -# define ISLOWER(c) ('a' <= (c) && (c) <= 'z') -# define TOUPPER(c) (ISLOWER(c) ? 'A' + ((c) - 'a') : (c)) -#else -# define ISLOWER(c) \ - (('a' <= (c) && (c) <= 'i') \ - || ('j' <= (c) && (c) <= 'r') \ - || ('s' <= (c) && (c) <= 'z')) -# define TOUPPER(c) (ISLOWER(c) ? ((c) | 0x40) : (c)) -#endif - -#define XOR(e, f) (((e) && !(f)) || (!(e) && (f))) -int -main () -{ - int i; - for (i = 0; i < 256; i++) - if (XOR (islower (i), ISLOWER (i)) - || toupper (i) != TOUPPER (i)) - exit(2); - exit (0); -} -_ACEOF -rm -f conftest$ac_exeext -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && { ac_try='./conftest$ac_exeext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - : -else - echo "$as_me: program exited with status $ac_status" >&5 -echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -( exit $ac_status ) -ac_cv_header_stdc=no -fi -rm -f core core.* *.core gmon.out bb.out conftest$ac_exeext conftest.$ac_objext conftest.$ac_ext -fi -fi -fi -echo "$as_me:$LINENO: result: $ac_cv_header_stdc" >&5 -echo "${ECHO_T}$ac_cv_header_stdc" >&6 -if test $ac_cv_header_stdc = yes; then - -cat >>confdefs.h <<\_ACEOF -#define STDC_HEADERS 1 -_ACEOF - -fi - -# On IRIX 5.3, sys/types and inttypes.h are conflicting. - - - - - - - - - -for ac_header in sys/types.h sys/stat.h stdlib.h string.h memory.h strings.h \ - inttypes.h stdint.h unistd.h -do -as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh` -echo "$as_me:$LINENO: checking for $ac_header" >&5 -echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 -if eval "test \"\${$as_ac_Header+set}\" = set"; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -$ac_includes_default - -#include <$ac_header> -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - eval "$as_ac_Header=yes" -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -eval "$as_ac_Header=no" -fi -rm -f conftest.$ac_objext conftest.$ac_ext -fi -echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 -echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 -if test `eval echo '${'$as_ac_Header'}'` = yes; then - cat >>confdefs.h <<_ACEOF -#define `echo "HAVE_$ac_header" | $as_tr_cpp` 1 -_ACEOF - -fi - -done - - - -for ac_header in dlfcn.h -do -as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh` -if eval "test \"\${$as_ac_Header+set}\" = set"; then - echo "$as_me:$LINENO: checking for $ac_header" >&5 -echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 -if eval "test \"\${$as_ac_Header+set}\" = set"; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -fi -echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 -echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 -else - # Is the header compilable? -echo "$as_me:$LINENO: checking $ac_header usability" >&5 -echo $ECHO_N "checking $ac_header usability... $ECHO_C" >&6 -cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -$ac_includes_default -#include <$ac_header> -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_header_compiler=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -ac_header_compiler=no -fi -rm -f conftest.$ac_objext conftest.$ac_ext -echo "$as_me:$LINENO: result: $ac_header_compiler" >&5 -echo "${ECHO_T}$ac_header_compiler" >&6 - -# Is the header present? -echo "$as_me:$LINENO: checking $ac_header presence" >&5 -echo $ECHO_N "checking $ac_header presence... $ECHO_C" >&6 -cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <$ac_header> -_ACEOF -if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 - (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 - ac_status=$? - grep -v '^ *+' conftest.er1 >conftest.err - rm -f conftest.er1 - cat conftest.err >&5 - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } >/dev/null; then - if test -s conftest.err; then - ac_cpp_err=$ac_c_preproc_warn_flag - else - ac_cpp_err= - fi -else - ac_cpp_err=yes -fi -if test -z "$ac_cpp_err"; then - ac_header_preproc=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - - ac_header_preproc=no -fi -rm -f conftest.err conftest.$ac_ext -echo "$as_me:$LINENO: result: $ac_header_preproc" >&5 -echo "${ECHO_T}$ac_header_preproc" >&6 - -# So? What about this header? -case $ac_header_compiler:$ac_header_preproc in - yes:no ) - { echo "$as_me:$LINENO: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&5 -echo "$as_me: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&2;} - { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the preprocessor's result" >&5 -echo "$as_me: WARNING: $ac_header: proceeding with the preprocessor's result" >&2;} - ( - cat <<\_ASBOX -## ------------------------------------ ## -## Report this to bug-autoconf@gnu.org. ## -## ------------------------------------ ## -_ASBOX - ) | - sed "s/^/$as_me: WARNING: /" >&2 - ;; - no:yes ) - { echo "$as_me:$LINENO: WARNING: $ac_header: present but cannot be compiled" >&5 -echo "$as_me: WARNING: $ac_header: present but cannot be compiled" >&2;} - { echo "$as_me:$LINENO: WARNING: $ac_header: check for missing prerequisite headers?" >&5 -echo "$as_me: WARNING: $ac_header: check for missing prerequisite headers?" >&2;} - { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the preprocessor's result" >&5 -echo "$as_me: WARNING: $ac_header: proceeding with the preprocessor's result" >&2;} - ( - cat <<\_ASBOX -## ------------------------------------ ## -## Report this to bug-autoconf@gnu.org. ## -## ------------------------------------ ## -_ASBOX - ) | - sed "s/^/$as_me: WARNING: /" >&2 - ;; -esac -echo "$as_me:$LINENO: checking for $ac_header" >&5 -echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 -if eval "test \"\${$as_ac_Header+set}\" = set"; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - eval "$as_ac_Header=$ac_header_preproc" -fi -echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 -echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 - -fi -if test `eval echo '${'$as_ac_Header'}'` = yes; then - cat >>confdefs.h <<_ACEOF -#define `echo "HAVE_$ac_header" | $as_tr_cpp` 1 -_ACEOF - -fi - -done - - - - - -# Only perform the check for file, if the check method requires it -case $deplibs_check_method in -file_magic*) - if test "$file_magic_cmd" = '$MAGIC_CMD'; then - echo "$as_me:$LINENO: checking for ${ac_tool_prefix}file" >&5 -echo $ECHO_N "checking for ${ac_tool_prefix}file... $ECHO_C" >&6 -if test "${lt_cv_path_MAGIC_CMD+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - case $MAGIC_CMD in - /*) - lt_cv_path_MAGIC_CMD="$MAGIC_CMD" # Let the user override the test with a path. - ;; - ?:/*) - lt_cv_path_MAGIC_CMD="$MAGIC_CMD" # Let the user override the test with a dos path. - ;; - *) - ac_save_MAGIC_CMD="$MAGIC_CMD" - IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS=":" - ac_dummy="/usr/bin:$PATH" - for ac_dir in $ac_dummy; do - test -z "$ac_dir" && ac_dir=. - if test -f $ac_dir/${ac_tool_prefix}file; then - lt_cv_path_MAGIC_CMD="$ac_dir/${ac_tool_prefix}file" - if test -n "$file_magic_test_file"; then - case $deplibs_check_method in - "file_magic "*) - file_magic_regex="`expr \"$deplibs_check_method\" : \"file_magic \(.*\)\"`" - MAGIC_CMD="$lt_cv_path_MAGIC_CMD" - if eval $file_magic_cmd \$file_magic_test_file 2> /dev/null | - egrep "$file_magic_regex" > /dev/null; then - : - else - cat <<EOF 1>&2 - -*** Warning: the command libtool uses to detect shared libraries, -*** $file_magic_cmd, produces output that libtool cannot recognize. -*** The result is that libtool may fail to recognize shared libraries -*** as such. This will affect the creation of libtool libraries that -*** depend on shared libraries, but programs linked with such libtool -*** libraries will work regardless of this problem. Nevertheless, you -*** may want to report the problem to your system manager and/or to -*** bug-libtool@gnu.org - -EOF - fi ;; - esac - fi - break - fi - done - IFS="$ac_save_ifs" - MAGIC_CMD="$ac_save_MAGIC_CMD" - ;; -esac -fi - -MAGIC_CMD="$lt_cv_path_MAGIC_CMD" -if test -n "$MAGIC_CMD"; then - echo "$as_me:$LINENO: result: $MAGIC_CMD" >&5 -echo "${ECHO_T}$MAGIC_CMD" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - -if test -z "$lt_cv_path_MAGIC_CMD"; then - if test -n "$ac_tool_prefix"; then - echo "$as_me:$LINENO: checking for file" >&5 -echo $ECHO_N "checking for file... $ECHO_C" >&6 -if test "${lt_cv_path_MAGIC_CMD+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - case $MAGIC_CMD in - /*) - lt_cv_path_MAGIC_CMD="$MAGIC_CMD" # Let the user override the test with a path. - ;; - ?:/*) - lt_cv_path_MAGIC_CMD="$MAGIC_CMD" # Let the user override the test with a dos path. - ;; - *) - ac_save_MAGIC_CMD="$MAGIC_CMD" - IFS="${IFS= }"; ac_save_ifs="$IFS"; IFS=":" - ac_dummy="/usr/bin:$PATH" - for ac_dir in $ac_dummy; do - test -z "$ac_dir" && ac_dir=. - if test -f $ac_dir/file; then - lt_cv_path_MAGIC_CMD="$ac_dir/file" - if test -n "$file_magic_test_file"; then - case $deplibs_check_method in - "file_magic "*) - file_magic_regex="`expr \"$deplibs_check_method\" : \"file_magic \(.*\)\"`" - MAGIC_CMD="$lt_cv_path_MAGIC_CMD" - if eval $file_magic_cmd \$file_magic_test_file 2> /dev/null | - egrep "$file_magic_regex" > /dev/null; then - : - else - cat <<EOF 1>&2 - -*** Warning: the command libtool uses to detect shared libraries, -*** $file_magic_cmd, produces output that libtool cannot recognize. -*** The result is that libtool may fail to recognize shared libraries -*** as such. This will affect the creation of libtool libraries that -*** depend on shared libraries, but programs linked with such libtool -*** libraries will work regardless of this problem. Nevertheless, you -*** may want to report the problem to your system manager and/or to -*** bug-libtool@gnu.org - -EOF - fi ;; - esac - fi - break - fi - done - IFS="$ac_save_ifs" - MAGIC_CMD="$ac_save_MAGIC_CMD" - ;; -esac -fi - -MAGIC_CMD="$lt_cv_path_MAGIC_CMD" -if test -n "$MAGIC_CMD"; then - echo "$as_me:$LINENO: result: $MAGIC_CMD" >&5 -echo "${ECHO_T}$MAGIC_CMD" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - - else - MAGIC_CMD=: - fi -fi - - fi - ;; -esac - -if test -n "$ac_tool_prefix"; then - # Extract the first word of "${ac_tool_prefix}ranlib", so it can be a program name with args. -set dummy ${ac_tool_prefix}ranlib; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 -if test "${ac_cv_prog_RANLIB+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -n "$RANLIB"; then - ac_cv_prog_RANLIB="$RANLIB" # Let the user override the test. -else -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - ac_cv_prog_RANLIB="${ac_tool_prefix}ranlib" - echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 - fi -done -done - -fi -fi -RANLIB=$ac_cv_prog_RANLIB -if test -n "$RANLIB"; then - echo "$as_me:$LINENO: result: $RANLIB" >&5 -echo "${ECHO_T}$RANLIB" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - -fi -if test -z "$ac_cv_prog_RANLIB"; then - ac_ct_RANLIB=$RANLIB - # Extract the first word of "ranlib", so it can be a program name with args. -set dummy ranlib; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 -if test "${ac_cv_prog_ac_ct_RANLIB+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -n "$ac_ct_RANLIB"; then - ac_cv_prog_ac_ct_RANLIB="$ac_ct_RANLIB" # Let the user override the test. -else -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - ac_cv_prog_ac_ct_RANLIB="ranlib" - echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 - fi -done -done - - test -z "$ac_cv_prog_ac_ct_RANLIB" && ac_cv_prog_ac_ct_RANLIB=":" -fi -fi -ac_ct_RANLIB=$ac_cv_prog_ac_ct_RANLIB -if test -n "$ac_ct_RANLIB"; then - echo "$as_me:$LINENO: result: $ac_ct_RANLIB" >&5 -echo "${ECHO_T}$ac_ct_RANLIB" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - - RANLIB=$ac_ct_RANLIB -else - RANLIB="$ac_cv_prog_RANLIB" -fi - -if test -n "$ac_tool_prefix"; then - # Extract the first word of "${ac_tool_prefix}strip", so it can be a program name with args. -set dummy ${ac_tool_prefix}strip; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 -if test "${ac_cv_prog_STRIP+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -n "$STRIP"; then - ac_cv_prog_STRIP="$STRIP" # Let the user override the test. -else -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - ac_cv_prog_STRIP="${ac_tool_prefix}strip" - echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 - fi -done -done - -fi -fi -STRIP=$ac_cv_prog_STRIP -if test -n "$STRIP"; then - echo "$as_me:$LINENO: result: $STRIP" >&5 -echo "${ECHO_T}$STRIP" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - -fi -if test -z "$ac_cv_prog_STRIP"; then - ac_ct_STRIP=$STRIP - # Extract the first word of "strip", so it can be a program name with args. -set dummy strip; ac_word=$2 -echo "$as_me:$LINENO: checking for $ac_word" >&5 -echo $ECHO_N "checking for $ac_word... $ECHO_C" >&6 -if test "${ac_cv_prog_ac_ct_STRIP+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test -n "$ac_ct_STRIP"; then - ac_cv_prog_ac_ct_STRIP="$ac_ct_STRIP" # Let the user override the test. -else -as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for ac_exec_ext in '' $ac_executable_extensions; do - if $as_executable_p "$as_dir/$ac_word$ac_exec_ext"; then - ac_cv_prog_ac_ct_STRIP="strip" - echo "$as_me:$LINENO: found $as_dir/$ac_word$ac_exec_ext" >&5 - break 2 - fi -done -done - - test -z "$ac_cv_prog_ac_ct_STRIP" && ac_cv_prog_ac_ct_STRIP=":" -fi -fi -ac_ct_STRIP=$ac_cv_prog_ac_ct_STRIP -if test -n "$ac_ct_STRIP"; then - echo "$as_me:$LINENO: result: $ac_ct_STRIP" >&5 -echo "${ECHO_T}$ac_ct_STRIP" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi - - STRIP=$ac_ct_STRIP -else - STRIP="$ac_cv_prog_STRIP" -fi - - -enable_dlopen=no -enable_win32_dll=no - -# Check whether --enable-libtool-lock or --disable-libtool-lock was given. -if test "${enable_libtool_lock+set}" = set; then - enableval="$enable_libtool_lock" - -fi; -test "x$enable_libtool_lock" != xno && enable_libtool_lock=yes - -# Some flags need to be propagated to the compiler or linker for good -# libtool support. -case $host in -*-*-irix6*) - # Find out which ABI we are using. - echo '#line 4014 "configure"' > conftest.$ac_ext - if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; then - case `/usr/bin/file conftest.$ac_objext` in - *32-bit*) - LD="${LD-ld} -32" - ;; - *N32*) - LD="${LD-ld} -n32" - ;; - *64-bit*) - LD="${LD-ld} -64" - ;; - esac - fi - rm -rf conftest* - ;; - -*-*-sco3.2v5*) - # On SCO OpenServer 5, we need -belf to get full-featured binaries. - SAVE_CFLAGS="$CFLAGS" - CFLAGS="$CFLAGS -belf" - echo "$as_me:$LINENO: checking whether the C compiler needs -belf" >&5 -echo $ECHO_N "checking whether the C compiler needs -belf... $ECHO_C" >&6 -if test "${lt_cv_cc_needs_belf+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - - - ac_ext=c -ac_cpp='$CPP $CPPFLAGS' -ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' -ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' -ac_compiler_gnu=$ac_cv_c_compiler_gnu - - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ - -int -main () -{ - - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext conftest$ac_exeext -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest$ac_exeext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - lt_cv_cc_needs_belf=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -lt_cv_cc_needs_belf=no -fi -rm -f conftest.$ac_objext conftest$ac_exeext conftest.$ac_ext - ac_ext=c -ac_cpp='$CPP $CPPFLAGS' -ac_compile='$CC -c $CFLAGS $CPPFLAGS conftest.$ac_ext >&5' -ac_link='$CC -o conftest$ac_exeext $CFLAGS $CPPFLAGS $LDFLAGS conftest.$ac_ext $LIBS >&5' -ac_compiler_gnu=$ac_cv_c_compiler_gnu - -fi -echo "$as_me:$LINENO: result: $lt_cv_cc_needs_belf" >&5 -echo "${ECHO_T}$lt_cv_cc_needs_belf" >&6 - if test x"$lt_cv_cc_needs_belf" != x"yes"; then - # this is probably gcc 2.8.0, egcs 1.0 or newer; no need for -belf - CFLAGS="$SAVE_CFLAGS" - fi - ;; - - -esac - -# Sed substitution that helps us do robust quoting. It backslashifies -# metacharacters that are still active within double-quoted strings. -Xsed='sed -e s/^X//' -sed_quote_subst='s/\([\\"\\`$\\\\]\)/\\\1/g' - -# Same as above, but do not quote variable references. -double_quote_subst='s/\([\\"\\`\\\\]\)/\\\1/g' - -# Sed substitution to delay expansion of an escaped shell variable in a -# double_quote_subst'ed string. -delay_variable_subst='s/\\\\\\\\\\\$/\\\\\\$/g' - -# Constants: -rm="rm -f" - -# Global variables: -default_ofile=libtool -can_build_shared=yes - -# All known linkers require a `.a' archive for static linking (except M$VC, -# which needs '.lib'). -libext=a -ltmain="$ac_aux_dir/ltmain.sh" -ofile="$default_ofile" -with_gnu_ld="$lt_cv_prog_gnu_ld" -need_locks="$enable_libtool_lock" - -old_CC="$CC" -old_CFLAGS="$CFLAGS" - -# Set sane defaults for various variables -test -z "$AR" && AR=ar -test -z "$AR_FLAGS" && AR_FLAGS=cru -test -z "$AS" && AS=as -test -z "$CC" && CC=cc -test -z "$DLLTOOL" && DLLTOOL=dlltool -test -z "$LD" && LD=ld -test -z "$LN_S" && LN_S="ln -s" -test -z "$MAGIC_CMD" && MAGIC_CMD=file -test -z "$NM" && NM=nm -test -z "$OBJDUMP" && OBJDUMP=objdump -test -z "$RANLIB" && RANLIB=: -test -z "$STRIP" && STRIP=: -test -z "$ac_objext" && ac_objext=o - -if test x"$host" != x"$build"; then - ac_tool_prefix=${host_alias}- -else - ac_tool_prefix= -fi - -# Transform linux* to *-*-linux-gnu*, to support old configure scripts. -case $host_os in -linux-gnu*) ;; -linux*) host=`echo $host | sed 's/^\(.*-.*-linux\)\(.*\)$/\1-gnu\2/'` -esac - -case $host_os in -aix3*) - # AIX sometimes has problems with the GCC collect2 program. For some - # reason, if we set the COLLECT_NAMES environment variable, the problems - # vanish in a puff of smoke. - if test "X${COLLECT_NAMES+set}" != Xset; then - COLLECT_NAMES= - export COLLECT_NAMES - fi - ;; -esac - -# Determine commands to create old-style static archives. -old_archive_cmds='$AR $AR_FLAGS $oldlib$oldobjs$old_deplibs' -old_postinstall_cmds='chmod 644 $oldlib' -old_postuninstall_cmds= - -if test -n "$RANLIB"; then - old_archive_cmds="$old_archive_cmds~\$RANLIB \$oldlib" - old_postinstall_cmds="\$RANLIB \$oldlib~$old_postinstall_cmds" -fi - -# Allow CC to be a program name with arguments. -set dummy $CC -compiler="$2" - -## FIXME: this should be a separate macro -## -echo "$as_me:$LINENO: checking for objdir" >&5 -echo $ECHO_N "checking for objdir... $ECHO_C" >&6 -rm -f .libs 2>/dev/null -mkdir .libs 2>/dev/null -if test -d .libs; then - objdir=.libs -else - # MS-DOS does not allow filenames that begin with a dot. - objdir=_libs -fi -rmdir .libs 2>/dev/null -echo "$as_me:$LINENO: result: $objdir" >&5 -echo "${ECHO_T}$objdir" >&6 -## -## END FIXME - - -## FIXME: this should be a separate macro -## - -# Check whether --with-pic or --without-pic was given. -if test "${with_pic+set}" = set; then - withval="$with_pic" - pic_mode="$withval" -else - pic_mode=default -fi; -test -z "$pic_mode" && pic_mode=default - -# We assume here that the value for lt_cv_prog_cc_pic will not be cached -# in isolation, and that seeing it set (from the cache) indicates that -# the associated values are set (in the cache) correctly too. -echo "$as_me:$LINENO: checking for $compiler option to produce PIC" >&5 -echo $ECHO_N "checking for $compiler option to produce PIC... $ECHO_C" >&6 -if test "${lt_cv_prog_cc_pic+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - lt_cv_prog_cc_pic= - lt_cv_prog_cc_shlib= - lt_cv_prog_cc_wl= - lt_cv_prog_cc_static= - lt_cv_prog_cc_no_builtin= - lt_cv_prog_cc_can_build_shared=$can_build_shared - - if test "$GCC" = yes; then - lt_cv_prog_cc_wl='-Wl,' - lt_cv_prog_cc_static='-static' - - case $host_os in - aix*) - # Below there is a dirty hack to force normal static linking with -ldl - # The problem is because libdl dynamically linked with both libc and - # libC (AIX C++ library), which obviously doesn't included in libraries - # list by gcc. This cause undefined symbols with -static flags. - # This hack allows C programs to be linked with "-static -ldl", but - # we not sure about C++ programs. - lt_cv_prog_cc_static="$lt_cv_prog_cc_static ${lt_cv_prog_cc_wl}-lC" - ;; - amigaos*) - # FIXME: we need at least 68020 code to build shared libraries, but - # adding the `-m68020' flag to GCC prevents building anything better, - # like `-m68040'. - lt_cv_prog_cc_pic='-m68020 -resident32 -malways-restore-a4' - ;; - beos* | irix5* | irix6* | osf3* | osf4* | osf5*) - # PIC is the default for these OSes. - ;; - darwin* | rhapsody*) - # PIC is the default on this platform - # Common symbols not allowed in MH_DYLIB files - lt_cv_prog_cc_pic='-fno-common' - ;; - cygwin* | mingw* | pw32* | os2*) - # This hack is so that the source file can tell whether it is being - # built for inclusion in a dll (and should export symbols for example). - lt_cv_prog_cc_pic='-DDLL_EXPORT' - ;; - sysv4*MP*) - if test -d /usr/nec; then - lt_cv_prog_cc_pic=-Kconform_pic - fi - ;; - *) - lt_cv_prog_cc_pic='-fPIC' - ;; - esac - else - # PORTME Check for PIC flags for the system compiler. - case $host_os in - aix3* | aix4* | aix5*) - # All AIX code is PIC. - if test "$host_cpu" = ia64; then - # AIX 5 now supports IA64 processor - lt_cv_prog_cc_static='-Bstatic' - lt_cv_prog_cc_wl='-Wl,' - else - lt_cv_prog_cc_static='-bnso -bI:/lib/syscalls.exp' - fi - ;; - - hpux9* | hpux10* | hpux11*) - # Is there a better lt_cv_prog_cc_static that works with the bundled CC? - lt_cv_prog_cc_wl='-Wl,' - lt_cv_prog_cc_static="${lt_cv_prog_cc_wl}-a ${lt_cv_prog_cc_wl}archive" - lt_cv_prog_cc_pic='+Z' - ;; - - irix5* | irix6*) - lt_cv_prog_cc_wl='-Wl,' - lt_cv_prog_cc_static='-non_shared' - # PIC (with -KPIC) is the default. - ;; - - cygwin* | mingw* | pw32* | os2*) - # This hack is so that the source file can tell whether it is being - # built for inclusion in a dll (and should export symbols for example). - lt_cv_prog_cc_pic='-DDLL_EXPORT' - ;; - - newsos6) - lt_cv_prog_cc_pic='-KPIC' - lt_cv_prog_cc_static='-Bstatic' - ;; - - osf3* | osf4* | osf5*) - # All OSF/1 code is PIC. - lt_cv_prog_cc_wl='-Wl,' - lt_cv_prog_cc_static='-non_shared' - ;; - - sco3.2v5*) - lt_cv_prog_cc_pic='-Kpic' - lt_cv_prog_cc_static='-dn' - lt_cv_prog_cc_shlib='-belf' - ;; - - solaris*) - lt_cv_prog_cc_pic='-KPIC' - lt_cv_prog_cc_static='-Bstatic' - lt_cv_prog_cc_wl='-Wl,' - ;; - - sunos4*) - lt_cv_prog_cc_pic='-PIC' - lt_cv_prog_cc_static='-Bstatic' - lt_cv_prog_cc_wl='-Qoption ld ' - ;; - - sysv4 | sysv4.2uw2* | sysv4.3* | sysv5*) - lt_cv_prog_cc_pic='-KPIC' - lt_cv_prog_cc_static='-Bstatic' - if test "x$host_vendor" = xsni; then - lt_cv_prog_cc_wl='-LD' - else - lt_cv_prog_cc_wl='-Wl,' - fi - ;; - - uts4*) - lt_cv_prog_cc_pic='-pic' - lt_cv_prog_cc_static='-Bstatic' - ;; - - sysv4*MP*) - if test -d /usr/nec ;then - lt_cv_prog_cc_pic='-Kconform_pic' - lt_cv_prog_cc_static='-Bstatic' - fi - ;; - - *) - lt_cv_prog_cc_can_build_shared=no - ;; - esac - fi - -fi - -if test -z "$lt_cv_prog_cc_pic"; then - echo "$as_me:$LINENO: result: none" >&5 -echo "${ECHO_T}none" >&6 -else - echo "$as_me:$LINENO: result: $lt_cv_prog_cc_pic" >&5 -echo "${ECHO_T}$lt_cv_prog_cc_pic" >&6 - - # Check to make sure the pic_flag actually works. - echo "$as_me:$LINENO: checking if $compiler PIC flag $lt_cv_prog_cc_pic works" >&5 -echo $ECHO_N "checking if $compiler PIC flag $lt_cv_prog_cc_pic works... $ECHO_C" >&6 - if test "${lt_cv_prog_cc_pic_works+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - save_CFLAGS="$CFLAGS" - CFLAGS="$CFLAGS $lt_cv_prog_cc_pic -DPIC" - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ - -int -main () -{ - - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - case $host_os in - hpux9* | hpux10* | hpux11*) - # On HP-UX, both CC and GCC only warn that PIC is supported... then - # they create non-PIC objects. So, if there were any warnings, we - # assume that PIC is not supported. - if test -s conftest.err; then - lt_cv_prog_cc_pic_works=no - else - lt_cv_prog_cc_pic_works=yes - fi - ;; - *) - lt_cv_prog_cc_pic_works=yes - ;; - esac - -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - - lt_cv_prog_cc_pic_works=no - -fi -rm -f conftest.$ac_objext conftest.$ac_ext - CFLAGS="$save_CFLAGS" - -fi - - - if test "X$lt_cv_prog_cc_pic_works" = Xno; then - lt_cv_prog_cc_pic= - lt_cv_prog_cc_can_build_shared=no - else - lt_cv_prog_cc_pic=" $lt_cv_prog_cc_pic" - fi - - echo "$as_me:$LINENO: result: $lt_cv_prog_cc_pic_works" >&5 -echo "${ECHO_T}$lt_cv_prog_cc_pic_works" >&6 -fi -## -## END FIXME - -# Check for any special shared library compilation flags. -if test -n "$lt_cv_prog_cc_shlib"; then - { echo "$as_me:$LINENO: WARNING: \`$CC' requires \`$lt_cv_prog_cc_shlib' to build shared libraries" >&5 -echo "$as_me: WARNING: \`$CC' requires \`$lt_cv_prog_cc_shlib' to build shared libraries" >&2;} - if echo "$old_CC $old_CFLAGS " | egrep -e "[ ]$lt_cv_prog_cc_shlib[ ]" >/dev/null; then : - else - { echo "$as_me:$LINENO: WARNING: add \`$lt_cv_prog_cc_shlib' to the CC or CFLAGS env variable and reconfigure" >&5 -echo "$as_me: WARNING: add \`$lt_cv_prog_cc_shlib' to the CC or CFLAGS env variable and reconfigure" >&2;} - lt_cv_prog_cc_can_build_shared=no - fi -fi - -## FIXME: this should be a separate macro -## -echo "$as_me:$LINENO: checking if $compiler static flag $lt_cv_prog_cc_static works" >&5 -echo $ECHO_N "checking if $compiler static flag $lt_cv_prog_cc_static works... $ECHO_C" >&6 -if test "${lt_cv_prog_cc_static_works+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - lt_cv_prog_cc_static_works=no - save_LDFLAGS="$LDFLAGS" - LDFLAGS="$LDFLAGS $lt_cv_prog_cc_static" - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ - -int -main () -{ - - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext conftest$ac_exeext -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest$ac_exeext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - lt_cv_prog_cc_static_works=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -fi -rm -f conftest.$ac_objext conftest$ac_exeext conftest.$ac_ext - LDFLAGS="$save_LDFLAGS" - -fi - - -# Belt *and* braces to stop my trousers falling down: -test "X$lt_cv_prog_cc_static_works" = Xno && lt_cv_prog_cc_static= -echo "$as_me:$LINENO: result: $lt_cv_prog_cc_static_works" >&5 -echo "${ECHO_T}$lt_cv_prog_cc_static_works" >&6 - -pic_flag="$lt_cv_prog_cc_pic" -special_shlib_compile_flags="$lt_cv_prog_cc_shlib" -wl="$lt_cv_prog_cc_wl" -link_static_flag="$lt_cv_prog_cc_static" -no_builtin_flag="$lt_cv_prog_cc_no_builtin" -can_build_shared="$lt_cv_prog_cc_can_build_shared" -## -## END FIXME - - -## FIXME: this should be a separate macro -## -# Check to see if options -o and -c are simultaneously supported by compiler -echo "$as_me:$LINENO: checking if $compiler supports -c -o file.$ac_objext" >&5 -echo $ECHO_N "checking if $compiler supports -c -o file.$ac_objext... $ECHO_C" >&6 -if test "${lt_cv_compiler_c_o+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - -$rm -r conftest 2>/dev/null -mkdir conftest -cd conftest -echo "int some_variable = 0;" > conftest.$ac_ext -mkdir out -# According to Tom Tromey, Ian Lance Taylor reported there are C compilers -# that will create temporary files in the current directory regardless of -# the output directory. Thus, making CWD read-only will cause this test -# to fail, enabling locking or at least warning the user not to do parallel -# builds. -chmod -w . -save_CFLAGS="$CFLAGS" -CFLAGS="$CFLAGS -o out/conftest2.$ac_objext" -compiler_c_o=no -if { (eval echo configure:4554: \"$ac_compile\") 1>&5; (eval $ac_compile) 2>out/conftest.err; } && test -s out/conftest2.$ac_objext; then - # The compiler can only warn and ignore the option if not recognized - # So say no if there are warnings - if test -s out/conftest.err; then - lt_cv_compiler_c_o=no - else - lt_cv_compiler_c_o=yes - fi -else - # Append any errors to the config.log. - cat out/conftest.err 1>&5 - lt_cv_compiler_c_o=no -fi -CFLAGS="$save_CFLAGS" -chmod u+w . -$rm conftest* out/* -rmdir out -cd .. -rmdir conftest -$rm -r conftest 2>/dev/null - -fi - -compiler_c_o=$lt_cv_compiler_c_o -echo "$as_me:$LINENO: result: $compiler_c_o" >&5 -echo "${ECHO_T}$compiler_c_o" >&6 - -if test x"$compiler_c_o" = x"yes"; then - # Check to see if we can write to a .lo - echo "$as_me:$LINENO: checking if $compiler supports -c -o file.lo" >&5 -echo $ECHO_N "checking if $compiler supports -c -o file.lo... $ECHO_C" >&6 - if test "${lt_cv_compiler_o_lo+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - - lt_cv_compiler_o_lo=no - save_CFLAGS="$CFLAGS" - CFLAGS="$CFLAGS -c -o conftest.lo" - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ - -int -main () -{ -int some_variable = 0; - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - # The compiler can only warn and ignore the option if not recognized - # So say no if there are warnings - if test -s conftest.err; then - lt_cv_compiler_o_lo=no - else - lt_cv_compiler_o_lo=yes - fi - -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -fi -rm -f conftest.$ac_objext conftest.$ac_ext - CFLAGS="$save_CFLAGS" - -fi - - compiler_o_lo=$lt_cv_compiler_o_lo - echo "$as_me:$LINENO: result: $compiler_c_lo" >&5 -echo "${ECHO_T}$compiler_c_lo" >&6 -else - compiler_o_lo=no -fi -## -## END FIXME - -## FIXME: this should be a separate macro -## -# Check to see if we can do hard links to lock some files if needed -hard_links="nottested" -if test "$compiler_c_o" = no && test "$need_locks" != no; then - # do not overwrite the value of need_locks provided by the user - echo "$as_me:$LINENO: checking if we can lock with hard links" >&5 -echo $ECHO_N "checking if we can lock with hard links... $ECHO_C" >&6 - hard_links=yes - $rm conftest* - ln conftest.a conftest.b 2>/dev/null && hard_links=no - touch conftest.a - ln conftest.a conftest.b 2>&5 || hard_links=no - ln conftest.a conftest.b 2>/dev/null && hard_links=no - echo "$as_me:$LINENO: result: $hard_links" >&5 -echo "${ECHO_T}$hard_links" >&6 - if test "$hard_links" = no; then - { echo "$as_me:$LINENO: WARNING: \`$CC' does not support \`-c -o', so \`make -j' may be unsafe" >&5 -echo "$as_me: WARNING: \`$CC' does not support \`-c -o', so \`make -j' may be unsafe" >&2;} - need_locks=warn - fi -else - need_locks=no -fi -## -## END FIXME - -## FIXME: this should be a separate macro -## -if test "$GCC" = yes; then - # Check to see if options -fno-rtti -fno-exceptions are supported by compiler - echo "$as_me:$LINENO: checking if $compiler supports -fno-rtti -fno-exceptions" >&5 -echo $ECHO_N "checking if $compiler supports -fno-rtti -fno-exceptions... $ECHO_C" >&6 - echo "int some_variable = 0;" > conftest.$ac_ext - save_CFLAGS="$CFLAGS" - CFLAGS="$CFLAGS -fno-rtti -fno-exceptions -c conftest.$ac_ext" - compiler_rtti_exceptions=no - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ - -int -main () -{ -int some_variable = 0; - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - # The compiler can only warn and ignore the option if not recognized - # So say no if there are warnings - if test -s conftest.err; then - compiler_rtti_exceptions=no - else - compiler_rtti_exceptions=yes - fi - -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -fi -rm -f conftest.$ac_objext conftest.$ac_ext - CFLAGS="$save_CFLAGS" - echo "$as_me:$LINENO: result: $compiler_rtti_exceptions" >&5 -echo "${ECHO_T}$compiler_rtti_exceptions" >&6 - - if test "$compiler_rtti_exceptions" = "yes"; then - no_builtin_flag=' -fno-builtin -fno-rtti -fno-exceptions' - else - no_builtin_flag=' -fno-builtin' - fi -fi -## -## END FIXME - -## FIXME: this should be a separate macro -## -# See if the linker supports building shared libraries. -echo "$as_me:$LINENO: checking whether the linker ($LD) supports shared libraries" >&5 -echo $ECHO_N "checking whether the linker ($LD) supports shared libraries... $ECHO_C" >&6 - -allow_undefined_flag= -no_undefined_flag= -need_lib_prefix=unknown -need_version=unknown -# when you set need_version to no, make sure it does not cause -set_version -# flags to be left without arguments -archive_cmds= -archive_expsym_cmds= -old_archive_from_new_cmds= -old_archive_from_expsyms_cmds= -export_dynamic_flag_spec= -whole_archive_flag_spec= -thread_safe_flag_spec= -hardcode_into_libs=no -hardcode_libdir_flag_spec= -hardcode_libdir_separator= -hardcode_direct=no -hardcode_minus_L=no -hardcode_shlibpath_var=unsupported -runpath_var= -link_all_deplibs=unknown -always_export_symbols=no -export_symbols_cmds='$NM $libobjs $convenience | $global_symbol_pipe | sed '\''s/.* //'\'' | sort | uniq > $export_symbols' -# include_expsyms should be a list of space-separated symbols to be *always* -# included in the symbol list -include_expsyms= -# exclude_expsyms can be an egrep regular expression of symbols to exclude -# it will be wrapped by ` (' and `)$', so one must not match beginning or -# end of line. Example: `a|bc|.*d.*' will exclude the symbols `a' and `bc', -# as well as any symbol that contains `d'. -exclude_expsyms="_GLOBAL_OFFSET_TABLE_" -# Although _GLOBAL_OFFSET_TABLE_ is a valid symbol C name, most a.out -# platforms (ab)use it in PIC code, but their linkers get confused if -# the symbol is explicitly referenced. Since portable code cannot -# rely on this symbol name, it's probably fine to never include it in -# preloaded symbol tables. -extract_expsyms_cmds= - -case $host_os in -cygwin* | mingw* | pw32* ) - # FIXME: the MSVC++ port hasn't been tested in a loooong time - # When not using gcc, we currently assume that we are using - # Microsoft Visual C++. - if test "$GCC" != yes; then - with_gnu_ld=no - fi - ;; - -esac - -ld_shlibs=yes -if test "$with_gnu_ld" = yes; then - # If archive_cmds runs LD, not CC, wlarc should be empty - wlarc='${wl}' - - # See if GNU ld supports shared libraries. - case $host_os in - aix3* | aix4* | aix5*) - # On AIX, the GNU linker is very broken - # Note:Check GNU linker on AIX 5-IA64 when/if it becomes available. - ld_shlibs=no - cat <<EOF 1>&2 - -*** Warning: the GNU linker, at least up to release 2.9.1, is reported -*** to be unable to reliably create shared libraries on AIX. -*** Therefore, libtool is disabling shared libraries support. If you -*** really care for shared libraries, you may want to modify your PATH -*** so that a non-GNU linker is found, and then restart. - -EOF - ;; - - amigaos*) - archive_cmds='$rm $output_objdir/a2ixlibrary.data~$echo "#define NAME $libname" > $output_objdir/a2ixlibrary.data~$echo "#define LIBRARY_ID 1" >> $output_objdir/a2ixlibrary.data~$echo "#define VERSION $major" >> $output_objdir/a2ixlibrary.data~$echo "#define REVISION $revision" >> $output_objdir/a2ixlibrary.data~$AR $AR_FLAGS $lib $libobjs~$RANLIB $lib~(cd $output_objdir && a2ixlibrary -32)' - hardcode_libdir_flag_spec='-L$libdir' - hardcode_minus_L=yes - - # Samuel A. Falvo II <kc5tja@dolphin.openprojects.net> reports - # that the semantics of dynamic libraries on AmigaOS, at least up - # to version 4, is to share data among multiple programs linked - # with the same dynamic library. Since this doesn't match the - # behavior of shared libraries on other platforms, we can use - # them. - ld_shlibs=no - ;; - - beos*) - if $LD --help 2>&1 | egrep ': supported targets:.* elf' > /dev/null; then - allow_undefined_flag=unsupported - # Joseph Beckenbach <jrb3@best.com> says some releases of gcc - # support --undefined. This deserves some investigation. FIXME - archive_cmds='$CC -nostart $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' - else - ld_shlibs=no - fi - ;; - - cygwin* | mingw* | pw32*) - # hardcode_libdir_flag_spec is actually meaningless, as there is - # no search path for DLLs. - hardcode_libdir_flag_spec='-L$libdir' - allow_undefined_flag=unsupported - always_export_symbols=yes - - extract_expsyms_cmds='test -f $output_objdir/impgen.c || \ - sed -e "/^# \/\* impgen\.c starts here \*\//,/^# \/\* impgen.c ends here \*\// { s/^# //;s/^# *$//; p; }" -e d < $''0 > $output_objdir/impgen.c~ - test -f $output_objdir/impgen.exe || (cd $output_objdir && \ - if test "x$HOST_CC" != "x" ; then $HOST_CC -o impgen impgen.c ; \ - else $CC -o impgen impgen.c ; fi)~ - $output_objdir/impgen $dir/$soroot > $output_objdir/$soname-def' - - old_archive_from_expsyms_cmds='$DLLTOOL --as=$AS --dllname $soname --def $output_objdir/$soname-def --output-lib $output_objdir/$newlib' - - # cygwin and mingw dlls have different entry points and sets of symbols - # to exclude. - # FIXME: what about values for MSVC? - dll_entry=__cygwin_dll_entry@12 - dll_exclude_symbols=DllMain@12,_cygwin_dll_entry@12,_cygwin_noncygwin_dll_entry@12~ - case $host_os in - mingw*) - # mingw values - dll_entry=_DllMainCRTStartup@12 - dll_exclude_symbols=DllMain@12,DllMainCRTStartup@12,DllEntryPoint@12~ - ;; - esac - - # mingw and cygwin differ, and it's simplest to just exclude the union - # of the two symbol sets. - dll_exclude_symbols=DllMain@12,_cygwin_dll_entry@12,_cygwin_noncygwin_dll_entry@12,DllMainCRTStartup@12,DllEntryPoint@12 - - # recent cygwin and mingw systems supply a stub DllMain which the user - # can override, but on older systems we have to supply one (in ltdll.c) - if test "x$lt_cv_need_dllmain" = "xyes"; then - ltdll_obj='$output_objdir/$soname-ltdll.'"$ac_objext " - ltdll_cmds='test -f $output_objdir/$soname-ltdll.c || sed -e "/^# \/\* ltdll\.c starts here \*\//,/^# \/\* ltdll.c ends here \*\// { s/^# //; p; }" -e d < [$]0 > $output_objdir/$soname-ltdll.c~ - test -f $output_objdir/$soname-ltdll.$ac_objext || (cd $output_objdir && $CC -c $soname-ltdll.c)~' - else - ltdll_obj= - ltdll_cmds= - fi - - # Extract the symbol export list from an `--export-all' def file, - # then regenerate the def file from the symbol export list, so that - # the compiled dll only exports the symbol export list. - # Be careful not to strip the DATA tag left be newer dlltools. - export_symbols_cmds="$ltdll_cmds"' - $DLLTOOL --export-all --exclude-symbols '$dll_exclude_symbols' --output-def $output_objdir/$soname-def '$ltdll_obj'$libobjs $convenience~ - sed -e "1,/EXPORTS/d" -e "s/ @ [0-9]*//" -e "s/ *;.*$//" < $output_objdir/$soname-def > $export_symbols' - - # If the export-symbols file already is a .def file (1st line - # is EXPORTS), use it as is. - # If DATA tags from a recent dlltool are present, honour them! - archive_expsym_cmds='if test "x`head -1 $export_symbols`" = xEXPORTS; then - cp $export_symbols $output_objdir/$soname-def; - else - echo EXPORTS > $output_objdir/$soname-def; - _lt_hint=1; - cat $export_symbols | while read symbol; do - set dummy \$symbol; - case \$# in - 2) echo " \$2 @ \$_lt_hint ; " >> $output_objdir/$soname-def;; - *) echo " \$2 @ \$_lt_hint \$3 ; " >> $output_objdir/$soname-def;; - esac; - _lt_hint=`expr 1 + \$_lt_hint`; - done; - fi~ - '"$ltdll_cmds"' - $CC -Wl,--base-file,$output_objdir/$soname-base '$lt_cv_cc_dll_switch' -Wl,-e,'$dll_entry' -o $output_objdir/$soname '$ltdll_obj'$libobjs $deplibs $compiler_flags~ - $DLLTOOL --as=$AS --dllname $soname --exclude-symbols '$dll_exclude_symbols' --def $output_objdir/$soname-def --base-file $output_objdir/$soname-base --output-exp $output_objdir/$soname-exp~ - $CC -Wl,--base-file,$output_objdir/$soname-base $output_objdir/$soname-exp '$lt_cv_cc_dll_switch' -Wl,-e,'$dll_entry' -o $output_objdir/$soname '$ltdll_obj'$libobjs $deplibs $compiler_flags~ - $DLLTOOL --as=$AS --dllname $soname --exclude-symbols '$dll_exclude_symbols' --def $output_objdir/$soname-def --base-file $output_objdir/$soname-base --output-exp $output_objdir/$soname-exp --output-lib $output_objdir/$libname.dll.a~ - $CC $output_objdir/$soname-exp '$lt_cv_cc_dll_switch' -Wl,-e,'$dll_entry' -o $output_objdir/$soname '$ltdll_obj'$libobjs $deplibs $compiler_flags' - ;; - - netbsd*) - if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then - archive_cmds='$LD -Bshareable $libobjs $deplibs $linker_flags -o $lib' - wlarc= - else - archive_cmds='$CC -shared -nodefaultlibs $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' - archive_expsym_cmds='$CC -shared -nodefaultlibs $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' - fi - ;; - - solaris* | sysv5*) - if $LD -v 2>&1 | egrep 'BFD 2\.8' > /dev/null; then - ld_shlibs=no - cat <<EOF 1>&2 - -*** Warning: The releases 2.8.* of the GNU linker cannot reliably -*** create shared libraries on Solaris systems. Therefore, libtool -*** is disabling shared libraries support. We urge you to upgrade GNU -*** binutils to release 2.9.1 or newer. Another option is to modify -*** your PATH or compiler configuration so that the native linker is -*** used, and then restart. - -EOF - elif $LD --help 2>&1 | egrep ': supported targets:.* elf' > /dev/null; then - archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' - archive_expsym_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' - else - ld_shlibs=no - fi - ;; - - sunos4*) - archive_cmds='$LD -assert pure-text -Bshareable -o $lib $libobjs $deplibs $linker_flags' - wlarc= - hardcode_direct=yes - hardcode_shlibpath_var=no - ;; - - *) - if $LD --help 2>&1 | egrep ': supported targets:.* elf' > /dev/null; then - archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname -o $lib' - archive_expsym_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname $wl$soname ${wl}-retain-symbols-file $wl$export_symbols -o $lib' - else - ld_shlibs=no - fi - ;; - esac - - if test "$ld_shlibs" = yes; then - runpath_var=LD_RUN_PATH - hardcode_libdir_flag_spec='${wl}--rpath ${wl}$libdir' - export_dynamic_flag_spec='${wl}--export-dynamic' - case $host_os in - cygwin* | mingw* | pw32*) - # dlltool doesn't understand --whole-archive et. al. - whole_archive_flag_spec= - ;; - *) - # ancient GNU ld didn't support --whole-archive et. al. - if $LD --help 2>&1 | egrep 'no-whole-archive' > /dev/null; then - whole_archive_flag_spec="$wlarc"'--whole-archive$convenience '"$wlarc"'--no-whole-archive' - else - whole_archive_flag_spec= - fi - ;; - esac - fi -else - # PORTME fill in a description of your system's linker (not GNU ld) - case $host_os in - aix3*) - allow_undefined_flag=unsupported - always_export_symbols=yes - archive_expsym_cmds='$LD -o $output_objdir/$soname $libobjs $deplibs $linker_flags -bE:$export_symbols -T512 -H512 -bM:SRE~$AR $AR_FLAGS $lib $output_objdir/$soname' - # Note: this linker hardcodes the directories in LIBPATH if there - # are no directories specified by -L. - hardcode_minus_L=yes - if test "$GCC" = yes && test -z "$link_static_flag"; then - # Neither direct hardcoding nor static linking is supported with a - # broken collect2. - hardcode_direct=unsupported - fi - ;; - - aix4* | aix5*) - # When large executables or shared objects are built, AIX ld can - # have problems creating the table of contents. If linking a library - # or program results in "error TOC overflow" add -mminimal-toc to - # CXXFLAGS/CFLAGS for g++/gcc. In the cases where that is not - # enough to fix the problem, add -Wl,-bbigtoc to LDFLAGS. - - archive_cmds='' - hardcode_libdir_separator=':' - if test "$GCC" = yes; then - collect2name=`${CC} -print-prog-name=collect2` - if test -f "$collect2name" && \ - strings "$collect2name" | grep resolve_lib_name >/dev/null - then - # We have reworked collect2 - hardcode_direct=yes - else - # We have old collect2 - hardcode_direct=unsupported - # It fails to find uninstalled libraries when the uninstalled - # path is not listed in the libpath. Setting hardcode_minus_L - # to unsupported forces relinking - hardcode_minus_L=yes - hardcode_libdir_flag_spec='-L$libdir' - hardcode_libdir_separator= - fi - shared_flag='-shared' - else - if test "$host_cpu" = ia64; then - shared_flag='-G' - else - shared_flag='${wl}-bM:SRE' - fi - hardcode_direct=yes - fi - - if test "$host_cpu" = ia64; then - # On IA64, the linker does run time linking by default, so we don't - # have to do anything special. - aix_use_runtimelinking=no - exp_sym_flag='-Bexport' - no_entry_flag="" - else - # Test if we are trying to use run time linking, or normal AIX style linking. - # If -brtl is somewhere in LDFLAGS, we need to do run time linking. - aix_use_runtimelinking=no - for ld_flag in $LDFLAGS; do - if (test $ld_flag = "-brtl" || test $ld_flag = "-Wl,-brtl" ); then - aix_use_runtimelinking=yes - break - fi - done - exp_sym_flag='-bexport' - no_entry_flag='-bnoentry' - fi - # It seems that -bexpall can do strange things, so it is better to - # generate a list of symbols to export. - always_export_symbols=yes - if test "$aix_use_runtimelinking" = yes; then - hardcode_libdir_flag_spec='${wl}-blibpath:$libdir:/usr/lib:/lib' - allow_undefined_flag=' -Wl,-G' - archive_expsym_cmds="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs $compiler_flags ${allow_undefined_flag} '"\${wl}$no_entry_flag \${wl}$exp_sym_flag:\$export_symbols" - else - if test "$host_cpu" = ia64; then - hardcode_libdir_flag_spec='${wl}-R $libdir:/usr/lib:/lib' - allow_undefined_flag="-znodefs" - archive_expsym_cmds="\$CC $shared_flag"' -o $output_objdir/$soname ${wl}-h$soname $libobjs $deplibs $compiler_flags ${wl}${allow_undefined_flag} '"\${wl}$no_entry_flag \${wl}$exp_sym_flag:\$export_symbols" - else - hardcode_libdir_flag_spec='${wl}-bnolibpath ${wl}-blibpath:$libdir:/usr/lib:/lib' - # Warning - without using the other run time loading flags, -berok will - # link without error, but may produce a broken library. - allow_undefined_flag='${wl}-berok" - # This is a bit strange, but is similar to how AIX traditionally builds - # it's shared libraries. - archive_expsym_cmds="\$CC $shared_flag"' -o $output_objdir/$soname $libobjs $deplibs $compiler_flags ${allow_undefined_flag} '"\${wl}$no_entry_flag \${wl}$exp_sym_flag:\$export_symbols"' ~$AR -crlo $objdir/$libname$release.a $objdir/$soname' - fi - fi - ;; - - amigaos*) - archive_cmds='$rm $output_objdir/a2ixlibrary.data~$echo "#define NAME $libname" > $output_objdir/a2ixlibrary.data~$echo "#define LIBRARY_ID 1" >> $output_objdir/a2ixlibrary.data~$echo "#define VERSION $major" >> $output_objdir/a2ixlibrary.data~$echo "#define REVISION $revision" >> $output_objdir/a2ixlibrary.data~$AR $AR_FLAGS $lib $libobjs~$RANLIB $lib~(cd $output_objdir && a2ixlibrary -32)' - hardcode_libdir_flag_spec='-L$libdir' - hardcode_minus_L=yes - # see comment about different semantics on the GNU ld section - ld_shlibs=no - ;; - - cygwin* | mingw* | pw32*) - # When not using gcc, we currently assume that we are using - # Microsoft Visual C++. - # hardcode_libdir_flag_spec is actually meaningless, as there is - # no search path for DLLs. - hardcode_libdir_flag_spec=' ' - allow_undefined_flag=unsupported - # Tell ltmain to make .lib files, not .a files. - libext=lib - # FIXME: Setting linknames here is a bad hack. - archive_cmds='$CC -o $lib $libobjs $compiler_flags `echo "$deplibs" | sed -e '\''s/ -lc$//'\''` -link -dll~linknames=' - # The linker will automatically build a .lib file if we build a DLL. - old_archive_from_new_cmds='true' - # FIXME: Should let the user specify the lib program. - old_archive_cmds='lib /OUT:$oldlib$oldobjs$old_deplibs' - fix_srcfile_path='`cygpath -w "$srcfile"`' - ;; - - darwin* | rhapsody*) - # This patch put in by hand by PH (10-Dec-2003) for Darwin 1.3. - case "$host_os" in - rhapsody* | darwin1.[[012]]) - allow_undefined_flag='-undefined suppress' - ;; - *) # Darwin 1.3 on - allow_undefined_flag='-flat_namespace -undefined suppress' - ;; - esac - # End of hand-inserted patch - - # FIXME: Relying on posixy $() will cause problems for - # cross-compilation, but unfortunately the echo tests do not - # yet detect zsh echo's removal of \ escapes. - archive_cmds='$CC $(test .$module = .yes && echo -bundle || echo -dynamiclib) $allow_undefined_flag -o $lib $libobjs $deplibs$linkopts -install_name $rpath/$soname $(test -n "$verstring" -a x$verstring != x0.0 && echo $verstring)' - # We need to add '_' to the symbols in $export_symbols first - #archive_expsym_cmds="$archive_cmds"' && strip -s $export_symbols' - hardcode_direct=yes - hardcode_shlibpath_var=no - whole_archive_flag_spec='-all_load $convenience' - ;; - - freebsd1*) - ld_shlibs=no - ;; - - # FreeBSD 2.2.[012] allows us to include c++rt0.o to get C++ constructor - # support. Future versions do this automatically, but an explicit c++rt0.o - # does not break anything, and helps significantly (at the cost of a little - # extra space). - freebsd2.2*) - archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags /usr/lib/c++rt0.o' - hardcode_libdir_flag_spec='-R$libdir' - hardcode_direct=yes - hardcode_shlibpath_var=no - ;; - - # Unfortunately, older versions of FreeBSD 2 do not have this feature. - freebsd2*) - archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' - hardcode_direct=yes - hardcode_minus_L=yes - hardcode_shlibpath_var=no - ;; - - # FreeBSD 3 and greater uses gcc -shared to do shared libraries. - freebsd*) - archive_cmds='$CC -shared -o $lib $libobjs $deplibs $compiler_flags' - hardcode_libdir_flag_spec='-R$libdir' - hardcode_direct=yes - hardcode_shlibpath_var=no - ;; - - hpux9* | hpux10* | hpux11*) - case $host_os in - hpux9*) archive_cmds='$rm $output_objdir/$soname~$LD -b +b $install_libdir -o $output_objdir/$soname $libobjs $deplibs $linker_flags~test $output_objdir/$soname = $lib || mv $output_objdir/$soname $lib' ;; - *) archive_cmds='$LD -b +h $soname +b $install_libdir -o $lib $libobjs $deplibs $linker_flags' ;; - esac - hardcode_libdir_flag_spec='${wl}+b ${wl}$libdir' - hardcode_libdir_separator=: - hardcode_direct=yes - hardcode_minus_L=yes # Not in the search PATH, but as the default - # location of the library. - export_dynamic_flag_spec='${wl}-E' - ;; - - irix5* | irix6*) - if test "$GCC" = yes; then - archive_cmds='$CC -shared $libobjs $deplibs $compiler_flags ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' - else - archive_cmds='$LD -shared $libobjs $deplibs $linker_flags -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' - fi - hardcode_libdir_flag_spec='${wl}-rpath ${wl}$libdir' - hardcode_libdir_separator=: - link_all_deplibs=yes - ;; - - netbsd*) - if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then - archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' # a.out - else - archive_cmds='$LD -shared -o $lib $libobjs $deplibs $linker_flags' # ELF - fi - hardcode_libdir_flag_spec='-R$libdir' - hardcode_direct=yes - hardcode_shlibpath_var=no - ;; - - newsos6) - archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linkopts' - hardcode_direct=yes - hardcode_libdir_flag_spec='${wl}-rpath ${wl}$libdir' - hardcode_libdir_separator=: - hardcode_shlibpath_var=no - ;; - - openbsd*) - archive_cmds='$LD -Bshareable -o $lib $libobjs $deplibs $linker_flags' - hardcode_libdir_flag_spec='-R$libdir' - hardcode_direct=yes - hardcode_shlibpath_var=no - ;; - - os2*) - hardcode_libdir_flag_spec='-L$libdir' - hardcode_minus_L=yes - allow_undefined_flag=unsupported - archive_cmds='$echo "LIBRARY $libname INITINSTANCE" > $output_objdir/$libname.def~$echo "DESCRIPTION \"$libname\"" >> $output_objdir/$libname.def~$echo DATA >> $output_objdir/$libname.def~$echo " SINGLE NONSHARED" >> $output_objdir/$libname.def~$echo EXPORTS >> $output_objdir/$libname.def~emxexp $libobjs >> $output_objdir/$libname.def~$CC -Zdll -Zcrtdll -o $lib $libobjs $deplibs $compiler_flags $output_objdir/$libname.def' - old_archive_from_new_cmds='emximp -o $output_objdir/$libname.a $output_objdir/$libname.def' - ;; - - osf3*) - if test "$GCC" = yes; then - allow_undefined_flag=' ${wl}-expect_unresolved ${wl}\*' - archive_cmds='$CC -shared${allow_undefined_flag} $libobjs $deplibs $compiler_flags ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' - else - allow_undefined_flag=' -expect_unresolved \*' - archive_cmds='$LD -shared${allow_undefined_flag} $libobjs $deplibs $linker_flags -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' - fi - hardcode_libdir_flag_spec='${wl}-rpath ${wl}$libdir' - hardcode_libdir_separator=: - ;; - - osf4* | osf5*) # as osf3* with the addition of -msym flag - if test "$GCC" = yes; then - allow_undefined_flag=' ${wl}-expect_unresolved ${wl}\*' - archive_cmds='$CC -shared${allow_undefined_flag} $libobjs $deplibs $compiler_flags ${wl}-msym ${wl}-soname ${wl}$soname `test -n "$verstring" && echo ${wl}-set_version ${wl}$verstring` ${wl}-update_registry ${wl}${output_objdir}/so_locations -o $lib' - hardcode_libdir_flag_spec='${wl}-rpath ${wl}$libdir' - else - allow_undefined_flag=' -expect_unresolved \*' - archive_cmds='$LD -shared${allow_undefined_flag} $libobjs $deplibs $linker_flags -msym -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${output_objdir}/so_locations -o $lib' - archive_expsym_cmds='for i in `cat $export_symbols`; do printf "-exported_symbol " >> $lib.exp; echo "\$i" >> $lib.exp; done; echo "-hidden">> $lib.exp~ - $LD -shared${allow_undefined_flag} -input $lib.exp $linker_flags $libobjs $deplibs -soname $soname `test -n "$verstring" && echo -set_version $verstring` -update_registry ${objdir}/so_locations -o $lib~$rm $lib.exp' - - #Both c and cxx compiler support -rpath directly - hardcode_libdir_flag_spec='-rpath $libdir' - fi - hardcode_libdir_separator=: - ;; - - sco3.2v5*) - archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' - hardcode_shlibpath_var=no - runpath_var=LD_RUN_PATH - hardcode_runpath_var=yes - ;; - - solaris*) - no_undefined_flag=' -z defs' - # $CC -shared without GNU ld will not create a library from C++ - # object files and a static libstdc++, better avoid it by now - archive_cmds='$LD -G${allow_undefined_flag} -h $soname -o $lib $libobjs $deplibs $linker_flags' - archive_expsym_cmds='$echo "{ global:" > $lib.exp~cat $export_symbols | sed -e "s/\(.*\)/\1;/" >> $lib.exp~$echo "local: *; };" >> $lib.exp~ - $LD -G${allow_undefined_flag} -M $lib.exp -h $soname -o $lib $libobjs $deplibs $linker_flags~$rm $lib.exp' - hardcode_libdir_flag_spec='-R$libdir' - hardcode_shlibpath_var=no - case $host_os in - solaris2.[0-5] | solaris2.[0-5].*) ;; - *) # Supported since Solaris 2.6 (maybe 2.5.1?) - whole_archive_flag_spec='-z allextract$convenience -z defaultextract' ;; - esac - link_all_deplibs=yes - ;; - - sunos4*) - if test "x$host_vendor" = xsequent; then - # Use $CC to link under sequent, because it throws in some extra .o - # files that make .init and .fini sections work. - archive_cmds='$CC -G ${wl}-h $soname -o $lib $libobjs $deplibs $compiler_flags' - else - archive_cmds='$LD -assert pure-text -Bstatic -o $lib $libobjs $deplibs $linker_flags' - fi - hardcode_libdir_flag_spec='-L$libdir' - hardcode_direct=yes - hardcode_minus_L=yes - hardcode_shlibpath_var=no - ;; - - sysv4) - if test "x$host_vendor" = xsno; then - archive_cmds='$LD -G -Bsymbolic -h $soname -o $lib $libobjs $deplibs $linkopts' - hardcode_direct=yes # is this really true??? - else - archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' - hardcode_direct=no #Motorola manual says yes, but my tests say they lie - fi - runpath_var='LD_RUN_PATH' - hardcode_shlibpath_var=no - ;; - - sysv4.3*) - archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' - hardcode_shlibpath_var=no - export_dynamic_flag_spec='-Bexport' - ;; - - sysv5*) - no_undefined_flag=' -z text' - # $CC -shared without GNU ld will not create a library from C++ - # object files and a static libstdc++, better avoid it by now - archive_cmds='$LD -G${allow_undefined_flag} -h $soname -o $lib $libobjs $deplibs $linker_flags' - archive_expsym_cmds='$echo "{ global:" > $lib.exp~cat $export_symbols | sed -e "s/\(.*\)/\1;/" >> $lib.exp~$echo "local: *; };" >> $lib.exp~ - $LD -G${allow_undefined_flag} -M $lib.exp -h $soname -o $lib $libobjs $deplibs $linker_flags~$rm $lib.exp' - hardcode_libdir_flag_spec= - hardcode_shlibpath_var=no - runpath_var='LD_RUN_PATH' - ;; - - uts4*) - archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' - hardcode_libdir_flag_spec='-L$libdir' - hardcode_shlibpath_var=no - ;; - - dgux*) - archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' - hardcode_libdir_flag_spec='-L$libdir' - hardcode_shlibpath_var=no - ;; - - sysv4*MP*) - if test -d /usr/nec; then - archive_cmds='$LD -G -h $soname -o $lib $libobjs $deplibs $linker_flags' - hardcode_shlibpath_var=no - runpath_var=LD_RUN_PATH - hardcode_runpath_var=yes - ld_shlibs=yes - fi - ;; - - sysv4.2uw2*) - archive_cmds='$LD -G -o $lib $libobjs $deplibs $linker_flags' - hardcode_direct=yes - hardcode_minus_L=no - hardcode_shlibpath_var=no - hardcode_runpath_var=yes - runpath_var=LD_RUN_PATH - ;; - - sysv5uw7* | unixware7*) - no_undefined_flag='${wl}-z ${wl}text' - if test "$GCC" = yes; then - archive_cmds='$CC -shared ${wl}-h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags' - else - archive_cmds='$CC -G ${wl}-h ${wl}$soname -o $lib $libobjs $deplibs $compiler_flags' - fi - runpath_var='LD_RUN_PATH' - hardcode_shlibpath_var=no - ;; - - *) - ld_shlibs=no - ;; - esac -fi -echo "$as_me:$LINENO: result: $ld_shlibs" >&5 -echo "${ECHO_T}$ld_shlibs" >&6 -test "$ld_shlibs" = no && can_build_shared=no -## -## END FIXME - -## FIXME: this should be a separate macro -## -# Check hardcoding attributes. -echo "$as_me:$LINENO: checking how to hardcode library paths into programs" >&5 -echo $ECHO_N "checking how to hardcode library paths into programs... $ECHO_C" >&6 -hardcode_action= -if test -n "$hardcode_libdir_flag_spec" || \ - test -n "$runpath_var"; then - - # We can hardcode non-existant directories. - if test "$hardcode_direct" != no && - # If the only mechanism to avoid hardcoding is shlibpath_var, we - # have to relink, otherwise we might link with an installed library - # when we should be linking with a yet-to-be-installed one - ## test "$hardcode_shlibpath_var" != no && - test "$hardcode_minus_L" != no; then - # Linking always hardcodes the temporary library directory. - hardcode_action=relink - else - # We can link without hardcoding, and we can hardcode nonexisting dirs. - hardcode_action=immediate - fi -else - # We cannot hardcode anything, or else we can only hardcode existing - # directories. - hardcode_action=unsupported -fi -echo "$as_me:$LINENO: result: $hardcode_action" >&5 -echo "${ECHO_T}$hardcode_action" >&6 -## -## END FIXME - -## FIXME: this should be a separate macro -## -striplib= -old_striplib= -echo "$as_me:$LINENO: checking whether stripping libraries is possible" >&5 -echo $ECHO_N "checking whether stripping libraries is possible... $ECHO_C" >&6 -if test -n "$STRIP" && $STRIP -V 2>&1 | grep "GNU strip" >/dev/null; then - test -z "$old_striplib" && old_striplib="$STRIP --strip-debug" - test -z "$striplib" && striplib="$STRIP --strip-unneeded" - echo "$as_me:$LINENO: result: yes" >&5 -echo "${ECHO_T}yes" >&6 -else - echo "$as_me:$LINENO: result: no" >&5 -echo "${ECHO_T}no" >&6 -fi -## -## END FIXME - -reload_cmds='$LD$reload_flag -o $output$reload_objs' -test -z "$deplibs_check_method" && deplibs_check_method=unknown - -## FIXME: this should be a separate macro -## -# PORTME Fill in your ld.so characteristics -echo "$as_me:$LINENO: checking dynamic linker characteristics" >&5 -echo $ECHO_N "checking dynamic linker characteristics... $ECHO_C" >&6 -library_names_spec= -libname_spec='lib$name' -soname_spec= -postinstall_cmds= -postuninstall_cmds= -finish_cmds= -finish_eval= -shlibpath_var= -shlibpath_overrides_runpath=unknown -version_type=none -dynamic_linker="$host_os ld.so" -sys_lib_dlsearch_path_spec="/lib /usr/lib" -sys_lib_search_path_spec="/lib /usr/lib /usr/local/lib" - -case $host_os in -aix3*) - version_type=linux - library_names_spec='${libname}${release}.so$versuffix $libname.a' - shlibpath_var=LIBPATH - - # AIX has no versioning support, so we append a major version to the name. - soname_spec='${libname}${release}.so$major' - ;; - -aix4* | aix5*) - version_type=linux - if test "$host_cpu" = ia64; then - # AIX 5 supports IA64 - library_names_spec='${libname}${release}.so$major ${libname}${release}.so$versuffix $libname.so' - shlibpath_var=LD_LIBRARY_PATH - else - # With GCC up to 2.95.x, collect2 would create an import file - # for dependence libraries. The import file would start with - # the line `#! .'. This would cause the generated library to - # depend on `.', always an invalid library. This was fixed in - # development snapshots of GCC prior to 3.0. - case $host_os in - aix4 | aix4.[01] | aix4.[01].*) - if { echo '#if __GNUC__ > 2 || (__GNUC__ == 2 && __GNUC_MINOR__ >= 97)' - echo ' yes ' - echo '#endif'; } | ${CC} -E - | grep yes > /dev/null; then - : - else - can_build_shared=no - fi - ;; - esac - # AIX (on Power*) has no versioning support, so currently we can not hardcode correct - # soname into executable. Probably we can add versioning support to - # collect2, so additional links can be useful in future. - if test "$aix_use_runtimelinking" = yes; then - # If using run time linking (on AIX 4.2 or later) use lib<name>.so instead of - # lib<name>.a to let people know that these are not typical AIX shared libraries. - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' - else - # We preserve .a as extension for shared libraries through AIX4.2 - # and later when we are not doing run time linking. - library_names_spec='${libname}${release}.a $libname.a' - soname_spec='${libname}${release}.so$major' - fi - shlibpath_var=LIBPATH - deplibs_check_method=pass_all - fi - ;; - -amigaos*) - library_names_spec='$libname.ixlibrary $libname.a' - # Create ${libname}_ixlibrary.a entries in /sys/libs. - finish_eval='for lib in `ls $libdir/*.ixlibrary 2>/dev/null`; do libname=`$echo "X$lib" | $Xsed -e '\''s%^.*/\([^/]*\)\.ixlibrary$%\1%'\''`; test $rm /sys/libs/${libname}_ixlibrary.a; $show "(cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a)"; (cd /sys/libs && $LN_S $lib ${libname}_ixlibrary.a) || exit 1; done' - ;; - -beos*) - library_names_spec='${libname}.so' - dynamic_linker="$host_os ld.so" - shlibpath_var=LIBRARY_PATH - ;; - -bsdi4*) - version_type=linux - need_version=no - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' - soname_spec='${libname}${release}.so$major' - finish_cmds='PATH="\$PATH:/sbin" ldconfig $libdir' - shlibpath_var=LD_LIBRARY_PATH - sys_lib_search_path_spec="/shlib /usr/lib /usr/X11/lib /usr/contrib/lib /lib /usr/local/lib" - sys_lib_dlsearch_path_spec="/shlib /usr/lib /usr/local/lib" - export_dynamic_flag_spec=-rdynamic - # the default ld.so.conf also contains /usr/contrib/lib and - # /usr/X11R6/lib (/usr/X11 is a link to /usr/X11R6), but let us allow - # libtool to hard-code these into programs - ;; - -cygwin* | mingw* | pw32*) - version_type=windows - need_version=no - need_lib_prefix=no - case $GCC,$host_os in - yes,cygwin*) - library_names_spec='$libname.dll.a' - soname_spec='`echo ${libname} | sed -e 's/^lib/cyg/'``echo ${release} | sed -e 's/[.]/-/g'`${versuffix}.dll' - postinstall_cmds='dlpath=`bash 2>&1 -c '\''. $dir/${file}i;echo \$dlname'\''`~ - dldir=$destdir/`dirname \$dlpath`~ - test -d \$dldir || mkdir -p \$dldir~ - $install_prog .libs/$dlname \$dldir/$dlname' - postuninstall_cmds='dldll=`bash 2>&1 -c '\''. $file; echo \$dlname'\''`~ - dlpath=$dir/\$dldll~ - $rm \$dlpath' - ;; - yes,mingw*) - library_names_spec='${libname}`echo ${release} | sed -e 's/[.]/-/g'`${versuffix}.dll' - sys_lib_search_path_spec=`$CC -print-search-dirs | grep "^libraries:" | sed -e "s/^libraries://" -e "s/;/ /g"` - ;; - yes,pw32*) - library_names_spec='`echo ${libname} | sed -e 's/^lib/pw/'``echo ${release} | sed -e 's/./-/g'`${versuffix}.dll' - ;; - *) - library_names_spec='${libname}`echo ${release} | sed -e 's/[.]/-/g'`${versuffix}.dll $libname.lib' - ;; - esac - dynamic_linker='Win32 ld.exe' - # FIXME: first we should search . and the directory the executable is in - shlibpath_var=PATH - ;; - -darwin* | rhapsody*) - dynamic_linker="$host_os dyld" - version_type=darwin - need_lib_prefix=no - need_version=no - # FIXME: Relying on posixy $() will cause problems for - # cross-compilation, but unfortunately the echo tests do not - # yet detect zsh echo's removal of \ escapes. - library_names_spec='${libname}${release}${versuffix}.$(test .$module = .yes && echo so || echo dylib) ${libname}${release}${major}.$(test .$module = .yes && echo so || echo dylib) ${libname}.$(test .$module = .yes && echo so || echo dylib)' - soname_spec='${libname}${release}${major}.$(test .$module = .yes && echo so || echo dylib)' - shlibpath_overrides_runpath=yes - shlibpath_var=DYLD_LIBRARY_PATH - ;; - -freebsd1*) - dynamic_linker=no - ;; - -freebsd*) - objformat=`test -x /usr/bin/objformat && /usr/bin/objformat || echo aout` - version_type=freebsd-$objformat - case $version_type in - freebsd-elf*) - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so $libname.so' - need_version=no - need_lib_prefix=no - ;; - freebsd-*) - library_names_spec='${libname}${release}.so$versuffix $libname.so$versuffix' - need_version=yes - ;; - esac - shlibpath_var=LD_LIBRARY_PATH - case $host_os in - freebsd2*) - shlibpath_overrides_runpath=yes - ;; - *) - shlibpath_overrides_runpath=no - hardcode_into_libs=yes - ;; - esac - ;; - -gnu*) - version_type=linux - need_lib_prefix=no - need_version=no - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so${major} ${libname}.so' - soname_spec='${libname}${release}.so$major' - shlibpath_var=LD_LIBRARY_PATH - hardcode_into_libs=yes - ;; - -hpux9* | hpux10* | hpux11*) - # Give a soname corresponding to the major version so that dld.sl refuses to - # link against other versions. - dynamic_linker="$host_os dld.sl" - version_type=sunos - need_lib_prefix=no - need_version=no - shlibpath_var=SHLIB_PATH - shlibpath_overrides_runpath=no # +s is required to enable SHLIB_PATH - library_names_spec='${libname}${release}.sl$versuffix ${libname}${release}.sl$major $libname.sl' - soname_spec='${libname}${release}.sl$major' - # HP-UX runs *really* slowly unless shared libraries are mode 555. - postinstall_cmds='chmod 555 $lib' - ;; - -irix5* | irix6*) - version_type=irix - need_lib_prefix=no - need_version=no - soname_spec='${libname}${release}.so$major' - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major ${libname}${release}.so $libname.so' - case $host_os in - irix5*) - libsuff= shlibsuff= - ;; - *) - case $LD in # libtool.m4 will add one of these switches to LD - *-32|*"-32 ") libsuff= shlibsuff= libmagic=32-bit;; - *-n32|*"-n32 ") libsuff=32 shlibsuff=N32 libmagic=N32;; - *-64|*"-64 ") libsuff=64 shlibsuff=64 libmagic=64-bit;; - *) libsuff= shlibsuff= libmagic=never-match;; - esac - ;; - esac - shlibpath_var=LD_LIBRARY${shlibsuff}_PATH - shlibpath_overrides_runpath=no - sys_lib_search_path_spec="/usr/lib${libsuff} /lib${libsuff} /usr/local/lib${libsuff}" - sys_lib_dlsearch_path_spec="/usr/lib${libsuff} /lib${libsuff}" - ;; - -# No shared lib support for Linux oldld, aout, or coff. -linux-gnuoldld* | linux-gnuaout* | linux-gnucoff*) - dynamic_linker=no - ;; - -# This must be Linux ELF. -linux-gnu*) - version_type=linux - need_lib_prefix=no - need_version=no - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' - soname_spec='${libname}${release}.so$major' - finish_cmds='PATH="\$PATH:/sbin" ldconfig -n $libdir' - shlibpath_var=LD_LIBRARY_PATH - shlibpath_overrides_runpath=no - # This implies no fast_install, which is unacceptable. - # Some rework will be needed to allow for fast_install - # before this can be enabled. - hardcode_into_libs=yes - - # We used to test for /lib/ld.so.1 and disable shared libraries on - # powerpc, because MkLinux only supported shared libraries with the - # GNU dynamic linker. Since this was broken with cross compilers, - # most powerpc-linux boxes support dynamic linking these days and - # people can always --disable-shared, the test was removed, and we - # assume the GNU/Linux dynamic linker is in use. - dynamic_linker='GNU/Linux ld.so' - ;; - -netbsd*) - version_type=sunos - need_lib_prefix=no - need_version=no - if echo __ELF__ | $CC -E - | grep __ELF__ >/dev/null; then - library_names_spec='${libname}${release}.so$versuffix ${libname}.so$versuffix' - finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' - dynamic_linker='NetBSD (a.out) ld.so' - else - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major ${libname}${release}.so ${libname}.so' - soname_spec='${libname}${release}.so$major' - dynamic_linker='NetBSD ld.elf_so' - fi - shlibpath_var=LD_LIBRARY_PATH - shlibpath_overrides_runpath=yes - hardcode_into_libs=yes - ;; - -newsos6) - version_type=linux - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' - shlibpath_var=LD_LIBRARY_PATH - shlibpath_overrides_runpath=yes - ;; - -openbsd*) - version_type=sunos - if test "$with_gnu_ld" = yes; then - need_lib_prefix=no - need_version=no - fi - library_names_spec='${libname}${release}.so$versuffix ${libname}.so$versuffix' - finish_cmds='PATH="\$PATH:/sbin" ldconfig -m $libdir' - shlibpath_var=LD_LIBRARY_PATH - ;; - -os2*) - libname_spec='$name' - need_lib_prefix=no - library_names_spec='$libname.dll $libname.a' - dynamic_linker='OS/2 ld.exe' - shlibpath_var=LIBPATH - ;; - -osf3* | osf4* | osf5*) - version_type=osf - need_version=no - soname_spec='${libname}${release}.so' - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so $libname.so' - shlibpath_var=LD_LIBRARY_PATH - sys_lib_search_path_spec="/usr/shlib /usr/ccs/lib /usr/lib/cmplrs/cc /usr/lib /usr/local/lib /var/shlib" - sys_lib_dlsearch_path_spec="$sys_lib_search_path_spec" - ;; - -sco3.2v5*) - version_type=osf - soname_spec='${libname}${release}.so$major' - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' - shlibpath_var=LD_LIBRARY_PATH - ;; - -solaris*) - version_type=linux - need_lib_prefix=no - need_version=no - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' - soname_spec='${libname}${release}.so$major' - shlibpath_var=LD_LIBRARY_PATH - shlibpath_overrides_runpath=yes - hardcode_into_libs=yes - # ldd complains unless libraries are executable - postinstall_cmds='chmod +x $lib' - ;; - -sunos4*) - version_type=sunos - library_names_spec='${libname}${release}.so$versuffix ${libname}.so$versuffix' - finish_cmds='PATH="\$PATH:/usr/etc" ldconfig $libdir' - shlibpath_var=LD_LIBRARY_PATH - shlibpath_overrides_runpath=yes - if test "$with_gnu_ld" = yes; then - need_lib_prefix=no - fi - need_version=yes - ;; - -sysv4 | sysv4.2uw2* | sysv4.3* | sysv5*) - version_type=linux - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' - soname_spec='${libname}${release}.so$major' - shlibpath_var=LD_LIBRARY_PATH - case $host_vendor in - sni) - shlibpath_overrides_runpath=no - ;; - motorola) - need_lib_prefix=no - need_version=no - shlibpath_overrides_runpath=no - sys_lib_search_path_spec='/lib /usr/lib /usr/ccs/lib' - ;; - esac - ;; - -uts4*) - version_type=linux - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' - soname_spec='${libname}${release}.so$major' - shlibpath_var=LD_LIBRARY_PATH - ;; - -dgux*) - version_type=linux - need_lib_prefix=no - need_version=no - library_names_spec='${libname}${release}.so$versuffix ${libname}${release}.so$major $libname.so' - soname_spec='${libname}${release}.so$major' - shlibpath_var=LD_LIBRARY_PATH - ;; - -sysv4*MP*) - if test -d /usr/nec ;then - version_type=linux - library_names_spec='$libname.so.$versuffix $libname.so.$major $libname.so' - soname_spec='$libname.so.$major' - shlibpath_var=LD_LIBRARY_PATH - fi - ;; - -*) - dynamic_linker=no - ;; -esac -echo "$as_me:$LINENO: result: $dynamic_linker" >&5 -echo "${ECHO_T}$dynamic_linker" >&6 -test "$dynamic_linker" = no && can_build_shared=no -## -## END FIXME - -## FIXME: this should be a separate macro -## -# Report the final consequences. -echo "$as_me:$LINENO: checking if libtool supports shared libraries" >&5 -echo $ECHO_N "checking if libtool supports shared libraries... $ECHO_C" >&6 -echo "$as_me:$LINENO: result: $can_build_shared" >&5 -echo "${ECHO_T}$can_build_shared" >&6 -## -## END FIXME - -if test "$hardcode_action" = relink; then - # Fast installation is not supported - enable_fast_install=no -elif test "$shlibpath_overrides_runpath" = yes || - test "$enable_shared" = no; then - # Fast installation is not necessary - enable_fast_install=needless -fi - -variables_saved_for_relink="PATH $shlibpath_var $runpath_var" -if test "$GCC" = yes; then - variables_saved_for_relink="$variables_saved_for_relink GCC_EXEC_PREFIX COMPILER_PATH LIBRARY_PATH" -fi - -if test "x$enable_dlopen" != xyes; then - enable_dlopen=unknown - enable_dlopen_self=unknown - enable_dlopen_self_static=unknown -else - lt_cv_dlopen=no - lt_cv_dlopen_libs= - - case $host_os in - beos*) - lt_cv_dlopen="load_add_on" - lt_cv_dlopen_libs= - lt_cv_dlopen_self=yes - ;; - - cygwin* | mingw* | pw32*) - lt_cv_dlopen="LoadLibrary" - lt_cv_dlopen_libs= - ;; - - *) - echo "$as_me:$LINENO: checking for dlopen in -ldl" >&5 -echo $ECHO_N "checking for dlopen in -ldl... $ECHO_C" >&6 -if test "${ac_cv_lib_dl_dlopen+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - ac_check_lib_save_LIBS=$LIBS -LIBS="-ldl $LIBS" -cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ - -/* Override any gcc2 internal prototype to avoid an error. */ -#ifdef __cplusplus -extern "C" -#endif -/* We use char because int might match the return type of a gcc2 - builtin and then its argument prototype would still apply. */ -char dlopen (); -int -main () -{ -dlopen (); - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext conftest$ac_exeext -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest$ac_exeext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_cv_lib_dl_dlopen=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -ac_cv_lib_dl_dlopen=no -fi -rm -f conftest.$ac_objext conftest$ac_exeext conftest.$ac_ext -LIBS=$ac_check_lib_save_LIBS -fi -echo "$as_me:$LINENO: result: $ac_cv_lib_dl_dlopen" >&5 -echo "${ECHO_T}$ac_cv_lib_dl_dlopen" >&6 -if test $ac_cv_lib_dl_dlopen = yes; then - lt_cv_dlopen="dlopen" lt_cv_dlopen_libs="-ldl" -else - echo "$as_me:$LINENO: checking for dlopen" >&5 -echo $ECHO_N "checking for dlopen... $ECHO_C" >&6 -if test "${ac_cv_func_dlopen+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -/* System header to define __stub macros and hopefully few prototypes, - which can conflict with char dlopen (); below. - Prefer <limits.h> to <assert.h> if __STDC__ is defined, since - <limits.h> exists even on freestanding compilers. */ -#ifdef __STDC__ -# include <limits.h> -#else -# include <assert.h> -#endif -/* Override any gcc2 internal prototype to avoid an error. */ -#ifdef __cplusplus -extern "C" -{ -#endif -/* We use char because int might match the return type of a gcc2 - builtin and then its argument prototype would still apply. */ -char dlopen (); -/* The GNU C library defines this for functions which it implements - to always fail with ENOSYS. Some functions are actually named - something starting with __ and the normal name is an alias. */ -#if defined (__stub_dlopen) || defined (__stub___dlopen) -choke me -#else -char (*f) () = dlopen; -#endif -#ifdef __cplusplus -} -#endif - -int -main () -{ -return f != dlopen; - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext conftest$ac_exeext -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest$ac_exeext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_cv_func_dlopen=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -ac_cv_func_dlopen=no -fi -rm -f conftest.$ac_objext conftest$ac_exeext conftest.$ac_ext -fi -echo "$as_me:$LINENO: result: $ac_cv_func_dlopen" >&5 -echo "${ECHO_T}$ac_cv_func_dlopen" >&6 -if test $ac_cv_func_dlopen = yes; then - lt_cv_dlopen="dlopen" -else - echo "$as_me:$LINENO: checking for shl_load" >&5 -echo $ECHO_N "checking for shl_load... $ECHO_C" >&6 -if test "${ac_cv_func_shl_load+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -/* System header to define __stub macros and hopefully few prototypes, - which can conflict with char shl_load (); below. - Prefer <limits.h> to <assert.h> if __STDC__ is defined, since - <limits.h> exists even on freestanding compilers. */ -#ifdef __STDC__ -# include <limits.h> -#else -# include <assert.h> -#endif -/* Override any gcc2 internal prototype to avoid an error. */ -#ifdef __cplusplus -extern "C" -{ -#endif -/* We use char because int might match the return type of a gcc2 - builtin and then its argument prototype would still apply. */ -char shl_load (); -/* The GNU C library defines this for functions which it implements - to always fail with ENOSYS. Some functions are actually named - something starting with __ and the normal name is an alias. */ -#if defined (__stub_shl_load) || defined (__stub___shl_load) -choke me -#else -char (*f) () = shl_load; -#endif -#ifdef __cplusplus -} -#endif - -int -main () -{ -return f != shl_load; - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext conftest$ac_exeext -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest$ac_exeext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_cv_func_shl_load=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -ac_cv_func_shl_load=no -fi -rm -f conftest.$ac_objext conftest$ac_exeext conftest.$ac_ext -fi -echo "$as_me:$LINENO: result: $ac_cv_func_shl_load" >&5 -echo "${ECHO_T}$ac_cv_func_shl_load" >&6 -if test $ac_cv_func_shl_load = yes; then - lt_cv_dlopen="shl_load" -else - echo "$as_me:$LINENO: checking for dlopen in -lsvld" >&5 -echo $ECHO_N "checking for dlopen in -lsvld... $ECHO_C" >&6 -if test "${ac_cv_lib_svld_dlopen+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - ac_check_lib_save_LIBS=$LIBS -LIBS="-lsvld $LIBS" -cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ - -/* Override any gcc2 internal prototype to avoid an error. */ -#ifdef __cplusplus -extern "C" -#endif -/* We use char because int might match the return type of a gcc2 - builtin and then its argument prototype would still apply. */ -char dlopen (); -int -main () -{ -dlopen (); - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext conftest$ac_exeext -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest$ac_exeext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_cv_lib_svld_dlopen=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -ac_cv_lib_svld_dlopen=no -fi -rm -f conftest.$ac_objext conftest$ac_exeext conftest.$ac_ext -LIBS=$ac_check_lib_save_LIBS -fi -echo "$as_me:$LINENO: result: $ac_cv_lib_svld_dlopen" >&5 -echo "${ECHO_T}$ac_cv_lib_svld_dlopen" >&6 -if test $ac_cv_lib_svld_dlopen = yes; then - lt_cv_dlopen="dlopen" lt_cv_dlopen_libs="-lsvld" -else - echo "$as_me:$LINENO: checking for shl_load in -ldld" >&5 -echo $ECHO_N "checking for shl_load in -ldld... $ECHO_C" >&6 -if test "${ac_cv_lib_dld_shl_load+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - ac_check_lib_save_LIBS=$LIBS -LIBS="-ldld $LIBS" -cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ - -/* Override any gcc2 internal prototype to avoid an error. */ -#ifdef __cplusplus -extern "C" -#endif -/* We use char because int might match the return type of a gcc2 - builtin and then its argument prototype would still apply. */ -char shl_load (); -int -main () -{ -shl_load (); - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext conftest$ac_exeext -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest$ac_exeext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_cv_lib_dld_shl_load=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -ac_cv_lib_dld_shl_load=no -fi -rm -f conftest.$ac_objext conftest$ac_exeext conftest.$ac_ext -LIBS=$ac_check_lib_save_LIBS -fi -echo "$as_me:$LINENO: result: $ac_cv_lib_dld_shl_load" >&5 -echo "${ECHO_T}$ac_cv_lib_dld_shl_load" >&6 -if test $ac_cv_lib_dld_shl_load = yes; then - lt_cv_dlopen="dld_link" lt_cv_dlopen_libs="-dld" -fi - - -fi - - -fi - - -fi - - -fi - - ;; - esac - - if test "x$lt_cv_dlopen" != xno; then - enable_dlopen=yes - else - enable_dlopen=no - fi - - case $lt_cv_dlopen in - dlopen) - save_CPPFLAGS="$CPPFLAGS" - test "x$ac_cv_header_dlfcn_h" = xyes && CPPFLAGS="$CPPFLAGS -DHAVE_DLFCN_H" - - save_LDFLAGS="$LDFLAGS" - eval LDFLAGS=\"\$LDFLAGS $export_dynamic_flag_spec\" - - save_LIBS="$LIBS" - LIBS="$lt_cv_dlopen_libs $LIBS" - - echo "$as_me:$LINENO: checking whether a program can dlopen itself" >&5 -echo $ECHO_N "checking whether a program can dlopen itself... $ECHO_C" >&6 -if test "${lt_cv_dlopen_self+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test "$cross_compiling" = yes; then : - lt_cv_dlopen_self=cross -else - lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2 - lt_status=$lt_dlunknown - cat > conftest.$ac_ext <<EOF -#line 6214 "configure" -#include "confdefs.h" - -#if HAVE_DLFCN_H -#include <dlfcn.h> -#endif - -#include <stdio.h> - -#ifdef RTLD_GLOBAL -# define LT_DLGLOBAL RTLD_GLOBAL -#else -# ifdef DL_GLOBAL -# define LT_DLGLOBAL DL_GLOBAL -# else -# define LT_DLGLOBAL 0 -# endif -#endif - -/* We may have to define LT_DLLAZY_OR_NOW in the command line if we - find out it does not work in some platform. */ -#ifndef LT_DLLAZY_OR_NOW -# ifdef RTLD_LAZY -# define LT_DLLAZY_OR_NOW RTLD_LAZY -# else -# ifdef DL_LAZY -# define LT_DLLAZY_OR_NOW DL_LAZY -# else -# ifdef RTLD_NOW -# define LT_DLLAZY_OR_NOW RTLD_NOW -# else -# ifdef DL_NOW -# define LT_DLLAZY_OR_NOW DL_NOW -# else -# define LT_DLLAZY_OR_NOW 0 -# endif -# endif -# endif -# endif -#endif - -#ifdef __cplusplus -extern "C" void exit (int); -#endif - -void fnord() { int i=42;} -int main () -{ - void *self = dlopen (0, LT_DLGLOBAL|LT_DLLAZY_OR_NOW); - int status = $lt_dlunknown; - - if (self) - { - if (dlsym (self,"fnord")) status = $lt_dlno_uscore; - else if (dlsym( self,"_fnord")) status = $lt_dlneed_uscore; - /* dlclose (self); */ - } - - exit (status); -} -EOF - if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && test -s conftest${ac_exeext} 2>/dev/null; then - (./conftest; exit; ) 2>/dev/null - lt_status=$? - case x$lt_status in - x$lt_dlno_uscore) lt_cv_dlopen_self=yes ;; - x$lt_dlneed_uscore) lt_cv_dlopen_self=yes ;; - x$lt_unknown|x*) lt_cv_dlopen_self=no ;; - esac - else : - # compilation failed - lt_cv_dlopen_self=no - fi -fi -rm -fr conftest* - - -fi -echo "$as_me:$LINENO: result: $lt_cv_dlopen_self" >&5 -echo "${ECHO_T}$lt_cv_dlopen_self" >&6 - - if test "x$lt_cv_dlopen_self" = xyes; then - LDFLAGS="$LDFLAGS $link_static_flag" - echo "$as_me:$LINENO: checking whether a statically linked program can dlopen itself" >&5 -echo $ECHO_N "checking whether a statically linked program can dlopen itself... $ECHO_C" >&6 -if test "${lt_cv_dlopen_self_static+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - if test "$cross_compiling" = yes; then : - lt_cv_dlopen_self_static=cross -else - lt_dlunknown=0; lt_dlno_uscore=1; lt_dlneed_uscore=2 - lt_status=$lt_dlunknown - cat > conftest.$ac_ext <<EOF -#line 6312 "configure" -#include "confdefs.h" - -#if HAVE_DLFCN_H -#include <dlfcn.h> -#endif - -#include <stdio.h> - -#ifdef RTLD_GLOBAL -# define LT_DLGLOBAL RTLD_GLOBAL -#else -# ifdef DL_GLOBAL -# define LT_DLGLOBAL DL_GLOBAL -# else -# define LT_DLGLOBAL 0 -# endif -#endif - -/* We may have to define LT_DLLAZY_OR_NOW in the command line if we - find out it does not work in some platform. */ -#ifndef LT_DLLAZY_OR_NOW -# ifdef RTLD_LAZY -# define LT_DLLAZY_OR_NOW RTLD_LAZY -# else -# ifdef DL_LAZY -# define LT_DLLAZY_OR_NOW DL_LAZY -# else -# ifdef RTLD_NOW -# define LT_DLLAZY_OR_NOW RTLD_NOW -# else -# ifdef DL_NOW -# define LT_DLLAZY_OR_NOW DL_NOW -# else -# define LT_DLLAZY_OR_NOW 0 -# endif -# endif -# endif -# endif -#endif - -#ifdef __cplusplus -extern "C" void exit (int); -#endif - -void fnord() { int i=42;} -int main () -{ - void *self = dlopen (0, LT_DLGLOBAL|LT_DLLAZY_OR_NOW); - int status = $lt_dlunknown; - - if (self) - { - if (dlsym (self,"fnord")) status = $lt_dlno_uscore; - else if (dlsym( self,"_fnord")) status = $lt_dlneed_uscore; - /* dlclose (self); */ - } - - exit (status); -} -EOF - if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && test -s conftest${ac_exeext} 2>/dev/null; then - (./conftest; exit; ) 2>/dev/null - lt_status=$? - case x$lt_status in - x$lt_dlno_uscore) lt_cv_dlopen_self_static=yes ;; - x$lt_dlneed_uscore) lt_cv_dlopen_self_static=yes ;; - x$lt_unknown|x*) lt_cv_dlopen_self_static=no ;; - esac - else : - # compilation failed - lt_cv_dlopen_self_static=no - fi -fi -rm -fr conftest* - - -fi -echo "$as_me:$LINENO: result: $lt_cv_dlopen_self_static" >&5 -echo "${ECHO_T}$lt_cv_dlopen_self_static" >&6 - fi - - CPPFLAGS="$save_CPPFLAGS" - LDFLAGS="$save_LDFLAGS" - LIBS="$save_LIBS" - ;; - esac - - case $lt_cv_dlopen_self in - yes|no) enable_dlopen_self=$lt_cv_dlopen_self ;; - *) enable_dlopen_self=unknown ;; - esac - - case $lt_cv_dlopen_self_static in - yes|no) enable_dlopen_self_static=$lt_cv_dlopen_self_static ;; - *) enable_dlopen_self_static=unknown ;; - esac -fi - - -## FIXME: this should be a separate macro -## -if test "$enable_shared" = yes && test "$GCC" = yes; then - case $archive_cmds in - *'~'*) - # FIXME: we may have to deal with multi-command sequences. - ;; - '$CC '*) - # Test whether the compiler implicitly links with -lc since on some - # systems, -lgcc has to come before -lc. If gcc already passes -lc - # to ld, don't add -lc before -lgcc. - echo "$as_me:$LINENO: checking whether -lc should be explicitly linked in" >&5 -echo $ECHO_N "checking whether -lc should be explicitly linked in... $ECHO_C" >&6 - if test "${lt_cv_archive_cmds_need_lc+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - $rm conftest* - echo 'static int dummy;' > conftest.$ac_ext - - if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; then - soname=conftest - lib=conftest - libobjs=conftest.$ac_objext - deplibs= - wl=$lt_cv_prog_cc_wl - compiler_flags=-v - linker_flags=-v - verstring= - output_objdir=. - libname=conftest - save_allow_undefined_flag=$allow_undefined_flag - allow_undefined_flag= - if { (eval echo "$as_me:$LINENO: \"$archive_cmds 2\>\&1 \| grep \" -lc \" \>/dev/null 2\>\&1\"") >&5 - (eval $archive_cmds 2\>\&1 \| grep \" -lc \" \>/dev/null 2\>\&1) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } - then - lt_cv_archive_cmds_need_lc=no - else - lt_cv_archive_cmds_need_lc=yes - fi - allow_undefined_flag=$save_allow_undefined_flag - else - cat conftest.err 1>&5 - fi -fi - - echo "$as_me:$LINENO: result: $lt_cv_archive_cmds_need_lc" >&5 -echo "${ECHO_T}$lt_cv_archive_cmds_need_lc" >&6 - ;; - esac -fi -need_lc=${lt_cv_archive_cmds_need_lc-yes} -## -## END FIXME - -## FIXME: this should be a separate macro -## -# The second clause should only fire when bootstrapping the -# libtool distribution, otherwise you forgot to ship ltmain.sh -# with your package, and you will get complaints that there are -# no rules to generate ltmain.sh. -if test -f "$ltmain"; then - : -else - # If there is no Makefile yet, we rely on a make rule to execute - # `config.status --recheck' to rerun these tests and create the - # libtool script then. - test -f Makefile && make "$ltmain" -fi - -if test -f "$ltmain"; then - trap "$rm \"${ofile}T\"; exit 1" 1 2 15 - $rm -f "${ofile}T" - - echo creating $ofile - - # Now quote all the things that may contain metacharacters while being - # careful not to overquote the AC_SUBSTed values. We take copies of the - # variables and quote the copies for generation of the libtool script. - for var in echo old_CC old_CFLAGS \ - AR AR_FLAGS CC LD LN_S NM SHELL \ - reload_flag reload_cmds wl \ - pic_flag link_static_flag no_builtin_flag export_dynamic_flag_spec \ - thread_safe_flag_spec whole_archive_flag_spec libname_spec \ - library_names_spec soname_spec \ - RANLIB old_archive_cmds old_archive_from_new_cmds old_postinstall_cmds \ - old_postuninstall_cmds archive_cmds archive_expsym_cmds postinstall_cmds \ - postuninstall_cmds extract_expsyms_cmds old_archive_from_expsyms_cmds \ - old_striplib striplib file_magic_cmd export_symbols_cmds \ - deplibs_check_method allow_undefined_flag no_undefined_flag \ - finish_cmds finish_eval global_symbol_pipe global_symbol_to_cdecl \ - hardcode_libdir_flag_spec hardcode_libdir_separator \ - sys_lib_search_path_spec sys_lib_dlsearch_path_spec \ - compiler_c_o compiler_o_lo need_locks exclude_expsyms include_expsyms; do - - case $var in - reload_cmds | old_archive_cmds | old_archive_from_new_cmds | \ - old_postinstall_cmds | old_postuninstall_cmds | \ - export_symbols_cmds | archive_cmds | archive_expsym_cmds | \ - extract_expsyms_cmds | old_archive_from_expsyms_cmds | \ - postinstall_cmds | postuninstall_cmds | \ - finish_cmds | sys_lib_search_path_spec | sys_lib_dlsearch_path_spec) - # Double-quote double-evaled strings. - eval "lt_$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$double_quote_subst\" -e \"\$sed_quote_subst\" -e \"\$delay_variable_subst\"\`\\\"" - ;; - *) - eval "lt_$var=\\\"\`\$echo \"X\$$var\" | \$Xsed -e \"\$sed_quote_subst\"\`\\\"" - ;; - esac - done - - cat <<__EOF__ > "${ofile}T" -#! $SHELL - -# `$echo "$ofile" | sed 's%^.*/%%'` - Provide generalized library-building support services. -# Generated automatically by $PROGRAM (GNU $PACKAGE $VERSION$TIMESTAMP) -# NOTE: Changes made to this file will be lost: look at ltmain.sh. -# -# Copyright (C) 1996-2000 Free Software Foundation, Inc. -# Originally by Gordon Matzigkeit <gord@gnu.ai.mit.edu>, 1996 -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, but -# WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. -# -# As a special exception to the GNU General Public License, if you -# distribute this file as part of a program that contains a -# configuration script generated by Autoconf, you may include it under -# the same distribution terms that you use for the rest of that program. - -# Sed that helps us avoid accidentally triggering echo(1) options like -n. -Xsed="sed -e s/^X//" - -# The HP-UX ksh and POSIX shell print the target directory to stdout -# if CDPATH is set. -if test "X\${CDPATH+set}" = Xset; then CDPATH=:; export CDPATH; fi - -# ### BEGIN LIBTOOL CONFIG - -# Libtool was configured on host `(hostname || uname -n) 2>/dev/null | sed 1q`: - -# Shell to use when invoking shell scripts. -SHELL=$lt_SHELL - -# Whether or not to build shared libraries. -build_libtool_libs=$enable_shared - -# Whether or not to add -lc for building shared libraries. -build_libtool_need_lc=$need_lc - -# Whether or not to build static libraries. -build_old_libs=$enable_static - -# Whether or not to optimize for fast installation. -fast_install=$enable_fast_install - -# The host system. -host_alias=$host_alias -host=$host - -# An echo program that does not interpret backslashes. -echo=$lt_echo - -# The archiver. -AR=$lt_AR -AR_FLAGS=$lt_AR_FLAGS - -# The default C compiler. -CC=$lt_CC - -# Is the compiler the GNU C compiler? -with_gcc=$GCC - -# The linker used to build libraries. -LD=$lt_LD - -# Whether we need hard or soft links. -LN_S=$lt_LN_S - -# A BSD-compatible nm program. -NM=$lt_NM - -# A symbol stripping program -STRIP=$STRIP - -# Used to examine libraries when file_magic_cmd begins "file" -MAGIC_CMD=$MAGIC_CMD - -# Used on cygwin: DLL creation program. -DLLTOOL="$DLLTOOL" - -# Used on cygwin: object dumper. -OBJDUMP="$OBJDUMP" - -# Used on cygwin: assembler. -AS="$AS" - -# The name of the directory that contains temporary libtool files. -objdir=$objdir - -# How to create reloadable object files. -reload_flag=$lt_reload_flag -reload_cmds=$lt_reload_cmds - -# How to pass a linker flag through the compiler. -wl=$lt_wl - -# Object file suffix (normally "o"). -objext="$ac_objext" - -# Old archive suffix (normally "a"). -libext="$libext" - -# Executable file suffix (normally ""). -exeext="$exeext" - -# Additional compiler flags for building library objects. -pic_flag=$lt_pic_flag -pic_mode=$pic_mode - -# Does compiler simultaneously support -c and -o options? -compiler_c_o=$lt_compiler_c_o - -# Can we write directly to a .lo ? -compiler_o_lo=$lt_compiler_o_lo - -# Must we lock files when doing compilation ? -need_locks=$lt_need_locks - -# Do we need the lib prefix for modules? -need_lib_prefix=$need_lib_prefix - -# Do we need a version for libraries? -need_version=$need_version - -# Whether dlopen is supported. -dlopen_support=$enable_dlopen - -# Whether dlopen of programs is supported. -dlopen_self=$enable_dlopen_self - -# Whether dlopen of statically linked programs is supported. -dlopen_self_static=$enable_dlopen_self_static - -# Compiler flag to prevent dynamic linking. -link_static_flag=$lt_link_static_flag - -# Compiler flag to turn off builtin functions. -no_builtin_flag=$lt_no_builtin_flag - -# Compiler flag to allow reflexive dlopens. -export_dynamic_flag_spec=$lt_export_dynamic_flag_spec - -# Compiler flag to generate shared objects directly from archives. -whole_archive_flag_spec=$lt_whole_archive_flag_spec - -# Compiler flag to generate thread-safe objects. -thread_safe_flag_spec=$lt_thread_safe_flag_spec - -# Library versioning type. -version_type=$version_type - -# Format of library name prefix. -libname_spec=$lt_libname_spec - -# List of archive names. First name is the real one, the rest are links. -# The last name is the one that the linker finds with -lNAME. -library_names_spec=$lt_library_names_spec - -# The coded name of the library, if different from the real name. -soname_spec=$lt_soname_spec - -# Commands used to build and install an old-style archive. -RANLIB=$lt_RANLIB -old_archive_cmds=$lt_old_archive_cmds -old_postinstall_cmds=$lt_old_postinstall_cmds -old_postuninstall_cmds=$lt_old_postuninstall_cmds - -# Create an old-style archive from a shared archive. -old_archive_from_new_cmds=$lt_old_archive_from_new_cmds - -# Create a temporary old-style archive to link instead of a shared archive. -old_archive_from_expsyms_cmds=$lt_old_archive_from_expsyms_cmds - -# Commands used to build and install a shared archive. -archive_cmds=$lt_archive_cmds -archive_expsym_cmds=$lt_archive_expsym_cmds -postinstall_cmds=$lt_postinstall_cmds -postuninstall_cmds=$lt_postuninstall_cmds - -# Commands to strip libraries. -old_striplib=$lt_old_striplib -striplib=$lt_striplib - -# Method to check whether dependent libraries are shared objects. -deplibs_check_method=$lt_deplibs_check_method - -# Command to use when deplibs_check_method == file_magic. -file_magic_cmd=$lt_file_magic_cmd - -# Flag that allows shared libraries with undefined symbols to be built. -allow_undefined_flag=$lt_allow_undefined_flag - -# Flag that forces no undefined symbols. -no_undefined_flag=$lt_no_undefined_flag - -# Commands used to finish a libtool library installation in a directory. -finish_cmds=$lt_finish_cmds - -# Same as above, but a single script fragment to be evaled but not shown. -finish_eval=$lt_finish_eval - -# Take the output of nm and produce a listing of raw symbols and C names. -global_symbol_pipe=$lt_global_symbol_pipe - -# Transform the output of nm in a proper C declaration -global_symbol_to_cdecl=$lt_global_symbol_to_cdecl - -# This is the shared library runtime path variable. -runpath_var=$runpath_var - -# This is the shared library path variable. -shlibpath_var=$shlibpath_var - -# Is shlibpath searched before the hard-coded library search path? -shlibpath_overrides_runpath=$shlibpath_overrides_runpath - -# How to hardcode a shared library path into an executable. -hardcode_action=$hardcode_action - -# Whether we should hardcode library paths into libraries. -hardcode_into_libs=$hardcode_into_libs - -# Flag to hardcode \$libdir into a binary during linking. -# This must work even if \$libdir does not exist. -hardcode_libdir_flag_spec=$lt_hardcode_libdir_flag_spec - -# Whether we need a single -rpath flag with a separated argument. -hardcode_libdir_separator=$lt_hardcode_libdir_separator - -# Set to yes if using DIR/libNAME.so during linking hardcodes DIR into the -# resulting binary. -hardcode_direct=$hardcode_direct - -# Set to yes if using the -LDIR flag during linking hardcodes DIR into the -# resulting binary. -hardcode_minus_L=$hardcode_minus_L - -# Set to yes if using SHLIBPATH_VAR=DIR during linking hardcodes DIR into -# the resulting binary. -hardcode_shlibpath_var=$hardcode_shlibpath_var - -# Variables whose values should be saved in libtool wrapper scripts and -# restored at relink time. -variables_saved_for_relink="$variables_saved_for_relink" - -# Whether libtool must link a program against all its dependency libraries. -link_all_deplibs=$link_all_deplibs - -# Compile-time system search path for libraries -sys_lib_search_path_spec=$lt_sys_lib_search_path_spec - -# Run-time system search path for libraries -sys_lib_dlsearch_path_spec=$lt_sys_lib_dlsearch_path_spec - -# Fix the shell variable \$srcfile for the compiler. -fix_srcfile_path="$fix_srcfile_path" - -# Set to yes if exported symbols are required. -always_export_symbols=$always_export_symbols - -# The commands to list exported symbols. -export_symbols_cmds=$lt_export_symbols_cmds - -# The commands to extract the exported symbol list from a shared archive. -extract_expsyms_cmds=$lt_extract_expsyms_cmds - -# Symbols that should not be listed in the preloaded symbols. -exclude_expsyms=$lt_exclude_expsyms - -# Symbols that must always be exported. -include_expsyms=$lt_include_expsyms - -# ### END LIBTOOL CONFIG - -__EOF__ - - case $host_os in - aix3*) - cat <<\EOF >> "${ofile}T" - -# AIX sometimes has problems with the GCC collect2 program. For some -# reason, if we set the COLLECT_NAMES environment variable, the problems -# vanish in a puff of smoke. -if test "X${COLLECT_NAMES+set}" != Xset; then - COLLECT_NAMES= - export COLLECT_NAMES -fi -EOF - ;; - esac - - case $host_os in - cygwin* | mingw* | pw32* | os2*) - cat <<'EOF' >> "${ofile}T" - # This is a source program that is used to create dlls on Windows - # Don't remove nor modify the starting and closing comments -# /* ltdll.c starts here */ -# #define WIN32_LEAN_AND_MEAN -# #include <windows.h> -# #undef WIN32_LEAN_AND_MEAN -# #include <stdio.h> -# -# #ifndef __CYGWIN__ -# # ifdef __CYGWIN32__ -# # define __CYGWIN__ __CYGWIN32__ -# # endif -# #endif -# -# #ifdef __cplusplus -# extern "C" { -# #endif -# BOOL APIENTRY DllMain (HINSTANCE hInst, DWORD reason, LPVOID reserved); -# #ifdef __cplusplus -# } -# #endif -# -# #ifdef __CYGWIN__ -# #include <cygwin/cygwin_dll.h> -# DECLARE_CYGWIN_DLL( DllMain ); -# #endif -# HINSTANCE __hDllInstance_base; -# -# BOOL APIENTRY -# DllMain (HINSTANCE hInst, DWORD reason, LPVOID reserved) -# { -# __hDllInstance_base = hInst; -# return TRUE; -# } -# /* ltdll.c ends here */ - # This is a source program that is used to create import libraries - # on Windows for dlls which lack them. Don't remove nor modify the - # starting and closing comments -# /* impgen.c starts here */ -# /* Copyright (C) 1999-2000 Free Software Foundation, Inc. -# -# This file is part of GNU libtool. -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, -# but WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the -# GNU General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. -# */ -# -# #include <stdio.h> /* for printf() */ -# #include <unistd.h> /* for open(), lseek(), read() */ -# #include <fcntl.h> /* for O_RDONLY, O_BINARY */ -# #include <string.h> /* for strdup() */ -# -# /* O_BINARY isn't required (or even defined sometimes) under Unix */ -# #ifndef O_BINARY -# #define O_BINARY 0 -# #endif -# -# static unsigned int -# pe_get16 (fd, offset) -# int fd; -# int offset; -# { -# unsigned char b[2]; -# lseek (fd, offset, SEEK_SET); -# read (fd, b, 2); -# return b[0] + (b[1]<<8); -# } -# -# static unsigned int -# pe_get32 (fd, offset) -# int fd; -# int offset; -# { -# unsigned char b[4]; -# lseek (fd, offset, SEEK_SET); -# read (fd, b, 4); -# return b[0] + (b[1]<<8) + (b[2]<<16) + (b[3]<<24); -# } -# -# static unsigned int -# pe_as32 (ptr) -# void *ptr; -# { -# unsigned char *b = ptr; -# return b[0] + (b[1]<<8) + (b[2]<<16) + (b[3]<<24); -# } -# -# int -# main (argc, argv) -# int argc; -# char *argv[]; -# { -# int dll; -# unsigned long pe_header_offset, opthdr_ofs, num_entries, i; -# unsigned long export_rva, export_size, nsections, secptr, expptr; -# unsigned long name_rvas, nexp; -# unsigned char *expdata, *erva; -# char *filename, *dll_name; -# -# filename = argv[1]; -# -# dll = open(filename, O_RDONLY|O_BINARY); -# if (dll < 1) -# return 1; -# -# dll_name = filename; -# -# for (i=0; filename[i]; i++) -# if (filename[i] == '/' || filename[i] == '\\' || filename[i] == ':') -# dll_name = filename + i +1; -# -# pe_header_offset = pe_get32 (dll, 0x3c); -# opthdr_ofs = pe_header_offset + 4 + 20; -# num_entries = pe_get32 (dll, opthdr_ofs + 92); -# -# if (num_entries < 1) /* no exports */ -# return 1; -# -# export_rva = pe_get32 (dll, opthdr_ofs + 96); -# export_size = pe_get32 (dll, opthdr_ofs + 100); -# nsections = pe_get16 (dll, pe_header_offset + 4 +2); -# secptr = (pe_header_offset + 4 + 20 + -# pe_get16 (dll, pe_header_offset + 4 + 16)); -# -# expptr = 0; -# for (i = 0; i < nsections; i++) -# { -# char sname[8]; -# unsigned long secptr1 = secptr + 40 * i; -# unsigned long vaddr = pe_get32 (dll, secptr1 + 12); -# unsigned long vsize = pe_get32 (dll, secptr1 + 16); -# unsigned long fptr = pe_get32 (dll, secptr1 + 20); -# lseek(dll, secptr1, SEEK_SET); -# read(dll, sname, 8); -# if (vaddr <= export_rva && vaddr+vsize > export_rva) -# { -# expptr = fptr + (export_rva - vaddr); -# if (export_rva + export_size > vaddr + vsize) -# export_size = vsize - (export_rva - vaddr); -# break; -# } -# } -# -# expdata = (unsigned char*)malloc(export_size); -# lseek (dll, expptr, SEEK_SET); -# read (dll, expdata, export_size); -# erva = expdata - export_rva; -# -# nexp = pe_as32 (expdata+24); -# name_rvas = pe_as32 (expdata+32); -# -# printf ("EXPORTS\n"); -# for (i = 0; i<nexp; i++) -# { -# unsigned long name_rva = pe_as32 (erva+name_rvas+i*4); -# printf ("\t%s @ %ld ;\n", erva+name_rva, 1+ i); -# } -# -# return 0; -# } -# /* impgen.c ends here */ - -EOF - ;; - esac - - # We use sed instead of cat because bash on DJGPP gets confused if - # if finds mixed CR/LF and LF-only lines. Since sed operates in - # text mode, it properly converts lines to CR/LF. This bash problem - # is reportedly fixed, but why not run on old versions too? - sed '$q' "$ltmain" >> "${ofile}T" || (rm -f "${ofile}T"; exit 1) - - mv -f "${ofile}T" "$ofile" || \ - (rm -f "$ofile" && cp "${ofile}T" "$ofile" && rm -f "${ofile}T") - chmod +x "$ofile" -fi -## -## END FIXME - - - - - -# This can be used to rebuild libtool when needed -LIBTOOL_DEPS="$ac_aux_dir/ltmain.sh" - -# Always use our own libtool. -LIBTOOL='$(SHELL) $(top_builddir)/libtool' - -# Prevent multiple expansion - - - - -CC_FOR_BUILD=${CC_FOR_BUILD:-'$(CC)'} -CFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD:-'$(CFLAGS)'} -BUILD_EXEEXT=${BUILD_EXEEXT:-'$(EXEEXT)'} -BUILD_OBJEXT=${BUILD_OBJEXT:-'$(OBJEXT)'} - - -echo "$as_me:$LINENO: checking for ANSI C header files" >&5 -echo $ECHO_N "checking for ANSI C header files... $ECHO_C" >&6 -if test "${ac_cv_header_stdc+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <stdlib.h> -#include <stdarg.h> -#include <string.h> -#include <float.h> - -int -main () -{ - - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_cv_header_stdc=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -ac_cv_header_stdc=no -fi -rm -f conftest.$ac_objext conftest.$ac_ext - -if test $ac_cv_header_stdc = yes; then - # SunOS 4.x string.h does not declare mem*, contrary to ANSI. - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <string.h> - -_ACEOF -if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | - $EGREP "memchr" >/dev/null 2>&1; then - : -else - ac_cv_header_stdc=no -fi -rm -f conftest* - -fi - -if test $ac_cv_header_stdc = yes; then - # ISC 2.0.2 stdlib.h does not declare free, contrary to ANSI. - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <stdlib.h> - -_ACEOF -if (eval "$ac_cpp conftest.$ac_ext") 2>&5 | - $EGREP "free" >/dev/null 2>&1; then - : -else - ac_cv_header_stdc=no -fi -rm -f conftest* - -fi - -if test $ac_cv_header_stdc = yes; then - # /bin/cc in Irix-4.0.5 gets non-ANSI ctype macros unless using -ansi. - if test "$cross_compiling" = yes; then - : -else - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <ctype.h> -#if ((' ' & 0x0FF) == 0x020) -# define ISLOWER(c) ('a' <= (c) && (c) <= 'z') -# define TOUPPER(c) (ISLOWER(c) ? 'A' + ((c) - 'a') : (c)) -#else -# define ISLOWER(c) \ - (('a' <= (c) && (c) <= 'i') \ - || ('j' <= (c) && (c) <= 'r') \ - || ('s' <= (c) && (c) <= 'z')) -# define TOUPPER(c) (ISLOWER(c) ? ((c) | 0x40) : (c)) -#endif - -#define XOR(e, f) (((e) && !(f)) || (!(e) && (f))) -int -main () -{ - int i; - for (i = 0; i < 256; i++) - if (XOR (islower (i), ISLOWER (i)) - || toupper (i) != TOUPPER (i)) - exit(2); - exit (0); -} -_ACEOF -rm -f conftest$ac_exeext -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && { ac_try='./conftest$ac_exeext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - : -else - echo "$as_me: program exited with status $ac_status" >&5 -echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -( exit $ac_status ) -ac_cv_header_stdc=no -fi -rm -f core core.* *.core gmon.out bb.out conftest$ac_exeext conftest.$ac_objext conftest.$ac_ext -fi -fi -fi -echo "$as_me:$LINENO: result: $ac_cv_header_stdc" >&5 -echo "${ECHO_T}$ac_cv_header_stdc" >&6 -if test $ac_cv_header_stdc = yes; then - -cat >>confdefs.h <<\_ACEOF -#define STDC_HEADERS 1 -_ACEOF - -fi - - -for ac_header in limits.h -do -as_ac_Header=`echo "ac_cv_header_$ac_header" | $as_tr_sh` -if eval "test \"\${$as_ac_Header+set}\" = set"; then - echo "$as_me:$LINENO: checking for $ac_header" >&5 -echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 -if eval "test \"\${$as_ac_Header+set}\" = set"; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -fi -echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 -echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 -else - # Is the header compilable? -echo "$as_me:$LINENO: checking $ac_header usability" >&5 -echo $ECHO_N "checking $ac_header usability... $ECHO_C" >&6 -cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -$ac_includes_default -#include <$ac_header> -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_header_compiler=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -ac_header_compiler=no -fi -rm -f conftest.$ac_objext conftest.$ac_ext -echo "$as_me:$LINENO: result: $ac_header_compiler" >&5 -echo "${ECHO_T}$ac_header_compiler" >&6 - -# Is the header present? -echo "$as_me:$LINENO: checking $ac_header presence" >&5 -echo $ECHO_N "checking $ac_header presence... $ECHO_C" >&6 -cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -#include <$ac_header> -_ACEOF -if { (eval echo "$as_me:$LINENO: \"$ac_cpp conftest.$ac_ext\"") >&5 - (eval $ac_cpp conftest.$ac_ext) 2>conftest.er1 - ac_status=$? - grep -v '^ *+' conftest.er1 >conftest.err - rm -f conftest.er1 - cat conftest.err >&5 - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } >/dev/null; then - if test -s conftest.err; then - ac_cpp_err=$ac_c_preproc_warn_flag - else - ac_cpp_err= - fi -else - ac_cpp_err=yes -fi -if test -z "$ac_cpp_err"; then - ac_header_preproc=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - - ac_header_preproc=no -fi -rm -f conftest.err conftest.$ac_ext -echo "$as_me:$LINENO: result: $ac_header_preproc" >&5 -echo "${ECHO_T}$ac_header_preproc" >&6 - -# So? What about this header? -case $ac_header_compiler:$ac_header_preproc in - yes:no ) - { echo "$as_me:$LINENO: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&5 -echo "$as_me: WARNING: $ac_header: accepted by the compiler, rejected by the preprocessor!" >&2;} - { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the preprocessor's result" >&5 -echo "$as_me: WARNING: $ac_header: proceeding with the preprocessor's result" >&2;} - ( - cat <<\_ASBOX -## ------------------------------------ ## -## Report this to bug-autoconf@gnu.org. ## -## ------------------------------------ ## -_ASBOX - ) | - sed "s/^/$as_me: WARNING: /" >&2 - ;; - no:yes ) - { echo "$as_me:$LINENO: WARNING: $ac_header: present but cannot be compiled" >&5 -echo "$as_me: WARNING: $ac_header: present but cannot be compiled" >&2;} - { echo "$as_me:$LINENO: WARNING: $ac_header: check for missing prerequisite headers?" >&5 -echo "$as_me: WARNING: $ac_header: check for missing prerequisite headers?" >&2;} - { echo "$as_me:$LINENO: WARNING: $ac_header: proceeding with the preprocessor's result" >&5 -echo "$as_me: WARNING: $ac_header: proceeding with the preprocessor's result" >&2;} - ( - cat <<\_ASBOX -## ------------------------------------ ## -## Report this to bug-autoconf@gnu.org. ## -## ------------------------------------ ## -_ASBOX - ) | - sed "s/^/$as_me: WARNING: /" >&2 - ;; -esac -echo "$as_me:$LINENO: checking for $ac_header" >&5 -echo $ECHO_N "checking for $ac_header... $ECHO_C" >&6 -if eval "test \"\${$as_ac_Header+set}\" = set"; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - eval "$as_ac_Header=$ac_header_preproc" -fi -echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_Header'}'`" >&5 -echo "${ECHO_T}`eval echo '${'$as_ac_Header'}'`" >&6 - -fi -if test `eval echo '${'$as_ac_Header'}'` = yes; then - cat >>confdefs.h <<_ACEOF -#define `echo "HAVE_$ac_header" | $as_tr_cpp` 1 -_ACEOF - -fi - -done - - - -echo "$as_me:$LINENO: checking for an ANSI C-conforming const" >&5 -echo $ECHO_N "checking for an ANSI C-conforming const... $ECHO_C" >&6 -if test "${ac_cv_c_const+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ - -int -main () -{ -/* FIXME: Include the comments suggested by Paul. */ -#ifndef __cplusplus - /* Ultrix mips cc rejects this. */ - typedef int charset[2]; - const charset x; - /* SunOS 4.1.1 cc rejects this. */ - char const *const *ccp; - char **p; - /* NEC SVR4.0.2 mips cc rejects this. */ - struct point {int x, y;}; - static struct point const zero = {0,0}; - /* AIX XL C 1.02.0.0 rejects this. - It does not let you subtract one const X* pointer from another in - an arm of an if-expression whose if-part is not a constant - expression */ - const char *g = "string"; - ccp = &g + (g ? g-g : 0); - /* HPUX 7.0 cc rejects these. */ - ++ccp; - p = (char**) ccp; - ccp = (char const *const *) p; - { /* SCO 3.2v4 cc rejects this. */ - char *t; - char const *s = 0 ? (char *) 0 : (char const *) 0; - - *t++ = 0; - } - { /* Someone thinks the Sun supposedly-ANSI compiler will reject this. */ - int x[] = {25, 17}; - const int *foo = &x[0]; - ++foo; - } - { /* Sun SC1.0 ANSI compiler rejects this -- but not the above. */ - typedef const int *iptr; - iptr p = 0; - ++p; - } - { /* AIX XL C 1.02.0.0 rejects this saying - "k.c", line 2.27: 1506-025 (S) Operand must be a modifiable lvalue. */ - struct s { int j; const int *ap[3]; }; - struct s *b; b->j = 5; - } - { /* ULTRIX-32 V3.1 (Rev 9) vcc rejects this */ - const int foo = 10; - } -#endif - - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_cv_c_const=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -ac_cv_c_const=no -fi -rm -f conftest.$ac_objext conftest.$ac_ext -fi -echo "$as_me:$LINENO: result: $ac_cv_c_const" >&5 -echo "${ECHO_T}$ac_cv_c_const" >&6 -if test $ac_cv_c_const = no; then - -cat >>confdefs.h <<\_ACEOF -#define const -_ACEOF - -fi - -echo "$as_me:$LINENO: checking for size_t" >&5 -echo $ECHO_N "checking for size_t... $ECHO_C" >&6 -if test "${ac_cv_type_size_t+set}" = set; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -$ac_includes_default -int -main () -{ -if ((size_t *) 0) - return 0; -if (sizeof (size_t)) - return 0; - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext -if { (eval echo "$as_me:$LINENO: \"$ac_compile\"") >&5 - (eval $ac_compile) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest.$ac_objext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - ac_cv_type_size_t=yes -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -ac_cv_type_size_t=no -fi -rm -f conftest.$ac_objext conftest.$ac_ext -fi -echo "$as_me:$LINENO: result: $ac_cv_type_size_t" >&5 -echo "${ECHO_T}$ac_cv_type_size_t" >&6 -if test $ac_cv_type_size_t = yes; then - : -else - -cat >>confdefs.h <<_ACEOF -#define size_t unsigned -_ACEOF - -fi - - - - - - -for ac_func in bcopy memmove strerror -do -as_ac_var=`echo "ac_cv_func_$ac_func" | $as_tr_sh` -echo "$as_me:$LINENO: checking for $ac_func" >&5 -echo $ECHO_N "checking for $ac_func... $ECHO_C" >&6 -if eval "test \"\${$as_ac_var+set}\" = set"; then - echo $ECHO_N "(cached) $ECHO_C" >&6 -else - cat >conftest.$ac_ext <<_ACEOF -#line $LINENO "configure" -/* confdefs.h. */ -_ACEOF -cat confdefs.h >>conftest.$ac_ext -cat >>conftest.$ac_ext <<_ACEOF -/* end confdefs.h. */ -/* System header to define __stub macros and hopefully few prototypes, - which can conflict with char $ac_func (); below. - Prefer <limits.h> to <assert.h> if __STDC__ is defined, since - <limits.h> exists even on freestanding compilers. */ -#ifdef __STDC__ -# include <limits.h> -#else -# include <assert.h> -#endif -/* Override any gcc2 internal prototype to avoid an error. */ -#ifdef __cplusplus -extern "C" -{ -#endif -/* We use char because int might match the return type of a gcc2 - builtin and then its argument prototype would still apply. */ -char $ac_func (); -/* The GNU C library defines this for functions which it implements - to always fail with ENOSYS. Some functions are actually named - something starting with __ and the normal name is an alias. */ -#if defined (__stub_$ac_func) || defined (__stub___$ac_func) -choke me -#else -char (*f) () = $ac_func; -#endif -#ifdef __cplusplus -} -#endif - -int -main () -{ -return f != $ac_func; - ; - return 0; -} -_ACEOF -rm -f conftest.$ac_objext conftest$ac_exeext -if { (eval echo "$as_me:$LINENO: \"$ac_link\"") >&5 - (eval $ac_link) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); } && - { ac_try='test -s conftest$ac_exeext' - { (eval echo "$as_me:$LINENO: \"$ac_try\"") >&5 - (eval $ac_try) 2>&5 - ac_status=$? - echo "$as_me:$LINENO: \$? = $ac_status" >&5 - (exit $ac_status); }; }; then - eval "$as_ac_var=yes" -else - echo "$as_me: failed program was:" >&5 -sed 's/^/| /' conftest.$ac_ext >&5 - -eval "$as_ac_var=no" -fi -rm -f conftest.$ac_objext conftest$ac_exeext conftest.$ac_ext -fi -echo "$as_me:$LINENO: result: `eval echo '${'$as_ac_var'}'`" >&5 -echo "${ECHO_T}`eval echo '${'$as_ac_var'}'`" >&6 -if test `eval echo '${'$as_ac_var'}'` = yes; then - cat >>confdefs.h <<_ACEOF -#define `echo "HAVE_$ac_func" | $as_tr_cpp` 1 -_ACEOF - -fi -done - - - -# Check whether --enable-utf8 or --disable-utf8 was given. -if test "${enable_utf8+set}" = set; then - enableval="$enable_utf8" - if test "$enableval" = "yes"; then - UTF8=-DSUPPORT_UTF8 -fi - -fi; - - -# Check whether --enable-newline-is-cr or --disable-newline-is-cr was given. -if test "${enable_newline_is_cr+set}" = set; then - enableval="$enable_newline_is_cr" - if test "$enableval" = "yes"; then - NEWLINE=-DNEWLINE=13 -fi - -fi; - - -# Check whether --enable-newline-is-lf or --disable-newline-is-lf was given. -if test "${enable_newline_is_lf+set}" = set; then - enableval="$enable_newline_is_lf" - if test "$enableval" = "yes"; then - NEWLINE=-DNEWLINE=10 -fi - -fi; - - -# Check whether --enable-ebcdic or --disable-ebcdic was given. -if test "${enable_ebcdic+set}" = set; then - enableval="$enable_ebcdic" - if test "$enableval" == "yes"; then - EBCDIC=-DEBCDIC=1 -fi - -fi; - -# Check whether --enable-recursion or --disable-recursion was given. -if test "${enable_recursion+set}" = set; then - enableval="$enable_recursion" - if test "$enableval" = "no"; then - NO_RECURSE=-DNO_RECURSE -fi - -fi; - - - - -# Check whether --with-posix-malloc-threshold or --without-posix-malloc-threshold was given. -if test "${with_posix_malloc_threshold+set}" = set; then - withval="$with_posix_malloc_threshold" - POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=$withval - -fi; - - - -# Check whether --with-link-size or --without-link-size was given. -if test "${with_link_size+set}" = set; then - withval="$with_link_size" - LINK_SIZE=-DLINK_SIZE=$withval - -fi; - - - -# Check whether --with-match-limit or --without-match-limit was given. -if test "${with_match_limit+set}" = set; then - withval="$with_match_limit" - MATCH_LIMIT=-DMATCH_LIMIT=$withval - -fi; - - - - - - - - - - - - - - - - - - - - - - - - - - -case $host_os in -mingw* ) - POSIX_OBJ=pcreposix.o - POSIX_LOBJ=pcreposix.lo - POSIX_LIB= - ON_WINDOWS= - NOT_ON_WINDOWS="#" - WIN_PREFIX= - ;; -* ) - ON_WINDOWS="#" - NOT_ON_WINDOWS= - POSIX_OBJ= - POSIX_LOBJ= - POSIX_LIB=libpcreposix.la - WIN_PREFIX= - ;; -esac - - - - - - - -if test "x$enable_shared" = "xno" ; then - -cat >>confdefs.h <<\_ACEOF -#define PCRE_STATIC 1 -_ACEOF - -fi - - ac_config_files="$ac_config_files Makefile pcre.h:pcre.in pcre-config:pcre-config.in RunTest:RunTest.in" - ac_config_commands="$ac_config_commands default" -cat >confcache <<\_ACEOF -# This file is a shell script that caches the results of configure -# tests run on this system so they can be shared between configure -# scripts and configure runs, see configure's option --config-cache. -# It is not useful on other systems. If it contains results you don't -# want to keep, you may remove or edit it. -# -# config.status only pays attention to the cache file if you give it -# the --recheck option to rerun configure. -# -# `ac_cv_env_foo' variables (set or unset) will be overridden when -# loading this file, other *unset* `ac_cv_foo' will be assigned the -# following values. - -_ACEOF - -# The following way of writing the cache mishandles newlines in values, -# but we know of no workaround that is simple, portable, and efficient. -# So, don't put newlines in cache variables' values. -# Ultrix sh set writes to stderr and can't be redirected directly, -# and sets the high bit in the cache file unless we assign to the vars. -{ - (set) 2>&1 | - case `(ac_space=' '; set | grep ac_space) 2>&1` in - *ac_space=\ *) - # `set' does not quote correctly, so add quotes (double-quote - # substitution turns \\\\ into \\, and sed turns \\ into \). - sed -n \ - "s/'/'\\\\''/g; - s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1='\\2'/p" - ;; - *) - # `set' quotes correctly as required by POSIX, so do not add quotes. - sed -n \ - "s/^\\([_$as_cr_alnum]*_cv_[_$as_cr_alnum]*\\)=\\(.*\\)/\\1=\\2/p" - ;; - esac; -} | - sed ' - t clear - : clear - s/^\([^=]*\)=\(.*[{}].*\)$/test "${\1+set}" = set || &/ - t end - /^ac_cv_env/!s/^\([^=]*\)=\(.*\)$/\1=${\1=\2}/ - : end' >>confcache -if diff $cache_file confcache >/dev/null 2>&1; then :; else - if test -w $cache_file; then - test "x$cache_file" != "x/dev/null" && echo "updating cache $cache_file" - cat confcache >$cache_file - else - echo "not updating unwritable cache $cache_file" - fi -fi -rm -f confcache - -test "x$prefix" = xNONE && prefix=$ac_default_prefix -# Let make expand exec_prefix. -test "x$exec_prefix" = xNONE && exec_prefix='${prefix}' - -# VPATH may cause trouble with some makes, so we remove $(srcdir), -# ${srcdir} and @srcdir@ from VPATH if srcdir is ".", strip leading and -# trailing colons and then remove the whole line if VPATH becomes empty -# (actually we leave an empty line to preserve line numbers). -if test "x$srcdir" = x.; then - ac_vpsub='/^[ ]*VPATH[ ]*=/{ -s/:*\$(srcdir):*/:/; -s/:*\${srcdir}:*/:/; -s/:*@srcdir@:*/:/; -s/^\([^=]*=[ ]*\):*/\1/; -s/:*$//; -s/^[^=]*=[ ]*$//; -}' -fi - -DEFS=-DHAVE_CONFIG_H - -ac_libobjs= -ac_ltlibobjs= -for ac_i in : $LIBOBJS; do test "x$ac_i" = x: && continue - # 1. Remove the extension, and $U if already installed. - ac_i=`echo "$ac_i" | - sed 's/\$U\././;s/\.o$//;s/\.obj$//'` - # 2. Add them. - ac_libobjs="$ac_libobjs $ac_i\$U.$ac_objext" - ac_ltlibobjs="$ac_ltlibobjs $ac_i"'$U.lo' -done -LIBOBJS=$ac_libobjs - -LTLIBOBJS=$ac_ltlibobjs - - - -: ${CONFIG_STATUS=./config.status} -ac_clean_files_save=$ac_clean_files -ac_clean_files="$ac_clean_files $CONFIG_STATUS" -{ echo "$as_me:$LINENO: creating $CONFIG_STATUS" >&5 -echo "$as_me: creating $CONFIG_STATUS" >&6;} -cat >$CONFIG_STATUS <<_ACEOF -#! $SHELL -# Generated by $as_me. -# Run this file to recreate the current configuration. -# Compiler output produced by configure, useful for debugging -# configure, is in config.log if it exists. - -debug=false -ac_cs_recheck=false -ac_cs_silent=false -SHELL=\${CONFIG_SHELL-$SHELL} -_ACEOF - -cat >>$CONFIG_STATUS <<\_ACEOF -## --------------------- ## -## M4sh Initialization. ## -## --------------------- ## - -# Be Bourne compatible -if test -n "${ZSH_VERSION+set}" && (emulate sh) >/dev/null 2>&1; then - emulate sh - NULLCMD=: - # Zsh 3.x and 4.x performs word splitting on ${1+"$@"}, which - # is contrary to our usage. Disable this feature. - alias -g '${1+"$@"}'='"$@"' -elif test -n "${BASH_VERSION+set}" && (set -o posix) >/dev/null 2>&1; then - set -o posix -fi - -# Support unset when possible. -if (FOO=FOO; unset FOO) >/dev/null 2>&1; then - as_unset=unset -else - as_unset=false -fi - - -# Work around bugs in pre-3.0 UWIN ksh. -$as_unset ENV MAIL MAILPATH -PS1='$ ' -PS2='> ' -PS4='+ ' - -# NLS nuisances. -for as_var in \ - LANG LANGUAGE LC_ADDRESS LC_ALL LC_COLLATE LC_CTYPE LC_IDENTIFICATION \ - LC_MEASUREMENT LC_MESSAGES LC_MONETARY LC_NAME LC_NUMERIC LC_PAPER \ - LC_TELEPHONE LC_TIME -do - if (set +x; test -n "`(eval $as_var=C; export $as_var) 2>&1`"); then - eval $as_var=C; export $as_var - else - $as_unset $as_var - fi -done - -# Required to use basename. -if expr a : '\(a\)' >/dev/null 2>&1; then - as_expr=expr -else - as_expr=false -fi - -if (basename /) >/dev/null 2>&1 && test "X`basename / 2>&1`" = "X/"; then - as_basename=basename -else - as_basename=false -fi - - -# Name of the executable. -as_me=`$as_basename "$0" || -$as_expr X/"$0" : '.*/\([^/][^/]*\)/*$' \| \ - X"$0" : 'X\(//\)$' \| \ - X"$0" : 'X\(/\)$' \| \ - . : '\(.\)' 2>/dev/null || -echo X/"$0" | - sed '/^.*\/\([^/][^/]*\)\/*$/{ s//\1/; q; } - /^X\/\(\/\/\)$/{ s//\1/; q; } - /^X\/\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` - - -# PATH needs CR, and LINENO needs CR and PATH. -# Avoid depending upon Character Ranges. -as_cr_letters='abcdefghijklmnopqrstuvwxyz' -as_cr_LETTERS='ABCDEFGHIJKLMNOPQRSTUVWXYZ' -as_cr_Letters=$as_cr_letters$as_cr_LETTERS -as_cr_digits='0123456789' -as_cr_alnum=$as_cr_Letters$as_cr_digits - -# The user is always right. -if test "${PATH_SEPARATOR+set}" != set; then - echo "#! /bin/sh" >conf$$.sh - echo "exit 0" >>conf$$.sh - chmod +x conf$$.sh - if (PATH="/nonexistent;."; conf$$.sh) >/dev/null 2>&1; then - PATH_SEPARATOR=';' - else - PATH_SEPARATOR=: - fi - rm -f conf$$.sh -fi - - - as_lineno_1=$LINENO - as_lineno_2=$LINENO - as_lineno_3=`(expr $as_lineno_1 + 1) 2>/dev/null` - test "x$as_lineno_1" != "x$as_lineno_2" && - test "x$as_lineno_3" = "x$as_lineno_2" || { - # Find who we are. Look in the path if we contain no path at all - # relative or not. - case $0 in - *[\\/]* ) as_myself=$0 ;; - *) as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in $PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - test -r "$as_dir/$0" && as_myself=$as_dir/$0 && break -done - - ;; - esac - # We did not find ourselves, most probably we were run as `sh COMMAND' - # in which case we are not to be found in the path. - if test "x$as_myself" = x; then - as_myself=$0 - fi - if test ! -f "$as_myself"; then - { { echo "$as_me:$LINENO: error: cannot find myself; rerun with an absolute path" >&5 -echo "$as_me: error: cannot find myself; rerun with an absolute path" >&2;} - { (exit 1); exit 1; }; } - fi - case $CONFIG_SHELL in - '') - as_save_IFS=$IFS; IFS=$PATH_SEPARATOR -for as_dir in /bin$PATH_SEPARATOR/usr/bin$PATH_SEPARATOR$PATH -do - IFS=$as_save_IFS - test -z "$as_dir" && as_dir=. - for as_base in sh bash ksh sh5; do - case $as_dir in - /*) - if ("$as_dir/$as_base" -c ' - as_lineno_1=$LINENO - as_lineno_2=$LINENO - as_lineno_3=`(expr $as_lineno_1 + 1) 2>/dev/null` - test "x$as_lineno_1" != "x$as_lineno_2" && - test "x$as_lineno_3" = "x$as_lineno_2" ') 2>/dev/null; then - $as_unset BASH_ENV || test "${BASH_ENV+set}" != set || { BASH_ENV=; export BASH_ENV; } - $as_unset ENV || test "${ENV+set}" != set || { ENV=; export ENV; } - CONFIG_SHELL=$as_dir/$as_base - export CONFIG_SHELL - exec "$CONFIG_SHELL" "$0" ${1+"$@"} - fi;; - esac - done -done -;; - esac - - # Create $as_me.lineno as a copy of $as_myself, but with $LINENO - # uniformly replaced by the line number. The first 'sed' inserts a - # line-number line before each line; the second 'sed' does the real - # work. The second script uses 'N' to pair each line-number line - # with the numbered line, and appends trailing '-' during - # substitution so that $LINENO is not a special case at line end. - # (Raja R Harinath suggested sed '=', and Paul Eggert wrote the - # second 'sed' script. Blame Lee E. McMahon for sed's syntax. :-) - sed '=' <$as_myself | - sed ' - N - s,$,-, - : loop - s,^\(['$as_cr_digits']*\)\(.*\)[$]LINENO\([^'$as_cr_alnum'_]\),\1\2\1\3, - t loop - s,-$,, - s,^['$as_cr_digits']*\n,, - ' >$as_me.lineno && - chmod +x $as_me.lineno || - { { echo "$as_me:$LINENO: error: cannot create $as_me.lineno; rerun with a POSIX shell" >&5 -echo "$as_me: error: cannot create $as_me.lineno; rerun with a POSIX shell" >&2;} - { (exit 1); exit 1; }; } - - # Don't try to exec as it changes $[0], causing all sort of problems - # (the dirname of $[0] is not the place where we might find the - # original and so on. Autoconf is especially sensible to this). - . ./$as_me.lineno - # Exit status is that of the last command. - exit -} - - -case `echo "testing\c"; echo 1,2,3`,`echo -n testing; echo 1,2,3` in - *c*,-n*) ECHO_N= ECHO_C=' -' ECHO_T=' ' ;; - *c*,* ) ECHO_N=-n ECHO_C= ECHO_T= ;; - *) ECHO_N= ECHO_C='\c' ECHO_T= ;; -esac - -if expr a : '\(a\)' >/dev/null 2>&1; then - as_expr=expr -else - as_expr=false -fi - -rm -f conf$$ conf$$.exe conf$$.file -echo >conf$$.file -if ln -s conf$$.file conf$$ 2>/dev/null; then - # We could just check for DJGPP; but this test a) works b) is more generic - # and c) will remain valid once DJGPP supports symlinks (DJGPP 2.04). - if test -f conf$$.exe; then - # Don't use ln at all; we don't have any links - as_ln_s='cp -p' - else - as_ln_s='ln -s' - fi -elif ln conf$$.file conf$$ 2>/dev/null; then - as_ln_s=ln -else - as_ln_s='cp -p' -fi -rm -f conf$$ conf$$.exe conf$$.file - -if mkdir -p . 2>/dev/null; then - as_mkdir_p=: -else - as_mkdir_p=false -fi - -as_executable_p="test -f" - -# Sed expression to map a string onto a valid CPP name. -as_tr_cpp="sed y%*$as_cr_letters%P$as_cr_LETTERS%;s%[^_$as_cr_alnum]%_%g" - -# Sed expression to map a string onto a valid variable name. -as_tr_sh="sed y%*+%pp%;s%[^_$as_cr_alnum]%_%g" - - -# IFS -# We need space, tab and new line, in precisely that order. -as_nl=' -' -IFS=" $as_nl" - -# CDPATH. -$as_unset CDPATH - -exec 6>&1 - -# Open the log real soon, to keep \$[0] and so on meaningful, and to -# report actual input values of CONFIG_FILES etc. instead of their -# values after options handling. Logging --version etc. is OK. -exec 5>>config.log -{ - echo - sed 'h;s/./-/g;s/^.../## /;s/...$/ ##/;p;x;p;x' <<_ASBOX -## Running $as_me. ## -_ASBOX -} >&5 -cat >&5 <<_CSEOF - -This file was extended by $as_me, which was -generated by GNU Autoconf 2.57. Invocation command line was - - CONFIG_FILES = $CONFIG_FILES - CONFIG_HEADERS = $CONFIG_HEADERS - CONFIG_LINKS = $CONFIG_LINKS - CONFIG_COMMANDS = $CONFIG_COMMANDS - $ $0 $@ - -_CSEOF -echo "on `(hostname || uname -n) 2>/dev/null | sed 1q`" >&5 -echo >&5 -_ACEOF - -# Files that config.status was made for. -if test -n "$ac_config_files"; then - echo "config_files=\"$ac_config_files\"" >>$CONFIG_STATUS -fi - -if test -n "$ac_config_headers"; then - echo "config_headers=\"$ac_config_headers\"" >>$CONFIG_STATUS -fi - -if test -n "$ac_config_links"; then - echo "config_links=\"$ac_config_links\"" >>$CONFIG_STATUS -fi - -if test -n "$ac_config_commands"; then - echo "config_commands=\"$ac_config_commands\"" >>$CONFIG_STATUS -fi - -cat >>$CONFIG_STATUS <<\_ACEOF - -ac_cs_usage="\ -\`$as_me' instantiates files from templates according to the -current configuration. - -Usage: $0 [OPTIONS] [FILE]... - - -h, --help print this help, then exit - -V, --version print version number, then exit - -q, --quiet do not print progress messages - -d, --debug don't remove temporary files - --recheck update $as_me by reconfiguring in the same conditions - --file=FILE[:TEMPLATE] - instantiate the configuration file FILE - --header=FILE[:TEMPLATE] - instantiate the configuration header FILE - -Configuration files: -$config_files - -Configuration headers: -$config_headers - -Configuration commands: -$config_commands - -Report bugs to <bug-autoconf@gnu.org>." -_ACEOF - -cat >>$CONFIG_STATUS <<_ACEOF -ac_cs_version="\\ -config.status -configured by $0, generated by GNU Autoconf 2.57, - with options \\"`echo "$ac_configure_args" | sed 's/[\\""\`\$]/\\\\&/g'`\\" - -Copyright 1992, 1993, 1994, 1995, 1996, 1998, 1999, 2000, 2001 -Free Software Foundation, Inc. -This config.status script is free software; the Free Software Foundation -gives unlimited permission to copy, distribute and modify it." -srcdir=$srcdir -INSTALL="$INSTALL" -_ACEOF - -cat >>$CONFIG_STATUS <<\_ACEOF -# If no file are specified by the user, then we need to provide default -# value. By we need to know if files were specified by the user. -ac_need_defaults=: -while test $# != 0 -do - case $1 in - --*=*) - ac_option=`expr "x$1" : 'x\([^=]*\)='` - ac_optarg=`expr "x$1" : 'x[^=]*=\(.*\)'` - ac_shift=: - ;; - -*) - ac_option=$1 - ac_optarg=$2 - ac_shift=shift - ;; - *) # This is not an option, so the user has probably given explicit - # arguments. - ac_option=$1 - ac_need_defaults=false;; - esac - - case $ac_option in - # Handling of the options. -_ACEOF -cat >>$CONFIG_STATUS <<\_ACEOF - -recheck | --recheck | --rechec | --reche | --rech | --rec | --re | --r) - ac_cs_recheck=: ;; - --version | --vers* | -V ) - echo "$ac_cs_version"; exit 0 ;; - --he | --h) - # Conflict between --help and --header - { { echo "$as_me:$LINENO: error: ambiguous option: $1 -Try \`$0 --help' for more information." >&5 -echo "$as_me: error: ambiguous option: $1 -Try \`$0 --help' for more information." >&2;} - { (exit 1); exit 1; }; };; - --help | --hel | -h ) - echo "$ac_cs_usage"; exit 0 ;; - --debug | --d* | -d ) - debug=: ;; - --file | --fil | --fi | --f ) - $ac_shift - CONFIG_FILES="$CONFIG_FILES $ac_optarg" - ac_need_defaults=false;; - --header | --heade | --head | --hea ) - $ac_shift - CONFIG_HEADERS="$CONFIG_HEADERS $ac_optarg" - ac_need_defaults=false;; - -q | -quiet | --quiet | --quie | --qui | --qu | --q \ - | -silent | --silent | --silen | --sile | --sil | --si | --s) - ac_cs_silent=: ;; - - # This is an error. - -*) { { echo "$as_me:$LINENO: error: unrecognized option: $1 -Try \`$0 --help' for more information." >&5 -echo "$as_me: error: unrecognized option: $1 -Try \`$0 --help' for more information." >&2;} - { (exit 1); exit 1; }; } ;; - - *) ac_config_targets="$ac_config_targets $1" ;; - - esac - shift -done - -ac_configure_extra_args= - -if $ac_cs_silent; then - exec 6>/dev/null - ac_configure_extra_args="$ac_configure_extra_args --silent" -fi - -_ACEOF -cat >>$CONFIG_STATUS <<_ACEOF -if \$ac_cs_recheck; then - echo "running $SHELL $0 " $ac_configure_args \$ac_configure_extra_args " --no-create --no-recursion" >&6 - exec $SHELL $0 $ac_configure_args \$ac_configure_extra_args --no-create --no-recursion -fi - -_ACEOF - - - - - -cat >>$CONFIG_STATUS <<\_ACEOF -for ac_config_target in $ac_config_targets -do - case "$ac_config_target" in - # Handling of arguments. - "Makefile" ) CONFIG_FILES="$CONFIG_FILES Makefile" ;; - "pcre.h" ) CONFIG_FILES="$CONFIG_FILES pcre.h:pcre.in" ;; - "pcre-config" ) CONFIG_FILES="$CONFIG_FILES pcre-config:pcre-config.in" ;; - "RunTest" ) CONFIG_FILES="$CONFIG_FILES RunTest:RunTest.in" ;; - "default" ) CONFIG_COMMANDS="$CONFIG_COMMANDS default" ;; - "config.h" ) CONFIG_HEADERS="$CONFIG_HEADERS config.h:config.in" ;; - *) { { echo "$as_me:$LINENO: error: invalid argument: $ac_config_target" >&5 -echo "$as_me: error: invalid argument: $ac_config_target" >&2;} - { (exit 1); exit 1; }; };; - esac -done - -# If the user did not use the arguments to specify the items to instantiate, -# then the envvar interface is used. Set only those that are not. -# We use the long form for the default assignment because of an extremely -# bizarre bug on SunOS 4.1.3. -if $ac_need_defaults; then - test "${CONFIG_FILES+set}" = set || CONFIG_FILES=$config_files - test "${CONFIG_HEADERS+set}" = set || CONFIG_HEADERS=$config_headers - test "${CONFIG_COMMANDS+set}" = set || CONFIG_COMMANDS=$config_commands -fi - -# Have a temporary directory for convenience. Make it in the build tree -# simply because there is no reason to put it here, and in addition, -# creating and moving files from /tmp can sometimes cause problems. -# Create a temporary directory, and hook for its removal unless debugging. -$debug || -{ - trap 'exit_status=$?; rm -rf $tmp && exit $exit_status' 0 - trap '{ (exit 1); exit 1; }' 1 2 13 15 -} - -# Create a (secure) tmp directory for tmp files. - -{ - tmp=`(umask 077 && mktemp -d -q "./confstatXXXXXX") 2>/dev/null` && - test -n "$tmp" && test -d "$tmp" -} || -{ - tmp=./confstat$$-$RANDOM - (umask 077 && mkdir $tmp) -} || -{ - echo "$me: cannot create a temporary directory in ." >&2 - { (exit 1); exit 1; } -} - -_ACEOF - -cat >>$CONFIG_STATUS <<_ACEOF - -# -# CONFIG_FILES section. -# - -# No need to generate the scripts if there are no CONFIG_FILES. -# This happens for instance when ./config.status config.h -if test -n "\$CONFIG_FILES"; then - # Protect against being on the right side of a sed subst in config.status. - sed 's/,@/@@/; s/@,/@@/; s/,;t t\$/@;t t/; /@;t t\$/s/[\\\\&,]/\\\\&/g; - s/@@/,@/; s/@@/@,/; s/@;t t\$/,;t t/' >\$tmp/subs.sed <<\\CEOF -s,@SHELL@,$SHELL,;t t -s,@PATH_SEPARATOR@,$PATH_SEPARATOR,;t t -s,@PACKAGE_NAME@,$PACKAGE_NAME,;t t -s,@PACKAGE_TARNAME@,$PACKAGE_TARNAME,;t t -s,@PACKAGE_VERSION@,$PACKAGE_VERSION,;t t -s,@PACKAGE_STRING@,$PACKAGE_STRING,;t t -s,@PACKAGE_BUGREPORT@,$PACKAGE_BUGREPORT,;t t -s,@exec_prefix@,$exec_prefix,;t t -s,@prefix@,$prefix,;t t -s,@program_transform_name@,$program_transform_name,;t t -s,@bindir@,$bindir,;t t -s,@sbindir@,$sbindir,;t t -s,@libexecdir@,$libexecdir,;t t -s,@datadir@,$datadir,;t t -s,@sysconfdir@,$sysconfdir,;t t -s,@sharedstatedir@,$sharedstatedir,;t t -s,@localstatedir@,$localstatedir,;t t -s,@libdir@,$libdir,;t t -s,@includedir@,$includedir,;t t -s,@oldincludedir@,$oldincludedir,;t t -s,@infodir@,$infodir,;t t -s,@mandir@,$mandir,;t t -s,@build_alias@,$build_alias,;t t -s,@host_alias@,$host_alias,;t t -s,@target_alias@,$target_alias,;t t -s,@DEFS@,$DEFS,;t t -s,@ECHO_C@,$ECHO_C,;t t -s,@ECHO_N@,$ECHO_N,;t t -s,@ECHO_T@,$ECHO_T,;t t -s,@LIBS@,$LIBS,;t t -s,@CC@,$CC,;t t -s,@CFLAGS@,$CFLAGS,;t t -s,@LDFLAGS@,$LDFLAGS,;t t -s,@CPPFLAGS@,$CPPFLAGS,;t t -s,@ac_ct_CC@,$ac_ct_CC,;t t -s,@EXEEXT@,$EXEEXT,;t t -s,@OBJEXT@,$OBJEXT,;t t -s,@INSTALL_PROGRAM@,$INSTALL_PROGRAM,;t t -s,@INSTALL_SCRIPT@,$INSTALL_SCRIPT,;t t -s,@INSTALL_DATA@,$INSTALL_DATA,;t t -s,@build@,$build,;t t -s,@build_cpu@,$build_cpu,;t t -s,@build_vendor@,$build_vendor,;t t -s,@build_os@,$build_os,;t t -s,@host@,$host,;t t -s,@host_cpu@,$host_cpu,;t t -s,@host_vendor@,$host_vendor,;t t -s,@host_os@,$host_os,;t t -s,@LN_S@,$LN_S,;t t -s,@ECHO@,$ECHO,;t t -s,@RANLIB@,$RANLIB,;t t -s,@ac_ct_RANLIB@,$ac_ct_RANLIB,;t t -s,@STRIP@,$STRIP,;t t -s,@ac_ct_STRIP@,$ac_ct_STRIP,;t t -s,@CPP@,$CPP,;t t -s,@EGREP@,$EGREP,;t t -s,@LIBTOOL@,$LIBTOOL,;t t -s,@BUILD_EXEEXT@,$BUILD_EXEEXT,;t t -s,@BUILD_OBJEXT@,$BUILD_OBJEXT,;t t -s,@CC_FOR_BUILD@,$CC_FOR_BUILD,;t t -s,@CFLAGS_FOR_BUILD@,$CFLAGS_FOR_BUILD,;t t -s,@EBCDIC@,$EBCDIC,;t t -s,@HAVE_MEMMOVE@,$HAVE_MEMMOVE,;t t -s,@HAVE_STRERROR@,$HAVE_STRERROR,;t t -s,@LINK_SIZE@,$LINK_SIZE,;t t -s,@MATCH_LIMIT@,$MATCH_LIMIT,;t t -s,@NEWLINE@,$NEWLINE,;t t -s,@NO_RECURSE@,$NO_RECURSE,;t t -s,@PCRE_MAJOR@,$PCRE_MAJOR,;t t -s,@PCRE_MINOR@,$PCRE_MINOR,;t t -s,@PCRE_DATE@,$PCRE_DATE,;t t -s,@PCRE_VERSION@,$PCRE_VERSION,;t t -s,@PCRE_LIB_VERSION@,$PCRE_LIB_VERSION,;t t -s,@PCRE_POSIXLIB_VERSION@,$PCRE_POSIXLIB_VERSION,;t t -s,@POSIX_MALLOC_THRESHOLD@,$POSIX_MALLOC_THRESHOLD,;t t -s,@UTF8@,$UTF8,;t t -s,@WIN_PREFIX@,$WIN_PREFIX,;t t -s,@ON_WINDOWS@,$ON_WINDOWS,;t t -s,@NOT_ON_WINDOWS@,$NOT_ON_WINDOWS,;t t -s,@POSIX_OBJ@,$POSIX_OBJ,;t t -s,@POSIX_LOBJ@,$POSIX_LOBJ,;t t -s,@POSIX_LIB@,$POSIX_LIB,;t t -s,@LIBOBJS@,$LIBOBJS,;t t -s,@LTLIBOBJS@,$LTLIBOBJS,;t t -CEOF - -_ACEOF - - cat >>$CONFIG_STATUS <<\_ACEOF - # Split the substitutions into bite-sized pieces for seds with - # small command number limits, like on Digital OSF/1 and HP-UX. - ac_max_sed_lines=48 - ac_sed_frag=1 # Number of current file. - ac_beg=1 # First line for current file. - ac_end=$ac_max_sed_lines # Line after last line for current file. - ac_more_lines=: - ac_sed_cmds= - while $ac_more_lines; do - if test $ac_beg -gt 1; then - sed "1,${ac_beg}d; ${ac_end}q" $tmp/subs.sed >$tmp/subs.frag - else - sed "${ac_end}q" $tmp/subs.sed >$tmp/subs.frag - fi - if test ! -s $tmp/subs.frag; then - ac_more_lines=false - else - # The purpose of the label and of the branching condition is to - # speed up the sed processing (if there are no `@' at all, there - # is no need to browse any of the substitutions). - # These are the two extra sed commands mentioned above. - (echo ':t - /@[a-zA-Z_][a-zA-Z_0-9]*@/!b' && cat $tmp/subs.frag) >$tmp/subs-$ac_sed_frag.sed - if test -z "$ac_sed_cmds"; then - ac_sed_cmds="sed -f $tmp/subs-$ac_sed_frag.sed" - else - ac_sed_cmds="$ac_sed_cmds | sed -f $tmp/subs-$ac_sed_frag.sed" - fi - ac_sed_frag=`expr $ac_sed_frag + 1` - ac_beg=$ac_end - ac_end=`expr $ac_end + $ac_max_sed_lines` - fi - done - if test -z "$ac_sed_cmds"; then - ac_sed_cmds=cat - fi -fi # test -n "$CONFIG_FILES" - -_ACEOF -cat >>$CONFIG_STATUS <<\_ACEOF -for ac_file in : $CONFIG_FILES; do test "x$ac_file" = x: && continue - # Support "outfile[:infile[:infile...]]", defaulting infile="outfile.in". - case $ac_file in - - | *:- | *:-:* ) # input from stdin - cat >$tmp/stdin - ac_file_in=`echo "$ac_file" | sed 's,[^:]*:,,'` - ac_file=`echo "$ac_file" | sed 's,:.*,,'` ;; - *:* ) ac_file_in=`echo "$ac_file" | sed 's,[^:]*:,,'` - ac_file=`echo "$ac_file" | sed 's,:.*,,'` ;; - * ) ac_file_in=$ac_file.in ;; - esac - - # Compute @srcdir@, @top_srcdir@, and @INSTALL@ for subdirectories. - ac_dir=`(dirname "$ac_file") 2>/dev/null || -$as_expr X"$ac_file" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ - X"$ac_file" : 'X\(//\)[^/]' \| \ - X"$ac_file" : 'X\(//\)$' \| \ - X"$ac_file" : 'X\(/\)' \| \ - . : '\(.\)' 2>/dev/null || -echo X"$ac_file" | - sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } - /^X\(\/\/\)[^/].*/{ s//\1/; q; } - /^X\(\/\/\)$/{ s//\1/; q; } - /^X\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` - { if $as_mkdir_p; then - mkdir -p "$ac_dir" - else - as_dir="$ac_dir" - as_dirs= - while test ! -d "$as_dir"; do - as_dirs="$as_dir $as_dirs" - as_dir=`(dirname "$as_dir") 2>/dev/null || -$as_expr X"$as_dir" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ - X"$as_dir" : 'X\(//\)[^/]' \| \ - X"$as_dir" : 'X\(//\)$' \| \ - X"$as_dir" : 'X\(/\)' \| \ - . : '\(.\)' 2>/dev/null || -echo X"$as_dir" | - sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } - /^X\(\/\/\)[^/].*/{ s//\1/; q; } - /^X\(\/\/\)$/{ s//\1/; q; } - /^X\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` - done - test ! -n "$as_dirs" || mkdir $as_dirs - fi || { { echo "$as_me:$LINENO: error: cannot create directory \"$ac_dir\"" >&5 -echo "$as_me: error: cannot create directory \"$ac_dir\"" >&2;} - { (exit 1); exit 1; }; }; } - - ac_builddir=. - -if test "$ac_dir" != .; then - ac_dir_suffix=/`echo "$ac_dir" | sed 's,^\.[\\/],,'` - # A "../" for each directory in $ac_dir_suffix. - ac_top_builddir=`echo "$ac_dir_suffix" | sed 's,/[^\\/]*,../,g'` -else - ac_dir_suffix= ac_top_builddir= -fi - -case $srcdir in - .) # No --srcdir option. We are building in place. - ac_srcdir=. - if test -z "$ac_top_builddir"; then - ac_top_srcdir=. - else - ac_top_srcdir=`echo $ac_top_builddir | sed 's,/$,,'` - fi ;; - [\\/]* | ?:[\\/]* ) # Absolute path. - ac_srcdir=$srcdir$ac_dir_suffix; - ac_top_srcdir=$srcdir ;; - *) # Relative path. - ac_srcdir=$ac_top_builddir$srcdir$ac_dir_suffix - ac_top_srcdir=$ac_top_builddir$srcdir ;; -esac -# Don't blindly perform a `cd "$ac_dir"/$ac_foo && pwd` since $ac_foo can be -# absolute. -ac_abs_builddir=`cd "$ac_dir" && cd $ac_builddir && pwd` -ac_abs_top_builddir=`cd "$ac_dir" && cd ${ac_top_builddir}. && pwd` -ac_abs_srcdir=`cd "$ac_dir" && cd $ac_srcdir && pwd` -ac_abs_top_srcdir=`cd "$ac_dir" && cd $ac_top_srcdir && pwd` - - - case $INSTALL in - [\\/$]* | ?:[\\/]* ) ac_INSTALL=$INSTALL ;; - *) ac_INSTALL=$ac_top_builddir$INSTALL ;; - esac - - if test x"$ac_file" != x-; then - { echo "$as_me:$LINENO: creating $ac_file" >&5 -echo "$as_me: creating $ac_file" >&6;} - rm -f "$ac_file" - fi - # Let's still pretend it is `configure' which instantiates (i.e., don't - # use $as_me), people would be surprised to read: - # /* config.h. Generated by config.status. */ - if test x"$ac_file" = x-; then - configure_input= - else - configure_input="$ac_file. " - fi - configure_input=$configure_input"Generated from `echo $ac_file_in | - sed 's,.*/,,'` by configure." - - # First look for the input files in the build tree, otherwise in the - # src tree. - ac_file_inputs=`IFS=: - for f in $ac_file_in; do - case $f in - -) echo $tmp/stdin ;; - [\\/$]*) - # Absolute (can't be DOS-style, as IFS=:) - test -f "$f" || { { echo "$as_me:$LINENO: error: cannot find input file: $f" >&5 -echo "$as_me: error: cannot find input file: $f" >&2;} - { (exit 1); exit 1; }; } - echo $f;; - *) # Relative - if test -f "$f"; then - # Build tree - echo $f - elif test -f "$srcdir/$f"; then - # Source tree - echo $srcdir/$f - else - # /dev/null tree - { { echo "$as_me:$LINENO: error: cannot find input file: $f" >&5 -echo "$as_me: error: cannot find input file: $f" >&2;} - { (exit 1); exit 1; }; } - fi;; - esac - done` || { (exit 1); exit 1; } -_ACEOF -cat >>$CONFIG_STATUS <<_ACEOF - sed "$ac_vpsub -$extrasub -_ACEOF -cat >>$CONFIG_STATUS <<\_ACEOF -:t -/@[a-zA-Z_][a-zA-Z_0-9]*@/!b -s,@configure_input@,$configure_input,;t t -s,@srcdir@,$ac_srcdir,;t t -s,@abs_srcdir@,$ac_abs_srcdir,;t t -s,@top_srcdir@,$ac_top_srcdir,;t t -s,@abs_top_srcdir@,$ac_abs_top_srcdir,;t t -s,@builddir@,$ac_builddir,;t t -s,@abs_builddir@,$ac_abs_builddir,;t t -s,@top_builddir@,$ac_top_builddir,;t t -s,@abs_top_builddir@,$ac_abs_top_builddir,;t t -s,@INSTALL@,$ac_INSTALL,;t t -" $ac_file_inputs | (eval "$ac_sed_cmds") >$tmp/out - rm -f $tmp/stdin - if test x"$ac_file" != x-; then - mv $tmp/out $ac_file - else - cat $tmp/out - rm -f $tmp/out - fi - -done -_ACEOF -cat >>$CONFIG_STATUS <<\_ACEOF - -# -# CONFIG_HEADER section. -# - -# These sed commands are passed to sed as "A NAME B NAME C VALUE D", where -# NAME is the cpp macro being defined and VALUE is the value it is being given. -# -# ac_d sets the value in "#define NAME VALUE" lines. -ac_dA='s,^\([ ]*\)#\([ ]*define[ ][ ]*\)' -ac_dB='[ ].*$,\1#\2' -ac_dC=' ' -ac_dD=',;t' -# ac_u turns "#undef NAME" without trailing blanks into "#define NAME VALUE". -ac_uA='s,^\([ ]*\)#\([ ]*\)undef\([ ][ ]*\)' -ac_uB='$,\1#\2define\3' -ac_uC=' ' -ac_uD=',;t' - -for ac_file in : $CONFIG_HEADERS; do test "x$ac_file" = x: && continue - # Support "outfile[:infile[:infile...]]", defaulting infile="outfile.in". - case $ac_file in - - | *:- | *:-:* ) # input from stdin - cat >$tmp/stdin - ac_file_in=`echo "$ac_file" | sed 's,[^:]*:,,'` - ac_file=`echo "$ac_file" | sed 's,:.*,,'` ;; - *:* ) ac_file_in=`echo "$ac_file" | sed 's,[^:]*:,,'` - ac_file=`echo "$ac_file" | sed 's,:.*,,'` ;; - * ) ac_file_in=$ac_file.in ;; - esac - - test x"$ac_file" != x- && { echo "$as_me:$LINENO: creating $ac_file" >&5 -echo "$as_me: creating $ac_file" >&6;} - - # First look for the input files in the build tree, otherwise in the - # src tree. - ac_file_inputs=`IFS=: - for f in $ac_file_in; do - case $f in - -) echo $tmp/stdin ;; - [\\/$]*) - # Absolute (can't be DOS-style, as IFS=:) - test -f "$f" || { { echo "$as_me:$LINENO: error: cannot find input file: $f" >&5 -echo "$as_me: error: cannot find input file: $f" >&2;} - { (exit 1); exit 1; }; } - echo $f;; - *) # Relative - if test -f "$f"; then - # Build tree - echo $f - elif test -f "$srcdir/$f"; then - # Source tree - echo $srcdir/$f - else - # /dev/null tree - { { echo "$as_me:$LINENO: error: cannot find input file: $f" >&5 -echo "$as_me: error: cannot find input file: $f" >&2;} - { (exit 1); exit 1; }; } - fi;; - esac - done` || { (exit 1); exit 1; } - # Remove the trailing spaces. - sed 's/[ ]*$//' $ac_file_inputs >$tmp/in - -_ACEOF - -# Transform confdefs.h into two sed scripts, `conftest.defines' and -# `conftest.undefs', that substitutes the proper values into -# config.h.in to produce config.h. The first handles `#define' -# templates, and the second `#undef' templates. -# And first: Protect against being on the right side of a sed subst in -# config.status. Protect against being in an unquoted here document -# in config.status. -rm -f conftest.defines conftest.undefs -# Using a here document instead of a string reduces the quoting nightmare. -# Putting comments in sed scripts is not portable. -# -# `end' is used to avoid that the second main sed command (meant for -# 0-ary CPP macros) applies to n-ary macro definitions. -# See the Autoconf documentation for `clear'. -cat >confdef2sed.sed <<\_ACEOF -s/[\\&,]/\\&/g -s,[\\$`],\\&,g -t clear -: clear -s,^[ ]*#[ ]*define[ ][ ]*\([^ (][^ (]*\)\(([^)]*)\)[ ]*\(.*\)$,${ac_dA}\1${ac_dB}\1\2${ac_dC}\3${ac_dD},gp -t end -s,^[ ]*#[ ]*define[ ][ ]*\([^ ][^ ]*\)[ ]*\(.*\)$,${ac_dA}\1${ac_dB}\1${ac_dC}\2${ac_dD},gp -: end -_ACEOF -# If some macros were called several times there might be several times -# the same #defines, which is useless. Nevertheless, we may not want to -# sort them, since we want the *last* AC-DEFINE to be honored. -uniq confdefs.h | sed -n -f confdef2sed.sed >conftest.defines -sed 's/ac_d/ac_u/g' conftest.defines >conftest.undefs -rm -f confdef2sed.sed - -# This sed command replaces #undef with comments. This is necessary, for -# example, in the case of _POSIX_SOURCE, which is predefined and required -# on some systems where configure will not decide to define it. -cat >>conftest.undefs <<\_ACEOF -s,^[ ]*#[ ]*undef[ ][ ]*[a-zA-Z_][a-zA-Z_0-9]*,/* & */, -_ACEOF - -# Break up conftest.defines because some shells have a limit on the size -# of here documents, and old seds have small limits too (100 cmds). -echo ' # Handle all the #define templates only if necessary.' >>$CONFIG_STATUS -echo ' if grep "^[ ]*#[ ]*define" $tmp/in >/dev/null; then' >>$CONFIG_STATUS -echo ' # If there are no defines, we may have an empty if/fi' >>$CONFIG_STATUS -echo ' :' >>$CONFIG_STATUS -rm -f conftest.tail -while grep . conftest.defines >/dev/null -do - # Write a limited-size here document to $tmp/defines.sed. - echo ' cat >$tmp/defines.sed <<CEOF' >>$CONFIG_STATUS - # Speed up: don't consider the non `#define' lines. - echo '/^[ ]*#[ ]*define/!b' >>$CONFIG_STATUS - # Work around the forget-to-reset-the-flag bug. - echo 't clr' >>$CONFIG_STATUS - echo ': clr' >>$CONFIG_STATUS - sed ${ac_max_here_lines}q conftest.defines >>$CONFIG_STATUS - echo 'CEOF - sed -f $tmp/defines.sed $tmp/in >$tmp/out - rm -f $tmp/in - mv $tmp/out $tmp/in -' >>$CONFIG_STATUS - sed 1,${ac_max_here_lines}d conftest.defines >conftest.tail - rm -f conftest.defines - mv conftest.tail conftest.defines -done -rm -f conftest.defines -echo ' fi # grep' >>$CONFIG_STATUS -echo >>$CONFIG_STATUS - -# Break up conftest.undefs because some shells have a limit on the size -# of here documents, and old seds have small limits too (100 cmds). -echo ' # Handle all the #undef templates' >>$CONFIG_STATUS -rm -f conftest.tail -while grep . conftest.undefs >/dev/null -do - # Write a limited-size here document to $tmp/undefs.sed. - echo ' cat >$tmp/undefs.sed <<CEOF' >>$CONFIG_STATUS - # Speed up: don't consider the non `#undef' - echo '/^[ ]*#[ ]*undef/!b' >>$CONFIG_STATUS - # Work around the forget-to-reset-the-flag bug. - echo 't clr' >>$CONFIG_STATUS - echo ': clr' >>$CONFIG_STATUS - sed ${ac_max_here_lines}q conftest.undefs >>$CONFIG_STATUS - echo 'CEOF - sed -f $tmp/undefs.sed $tmp/in >$tmp/out - rm -f $tmp/in - mv $tmp/out $tmp/in -' >>$CONFIG_STATUS - sed 1,${ac_max_here_lines}d conftest.undefs >conftest.tail - rm -f conftest.undefs - mv conftest.tail conftest.undefs -done -rm -f conftest.undefs - -cat >>$CONFIG_STATUS <<\_ACEOF - # Let's still pretend it is `configure' which instantiates (i.e., don't - # use $as_me), people would be surprised to read: - # /* config.h. Generated by config.status. */ - if test x"$ac_file" = x-; then - echo "/* Generated by configure. */" >$tmp/config.h - else - echo "/* $ac_file. Generated by configure. */" >$tmp/config.h - fi - cat $tmp/in >>$tmp/config.h - rm -f $tmp/in - if test x"$ac_file" != x-; then - if diff $ac_file $tmp/config.h >/dev/null 2>&1; then - { echo "$as_me:$LINENO: $ac_file is unchanged" >&5 -echo "$as_me: $ac_file is unchanged" >&6;} - else - ac_dir=`(dirname "$ac_file") 2>/dev/null || -$as_expr X"$ac_file" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ - X"$ac_file" : 'X\(//\)[^/]' \| \ - X"$ac_file" : 'X\(//\)$' \| \ - X"$ac_file" : 'X\(/\)' \| \ - . : '\(.\)' 2>/dev/null || -echo X"$ac_file" | - sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } - /^X\(\/\/\)[^/].*/{ s//\1/; q; } - /^X\(\/\/\)$/{ s//\1/; q; } - /^X\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` - { if $as_mkdir_p; then - mkdir -p "$ac_dir" - else - as_dir="$ac_dir" - as_dirs= - while test ! -d "$as_dir"; do - as_dirs="$as_dir $as_dirs" - as_dir=`(dirname "$as_dir") 2>/dev/null || -$as_expr X"$as_dir" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ - X"$as_dir" : 'X\(//\)[^/]' \| \ - X"$as_dir" : 'X\(//\)$' \| \ - X"$as_dir" : 'X\(/\)' \| \ - . : '\(.\)' 2>/dev/null || -echo X"$as_dir" | - sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } - /^X\(\/\/\)[^/].*/{ s//\1/; q; } - /^X\(\/\/\)$/{ s//\1/; q; } - /^X\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` - done - test ! -n "$as_dirs" || mkdir $as_dirs - fi || { { echo "$as_me:$LINENO: error: cannot create directory \"$ac_dir\"" >&5 -echo "$as_me: error: cannot create directory \"$ac_dir\"" >&2;} - { (exit 1); exit 1; }; }; } - - rm -f $ac_file - mv $tmp/config.h $ac_file - fi - else - cat $tmp/config.h - rm -f $tmp/config.h - fi -done -_ACEOF -cat >>$CONFIG_STATUS <<\_ACEOF - -# -# CONFIG_COMMANDS section. -# -for ac_file in : $CONFIG_COMMANDS; do test "x$ac_file" = x: && continue - ac_dest=`echo "$ac_file" | sed 's,:.*,,'` - ac_source=`echo "$ac_file" | sed 's,[^:]*:,,'` - ac_dir=`(dirname "$ac_dest") 2>/dev/null || -$as_expr X"$ac_dest" : 'X\(.*[^/]\)//*[^/][^/]*/*$' \| \ - X"$ac_dest" : 'X\(//\)[^/]' \| \ - X"$ac_dest" : 'X\(//\)$' \| \ - X"$ac_dest" : 'X\(/\)' \| \ - . : '\(.\)' 2>/dev/null || -echo X"$ac_dest" | - sed '/^X\(.*[^/]\)\/\/*[^/][^/]*\/*$/{ s//\1/; q; } - /^X\(\/\/\)[^/].*/{ s//\1/; q; } - /^X\(\/\/\)$/{ s//\1/; q; } - /^X\(\/\).*/{ s//\1/; q; } - s/.*/./; q'` - ac_builddir=. - -if test "$ac_dir" != .; then - ac_dir_suffix=/`echo "$ac_dir" | sed 's,^\.[\\/],,'` - # A "../" for each directory in $ac_dir_suffix. - ac_top_builddir=`echo "$ac_dir_suffix" | sed 's,/[^\\/]*,../,g'` -else - ac_dir_suffix= ac_top_builddir= -fi - -case $srcdir in - .) # No --srcdir option. We are building in place. - ac_srcdir=. - if test -z "$ac_top_builddir"; then - ac_top_srcdir=. - else - ac_top_srcdir=`echo $ac_top_builddir | sed 's,/$,,'` - fi ;; - [\\/]* | ?:[\\/]* ) # Absolute path. - ac_srcdir=$srcdir$ac_dir_suffix; - ac_top_srcdir=$srcdir ;; - *) # Relative path. - ac_srcdir=$ac_top_builddir$srcdir$ac_dir_suffix - ac_top_srcdir=$ac_top_builddir$srcdir ;; -esac -# Don't blindly perform a `cd "$ac_dir"/$ac_foo && pwd` since $ac_foo can be -# absolute. -ac_abs_builddir=`cd "$ac_dir" && cd $ac_builddir && pwd` -ac_abs_top_builddir=`cd "$ac_dir" && cd ${ac_top_builddir}. && pwd` -ac_abs_srcdir=`cd "$ac_dir" && cd $ac_srcdir && pwd` -ac_abs_top_srcdir=`cd "$ac_dir" && cd $ac_top_srcdir && pwd` - - - { echo "$as_me:$LINENO: executing $ac_dest commands" >&5 -echo "$as_me: executing $ac_dest commands" >&6;} - case $ac_dest in - default ) chmod a+x RunTest pcre-config ;; - esac -done -_ACEOF - -cat >>$CONFIG_STATUS <<\_ACEOF - -{ (exit 0); exit 0; } -_ACEOF -chmod +x $CONFIG_STATUS -ac_clean_files=$ac_clean_files_save - - -# configure is writing to config.log, and then calls config.status. -# config.status does its own redirection, appending to config.log. -# Unfortunately, on DOS this fails, as config.log is still kept open -# by configure, so config.status won't be able to write to it; its -# output is simply discarded. So we exec the FD to /dev/null, -# effectively closing config.log, so it can be properly (re)opened and -# appended to by config.status. When coming back to configure, we -# need to make the FD available again. -if test "$no_create" != yes; then - ac_cs_success=: - ac_config_status_args= - test "$silent" = yes && - ac_config_status_args="$ac_config_status_args --quiet" - exec 5>/dev/null - $SHELL $CONFIG_STATUS $ac_config_status_args || ac_cs_success=false - exec 5>>config.log - # Use ||, not &&, to avoid exiting from the if with $? = 1, which - # would make configure fail if this is the last instruction. - $ac_cs_success || { (exit 1); exit 1; } -fi - diff --git a/external-libs/pcre/configure.in b/external-libs/pcre/configure.in deleted file mode 100644 index d32b301d..00000000 --- a/external-libs/pcre/configure.in +++ /dev/null @@ -1,201 +0,0 @@ -dnl Process this file with autoconf to produce a configure script. - -dnl This is required at the start; the name is the name of a file -dnl it should be seeing, to verify it is in the same directory. - -AC_INIT(dftables.c) - -dnl A safety precaution - -AC_PREREQ(2.57) - -dnl Arrange to build config.h from config.in. Note that pcre.h is -dnl built differently, as it is just a "substitution" file. -dnl Manual says this macro should come right after AC_INIT. -AC_CONFIG_HEADER(config.h:config.in) - -dnl Provide the current PCRE version information. Do not use numbers -dnl with leading zeros for the minor version, as they end up in a C -dnl macro, and may be treated as octal constants. Stick to single -dnl digits for minor numbers less than 10. There are unlikely to be -dnl that many releases anyway. - -PCRE_MAJOR=4 -PCRE_MINOR=5 -PCRE_DATE=01-December-2003 -PCRE_VERSION=${PCRE_MAJOR}.${PCRE_MINOR} - -dnl Default values for miscellaneous macros - -POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=10 - -dnl Provide versioning information for libtool shared libraries that -dnl are built by default on Unix systems. - -PCRE_LIB_VERSION=0:1:0 -PCRE_POSIXLIB_VERSION=0:0:0 - -dnl Checks for programs. - -AC_PROG_CC -AC_PROG_INSTALL -AC_LIBTOOL_WIN32_DLL -AC_PROG_LIBTOOL - -dnl We need to find a compiler for compiling a program to run on the local host -dnl while building. It needs to be different from CC when cross-compiling. -dnl There is a macro called AC_PROG_CC_FOR_BUILD in the GNU archive for -dnl figuring this out automatically. Unfortunately, it does not work with the -dnl latest versions of autoconf. So for the moment, we just default to the -dnl same values as the "main" compiler. People who are corss-compiling will -dnl just have to adjust the Makefile by hand or set these values when they -dnl run "configure". - -CC_FOR_BUILD=${CC_FOR_BUILD:-'$(CC)'} -CFLAGS_FOR_BUILD=${CFLAGS_FOR_BUILD:-'$(CFLAGS)'} -BUILD_EXEEXT=${BUILD_EXEEXT:-'$(EXEEXT)'} -BUILD_OBJEXT=${BUILD_OBJEXT:-'$(OBJEXT)'} - -dnl Checks for header files. - -AC_HEADER_STDC -AC_CHECK_HEADERS(limits.h) - -dnl Checks for typedefs, structures, and compiler characteristics. - -AC_C_CONST -AC_TYPE_SIZE_T - -dnl Checks for library functions. - -AC_CHECK_FUNCS(bcopy memmove strerror) - -dnl Handle --enable-utf8 - -AC_ARG_ENABLE(utf8, -[ --enable-utf8 enable UTF8 support], -if test "$enableval" = "yes"; then - UTF8=-DSUPPORT_UTF8 -fi -) - -dnl Handle --enable-newline-is-cr - -AC_ARG_ENABLE(newline-is-cr, -[ --enable-newline-is-cr use CR as the newline character], -if test "$enableval" = "yes"; then - NEWLINE=-DNEWLINE=13 -fi -) - -dnl Handle --enable-newline-is-lf - -AC_ARG_ENABLE(newline-is-lf, -[ --enable-newline-is-lf use LF as the newline character], -if test "$enableval" = "yes"; then - NEWLINE=-DNEWLINE=10 -fi -) - -dnl Handle --enable-ebcdic - -AC_ARG_ENABLE(ebcdic, -[ --enable-ebcdic assume EBCDIC coding rather than ASCII], -if test "$enableval" == "yes"; then - EBCDIC=-DEBCDIC=1 -fi -) - -dnl Handle --disable-stack-for-recursion -AC_ARG_ENABLE(recursion, -[ --disable-stack-for-recursion disable use of stack recursion when matching], -if test "$enableval" = "no"; then - NO_RECURSE=-DNO_RECURSE -fi -) - -dnl There doesn't seem to be a straightforward way of having parameters -dnl that set values, other than fudging the --with thing. So that's what -dnl I've done. - -dnl Handle --with-posix-malloc-threshold=n - -AC_ARG_WITH(posix-malloc-threshold, -[ --with-posix-malloc-threshold=5 threshold for POSIX malloc usage], - POSIX_MALLOC_THRESHOLD=-DPOSIX_MALLOC_THRESHOLD=$withval -) - -dnl Handle --with-link-size=n - -AC_ARG_WITH(link-size, -[ --with-link-size=2 internal link size (2, 3, or 4 allowed)], - LINK_SIZE=-DLINK_SIZE=$withval -) - -dnl Handle --with-match_limit=n - -AC_ARG_WITH(match-limit, -[ --with-match-limit=10000000 default limit on internal looping)], - MATCH_LIMIT=-DMATCH_LIMIT=$withval -) - -dnl Now arrange to build libtool - -AC_PROG_LIBTOOL - -dnl "Export" these variables - -AC_SUBST(BUILD_EXEEXT) -AC_SUBST(BUILD_OBJEXT) -AC_SUBST(CC_FOR_BUILD) -AC_SUBST(CFLAGS_FOR_BUILD) -AC_SUBST(EBCDIC) -AC_SUBST(HAVE_MEMMOVE) -AC_SUBST(HAVE_STRERROR) -AC_SUBST(LINK_SIZE) -AC_SUBST(MATCH_LIMIT) -AC_SUBST(NEWLINE) -AC_SUBST(NO_RECURSE) -AC_SUBST(PCRE_MAJOR) -AC_SUBST(PCRE_MINOR) -AC_SUBST(PCRE_DATE) -AC_SUBST(PCRE_VERSION) -AC_SUBST(PCRE_LIB_VERSION) -AC_SUBST(PCRE_POSIXLIB_VERSION) -AC_SUBST(POSIX_MALLOC_THRESHOLD) -AC_SUBST(UTF8) - -dnl Stuff to make MinGW work better. Special treatment is no longer -dnl needed for Cygwin. - -case $host_os in -mingw* ) - POSIX_OBJ=pcreposix.o - POSIX_LOBJ=pcreposix.lo - POSIX_LIB= - ON_WINDOWS= - NOT_ON_WINDOWS="#" - WIN_PREFIX= - ;; -* ) - ON_WINDOWS="#" - NOT_ON_WINDOWS= - POSIX_OBJ= - POSIX_LOBJ= - POSIX_LIB=libpcreposix.la - WIN_PREFIX= - ;; -esac -AC_SUBST(WIN_PREFIX) -AC_SUBST(ON_WINDOWS) -AC_SUBST(NOT_ON_WINDOWS) -AC_SUBST(POSIX_OBJ) -AC_SUBST(POSIX_LOBJ) -AC_SUBST(POSIX_LIB) - -if test "x$enable_shared" = "xno" ; then - AC_DEFINE([PCRE_STATIC],[1],[to link statically]) -fi - -dnl This must be last; it determines what files are written as well as config.h -AC_OUTPUT(Makefile pcre.h:pcre.in pcre-config:pcre-config.in RunTest:RunTest.in,[chmod a+x RunTest pcre-config]) diff --git a/external-libs/pcre/doc/Tech.Notes b/external-libs/pcre/doc/Tech.Notes deleted file mode 100644 index 73c31c7c..00000000 --- a/external-libs/pcre/doc/Tech.Notes +++ /dev/null @@ -1,281 +0,0 @@ -Technical Notes about PCRE --------------------------- - -Many years ago I implemented some regular expression functions to an algorithm -suggested by Martin Richards. These were not Unix-like in form, and were quite -restricted in what they could do by comparison with Perl. The interesting part -about the algorithm was that the amount of space required to hold the compiled -form of an expression was known in advance. The code to apply an expression did -not operate by backtracking, as the original Henry Spencer code and current -Perl code does, but instead checked all possibilities simultaneously by keeping -a list of current states and checking all of them as it advanced through the -subject string. (In the terminology of Jeffrey Friedl's book, it was a "DFA -algorithm".) When the pattern was all used up, all remaining states were -possible matches, and the one matching the longest subset of the subject string -was chosen. This did not necessarily maximize the individual wild portions of -the pattern, as is expected in Unix and Perl-style regular expressions. - -By contrast, the code originally written by Henry Spencer and subsequently -heavily modified for Perl actually compiles the expression twice: once in a -dummy mode in order to find out how much store will be needed, and then for -real. The execution function operates by backtracking and maximizing (or, -optionally, minimizing in Perl) the amount of the subject that matches -individual wild portions of the pattern. This is an "NFA algorithm" in Friedl's -terminology. - -For the set of functions that forms PCRE (which are unrelated to those -mentioned above), I tried at first to invent an algorithm that used an amount -of store bounded by a multiple of the number of characters in the pattern, to -save on compiling time. However, because of the greater complexity in Perl -regular expressions, I couldn't do this. In any case, a first pass through the -pattern is needed, for a number of reasons. PCRE works by running a very -degenerate first pass to calculate a maximum store size, and then a second pass -to do the real compile - which may use a bit less than the predicted amount of -store. The idea is that this is going to turn out faster because the first pass -is degenerate and the second pass can just store stuff straight into the -vector. It does make the compiling functions bigger, of course, but they have -got quite big anyway to handle all the Perl stuff. - -The compiled form of a pattern is a vector of bytes, containing items of -variable length. The first byte in an item is an opcode, and the length of the -item is either implicit in the opcode or contained in the data bytes which -follow it. A list of all the opcodes follows: - -Opcodes with no following data ------------------------------- - -These items are all just one byte long - - OP_END end of pattern - OP_ANY match any character - OP_ANYBYTE match any single byte, even in UTF-8 mode - OP_SOD match start of data: \A - OP_SOM, start of match (subject + offset): \G - OP_CIRC ^ (start of data, or after \n in multiline) - OP_NOT_WORD_BOUNDARY \W - OP_WORD_BOUNDARY \w - OP_NOT_DIGIT \D - OP_DIGIT \d - OP_NOT_WHITESPACE \S - OP_WHITESPACE \s - OP_NOT_WORDCHAR \W - OP_WORDCHAR \w - OP_EODN match end of data or \n at end: \Z - OP_EOD match end of data: \z - OP_DOLL $ (end of data, or before \n in multiline) - - -Repeating single characters ---------------------------- - -The common repeats (*, +, ?) when applied to a single character appear as -two-byte items using the following opcodes: - - OP_STAR - OP_MINSTAR - OP_PLUS - OP_MINPLUS - OP_QUERY - OP_MINQUERY - -Those with "MIN" in their name are the minimizing versions. Each is followed by -the character that is to be repeated. Other repeats make use of - - OP_UPTO - OP_MINUPTO - OP_EXACT - -which are followed by a two-byte count (most significant first) and the -repeated character. OP_UPTO matches from 0 to the given number. A repeat with a -non-zero minimum and a fixed maximum is coded as an OP_EXACT followed by an -OP_UPTO (or OP_MINUPTO). - - -Repeating character types -------------------------- - -Repeats of things like \d are done exactly as for single characters, except -that instead of a character, the opcode for the type is stored in the data -byte. The opcodes are: - - OP_TYPESTAR - OP_TYPEMINSTAR - OP_TYPEPLUS - OP_TYPEMINPLUS - OP_TYPEQUERY - OP_TYPEMINQUERY - OP_TYPEUPTO - OP_TYPEMINUPTO - OP_TYPEEXACT - - -Matching a character string ---------------------------- - -The OP_CHARS opcode is followed by a one-byte count and then that number of -characters. If there are more than 255 characters in sequence, successive -instances of OP_CHARS are used. - - -Character classes ------------------ - -If there is only one character, OP_CHARS is used for a positive class, -and OP_NOT for a negative one (that is, for something like [^a]). However, in -UTF-8 mode, this applies only to characters with values < 128, because OP_NOT -is confined to single bytes. - -Another set of repeating opcodes (OP_NOTSTAR etc.) are used for a repeated, -negated, single-character class. The normal ones (OP_STAR etc.) are used for a -repeated positive single-character class. - -When there's more than one character in a class and all the characters are less -than 256, OP_CLASS is used for a positive class, and OP_NCLASS for a negative -one. In either case, the opcode is followed by a 32-byte bit map containing a 1 -bit for every character that is acceptable. The bits are counted from the least -significant end of each byte. - -The reason for having both OP_CLASS and OP_NCLASS is so that, in UTF-8 mode, -subject characters with values greater than 256 can be handled correctly. For -OP_CLASS they don't match, whereas for OP_NCLASS they do. - -For classes containing characters with values > 255, OP_XCLASS is used. It -optionally uses a bit map (if any characters lie within it), followed by a list -of pairs and single characters. There is a flag character than indicates -whether it's a positive or a negative class. - - -Back references ---------------- - -OP_REF is followed by two bytes containing the reference number. - - -Repeating character classes and back references ------------------------------------------------ - -Single-character classes are handled specially (see above). This applies to -OP_CLASS and OP_REF. In both cases, the repeat information follows the base -item. The matching code looks at the following opcode to see if it is one of - - OP_CRSTAR - OP_CRMINSTAR - OP_CRPLUS - OP_CRMINPLUS - OP_CRQUERY - OP_CRMINQUERY - OP_CRRANGE - OP_CRMINRANGE - -All but the last two are just single-byte items. The others are followed by -four bytes of data, comprising the minimum and maximum repeat counts. - - -Brackets and alternation ------------------------- - -A pair of non-capturing (round) brackets is wrapped round each expression at -compile time, so alternation always happens in the context of brackets. - -Non-capturing brackets use the opcode OP_BRA, while capturing brackets use -OP_BRA+1, OP_BRA+2, etc. [Note for North Americans: "bracket" to some English -speakers, including myself, can be round, square, curly, or pointy. Hence this -usage.] - -Originally PCRE was limited to 99 capturing brackets (so as not to use up all -the opcodes). From release 3.5, there is no limit. What happens is that the -first ones, up to EXTRACT_BASIC_MAX are handled with separate opcodes, as -above. If there are more, the opcode is set to EXTRACT_BASIC_MAX+1, and the -first operation in the bracket is OP_BRANUMBER, followed by a 2-byte bracket -number. This opcode is ignored while matching, but is fished out when handling -the bracket itself. (They could have all been done like this, but I was making -minimal changes.) - -A bracket opcode is followed by two bytes which give the offset to the next -alternative OP_ALT or, if there aren't any branches, to the matching KET -opcode. Each OP_ALT is followed by two bytes giving the offset to the next one, -or to the KET opcode. - -OP_KET is used for subpatterns that do not repeat indefinitely, while -OP_KETRMIN and OP_KETRMAX are used for indefinite repetitions, minimally or -maximally respectively. All three are followed by two bytes giving (as a -positive number) the offset back to the matching BRA opcode. - -If a subpattern is quantified such that it is permitted to match zero times, it -is preceded by one of OP_BRAZERO or OP_BRAMINZERO. These are single-byte -opcodes which tell the matcher that skipping this subpattern entirely is a -valid branch. - -A subpattern with an indefinite maximum repetition is replicated in the -compiled data its minimum number of times (or once with a BRAZERO if the -minimum is zero), with the final copy terminating with a KETRMIN or KETRMAX as -appropriate. - -A subpattern with a bounded maximum repetition is replicated in a nested -fashion up to the maximum number of times, with BRAZERO or BRAMINZERO before -each replication after the minimum, so that, for example, (abc){2,5} is -compiled as (abc)(abc)((abc)((abc)(abc)?)?)?. The 99 and 200 bracket limits do -not apply to these internally generated brackets. - - -Assertions ----------- - -Forward assertions are just like other subpatterns, but starting with one of -the opcodes OP_ASSERT or OP_ASSERT_NOT. Backward assertions use the opcodes -OP_ASSERTBACK and OP_ASSERTBACK_NOT, and the first opcode inside the assertion -is OP_REVERSE, followed by a two byte count of the number of characters to move -back the pointer in the subject string. When operating in UTF-8 mode, the count -is a character count rather than a byte count. A separate count is present in -each alternative of a lookbehind assertion, allowing them to have different -fixed lengths. - - -Once-only subpatterns ---------------------- - -These are also just like other subpatterns, but they start with the opcode -OP_ONCE. - - -Conditional subpatterns ------------------------ - -These are like other subpatterns, but they start with the opcode OP_COND. If -the condition is a back reference, this is stored at the start of the -subpattern using the opcode OP_CREF followed by two bytes containing the -reference number. If the condition is "in recursion" (coded as "(?(R)"), the -same scheme is used, with a "reference number" of 0xffff. Otherwise, a -conditional subpattern always starts with one of the assertions. - - -Recursion ---------- - -Recursion either matches the current regex, or some subexpression. The opcode -OP_RECURSE is followed by an value which is the offset to the starting bracket -from the start of the whole pattern. - - -Callout -------- - -OP_CALLOUT is followed by one byte of data that holds a callout number in the -range 0 to 255. - - -Changing options ----------------- - -If any of the /i, /m, or /s options are changed within a pattern, an OP_OPT -opcode is compiled, followed by one byte containing the new settings of these -flags. If there are several alternatives, there is an occurrence of OP_OPT at -the start of all those following the first options change, to set appropriate -options for the start of the alternative. Immediately after the end of the -group there is another such item to reset the flags to their previous values. A -change of flag right at the very start of the pattern can be handled entirely -at compile time, and so does not cause anything to be put into the compiled -data. - -Philip Hazel -August 2003 diff --git a/external-libs/pcre/doc/html/index.html b/external-libs/pcre/doc/html/index.html deleted file mode 100644 index 3751ff0f..00000000 --- a/external-libs/pcre/doc/html/index.html +++ /dev/null @@ -1,102 +0,0 @@ -<html> -<head> -<title>PCRE specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -<h1>Perl-compatible Regular Expressions (PCRE)</h1> -<p> -The HTML documentation for PCRE comprises the following pages: -</p> - -<table> -<tr><td><a href="pcre.html">pcre</a></td> - <td> Introductory page</td></tr> - -<tr><td><a href="pcreapi.html">pcreapi</a></td> - <td> PCRE's native API</td></tr> - -<tr><td><a href="pcrebuild.html">pcrebuild</a></td> - <td> Options for building PCRE</td></tr> - -<tr><td><a href="pcrecallout.html">pcrecallout</a></td> - <td> The <i>callout</i> facility</td></tr> - -<tr><td><a href="pcrecompat.html">pcrecompat</a></td> - <td> Compability with Perl</td></tr> - -<tr><td><a href="pcregrep.html">pcregrep</a></td> - <td> The <b>pcregrep</b> command</td></tr> - -<tr><td><a href="pcrepattern.html">pcrepattern</a></td> - <td> Regular expressions supported by PCRE</td></tr> - -<tr><td><a href="pcreperform.html">pcreperform</a></td> - <td> Some comments on performance</td></tr> - -<tr><td><a href="pcreposix.html">pcreposix</a></td> - <td> The POSIX API to the PCRE library</td></tr> - -<tr><td><a href="pcresample.html">pcresample</a></td> - <td> Description of the sample program</td></tr> - -<tr><td><a href="pcretest.html">pcretest</a></td> - <td> The <b>pcretest</b> command for testing PCRE</td></tr> -</table> - -<p> -There are also individual pages that summarize the interface for each function -in the library: -</p> - -<table> - -<tr><td><a href="pcre_compile.html">pcre_compile</a></td> - <td> Compile a regular expression</td></tr> - -<tr><td><a href="pcre_config.html">pcre_config</a></td> - <td> Show build-time configuration options</td></tr> - -<tr><td><a href="pcre_copy_named_substring.html">pcre_copy_named_substring</a></td> - <td> Extract named substring into given buffer</td></tr> - -<tr><td><a href="pcre_copy_substring.html">pcre_copy_substring</a></td> - <td> Extract numbered substring into given buffer</td></tr> - -<tr><td><a href="pcre_exec.html">pcre_exec</a></td> - <td> Match a compiled pattern to a subject string</td></tr> - -<tr><td><a href="pcre_free_substring.html">pcre_free_substring</a></td> - <td> Free extracted substring</td></tr> - -<tr><td><a href="pcre_free_substring_list.html">pcre_free_substring_list</a></td> - <td> Free list of extracted substrings</td></tr> - -<tr><td><a href="pcre_fullinfo.html">pcre_fullinfo</a></td> - <td> Extract information about a pattern</td></tr> - -<tr><td><a href="pcre_get_named_substring.html">pcre_get_named_substring</a></td> - <td> Extract named substring into new memory</td></tr> - -<tr><td><a href="pcre_get_stringnumber.html">pcre_get_stringnumber</a></td> - <td> Convert captured string name to number</td></tr> - -<tr><td><a href="pcre_get_substring.html">pcre_get_substring</a></td> - <td> Extract numbered substring into new memory</td></tr> - -<tr><td><a href="pcre_get_substring_list.html">pcre_get_substring_list</a></td> - <td> Extract all substrings into new memory</td></tr> - -<tr><td><a href="pcre_info.html">pcre_info</a></td> - <td> Obsolete information extraction function</td></tr> - -<tr><td><a href="pcre_maketables.html">pcre_maketables</a></td> - <td> Build character tables in current locale</td></tr> - -<tr><td><a href="pcre_study.html">pcre_study</a></td> - <td> Study a compiled pattern</td></tr> - -<tr><td><a href="pcre_version.html">pcre_version</a></td> - <td> Return PCRE version and release date</td></tr> -</table> - -</html> diff --git a/external-libs/pcre/doc/html/pcre.html b/external-libs/pcre/doc/html/pcre.html deleted file mode 100644 index bb0d3548..00000000 --- a/external-libs/pcre/doc/html/pcre.html +++ /dev/null @@ -1,190 +0,0 @@ -<html> -<head> -<title>pcre specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<ul> -<li><a name="TOC1" href="#SEC1">DESCRIPTION</a> -<li><a name="TOC2" href="#SEC2">USER DOCUMENTATION</a> -<li><a name="TOC3" href="#SEC3">LIMITATIONS</a> -<li><a name="TOC4" href="#SEC4">UTF-8 SUPPORT</a> -<li><a name="TOC5" href="#SEC5">AUTHOR</a> -</ul> -<br><a name="SEC1" href="#TOC1">DESCRIPTION</a><br> -<P> -The PCRE library is a set of functions that implement regular expression -pattern matching using the same syntax and semantics as Perl, with just a few -differences. The current implementation of PCRE (release 4.x) corresponds -approximately with Perl 5.8, including support for UTF-8 encoded strings. -However, this support has to be explicitly enabled; it is not the default. -</P> -<P> -PCRE is written in C and released as a C library. However, a number of people -have written wrappers and interfaces of various kinds. A C++ class is included -in these contributions, which can be found in the <i>Contrib</i> directory at -the primary FTP site, which is: -</P> -<a href="ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre">ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre</a> -<P> -Details of exactly which Perl regular expression features are and are not -supported by PCRE are given in separate documents. See the -<a href="pcrepattern.html"><b>pcrepattern</b></a> -and -<a href="pcrecompat.html"><b>pcrecompat</b></a> -pages. -</P> -<P> -Some features of PCRE can be included, excluded, or changed when the library is -built. The -<a href="pcre_config.html"><b>pcre_config()</b></a> -function makes it possible for a client to discover which features are -available. Documentation about building PCRE for various operating systems can -be found in the <b>README</b> file in the source distribution. -</P> -<br><a name="SEC2" href="#TOC1">USER DOCUMENTATION</a><br> -<P> -The user documentation for PCRE has been split up into a number of different -sections. In the "man" format, each of these is a separate "man page". In the -HTML format, each is a separate page, linked from the index page. In the plain -text format, all the sections are concatenated, for ease of searching. The -sections are as follows: -</P> -<P> -<pre> - pcre this document - pcreapi details of PCRE's native API - pcrebuild options for building PCRE - pcrecallout details of the callout feature - pcrecompat discussion of Perl compatibility - pcregrep description of the <b>pcregrep</b> command - pcrepattern syntax and semantics of supported - regular expressions - pcreperform discussion of performance issues - pcreposix the POSIX-compatible API - pcresample discussion of the sample program - pcretest the <b>pcretest</b> testing command -</PRE> -</P> -<P> -In addition, in the "man" and HTML formats, there is a short page for each -library function, listing its arguments and results. -</P> -<br><a name="SEC3" href="#TOC1">LIMITATIONS</a><br> -<P> -There are some size limitations in PCRE but it is hoped that they will never in -practice be relevant. -</P> -<P> -The maximum length of a compiled pattern is 65539 (sic) bytes if PCRE is -compiled with the default internal linkage size of 2. If you want to process -regular expressions that are truly enormous, you can compile PCRE with an -internal linkage size of 3 or 4 (see the <b>README</b> file in the source -distribution and the -<a href="pcrebuild.html"><b>pcrebuild</b></a> -documentation for details). If these cases the limit is substantially larger. -However, the speed of execution will be slower. -</P> -<P> -All values in repeating quantifiers must be less than 65536. -The maximum number of capturing subpatterns is 65535. -</P> -<P> -There is no limit to the number of non-capturing subpatterns, but the maximum -depth of nesting of all kinds of parenthesized subpattern, including capturing -subpatterns, assertions, and other types of subpattern, is 200. -</P> -<P> -The maximum length of a subject string is the largest positive number that an -integer variable can hold. However, PCRE uses recursion to handle subpatterns -and indefinite repetition. This means that the available stack space may limit -the size of a subject string that can be processed by certain patterns. -</P> -<a name="utf8support"></a><br><a name="SEC4" href="#TOC1">UTF-8 SUPPORT</a><br> -<P> -Starting at release 3.3, PCRE has had some support for character strings -encoded in the UTF-8 format. For release 4.0 this has been greatly extended to -cover most common requirements. -</P> -<P> -In order process UTF-8 strings, you must build PCRE to include UTF-8 support in -the code, and, in addition, you must call -<a href="pcre_compile.html"><b>pcre_compile()</b></a> -with the PCRE_UTF8 option flag. When you do this, both the pattern and any -subject strings that are matched against it are treated as UTF-8 strings -instead of just strings of bytes. -</P> -<P> -If you compile PCRE with UTF-8 support, but do not use it at run time, the -library will be a bit bigger, but the additional run time overhead is limited -to testing the PCRE_UTF8 flag in several places, so should not be very large. -</P> -<P> -The following comments apply when PCRE is running in UTF-8 mode: -</P> -<P> -1. When you set the PCRE_UTF8 flag, the strings passed as patterns and subjects -are checked for validity on entry to the relevant functions. If an invalid -UTF-8 string is passed, an error return is given. In some situations, you may -already know that your strings are valid, and therefore want to skip these -checks in order to improve performance. If you set the PCRE_NO_UTF8_CHECK flag -at compile time or at run time, PCRE assumes that the pattern or subject it -is given (respectively) contains only valid UTF-8 codes. In this case, it does -not diagnose an invalid UTF-8 string. If you pass an invalid UTF-8 string to -PCRE when PCRE_NO_UTF8_CHECK is set, the results are undefined. Your program -may crash. -</P> -<P> -2. In a pattern, the escape sequence \x{...}, where the contents of the braces -is a string of hexadecimal digits, is interpreted as a UTF-8 character whose -code number is the given hexadecimal number, for example: \x{1234}. If a -non-hexadecimal digit appears between the braces, the item is not recognized. -This escape sequence can be used either as a literal, or within a character -class. -</P> -<P> -3. The original hexadecimal escape sequence, \xhh, matches a two-byte UTF-8 -character if the value is greater than 127. -</P> -<P> -4. Repeat quantifiers apply to complete UTF-8 characters, not to individual -bytes, for example: \x{100}{3}. -</P> -<P> -5. The dot metacharacter matches one UTF-8 character instead of a single byte. -</P> -<P> -6. The escape sequence \C can be used to match a single byte in UTF-8 mode, -but its use can lead to some strange effects. -</P> -<P> -7. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly -test characters of any code value, but the characters that PCRE recognizes as -digits, spaces, or word characters remain the same set as before, all with -values less than 256. -</P> -<P> -8. Case-insensitive matching applies only to characters whose values are less -than 256. PCRE does not support the notion of "case" for higher-valued -characters. -</P> -<P> -9. PCRE does not support the use of Unicode tables and properties or the Perl -escapes \p, \P, and \X. -</P> -<br><a name="SEC5" href="#TOC1">AUTHOR</a><br> -<P> -Philip Hazel <ph10@cam.ac.uk> -<br> -University Computing Service, -<br> -Cambridge CB2 3QG, England. -<br> -Phone: +44 1223 334714 -</P> -<P> -Last updated: 20 August 2003 -<br> -Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcre_compile.html b/external-libs/pcre/doc/html/pcre_compile.html deleted file mode 100644 index e1a43793..00000000 --- a/external-libs/pcre/doc/html/pcre_compile.html +++ /dev/null @@ -1,71 +0,0 @@ -<html> -<head> -<title>pcre_compile specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b> -<b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b> -<b>const unsigned char *<i>tableptr</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This function compiles a regular expression into an internal form. Its -arguments are: -</P> -<P> -<pre> - <i>pattern</i> A zero-terminated string containing the - regular expression to be compiled - <i>options</i> Zero or more option bits - <i>errptr</i> Where to put an error message - <i>erroffset</i> Offset in pattern where error was found - <i>tableptr</i> Pointer to character tables, or NULL to - use the built-in default -</PRE> -</P> -<P> -The option bits are: -</P> -<P> -<pre> - PCRE_ANCHORED Force pattern anchoring - PCRE_CASELESS Do caseless matching - PCRE_DOLLAR_ENDONLY $ not to match newline at end - PCRE_DOTALL . matches anything including NL - PCRE_EXTENDED Ignore whitespace and # comments - PCRE_EXTRA PCRE extra features - (not much use currently) - PCRE_MULTILINE ^ and $ match newlines within data - PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- - theses (named ones available) - PCRE_UNGREEDY Invert greediness of quantifiers - PCRE_UTF8 Run in UTF-8 mode - PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 - validity (only relevant if - PCRE_UTF8 is set) -</PRE> -</P> -<P> -PCRE must be compiled with UTF-8 support in order to use PCRE_UTF8 -(or PCRE_NO_UTF8_CHECK). -</P> -<P> -The yield of the function is a pointer to a private data structure that -contains the compiled pattern, or NULL if an error was detected. -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_config.html b/external-libs/pcre/doc/html/pcre_config.html deleted file mode 100644 index 3328b792..00000000 --- a/external-libs/pcre/doc/html/pcre_config.html +++ /dev/null @@ -1,56 +0,0 @@ -<html> -<head> -<title>pcre_config specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This function makes it possible for a client program to find out which optional -features are available in the version of the PCRE library it is using. Its -arguments are as follows: -</P> -<P> -<pre> - <i>what</i> A code specifying what information is required - <i>where</i> Points to where to put the data -</PRE> -</P> -<P> -The available codes are: -</P> -<P> -<pre> - PCRE_CONFIG_LINK_SIZE Internal link size: 2, 3, or 4 - PCRE_CONFIG_MATCH_LIMIT Internal resource limit - PCRE_CONFIG_NEWLINE Value of the newline character - PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - Threshold of return slots, above - which <b>malloc()</b> is used by - the POSIX API - PCRE_CONFIG_STACKRECURSE Recursion implementation (1=stack 0=heap) - PCRE_CONFIG_UTF8 Availability of UTF-8 support (1=yes 0=no) -</PRE> -</P> -<P> -The function yields 0 on success or PCRE_ERROR_BADOPTION otherwise. -</P> -<P> -There is a complete description of the PCRE native API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page, and a description of the POSIX API in the -<a href="pcreposix.html"><b>pcreposix</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_copy_named_substring.html b/external-libs/pcre/doc/html/pcre_copy_named_substring.html deleted file mode 100644 index 3b1da364..00000000 --- a/external-libs/pcre/doc/html/pcre_copy_named_substring.html +++ /dev/null @@ -1,46 +0,0 @@ -<html> -<head> -<title>pcre_copy_named_substring specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b> -<b>const char *<i>subject</i>, int *<i>ovector</i>,</b> -<b>int <i>stringcount</i>, const char *<i>stringname</i>,</b> -<b>char *<i>buffer</i>, int <i>buffersize</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This is a convenience function for extracting a captured substring, identified -by name, into a given buffer. The arguments are: -</P> -<P> -<pre> - <i>code</i> Pattern that was successfully matched - <i>subject</i> Subject that has been successfully matched - <i>ovector</i> Offset vector that <b>pcre_exec()</b> used - <i>stringcount</i> Value returned by <b>pcre_exec()</b> - <i>stringname</i> Name of the required substring - <i>buffer</i> Buffer to receive the string - <i>buffersize</i> Size of buffer -</PRE> -</P> -<P> -The yield is the length of the substring, PCRE_ERROR_NOMEMORY if the buffer was -too small, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_copy_substring.html b/external-libs/pcre/doc/html/pcre_copy_substring.html deleted file mode 100644 index f5b9b553..00000000 --- a/external-libs/pcre/doc/html/pcre_copy_substring.html +++ /dev/null @@ -1,44 +0,0 @@ -<html> -<head> -<title>pcre_copy_substring specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b> -<b>int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b> -<b>int <i>buffersize</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This is a convenience function for extracting a captured substring into a given -buffer. The arguments are: -</P> -<P> -<pre> - <i>subject</i> Subject that has been successfully matched - <i>ovector</i> Offset vector that <b>pcre_exec()</b> used - <i>stringcount</i> Value returned by <b>pcre_exec()</b> - <i>stringnumber</i> Number of the required substring - <i>buffer</i> Buffer to receive the string - <i>buffersize</i> Size of buffer -</PRE> -</P> -<P> -The yield is the legnth of the string, PCRE_ERROR_NOMEMORY if the buffer was -too small, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_exec.html b/external-libs/pcre/doc/html/pcre_exec.html deleted file mode 100644 index cf86dfda..00000000 --- a/external-libs/pcre/doc/html/pcre_exec.html +++ /dev/null @@ -1,58 +0,0 @@ -<html> -<head> -<title>pcre_exec specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> -<b>const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> -<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This function matches a compiled regular expression against a given subject -string, and returns offsets to capturing subexpressions. Its arguments are: -</P> -<P> -<pre> - <i>code</i> Points to the compiled pattern - <i>extra</i> Points to an associated <b>pcre_extra</b> structure, - or is NULL - <i>subject</i> Points to the subject string - <i>length</i> Length of the subject string, in bytes - <i>startoffset</i> Offset in bytes in the subject at which to - start matching - <i>options</i> Option bits - <i>ovector</i> Points to a vector of ints for result offsets - <i>ovecsize</i> Size of the vector (a multiple of 3) -</PRE> -</P> -<P> -The options are: -</P> -<P> -<pre> - PCRE_ANCHORED Match only at the first position - PCRE_NOTBOL Subject is not the beginning of a line - PCRE_NOTEOL Subject is not the end of a line - PCRE_NOTEMPTY An empty string is not a valid match - PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 - validity (only relevant if PCRE_UTF8 - was set at compile time) -</PRE> -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_free_substring.html b/external-libs/pcre/doc/html/pcre_free_substring.html deleted file mode 100644 index 08b16078..00000000 --- a/external-libs/pcre/doc/html/pcre_free_substring.html +++ /dev/null @@ -1,29 +0,0 @@ -<html> -<head> -<title>pcre_free_substring specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>void pcre_free_substring(const char *<i>stringptr</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This is a convenience function for freeing the store obtained by a previous -call to <b>pcre_get_substring()</b> or <b>pcre_get_named_substring()</b>. Its -only argument is a pointer to the string. -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_free_substring_list.html b/external-libs/pcre/doc/html/pcre_free_substring_list.html deleted file mode 100644 index c130f281..00000000 --- a/external-libs/pcre/doc/html/pcre_free_substring_list.html +++ /dev/null @@ -1,29 +0,0 @@ -<html> -<head> -<title>pcre_free_substring_list specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>void pcre_free_substring_list(const char **<i>stringptr</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This is a convenience function for freeing the store obtained by a previous -call to <b>pcre_get_substring_list()</b>. Its only argument is a pointer to the -list of string pointers. -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_fullinfo.html b/external-libs/pcre/doc/html/pcre_fullinfo.html deleted file mode 100644 index f43fa65f..00000000 --- a/external-libs/pcre/doc/html/pcre_fullinfo.html +++ /dev/null @@ -1,68 +0,0 @@ -<html> -<head> -<title>pcre_fullinfo specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> -<b>int <i>what</i>, void *<i>where</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This function returns information about a compiled pattern. Its arguments are: -</P> -<P> -<pre> - <i>code</i> Compiled regular expression - <i>extra</i> Result of <b>pcre_study()</b> or NULL - <i>what</i> What information is required - <i>where</i> Where to put the information -</PRE> -</P> -<P> -The following information is available: -</P> -<P> -<pre> - PCRE_INFO_BACKREFMAX Number of highest back reference - PCRE_INFO_CAPTURECOUNT Number of capturing subpatterns - PCRE_INFO_FIRSTBYTE Fixed first byte for a match, or - -1 for start of string - or after newline, or - -2 otherwise - PCRE_INFO_FIRSTTABLE Table of first bytes - (after studying) - PCRE_INFO_LASTLITERAL Literal last byte required - PCRE_INFO_NAMECOUNT Number of named subpatterns - PCRE_INFO_NAMEENTRYSIZE Size of name table entry - PCRE_INFO_NAMETABLE Pointer to name table - PCRE_INFO_OPTIONS Options used for compilation - PCRE_INFO_SIZE Size of compiled pattern -</PRE> -</P> -<P> -The yield of the function is zero on success or: -</P> -<P> -<pre> - PCRE_ERROR_NULL the argument <i>code</i> was NULL - the argument <i>where</i> was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found - PCRE_ERROR_BADOPTION the value of <i>what</i> was invalid -</PRE> -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_get_named_substring.html b/external-libs/pcre/doc/html/pcre_get_named_substring.html deleted file mode 100644 index 89a2beeb..00000000 --- a/external-libs/pcre/doc/html/pcre_get_named_substring.html +++ /dev/null @@ -1,46 +0,0 @@ -<html> -<head> -<title>pcre_get_named_substring specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>int pcre_get_named_substring(const pcre *<i>code</i>,</b> -<b>const char *<i>subject</i>, int *<i>ovector</i>,</b> -<b>int <i>stringcount</i>, const char *<i>stringname</i>,</b> -<b>const char **<i>stringptr</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This is a convenience function for extracting a captured substring by name. The -arguments are: -</P> -<P> -<pre> - <i>code</i> Compiled pattern - <i>subject</i> Subject that has been successfully matched - <i>ovector</i> Offset vector that <b>pcre_exec()</b> used - <i>stringcount</i> Value returned by <b>pcre_exec()</b> - <i>stringname</i> Name of the required substring - <i>stringptr</i> Where to put the string pointer -</PRE> -</P> -<P> -The yield is the length of the extracted substring, PCRE_ERROR_NOMEMORY if -sufficient memory could not be obtained, or PCRE_ERROR_NOSUBSTRING if the -string name is invalid. -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_get_stringnumber.html b/external-libs/pcre/doc/html/pcre_get_stringnumber.html deleted file mode 100644 index ee1c0a9c..00000000 --- a/external-libs/pcre/doc/html/pcre_get_stringnumber.html +++ /dev/null @@ -1,39 +0,0 @@ -<html> -<head> -<title>pcre_get_stringnumber specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b> -<b>const char *<i>name</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This convenience function finds the number of a named substring capturing -parenthesis in a compiled pattern. Its arguments are: -</P> -<P> -<pre> - <i>code</i> Compiled regular expression - <i>name</i> Name whose number is required -</PRE> -</P> -<P> -The yield of the function is the number of the parenthesis if the name is -found, or PCRE_ERROR_NOSUBSTRING otherwise. -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_get_substring.html b/external-libs/pcre/doc/html/pcre_get_substring.html deleted file mode 100644 index 2a55c10f..00000000 --- a/external-libs/pcre/doc/html/pcre_get_substring.html +++ /dev/null @@ -1,44 +0,0 @@ -<html> -<head> -<title>pcre_get_substring specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b> -<b>int <i>stringcount</i>, int <i>stringnumber</i>,</b> -<b>const char **<i>stringptr</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This is a convenience function for extracting a captured substring. The -arguments are: -</P> -<P> -<pre> - <i>subject</i> Subject that has been successfully matched - <i>ovector</i> Offset vector that <b>pcre_exec()</b> used - <i>stringcount</i> Value returned by <b>pcre_exec()</b> - <i>stringnumber</i> Number of the required substring - <i>stringptr</i> Where to put the string pointer -</PRE> -</P> -<P> -The yield is the length of the substring, PCRE_ERROR_NOMEMORY if sufficient -memory could not be obtained, or PCRE_ERROR_NOSUBSTRING if the string number is -invalid. -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_get_substring_list.html b/external-libs/pcre/doc/html/pcre_get_substring_list.html deleted file mode 100644 index 7e91f56b..00000000 --- a/external-libs/pcre/doc/html/pcre_get_substring_list.html +++ /dev/null @@ -1,41 +0,0 @@ -<html> -<head> -<title>pcre_get_substring_list specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>int pcre_get_substring_list(const char *<i>subject</i>,</b> -<b>int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This is a convenience function for extracting a list of all the captured -substrings. The arguments are: -</P> -<P> -<pre> - <i>subject</i> Subject that has been successfully matched - <i>ovector</i> Offset vector that <b>pcre_exec</b> used - <i>stringcount</i> Value returned by <b>pcre_exec</b> - <i>listptr</i> Where to put a pointer to the list -</PRE> -</P> -<P> -The yield is zero on success or PCRE_ERROR_NOMEMORY if sufficient memory could -not be obtained. -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_info.html b/external-libs/pcre/doc/html/pcre_info.html deleted file mode 100644 index 97fc59b4..00000000 --- a/external-libs/pcre/doc/html/pcre_info.html +++ /dev/null @@ -1,28 +0,0 @@ -<html> -<head> -<title>pcre_info specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>int pcre_info(const pcre *<i>code</i>, int *<i>optptr</i>, int</b> -<b>*<i>firstcharptr</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This function is obsolete. You should be using <b>pcre_fullinfo()</b> instead. -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_maketables.html b/external-libs/pcre/doc/html/pcre_maketables.html deleted file mode 100644 index ba3e026b..00000000 --- a/external-libs/pcre/doc/html/pcre_maketables.html +++ /dev/null @@ -1,31 +0,0 @@ -<html> -<head> -<title>pcre_maketables specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>const unsigned char *pcre_maketables(void);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This function builds a set of character tables which can be passed to -<b>pcre_compile()</b> to override PCRE's internal, built-in tables (which were -made by <b>pcre_maketables()</b> when PCRE was compiled). You might want to do -this if you are using a non-standard locale. The function yields a pointer to -the tables. -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_study.html b/external-libs/pcre/doc/html/pcre_study.html deleted file mode 100644 index f3727d1f..00000000 --- a/external-libs/pcre/doc/html/pcre_study.html +++ /dev/null @@ -1,45 +0,0 @@ -<html> -<head> -<title>pcre_study specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b> -<b>const char **<i>errptr</i>);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This function studies a compiled pattern, to see if additional information can -be extracted that might speed up matching. Its arguments are: -</P> -<P> -<pre> - <i>code</i> A compiled regular expression - <i>options</i> Options for <b>pcre_study()</b> - <i>errptr</i> Where to put an error message -</PRE> -</P> -<P> -If the function returns NULL, either it could not find any additional -information, or there was an error. You can tell the difference by looking at -the error value. It is NULL in first case. -</P> -<P> -There are currently no options defined; the value of the second argument should -always be zero. -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcre_version.html b/external-libs/pcre/doc/html/pcre_version.html deleted file mode 100644 index 35c47cd6..00000000 --- a/external-libs/pcre/doc/html/pcre_version.html +++ /dev/null @@ -1,28 +0,0 @@ -<html> -<head> -<title>pcre_version specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<br><b> -SYNOPSIS -</b><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>char *pcre_version(void);</b> -</P> -<br><b> -DESCRIPTION -</b><br> -<P> -This function returns a character string that gives the version number of the -PCRE library, and its date of release. -</P> -<P> -There is a complete description of the PCRE API in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page. diff --git a/external-libs/pcre/doc/html/pcreapi.html b/external-libs/pcre/doc/html/pcreapi.html deleted file mode 100644 index 8ae6fb1e..00000000 --- a/external-libs/pcre/doc/html/pcreapi.html +++ /dev/null @@ -1,1346 +0,0 @@ -<html> -<head> -<title>pcreapi specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<ul> -<li><a name="TOC1" href="#SEC1">SYNOPSIS OF PCRE API</a> -<li><a name="TOC2" href="#SEC2">PCRE API</a> -<li><a name="TOC3" href="#SEC3">MULTITHREADING</a> -<li><a name="TOC4" href="#SEC4">CHECKING BUILD-TIME OPTIONS</a> -<li><a name="TOC5" href="#SEC5">COMPILING A PATTERN</a> -<li><a name="TOC6" href="#SEC6">STUDYING A PATTERN</a> -<li><a name="TOC7" href="#SEC7">LOCALE SUPPORT</a> -<li><a name="TOC8" href="#SEC8">INFORMATION ABOUT A PATTERN</a> -<li><a name="TOC9" href="#SEC9">OBSOLETE INFO FUNCTION</a> -<li><a name="TOC10" href="#SEC10">MATCHING A PATTERN</a> -<li><a name="TOC11" href="#SEC11">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a> -<li><a name="TOC12" href="#SEC12">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a> -</ul> -<br><a name="SEC1" href="#TOC1">SYNOPSIS OF PCRE API</a><br> -<P> -<b>#include <pcre.h></b> -</P> -<P> -<b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b> -<b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b> -<b>const unsigned char *<i>tableptr</i>);</b> -</P> -<P> -<b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b> -<b>const char **<i>errptr</i>);</b> -</P> -<P> -<b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> -<b>const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> -<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b> -</P> -<P> -<b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b> -<b>const char *<i>subject</i>, int *<i>ovector</i>,</b> -<b>int <i>stringcount</i>, const char *<i>stringname</i>,</b> -<b>char *<i>buffer</i>, int <i>buffersize</i>);</b> -</P> -<P> -<b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b> -<b>int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b> -<b>int <i>buffersize</i>);</b> -</P> -<P> -<b>int pcre_get_named_substring(const pcre *<i>code</i>,</b> -<b>const char *<i>subject</i>, int *<i>ovector</i>,</b> -<b>int <i>stringcount</i>, const char *<i>stringname</i>,</b> -<b>const char **<i>stringptr</i>);</b> -</P> -<P> -<b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b> -<b>const char *<i>name</i>);</b> -</P> -<P> -<b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b> -<b>int <i>stringcount</i>, int <i>stringnumber</i>,</b> -<b>const char **<i>stringptr</i>);</b> -</P> -<P> -<b>int pcre_get_substring_list(const char *<i>subject</i>,</b> -<b>int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b> -</P> -<P> -<b>void pcre_free_substring(const char *<i>stringptr</i>);</b> -</P> -<P> -<b>void pcre_free_substring_list(const char **<i>stringptr</i>);</b> -</P> -<P> -<b>const unsigned char *pcre_maketables(void);</b> -</P> -<P> -<b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> -<b>int <i>what</i>, void *<i>where</i>);</b> -</P> -<P> -<b>int pcre_info(const pcre *<i>code</i>, int *<i>optptr</i>, int</b> -<b>*<i>firstcharptr</i>);</b> -</P> -<P> -<b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b> -</P> -<P> -<b>char *pcre_version(void);</b> -</P> -<P> -<b>void *(*pcre_malloc)(size_t);</b> -</P> -<P> -<b>void (*pcre_free)(void *);</b> -</P> -<P> -<b>void *(*pcre_stack_malloc)(size_t);</b> -</P> -<P> -<b>void (*pcre_stack_free)(void *);</b> -</P> -<P> -<b>int (*pcre_callout)(pcre_callout_block *);</b> -</P> -<br><a name="SEC2" href="#TOC1">PCRE API</a><br> -<P> -PCRE has its own native API, which is described in this document. There is also -a set of wrapper functions that correspond to the POSIX regular expression API. -These are described in the <b>pcreposix</b> documentation. -</P> -<P> -The native API function prototypes are defined in the header file <b>pcre.h</b>, -and on Unix systems the library itself is called <b>libpcre.a</b>, so can be -accessed by adding <b>-lpcre</b> to the command for linking an application which -calls it. The header file defines the macros PCRE_MAJOR and PCRE_MINOR to -contain the major and minor release numbers for the library. Applications can -use these to include support for different releases. -</P> -<P> -The functions <b>pcre_compile()</b>, <b>pcre_study()</b>, and <b>pcre_exec()</b> -are used for compiling and matching regular expressions. A sample program that -demonstrates the simplest way of using them is given in the file -<i>pcredemo.c</i>. The <b>pcresample</b> documentation describes how to run it. -</P> -<P> -There are convenience functions for extracting captured substrings from a -matched subject string. They are: -</P> -<P> -<pre> - <b>pcre_copy_substring()</b> - <b>pcre_copy_named_substring()</b> - <b>pcre_get_substring()</b> - <b>pcre_get_named_substring()</b> - <b>pcre_get_substring_list()</b> -</PRE> -</P> -<P> -<b>pcre_free_substring()</b> and <b>pcre_free_substring_list()</b> are also -provided, to free the memory used for extracted strings. -</P> -<P> -The function <b>pcre_maketables()</b> is used (optionally) to build a set of -character tables in the current locale for passing to <b>pcre_compile()</b>. -</P> -<P> -The function <b>pcre_fullinfo()</b> is used to find out information about a -compiled pattern; <b>pcre_info()</b> is an obsolete version which returns only -some of the available information, but is retained for backwards compatibility. -The function <b>pcre_version()</b> returns a pointer to a string containing the -version of PCRE and its date of release. -</P> -<P> -The global variables <b>pcre_malloc</b> and <b>pcre_free</b> initially contain -the entry points of the standard <b>malloc()</b> and <b>free()</b> functions -respectively. PCRE calls the memory management functions via these variables, -so a calling program can replace them if it wishes to intercept the calls. This -should be done before calling any PCRE functions. -</P> -<P> -The global variables <b>pcre_stack_malloc</b> and <b>pcre_stack_free</b> are also -indirections to memory management functions. These special functions are used -only when PCRE is compiled to use the heap for remembering data, instead of -recursive function calls. This is a non-standard way of building PCRE, for use -in environments that have limited stacks. Because of the greater use of memory -management, it runs more slowly. Separate functions are provided so that -special-purpose external code can be used for this case. When used, these -functions are always called in a stack-like manner (last obtained, first -freed), and always for memory blocks of the same size. -</P> -<P> -The global variable <b>pcre_callout</b> initially contains NULL. It can be set -by the caller to a "callout" function, which PCRE will then call at specified -points during a matching operation. Details are given in the <b>pcrecallout</b> -documentation. -</P> -<br><a name="SEC3" href="#TOC1">MULTITHREADING</a><br> -<P> -The PCRE functions can be used in multi-threading applications, with the -proviso that the memory management functions pointed to by <b>pcre_malloc</b>, -<b>pcre_free</b>, <b>pcre_stack_malloc</b>, and <b>pcre_stack_free</b>, and the -callout function pointed to by <b>pcre_callout</b>, are shared by all threads. -</P> -<P> -The compiled form of a regular expression is not altered during matching, so -the same compiled pattern can safely be used by several threads at once. -</P> -<br><a name="SEC4" href="#TOC1">CHECKING BUILD-TIME OPTIONS</a><br> -<P> -<b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b> -</P> -<P> -The function <b>pcre_config()</b> makes it possible for a PCRE client to -discover which optional features have been compiled into the PCRE library. The -<a href="pcrebuild.html"><b>pcrebuild</b></a> -documentation has more details about these optional features. -</P> -<P> -The first argument for <b>pcre_config()</b> is an integer, specifying which -information is required; the second argument is a pointer to a variable into -which the information is placed. The following information is available: -</P> -<P> -<pre> - PCRE_CONFIG_UTF8 -</PRE> -</P> -<P> -The output is an integer that is set to one if UTF-8 support is available; -otherwise it is set to zero. -</P> -<P> -<pre> - PCRE_CONFIG_NEWLINE -</PRE> -</P> -<P> -The output is an integer that is set to the value of the code that is used for -the newline character. It is either linefeed (10) or carriage return (13), and -should normally be the standard character for your operating system. -</P> -<P> -<pre> - PCRE_CONFIG_LINK_SIZE -</PRE> -</P> -<P> -The output is an integer that contains the number of bytes used for internal -linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values -allow larger regular expressions to be compiled, at the expense of slower -matching. The default value of 2 is sufficient for all but the most massive -patterns, since it allows the compiled pattern to be up to 64K in size. -</P> -<P> -<pre> - PCRE_CONFIG_POSIX_MALLOC_THRESHOLD -</PRE> -</P> -<P> -The output is an integer that contains the threshold above which the POSIX -interface uses <b>malloc()</b> for output vectors. Further details are given in -the <b>pcreposix</b> documentation. -</P> -<P> -<pre> - PCRE_CONFIG_MATCH_LIMIT -</PRE> -</P> -<P> -The output is an integer that gives the default limit for the number of -internal matching function calls in a <b>pcre_exec()</b> execution. Further -details are given with <b>pcre_exec()</b> below. -</P> -<P> -<pre> - PCRE_CONFIG_STACKRECURSE -</PRE> -</P> -<P> -The output is an integer that is set to one if internal recursion is -implemented by recursive function calls that use the stack to remember their -state. This is the usual way that PCRE is compiled. The output is zero if PCRE -was compiled to use blocks of data on the heap instead of recursive function -calls. In this case, <b>pcre_stack_malloc</b> and <b>pcre_stack_free</b> are -called to manage memory blocks on the heap, thus avoiding the use of the stack. -</P> -<br><a name="SEC5" href="#TOC1">COMPILING A PATTERN</a><br> -<P> -<b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b> -<b>const char **<i>errptr</i>, int *<i>erroffset</i>,</b> -<b>const unsigned char *<i>tableptr</i>);</b> -</P> -<P> -The function <b>pcre_compile()</b> is called to compile a pattern into an -internal form. The pattern is a C string terminated by a binary zero, and -is passed in the argument <i>pattern</i>. A pointer to a single block of memory -that is obtained via <b>pcre_malloc</b> is returned. This contains the compiled -code and related data. The <b>pcre</b> type is defined for the returned block; -this is a typedef for a structure whose contents are not externally defined. It -is up to the caller to free the memory when it is no longer required. -</P> -<P> -Although the compiled code of a PCRE regex is relocatable, that is, it does not -depend on memory location, the complete <b>pcre</b> data block is not -fully relocatable, because it contains a copy of the <i>tableptr</i> argument, -which is an address (see below). -</P> -<P> -The <i>options</i> argument contains independent bits that affect the -compilation. It should be zero if no options are required. Some of the options, -in particular, those that are compatible with Perl, can also be set and unset -from within the pattern (see the detailed description of regular expressions -in the <b>pcrepattern</b> documentation). For these options, the contents of the -<i>options</i> argument specifies their initial settings at the start of -compilation and execution. The PCRE_ANCHORED option can be set at the time of -matching as well as at compile time. -</P> -<P> -If <i>errptr</i> is NULL, <b>pcre_compile()</b> returns NULL immediately. -Otherwise, if compilation of a pattern fails, <b>pcre_compile()</b> returns -NULL, and sets the variable pointed to by <i>errptr</i> to point to a textual -error message. The offset from the start of the pattern to the character where -the error was discovered is placed in the variable pointed to by -<i>erroffset</i>, which must not be NULL. If it is, an immediate error is given. -</P> -<P> -If the final argument, <i>tableptr</i>, is NULL, PCRE uses a default set of -character tables which are built when it is compiled, using the default C -locale. Otherwise, <i>tableptr</i> must be the result of a call to -<b>pcre_maketables()</b>. See the section on locale support below. -</P> -<P> -This code fragment shows a typical straightforward call to <b>pcre_compile()</b>: -</P> -<P> -<pre> - pcre *re; - const char *error; - int erroffset; - re = pcre_compile( - "^A.*Z", /* the pattern */ - 0, /* default options */ - &error, /* for error message */ - &erroffset, /* for error offset */ - NULL); /* use default character tables */ -</PRE> -</P> -<P> -The following option bits are defined: -</P> -<P> -<pre> - PCRE_ANCHORED -</PRE> -</P> -<P> -If this bit is set, the pattern is forced to be "anchored", that is, it is -constrained to match only at the first matching point in the string which is -being searched (the "subject string"). This effect can also be achieved by -appropriate constructs in the pattern itself, which is the only way to do it in -Perl. -</P> -<P> -<pre> - PCRE_CASELESS -</PRE> -</P> -<P> -If this bit is set, letters in the pattern match both upper and lower case -letters. It is equivalent to Perl's /i option, and it can be changed within a -pattern by a (?i) option setting. -</P> -<P> -<pre> - PCRE_DOLLAR_ENDONLY -</PRE> -</P> -<P> -If this bit is set, a dollar metacharacter in the pattern matches only at the -end of the subject string. Without this option, a dollar also matches -immediately before the final character if it is a newline (but not before any -other newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is -set. There is no equivalent to this option in Perl, and no way to set it within -a pattern. -</P> -<P> -<pre> - PCRE_DOTALL -</PRE> -</P> -<P> -If this bit is set, a dot metacharater in the pattern matches all characters, -including newlines. Without it, newlines are excluded. This option is -equivalent to Perl's /s option, and it can be changed within a pattern by a -(?s) option setting. A negative class such as [^a] always matches a newline -character, independent of the setting of this option. -</P> -<P> -<pre> - PCRE_EXTENDED -</PRE> -</P> -<P> -If this bit is set, whitespace data characters in the pattern are totally -ignored except when escaped or inside a character class. Whitespace does not -include the VT character (code 11). In addition, characters between an -unescaped # outside a character class and the next newline character, -inclusive, are also ignored. This is equivalent to Perl's /x option, and it can -be changed within a pattern by a (?x) option setting. -</P> -<P> -This option makes it possible to include comments inside complicated patterns. -Note, however, that this applies only to data characters. Whitespace characters -may never appear within special character sequences in a pattern, for example -within the sequence (?( which introduces a conditional subpattern. -</P> -<P> -<pre> - PCRE_EXTRA -</PRE> -</P> -<P> -This option was invented in order to turn on additional functionality of PCRE -that is incompatible with Perl, but it is currently of very little use. When -set, any backslash in a pattern that is followed by a letter that has no -special meaning causes an error, thus reserving these combinations for future -expansion. By default, as in Perl, a backslash followed by a letter with no -special meaning is treated as a literal. There are at present no other features -controlled by this option. It can also be set by a (?X) option setting within a -pattern. -</P> -<P> -<pre> - PCRE_MULTILINE -</PRE> -</P> -<P> -By default, PCRE treats the subject string as consisting of a single "line" of -characters (even if it actually contains several newlines). The "start of line" -metacharacter (^) matches only at the start of the string, while the "end of -line" metacharacter ($) matches only at the end of the string, or before a -terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as -Perl. -</P> -<P> -When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs -match immediately following or immediately before any newline in the subject -string, respectively, as well as at the very start and end. This is equivalent -to Perl's /m option, and it can be changed within a pattern by a (?m) option -setting. If there are no "\n" characters in a subject string, or no -occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect. -</P> -<P> -<pre> - PCRE_NO_AUTO_CAPTURE -</PRE> -</P> -<P> -If this option is set, it disables the use of numbered capturing parentheses in -the pattern. Any opening parenthesis that is not followed by ? behaves as if it -were followed by ?: but named parentheses can still be used for capturing (and -they acquire numbers in the usual way). There is no equivalent of this option -in Perl. -</P> -<P> -<pre> - PCRE_UNGREEDY -</PRE> -</P> -<P> -This option inverts the "greediness" of the quantifiers so that they are not -greedy by default, but become greedy if followed by "?". It is not compatible -with Perl. It can also be set by a (?U) option setting within the pattern. -</P> -<P> -<pre> - PCRE_UTF8 -</PRE> -</P> -<P> -This option causes PCRE to regard both the pattern and the subject as strings -of UTF-8 characters instead of single-byte character strings. However, it is -available only if PCRE has been built to include UTF-8 support. If not, the use -of this option provokes an error. Details of how this option changes the -behaviour of PCRE are given in the -<a href="pcre.html#utf8support">section on UTF-8 support</a> -in the main -<a href="pcre.html"><b>pcre</b></a> -page. -</P> -<P> -<pre> - PCRE_NO_UTF8_CHECK -</PRE> -</P> -<P> -When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is -automatically checked. If an invalid UTF-8 sequence of bytes is found, -<b>pcre_compile()</b> returns an error. If you already know that your pattern is -valid, and you want to skip this check for performance reasons, you can set the -PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid -UTF-8 string as a pattern is undefined. It may cause your program to crash. -Note that there is a similar option for suppressing the checking of subject -strings passed to <b>pcre_exec()</b>. -</P> -<br><a name="SEC6" href="#TOC1">STUDYING A PATTERN</a><br> -<P> -<b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b> -<b>const char **<i>errptr</i>);</b> -</P> -<P> -When a pattern is going to be used several times, it is worth spending more -time analyzing it in order to speed up the time taken for matching. The -function <b>pcre_study()</b> takes a pointer to a compiled pattern as its first -argument. If studing the pattern produces additional information that will help -speed up matching, <b>pcre_study()</b> returns a pointer to a <b>pcre_extra</b> -block, in which the <i>study_data</i> field points to the results of the study. -</P> -<P> -The returned value from a <b>pcre_study()</b> can be passed directly to -<b>pcre_exec()</b>. However, the <b>pcre_extra</b> block also contains other -fields that can be set by the caller before the block is passed; these are -described below. If studying the pattern does not produce any additional -information, <b>pcre_study()</b> returns NULL. In that circumstance, if the -calling program wants to pass some of the other fields to <b>pcre_exec()</b>, it -must set up its own <b>pcre_extra</b> block. -</P> -<P> -The second argument contains option bits. At present, no options are defined -for <b>pcre_study()</b>, and this argument should always be zero. -</P> -<P> -The third argument for <b>pcre_study()</b> is a pointer for an error message. If -studying succeeds (even if no data is returned), the variable it points to is -set to NULL. Otherwise it points to a textual error message. You should -therefore test the error pointer for NULL after calling <b>pcre_study()</b>, to -be sure that it has run successfully. -</P> -<P> -This is a typical call to <b>pcre_study</b>(): -</P> -<P> -<pre> - pcre_extra *pe; - pe = pcre_study( - re, /* result of pcre_compile() */ - 0, /* no options exist */ - &error); /* set to NULL or points to a message */ -</PRE> -</P> -<P> -At present, studying a pattern is useful only for non-anchored patterns that do -not have a single fixed starting character. A bitmap of possible starting -characters is created. -</P> -<a name="localesupport"></a><br><a name="SEC7" href="#TOC1">LOCALE SUPPORT</a><br> -<P> -PCRE handles caseless matching, and determines whether characters are letters, -digits, or whatever, by reference to a set of tables. When running in UTF-8 -mode, this applies only to characters with codes less than 256. The library -contains a default set of tables that is created in the default C locale when -PCRE is compiled. This is used when the final argument of <b>pcre_compile()</b> -is NULL, and is sufficient for many applications. -</P> -<P> -An alternative set of tables can, however, be supplied. Such tables are built -by calling the <b>pcre_maketables()</b> function, which has no arguments, in the -relevant locale. The result can then be passed to <b>pcre_compile()</b> as often -as necessary. For example, to build and use tables that are appropriate for the -French locale (where accented characters with codes greater than 128 are -treated as letters), the following code could be used: -</P> -<P> -<pre> - setlocale(LC_CTYPE, "fr"); - tables = pcre_maketables(); - re = pcre_compile(..., tables); -</PRE> -</P> -<P> -The tables are built in memory that is obtained via <b>pcre_malloc</b>. The -pointer that is passed to <b>pcre_compile</b> is saved with the compiled -pattern, and the same tables are used via this pointer by <b>pcre_study()</b> -and <b>pcre_exec()</b>. Thus, for any single pattern, compilation, studying and -matching all happen in the same locale, but different patterns can be compiled -in different locales. It is the caller's responsibility to ensure that the -memory containing the tables remains available for as long as it is needed. -</P> -<br><a name="SEC8" href="#TOC1">INFORMATION ABOUT A PATTERN</a><br> -<P> -<b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> -<b>int <i>what</i>, void *<i>where</i>);</b> -</P> -<P> -The <b>pcre_fullinfo()</b> function returns information about a compiled -pattern. It replaces the obsolete <b>pcre_info()</b> function, which is -nevertheless retained for backwards compability (and is documented below). -</P> -<P> -The first argument for <b>pcre_fullinfo()</b> is a pointer to the compiled -pattern. The second argument is the result of <b>pcre_study()</b>, or NULL if -the pattern was not studied. The third argument specifies which piece of -information is required, and the fourth argument is a pointer to a variable -to receive the data. The yield of the function is zero for success, or one of -the following negative numbers: -</P> -<P> -<pre> - PCRE_ERROR_NULL the argument <i>code</i> was NULL - the argument <i>where</i> was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found - PCRE_ERROR_BADOPTION the value of <i>what</i> was invalid -</PRE> -</P> -<P> -Here is a typical call of <b>pcre_fullinfo()</b>, to obtain the length of the -compiled pattern: -</P> -<P> -<pre> - int rc; - unsigned long int length; - rc = pcre_fullinfo( - re, /* result of pcre_compile() */ - pe, /* result of pcre_study(), or NULL */ - PCRE_INFO_SIZE, /* what is required */ - &length); /* where to put the data */ -</PRE> -</P> -<P> -The possible values for the third argument are defined in <b>pcre.h</b>, and are -as follows: -</P> -<P> -<pre> - PCRE_INFO_BACKREFMAX -</PRE> -</P> -<P> -Return the number of the highest back reference in the pattern. The fourth -argument should point to an <b>int</b> variable. Zero is returned if there are -no back references. -</P> -<P> -<pre> - PCRE_INFO_CAPTURECOUNT -</PRE> -</P> -<P> -Return the number of capturing subpatterns in the pattern. The fourth argument -should point to an \fbint\fR variable. -</P> -<P> -<pre> - PCRE_INFO_FIRSTBYTE -</PRE> -</P> -<P> -Return information about the first byte of any matched string, for a -non-anchored pattern. (This option used to be called PCRE_INFO_FIRSTCHAR; the -old name is still recognized for backwards compatibility.) -</P> -<P> -If there is a fixed first byte, e.g. from a pattern such as (cat|cow|coyote), -it is returned in the integer pointed to by <i>where</i>. Otherwise, if either -</P> -<P> -(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch -starts with "^", or -</P> -<P> -(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set -(if it were set, the pattern would be anchored), -</P> -<P> --1 is returned, indicating that the pattern matches only at the start of a -subject string or after any newline within the string. Otherwise -2 is -returned. For anchored patterns, -2 is returned. -</P> -<P> -<pre> - PCRE_INFO_FIRSTTABLE -</PRE> -</P> -<P> -If the pattern was studied, and this resulted in the construction of a 256-bit -table indicating a fixed set of bytes for the first byte in any matching -string, a pointer to the table is returned. Otherwise NULL is returned. The -fourth argument should point to an <b>unsigned char *</b> variable. -</P> -<P> -<pre> - PCRE_INFO_LASTLITERAL -</PRE> -</P> -<P> -Return the value of the rightmost literal byte that must exist in any matched -string, other than at its start, if such a byte has been recorded. The fourth -argument should point to an <b>int</b> variable. If there is no such byte, -1 is -returned. For anchored patterns, a last literal byte is recorded only if it -follows something of variable length. For example, for the pattern -/^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value -is -1. -</P> -<P> -<pre> - PCRE_INFO_NAMECOUNT - PCRE_INFO_NAMEENTRYSIZE - PCRE_INFO_NAMETABLE -</PRE> -</P> -<P> -PCRE supports the use of named as well as numbered capturing parentheses. The -names are just an additional way of identifying the parentheses, which still -acquire a number. A caller that wants to extract data from a named subpattern -must convert the name to a number in order to access the correct pointers in -the output vector (described with <b>pcre_exec()</b> below). In order to do -this, it must first use these three values to obtain the name-to-number mapping -table for the pattern. -</P> -<P> -The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives -the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each -entry; both of these return an <b>int</b> value. The entry size depends on the -length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first -entry of the table (a pointer to <b>char</b>). The first two bytes of each entry -are the number of the capturing parenthesis, most significant byte first. The -rest of the entry is the corresponding name, zero terminated. The names are in -alphabetical order. For example, consider the following pattern (assume -PCRE_EXTENDED is set, so white space - including newlines - is ignored): -</P> -<P> -<pre> - (?P<date> (?P<year>(\d\d)?\d\d) - - (?P<month>\d\d) - (?P<day>\d\d) ) -</PRE> -</P> -<P> -There are four named subpatterns, so the table has four entries, and each entry -in the table is eight bytes long. The table is as follows, with non-printing -bytes shows in hex, and undefined bytes shown as ??: -</P> -<P> -<pre> - 00 01 d a t e 00 ?? - 00 05 d a y 00 ?? ?? - 00 04 m o n t h 00 - 00 02 y e a r 00 ?? -</PRE> -</P> -<P> -When writing code to extract data from named subpatterns, remember that the -length of each entry may be different for each compiled pattern. -</P> -<P> -<pre> - PCRE_INFO_OPTIONS -</PRE> -</P> -<P> -Return a copy of the options with which the pattern was compiled. The fourth -argument should point to an <b>unsigned long int</b> variable. These option bits -are those specified in the call to <b>pcre_compile()</b>, modified by any -top-level option settings within the pattern itself. -</P> -<P> -A pattern is automatically anchored by PCRE if all of its top-level -alternatives begin with one of the following: -</P> -<P> -<pre> - ^ unless PCRE_MULTILINE is set - \A always - \G always - .* if PCRE_DOTALL is set and there are no back - references to the subpattern in which .* appears -</PRE> -</P> -<P> -For such patterns, the PCRE_ANCHORED bit is set in the options returned by -<b>pcre_fullinfo()</b>. -</P> -<P> -<pre> - PCRE_INFO_SIZE -</PRE> -</P> -<P> -Return the size of the compiled pattern, that is, the value that was passed as -the argument to <b>pcre_malloc()</b> when PCRE was getting memory in which to -place the compiled data. The fourth argument should point to a <b>size_t</b> -variable. -</P> -<P> -<pre> - PCRE_INFO_STUDYSIZE -</PRE> -</P> -<P> -Returns the size of the data block pointed to by the <i>study_data</i> field in -a <b>pcre_extra</b> block. That is, it is the value that was passed to -<b>pcre_malloc()</b> when PCRE was getting memory into which to place the data -created by <b>pcre_study()</b>. The fourth argument should point to a -<b>size_t</b> variable. -</P> -<br><a name="SEC9" href="#TOC1">OBSOLETE INFO FUNCTION</a><br> -<P> -<b>int pcre_info(const pcre *<i>code</i>, int *<i>optptr</i>, int</b> -<b>*<i>firstcharptr</i>);</b> -</P> -<P> -The <b>pcre_info()</b> function is now obsolete because its interface is too -restrictive to return all the available data about a compiled pattern. New -programs should use <b>pcre_fullinfo()</b> instead. The yield of -<b>pcre_info()</b> is the number of capturing subpatterns, or one of the -following negative numbers: -</P> -<P> -<pre> - PCRE_ERROR_NULL the argument <i>code</i> was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found -</PRE> -</P> -<P> -If the <i>optptr</i> argument is not NULL, a copy of the options with which the -pattern was compiled is placed in the integer it points to (see -PCRE_INFO_OPTIONS above). -</P> -<P> -If the pattern is not anchored and the <i>firstcharptr</i> argument is not NULL, -it is used to pass back information about the first character of any matched -string (see PCRE_INFO_FIRSTBYTE above). -</P> -<br><a name="SEC10" href="#TOC1">MATCHING A PATTERN</a><br> -<P> -<b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b> -<b>const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b> -<b>int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b> -</P> -<P> -The function <b>pcre_exec()</b> is called to match a subject string against a -pre-compiled pattern, which is passed in the <i>code</i> argument. If the -pattern has been studied, the result of the study should be passed in the -<i>extra</i> argument. -</P> -<P> -Here is an example of a simple call to <b>pcre_exec()</b>: -</P> -<P> -<pre> - int rc; - int ovector[30]; - rc = pcre_exec( - re, /* result of pcre_compile() */ - NULL, /* we didn't study the pattern */ - "some string", /* the subject string */ - 11, /* the length of the subject string */ - 0, /* start at offset 0 in the subject */ - 0, /* default options */ - ovector, /* vector for substring information */ - 30); /* number of elements in the vector */ -</PRE> -</P> -<P> -If the <i>extra</i> argument is not NULL, it must point to a <b>pcre_extra</b> -data block. The <b>pcre_study()</b> function returns such a block (when it -doesn't return NULL), but you can also create one for yourself, and pass -additional information in it. The fields in the block are as follows: -</P> -<P> -<pre> - unsigned long int <i>flags</i>; - void *<i>study_data</i>; - unsigned long int <i>match_limit</i>; - void *<i>callout_data</i>; -</PRE> -</P> -<P> -The <i>flags</i> field is a bitmap that specifies which of the other fields -are set. The flag bits are: -</P> -<P> -<pre> - PCRE_EXTRA_STUDY_DATA - PCRE_EXTRA_MATCH_LIMIT - PCRE_EXTRA_CALLOUT_DATA -</PRE> -</P> -<P> -Other flag bits should be set to zero. The <i>study_data</i> field is set in the -<b>pcre_extra</b> block that is returned by <b>pcre_study()</b>, together with -the appropriate flag bit. You should not set this yourself, but you can add to -the block by setting the other fields. -</P> -<P> -The <i>match_limit</i> field provides a means of preventing PCRE from using up a -vast amount of resources when running patterns that are not going to match, -but which have a very large number of possibilities in their search trees. The -classic example is the use of nested unlimited repeats. Internally, PCRE uses a -function called <b>match()</b> which it calls repeatedly (sometimes -recursively). The limit is imposed on the number of times this function is -called during a match, which has the effect of limiting the amount of recursion -and backtracking that can take place. For patterns that are not anchored, the -count starts from zero for each position in the subject string. -</P> -<P> -The default limit for the library can be set when PCRE is built; the default -default is 10 million, which handles all but the most extreme cases. You can -reduce the default by suppling <b>pcre_exec()</b> with a \fRpcre_extra\fR block -in which <i>match_limit</i> is set to a smaller value, and -PCRE_EXTRA_MATCH_LIMIT is set in the <i>flags</i> field. If the limit is -exceeded, <b>pcre_exec()</b> returns PCRE_ERROR_MATCHLIMIT. -</P> -<P> -The <i>pcre_callout</i> field is used in conjunction with the "callout" feature, -which is described in the <b>pcrecallout</b> documentation. -</P> -<P> -The PCRE_ANCHORED option can be passed in the <i>options</i> argument, whose -unused bits must be zero. This limits <b>pcre_exec()</b> to matching at the -first matching position. However, if a pattern was compiled with PCRE_ANCHORED, -or turned out to be anchored by virtue of its contents, it cannot be made -unachored at matching time. -</P> -<P> -When PCRE_UTF8 was set at compile time, the validity of the subject as a UTF-8 -string is automatically checked, and the value of <i>startoffset</i> is also -checked to ensure that it points to the start of a UTF-8 character. If an -invalid UTF-8 sequence of bytes is found, <b>pcre_exec()</b> returns the error -PCRE_ERROR_BADUTF8. If <i>startoffset</i> contains an invalid value, -PCRE_ERROR_BADUTF8_OFFSET is returned. -</P> -<P> -If you already know that your subject is valid, and you want to skip these -checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when -calling <b>pcre_exec()</b>. You might want to do this for the second and -subsequent calls to <b>pcre_exec()</b> if you are making repeated calls to find -all the matches in a single subject string. However, you should be sure that -the value of <i>startoffset</i> points to the start of a UTF-8 character. When -PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a -subject, or a value of <i>startoffset</i> that does not point to the start of a -UTF-8 character, is undefined. Your program may crash. -</P> -<P> -There are also three further options that can be set only at matching time: -</P> -<P> -<pre> - PCRE_NOTBOL -</PRE> -</P> -<P> -The first character of the string is not the beginning of a line, so the -circumflex metacharacter should not match before it. Setting this without -PCRE_MULTILINE (at compile time) causes circumflex never to match. -</P> -<P> -<pre> - PCRE_NOTEOL -</PRE> -</P> -<P> -The end of the string is not the end of a line, so the dollar metacharacter -should not match it nor (except in multiline mode) a newline immediately before -it. Setting this without PCRE_MULTILINE (at compile time) causes dollar never -to match. -</P> -<P> -<pre> - PCRE_NOTEMPTY -</PRE> -</P> -<P> -An empty string is not considered to be a valid match if this option is set. If -there are alternatives in the pattern, they are tried. If all the alternatives -match the empty string, the entire match fails. For example, if the pattern -</P> -<P> -<pre> - a?b? -</PRE> -</P> -<P> -is applied to a string not beginning with "a" or "b", it matches the empty -string at the start of the subject. With PCRE_NOTEMPTY set, this match is not -valid, so PCRE searches further into the string for occurrences of "a" or "b". -</P> -<P> -Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case -of a pattern match of the empty string within its <b>split()</b> function, and -when using the /g modifier. It is possible to emulate Perl's behaviour after -matching a null string by first trying the match again at the same offset with -PCRE_NOTEMPTY set, and then if that fails by advancing the starting offset (see -below) and trying an ordinary match again. -</P> -<P> -The subject string is passed to <b>pcre_exec()</b> as a pointer in -<i>subject</i>, a length in <i>length</i>, and a starting byte offset in -<i>startoffset</i>. Unlike the pattern string, the subject may contain binary -zero bytes. When the starting offset is zero, the search for a match starts at -the beginning of the subject, and this is by far the most common case. -</P> -<P> -If the pattern was compiled with the PCRE_UTF8 option, the subject must be a -sequence of bytes that is a valid UTF-8 string, and the starting offset must -point to the beginning of a UTF-8 character. If an invalid UTF-8 string or -offset is passed, an error (either PCRE_ERROR_BADUTF8 or -PCRE_ERROR_BADUTF8_OFFSET) is returned, unless the option PCRE_NO_UTF8_CHECK is -set, in which case PCRE's behaviour is not defined. -</P> -<P> -A non-zero starting offset is useful when searching for another match in the -same subject by calling <b>pcre_exec()</b> again after a previous success. -Setting <i>startoffset</i> differs from just passing over a shortened string and -setting PCRE_NOTBOL in the case of a pattern that begins with any kind of -lookbehind. For example, consider the pattern -</P> -<P> -<pre> - \Biss\B -</PRE> -</P> -<P> -which finds occurrences of "iss" in the middle of words. (\B matches only if -the current position in the subject is not a word boundary.) When applied to -the string "Mississipi" the first call to <b>pcre_exec()</b> finds the first -occurrence. If <b>pcre_exec()</b> is called again with just the remainder of the -subject, namely "issipi", it does not match, because \B is always false at the -start of the subject, which is deemed to be a word boundary. However, if -<b>pcre_exec()</b> is passed the entire string again, but with <i>startoffset</i> -set to 4, it finds the second occurrence of "iss" because it is able to look -behind the starting point to discover that it is preceded by a letter. -</P> -<P> -If a non-zero starting offset is passed when the pattern is anchored, one -attempt to match at the given offset is tried. This can only succeed if the -pattern does not require the match to be at the start of the subject. -</P> -<P> -In general, a pattern matches a certain portion of the subject, and in -addition, further substrings from the subject may be picked out by parts of the -pattern. Following the usage in Jeffrey Friedl's book, this is called -"capturing" in what follows, and the phrase "capturing subpattern" is used for -a fragment of a pattern that picks out a substring. PCRE supports several other -kinds of parenthesized subpattern that do not cause substrings to be captured. -</P> -<P> -Captured substrings are returned to the caller via a vector of integer offsets -whose address is passed in <i>ovector</i>. The number of elements in the vector -is passed in <i>ovecsize</i>. The first two-thirds of the vector is used to pass -back captured substrings, each substring using a pair of integers. The -remaining third of the vector is used as workspace by <b>pcre_exec()</b> while -matching capturing subpatterns, and is not available for passing back -information. The length passed in <i>ovecsize</i> should always be a multiple of -three. If it is not, it is rounded down. -</P> -<P> -When a match has been successful, information about captured substrings is -returned in pairs of integers, starting at the beginning of <i>ovector</i>, and -continuing up to two-thirds of its length at the most. The first element of a -pair is set to the offset of the first character in a substring, and the second -is set to the offset of the first character after the end of a substring. The -first pair, <i>ovector[0]</i> and <i>ovector[1]</i>, identify the portion of the -subject string matched by the entire pattern. The next pair is used for the -first capturing subpattern, and so on. The value returned by <b>pcre_exec()</b> -is the number of pairs that have been set. If there are no capturing -subpatterns, the return value from a successful match is 1, indicating that -just the first pair of offsets has been set. -</P> -<P> -Some convenience functions are provided for extracting the captured substrings -as separate strings. These are described in the following section. -</P> -<P> -It is possible for an capturing subpattern number <i>n+1</i> to match some -part of the subject when subpattern <i>n</i> has not been used at all. For -example, if the string "abc" is matched against the pattern (a|(z))(bc) -subpatterns 1 and 3 are matched, but 2 is not. When this happens, both offset -values corresponding to the unused subpattern are set to -1. -</P> -<P> -If a capturing subpattern is matched repeatedly, it is the last portion of the -string that it matched that gets returned. -</P> -<P> -If the vector is too small to hold all the captured substrings, it is used as -far as possible (up to two-thirds of its length), and the function returns a -value of zero. In particular, if the substring offsets are not of interest, -<b>pcre_exec()</b> may be called with <i>ovector</i> passed as NULL and -<i>ovecsize</i> as zero. However, if the pattern contains back references and -the <i>ovector</i> isn't big enough to remember the related substrings, PCRE has -to get additional memory for use during matching. Thus it is usually advisable -to supply an <i>ovector</i>. -</P> -<P> -Note that <b>pcre_info()</b> can be used to find out how many capturing -subpatterns there are in a compiled pattern. The smallest size for -<i>ovector</i> that will allow for <i>n</i> captured substrings, in addition to -the offsets of the substring matched by the whole pattern, is (<i>n</i>+1)*3. -</P> -<P> -If <b>pcre_exec()</b> fails, it returns a negative number. The following are -defined in the header file: -</P> -<P> -<pre> - PCRE_ERROR_NOMATCH (-1) -</PRE> -</P> -<P> -The subject string did not match the pattern. -</P> -<P> -<pre> - PCRE_ERROR_NULL (-2) -</PRE> -</P> -<P> -Either <i>code</i> or <i>subject</i> was passed as NULL, or <i>ovector</i> was -NULL and <i>ovecsize</i> was not zero. -</P> -<P> -<pre> - PCRE_ERROR_BADOPTION (-3) -</PRE> -</P> -<P> -An unrecognized bit was set in the <i>options</i> argument. -</P> -<P> -<pre> - PCRE_ERROR_BADMAGIC (-4) -</PRE> -</P> -<P> -PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch -the case when it is passed a junk pointer. This is the error it gives when the -magic number isn't present. -</P> -<P> -<pre> - PCRE_ERROR_UNKNOWN_NODE (-5) -</PRE> -</P> -<P> -While running the pattern match, an unknown item was encountered in the -compiled pattern. This error could be caused by a bug in PCRE or by overwriting -of the compiled pattern. -</P> -<P> -<pre> - PCRE_ERROR_NOMEMORY (-6) -</PRE> -</P> -<P> -If a pattern contains back references, but the <i>ovector</i> that is passed to -<b>pcre_exec()</b> is not big enough to remember the referenced substrings, PCRE -gets a block of memory at the start of matching to use for this purpose. If the -call via <b>pcre_malloc()</b> fails, this error is given. The memory is freed at -the end of matching. -</P> -<P> -<pre> - PCRE_ERROR_NOSUBSTRING (-7) -</PRE> -</P> -<P> -This error is used by the <b>pcre_copy_substring()</b>, -<b>pcre_get_substring()</b>, and <b>pcre_get_substring_list()</b> functions (see -below). It is never returned by <b>pcre_exec()</b>. -</P> -<P> -<pre> - PCRE_ERROR_MATCHLIMIT (-8) -</PRE> -</P> -<P> -The recursion and backtracking limit, as specified by the <i>match_limit</i> -field in a <b>pcre_extra</b> structure (or defaulted) was reached. See the -description above. -</P> -<P> -<pre> - PCRE_ERROR_CALLOUT (-9) -</PRE> -</P> -<P> -This error is never generated by <b>pcre_exec()</b> itself. It is provided for -use by callout functions that want to yield a distinctive error code. See the -<b>pcrecallout</b> documentation for details. -</P> -<P> -<pre> - PCRE_ERROR_BADUTF8 (-10) -</PRE> -</P> -<P> -A string that contains an invalid UTF-8 byte sequence was passed as a subject. -</P> -<P> -<pre> - PCRE_ERROR_BADUTF8_OFFSET (-11) -</PRE> -</P> -<P> -The UTF-8 byte sequence that was passed as a subject was valid, but the value -of <i>startoffset</i> did not point to the beginning of a UTF-8 character. -</P> -<br><a name="SEC11" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a><br> -<P> -<b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b> -<b>int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b> -<b>int <i>buffersize</i>);</b> -</P> -<P> -<b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b> -<b>int <i>stringcount</i>, int <i>stringnumber</i>,</b> -<b>const char **<i>stringptr</i>);</b> -</P> -<P> -<b>int pcre_get_substring_list(const char *<i>subject</i>,</b> -<b>int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b> -</P> -<P> -Captured substrings can be accessed directly by using the offsets returned by -<b>pcre_exec()</b> in <i>ovector</i>. For convenience, the functions -<b>pcre_copy_substring()</b>, <b>pcre_get_substring()</b>, and -<b>pcre_get_substring_list()</b> are provided for extracting captured substrings -as new, separate, zero-terminated strings. These functions identify substrings -by number. The next section describes functions for extracting named -substrings. A substring that contains a binary zero is correctly extracted and -has a further zero added on the end, but the result is not, of course, -a C string. -</P> -<P> -The first three arguments are the same for all three of these functions: -<i>subject</i> is the subject string which has just been successfully matched, -<i>ovector</i> is a pointer to the vector of integer offsets that was passed to -<b>pcre_exec()</b>, and <i>stringcount</i> is the number of substrings that were -captured by the match, including the substring that matched the entire regular -expression. This is the value returned by <b>pcre_exec</b> if it is greater than -zero. If <b>pcre_exec()</b> returned zero, indicating that it ran out of space -in <i>ovector</i>, the value passed as <i>stringcount</i> should be the size of -the vector divided by three. -</P> -<P> -The functions <b>pcre_copy_substring()</b> and <b>pcre_get_substring()</b> -extract a single substring, whose number is given as <i>stringnumber</i>. A -value of zero extracts the substring that matched the entire pattern, while -higher values extract the captured substrings. For <b>pcre_copy_substring()</b>, -the string is placed in <i>buffer</i>, whose length is given by -<i>buffersize</i>, while for <b>pcre_get_substring()</b> a new block of memory is -obtained via <b>pcre_malloc</b>, and its address is returned via -<i>stringptr</i>. The yield of the function is the length of the string, not -including the terminating zero, or one of -</P> -<P> -<pre> - PCRE_ERROR_NOMEMORY (-6) -</PRE> -</P> -<P> -The buffer was too small for <b>pcre_copy_substring()</b>, or the attempt to get -memory failed for <b>pcre_get_substring()</b>. -</P> -<P> -<pre> - PCRE_ERROR_NOSUBSTRING (-7) -</PRE> -</P> -<P> -There is no substring whose number is <i>stringnumber</i>. -</P> -<P> -The <b>pcre_get_substring_list()</b> function extracts all available substrings -and builds a list of pointers to them. All this is done in a single block of -memory which is obtained via <b>pcre_malloc</b>. The address of the memory block -is returned via <i>listptr</i>, which is also the start of the list of string -pointers. The end of the list is marked by a NULL pointer. The yield of the -function is zero if all went well, or -</P> -<P> -<pre> - PCRE_ERROR_NOMEMORY (-6) -</PRE> -</P> -<P> -if the attempt to get the memory block failed. -</P> -<P> -When any of these functions encounter a substring that is unset, which can -happen when capturing subpattern number <i>n+1</i> matches some part of the -subject, but subpattern <i>n</i> has not been used at all, they return an empty -string. This can be distinguished from a genuine zero-length substring by -inspecting the appropriate offset in <i>ovector</i>, which is negative for unset -substrings. -</P> -<P> -The two convenience functions <b>pcre_free_substring()</b> and -<b>pcre_free_substring_list()</b> can be used to free the memory returned by -a previous call of <b>pcre_get_substring()</b> or -<b>pcre_get_substring_list()</b>, respectively. They do nothing more than call -the function pointed to by <b>pcre_free</b>, which of course could be called -directly from a C program. However, PCRE is used in some situations where it is -linked via a special interface to another programming language which cannot use -<b>pcre_free</b> directly; it is for these cases that the functions are -provided. -</P> -<br><a name="SEC12" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a><br> -<P> -<b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b> -<b>const char *<i>subject</i>, int *<i>ovector</i>,</b> -<b>int <i>stringcount</i>, const char *<i>stringname</i>,</b> -<b>char *<i>buffer</i>, int <i>buffersize</i>);</b> -</P> -<P> -<b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b> -<b>const char *<i>name</i>);</b> -</P> -<P> -<b>int pcre_get_named_substring(const pcre *<i>code</i>,</b> -<b>const char *<i>subject</i>, int *<i>ovector</i>,</b> -<b>int <i>stringcount</i>, const char *<i>stringname</i>,</b> -<b>const char **<i>stringptr</i>);</b> -</P> -<P> -To extract a substring by name, you first have to find associated number. This -can be done by calling <b>pcre_get_stringnumber()</b>. The first argument is the -compiled pattern, and the second is the name. For example, for this pattern -</P> -<P> -<pre> - ab(?<xxx>\d+)... -</PRE> -</P> -<P> -the number of the subpattern called "xxx" is 1. Given the number, you can then -extract the substring directly, or use one of the functions described in the -previous section. For convenience, there are also two functions that do the -whole job. -</P> -<P> -Most of the arguments of <i>pcre_copy_named_substring()</i> and -<i>pcre_get_named_substring()</i> are the same as those for the functions that -extract by number, and so are not re-described here. There are just two -differences. -</P> -<P> -First, instead of a substring number, a substring name is given. Second, there -is an extra argument, given at the start, which is a pointer to the compiled -pattern. This is needed in order to gain access to the name-to-number -translation table. -</P> -<P> -These functions call <b>pcre_get_stringnumber()</b>, and if it succeeds, they -then call <i>pcre_copy_substring()</i> or <i>pcre_get_substring()</i>, as -appropriate. -</P> -<P> -Last updated: 09 December 2003 -<br> -Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcrebuild.html b/external-libs/pcre/doc/html/pcrebuild.html deleted file mode 100644 index c70f8221..00000000 --- a/external-libs/pcre/doc/html/pcrebuild.html +++ /dev/null @@ -1,189 +0,0 @@ -<html> -<head> -<title>pcrebuild specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<ul> -<li><a name="TOC1" href="#SEC1">PCRE BUILD-TIME OPTIONS</a> -<li><a name="TOC2" href="#SEC2">UTF-8 SUPPORT</a> -<li><a name="TOC3" href="#SEC3">CODE VALUE OF NEWLINE</a> -<li><a name="TOC4" href="#SEC4">BUILDING SHARED AND STATIC LIBRARIES</a> -<li><a name="TOC5" href="#SEC5">POSIX MALLOC USAGE</a> -<li><a name="TOC6" href="#SEC6">LIMITING PCRE RESOURCE USAGE</a> -<li><a name="TOC7" href="#SEC7">HANDLING VERY LARGE PATTERNS</a> -<li><a name="TOC8" href="#SEC8">AVOIDING EXCESSIVE STACK USAGE</a> -<li><a name="TOC9" href="#SEC9">USING EBCDIC CODE</a> -</ul> -<br><a name="SEC1" href="#TOC1">PCRE BUILD-TIME OPTIONS</a><br> -<P> -This document describes the optional features of PCRE that can be selected when -the library is compiled. They are all selected, or deselected, by providing -options to the <b>configure</b> script which is run before the <b>make</b> -command. The complete list of options for <b>configure</b> (which includes the -standard ones such as the selection of the installation directory) can be -obtained by running -</P> -<P> -<pre> - ./configure --help -</PRE> -</P> -<P> -The following sections describe certain options whose names begin with --enable -or --disable. These settings specify changes to the defaults for the -<b>configure</b> command. Because of the way that <b>configure</b> works, ---enable and --disable always come in pairs, so the complementary option always -exists as well, but as it specifies the default, it is not described. -</P> -<br><a name="SEC2" href="#TOC1">UTF-8 SUPPORT</a><br> -<P> -To build PCRE with support for UTF-8 character strings, add -</P> -<P> -<pre> - --enable-utf8 -</PRE> -</P> -<P> -to the <b>configure</b> command. Of itself, this does not make PCRE treat -strings as UTF-8. As well as compiling PCRE with this option, you also have -have to set the PCRE_UTF8 option when you call the <b>pcre_compile()</b> -function. -</P> -<br><a name="SEC3" href="#TOC1">CODE VALUE OF NEWLINE</a><br> -<P> -By default, PCRE treats character 10 (linefeed) as the newline character. This -is the normal newline character on Unix-like systems. You can compile PCRE to -use character 13 (carriage return) instead by adding -</P> -<P> -<pre> - --enable-newline-is-cr -</PRE> -</P> -<P> -to the <b>configure</b> command. For completeness there is also a ---enable-newline-is-lf option, which explicitly specifies linefeed as the -newline character. -</P> -<br><a name="SEC4" href="#TOC1">BUILDING SHARED AND STATIC LIBRARIES</a><br> -<P> -The PCRE building process uses <b>libtool</b> to build both shared and static -Unix libraries by default. You can suppress one of these by adding one of -</P> -<P> -<pre> - --disable-shared - --disable-static -</PRE> -</P> -<P> -to the <b>configure</b> command, as required. -</P> -<br><a name="SEC5" href="#TOC1">POSIX MALLOC USAGE</a><br> -<P> -When PCRE is called through the POSIX interface (see the <b>pcreposix</b> -documentation), additional working storage is required for holding the pointers -to capturing substrings because PCRE requires three integers per substring, -whereas the POSIX interface provides only two. If the number of expected -substrings is small, the wrapper function uses space on the stack, because this -is faster than using <b>malloc()</b> for each call. The default threshold above -which the stack is no longer used is 10; it can be changed by adding a setting -such as -</P> -<P> -<pre> - --with-posix-malloc-threshold=20 -</PRE> -</P> -<P> -to the <b>configure</b> command. -</P> -<br><a name="SEC6" href="#TOC1">LIMITING PCRE RESOURCE USAGE</a><br> -<P> -Internally, PCRE has a function called <b>match()</b> which it calls repeatedly -(possibly recursively) when performing a matching operation. By limiting the -number of times this function may be called, a limit can be placed on the -resources used by a single call to <b>pcre_exec()</b>. The limit can be changed -at run time, as described in the <b>pcreapi</b> documentation. The default is 10 -million, but this can be changed by adding a setting such as -</P> -<P> -<pre> - --with-match-limit=500000 -</PRE> -</P> -<P> -to the <b>configure</b> command. -</P> -<br><a name="SEC7" href="#TOC1">HANDLING VERY LARGE PATTERNS</a><br> -<P> -Within a compiled pattern, offset values are used to point from one part to -another (for example, from an opening parenthesis to an alternation -metacharacter). By default two-byte values are used for these offsets, leading -to a maximum size for a compiled pattern of around 64K. This is sufficient to -handle all but the most gigantic patterns. Nevertheless, some people do want to -process enormous patterns, so it is possible to compile PCRE to use three-byte -or four-byte offsets by adding a setting such as -</P> -<P> -<pre> - --with-link-size=3 -</PRE> -</P> -<P> -to the <b>configure</b> command. The value given must be 2, 3, or 4. Using -longer offsets slows down the operation of PCRE because it has to load -additional bytes when handling them. -</P> -<P> -If you build PCRE with an increased link size, test 2 (and test 5 if you are -using UTF-8) will fail. Part of the output of these tests is a representation -of the compiled pattern, and this changes with the link size. -</P> -<br><a name="SEC8" href="#TOC1">AVOIDING EXCESSIVE STACK USAGE</a><br> -<P> -PCRE implements backtracking while matching by making recursive calls to an -internal function called <b>match()</b>. In environments where the size of the -stack is limited, this can severely limit PCRE's operation. (The Unix -environment does not usually suffer from this problem.) An alternative approach -that uses memory from the heap to remember data, instead of using recursive -function calls, has been implemented to work round this problem. If you want to -build a version of PCRE that works this way, add -</P> -<P> -<pre> - --disable-stack-for-recursion -</PRE> -</P> -<P> -to the <b>configure</b> command. With this configuration, PCRE will use the -<b>pcre_stack_malloc</b> and <b>pcre_stack_free</b> variables to call memory -management functions. Separate functions are provided because the usage is very -predictable: the block sizes requested are always the same, and the blocks are -always freed in reverse order. A calling program might be able to implement -optimized functions that perform better than the standard <b>malloc()</b> and -<b>free()</b> functions. PCRE runs noticeably more slowly when built in this -way. -</P> -<br><a name="SEC9" href="#TOC1">USING EBCDIC CODE</a><br> -<P> -PCRE assumes by default that it will run in an environment where the character -code is ASCII (or UTF-8, which is a superset of ASCII). PCRE can, however, be -compiled to run in an EBCDIC environment by adding -</P> -<P> -<pre> - --enable-ebcdic -</PRE> -</P> -<P> -to the <b>configure</b> command. -</P> -<P> -Last updated: 09 December 2003 -<br> -Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcrecallout.html b/external-libs/pcre/doc/html/pcrecallout.html deleted file mode 100644 index f4b7104e..00000000 --- a/external-libs/pcre/doc/html/pcrecallout.html +++ /dev/null @@ -1,117 +0,0 @@ -<html> -<head> -<title>pcrecallout specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<ul> -<li><a name="TOC1" href="#SEC1">PCRE CALLOUTS</a> -<li><a name="TOC2" href="#SEC2">RETURN VALUES</a> -</ul> -<br><a name="SEC1" href="#TOC1">PCRE CALLOUTS</a><br> -<P> -<b>int (*pcre_callout)(pcre_callout_block *);</b> -</P> -<P> -PCRE provides a feature called "callout", which is a means of temporarily -passing control to the caller of PCRE in the middle of pattern matching. The -caller of PCRE provides an external function by putting its entry point in the -global variable <i>pcre_callout</i>. By default, this variable contains NULL, -which disables all calling out. -</P> -<P> -Within a regular expression, (?C) indicates the points at which the external -function is to be called. Different callout points can be identified by putting -a number less than 256 after the letter C. The default value is zero. -For example, this pattern has two callout points: -</P> -<P> -<pre> - (?C1)\dabc(?C2)def -</PRE> -</P> -<P> -During matching, when PCRE reaches a callout point (and <i>pcre_callout</i> is -set), the external function is called. Its only argument is a pointer to a -<b>pcre_callout</b> block. This contains the following variables: -</P> -<P> -<pre> - int <i>version</i>; - int <i>callout_number</i>; - int *<i>offset_vector</i>; - const char *<i>subject</i>; - int <i>subject_length</i>; - int <i>start_match</i>; - int <i>current_position</i>; - int <i>capture_top</i>; - int <i>capture_last</i>; - void *<i>callout_data</i>; -</PRE> -</P> -<P> -The <i>version</i> field is an integer containing the version number of the -block format. The current version is zero. The version number may change in -future if additional fields are added, but the intention is never to remove any -of the existing fields. -</P> -<P> -The <i>callout_number</i> field contains the number of the callout, as compiled -into the pattern (that is, the number after ?C). -</P> -<P> -The <i>offset_vector</i> field is a pointer to the vector of offsets that was -passed by the caller to <b>pcre_exec()</b>. The contents can be inspected in -order to extract substrings that have been matched so far, in the same way as -for extracting substrings after a match has completed. -</P> -<P> -The <i>subject</i> and <i>subject_length</i> fields contain copies the values -that were passed to <b>pcre_exec()</b>. -</P> -<P> -The <i>start_match</i> field contains the offset within the subject at which the -current match attempt started. If the pattern is not anchored, the callout -function may be called several times for different starting points. -</P> -<P> -The <i>current_position</i> field contains the offset within the subject of the -current match pointer. -</P> -<P> -The <i>capture_top</i> field contains one more than the number of the highest -numbered captured substring so far. If no substrings have been captured, -the value of <i>capture_top</i> is one. -</P> -<P> -The <i>capture_last</i> field contains the number of the most recently captured -substring. -</P> -<P> -The <i>callout_data</i> field contains a value that is passed to -<b>pcre_exec()</b> by the caller specifically so that it can be passed back in -callouts. It is passed in the <i>pcre_callout</i> field of the <b>pcre_extra</b> -data structure. If no such data was passed, the value of <i>callout_data</i> in -a <b>pcre_callout</b> block is NULL. There is a description of the -<b>pcre_extra</b> structure in the <b>pcreapi</b> documentation. -</P> -<br><a name="SEC2" href="#TOC1">RETURN VALUES</a><br> -<P> -The callout function returns an integer. If the value is zero, matching -proceeds as normal. If the value is greater than zero, matching fails at the -current point, but backtracking to test other possibilities goes ahead, just as -if a lookahead assertion had failed. If the value is less than zero, the match -is abandoned, and <b>pcre_exec()</b> returns the value. -</P> -<P> -Negative values should normally be chosen from the set of PCRE_ERROR_xxx -values. In particular, PCRE_ERROR_NOMATCH forces a standard "no match" failure. -The error number PCRE_ERROR_CALLOUT is reserved for use by callout functions; -it will never be used by PCRE itself. -</P> -<P> -Last updated: 21 January 2003 -<br> -Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcrecompat.html b/external-libs/pcre/doc/html/pcrecompat.html deleted file mode 100644 index 1ec22038..00000000 --- a/external-libs/pcre/doc/html/pcrecompat.html +++ /dev/null @@ -1,136 +0,0 @@ -<html> -<head> -<title>pcrecompat specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<ul> -<li><a name="TOC1" href="#SEC1">DIFFERENCES FROM PERL</a> -</ul> -<br><a name="SEC1" href="#TOC1">DIFFERENCES FROM PERL</a><br> -<P> -This document describes the differences in the ways that PCRE and Perl handle -regular expressions. The differences described here are with respect to Perl -5.8. -</P> -<P> -1. PCRE does not have full UTF-8 support. Details of what it does have are -given in the -<a href="pcre.html#utf8support">section on UTF-8 support</a> -in the main -<a href="pcre.html"><b>pcre</b></a> -page. -</P> -<P> -2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl permits -them, but they do not mean what you might think. For example, (?!a){3} does -not assert that the next three characters are not "a". It just asserts that the -next character is not "a" three times. -</P> -<P> -3. Capturing subpatterns that occur inside negative lookahead assertions are -counted, but their entries in the offsets vector are never set. Perl sets its -numerical variables from any such patterns that are matched before the -assertion fails to match something (thereby succeeding), but only if the -negative lookahead assertion contains just one branch. -</P> -<P> -4. Though binary zero characters are supported in the subject string, they are -not allowed in a pattern string because it is passed as a normal C string, -terminated by zero. The escape sequence "\0" can be used in the pattern to -represent a binary zero. -</P> -<P> -5. The following Perl escape sequences are not supported: \l, \u, \L, -\U, \P, \p, \N, and \X. In fact these are implemented by Perl's general -string-handling and are not part of its pattern matching engine. If any of -these are encountered by PCRE, an error is generated. -</P> -<P> -6. PCRE does support the \Q...\E escape for quoting substrings. Characters in -between are treated as literals. This is slightly different from Perl in that $ -and @ are also handled as literals inside the quotes. In Perl, they cause -variable interpolation (but of course PCRE does not have variables). Note the -following examples: -</P> -<P> -<pre> - Pattern PCRE matches Perl matches -</PRE> -</P> -<P> -<pre> - \Qabc$xyz\E abc$xyz abc followed by the - contents of $xyz - \Qabc\$xyz\E abc\$xyz abc\$xyz - \Qabc\E\$\Qxyz\E abc$xyz abc$xyz -</PRE> -</P> -<P> -The \Q...\E sequence is recognized both inside and outside character classes. -</P> -<P> -7. Fairly obviously, PCRE does not support the (?{code}) and (?p{code}) -constructions. However, there is some experimental support for recursive -patterns using the non-Perl items (?R), (?number) and (?P>name). Also, the PCRE -"callout" feature allows an external function to be called during pattern -matching. -</P> -<P> -8. There are some differences that are concerned with the settings of captured -strings when part of a pattern is repeated. For example, matching "aba" against -the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". -</P> -<P> -9. PCRE provides some extensions to the Perl regular expression facilities: -</P> -<P> -(a) Although lookbehind assertions must match fixed length strings, each -alternative branch of a lookbehind assertion can match a different length of -string. Perl requires them all to have the same length. -</P> -<P> -(b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ -meta-character matches only at the very end of the string. -</P> -<P> -© If PCRE_EXTRA is set, a backslash followed by a letter with no special -meaning is faulted. -</P> -<P> -(d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is -inverted, that is, by default they are not greedy, but if followed by a -question mark they are. -</P> -<P> -(e) PCRE_ANCHORED can be used to force a pattern to be tried only at the first -matching position in the subject string. -</P> -<P> -(f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAPTURE -options for <b>pcre_exec()</b> have no Perl equivalents. -</P> -<P> -(g) The (?R), (?number), and (?P>name) constructs allows for recursive pattern -matching (Perl can do this using the (?p{code}) construct, which PCRE cannot -support.) -</P> -<P> -(h) PCRE supports named capturing substrings, using the Python syntax. -</P> -<P> -(i) PCRE supports the possessive quantifier "++" syntax, taken from Sun's Java -package. -</P> -<P> -(j) The (R) condition, for testing recursion, is a PCRE extension. -</P> -<P> -(k) The callout facility is PCRE-specific. -</P> -<P> -Last updated: 09 December 2003 -<br> -Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcregrep.html b/external-libs/pcre/doc/html/pcregrep.html deleted file mode 100644 index a76cac21..00000000 --- a/external-libs/pcre/doc/html/pcregrep.html +++ /dev/null @@ -1,153 +0,0 @@ -<html> -<head> -<title>pcregrep specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<ul> -<li><a name="TOC1" href="#SEC1">SYNOPSIS</a> -<li><a name="TOC2" href="#SEC2">DESCRIPTION</a> -<li><a name="TOC3" href="#SEC3">OPTIONS</a> -<li><a name="TOC4" href="#SEC4">LONG OPTIONS</a> -<li><a name="TOC5" href="#SEC5">DIAGNOSTICS</a> -<li><a name="TOC6" href="#SEC6">AUTHOR</a> -</ul> -<br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br> -<P> -<b>pcregrep [-Vcfhilnrsuvx] [long options] [pattern] [file1 file2 ...]</b> -</P> -<br><a name="SEC2" href="#TOC1">DESCRIPTION</a><br> -<P> -<b>pcregrep</b> searches files for character patterns, in the same way as other -grep commands do, but it uses the PCRE regular expression library to support -patterns that are compatible with the regular expressions of Perl 5. See -<a href="pcrepattern.html"><b>pcrepattern</b></a> -for a full description of syntax and semantics of the regular expressions that -PCRE supports. -</P> -<P> -A pattern must be specified on the command line unless the <b>-f</b> option is -used (see below). -</P> -<P> -If no files are specified, <b>pcregrep</b> reads the standard input. By default, -each line that matches the pattern is copied to the standard output, and if -there is more than one file, the file name is printed before each line of -output. However, there are options that can change how <b>pcregrep</b> behaves. -</P> -<P> -Lines are limited to BUFSIZ characters. BUFSIZ is defined in <b><stdio.h></b>. -The newline character is removed from the end of each line before it is matched -against the pattern. -</P> -<br><a name="SEC3" href="#TOC1">OPTIONS</a><br> -<P> -<b>-V</b> -Write the version number of the PCRE library being used to the standard error -stream. -</P> -<P> -<b>-c</b> -Do not print individual lines; instead just print a count of the number of -lines that would otherwise have been printed. If several files are given, a -count is printed for each of them. -</P> -<P> -<b>-f</b><i>filename</i> -Read a number of patterns from the file, one per line, and match all of them -against each line of input. A line is output if any of the patterns match it. -When <b>-f</b> is used, no pattern is taken from the command line; all arguments -are treated as file names. There is a maximum of 100 patterns. Trailing white -space is removed, and blank lines are ignored. An empty file contains no -patterns and therefore matches nothing. -</P> -<P> -<b>-h</b> -Suppress printing of filenames when searching multiple files. -</P> -<P> -<b>-i</b> -Ignore upper/lower case distinctions during comparisons. -</P> -<P> -<b>-l</b> -Instead of printing lines from the files, just print the names of the files -containing lines that would have been printed. Each file name is printed -once, on a separate line. -</P> -<P> -<b>-n</b> -Precede each line by its line number in the file. -</P> -<P> -<b>-r</b> -If any file is a directory, recursively scan the files it contains. Without -<b>-r</b> a directory is scanned as a normal file. -</P> -<P> -<b>-s</b> -Work silently, that is, display nothing except error messages. -The exit status indicates whether any matches were found. -</P> -<P> -<b>-u</b> -Operate in UTF-8 mode. This option is available only if PCRE has been compiled -with UTF-8 support. Both the pattern and each subject line are assumed to be -valid strings of UTF-8 characters. -</P> -<P> -<b>-v</b> -Invert the sense of the match, so that lines which do <i>not</i> match the -pattern are now the ones that are found. -</P> -<P> -<b>-x</b> -Force the pattern to be anchored (it must start matching at the beginning of -the line) and in addition, require it to match the entire line. This is -equivalent to having ^ and $ characters at the start and end of each -alternative branch in the regular expression. -</P> -<br><a name="SEC4" href="#TOC1">LONG OPTIONS</a><br> -<P> -Long forms of all the options are available, as in GNU grep. They are shown in -the following table: -</P> -<P> -<pre> - -c --count - -h --no-filename - -i --ignore-case - -l --files-with-matches - -n --line-number - -r --recursive - -s --no-messages - -u --utf-8 - -V --version - -v --invert-match - -x --line-regex - -x --line-regexp -</PRE> -</P> -<P> -In addition, --file=<i>filename</i> is equivalent to -f<i>filename</i>, and ---help shows the list of options and then exits. -</P> -<br><a name="SEC5" href="#TOC1">DIAGNOSTICS</a><br> -<P> -Exit status is 0 if any matches were found, 1 if no matches were found, and 2 -for syntax errors or inacessible files (even if matches were found). -</P> -<br><a name="SEC6" href="#TOC1">AUTHOR</a><br> -<P> -Philip Hazel <ph10@cam.ac.uk> -<br> -University Computing Service -<br> -Cambridge CB2 3QG, England. -</P> -<P> -Last updated: 03 February 2003 -<br> -Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcrepattern.html b/external-libs/pcre/doc/html/pcrepattern.html deleted file mode 100644 index 65abcc21..00000000 --- a/external-libs/pcre/doc/html/pcrepattern.html +++ /dev/null @@ -1,1607 +0,0 @@ -<html> -<head> -<title>pcrepattern specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<ul> -<li><a name="TOC1" href="#SEC1">PCRE REGULAR EXPRESSION DETAILS</a> -<li><a name="TOC2" href="#SEC2">BACKSLASH</a> -<li><a name="TOC3" href="#SEC3">CIRCUMFLEX AND DOLLAR</a> -<li><a name="TOC4" href="#SEC4">FULL STOP (PERIOD, DOT)</a> -<li><a name="TOC5" href="#SEC5">MATCHING A SINGLE BYTE</a> -<li><a name="TOC6" href="#SEC6">SQUARE BRACKETS</a> -<li><a name="TOC7" href="#SEC7">POSIX CHARACTER CLASSES</a> -<li><a name="TOC8" href="#SEC8">VERTICAL BAR</a> -<li><a name="TOC9" href="#SEC9">INTERNAL OPTION SETTING</a> -<li><a name="TOC10" href="#SEC10">SUBPATTERNS</a> -<li><a name="TOC11" href="#SEC11">NAMED SUBPATTERNS</a> -<li><a name="TOC12" href="#SEC12">REPETITION</a> -<li><a name="TOC13" href="#SEC13">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a> -<li><a name="TOC14" href="#SEC14">BACK REFERENCES</a> -<li><a name="TOC15" href="#SEC15">ASSERTIONS</a> -<li><a name="TOC16" href="#SEC16">CONDITIONAL SUBPATTERNS</a> -<li><a name="TOC17" href="#SEC17">COMMENTS</a> -<li><a name="TOC18" href="#SEC18">RECURSIVE PATTERNS</a> -<li><a name="TOC19" href="#SEC19">SUBPATTERNS AS SUBROUTINES</a> -<li><a name="TOC20" href="#SEC20">CALLOUTS</a> -</ul> -<br><a name="SEC1" href="#TOC1">PCRE REGULAR EXPRESSION DETAILS</a><br> -<P> -The syntax and semantics of the regular expressions supported by PCRE are -described below. Regular expressions are also described in the Perl -documentation and in a number of other books, some of which have copious -examples. Jeffrey Friedl's "Mastering Regular Expressions", published by -O'Reilly, covers them in great detail. The description here is intended as -reference documentation. -</P> -<P> -The basic operation of PCRE is on strings of bytes. However, there is also -support for UTF-8 character strings. To use this support you must build PCRE to -include UTF-8 support, and then call <b>pcre_compile()</b> with the PCRE_UTF8 -option. How this affects the pattern matching is mentioned in several places -below. There is also a summary of UTF-8 features in the -<a href="pcre.html#utf8support">section on UTF-8 support</a> -in the main -<a href="pcre.html"><b>pcre</b></a> -page. -</P> -<P> -A regular expression is a pattern that is matched against a subject string from -left to right. Most characters stand for themselves in a pattern, and match the -corresponding characters in the subject. As a trivial example, the pattern -</P> -<P> -<pre> - The quick brown fox -</PRE> -</P> -<P> -matches a portion of a subject string that is identical to itself. The power of -regular expressions comes from the ability to include alternatives and -repetitions in the pattern. These are encoded in the pattern by the use of -<i>meta-characters</i>, which do not stand for themselves but instead are -interpreted in some special way. -</P> -<P> -There are two different sets of meta-characters: those that are recognized -anywhere in the pattern except within square brackets, and those that are -recognized in square brackets. Outside square brackets, the meta-characters are -as follows: -</P> -<P> -<pre> - \ general escape character with several uses - ^ assert start of string (or line, in multiline mode) - $ assert end of string (or line, in multiline mode) - . match any character except newline (by default) - [ start character class definition - | start of alternative branch - ( start subpattern - ) end subpattern - ? extends the meaning of ( - also 0 or 1 quantifier - also quantifier minimizer - * 0 or more quantifier - + 1 or more quantifier - also "possessive quantifier" - { start min/max quantifier -</PRE> -</P> -<P> -Part of a pattern that is in square brackets is called a "character class". In -a character class the only meta-characters are: -</P> -<P> -<pre> - \ general escape character - ^ negate the class, but only if the first character - - indicates character range - [ POSIX character class (only if followed by POSIX - syntax) - ] terminates the character class -</PRE> -</P> -<P> -The following sections describe the use of each of the meta-characters. -</P> -<br><a name="SEC2" href="#TOC1">BACKSLASH</a><br> -<P> -The backslash character has several uses. Firstly, if it is followed by a -non-alphameric character, it takes away any special meaning that character may -have. This use of backslash as an escape character applies both inside and -outside character classes. -</P> -<P> -For example, if you want to match a * character, you write \* in the pattern. -This escaping action applies whether or not the following character would -otherwise be interpreted as a meta-character, so it is always safe to precede a -non-alphameric with backslash to specify that it stands for itself. In -particular, if you want to match a backslash, you write \\. -</P> -<P> -If a pattern is compiled with the PCRE_EXTENDED option, whitespace in the -pattern (other than in a character class) and characters between a # outside -a character class and the next newline character are ignored. An escaping -backslash can be used to include a whitespace or # character as part of the -pattern. -</P> -<P> -If you want to remove the special meaning from a sequence of characters, you -can do so by putting them between \Q and \E. This is different from Perl in -that $ and @ are handled as literals in \Q...\E sequences in PCRE, whereas in -Perl, $ and @ cause variable interpolation. Note the following examples: -</P> -<P> -<pre> - Pattern PCRE matches Perl matches -</PRE> -</P> -<P> -<pre> - \Qabc$xyz\E abc$xyz abc followed by the - contents of $xyz - \Qabc\$xyz\E abc\$xyz abc\$xyz - \Qabc\E\$\Qxyz\E abc$xyz abc$xyz -</PRE> -</P> -<P> -The \Q...\E sequence is recognized both inside and outside character classes. -</P> -<P> -A second use of backslash provides a way of encoding non-printing characters -in patterns in a visible manner. There is no restriction on the appearance of -non-printing characters, apart from the binary zero that terminates a pattern, -but when a pattern is being prepared by text editing, it is usually easier to -use one of the following escape sequences than the binary character it -represents: -</P> -<P> -<pre> - \a alarm, that is, the BEL character (hex 07) - \cx "control-x", where x is any character - \e escape (hex 1B) - \f formfeed (hex 0C) - \n newline (hex 0A) - \r carriage return (hex 0D) - \t tab (hex 09) - \ddd character with octal code ddd, or backreference - \xhh character with hex code hh - \x{hhh..} character with hex code hhh... (UTF-8 mode only) -</PRE> -</P> -<P> -The precise effect of \cx is as follows: if x is a lower case letter, it -is converted to upper case. Then bit 6 of the character (hex 40) is inverted. -Thus \cz becomes hex 1A, but \c{ becomes hex 3B, while \c; becomes hex -7B. -</P> -<P> -After \x, from zero to two hexadecimal digits are read (letters can be in -upper or lower case). In UTF-8 mode, any number of hexadecimal digits may -appear between \x{ and }, but the value of the character code must be less -than 2**31 (that is, the maximum hexadecimal value is 7FFFFFFF). If characters -other than hexadecimal digits appear between \x{ and }, or if there is no -terminating }, this form of escape is not recognized. Instead, the initial -\x will be interpreted as a basic hexadecimal escape, with no following -digits, giving a byte whose value is zero. -</P> -<P> -Characters whose value is less than 256 can be defined by either of the two -syntaxes for \x when PCRE is in UTF-8 mode. There is no difference in the -way they are handled. For example, \xdc is exactly the same as \x{dc}. -</P> -<P> -After \0 up to two further octal digits are read. In both cases, if there -are fewer than two digits, just those that are present are used. Thus the -sequence \0\x\07 specifies two binary zeros followed by a BEL character -(code value 7). Make sure you supply two digits after the initial zero if the -character that follows is itself an octal digit. -</P> -<P> -The handling of a backslash followed by a digit other than 0 is complicated. -Outside a character class, PCRE reads it and any following digits as a decimal -number. If the number is less than 10, or if there have been at least that many -previous capturing left parentheses in the expression, the entire sequence is -taken as a <i>back reference</i>. A description of how this works is given -later, following the discussion of parenthesized subpatterns. -</P> -<P> -Inside a character class, or if the decimal number is greater than 9 and there -have not been that many capturing subpatterns, PCRE re-reads up to three octal -digits following the backslash, and generates a single byte from the least -significant 8 bits of the value. Any subsequent digits stand for themselves. -For example: -</P> -<P> -<pre> - \040 is another way of writing a space - \40 is the same, provided there are fewer than 40 - previous capturing subpatterns - \7 is always a back reference - \11 might be a back reference, or another way of - writing a tab - \011 is always a tab - \0113 is a tab followed by the character "3" - \113 might be a back reference, otherwise the - character with octal code 113 - \377 might be a back reference, otherwise - the byte consisting entirely of 1 bits - \81 is either a back reference, or a binary zero - followed by the two characters "8" and "1" -</PRE> -</P> -<P> -Note that octal values of 100 or greater must not be introduced by a leading -zero, because no more than three octal digits are ever read. -</P> -<P> -All the sequences that define a single byte value or a single UTF-8 character -(in UTF-8 mode) can be used both inside and outside character classes. In -addition, inside a character class, the sequence \b is interpreted as the -backspace character (hex 08). Outside a character class it has a different -meaning (see below). -</P> -<P> -The third use of backslash is for specifying generic character types: -</P> -<P> -<pre> - \d any decimal digit - \D any character that is not a decimal digit - \s any whitespace character - \S any character that is not a whitespace character - \w any "word" character - \W any "non-word" character -</PRE> -</P> -<P> -Each pair of escape sequences partitions the complete set of characters into -two disjoint sets. Any given character matches one, and only one, of each pair. -</P> -<P> -In UTF-8 mode, characters with values greater than 255 never match \d, \s, or -\w, and always match \D, \S, and \W. -</P> -<P> -For compatibility with Perl, \s does not match the VT character (code 11). -This makes it different from the the POSIX "space" class. The \s characters -are HT (9), LF (10), FF (12), CR (13), and space (32). -</P> -<P> -A "word" character is any letter or digit or the underscore character, that is, -any character which can be part of a Perl "word". The definition of letters and -digits is controlled by PCRE's character tables, and may vary if locale- -specific matching is taking place (see -<a href="pcreapi.html#localesupport">"Locale support"</a> -in the -<a href="pcreapi.html"><b>pcreapi</b></a> -page). For example, in the "fr" (French) locale, some character codes greater -than 128 are used for accented letters, and these are matched by \w. -</P> -<P> -These character type sequences can appear both inside and outside character -classes. They each match one character of the appropriate type. If the current -matching point is at the end of the subject string, all of them fail, since -there is no character to match. -</P> -<P> -The fourth use of backslash is for certain simple assertions. An assertion -specifies a condition that has to be met at a particular point in a match, -without consuming any characters from the subject string. The use of -subpatterns for more complicated assertions is described below. The backslashed -assertions are -</P> -<P> -<pre> - \b matches at a word boundary - \B matches when not at a word boundary - \A matches at start of subject - \Z matches at end of subject or before newline at end - \z matches at end of subject - \G matches at first matching position in subject -</PRE> -</P> -<P> -These assertions may not appear in character classes (but note that \b has a -different meaning, namely the backspace character, inside a character class). -</P> -<P> -A word boundary is a position in the subject string where the current character -and the previous character do not both match \w or \W (i.e. one matches -\w and the other matches \W), or the start or end of the string if the -first or last character matches \w, respectively. -</P> -<P> -The \A, \Z, and \z assertions differ from the traditional circumflex and -dollar (described below) in that they only ever match at the very start and end -of the subject string, whatever options are set. Thus, they are independent of -multiline mode. -</P> -<P> -They are not affected by the PCRE_NOTBOL or PCRE_NOTEOL options. If the -<i>startoffset</i> argument of <b>pcre_exec()</b> is non-zero, indicating that -matching is to start at a point other than the beginning of the subject, \A -can never match. The difference between \Z and \z is that \Z matches before -a newline that is the last character of the string as well as at the end of the -string, whereas \z matches only at the end. -</P> -<P> -The \G assertion is true only when the current matching position is at the -start point of the match, as specified by the <i>startoffset</i> argument of -<b>pcre_exec()</b>. It differs from \A when the value of <i>startoffset</i> is -non-zero. By calling <b>pcre_exec()</b> multiple times with appropriate -arguments, you can mimic Perl's /g option, and it is in this kind of -implementation where \G can be useful. -</P> -<P> -Note, however, that PCRE's interpretation of \G, as the start of the current -match, is subtly different from Perl's, which defines it as the end of the -previous match. In Perl, these can be different when the previously matched -string was empty. Because PCRE does just one match at a time, it cannot -reproduce this behaviour. -</P> -<P> -If all the alternatives of a pattern begin with \G, the expression is anchored -to the starting match position, and the "anchored" flag is set in the compiled -regular expression. -</P> -<br><a name="SEC3" href="#TOC1">CIRCUMFLEX AND DOLLAR</a><br> -<P> -Outside a character class, in the default matching mode, the circumflex -character is an assertion which is true only if the current matching point is -at the start of the subject string. If the <i>startoffset</i> argument of -<b>pcre_exec()</b> is non-zero, circumflex can never match if the PCRE_MULTILINE -option is unset. Inside a character class, circumflex has an entirely different -meaning (see below). -</P> -<P> -Circumflex need not be the first character of the pattern if a number of -alternatives are involved, but it should be the first thing in each alternative -in which it appears if the pattern is ever to match that branch. If all -possible alternatives start with a circumflex, that is, if the pattern is -constrained to match only at the start of the subject, it is said to be an -"anchored" pattern. (There are also other constructs that can cause a pattern -to be anchored.) -</P> -<P> -A dollar character is an assertion which is true only if the current matching -point is at the end of the subject string, or immediately before a newline -character that is the last character in the string (by default). Dollar need -not be the last character of the pattern if a number of alternatives are -involved, but it should be the last item in any branch in which it appears. -Dollar has no special meaning in a character class. -</P> -<P> -The meaning of dollar can be changed so that it matches only at the very end of -the string, by setting the PCRE_DOLLAR_ENDONLY option at compile time. This -does not affect the \Z assertion. -</P> -<P> -The meanings of the circumflex and dollar characters are changed if the -PCRE_MULTILINE option is set. When this is the case, they match immediately -after and immediately before an internal newline character, respectively, in -addition to matching at the start and end of the subject string. For example, -the pattern /^abc$/ matches the subject string "def\nabc" in multiline mode, -but not otherwise. Consequently, patterns that are anchored in single line mode -because all branches start with ^ are not anchored in multiline mode, and a -match for circumflex is possible when the <i>startoffset</i> argument of -<b>pcre_exec()</b> is non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if -PCRE_MULTILINE is set. -</P> -<P> -Note that the sequences \A, \Z, and \z can be used to match the start and -end of the subject in both modes, and if all branches of a pattern start with -\A it is always anchored, whether PCRE_MULTILINE is set or not. -</P> -<br><a name="SEC4" href="#TOC1">FULL STOP (PERIOD, DOT)</a><br> -<P> -Outside a character class, a dot in the pattern matches any one character in -the subject, including a non-printing character, but not (by default) newline. -In UTF-8 mode, a dot matches any UTF-8 character, which might be more than one -byte long, except (by default) for newline. If the PCRE_DOTALL option is set, -dots match newlines as well. The handling of dot is entirely independent of the -handling of circumflex and dollar, the only relationship being that they both -involve newline characters. Dot has no special meaning in a character class. -</P> -<br><a name="SEC5" href="#TOC1">MATCHING A SINGLE BYTE</a><br> -<P> -Outside a character class, the escape sequence \C matches any one byte, both -in and out of UTF-8 mode. Unlike a dot, it always matches a newline. The -feature is provided in Perl in order to match individual bytes in UTF-8 mode. -Because it breaks up UTF-8 characters into individual bytes, what remains in -the string may be a malformed UTF-8 string. For this reason it is best avoided. -</P> -<P> -PCRE does not allow \C to appear in lookbehind assertions (see below), because -in UTF-8 mode it makes it impossible to calculate the length of the lookbehind. -</P> -<br><a name="SEC6" href="#TOC1">SQUARE BRACKETS</a><br> -<P> -An opening square bracket introduces a character class, terminated by a closing -square bracket. A closing square bracket on its own is not special. If a -closing square bracket is required as a member of the class, it should be the -first data character in the class (after an initial circumflex, if present) or -escaped with a backslash. -</P> -<P> -A character class matches a single character in the subject. In UTF-8 mode, the -character may occupy more than one byte. A matched character must be in the set -of characters defined by the class, unless the first character in the class -definition is a circumflex, in which case the subject character must not be in -the set defined by the class. If a circumflex is actually required as a member -of the class, ensure it is not the first character, or escape it with a -backslash. -</P> -<P> -For example, the character class [aeiou] matches any lower case vowel, while -[^aeiou] matches any character that is not a lower case vowel. Note that a -circumflex is just a convenient notation for specifying the characters which -are in the class by enumerating those that are not. It is not an assertion: it -still consumes a character from the subject string, and fails if the current -pointer is at the end of the string. -</P> -<P> -In UTF-8 mode, characters with values greater than 255 can be included in a -class as a literal string of bytes, or by using the \x{ escaping mechanism. -</P> -<P> -When caseless matching is set, any letters in a class represent both their -upper case and lower case versions, so for example, a caseless [aeiou] matches -"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a -caseful version would. PCRE does not support the concept of case for characters -with values greater than 255. -</P> -<P> -The newline character is never treated in any special way in character classes, -whatever the setting of the PCRE_DOTALL or PCRE_MULTILINE options is. A class -such as [^a] will always match a newline. -</P> -<P> -The minus (hyphen) character can be used to specify a range of characters in a -character class. For example, [d-m] matches any letter between d and m, -inclusive. If a minus character is required in a class, it must be escaped with -a backslash or appear in a position where it cannot be interpreted as -indicating a range, typically as the first or last character in the class. -</P> -<P> -It is not possible to have the literal character "]" as the end character of a -range. A pattern such as [W-]46] is interpreted as a class of two characters -("W" and "-") followed by a literal string "46]", so it would match "W46]" or -"-46]". However, if the "]" is escaped with a backslash it is interpreted as -the end of range, so [W-\]46] is interpreted as a single class containing a -range followed by two separate characters. The octal or hexadecimal -representation of "]" can also be used to end a range. -</P> -<P> -Ranges operate in the collating sequence of character values. They can also be -used for characters specified numerically, for example [\000-\037]. In UTF-8 -mode, ranges can include characters whose values are greater than 255, for -example [\x{100}-\x{2ff}]. -</P> -<P> -If a range that includes letters is used when caseless matching is set, it -matches the letters in either case. For example, [W-c] is equivalent to -[][\^_`wxyzabc], matched caselessly, and if character tables for the "fr" -locale are in use, [\xc8-\xcb] matches accented E characters in both cases. -</P> -<P> -The character types \d, \D, \s, \S, \w, and \W may also appear in a -character class, and add the characters that they match to the class. For -example, [\dABCDEF] matches any hexadecimal digit. A circumflex can -conveniently be used with the upper case character types to specify a more -restricted set of characters than the matching lower case type. For example, -the class [^\W_] matches any letter or digit, but not underscore. -</P> -<P> -All non-alphameric characters other than \, -, ^ (at the start) and the -terminating ] are non-special in character classes, but it does no harm if they -are escaped. -</P> -<br><a name="SEC7" href="#TOC1">POSIX CHARACTER CLASSES</a><br> -<P> -Perl supports the POSIX notation for character classes, which uses names -enclosed by [: and :] within the enclosing square brackets. PCRE also supports -this notation. For example, -</P> -<P> -<pre> - [01[:alpha:]%] -</PRE> -</P> -<P> -matches "0", "1", any alphabetic character, or "%". The supported class names -are -</P> -<P> -<pre> - alnum letters and digits - alpha letters - ascii character codes 0 - 127 - blank space or tab only - cntrl control characters - digit decimal digits (same as \d) - graph printing characters, excluding space - lower lower case letters - print printing characters, including space - punct printing characters, excluding letters and digits - space white space (not quite the same as \s) - upper upper case letters - word "word" characters (same as \w) - xdigit hexadecimal digits -</PRE> -</P> -<P> -The "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), and -space (32). Notice that this list includes the VT character (code 11). This -makes "space" different to \s, which does not include VT (for Perl -compatibility). -</P> -<P> -The name "word" is a Perl extension, and "blank" is a GNU extension from Perl -5.8. Another Perl extension is negation, which is indicated by a ^ character -after the colon. For example, -</P> -<P> -<pre> - [12[:^digit:]] -</PRE> -</P> -<P> -matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the POSIX -syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not -supported, and an error is given if they are encountered. -</P> -<P> -In UTF-8 mode, characters with values greater than 255 do not match any of -the POSIX character classes. -</P> -<br><a name="SEC8" href="#TOC1">VERTICAL BAR</a><br> -<P> -Vertical bar characters are used to separate alternative patterns. For example, -the pattern -</P> -<P> -<pre> - gilbert|sullivan -</PRE> -</P> -<P> -matches either "gilbert" or "sullivan". Any number of alternatives may appear, -and an empty alternative is permitted (matching the empty string). -The matching process tries each alternative in turn, from left to right, -and the first one that succeeds is used. If the alternatives are within a -subpattern (defined below), "succeeds" means matching the rest of the main -pattern as well as the alternative in the subpattern. -</P> -<br><a name="SEC9" href="#TOC1">INTERNAL OPTION SETTING</a><br> -<P> -The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and -PCRE_EXTENDED options can be changed from within the pattern by a sequence of -Perl option letters enclosed between "(?" and ")". The option letters are -</P> -<P> -<pre> - i for PCRE_CASELESS - m for PCRE_MULTILINE - s for PCRE_DOTALL - x for PCRE_EXTENDED -</PRE> -</P> -<P> -For example, (?im) sets caseless, multiline matching. It is also possible to -unset these options by preceding the letter with a hyphen, and a combined -setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and -PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also -permitted. If a letter appears both before and after the hyphen, the option is -unset. -</P> -<P> -When an option change occurs at top level (that is, not inside subpattern -parentheses), the change applies to the remainder of the pattern that follows. -If the change is placed right at the start of a pattern, PCRE extracts it into -the global options (and it will therefore show up in data extracted by the -<b>pcre_fullinfo()</b> function). -</P> -<P> -An option change within a subpattern affects only that part of the current -pattern that follows it, so -</P> -<P> -<pre> - (a(?i)b)c -</PRE> -</P> -<P> -matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used). -By this means, options can be made to have different settings in different -parts of the pattern. Any changes made in one alternative do carry on -into subsequent branches within the same subpattern. For example, -</P> -<P> -<pre> - (a(?i)b|c) -</PRE> -</P> -<P> -matches "ab", "aB", "c", and "C", even though when matching "C" the first -branch is abandoned before the option setting. This is because the effects of -option settings happen at compile time. There would be some very weird -behaviour otherwise. -</P> -<P> -The PCRE-specific options PCRE_UNGREEDY and PCRE_EXTRA can be changed in the -same way as the Perl-compatible options by using the characters U and X -respectively. The (?X) flag setting is special in that it must always occur -earlier in the pattern than any of the additional features it turns on, even -when it is at top level. It is best put at the start. -</P> -<br><a name="SEC10" href="#TOC1">SUBPATTERNS</a><br> -<P> -Subpatterns are delimited by parentheses (round brackets), which can be nested. -Marking part of a pattern as a subpattern does two things: -</P> -<P> -1. It localizes a set of alternatives. For example, the pattern -</P> -<P> -<pre> - cat(aract|erpillar|) -</PRE> -</P> -<P> -matches one of the words "cat", "cataract", or "caterpillar". Without the -parentheses, it would match "cataract", "erpillar" or the empty string. -</P> -<P> -2. It sets up the subpattern as a capturing subpattern (as defined above). -When the whole pattern matches, that portion of the subject string that matched -the subpattern is passed back to the caller via the <i>ovector</i> argument of -<b>pcre_exec()</b>. Opening parentheses are counted from left to right (starting -from 1) to obtain the numbers of the capturing subpatterns. -</P> -<P> -For example, if the string "the red king" is matched against the pattern -</P> -<P> -<pre> - the ((red|white) (king|queen)) -</PRE> -</P> -<P> -the captured substrings are "red king", "red", and "king", and are numbered 1, -2, and 3, respectively. -</P> -<P> -The fact that plain parentheses fulfil two functions is not always helpful. -There are often times when a grouping subpattern is required without a -capturing requirement. If an opening parenthesis is followed by a question mark -and a colon, the subpattern does not do any capturing, and is not counted when -computing the number of any subsequent capturing subpatterns. For example, if -the string "the white queen" is matched against the pattern -</P> -<P> -<pre> - the ((?:red|white) (king|queen)) -</PRE> -</P> -<P> -the captured substrings are "white queen" and "queen", and are numbered 1 and -2. The maximum number of capturing subpatterns is 65535, and the maximum depth -of nesting of all subpatterns, both capturing and non-capturing, is 200. -</P> -<P> -As a convenient shorthand, if any option settings are required at the start of -a non-capturing subpattern, the option letters may appear between the "?" and -the ":". Thus the two patterns -</P> -<P> -<pre> - (?i:saturday|sunday) - (?:(?i)saturday|sunday) -</PRE> -</P> -<P> -match exactly the same set of strings. Because alternative branches are tried -from left to right, and options are not reset until the end of the subpattern -is reached, an option setting in one branch does affect subsequent branches, so -the above patterns match "SUNDAY" as well as "Saturday". -</P> -<br><a name="SEC11" href="#TOC1">NAMED SUBPATTERNS</a><br> -<P> -Identifying capturing parentheses by number is simple, but it can be very hard -to keep track of the numbers in complicated regular expressions. Furthermore, -if an expression is modified, the numbers may change. To help with the -difficulty, PCRE supports the naming of subpatterns, something that Perl does -not provide. The Python syntax (?P<name>...) is used. Names consist of -alphanumeric characters and underscores, and must be unique within a pattern. -</P> -<P> -Named capturing parentheses are still allocated numbers as well as names. The -PCRE API provides function calls for extracting the name-to-number translation -table from a compiled pattern. For further details see the -<a href="pcreapi.html"><b>pcreapi</b></a> -documentation. -</P> -<br><a name="SEC12" href="#TOC1">REPETITION</a><br> -<P> -Repetition is specified by quantifiers, which can follow any of the following -items: -</P> -<P> -<pre> - a literal data character - the . metacharacter - the \C escape sequence - escapes such as \d that match single characters - a character class - a back reference (see next section) - a parenthesized subpattern (unless it is an assertion) -</PRE> -</P> -<P> -The general repetition quantifier specifies a minimum and maximum number of -permitted matches, by giving the two numbers in curly brackets (braces), -separated by a comma. The numbers must be less than 65536, and the first must -be less than or equal to the second. For example: -</P> -<P> -<pre> - z{2,4} -</PRE> -</P> -<P> -matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special -character. If the second number is omitted, but the comma is present, there is -no upper limit; if the second number and the comma are both omitted, the -quantifier specifies an exact number of required matches. Thus -</P> -<P> -<pre> - [aeiou]{3,} -</PRE> -</P> -<P> -matches at least 3 successive vowels, but may match many more, while -</P> -<P> -<pre> - \d{8} -</PRE> -</P> -<P> -matches exactly 8 digits. An opening curly bracket that appears in a position -where a quantifier is not allowed, or one that does not match the syntax of a -quantifier, is taken as a literal character. For example, {,6} is not a -quantifier, but a literal string of four characters. -</P> -<P> -In UTF-8 mode, quantifiers apply to UTF-8 characters rather than to individual -bytes. Thus, for example, \x{100}{2} matches two UTF-8 characters, each of -which is represented by a two-byte sequence. -</P> -<P> -The quantifier {0} is permitted, causing the expression to behave as if the -previous item and the quantifier were not present. -</P> -<P> -For convenience (and historical compatibility) the three most common -quantifiers have single-character abbreviations: -</P> -<P> -<pre> - * is equivalent to {0,} - + is equivalent to {1,} - ? is equivalent to {0,1} -</PRE> -</P> -<P> -It is possible to construct infinite loops by following a subpattern that can -match no characters with a quantifier that has no upper limit, for example: -</P> -<P> -<pre> - (a?)* -</PRE> -</P> -<P> -Earlier versions of Perl and PCRE used to give an error at compile time for -such patterns. However, because there are cases where this can be useful, such -patterns are now accepted, but if any repetition of the subpattern does in fact -match no characters, the loop is forcibly broken. -</P> -<P> -By default, the quantifiers are "greedy", that is, they match as much as -possible (up to the maximum number of permitted times), without causing the -rest of the pattern to fail. The classic example of where this gives problems -is in trying to match comments in C programs. These appear between the -sequences /* and */ and within the sequence, individual * and / characters may -appear. An attempt to match C comments by applying the pattern -</P> -<P> -<pre> - /\*.*\*/ -</PRE> -</P> -<P> -to the string -</P> -<P> -<pre> - /* first command */ not comment /* second comment */ -</PRE> -</P> -<P> -fails, because it matches the entire string owing to the greediness of the .* -item. -</P> -<P> -However, if a quantifier is followed by a question mark, it ceases to be -greedy, and instead matches the minimum number of times possible, so the -pattern -</P> -<P> -<pre> - /\*.*?\*/ -</PRE> -</P> -<P> -does the right thing with the C comments. The meaning of the various -quantifiers is not otherwise changed, just the preferred number of matches. -Do not confuse this use of question mark with its use as a quantifier in its -own right. Because it has two uses, it can sometimes appear doubled, as in -</P> -<P> -<pre> - \d??\d -</PRE> -</P> -<P> -which matches one digit by preference, but can match two if that is the only -way the rest of the pattern matches. -</P> -<P> -If the PCRE_UNGREEDY option is set (an option which is not available in Perl), -the quantifiers are not greedy by default, but individual ones can be made -greedy by following them with a question mark. In other words, it inverts the -default behaviour. -</P> -<P> -When a parenthesized subpattern is quantified with a minimum repeat count that -is greater than 1 or with a limited maximum, more store is required for the -compiled pattern, in proportion to the size of the minimum or maximum. -</P> -<P> -If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent -to Perl's /s) is set, thus allowing the . to match newlines, the pattern is -implicitly anchored, because whatever follows will be tried against every -character position in the subject string, so there is no point in retrying the -overall match at any position after the first. PCRE normally treats such a -pattern as though it were preceded by \A. -</P> -<P> -In cases where it is known that the subject string contains no newlines, it is -worth setting PCRE_DOTALL in order to obtain this optimization, or -alternatively using ^ to indicate anchoring explicitly. -</P> -<P> -However, there is one situation where the optimization cannot be used. When .* -is inside capturing parentheses that are the subject of a backreference -elsewhere in the pattern, a match at the start may fail, and a later one -succeed. Consider, for example: -</P> -<P> -<pre> - (.*)abc\1 -</PRE> -</P> -<P> -If the subject is "xyz123abc123" the match point is the fourth character. For -this reason, such a pattern is not implicitly anchored. -</P> -<P> -When a capturing subpattern is repeated, the value captured is the substring -that matched the final iteration. For example, after -</P> -<P> -<pre> - (tweedle[dume]{3}\s*)+ -</PRE> -</P> -<P> -has matched "tweedledum tweedledee" the value of the captured substring is -"tweedledee". However, if there are nested capturing subpatterns, the -corresponding captured values may have been set in previous iterations. For -example, after -</P> -<P> -<pre> - /(a|(b))+/ -</PRE> -</P> -<P> -matches "aba" the value of the second captured substring is "b". -</P> -<br><a name="SEC13" href="#TOC1">ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS</a><br> -<P> -With both maximizing and minimizing repetition, failure of what follows -normally causes the repeated item to be re-evaluated to see if a different -number of repeats allows the rest of the pattern to match. Sometimes it is -useful to prevent this, either to change the nature of the match, or to cause -it fail earlier than it otherwise might, when the author of the pattern knows -there is no point in carrying on. -</P> -<P> -Consider, for example, the pattern \d+foo when applied to the subject line -</P> -<P> -<pre> - 123456bar -</PRE> -</P> -<P> -After matching all 6 digits and then failing to match "foo", the normal -action of the matcher is to try again with only 5 digits matching the \d+ -item, and then with 4, and so on, before ultimately failing. "Atomic grouping" -(a term taken from Jeffrey Friedl's book) provides the means for specifying -that once a subpattern has matched, it is not to be re-evaluated in this way. -</P> -<P> -If we use atomic grouping for the previous example, the matcher would give up -immediately on failing to match "foo" the first time. The notation is a kind of -special parenthesis, starting with (?> as in this example: -</P> -<P> -<pre> - (?>\d+)foo -</PRE> -</P> -<P> -This kind of parenthesis "locks up" the part of the pattern it contains once -it has matched, and a failure further into the pattern is prevented from -backtracking into it. Backtracking past it to previous items, however, works as -normal. -</P> -<P> -An alternative description is that a subpattern of this type matches the string -of characters that an identical standalone pattern would match, if anchored at -the current point in the subject string. -</P> -<P> -Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as -the above example can be thought of as a maximizing repeat that must swallow -everything it can. So, while both \d+ and \d+? are prepared to adjust the -number of digits they match in order to make the rest of the pattern match, -(?>\d+) can only match an entire sequence of digits. -</P> -<P> -Atomic groups in general can of course contain arbitrarily complicated -subpatterns, and can be nested. However, when the subpattern for an atomic -group is just a single repeated item, as in the example above, a simpler -notation, called a "possessive quantifier" can be used. This consists of an -additional + character following a quantifier. Using this notation, the -previous example can be rewritten as -</P> -<P> -<pre> - \d++bar -</PRE> -</P> -<P> -Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY -option is ignored. They are a convenient notation for the simpler forms of -atomic group. However, there is no difference in the meaning or processing of a -possessive quantifier and the equivalent atomic group. -</P> -<P> -The possessive quantifier syntax is an extension to the Perl syntax. It -originates in Sun's Java package. -</P> -<P> -When a pattern contains an unlimited repeat inside a subpattern that can itself -be repeated an unlimited number of times, the use of an atomic group is the -only way to avoid some failing matches taking a very long time indeed. The -pattern -</P> -<P> -<pre> - (\D+|<\d+>)*[!?] -</PRE> -</P> -<P> -matches an unlimited number of substrings that either consist of non-digits, or -digits enclosed in <>, followed by either ! or ?. When it matches, it runs -quickly. However, if it is applied to -</P> -<P> -<pre> - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -</PRE> -</P> -<P> -it takes a long time before reporting failure. This is because the string can -be divided between the two repeats in a large number of ways, and all have to -be tried. (The example used [!?] rather than a single character at the end, -because both PCRE and Perl have an optimization that allows for fast failure -when a single character is used. They remember the last single character that -is required for a match, and fail early if it is not present in the string.) -If the pattern is changed to -</P> -<P> -<pre> - ((?>\D+)|<\d+>)*[!?] -</PRE> -</P> -<P> -sequences of non-digits cannot be broken, and failure happens quickly. -</P> -<br><a name="SEC14" href="#TOC1">BACK REFERENCES</a><br> -<P> -Outside a character class, a backslash followed by a digit greater than 0 (and -possibly further digits) is a back reference to a capturing subpattern earlier -(that is, to its left) in the pattern, provided there have been that many -previous capturing left parentheses. -</P> -<P> -However, if the decimal number following the backslash is less than 10, it is -always taken as a back reference, and causes an error only if there are not -that many capturing left parentheses in the entire pattern. In other words, the -parentheses that are referenced need not be to the left of the reference for -numbers less than 10. See the section entitled "Backslash" above for further -details of the handling of digits following a backslash. -</P> -<P> -A back reference matches whatever actually matched the capturing subpattern in -the current subject string, rather than anything matching the subpattern -itself (see -<a href="#subpatternsassubroutines">"Subpatterns as subroutines"</a> -below for a way of doing that). So the pattern -</P> -<P> -<pre> - (sens|respons)e and \1ibility -</PRE> -</P> -<P> -matches "sense and sensibility" and "response and responsibility", but not -"sense and responsibility". If caseful matching is in force at the time of the -back reference, the case of letters is relevant. For example, -</P> -<P> -<pre> - ((?i)rah)\s+\1 -</PRE> -</P> -<P> -matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original -capturing subpattern is matched caselessly. -</P> -<P> -Back references to named subpatterns use the Python syntax (?P=name). We could -rewrite the above example as follows: -</P> -<P> -<pre> - (?<p1>(?i)rah)\s+(?P=p1) -</PRE> -</P> -<P> -There may be more than one back reference to the same subpattern. If a -subpattern has not actually been used in a particular match, any back -references to it always fail. For example, the pattern -</P> -<P> -<pre> - (a|(bc))\2 -</PRE> -</P> -<P> -always fails if it starts to match "a" rather than "bc". Because there may be -many capturing parentheses in a pattern, all digits following the backslash are -taken as part of a potential back reference number. If the pattern continues -with a digit character, some delimiter must be used to terminate the back -reference. If the PCRE_EXTENDED option is set, this can be whitespace. -Otherwise an empty comment can be used. -</P> -<P> -A back reference that occurs inside the parentheses to which it refers fails -when the subpattern is first used, so, for example, (a\1) never matches. -However, such references can be useful inside repeated subpatterns. For -example, the pattern -</P> -<P> -<pre> - (a|b\1)+ -</PRE> -</P> -<P> -matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of -the subpattern, the back reference matches the character string corresponding -to the previous iteration. In order for this to work, the pattern must be such -that the first iteration does not need to match the back reference. This can be -done using alternation, as in the example above, or by a quantifier with a -minimum of zero. -</P> -<br><a name="SEC15" href="#TOC1">ASSERTIONS</a><br> -<P> -An assertion is a test on the characters following or preceding the current -matching point that does not actually consume any characters. The simple -assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are described above. -More complicated assertions are coded as subpatterns. There are two kinds: -those that look ahead of the current position in the subject string, and those -that look behind it. -</P> -<P> -An assertion subpattern is matched in the normal way, except that it does not -cause the current matching position to be changed. Lookahead assertions start -with (?= for positive assertions and (?! for negative assertions. For example, -</P> -<P> -<pre> - \w+(?=;) -</PRE> -</P> -<P> -matches a word followed by a semicolon, but does not include the semicolon in -the match, and -</P> -<P> -<pre> - foo(?!bar) -</PRE> -</P> -<P> -matches any occurrence of "foo" that is not followed by "bar". Note that the -apparently similar pattern -</P> -<P> -<pre> - (?!foo)bar -</PRE> -</P> -<P> -does not find an occurrence of "bar" that is preceded by something other than -"foo"; it finds any occurrence of "bar" whatsoever, because the assertion -(?!foo) is always true when the next three characters are "bar". A -lookbehind assertion is needed to achieve this effect. -</P> -<P> -If you want to force a matching failure at some point in a pattern, the most -convenient way to do it is with (?!) because an empty string always matches, so -an assertion that requires there not to be an empty string must always fail. -</P> -<P> -Lookbehind assertions start with (?<= for positive assertions and (?<! for -negative assertions. For example, -</P> -<P> -<pre> - (?<!foo)bar -</PRE> -</P> -<P> -does find an occurrence of "bar" that is not preceded by "foo". The contents of -a lookbehind assertion are restricted such that all the strings it matches must -have a fixed length. However, if there are several alternatives, they do not -all have to have the same fixed length. Thus -</P> -<P> -<pre> - (?<=bullock|donkey) -</PRE> -</P> -<P> -is permitted, but -</P> -<P> -<pre> - (?<!dogs?|cats?) -</PRE> -</P> -<P> -causes an error at compile time. Branches that match different length strings -are permitted only at the top level of a lookbehind assertion. This is an -extension compared with Perl (at least for 5.8), which requires all branches to -match the same length of string. An assertion such as -</P> -<P> -<pre> - (?<=ab(c|de)) -</PRE> -</P> -<P> -is not permitted, because its single top-level branch can match two different -lengths, but it is acceptable if rewritten to use two top-level branches: -</P> -<P> -<pre> - (?<=abc|abde) -</PRE> -</P> -<P> -The implementation of lookbehind assertions is, for each alternative, to -temporarily move the current position back by the fixed width and then try to -match. If there are insufficient characters before the current position, the -match is deemed to fail. -</P> -<P> -PCRE does not allow the \C escape (which matches a single byte in UTF-8 mode) -to appear in lookbehind assertions, because it makes it impossible to calculate -the length of the lookbehind. -</P> -<P> -Atomic groups can be used in conjunction with lookbehind assertions to specify -efficient matching at the end of the subject string. Consider a simple pattern -such as -</P> -<P> -<pre> - abcd$ -</PRE> -</P> -<P> -when applied to a long string that does not match. Because matching proceeds -from left to right, PCRE will look for each "a" in the subject and then see if -what follows matches the rest of the pattern. If the pattern is specified as -</P> -<P> -<pre> - ^.*abcd$ -</PRE> -</P> -<P> -the initial .* matches the entire string at first, but when this fails (because -there is no following "a"), it backtracks to match all but the last character, -then all but the last two characters, and so on. Once again the search for "a" -covers the entire string, from right to left, so we are no better off. However, -if the pattern is written as -</P> -<P> -<pre> - ^(?>.*)(?<=abcd) -</PRE> -</P> -<P> -or, equivalently, -</P> -<P> -<pre> - ^.*+(?<=abcd) -</PRE> -</P> -<P> -there can be no backtracking for the .* item; it can match only the entire -string. The subsequent lookbehind assertion does a single test on the last four -characters. If it fails, the match fails immediately. For long strings, this -approach makes a significant difference to the processing time. -</P> -<P> -Several assertions (of any sort) may occur in succession. For example, -</P> -<P> -<pre> - (?<=\d{3})(?<!999)foo -</PRE> -</P> -<P> -matches "foo" preceded by three digits that are not "999". Notice that each of -the assertions is applied independently at the same point in the subject -string. First there is a check that the previous three characters are all -digits, and then there is a check that the same three characters are not "999". -This pattern does <i>not</i> match "foo" preceded by six characters, the first -of which are digits and the last three of which are not "999". For example, it -doesn't match "123abcfoo". A pattern to do that is -</P> -<P> -<pre> - (?<=\d{3}...)(?<!999)foo -</PRE> -</P> -<P> -This time the first assertion looks at the preceding six characters, checking -that the first three are digits, and then the second assertion checks that the -preceding three characters are not "999". -</P> -<P> -Assertions can be nested in any combination. For example, -</P> -<P> -<pre> - (?<=(?<!foo)bar)baz -</PRE> -</P> -<P> -matches an occurrence of "baz" that is preceded by "bar" which in turn is not -preceded by "foo", while -</P> -<P> -<pre> - (?<=\d{3}(?!999)...)foo -</PRE> -</P> -<P> -is another pattern which matches "foo" preceded by three digits and any three -characters that are not "999". -</P> -<P> -Assertion subpatterns are not capturing subpatterns, and may not be repeated, -because it makes no sense to assert the same thing several times. If any kind -of assertion contains capturing subpatterns within it, these are counted for -the purposes of numbering the capturing subpatterns in the whole pattern. -However, substring capturing is carried out only for positive assertions, -because it does not make sense for negative assertions. -</P> -<br><a name="SEC16" href="#TOC1">CONDITIONAL SUBPATTERNS</a><br> -<P> -It is possible to cause the matching process to obey a subpattern -conditionally or to choose between two alternative subpatterns, depending on -the result of an assertion, or whether a previous capturing subpattern matched -or not. The two possible forms of conditional subpattern are -</P> -<P> -<pre> - (?(condition)yes-pattern) - (?(condition)yes-pattern|no-pattern) -</PRE> -</P> -<P> -If the condition is satisfied, the yes-pattern is used; otherwise the -no-pattern (if present) is used. If there are more than two alternatives in the -subpattern, a compile-time error occurs. -</P> -<P> -There are three kinds of condition. If the text between the parentheses -consists of a sequence of digits, the condition is satisfied if the capturing -subpattern of that number has previously matched. The number must be greater -than zero. Consider the following pattern, which contains non-significant white -space to make it more readable (assume the PCRE_EXTENDED option) and to divide -it into three parts for ease of discussion: -</P> -<P> -<pre> - ( \( )? [^()]+ (?(1) \) ) -</PRE> -</P> -<P> -The first part matches an optional opening parenthesis, and if that -character is present, sets it as the first captured substring. The second part -matches one or more characters that are not parentheses. The third part is a -conditional subpattern that tests whether the first set of parentheses matched -or not. If they did, that is, if subject started with an opening parenthesis, -the condition is true, and so the yes-pattern is executed and a closing -parenthesis is required. Otherwise, since no-pattern is not present, the -subpattern matches nothing. In other words, this pattern matches a sequence of -non-parentheses, optionally enclosed in parentheses. -</P> -<P> -If the condition is the string (R), it is satisfied if a recursive call to the -pattern or subpattern has been made. At "top level", the condition is false. -This is a PCRE extension. Recursive patterns are described in the next section. -</P> -<P> -If the condition is not a sequence of digits or (R), it must be an assertion. -This may be a positive or negative lookahead or lookbehind assertion. Consider -this pattern, again containing non-significant white space, and with the two -alternatives on the second line: -</P> -<P> -<pre> - (?(?=[^a-z]*[a-z]) - \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) -</PRE> -</P> -<P> -The condition is a positive lookahead assertion that matches an optional -sequence of non-letters followed by a letter. In other words, it tests for the -presence of at least one letter in the subject. If a letter is found, the -subject is matched against the first alternative; otherwise it is matched -against the second. This pattern matches strings in one of the two forms -dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. -</P> -<br><a name="SEC17" href="#TOC1">COMMENTS</a><br> -<P> -The sequence (?# marks the start of a comment which continues up to the next -closing parenthesis. Nested parentheses are not permitted. The characters -that make up a comment play no part in the pattern matching at all. -</P> -<P> -If the PCRE_EXTENDED option is set, an unescaped # character outside a -character class introduces a comment that continues up to the next newline -character in the pattern. -</P> -<br><a name="SEC18" href="#TOC1">RECURSIVE PATTERNS</a><br> -<P> -Consider the problem of matching a string in parentheses, allowing for -unlimited nested parentheses. Without the use of recursion, the best that can -be done is to use a pattern that matches up to some fixed depth of nesting. It -is not possible to handle an arbitrary nesting depth. Perl has provided an -experimental facility that allows regular expressions to recurse (amongst other -things). It does this by interpolating Perl code in the expression at run time, -and the code can refer to the expression itself. A Perl pattern to solve the -parentheses problem can be created like this: -</P> -<P> -<pre> - $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x; -</PRE> -</P> -<P> -The (?p{...}) item interpolates Perl code at run time, and in this case refers -recursively to the pattern in which it appears. Obviously, PCRE cannot support -the interpolation of Perl code. Instead, it supports some special syntax for -recursion of the entire pattern, and also for individual subpattern recursion. -</P> -<P> -The special item that consists of (? followed by a number greater than zero and -a closing parenthesis is a recursive call of the subpattern of the given -number, provided that it occurs inside that subpattern. (If not, it is a -"subroutine" call, which is described in the next section.) The special item -(?R) is a recursive call of the entire regular expression. -</P> -<P> -For example, this PCRE pattern solves the nested parentheses problem (assume -the PCRE_EXTENDED option is set so that white space is ignored): -</P> -<P> -<pre> - \( ( (?>[^()]+) | (?R) )* \) -</PRE> -</P> -<P> -First it matches an opening parenthesis. Then it matches any number of -substrings which can either be a sequence of non-parentheses, or a recursive -match of the pattern itself (that is a correctly parenthesized substring). -Finally there is a closing parenthesis. -</P> -<P> -If this were part of a larger pattern, you would not want to recurse the entire -pattern, so instead you could use this: -</P> -<P> -<pre> - ( \( ( (?>[^()]+) | (?1) )* \) ) -</PRE> -</P> -<P> -We have put the pattern into parentheses, and caused the recursion to refer to -them instead of the whole pattern. In a larger pattern, keeping track of -parenthesis numbers can be tricky. It may be more convenient to use named -parentheses instead. For this, PCRE uses (?P>name), which is an extension to -the Python syntax that PCRE uses for named parentheses (Perl does not provide -named parentheses). We could rewrite the above example as follows: -</P> -<P> -<pre> - (?P<pn> \( ( (?>[^()]+) | (?P>pn) )* \) ) -</PRE> -</P> -<P> -This particular example pattern contains nested unlimited repeats, and so the -use of atomic grouping for matching strings of non-parentheses is important -when applying the pattern to strings that do not match. For example, when this -pattern is applied to -</P> -<P> -<pre> - (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() -</PRE> -</P> -<P> -it yields "no match" quickly. However, if atomic grouping is not used, -the match runs for a very long time indeed because there are so many different -ways the + and * repeats can carve up the subject, and all have to be tested -before failure can be reported. -</P> -<P> -At the end of a match, the values set for any capturing subpatterns are those -from the outermost level of the recursion at which the subpattern value is set. -If you want to obtain intermediate values, a callout function can be used (see -below and the -<a href="pcrecallout.html"><b>pcrecallout</b></a> -documentation). If the pattern above is matched against -</P> -<P> -<pre> - (ab(cd)ef) -</PRE> -</P> -<P> -the value for the capturing parentheses is "ef", which is the last value taken -on at the top level. If additional parentheses are added, giving -</P> -<P> -<pre> - \( ( ( (?>[^()]+) | (?R) )* ) \) - ^ ^ - ^ ^ -</PRE> -</P> -<P> -the string they capture is "ab(cd)ef", the contents of the top level -parentheses. If there are more than 15 capturing parentheses in a pattern, PCRE -has to obtain extra memory to store data during a recursion, which it does by -using <b>pcre_malloc</b>, freeing it via <b>pcre_free</b> afterwards. If no -memory can be obtained, the match fails with the PCRE_ERROR_NOMEMORY error. -</P> -<P> -Do not confuse the (?R) item with the condition (R), which tests for recursion. -Consider this pattern, which matches text in angle brackets, allowing for -arbitrary nesting. Only digits are allowed in nested brackets (that is, when -recursing), whereas any characters are permitted at the outer level. -</P> -<P> -<pre> - < (?: (?(R) \d++ | [^<>]*+) | (?R)) * > -</PRE> -</P> -<P> -In this pattern, (?(R) is the start of a conditional subpattern, with two -different alternatives for the recursive and non-recursive cases. The (?R) item -is the actual recursive call. -</P> -<a name="subpatternsassubroutines"></a><br><a name="SEC19" href="#TOC1">SUBPATTERNS AS SUBROUTINES</a><br> -<P> -If the syntax for a recursive subpattern reference (either by number or by -name) is used outside the parentheses to which it refers, it operates like a -subroutine in a programming language. An earlier example pointed out that the -pattern -</P> -<P> -<pre> - (sens|respons)e and \1ibility -</PRE> -</P> -<P> -matches "sense and sensibility" and "response and responsibility", but not -"sense and responsibility". If instead the pattern -</P> -<P> -<pre> - (sens|respons)e and (?1)ibility -</PRE> -</P> -<P> -is used, it does match "sense and responsibility" as well as the other two -strings. Such references must, however, follow the subpattern to which they -refer. -</P> -<br><a name="SEC20" href="#TOC1">CALLOUTS</a><br> -<P> -Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl -code to be obeyed in the middle of matching a regular expression. This makes it -possible, amongst other things, to extract different substrings that match the -same pair of parentheses when there is a repetition. -</P> -<P> -PCRE provides a similar feature, but of course it cannot obey arbitrary Perl -code. The feature is called "callout". The caller of PCRE provides an external -function by putting its entry point in the global variable <i>pcre_callout</i>. -By default, this variable contains NULL, which disables all calling out. -</P> -<P> -Within a regular expression, (?C) indicates the points at which the external -function is to be called. If you want to identify different callout points, you -can put a number less than 256 after the letter C. The default value is zero. -For example, this pattern has two callout points: -</P> -<P> -<pre> - (?C1)\dabc(?C2)def -</PRE> -</P> -<P> -During matching, when PCRE reaches a callout point (and <i>pcre_callout</i> is -set), the external function is called. It is provided with the number of the -callout, and, optionally, one item of data originally supplied by the caller of -<b>pcre_exec()</b>. The callout function may cause matching to backtrack, or to -fail altogether. A complete description of the interface to the callout -function is given in the -<a href="pcrecallout.html"><b>pcrecallout</b></a> -documentation. -</P> -<P> -Last updated: 03 February 2003 -<br> -Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcreperform.html b/external-libs/pcre/doc/html/pcreperform.html deleted file mode 100644 index 418ac6d4..00000000 --- a/external-libs/pcre/doc/html/pcreperform.html +++ /dev/null @@ -1,93 +0,0 @@ -<html> -<head> -<title>pcreperform specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<ul> -<li><a name="TOC1" href="#SEC1">PCRE PERFORMANCE</a> -</ul> -<br><a name="SEC1" href="#TOC1">PCRE PERFORMANCE</a><br> -<P> -Certain items that may appear in regular expression patterns are more efficient -than others. It is more efficient to use a character class like [aeiou] than a -set of alternatives such as (a|e|i|o|u). In general, the simplest construction -that provides the required behaviour is usually the most efficient. Jeffrey -Friedl's book contains a lot of discussion about optimizing regular expressions -for efficient performance. -</P> -<P> -When a pattern begins with .* not in parentheses, or in parentheses that are -not the subject of a backreference, and the PCRE_DOTALL option is set, the -pattern is implicitly anchored by PCRE, since it can match only at the start of -a subject string. However, if PCRE_DOTALL is not set, PCRE cannot make this -optimization, because the . metacharacter does not then match a newline, and if -the subject string contains newlines, the pattern may match from the character -immediately following one of them instead of from the very start. For example, -the pattern -</P> -<P> -<pre> - .*second -</PRE> -</P> -<P> -matches the subject "first\nand second" (where \n stands for a newline -character), with the match starting at the seventh character. In order to do -this, PCRE has to retry the match starting after every newline in the subject. -</P> -<P> -If you are using such a pattern with subject strings that do not contain -newlines, the best performance is obtained by setting PCRE_DOTALL, or starting -the pattern with ^.* to indicate explicit anchoring. That saves PCRE from -having to scan along the subject looking for a newline to restart at. -</P> -<P> -Beware of patterns that contain nested indefinite repeats. These can take a -long time to run when applied to a string that does not match. Consider the -pattern fragment -</P> -<P> -<pre> - (a+)* -</PRE> -</P> -<P> -This can match "aaaa" in 33 different ways, and this number increases very -rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 -times, and for each of those cases other than 0, the + repeats can match -different numbers of times.) When the remainder of the pattern is such that the -entire match is going to fail, PCRE has in principle to try every possible -variation, and this can take an extremely long time. -</P> -<P> -An optimization catches some of the more simple cases such as -</P> -<P> -<pre> - (a+)*b -</PRE> -</P> -<P> -where a literal character follows. Before embarking on the standard matching -procedure, PCRE checks that there is a "b" later in the subject string, and if -there is not, it fails the match immediately. However, when there is no -following literal this optimization cannot be used. You can see the difference -by comparing the behaviour of -</P> -<P> -<pre> - (a+)*\d -</PRE> -</P> -<P> -with the pattern above. The former gives a failure almost instantly when -applied to a whole line of "a" characters, whereas the latter takes an -appreciable time with strings longer than about 20 characters. -</P> -<P> -Last updated: 03 February 2003 -<br> -Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcreposix.html b/external-libs/pcre/doc/html/pcreposix.html deleted file mode 100644 index d0a5e127..00000000 --- a/external-libs/pcre/doc/html/pcreposix.html +++ /dev/null @@ -1,237 +0,0 @@ -<html> -<head> -<title>pcreposix specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<ul> -<li><a name="TOC1" href="#SEC1">SYNOPSIS OF POSIX API</a> -<li><a name="TOC2" href="#SEC2">DESCRIPTION</a> -<li><a name="TOC3" href="#SEC3">COMPILING A PATTERN</a> -<li><a name="TOC4" href="#SEC4">MATCHING NEWLINE CHARACTERS</a> -<li><a name="TOC5" href="#SEC5">MATCHING A PATTERN</a> -<li><a name="TOC6" href="#SEC6">ERROR MESSAGES</a> -<li><a name="TOC7" href="#SEC7">STORAGE</a> -<li><a name="TOC8" href="#SEC8">AUTHOR</a> -</ul> -<br><a name="SEC1" href="#TOC1">SYNOPSIS OF POSIX API</a><br> -<P> -<b>#include <pcreposix.h></b> -</P> -<P> -<b>int regcomp(regex_t *<i>preg</i>, const char *<i>pattern</i>,</b> -<b>int <i>cflags</i>);</b> -</P> -<P> -<b>int regexec(regex_t *<i>preg</i>, const char *<i>string</i>,</b> -<b>size_t <i>nmatch</i>, regmatch_t <i>pmatch</i>[], int <i>eflags</i>);</b> -</P> -<P> -<b>size_t regerror(int <i>errcode</i>, const regex_t *<i>preg</i>,</b> -<b>char *<i>errbuf</i>, size_t <i>errbuf_size</i>);</b> -</P> -<P> -<b>void regfree(regex_t *<i>preg</i>);</b> -</P> -<br><a name="SEC2" href="#TOC1">DESCRIPTION</a><br> -<P> -This set of functions provides a POSIX-style API to the PCRE regular expression -package. See the -<a href="pcreapi.html"><b>pcreapi</b></a> -documentation for a description of the native API, which contains additional -functionality. -</P> -<P> -The functions described here are just wrapper functions that ultimately call -the PCRE native API. Their prototypes are defined in the <b>pcreposix.h</b> -header file, and on Unix systems the library itself is called -<b>pcreposix.a</b>, so can be accessed by adding <b>-lpcreposix</b> to the -command for linking an application which uses them. Because the POSIX functions -call the native ones, it is also necessary to add \fR-lpcre\fR. -</P> -<P> -I have implemented only those option bits that can be reasonably mapped to PCRE -native options. In addition, the options REG_EXTENDED and REG_NOSUB are defined -with the value zero. They have no effect, but since programs that are written -to the POSIX interface often use them, this makes it easier to slot in PCRE as -a replacement library. Other POSIX options are not even defined. -</P> -<P> -When PCRE is called via these functions, it is only the API that is POSIX-like -in style. The syntax and semantics of the regular expressions themselves are -still those of Perl, subject to the setting of various PCRE options, as -described below. "POSIX-like in style" means that the API approximates to the -POSIX definition; it is not fully POSIX-compatible, and in multi-byte encoding -domains it is probably even less compatible. -</P> -<P> -The header for these functions is supplied as <b>pcreposix.h</b> to avoid any -potential clash with other POSIX libraries. It can, of course, be renamed or -aliased as <b>regex.h</b>, which is the "correct" name. It provides two -structure types, <i>regex_t</i> for compiled internal forms, and -<i>regmatch_t</i> for returning captured substrings. It also defines some -constants whose names start with "REG_"; these are used for setting options and -identifying error codes. -</P> -<br><a name="SEC3" href="#TOC1">COMPILING A PATTERN</a><br> -<P> -The function <b>regcomp()</b> is called to compile a pattern into an -internal form. The pattern is a C string terminated by a binary zero, and -is passed in the argument <i>pattern</i>. The <i>preg</i> argument is a pointer -to a regex_t structure which is used as a base for storing information about -the compiled expression. -</P> -<P> -The argument <i>cflags</i> is either zero, or contains one or more of the bits -defined by the following macros: -</P> -<P> -<pre> - REG_ICASE -</PRE> -</P> -<P> -The PCRE_CASELESS option is set when the expression is passed for compilation -to the native function. -</P> -<P> -<pre> - REG_NEWLINE -</PRE> -</P> -<P> -The PCRE_MULTILINE option is set when the expression is passed for compilation -to the native function. Note that this does <i>not</i> mimic the defined POSIX -behaviour for REG_NEWLINE (see the following section). -</P> -<P> -In the absence of these flags, no options are passed to the native function. -This means the the regex is compiled with PCRE default semantics. In -particular, the way it handles newline characters in the subject string is the -Perl way, not the POSIX way. Note that setting PCRE_MULTILINE has only -<i>some</i> of the effects specified for REG_NEWLINE. It does not affect the way -newlines are matched by . (they aren't) or by a negative class such as [^a] -(they are). -</P> -<P> -The yield of <b>regcomp()</b> is zero on success, and non-zero otherwise. The -<i>preg</i> structure is filled in on success, and one member of the structure -is public: <i>re_nsub</i> contains the number of capturing subpatterns in -the regular expression. Various error codes are defined in the header file. -</P> -<br><a name="SEC4" href="#TOC1">MATCHING NEWLINE CHARACTERS</a><br> -<P> -This area is not simple, because POSIX and Perl take different views of things. -It is not possible to get PCRE to obey POSIX semantics, but then PCRE was never -intended to be a POSIX engine. The following table lists the different -possibilities for matching newline characters in PCRE: -</P> -<P> -<pre> - Default Change with -</PRE> -</P> -<P> -<pre> - . matches newline no PCRE_DOTALL - newline matches [^a] yes not changeable - $ matches \n at end yes PCRE_DOLLARENDONLY - $ matches \n in middle no PCRE_MULTILINE - ^ matches \n in middle no PCRE_MULTILINE -</PRE> -</P> -<P> -This is the equivalent table for POSIX: -</P> -<P> -<pre> - Default Change with -</PRE> -</P> -<P> -<pre> - . matches newline yes REG_NEWLINE - newline matches [^a] yes REG_NEWLINE - $ matches \n at end no REG_NEWLINE - $ matches \n in middle no REG_NEWLINE - ^ matches \n in middle no REG_NEWLINE -</PRE> -</P> -<P> -PCRE's behaviour is the same as Perl's, except that there is no equivalent for -PCRE_DOLLARENDONLY in Perl. In both PCRE and Perl, there is no way to stop -newline from matching [^a]. -</P> -<P> -The default POSIX newline handling can be obtained by setting PCRE_DOTALL and -PCRE_DOLLARENDONLY, but there is no way to make PCRE behave exactly as for the -REG_NEWLINE action. -</P> -<br><a name="SEC5" href="#TOC1">MATCHING A PATTERN</a><br> -<P> -The function <b>regexec()</b> is called to match a pre-compiled pattern -<i>preg</i> against a given <i>string</i>, which is terminated by a zero byte, -subject to the options in <i>eflags</i>. These can be: -</P> -<P> -<pre> - REG_NOTBOL -</PRE> -</P> -<P> -The PCRE_NOTBOL option is set when calling the underlying PCRE matching -function. -</P> -<P> -<pre> - REG_NOTEOL -</PRE> -</P> -<P> -The PCRE_NOTEOL option is set when calling the underlying PCRE matching -function. -</P> -<P> -The portion of the string that was matched, and also any captured substrings, -are returned via the <i>pmatch</i> argument, which points to an array of -<i>nmatch</i> structures of type <i>regmatch_t</i>, containing the members -<i>rm_so</i> and <i>rm_eo</i>. These contain the offset to the first character of -each substring and the offset to the first character after the end of each -substring, respectively. The 0th element of the vector relates to the entire -portion of <i>string</i> that was matched; subsequent elements relate to the -capturing subpatterns of the regular expression. Unused entries in the array -have both structure members set to -1. -</P> -<P> -A successful match yields a zero return; various error codes are defined in the -header file, of which REG_NOMATCH is the "expected" failure code. -</P> -<br><a name="SEC6" href="#TOC1">ERROR MESSAGES</a><br> -<P> -The <b>regerror()</b> function maps a non-zero errorcode from either -<b>regcomp()</b> or <b>regexec()</b> to a printable message. If <i>preg</i> is not -NULL, the error should have arisen from the use of that structure. A message -terminated by a binary zero is placed in <i>errbuf</i>. The length of the -message, including the zero, is limited to <i>errbuf_size</i>. The yield of the -function is the size of buffer needed to hold the whole message. -</P> -<br><a name="SEC7" href="#TOC1">STORAGE</a><br> -<P> -Compiling a regular expression causes memory to be allocated and associated -with the <i>preg</i> structure. The function <b>regfree()</b> frees all such -memory, after which <i>preg</i> may no longer be used as a compiled expression. -</P> -<br><a name="SEC8" href="#TOC1">AUTHOR</a><br> -<P> -Philip Hazel <ph10@cam.ac.uk> -<br> -University Computing Service, -<br> -Cambridge CB2 3QG, England. -</P> -<P> -Last updated: 03 February 2003 -<br> -Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcresample.html b/external-libs/pcre/doc/html/pcresample.html deleted file mode 100644 index fed41f62..00000000 --- a/external-libs/pcre/doc/html/pcresample.html +++ /dev/null @@ -1,79 +0,0 @@ -<html> -<head> -<title>pcresample specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<ul> -<li><a name="TOC1" href="#SEC1">PCRE SAMPLE PROGRAM</a> -</ul> -<br><a name="SEC1" href="#TOC1">PCRE SAMPLE PROGRAM</a><br> -<P> -A simple, complete demonstration program, to get you started with using PCRE, -is supplied in the file <i>pcredemo.c</i> in the PCRE distribution. -</P> -<P> -The program compiles the regular expression that is its first argument, and -matches it against the subject string in its second argument. No PCRE options -are set, and default character tables are used. If matching succeeds, the -program outputs the portion of the subject that matched, together with the -contents of any captured substrings. -</P> -<P> -If the -g option is given on the command line, the program then goes on to -check for further matches of the same regular expression in the same subject -string. The logic is a little bit tricky because of the possibility of matching -an empty string. Comments in the code explain what is going on. -</P> -<P> -On a Unix system that has PCRE installed in <i>/usr/local</i>, you can compile -the demonstration program using a command like this: -</P> -<P> -<pre> - gcc -o pcredemo pcredemo.c -I/usr/local/include \ - -L/usr/local/lib -lpcre -</PRE> -</P> -<P> -Then you can run simple tests like this: -</P> -<P> -<pre> - ./pcredemo 'cat|dog' 'the cat sat on the mat' - ./pcredemo -g 'cat|dog' 'the dog sat on the cat' -</PRE> -</P> -<P> -Note that there is a much more comprehensive test program, called -<b>pcretest</b>, which supports many more facilities for testing regular -expressions and the PCRE library. The <b>pcredemo</b> program is provided as a -simple coding example. -</P> -<P> -On some operating systems (e.g. Solaris) you may get an error like this when -you try to run <b>pcredemo</b>: -</P> -<P> -<pre> - ld.so.1: a.out: fatal: libpcre.so.0: open failed: No such file or directory -</PRE> -</P> -<P> -This is caused by the way shared library support works on those systems. You -need to add -</P> -<P> -<pre> - -R/usr/local/lib -</PRE> -</P> -<P> -to the compile command to get round this problem. -</P> -<P> -Last updated: 28 January 2003 -<br> -Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcretest.html b/external-libs/pcre/doc/html/pcretest.html deleted file mode 100644 index 2ba9893d..00000000 --- a/external-libs/pcre/doc/html/pcretest.html +++ /dev/null @@ -1,443 +0,0 @@ -<html> -<head> -<title>pcretest specification</title> -</head> -<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB"> -This HTML document has been generated automatically from the original man page. -If there is any nonsense in it, please consult the man page, in case the -conversion went wrong.<br> -<ul> -<li><a name="TOC1" href="#SEC1">SYNOPSIS</a> -<li><a name="TOC2" href="#SEC2">OPTIONS</a> -<li><a name="TOC3" href="#SEC3">DESCRIPTION</a> -<li><a name="TOC4" href="#SEC4">PATTERN MODIFIERS</a> -<li><a name="TOC5" href="#SEC5">CALLOUTS</a> -<li><a name="TOC6" href="#SEC6">DATA LINES</a> -<li><a name="TOC7" href="#SEC7">OUTPUT FROM PCRETEST</a> -<li><a name="TOC8" href="#SEC8">AUTHOR</a> -</ul> -<br><a name="SEC1" href="#TOC1">SYNOPSIS</a><br> -<P> -<b>pcretest [-d] [-i] [-m] [-o osize] [-p] [-t] [source] [destination]</b> -</P> -<P> -<b>pcretest</b> was written as a test program for the PCRE regular expression -library itself, but it can also be used for experimenting with regular -expressions. This document describes the features of the test program; for -details of the regular expressions themselves, see the -<a href="pcrepattern.html"><b>pcrepattern</b></a> -documentation. For details of PCRE and its options, see the -<a href="pcreapi.html"><b>pcreapi</b></a> -documentation. -</P> -<br><a name="SEC2" href="#TOC1">OPTIONS</a><br> -<P> -<b>-C</b> -Output the version number of the PCRE library, and all available information -about the optional features that are included, and then exit. -</P> -<P> -<b>-d</b> -Behave as if each regex had the <b>/D</b> modifier (see below); the internal -form is output after compilation. -</P> -<P> -<b>-i</b> -Behave as if each regex had the <b>/I</b> modifier; information about the -compiled pattern is given after compilation. -</P> -<P> -<b>-m</b> -Output the size of each compiled pattern after it has been compiled. This is -equivalent to adding /M to each regular expression. For compatibility with -earlier versions of pcretest, <b>-s</b> is a synonym for <b>-m</b>. -</P> -<P> -<b>-o</b> <i>osize</i> -Set the number of elements in the output vector that is used when calling PCRE -to be <i>osize</i>. The default value is 45, which is enough for 14 capturing -subexpressions. The vector size can be changed for individual matching calls by -including \O in the data line (see below). -</P> -<P> -<b>-p</b> -Behave as if each regex has <b>/P</b> modifier; the POSIX wrapper API is used -to call PCRE. None of the other options has any effect when <b>-p</b> is set. -</P> -<P> -<b>-t</b> -Run each compile, study, and match many times with a timer, and output -resulting time per compile or match (in milliseconds). Do not set <b>-t</b> with -<b>-m</b>, because you will then get the size output 20000 times and the timing -will be distorted. -</P> -<br><a name="SEC3" href="#TOC1">DESCRIPTION</a><br> -<P> -If <b>pcretest</b> is given two filename arguments, it reads from the first and -writes to the second. If it is given only one filename argument, it reads from -that file and writes to stdout. Otherwise, it reads from stdin and writes to -stdout, and prompts for each line of input, using "re>" to prompt for regular -expressions, and "data>" to prompt for data lines. -</P> -<P> -The program handles any number of sets of input on a single input file. Each -set starts with a regular expression, and continues with any number of data -lines to be matched against the pattern. -</P> -<P> -Each line is matched separately and independently. If you want to do -multiple-line matches, you have to use the \n escape sequence in a single line -of input to encode the newline characters. The maximum length of data line is -30,000 characters. -</P> -<P> -An empty line signals the end of the data lines, at which point a new regular -expression is read. The regular expressions are given enclosed in any -non-alphameric delimiters other than backslash, for example -</P> -<P> -<pre> - /(a|bc)x+yz/ -</PRE> -</P> -<P> -White space before the initial delimiter is ignored. A regular expression may -be continued over several input lines, in which case the newline characters are -included within it. It is possible to include the delimiter within the pattern -by escaping it, for example -</P> -<P> -<pre> - /abc\/def/ -</PRE> -</P> -<P> -If you do so, the escape and the delimiter form part of the pattern, but since -delimiters are always non-alphameric, this does not affect its interpretation. -If the terminating delimiter is immediately followed by a backslash, for -example, -</P> -<P> -<pre> - /abc/\ -</PRE> -</P> -<P> -then a backslash is added to the end of the pattern. This is done to provide a -way of testing the error condition that arises if a pattern finishes with a -backslash, because -</P> -<P> -<pre> - /abc\/ -</PRE> -</P> -<P> -is interpreted as the first line of a pattern that starts with "abc/", causing -pcretest to read the next line as a continuation of the regular expression. -</P> -<br><a name="SEC4" href="#TOC1">PATTERN MODIFIERS</a><br> -<P> -The pattern may be followed by <b>i</b>, <b>m</b>, <b>s</b>, or <b>x</b> to set the -PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, or PCRE_EXTENDED options, -respectively. For example: -</P> -<P> -<pre> - /caseless/i -</PRE> -</P> -<P> -These modifier letters have the same effect as they do in Perl. There are -others that set PCRE options that do not correspond to anything in Perl: -<b>/A</b>, <b>/E</b>, <b>/N</b>, <b>/U</b>, and <b>/X</b> set PCRE_ANCHORED, -PCRE_DOLLAR_ENDONLY, PCRE_NO_AUTO_CAPTURE, PCRE_UNGREEDY, and PCRE_EXTRA -respectively. -</P> -<P> -Searching for all possible matches within each subject string can be requested -by the <b>/g</b> or <b>/G</b> modifier. After finding a match, PCRE is called -again to search the remainder of the subject string. The difference between -<b>/g</b> and <b>/G</b> is that the former uses the <i>startoffset</i> argument to -<b>pcre_exec()</b> to start searching at a new point within the entire string -(which is in effect what Perl does), whereas the latter passes over a shortened -substring. This makes a difference to the matching process if the pattern -begins with a lookbehind assertion (including \b or \B). -</P> -<P> -If any call to <b>pcre_exec()</b> in a <b>/g</b> or <b>/G</b> sequence matches an -empty string, the next call is done with the PCRE_NOTEMPTY and PCRE_ANCHORED -flags set in order to search for another, non-empty, match at the same point. -If this second match fails, the start offset is advanced by one, and the normal -match is retried. This imitates the way Perl handles such cases when using the -<b>/g</b> modifier or the <b>split()</b> function. -</P> -<P> -There are a number of other modifiers for controlling the way <b>pcretest</b> -operates. -</P> -<P> -The <b>/+</b> modifier requests that as well as outputting the substring that -matched the entire pattern, pcretest should in addition output the remainder of -the subject string. This is useful for tests where the subject contains -multiple copies of the same substring. -</P> -<P> -The <b>/L</b> modifier must be followed directly by the name of a locale, for -example, -</P> -<P> -<pre> - /pattern/Lfr -</PRE> -</P> -<P> -For this reason, it must be the last modifier letter. The given locale is set, -<b>pcre_maketables()</b> is called to build a set of character tables for the -locale, and this is then passed to <b>pcre_compile()</b> when compiling the -regular expression. Without an <b>/L</b> modifier, NULL is passed as the tables -pointer; that is, <b>/L</b> applies only to the expression on which it appears. -</P> -<P> -The <b>/I</b> modifier requests that <b>pcretest</b> output information about the -compiled expression (whether it is anchored, has a fixed first character, and -so on). It does this by calling <b>pcre_fullinfo()</b> after compiling an -expression, and outputting the information it gets back. If the pattern is -studied, the results of that are also output. -</P> -<P> -The <b>/D</b> modifier is a PCRE debugging feature, which also assumes <b>/I</b>. -It causes the internal form of compiled regular expressions to be output after -compilation. If the pattern was studied, the information returned is also -output. -</P> -<P> -The <b>/S</b> modifier causes <b>pcre_study()</b> to be called after the -expression has been compiled, and the results used when the expression is -matched. -</P> -<P> -The <b>/M</b> modifier causes the size of memory block used to hold the compiled -pattern to be output. -</P> -<P> -The <b>/P</b> modifier causes <b>pcretest</b> to call PCRE via the POSIX wrapper -API rather than its native API. When this is done, all other modifiers except -<b>/i</b>, <b>/m</b>, and <b>/+</b> are ignored. REG_ICASE is set if <b>/i</b> is -present, and REG_NEWLINE is set if <b>/m</b> is present. The wrapper functions -force PCRE_DOLLAR_ENDONLY always, and PCRE_DOTALL unless REG_NEWLINE is set. -</P> -<P> -The <b>/8</b> modifier causes <b>pcretest</b> to call PCRE with the PCRE_UTF8 -option set. This turns on support for UTF-8 character handling in PCRE, -provided that it was compiled with this support enabled. This modifier also -causes any non-printing characters in output strings to be printed using the -\x{hh...} notation if they are valid UTF-8 sequences. -</P> -<P> -If the <b>/?</b> modifier is used with <b>/8</b>, it causes <b>pcretest</b> to -call <b>pcre_compile()</b> with the PCRE_NO_UTF8_CHECK option, to suppress the -checking of the string for UTF-8 validity. -</P> -<br><a name="SEC5" href="#TOC1">CALLOUTS</a><br> -<P> -If the pattern contains any callout requests, <b>pcretest</b>'s callout function -will be called. By default, it displays the callout number, and the start and -current positions in the text at the callout time. For example, the output -</P> -<P> -<pre> - --->pqrabcdef - 0 ^ ^ -</PRE> -</P> -<P> -indicates that callout number 0 occurred for a match attempt starting at the -fourth character of the subject string, when the pointer was at the seventh -character. The callout function returns zero (carry on matching) by default. -</P> -<P> -Inserting callouts may be helpful when using <b>pcretest</b> to check -complicated regular expressions. For further information about callouts, see -the -<a href="pcrecallout.html"><b>pcrecallout</b></a> -documentation. -</P> -<P> -For testing the PCRE library, additional control of callout behaviour is -available via escape sequences in the data, as described in the following -section. In particular, it is possible to pass in a number as callout data (the -default is zero). If the callout function receives a non-zero number, it -returns that value instead of zero. -</P> -<br><a name="SEC6" href="#TOC1">DATA LINES</a><br> -<P> -Before each data line is passed to <b>pcre_exec()</b>, leading and trailing -whitespace is removed, and it is then scanned for \ escapes. Some of these are -pretty esoteric features, intended for checking out some of the more -complicated features of PCRE. If you are just testing "ordinary" regular -expressions, you probably don't need any of these. The following escapes are -recognized: -</P> -<P> -<pre> - \a alarm (= BEL) - \b backspace - \e escape - \f formfeed - \n newline - \r carriage return - \t tab - \v vertical tab - \nnn octal character (up to 3 octal digits) - \xhh hexadecimal character (up to 2 hex digits) - \x{hh...} hexadecimal character, any number of digits - in UTF-8 mode - \A pass the PCRE_ANCHORED option to <b>pcre_exec()</b> - \B pass the PCRE_NOTBOL option to <b>pcre_exec()</b> - \Cdd call pcre_copy_substring() for substring dd - after a successful match (any decimal number - less than 32) - \Cname call pcre_copy_named_substring() for substring - "name" after a successful match (name termin- - ated by next non alphanumeric character) - \C+ show the current captured substrings at callout - time - \C- do not supply a callout function - \C!n return 1 instead of 0 when callout number n is - reached - \C!n!m return 1 instead of 0 when callout number n is - reached for the nth time - \C*n pass the number n (may be negative) as callout - data - \Gdd call pcre_get_substring() for substring dd - after a successful match (any decimal number - less than 32) - \Gname call pcre_get_named_substring() for substring - "name" after a successful match (name termin- - ated by next non-alphanumeric character) - \L call pcre_get_substringlist() after a - successful match - \M discover the minimum MATCH_LIMIT setting - \N pass the PCRE_NOTEMPTY option to <b>pcre_exec()</b> - \Odd set the size of the output vector passed to - <b>pcre_exec()</b> to dd (any number of decimal - digits) - \S output details of memory get/free calls during matching - \Z pass the PCRE_NOTEOL option to <b>pcre_exec()</b> - \? pass the PCRE_NO_UTF8_CHECK option to - <b>pcre_exec()</b> -</PRE> -</P> -<P> -If \M is present, <b>pcretest</b> calls <b>pcre_exec()</b> several times, with -different values in the <i>match_limit</i> field of the <b>pcre_extra</b> data -structure, until it finds the minimum number that is needed for -<b>pcre_exec()</b> to complete. This number is a measure of the amount of -recursion and backtracking that takes place, and checking it out can be -instructive. For most simple matches, the number is quite small, but for -patterns with very large numbers of matching possibilities, it can become large -very quickly with increasing length of subject string. -</P> -<P> -When \O is used, it may be higher or lower than the size set by the <b>-O</b> -option (or defaulted to 45); \O applies only to the call of <b>pcre_exec()</b> -for the line in which it appears. -</P> -<P> -A backslash followed by anything else just escapes the anything else. If the -very last character is a backslash, it is ignored. This gives a way of passing -an empty line as data, since a real empty line terminates the data input. -</P> -<P> -If <b>/P</b> was present on the regex, causing the POSIX wrapper API to be used, -only <b>\B</b>, and <b>\Z</b> have any effect, causing REG_NOTBOL and REG_NOTEOL -to be passed to <b>regexec()</b> respectively. -</P> -<P> -The use of \x{hh...} to represent UTF-8 characters is not dependent on the use -of the <b>/8</b> modifier on the pattern. It is recognized always. There may be -any number of hexadecimal digits inside the braces. The result is from one to -six bytes, encoded according to the UTF-8 rules. -</P> -<br><a name="SEC7" href="#TOC1">OUTPUT FROM PCRETEST</a><br> -<P> -When a match succeeds, pcretest outputs the list of captured substrings that -<b>pcre_exec()</b> returns, starting with number 0 for the string that matched -the whole pattern. Here is an example of an interactive pcretest run. -</P> -<P> -<pre> - $ pcretest - PCRE version 4.00 08-Jan-2003 -</PRE> -</P> -<P> -<pre> - re> /^abc(\d+)/ - data> abc123 - 0: abc123 - 1: 123 - data> xyz - No match -</PRE> -</P> -<P> -If the strings contain any non-printing characters, they are output as \0x -escapes, or as \x{...} escapes if the <b>/8</b> modifier was present on the -pattern. If the pattern has the <b>/+</b> modifier, then the output for -substring 0 is followed by the the rest of the subject string, identified by -"0+" like this: -</P> -<P> -<pre> - re> /cat/+ - data> cataract - 0: cat - 0+ aract -</PRE> -</P> -<P> -If the pattern has the <b>/g</b> or <b>/G</b> modifier, the results of successive -matching attempts are output in sequence, like this: -</P> -<P> -<pre> - re> /\Bi(\w\w)/g - data> Mississippi - 0: iss - 1: ss - 0: iss - 1: ss - 0: ipp - 1: pp -</PRE> -</P> -<P> -"No match" is output only if the first match attempt fails. -</P> -<P> -If any of the sequences <b>\C</b>, <b>\G</b>, or <b>\L</b> are present in a -data line that is successfully matched, the substrings extracted by the -convenience functions are output with C, G, or L after the string number -instead of a colon. This is in addition to the normal full list. The string -length (that is, the return from the extraction function) is given in -parentheses after each string for <b>\C</b> and <b>\G</b>. -</P> -<P> -Note that while patterns can be continued over several lines (a plain ">" -prompt is used for continuations), data lines may not. However newlines can be -included in data by means of the \n escape. -</P> -<br><a name="SEC8" href="#TOC1">AUTHOR</a><br> -<P> -Philip Hazel <ph10@cam.ac.uk> -<br> -University Computing Service, -<br> -Cambridge CB2 3QG, England. -</P> -<P> -Last updated: 09 December 2003 -<br> -Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/pcre.3 b/external-libs/pcre/doc/pcre.3 deleted file mode 100644 index c0c71419..00000000 --- a/external-libs/pcre/doc/pcre.3 +++ /dev/null @@ -1,174 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH DESCRIPTION -.rs -.sp -The PCRE library is a set of functions that implement regular expression -pattern matching using the same syntax and semantics as Perl, with just a few -differences. The current implementation of PCRE (release 4.x) corresponds -approximately with Perl 5.8, including support for UTF-8 encoded strings. -However, this support has to be explicitly enabled; it is not the default. - -PCRE is written in C and released as a C library. However, a number of people -have written wrappers and interfaces of various kinds. A C++ class is included -in these contributions, which can be found in the \fIContrib\fR directory at -the primary FTP site, which is: - -.\" HTML <a href="ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre"> -.\" </a> -ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre - -Details of exactly which Perl regular expression features are and are not -supported by PCRE are given in separate documents. See the -.\" HREF -\fBpcrepattern\fR -.\" -and -.\" HREF -\fBpcrecompat\fR -.\" -pages. - -Some features of PCRE can be included, excluded, or changed when the library is -built. The -.\" HREF -\fBpcre_config()\fR -.\" -function makes it possible for a client to discover which features are -available. Documentation about building PCRE for various operating systems can -be found in the \fBREADME\fR file in the source distribution. - -.SH USER DOCUMENTATION -.rs -.sp -The user documentation for PCRE has been split up into a number of different -sections. In the "man" format, each of these is a separate "man page". In the -HTML format, each is a separate page, linked from the index page. In the plain -text format, all the sections are concatenated, for ease of searching. The -sections are as follows: - - pcre this document - pcreapi details of PCRE's native API - pcrebuild options for building PCRE - pcrecallout details of the callout feature - pcrecompat discussion of Perl compatibility - pcregrep description of the \fBpcregrep\fR command - pcrepattern syntax and semantics of supported - regular expressions - pcreperform discussion of performance issues - pcreposix the POSIX-compatible API - pcresample discussion of the sample program - pcretest the \fBpcretest\fR testing command - -In addition, in the "man" and HTML formats, there is a short page for each -library function, listing its arguments and results. - -.SH LIMITATIONS -.rs -.sp -There are some size limitations in PCRE but it is hoped that they will never in -practice be relevant. - -The maximum length of a compiled pattern is 65539 (sic) bytes if PCRE is -compiled with the default internal linkage size of 2. If you want to process -regular expressions that are truly enormous, you can compile PCRE with an -internal linkage size of 3 or 4 (see the \fBREADME\fR file in the source -distribution and the -.\" HREF -\fBpcrebuild\fR -.\" -documentation for details). If these cases the limit is substantially larger. -However, the speed of execution will be slower. - -All values in repeating quantifiers must be less than 65536. -The maximum number of capturing subpatterns is 65535. - -There is no limit to the number of non-capturing subpatterns, but the maximum -depth of nesting of all kinds of parenthesized subpattern, including capturing -subpatterns, assertions, and other types of subpattern, is 200. - -The maximum length of a subject string is the largest positive number that an -integer variable can hold. However, PCRE uses recursion to handle subpatterns -and indefinite repetition. This means that the available stack space may limit -the size of a subject string that can be processed by certain patterns. - -.\" HTML <a name="utf8support"></a> -.SH UTF-8 SUPPORT -.rs -.sp -Starting at release 3.3, PCRE has had some support for character strings -encoded in the UTF-8 format. For release 4.0 this has been greatly extended to -cover most common requirements. - -In order process UTF-8 strings, you must build PCRE to include UTF-8 support in -the code, and, in addition, you must call -.\" HREF -\fBpcre_compile()\fR -.\" -with the PCRE_UTF8 option flag. When you do this, both the pattern and any -subject strings that are matched against it are treated as UTF-8 strings -instead of just strings of bytes. - -If you compile PCRE with UTF-8 support, but do not use it at run time, the -library will be a bit bigger, but the additional run time overhead is limited -to testing the PCRE_UTF8 flag in several places, so should not be very large. - -The following comments apply when PCRE is running in UTF-8 mode: - -1. When you set the PCRE_UTF8 flag, the strings passed as patterns and subjects -are checked for validity on entry to the relevant functions. If an invalid -UTF-8 string is passed, an error return is given. In some situations, you may -already know that your strings are valid, and therefore want to skip these -checks in order to improve performance. If you set the PCRE_NO_UTF8_CHECK flag -at compile time or at run time, PCRE assumes that the pattern or subject it -is given (respectively) contains only valid UTF-8 codes. In this case, it does -not diagnose an invalid UTF-8 string. If you pass an invalid UTF-8 string to -PCRE when PCRE_NO_UTF8_CHECK is set, the results are undefined. Your program -may crash. - -2. In a pattern, the escape sequence \\x{...}, where the contents of the braces -is a string of hexadecimal digits, is interpreted as a UTF-8 character whose -code number is the given hexadecimal number, for example: \\x{1234}. If a -non-hexadecimal digit appears between the braces, the item is not recognized. -This escape sequence can be used either as a literal, or within a character -class. - -3. The original hexadecimal escape sequence, \\xhh, matches a two-byte UTF-8 -character if the value is greater than 127. - -4. Repeat quantifiers apply to complete UTF-8 characters, not to individual -bytes, for example: \\x{100}{3}. - -5. The dot metacharacter matches one UTF-8 character instead of a single byte. - -6. The escape sequence \\C can be used to match a single byte in UTF-8 mode, -but its use can lead to some strange effects. - -7. The character escapes \\b, \\B, \\d, \\D, \\s, \\S, \\w, and \\W correctly -test characters of any code value, but the characters that PCRE recognizes as -digits, spaces, or word characters remain the same set as before, all with -values less than 256. - -8. Case-insensitive matching applies only to characters whose values are less -than 256. PCRE does not support the notion of "case" for higher-valued -characters. - -9. PCRE does not support the use of Unicode tables and properties or the Perl -escapes \\p, \\P, and \\X. - -.SH AUTHOR -.rs -.sp -Philip Hazel <ph10@cam.ac.uk> -.br -University Computing Service, -.br -Cambridge CB2 3QG, England. -.br -Phone: +44 1223 334714 - -.in 0 -Last updated: 20 August 2003 -.br -Copyright (c) 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/pcre.txt b/external-libs/pcre/doc/pcre.txt deleted file mode 100644 index 698baa52..00000000 --- a/external-libs/pcre/doc/pcre.txt +++ /dev/null @@ -1,3169 +0,0 @@ -This file contains a concatenation of the PCRE man pages, converted to plain -text format for ease of searching with a text editor, or for use on systems -that do not have a man page processor. The small individual files that give -synopses of each function in the library have not been included. There are -separate text files for the pcregrep and pcretest commands. ------------------------------------------------------------------------------ - -PCRE(3) PCRE(3) - - - -NAME - PCRE - Perl-compatible regular expressions - -DESCRIPTION - - The PCRE library is a set of functions that implement regular expres- - sion pattern matching using the same syntax and semantics as Perl, with - just a few differences. The current implementation of PCRE (release - 4.x) corresponds approximately with Perl 5.8, including support for - UTF-8 encoded strings. However, this support has to be explicitly - enabled; it is not the default. - - PCRE is written in C and released as a C library. However, a number of - people have written wrappers and interfaces of various kinds. A C++ - class is included in these contributions, which can be found in the - Contrib directory at the primary FTP site, which is: - - ftp://ftp.csx.cam.ac.uk/pub/software/programming/pcre - - Details of exactly which Perl regular expression features are and are - not supported by PCRE are given in separate documents. See the pcrepat- - tern and pcrecompat pages. - - Some features of PCRE can be included, excluded, or changed when the - library is built. The pcre_config() function makes it possible for a - client to discover which features are available. Documentation about - building PCRE for various operating systems can be found in the README - file in the source distribution. - - -USER DOCUMENTATION - - The user documentation for PCRE has been split up into a number of dif- - ferent sections. In the "man" format, each of these is a separate "man - page". In the HTML format, each is a separate page, linked from the - index page. In the plain text format, all the sections are concate- - nated, for ease of searching. The sections are as follows: - - pcre this document - pcreapi details of PCRE's native API - pcrebuild options for building PCRE - pcrecallout details of the callout feature - pcrecompat discussion of Perl compatibility - pcregrep description of the pcregrep command - pcrepattern syntax and semantics of supported - regular expressions - pcreperform discussion of performance issues - pcreposix the POSIX-compatible API - pcresample discussion of the sample program - pcretest the pcretest testing command - - In addition, in the "man" and HTML formats, there is a short page for - each library function, listing its arguments and results. - - -LIMITATIONS - - There are some size limitations in PCRE but it is hoped that they will - never in practice be relevant. - - The maximum length of a compiled pattern is 65539 (sic) bytes if PCRE - is compiled with the default internal linkage size of 2. If you want to - process regular expressions that are truly enormous, you can compile - PCRE with an internal linkage size of 3 or 4 (see the README file in - the source distribution and the pcrebuild documentation for details). - If these cases the limit is substantially larger. However, the speed - of execution will be slower. - - All values in repeating quantifiers must be less than 65536. The maxi- - mum number of capturing subpatterns is 65535. - - There is no limit to the number of non-capturing subpatterns, but the - maximum depth of nesting of all kinds of parenthesized subpattern, - including capturing subpatterns, assertions, and other types of subpat- - tern, is 200. - - The maximum length of a subject string is the largest positive number - that an integer variable can hold. However, PCRE uses recursion to han- - dle subpatterns and indefinite repetition. This means that the avail- - able stack space may limit the size of a subject string that can be - processed by certain patterns. - - -UTF-8 SUPPORT - - Starting at release 3.3, PCRE has had some support for character - strings encoded in the UTF-8 format. For release 4.0 this has been - greatly extended to cover most common requirements. - - In order process UTF-8 strings, you must build PCRE to include UTF-8 - support in the code, and, in addition, you must call pcre_compile() - with the PCRE_UTF8 option flag. When you do this, both the pattern and - any subject strings that are matched against it are treated as UTF-8 - strings instead of just strings of bytes. - - If you compile PCRE with UTF-8 support, but do not use it at run time, - the library will be a bit bigger, but the additional run time overhead - is limited to testing the PCRE_UTF8 flag in several places, so should - not be very large. - - The following comments apply when PCRE is running in UTF-8 mode: - - 1. When you set the PCRE_UTF8 flag, the strings passed as patterns and - subjects are checked for validity on entry to the relevant functions. - If an invalid UTF-8 string is passed, an error return is given. In some - situations, you may already know that your strings are valid, and - therefore want to skip these checks in order to improve performance. If - you set the PCRE_NO_UTF8_CHECK flag at compile time or at run time, - PCRE assumes that the pattern or subject it is given (respectively) - contains only valid UTF-8 codes. In this case, it does not diagnose an - invalid UTF-8 string. If you pass an invalid UTF-8 string to PCRE when - PCRE_NO_UTF8_CHECK is set, the results are undefined. Your program may - crash. - - 2. In a pattern, the escape sequence \x{...}, where the contents of the - braces is a string of hexadecimal digits, is interpreted as a UTF-8 - character whose code number is the given hexadecimal number, for exam- - ple: \x{1234}. If a non-hexadecimal digit appears between the braces, - the item is not recognized. This escape sequence can be used either as - a literal, or within a character class. - - 3. The original hexadecimal escape sequence, \xhh, matches a two-byte - UTF-8 character if the value is greater than 127. - - 4. Repeat quantifiers apply to complete UTF-8 characters, not to indi- - vidual bytes, for example: \x{100}{3}. - - 5. The dot metacharacter matches one UTF-8 character instead of a - single byte. - - 6. The escape sequence \C can be used to match a single byte in UTF-8 - mode, but its use can lead to some strange effects. - - 7. The character escapes \b, \B, \d, \D, \s, \S, \w, and \W correctly - test characters of any code value, but the characters that PCRE recog- - nizes as digits, spaces, or word characters remain the same set as - before, all with values less than 256. - - 8. Case-insensitive matching applies only to characters whose values - are less than 256. PCRE does not support the notion of "case" for - higher-valued characters. - - 9. PCRE does not support the use of Unicode tables and properties or - the Perl escapes \p, \P, and \X. - - -AUTHOR - - Philip Hazel <ph10@cam.ac.uk> - University Computing Service, - Cambridge CB2 3QG, England. - Phone: +44 1223 334714 - -Last updated: 20 August 2003 -Copyright (c) 1997-2003 University of Cambridge. ------------------------------------------------------------------------------ - -PCRE(3) PCRE(3) - - - -NAME - PCRE - Perl-compatible regular expressions - -PCRE BUILD-TIME OPTIONS - - This document describes the optional features of PCRE that can be - selected when the library is compiled. They are all selected, or dese- - lected, by providing options to the configure script which is run - before the make command. The complete list of options for configure - (which includes the standard ones such as the selection of the instal- - lation directory) can be obtained by running - - ./configure --help - - The following sections describe certain options whose names begin with - --enable or --disable. These settings specify changes to the defaults - for the configure command. Because of the way that configure works, - --enable and --disable always come in pairs, so the complementary - option always exists as well, but as it specifies the default, it is - not described. - - -UTF-8 SUPPORT - - To build PCRE with support for UTF-8 character strings, add - - --enable-utf8 - - to the configure command. Of itself, this does not make PCRE treat - strings as UTF-8. As well as compiling PCRE with this option, you also - have have to set the PCRE_UTF8 option when you call the pcre_compile() - function. - - -CODE VALUE OF NEWLINE - - By default, PCRE treats character 10 (linefeed) as the newline charac- - ter. This is the normal newline character on Unix-like systems. You can - compile PCRE to use character 13 (carriage return) instead by adding - - --enable-newline-is-cr - - to the configure command. For completeness there is also a --enable- - newline-is-lf option, which explicitly specifies linefeed as the new- - line character. - - -BUILDING SHARED AND STATIC LIBRARIES - - The PCRE building process uses libtool to build both shared and static - Unix libraries by default. You can suppress one of these by adding one - of - - --disable-shared - --disable-static - - to the configure command, as required. - - -POSIX MALLOC USAGE - - When PCRE is called through the POSIX interface (see the pcreposix - documentation), additional working storage is required for holding the - pointers to capturing substrings because PCRE requires three integers - per substring, whereas the POSIX interface provides only two. If the - number of expected substrings is small, the wrapper function uses space - on the stack, because this is faster than using malloc() for each call. - The default threshold above which the stack is no longer used is 10; it - can be changed by adding a setting such as - - --with-posix-malloc-threshold=20 - - to the configure command. - - -LIMITING PCRE RESOURCE USAGE - - Internally, PCRE has a function called match() which it calls repeat- - edly (possibly recursively) when performing a matching operation. By - limiting the number of times this function may be called, a limit can - be placed on the resources used by a single call to pcre_exec(). The - limit can be changed at run time, as described in the pcreapi documen- - tation. The default is 10 million, but this can be changed by adding a - setting such as - - --with-match-limit=500000 - - to the configure command. - - -HANDLING VERY LARGE PATTERNS - - Within a compiled pattern, offset values are used to point from one - part to another (for example, from an opening parenthesis to an alter- - nation metacharacter). By default two-byte values are used for these - offsets, leading to a maximum size for a compiled pattern of around - 64K. This is sufficient to handle all but the most gigantic patterns. - Nevertheless, some people do want to process enormous patterns, so it - is possible to compile PCRE to use three-byte or four-byte offsets by - adding a setting such as - - --with-link-size=3 - - to the configure command. The value given must be 2, 3, or 4. Using - longer offsets slows down the operation of PCRE because it has to load - additional bytes when handling them. - - If you build PCRE with an increased link size, test 2 (and test 5 if - you are using UTF-8) will fail. Part of the output of these tests is a - representation of the compiled pattern, and this changes with the link - size. - - -AVOIDING EXCESSIVE STACK USAGE - - PCRE implements backtracking while matching by making recursive calls - to an internal function called match(). In environments where the size - of the stack is limited, this can severely limit PCRE's operation. (The - Unix environment does not usually suffer from this problem.) An alter- - native approach that uses memory from the heap to remember data, - instead of using recursive function calls, has been implemented to work - round this problem. If you want to build a version of PCRE that works - this way, add - - --disable-stack-for-recursion - - to the configure command. With this configuration, PCRE will use the - pcre_stack_malloc and pcre_stack_free variables to call memory - management functions. Separate functions are provided because the usage - is very predictable: the block sizes requested are always the same, and - the blocks are always freed in reverse order. A calling program might - be able to implement optimized functions that perform better than the - standard malloc() and free() functions. PCRE runs noticeably more - slowly when built in this way. - - -USING EBCDIC CODE - - PCRE assumes by default that it will run in an environment where the - character code is ASCII (or UTF-8, which is a superset of ASCII). PCRE - can, however, be compiled to run in an EBCDIC environment by adding - - --enable-ebcdic - - to the configure command. - -Last updated: 09 December 2003 -Copyright (c) 1997-2003 University of Cambridge. ------------------------------------------------------------------------------ - -PCRE(3) PCRE(3) - - - -NAME - PCRE - Perl-compatible regular expressions - -SYNOPSIS OF PCRE API - - #include <pcre.h> - - pcre *pcre_compile(const char *pattern, int options, - const char **errptr, int *erroffset, - const unsigned char *tableptr); - - pcre_extra *pcre_study(const pcre *code, int options, - const char **errptr); - - int pcre_exec(const pcre *code, const pcre_extra *extra, - const char *subject, int length, int startoffset, - int options, int *ovector, int ovecsize); - - int pcre_copy_named_substring(const pcre *code, - const char *subject, int *ovector, - int stringcount, const char *stringname, - char *buffer, int buffersize); - - int pcre_copy_substring(const char *subject, int *ovector, - int stringcount, int stringnumber, char *buffer, - int buffersize); - - int pcre_get_named_substring(const pcre *code, - const char *subject, int *ovector, - int stringcount, const char *stringname, - const char **stringptr); - - int pcre_get_stringnumber(const pcre *code, - const char *name); - - int pcre_get_substring(const char *subject, int *ovector, - int stringcount, int stringnumber, - const char **stringptr); - - int pcre_get_substring_list(const char *subject, - int *ovector, int stringcount, const char ***listptr); - - void pcre_free_substring(const char *stringptr); - - void pcre_free_substring_list(const char **stringptr); - - const unsigned char *pcre_maketables(void); - - int pcre_fullinfo(const pcre *code, const pcre_extra *extra, - int what, void *where); - - int pcre_info(const pcre *code, int *optptr, int *firstcharptr); - - int pcre_config(int what, void *where); - - char *pcre_version(void); - - void *(*pcre_malloc)(size_t); - - void (*pcre_free)(void *); - - void *(*pcre_stack_malloc)(size_t); - - void (*pcre_stack_free)(void *); - - int (*pcre_callout)(pcre_callout_block *); - - -PCRE API - - PCRE has its own native API, which is described in this document. There - is also a set of wrapper functions that correspond to the POSIX regular - expression API. These are described in the pcreposix documentation. - - The native API function prototypes are defined in the header file - pcre.h, and on Unix systems the library itself is called libpcre.a, so - can be accessed by adding -lpcre to the command for linking an applica- - tion which calls it. The header file defines the macros PCRE_MAJOR and - PCRE_MINOR to contain the major and minor release numbers for the - library. Applications can use these to include support for different - releases. - - The functions pcre_compile(), pcre_study(), and pcre_exec() are used - for compiling and matching regular expressions. A sample program that - demonstrates the simplest way of using them is given in the file pcre- - demo.c. The pcresample documentation describes how to run it. - - There are convenience functions for extracting captured substrings from - a matched subject string. They are: - - pcre_copy_substring() - pcre_copy_named_substring() - pcre_get_substring() - pcre_get_named_substring() - pcre_get_substring_list() - - pcre_free_substring() and pcre_free_substring_list() are also provided, - to free the memory used for extracted strings. - - The function pcre_maketables() is used (optionally) to build a set of - character tables in the current locale for passing to pcre_compile(). - - The function pcre_fullinfo() is used to find out information about a - compiled pattern; pcre_info() is an obsolete version which returns only - some of the available information, but is retained for backwards com- - patibility. The function pcre_version() returns a pointer to a string - containing the version of PCRE and its date of release. - - The global variables pcre_malloc and pcre_free initially contain the - entry points of the standard malloc() and free() functions respec- - tively. PCRE calls the memory management functions via these variables, - so a calling program can replace them if it wishes to intercept the - calls. This should be done before calling any PCRE functions. - - The global variables pcre_stack_malloc and pcre_stack_free are also - indirections to memory management functions. These special functions - are used only when PCRE is compiled to use the heap for remembering - data, instead of recursive function calls. This is a non-standard way - of building PCRE, for use in environments that have limited stacks. - Because of the greater use of memory management, it runs more slowly. - Separate functions are provided so that special-purpose external code - can be used for this case. When used, these functions are always called - in a stack-like manner (last obtained, first freed), and always for - memory blocks of the same size. - - The global variable pcre_callout initially contains NULL. It can be set - by the caller to a "callout" function, which PCRE will then call at - specified points during a matching operation. Details are given in the - pcrecallout documentation. - - -MULTITHREADING - - The PCRE functions can be used in multi-threading applications, with - the proviso that the memory management functions pointed to by - pcre_malloc, pcre_free, pcre_stack_malloc, and pcre_stack_free, and the - callout function pointed to by pcre_callout, are shared by all threads. - - The compiled form of a regular expression is not altered during match- - ing, so the same compiled pattern can safely be used by several threads - at once. - - -CHECKING BUILD-TIME OPTIONS - - int pcre_config(int what, void *where); - - The function pcre_config() makes it possible for a PCRE client to dis- - cover which optional features have been compiled into the PCRE library. - The pcrebuild documentation has more details about these optional fea- - tures. - - The first argument for pcre_config() is an integer, specifying which - information is required; the second argument is a pointer to a variable - into which the information is placed. The following information is - available: - - PCRE_CONFIG_UTF8 - - The output is an integer that is set to one if UTF-8 support is avail- - able; otherwise it is set to zero. - - PCRE_CONFIG_NEWLINE - - The output is an integer that is set to the value of the code that is - used for the newline character. It is either linefeed (10) or carriage - return (13), and should normally be the standard character for your - operating system. - - PCRE_CONFIG_LINK_SIZE - - The output is an integer that contains the number of bytes used for - internal linkage in compiled regular expressions. The value is 2, 3, or - 4. Larger values allow larger regular expressions to be compiled, at - the expense of slower matching. The default value of 2 is sufficient - for all but the most massive patterns, since it allows the compiled - pattern to be up to 64K in size. - - PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - - The output is an integer that contains the threshold above which the - POSIX interface uses malloc() for output vectors. Further details are - given in the pcreposix documentation. - - PCRE_CONFIG_MATCH_LIMIT - - The output is an integer that gives the default limit for the number of - internal matching function calls in a pcre_exec() execution. Further - details are given with pcre_exec() below. - - PCRE_CONFIG_STACKRECURSE - - The output is an integer that is set to one if internal recursion is - implemented by recursive function calls that use the stack to remember - their state. This is the usual way that PCRE is compiled. The output is - zero if PCRE was compiled to use blocks of data on the heap instead of - recursive function calls. In this case, pcre_stack_malloc and - pcre_stack_free are called to manage memory blocks on the heap, thus - avoiding the use of the stack. - - -COMPILING A PATTERN - - pcre *pcre_compile(const char *pattern, int options, - const char **errptr, int *erroffset, - const unsigned char *tableptr); - - - The function pcre_compile() is called to compile a pattern into an - internal form. The pattern is a C string terminated by a binary zero, - and is passed in the argument pattern. A pointer to a single block of - memory that is obtained via pcre_malloc is returned. This contains the - compiled code and related data. The pcre type is defined for the - returned block; this is a typedef for a structure whose contents are - not externally defined. It is up to the caller to free the memory when - it is no longer required. - - Although the compiled code of a PCRE regex is relocatable, that is, it - does not depend on memory location, the complete pcre data block is not - fully relocatable, because it contains a copy of the tableptr argument, - which is an address (see below). - - The options argument contains independent bits that affect the compila- - tion. It should be zero if no options are required. Some of the - options, in particular, those that are compatible with Perl, can also - be set and unset from within the pattern (see the detailed description - of regular expressions in the pcrepattern documentation). For these - options, the contents of the options argument specifies their initial - settings at the start of compilation and execution. The PCRE_ANCHORED - option can be set at the time of matching as well as at compile time. - - If errptr is NULL, pcre_compile() returns NULL immediately. Otherwise, - if compilation of a pattern fails, pcre_compile() returns NULL, and - sets the variable pointed to by errptr to point to a textual error mes- - sage. The offset from the start of the pattern to the character where - the error was discovered is placed in the variable pointed to by - erroffset, which must not be NULL. If it is, an immediate error is - given. - - If the final argument, tableptr, is NULL, PCRE uses a default set of - character tables which are built when it is compiled, using the default - C locale. Otherwise, tableptr must be the result of a call to - pcre_maketables(). See the section on locale support below. - - This code fragment shows a typical straightforward call to pcre_com- - pile(): - - pcre *re; - const char *error; - int erroffset; - re = pcre_compile( - "^A.*Z", /* the pattern */ - 0, /* default options */ - &error, /* for error message */ - &erroffset, /* for error offset */ - NULL); /* use default character tables */ - - The following option bits are defined: - - PCRE_ANCHORED - - If this bit is set, the pattern is forced to be "anchored", that is, it - is constrained to match only at the first matching point in the string - which is being searched (the "subject string"). This effect can also be - achieved by appropriate constructs in the pattern itself, which is the - only way to do it in Perl. - - PCRE_CASELESS - - If this bit is set, letters in the pattern match both upper and lower - case letters. It is equivalent to Perl's /i option, and it can be - changed within a pattern by a (?i) option setting. - - PCRE_DOLLAR_ENDONLY - - If this bit is set, a dollar metacharacter in the pattern matches only - at the end of the subject string. Without this option, a dollar also - matches immediately before the final character if it is a newline (but - not before any other newlines). The PCRE_DOLLAR_ENDONLY option is - ignored if PCRE_MULTILINE is set. There is no equivalent to this option - in Perl, and no way to set it within a pattern. - - PCRE_DOTALL - - If this bit is set, a dot metacharater in the pattern matches all char- - acters, including newlines. Without it, newlines are excluded. This - option is equivalent to Perl's /s option, and it can be changed within - a pattern by a (?s) option setting. A negative class such as [^a] - always matches a newline character, independent of the setting of this - option. - - PCRE_EXTENDED - - If this bit is set, whitespace data characters in the pattern are - totally ignored except when escaped or inside a character class. - Whitespace does not include the VT character (code 11). In addition, - characters between an unescaped # outside a character class and the - next newline character, inclusive, are also ignored. This is equivalent - to Perl's /x option, and it can be changed within a pattern by a (?x) - option setting. - - This option makes it possible to include comments inside complicated - patterns. Note, however, that this applies only to data characters. - Whitespace characters may never appear within special character - sequences in a pattern, for example within the sequence (?( which - introduces a conditional subpattern. - - PCRE_EXTRA - - This option was invented in order to turn on additional functionality - of PCRE that is incompatible with Perl, but it is currently of very - little use. When set, any backslash in a pattern that is followed by a - letter that has no special meaning causes an error, thus reserving - these combinations for future expansion. By default, as in Perl, a - backslash followed by a letter with no special meaning is treated as a - literal. There are at present no other features controlled by this - option. It can also be set by a (?X) option setting within a pattern. - - PCRE_MULTILINE - - By default, PCRE treats the subject string as consisting of a single - "line" of characters (even if it actually contains several newlines). - The "start of line" metacharacter (^) matches only at the start of the - string, while the "end of line" metacharacter ($) matches only at the - end of the string, or before a terminating newline (unless PCRE_DOL- - LAR_ENDONLY is set). This is the same as Perl. - - When PCRE_MULTILINE it is set, the "start of line" and "end of line" - constructs match immediately following or immediately before any new- - line in the subject string, respectively, as well as at the very start - and end. This is equivalent to Perl's /m option, and it can be changed - within a pattern by a (?m) option setting. If there are no "\n" charac- - ters in a subject string, or no occurrences of ^ or $ in a pattern, - setting PCRE_MULTILINE has no effect. - - PCRE_NO_AUTO_CAPTURE - - If this option is set, it disables the use of numbered capturing paren- - theses in the pattern. Any opening parenthesis that is not followed by - ? behaves as if it were followed by ?: but named parentheses can still - be used for capturing (and they acquire numbers in the usual way). - There is no equivalent of this option in Perl. - - PCRE_UNGREEDY - - This option inverts the "greediness" of the quantifiers so that they - are not greedy by default, but become greedy if followed by "?". It is - not compatible with Perl. It can also be set by a (?U) option setting - within the pattern. - - PCRE_UTF8 - - This option causes PCRE to regard both the pattern and the subject as - strings of UTF-8 characters instead of single-byte character strings. - However, it is available only if PCRE has been built to include UTF-8 - support. If not, the use of this option provokes an error. Details of - how this option changes the behaviour of PCRE are given in the section - on UTF-8 support in the main pcre page. - - PCRE_NO_UTF8_CHECK - - When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is - automatically checked. If an invalid UTF-8 sequence of bytes is found, - pcre_compile() returns an error. If you already know that your pattern - is valid, and you want to skip this check for performance reasons, you - can set the PCRE_NO_UTF8_CHECK option. When it is set, the effect of - passing an invalid UTF-8 string as a pattern is undefined. It may cause - your program to crash. Note that there is a similar option for sup- - pressing the checking of subject strings passed to pcre_exec(). - - - -STUDYING A PATTERN - - pcre_extra *pcre_study(const pcre *code, int options, - const char **errptr); - - When a pattern is going to be used several times, it is worth spending - more time analyzing it in order to speed up the time taken for match- - ing. The function pcre_study() takes a pointer to a compiled pattern as - its first argument. If studing the pattern produces additional informa- - tion that will help speed up matching, pcre_study() returns a pointer - to a pcre_extra block, in which the study_data field points to the - results of the study. - - The returned value from a pcre_study() can be passed directly to - pcre_exec(). However, the pcre_extra block also contains other fields - that can be set by the caller before the block is passed; these are - described below. If studying the pattern does not produce any addi- - tional information, pcre_study() returns NULL. In that circumstance, if - the calling program wants to pass some of the other fields to - pcre_exec(), it must set up its own pcre_extra block. - - The second argument contains option bits. At present, no options are - defined for pcre_study(), and this argument should always be zero. - - The third argument for pcre_study() is a pointer for an error message. - If studying succeeds (even if no data is returned), the variable it - points to is set to NULL. Otherwise it points to a textual error mes- - sage. You should therefore test the error pointer for NULL after call- - ing pcre_study(), to be sure that it has run successfully. - - This is a typical call to pcre_study(): - - pcre_extra *pe; - pe = pcre_study( - re, /* result of pcre_compile() */ - 0, /* no options exist */ - &error); /* set to NULL or points to a message */ - - At present, studying a pattern is useful only for non-anchored patterns - that do not have a single fixed starting character. A bitmap of possi- - ble starting characters is created. - - -LOCALE SUPPORT - - PCRE handles caseless matching, and determines whether characters are - letters, digits, or whatever, by reference to a set of tables. When - running in UTF-8 mode, this applies only to characters with codes less - than 256. The library contains a default set of tables that is created - in the default C locale when PCRE is compiled. This is used when the - final argument of pcre_compile() is NULL, and is sufficient for many - applications. - - An alternative set of tables can, however, be supplied. Such tables are - built by calling the pcre_maketables() function, which has no argu- - ments, in the relevant locale. The result can then be passed to - pcre_compile() as often as necessary. For example, to build and use - tables that are appropriate for the French locale (where accented char- - acters with codes greater than 128 are treated as letters), the follow- - ing code could be used: - - setlocale(LC_CTYPE, "fr"); - tables = pcre_maketables(); - re = pcre_compile(..., tables); - - The tables are built in memory that is obtained via pcre_malloc. The - pointer that is passed to pcre_compile is saved with the compiled pat- - tern, and the same tables are used via this pointer by pcre_study() and - pcre_exec(). Thus, for any single pattern, compilation, studying and - matching all happen in the same locale, but different patterns can be - compiled in different locales. It is the caller's responsibility to - ensure that the memory containing the tables remains available for as - long as it is needed. - - -INFORMATION ABOUT A PATTERN - - int pcre_fullinfo(const pcre *code, const pcre_extra *extra, - int what, void *where); - - The pcre_fullinfo() function returns information about a compiled pat- - tern. It replaces the obsolete pcre_info() function, which is neverthe- - less retained for backwards compability (and is documented below). - - The first argument for pcre_fullinfo() is a pointer to the compiled - pattern. The second argument is the result of pcre_study(), or NULL if - the pattern was not studied. The third argument specifies which piece - of information is required, and the fourth argument is a pointer to a - variable to receive the data. The yield of the function is zero for - success, or one of the following negative numbers: - - PCRE_ERROR_NULL the argument code was NULL - the argument where was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found - PCRE_ERROR_BADOPTION the value of what was invalid - - Here is a typical call of pcre_fullinfo(), to obtain the length of the - compiled pattern: - - int rc; - unsigned long int length; - rc = pcre_fullinfo( - re, /* result of pcre_compile() */ - pe, /* result of pcre_study(), or NULL */ - PCRE_INFO_SIZE, /* what is required */ - &length); /* where to put the data */ - - The possible values for the third argument are defined in pcre.h, and - are as follows: - - PCRE_INFO_BACKREFMAX - - Return the number of the highest back reference in the pattern. The - fourth argument should point to an int variable. Zero is returned if - there are no back references. - - PCRE_INFO_CAPTURECOUNT - - Return the number of capturing subpatterns in the pattern. The fourth - argument should point to an int variable. - - PCRE_INFO_FIRSTBYTE - - Return information about the first byte of any matched string, for a - non-anchored pattern. (This option used to be called - PCRE_INFO_FIRSTCHAR; the old name is still recognized for backwards - compatibility.) - - If there is a fixed first byte, e.g. from a pattern such as - (cat|cow|coyote), it is returned in the integer pointed to by where. - Otherwise, if either - - (a) the pattern was compiled with the PCRE_MULTILINE option, and every - branch starts with "^", or - - (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not - set (if it were set, the pattern would be anchored), - - -1 is returned, indicating that the pattern matches only at the start - of a subject string or after any newline within the string. Otherwise - -2 is returned. For anchored patterns, -2 is returned. - - PCRE_INFO_FIRSTTABLE - - If the pattern was studied, and this resulted in the construction of a - 256-bit table indicating a fixed set of bytes for the first byte in any - matching string, a pointer to the table is returned. Otherwise NULL is - returned. The fourth argument should point to an unsigned char * vari- - able. - - PCRE_INFO_LASTLITERAL - - Return the value of the rightmost literal byte that must exist in any - matched string, other than at its start, if such a byte has been - recorded. The fourth argument should point to an int variable. If there - is no such byte, -1 is returned. For anchored patterns, a last literal - byte is recorded only if it follows something of variable length. For - example, for the pattern /^a\d+z\d+/ the returned value is "z", but for - /^a\dz\d/ the returned value is -1. - - PCRE_INFO_NAMECOUNT - PCRE_INFO_NAMEENTRYSIZE - PCRE_INFO_NAMETABLE - - PCRE supports the use of named as well as numbered capturing parenthe- - ses. The names are just an additional way of identifying the parenthe- - ses, which still acquire a number. A caller that wants to extract data - from a named subpattern must convert the name to a number in order to - access the correct pointers in the output vector (described with - pcre_exec() below). In order to do this, it must first use these three - values to obtain the name-to-number mapping table for the pattern. - - The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT - gives the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size - of each entry; both of these return an int value. The entry size - depends on the length of the longest name. PCRE_INFO_NAMETABLE returns - a pointer to the first entry of the table (a pointer to char). The - first two bytes of each entry are the number of the capturing parenthe- - sis, most significant byte first. The rest of the entry is the corre- - sponding name, zero terminated. The names are in alphabetical order. - For example, consider the following pattern (assume PCRE_EXTENDED is - set, so white space - including newlines - is ignored): - - (?P<date> (?P<year>(\d\d)?\d\d) - - (?P<month>\d\d) - (?P<day>\d\d) ) - - There are four named subpatterns, so the table has four entries, and - each entry in the table is eight bytes long. The table is as follows, - with non-printing bytes shows in hex, and undefined bytes shown as ??: - - 00 01 d a t e 00 ?? - 00 05 d a y 00 ?? ?? - 00 04 m o n t h 00 - 00 02 y e a r 00 ?? - - When writing code to extract data from named subpatterns, remember that - the length of each entry may be different for each compiled pattern. - - PCRE_INFO_OPTIONS - - Return a copy of the options with which the pattern was compiled. The - fourth argument should point to an unsigned long int variable. These - option bits are those specified in the call to pcre_compile(), modified - by any top-level option settings within the pattern itself. - - A pattern is automatically anchored by PCRE if all of its top-level - alternatives begin with one of the following: - - ^ unless PCRE_MULTILINE is set - \A always - \G always - .* if PCRE_DOTALL is set and there are no back - references to the subpattern in which .* appears - - For such patterns, the PCRE_ANCHORED bit is set in the options returned - by pcre_fullinfo(). - - PCRE_INFO_SIZE - - Return the size of the compiled pattern, that is, the value that was - passed as the argument to pcre_malloc() when PCRE was getting memory in - which to place the compiled data. The fourth argument should point to a - size_t variable. - - PCRE_INFO_STUDYSIZE - - Returns the size of the data block pointed to by the study_data field - in a pcre_extra block. That is, it is the value that was passed to - pcre_malloc() when PCRE was getting memory into which to place the data - created by pcre_study(). The fourth argument should point to a size_t - variable. - - -OBSOLETE INFO FUNCTION - - int pcre_info(const pcre *code, int *optptr, int *firstcharptr); - - The pcre_info() function is now obsolete because its interface is too - restrictive to return all the available data about a compiled pattern. - New programs should use pcre_fullinfo() instead. The yield of - pcre_info() is the number of capturing subpatterns, or one of the fol- - lowing negative numbers: - - PCRE_ERROR_NULL the argument code was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found - - If the optptr argument is not NULL, a copy of the options with which - the pattern was compiled is placed in the integer it points to (see - PCRE_INFO_OPTIONS above). - - If the pattern is not anchored and the firstcharptr argument is not - NULL, it is used to pass back information about the first character of - any matched string (see PCRE_INFO_FIRSTBYTE above). - - -MATCHING A PATTERN - - int pcre_exec(const pcre *code, const pcre_extra *extra, - const char *subject, int length, int startoffset, - int options, int *ovector, int ovecsize); - - The function pcre_exec() is called to match a subject string against a - pre-compiled pattern, which is passed in the code argument. If the pat- - tern has been studied, the result of the study should be passed in the - extra argument. - - Here is an example of a simple call to pcre_exec(): - - int rc; - int ovector[30]; - rc = pcre_exec( - re, /* result of pcre_compile() */ - NULL, /* we didn't study the pattern */ - "some string", /* the subject string */ - 11, /* the length of the subject string */ - 0, /* start at offset 0 in the subject */ - 0, /* default options */ - ovector, /* vector for substring information */ - 30); /* number of elements in the vector */ - - If the extra argument is not NULL, it must point to a pcre_extra data - block. The pcre_study() function returns such a block (when it doesn't - return NULL), but you can also create one for yourself, and pass addi- - tional information in it. The fields in the block are as follows: - - unsigned long int flags; - void *study_data; - unsigned long int match_limit; - void *callout_data; - - The flags field is a bitmap that specifies which of the other fields - are set. The flag bits are: - - PCRE_EXTRA_STUDY_DATA - PCRE_EXTRA_MATCH_LIMIT - PCRE_EXTRA_CALLOUT_DATA - - Other flag bits should be set to zero. The study_data field is set in - the pcre_extra block that is returned by pcre_study(), together with - the appropriate flag bit. You should not set this yourself, but you can - add to the block by setting the other fields. - - The match_limit field provides a means of preventing PCRE from using up - a vast amount of resources when running patterns that are not going to - match, but which have a very large number of possibilities in their - search trees. The classic example is the use of nested unlimited - repeats. Internally, PCRE uses a function called match() which it calls - repeatedly (sometimes recursively). The limit is imposed on the number - of times this function is called during a match, which has the effect - of limiting the amount of recursion and backtracking that can take - place. For patterns that are not anchored, the count starts from zero - for each position in the subject string. - - The default limit for the library can be set when PCRE is built; the - default default is 10 million, which handles all but the most extreme - cases. You can reduce the default by suppling pcre_exec() with a - pcre_extra block in which match_limit is set to a smaller value, and - PCRE_EXTRA_MATCH_LIMIT is set in the flags field. If the limit is - exceeded, pcre_exec() returns PCRE_ERROR_MATCHLIMIT. - - The pcre_callout field is used in conjunction with the "callout" fea- - ture, which is described in the pcrecallout documentation. - - The PCRE_ANCHORED option can be passed in the options argument, whose - unused bits must be zero. This limits pcre_exec() to matching at the - first matching position. However, if a pattern was compiled with - PCRE_ANCHORED, or turned out to be anchored by virtue of its contents, - it cannot be made unachored at matching time. - - When PCRE_UTF8 was set at compile time, the validity of the subject as - a UTF-8 string is automatically checked, and the value of startoffset - is also checked to ensure that it points to the start of a UTF-8 char- - acter. If an invalid UTF-8 sequence of bytes is found, pcre_exec() - returns the error PCRE_ERROR_BADUTF8. If startoffset contains an - invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned. - - If you already know that your subject is valid, and you want to skip - these checks for performance reasons, you can set the - PCRE_NO_UTF8_CHECK option when calling pcre_exec(). You might want to - do this for the second and subsequent calls to pcre_exec() if you are - making repeated calls to find all the matches in a single subject - string. However, you should be sure that the value of startoffset - points to the start of a UTF-8 character. When PCRE_NO_UTF8_CHECK is - set, the effect of passing an invalid UTF-8 string as a subject, or a - value of startoffset that does not point to the start of a UTF-8 char- - acter, is undefined. Your program may crash. - - There are also three further options that can be set only at matching - time: - - PCRE_NOTBOL - - The first character of the string is not the beginning of a line, so - the circumflex metacharacter should not match before it. Setting this - without PCRE_MULTILINE (at compile time) causes circumflex never to - match. - - PCRE_NOTEOL - - The end of the string is not the end of a line, so the dollar metachar- - acter should not match it nor (except in multiline mode) a newline - immediately before it. Setting this without PCRE_MULTILINE (at compile - time) causes dollar never to match. - - PCRE_NOTEMPTY - - An empty string is not considered to be a valid match if this option is - set. If there are alternatives in the pattern, they are tried. If all - the alternatives match the empty string, the entire match fails. For - example, if the pattern - - a?b? - - is applied to a string not beginning with "a" or "b", it matches the - empty string at the start of the subject. With PCRE_NOTEMPTY set, this - match is not valid, so PCRE searches further into the string for occur- - rences of "a" or "b". - - Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a spe- - cial case of a pattern match of the empty string within its split() - function, and when using the /g modifier. It is possible to emulate - Perl's behaviour after matching a null string by first trying the match - again at the same offset with PCRE_NOTEMPTY set, and then if that fails - by advancing the starting offset (see below) and trying an ordinary - match again. - - The subject string is passed to pcre_exec() as a pointer in subject, a - length in length, and a starting byte offset in startoffset. Unlike the - pattern string, the subject may contain binary zero bytes. When the - starting offset is zero, the search for a match starts at the beginning - of the subject, and this is by far the most common case. - - If the pattern was compiled with the PCRE_UTF8 option, the subject must - be a sequence of bytes that is a valid UTF-8 string, and the starting - offset must point to the beginning of a UTF-8 character. If an invalid - UTF-8 string or offset is passed, an error (either PCRE_ERROR_BADUTF8 - or PCRE_ERROR_BADUTF8_OFFSET) is returned, unless the option - PCRE_NO_UTF8_CHECK is set, in which case PCRE's behaviour is not - defined. - - A non-zero starting offset is useful when searching for another match - in the same subject by calling pcre_exec() again after a previous suc- - cess. Setting startoffset differs from just passing over a shortened - string and setting PCRE_NOTBOL in the case of a pattern that begins - with any kind of lookbehind. For example, consider the pattern - - \Biss\B - - which finds occurrences of "iss" in the middle of words. (\B matches - only if the current position in the subject is not a word boundary.) - When applied to the string "Mississipi" the first call to pcre_exec() - finds the first occurrence. If pcre_exec() is called again with just - the remainder of the subject, namely "issipi", it does not match, - because \B is always false at the start of the subject, which is deemed - to be a word boundary. However, if pcre_exec() is passed the entire - string again, but with startoffset set to 4, it finds the second - occurrence of "iss" because it is able to look behind the starting - point to discover that it is preceded by a letter. - - If a non-zero starting offset is passed when the pattern is anchored, - one attempt to match at the given offset is tried. This can only suc- - ceed if the pattern does not require the match to be at the start of - the subject. - - In general, a pattern matches a certain portion of the subject, and in - addition, further substrings from the subject may be picked out by - parts of the pattern. Following the usage in Jeffrey Friedl's book, - this is called "capturing" in what follows, and the phrase "capturing - subpattern" is used for a fragment of a pattern that picks out a sub- - string. PCRE supports several other kinds of parenthesized subpattern - that do not cause substrings to be captured. - - Captured substrings are returned to the caller via a vector of integer - offsets whose address is passed in ovector. The number of elements in - the vector is passed in ovecsize. The first two-thirds of the vector is - used to pass back captured substrings, each substring using a pair of - integers. The remaining third of the vector is used as workspace by - pcre_exec() while matching capturing subpatterns, and is not available - for passing back information. The length passed in ovecsize should - always be a multiple of three. If it is not, it is rounded down. - - When a match has been successful, information about captured substrings - is returned in pairs of integers, starting at the beginning of ovector, - and continuing up to two-thirds of its length at the most. The first - element of a pair is set to the offset of the first character in a sub- - string, and the second is set to the offset of the first character - after the end of a substring. The first pair, ovector[0] and ovec- - tor[1], identify the portion of the subject string matched by the - entire pattern. The next pair is used for the first capturing subpat- - tern, and so on. The value returned by pcre_exec() is the number of - pairs that have been set. If there are no capturing subpatterns, the - return value from a successful match is 1, indicating that just the - first pair of offsets has been set. - - Some convenience functions are provided for extracting the captured - substrings as separate strings. These are described in the following - section. - - It is possible for an capturing subpattern number n+1 to match some - part of the subject when subpattern n has not been used at all. For - example, if the string "abc" is matched against the pattern (a|(z))(bc) - subpatterns 1 and 3 are matched, but 2 is not. When this happens, both - offset values corresponding to the unused subpattern are set to -1. - - If a capturing subpattern is matched repeatedly, it is the last portion - of the string that it matched that gets returned. - - If the vector is too small to hold all the captured substrings, it is - used as far as possible (up to two-thirds of its length), and the func- - tion returns a value of zero. In particular, if the substring offsets - are not of interest, pcre_exec() may be called with ovector passed as - NULL and ovecsize as zero. However, if the pattern contains back refer- - ences and the ovector isn't big enough to remember the related sub- - strings, PCRE has to get additional memory for use during matching. - Thus it is usually advisable to supply an ovector. - - Note that pcre_info() can be used to find out how many capturing sub- - patterns there are in a compiled pattern. The smallest size for ovector - that will allow for n captured substrings, in addition to the offsets - of the substring matched by the whole pattern, is (n+1)*3. - - If pcre_exec() fails, it returns a negative number. The following are - defined in the header file: - - PCRE_ERROR_NOMATCH (-1) - - The subject string did not match the pattern. - - PCRE_ERROR_NULL (-2) - - Either code or subject was passed as NULL, or ovector was NULL and - ovecsize was not zero. - - PCRE_ERROR_BADOPTION (-3) - - An unrecognized bit was set in the options argument. - - PCRE_ERROR_BADMAGIC (-4) - - PCRE stores a 4-byte "magic number" at the start of the compiled code, - to catch the case when it is passed a junk pointer. This is the error - it gives when the magic number isn't present. - - PCRE_ERROR_UNKNOWN_NODE (-5) - - While running the pattern match, an unknown item was encountered in the - compiled pattern. This error could be caused by a bug in PCRE or by - overwriting of the compiled pattern. - - PCRE_ERROR_NOMEMORY (-6) - - If a pattern contains back references, but the ovector that is passed - to pcre_exec() is not big enough to remember the referenced substrings, - PCRE gets a block of memory at the start of matching to use for this - purpose. If the call via pcre_malloc() fails, this error is given. The - memory is freed at the end of matching. - - PCRE_ERROR_NOSUBSTRING (-7) - - This error is used by the pcre_copy_substring(), pcre_get_substring(), - and pcre_get_substring_list() functions (see below). It is never - returned by pcre_exec(). - - PCRE_ERROR_MATCHLIMIT (-8) - - The recursion and backtracking limit, as specified by the match_limit - field in a pcre_extra structure (or defaulted) was reached. See the - description above. - - PCRE_ERROR_CALLOUT (-9) - - This error is never generated by pcre_exec() itself. It is provided for - use by callout functions that want to yield a distinctive error code. - See the pcrecallout documentation for details. - - PCRE_ERROR_BADUTF8 (-10) - - A string that contains an invalid UTF-8 byte sequence was passed as a - subject. - - PCRE_ERROR_BADUTF8_OFFSET (-11) - - The UTF-8 byte sequence that was passed as a subject was valid, but the - value of startoffset did not point to the beginning of a UTF-8 charac- - ter. - - -EXTRACTING CAPTURED SUBSTRINGS BY NUMBER - - int pcre_copy_substring(const char *subject, int *ovector, - int stringcount, int stringnumber, char *buffer, - int buffersize); - - int pcre_get_substring(const char *subject, int *ovector, - int stringcount, int stringnumber, - const char **stringptr); - - int pcre_get_substring_list(const char *subject, - int *ovector, int stringcount, const char ***listptr); - - Captured substrings can be accessed directly by using the offsets - returned by pcre_exec() in ovector. For convenience, the functions - pcre_copy_substring(), pcre_get_substring(), and pcre_get_sub- - string_list() are provided for extracting captured substrings as new, - separate, zero-terminated strings. These functions identify substrings - by number. The next section describes functions for extracting named - substrings. A substring that contains a binary zero is correctly - extracted and has a further zero added on the end, but the result is - not, of course, a C string. - - The first three arguments are the same for all three of these func- - tions: subject is the subject string which has just been successfully - matched, ovector is a pointer to the vector of integer offsets that was - passed to pcre_exec(), and stringcount is the number of substrings that - were captured by the match, including the substring that matched the - entire regular expression. This is the value returned by pcre_exec if - it is greater than zero. If pcre_exec() returned zero, indicating that - it ran out of space in ovector, the value passed as stringcount should - be the size of the vector divided by three. - - The functions pcre_copy_substring() and pcre_get_substring() extract a - single substring, whose number is given as stringnumber. A value of - zero extracts the substring that matched the entire pattern, while - higher values extract the captured substrings. For pcre_copy_sub- - string(), the string is placed in buffer, whose length is given by - buffersize, while for pcre_get_substring() a new block of memory is - obtained via pcre_malloc, and its address is returned via stringptr. - The yield of the function is the length of the string, not including - the terminating zero, or one of - - PCRE_ERROR_NOMEMORY (-6) - - The buffer was too small for pcre_copy_substring(), or the attempt to - get memory failed for pcre_get_substring(). - - PCRE_ERROR_NOSUBSTRING (-7) - - There is no substring whose number is stringnumber. - - The pcre_get_substring_list() function extracts all available sub- - strings and builds a list of pointers to them. All this is done in a - single block of memory which is obtained via pcre_malloc. The address - of the memory block is returned via listptr, which is also the start of - the list of string pointers. The end of the list is marked by a NULL - pointer. The yield of the function is zero if all went well, or - - PCRE_ERROR_NOMEMORY (-6) - - if the attempt to get the memory block failed. - - When any of these functions encounter a substring that is unset, which - can happen when capturing subpattern number n+1 matches some part of - the subject, but subpattern n has not been used at all, they return an - empty string. This can be distinguished from a genuine zero-length sub- - string by inspecting the appropriate offset in ovector, which is nega- - tive for unset substrings. - - The two convenience functions pcre_free_substring() and - pcre_free_substring_list() can be used to free the memory returned by a - previous call of pcre_get_substring() or pcre_get_substring_list(), - respectively. They do nothing more than call the function pointed to by - pcre_free, which of course could be called directly from a C program. - However, PCRE is used in some situations where it is linked via a spe- - cial interface to another programming language which cannot use - pcre_free directly; it is for these cases that the functions are pro- - vided. - - -EXTRACTING CAPTURED SUBSTRINGS BY NAME - - int pcre_copy_named_substring(const pcre *code, - const char *subject, int *ovector, - int stringcount, const char *stringname, - char *buffer, int buffersize); - - int pcre_get_stringnumber(const pcre *code, - const char *name); - - int pcre_get_named_substring(const pcre *code, - const char *subject, int *ovector, - int stringcount, const char *stringname, - const char **stringptr); - - To extract a substring by name, you first have to find associated num- - ber. This can be done by calling pcre_get_stringnumber(). The first - argument is the compiled pattern, and the second is the name. For exam- - ple, for this pattern - - ab(?<xxx>\d+)... - - the number of the subpattern called "xxx" is 1. Given the number, you - can then extract the substring directly, or use one of the functions - described in the previous section. For convenience, there are also two - functions that do the whole job. - - Most of the arguments of pcre_copy_named_substring() and - pcre_get_named_substring() are the same as those for the functions that - extract by number, and so are not re-described here. There are just two - differences. - - First, instead of a substring number, a substring name is given. Sec- - ond, there is an extra argument, given at the start, which is a pointer - to the compiled pattern. This is needed in order to gain access to the - name-to-number translation table. - - These functions call pcre_get_stringnumber(), and if it succeeds, they - then call pcre_copy_substring() or pcre_get_substring(), as appropri- - ate. - -Last updated: 09 December 2003 -Copyright (c) 1997-2003 University of Cambridge. ------------------------------------------------------------------------------ - -PCRE(3) PCRE(3) - - - -NAME - PCRE - Perl-compatible regular expressions - -PCRE CALLOUTS - - int (*pcre_callout)(pcre_callout_block *); - - PCRE provides a feature called "callout", which is a means of temporar- - ily passing control to the caller of PCRE in the middle of pattern - matching. The caller of PCRE provides an external function by putting - its entry point in the global variable pcre_callout. By default, this - variable contains NULL, which disables all calling out. - - Within a regular expression, (?C) indicates the points at which the - external function is to be called. Different callout points can be - identified by putting a number less than 256 after the letter C. The - default value is zero. For example, this pattern has two callout - points: - - (?C1)abc(?C2)def - - During matching, when PCRE reaches a callout point (and pcre_callout is - set), the external function is called. Its only argument is a pointer - to a pcre_callout block. This contains the following variables: - - int version; - int callout_number; - int *offset_vector; - const char *subject; - int subject_length; - int start_match; - int current_position; - int capture_top; - int capture_last; - void *callout_data; - - The version field is an integer containing the version number of the - block format. The current version is zero. The version number may - change in future if additional fields are added, but the intention is - never to remove any of the existing fields. - - The callout_number field contains the number of the callout, as com- - piled into the pattern (that is, the number after ?C). - - The offset_vector field is a pointer to the vector of offsets that was - passed by the caller to pcre_exec(). The contents can be inspected in - order to extract substrings that have been matched so far, in the same - way as for extracting substrings after a match has completed. - - The subject and subject_length fields contain copies the values that - were passed to pcre_exec(). - - The start_match field contains the offset within the subject at which - the current match attempt started. If the pattern is not anchored, the - callout function may be called several times for different starting - points. - - The current_position field contains the offset within the subject of - the current match pointer. - - The capture_top field contains one more than the number of the highest - numbered captured substring so far. If no substrings have been - captured, the value of capture_top is one. - - The capture_last field contains the number of the most recently cap- - tured substring. - - The callout_data field contains a value that is passed to pcre_exec() - by the caller specifically so that it can be passed back in callouts. - It is passed in the pcre_callout field of the pcre_extra data struc- - ture. If no such data was passed, the value of callout_data in a - pcre_callout block is NULL. There is a description of the pcre_extra - structure in the pcreapi documentation. - - - -RETURN VALUES - - The callout function returns an integer. If the value is zero, matching - proceeds as normal. If the value is greater than zero, matching fails - at the current point, but backtracking to test other possibilities goes - ahead, just as if a lookahead assertion had failed. If the value is - less than zero, the match is abandoned, and pcre_exec() returns the - value. - - Negative values should normally be chosen from the set of - PCRE_ERROR_xxx values. In particular, PCRE_ERROR_NOMATCH forces a stan- - dard "no match" failure. The error number PCRE_ERROR_CALLOUT is - reserved for use by callout functions; it will never be used by PCRE - itself. - -Last updated: 21 January 2003 -Copyright (c) 1997-2003 University of Cambridge. ------------------------------------------------------------------------------ - -PCRE(3) PCRE(3) - - - -NAME - PCRE - Perl-compatible regular expressions - -DIFFERENCES FROM PERL - - This document describes the differences in the ways that PCRE and Perl - handle regular expressions. The differences described here are with - respect to Perl 5.8. - - 1. PCRE does not have full UTF-8 support. Details of what it does have - are given in the section on UTF-8 support in the main pcre page. - - 2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl - permits them, but they do not mean what you might think. For example, - (?!a){3} does not assert that the next three characters are not "a". It - just asserts that the next character is not "a" three times. - - 3. Capturing subpatterns that occur inside negative lookahead asser- - tions are counted, but their entries in the offsets vector are never - set. Perl sets its numerical variables from any such patterns that are - matched before the assertion fails to match something (thereby succeed- - ing), but only if the negative lookahead assertion contains just one - branch. - - 4. Though binary zero characters are supported in the subject string, - they are not allowed in a pattern string because it is passed as a nor- - mal C string, terminated by zero. The escape sequence "\0" can be used - in the pattern to represent a binary zero. - - 5. The following Perl escape sequences are not supported: \l, \u, \L, - \U, \P, \p, \N, and \X. In fact these are implemented by Perl's general - string-handling and are not part of its pattern matching engine. If any - of these are encountered by PCRE, an error is generated. - - 6. PCRE does support the \Q...\E escape for quoting substrings. Charac- - ters in between are treated as literals. This is slightly different - from Perl in that $ and @ are also handled as literals inside the - quotes. In Perl, they cause variable interpolation (but of course PCRE - does not have variables). Note the following examples: - - Pattern PCRE matches Perl matches - - \Qabc$xyz\E abc$xyz abc followed by the - contents of $xyz - \Qabc\$xyz\E abc\$xyz abc\$xyz - \Qabc\E\$\Qxyz\E abc$xyz abc$xyz - - The \Q...\E sequence is recognized both inside and outside character - classes. - - 7. Fairly obviously, PCRE does not support the (?{code}) and (?p{code}) - constructions. However, there is some experimental support for recur- - sive patterns using the non-Perl items (?R), (?number) and (?P>name). - Also, the PCRE "callout" feature allows an external function to be - called during pattern matching. - - 8. There are some differences that are concerned with the settings of - captured strings when part of a pattern is repeated. For example, - matching "aba" against the pattern /^(a(b)?)+$/ in Perl leaves $2 - unset, but in PCRE it is set to "b". - - 9. PCRE provides some extensions to the Perl regular expression - facilities: - - (a) Although lookbehind assertions must match fixed length strings, - each alternative branch of a lookbehind assertion can match a different - length of string. Perl requires them all to have the same length. - - (b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ - meta-character matches only at the very end of the string. - - (c) If PCRE_EXTRA is set, a backslash followed by a letter with no spe- - cial meaning is faulted. - - (d) If PCRE_UNGREEDY is set, the greediness of the repetition quanti- - fiers is inverted, that is, by default they are not greedy, but if fol- - lowed by a question mark they are. - - (e) PCRE_ANCHORED can be used to force a pattern to be tried only at - the first matching position in the subject string. - - (f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAP- - TURE options for pcre_exec() have no Perl equivalents. - - (g) The (?R), (?number), and (?P>name) constructs allows for recursive - pattern matching (Perl can do this using the (?p{code}) construct, - which PCRE cannot support.) - - (h) PCRE supports named capturing substrings, using the Python syntax. - - (i) PCRE supports the possessive quantifier "++" syntax, taken from - Sun's Java package. - - (j) The (R) condition, for testing recursion, is a PCRE extension. - - (k) The callout facility is PCRE-specific. - -Last updated: 09 December 2003 -Copyright (c) 1997-2003 University of Cambridge. ------------------------------------------------------------------------------ - -PCRE(3) PCRE(3) - - - -NAME - PCRE - Perl-compatible regular expressions - -PCRE REGULAR EXPRESSION DETAILS - - The syntax and semantics of the regular expressions supported by PCRE - are described below. Regular expressions are also described in the Perl - documentation and in a number of other books, some of which have copi- - ous examples. Jeffrey Friedl's "Mastering Regular Expressions", pub- - lished by O'Reilly, covers them in great detail. The description here - is intended as reference documentation. - - The basic operation of PCRE is on strings of bytes. However, there is - also support for UTF-8 character strings. To use this support you must - build PCRE to include UTF-8 support, and then call pcre_compile() with - the PCRE_UTF8 option. How this affects the pattern matching is men- - tioned in several places below. There is also a summary of UTF-8 fea- - tures in the section on UTF-8 support in the main pcre page. - - A regular expression is a pattern that is matched against a subject - string from left to right. Most characters stand for themselves in a - pattern, and match the corresponding characters in the subject. As a - trivial example, the pattern - - The quick brown fox - - matches a portion of a subject string that is identical to itself. The - power of regular expressions comes from the ability to include alterna- - tives and repetitions in the pattern. These are encoded in the pattern - by the use of meta-characters, which do not stand for themselves but - instead are interpreted in some special way. - - There are two different sets of meta-characters: those that are recog- - nized anywhere in the pattern except within square brackets, and those - that are recognized in square brackets. Outside square brackets, the - meta-characters are as follows: - - \ general escape character with several uses - ^ assert start of string (or line, in multiline mode) - $ assert end of string (or line, in multiline mode) - . match any character except newline (by default) - [ start character class definition - | start of alternative branch - ( start subpattern - ) end subpattern - ? extends the meaning of ( - also 0 or 1 quantifier - also quantifier minimizer - * 0 or more quantifier - + 1 or more quantifier - also "possessive quantifier" - { start min/max quantifier - - Part of a pattern that is in square brackets is called a "character - class". In a character class the only meta-characters are: - - \ general escape character - ^ negate the class, but only if the first character - - indicates character range - [ POSIX character class (only if followed by POSIX - syntax) - ] terminates the character class - - The following sections describe the use of each of the meta-characters. - - -BACKSLASH - - The backslash character has several uses. Firstly, if it is followed by - a non-alphameric character, it takes away any special meaning that - character may have. This use of backslash as an escape character - applies both inside and outside character classes. - - For example, if you want to match a * character, you write \* in the - pattern. This escaping action applies whether or not the following - character would otherwise be interpreted as a meta-character, so it is - always safe to precede a non-alphameric with backslash to specify that - it stands for itself. In particular, if you want to match a backslash, - you write \\. - - If a pattern is compiled with the PCRE_EXTENDED option, whitespace in - the pattern (other than in a character class) and characters between a - # outside a character class and the next newline character are ignored. - An escaping backslash can be used to include a whitespace or # charac- - ter as part of the pattern. - - If you want to remove the special meaning from a sequence of charac- - ters, you can do so by putting them between \Q and \E. This is differ- - ent from Perl in that $ and @ are handled as literals in \Q...\E - sequences in PCRE, whereas in Perl, $ and @ cause variable interpola- - tion. Note the following examples: - - Pattern PCRE matches Perl matches - - \Qabc$xyz\E abc$xyz abc followed by the - contents of $xyz - \Qabc\$xyz\E abc\$xyz abc\$xyz - \Qabc\E\$\Qxyz\E abc$xyz abc$xyz - - The \Q...\E sequence is recognized both inside and outside character - classes. - - A second use of backslash provides a way of encoding non-printing char- - acters in patterns in a visible manner. There is no restriction on the - appearance of non-printing characters, apart from the binary zero that - terminates a pattern, but when a pattern is being prepared by text - editing, it is usually easier to use one of the following escape - sequences than the binary character it represents: - - \a alarm, that is, the BEL character (hex 07) - \cx "control-x", where x is any character - \e escape (hex 1B) - \f formfeed (hex 0C) - \n newline (hex 0A) - \r carriage return (hex 0D) - \t tab (hex 09) - \ddd character with octal code ddd, or backreference - \xhh character with hex code hh - \x{hhh..} character with hex code hhh... (UTF-8 mode only) - - The precise effect of \cx is as follows: if x is a lower case letter, - it is converted to upper case. Then bit 6 of the character (hex 40) is - inverted. Thus \cz becomes hex 1A, but \c{ becomes hex 3B, while \c; - becomes hex 7B. - - After \x, from zero to two hexadecimal digits are read (letters can be - in upper or lower case). In UTF-8 mode, any number of hexadecimal dig- - its may appear between \x{ and }, but the value of the character code - must be less than 2**31 (that is, the maximum hexadecimal value is - 7FFFFFFF). If characters other than hexadecimal digits appear between - \x{ and }, or if there is no terminating }, this form of escape is not - recognized. Instead, the initial \x will be interpreted as a basic hex- - adecimal escape, with no following digits, giving a byte whose value is - zero. - - Characters whose value is less than 256 can be defined by either of the - two syntaxes for \x when PCRE is in UTF-8 mode. There is no difference - in the way they are handled. For example, \xdc is exactly the same as - \x{dc}. - - After \0 up to two further octal digits are read. In both cases, if - there are fewer than two digits, just those that are present are used. - Thus the sequence \0\x\07 specifies two binary zeros followed by a BEL - character (code value 7). Make sure you supply two digits after the - initial zero if the character that follows is itself an octal digit. - - The handling of a backslash followed by a digit other than 0 is compli- - cated. Outside a character class, PCRE reads it and any following dig- - its as a decimal number. If the number is less than 10, or if there - have been at least that many previous capturing left parentheses in the - expression, the entire sequence is taken as a back reference. A - description of how this works is given later, following the discussion - of parenthesized subpatterns. - - Inside a character class, or if the decimal number is greater than 9 - and there have not been that many capturing subpatterns, PCRE re-reads - up to three octal digits following the backslash, and generates a sin- - gle byte from the least significant 8 bits of the value. Any subsequent - digits stand for themselves. For example: - - \040 is another way of writing a space - \40 is the same, provided there are fewer than 40 - previous capturing subpatterns - \7 is always a back reference - \11 might be a back reference, or another way of - writing a tab - \011 is always a tab - \0113 is a tab followed by the character "3" - \113 might be a back reference, otherwise the - character with octal code 113 - \377 might be a back reference, otherwise - the byte consisting entirely of 1 bits - \81 is either a back reference, or a binary zero - followed by the two characters "8" and "1" - - Note that octal values of 100 or greater must not be introduced by a - leading zero, because no more than three octal digits are ever read. - - All the sequences that define a single byte value or a single UTF-8 - character (in UTF-8 mode) can be used both inside and outside character - classes. In addition, inside a character class, the sequence \b is - interpreted as the backspace character (hex 08). Outside a character - class it has a different meaning (see below). - - The third use of backslash is for specifying generic character types: - - \d any decimal digit - \D any character that is not a decimal digit - \s any whitespace character - \S any character that is not a whitespace character - \w any "word" character - \W any "non-word" character - - Each pair of escape sequences partitions the complete set of characters - into two disjoint sets. Any given character matches one, and only one, - of each pair. - - In UTF-8 mode, characters with values greater than 255 never match \d, - \s, or \w, and always match \D, \S, and \W. - - For compatibility with Perl, \s does not match the VT character (code - 11). This makes it different from the the POSIX "space" class. The \s - characters are HT (9), LF (10), FF (12), CR (13), and space (32). - - A "word" character is any letter or digit or the underscore character, - that is, any character which can be part of a Perl "word". The defini- - tion of letters and digits is controlled by PCRE's character tables, - and may vary if locale- specific matching is taking place (see "Locale - support" in the pcreapi page). For example, in the "fr" (French) - locale, some character codes greater than 128 are used for accented - letters, and these are matched by \w. - - These character type sequences can appear both inside and outside char- - acter classes. They each match one character of the appropriate type. - If the current matching point is at the end of the subject string, all - of them fail, since there is no character to match. - - The fourth use of backslash is for certain simple assertions. An asser- - tion specifies a condition that has to be met at a particular point in - a match, without consuming any characters from the subject string. The - use of subpatterns for more complicated assertions is described below. - The backslashed assertions are - - \b matches at a word boundary - \B matches when not at a word boundary - \A matches at start of subject - \Z matches at end of subject or before newline at end - \z matches at end of subject - \G matches at first matching position in subject - - These assertions may not appear in character classes (but note that \b - has a different meaning, namely the backspace character, inside a char- - acter class). - - A word boundary is a position in the subject string where the current - character and the previous character do not both match \w or \W (i.e. - one matches \w and the other matches \W), or the start or end of the - string if the first or last character matches \w, respectively. - - The \A, \Z, and \z assertions differ from the traditional circumflex - and dollar (described below) in that they only ever match at the very - start and end of the subject string, whatever options are set. Thus, - they are independent of multiline mode. - - They are not affected by the PCRE_NOTBOL or PCRE_NOTEOL options. If the - startoffset argument of pcre_exec() is non-zero, indicating that match- - ing is to start at a point other than the beginning of the subject, \A - can never match. The difference between \Z and \z is that \Z matches - before a newline that is the last character of the string as well as at - the end of the string, whereas \z matches only at the end. - - The \G assertion is true only when the current matching position is at - the start point of the match, as specified by the startoffset argument - of pcre_exec(). It differs from \A when the value of startoffset is - non-zero. By calling pcre_exec() multiple times with appropriate argu- - ments, you can mimic Perl's /g option, and it is in this kind of imple- - mentation where \G can be useful. - - Note, however, that PCRE's interpretation of \G, as the start of the - current match, is subtly different from Perl's, which defines it as the - end of the previous match. In Perl, these can be different when the - previously matched string was empty. Because PCRE does just one match - at a time, it cannot reproduce this behaviour. - - If all the alternatives of a pattern begin with \G, the expression is - anchored to the starting match position, and the "anchored" flag is set - in the compiled regular expression. - - -CIRCUMFLEX AND DOLLAR - - Outside a character class, in the default matching mode, the circumflex - character is an assertion which is true only if the current matching - point is at the start of the subject string. If the startoffset argu- - ment of pcre_exec() is non-zero, circumflex can never match if the - PCRE_MULTILINE option is unset. Inside a character class, circumflex - has an entirely different meaning (see below). - - Circumflex need not be the first character of the pattern if a number - of alternatives are involved, but it should be the first thing in each - alternative in which it appears if the pattern is ever to match that - branch. If all possible alternatives start with a circumflex, that is, - if the pattern is constrained to match only at the start of the sub- - ject, it is said to be an "anchored" pattern. (There are also other - constructs that can cause a pattern to be anchored.) - - A dollar character is an assertion which is true only if the current - matching point is at the end of the subject string, or immediately - before a newline character that is the last character in the string (by - default). Dollar need not be the last character of the pattern if a - number of alternatives are involved, but it should be the last item in - any branch in which it appears. Dollar has no special meaning in a - character class. - - The meaning of dollar can be changed so that it matches only at the - very end of the string, by setting the PCRE_DOLLAR_ENDONLY option at - compile time. This does not affect the \Z assertion. - - The meanings of the circumflex and dollar characters are changed if the - PCRE_MULTILINE option is set. When this is the case, they match immedi- - ately after and immediately before an internal newline character, - respectively, in addition to matching at the start and end of the sub- - ject string. For example, the pattern /^abc$/ matches the subject - string "def\nabc" in multiline mode, but not otherwise. Consequently, - patterns that are anchored in single line mode because all branches - start with ^ are not anchored in multiline mode, and a match for cir- - cumflex is possible when the startoffset argument of pcre_exec() is - non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE - is set. - - Note that the sequences \A, \Z, and \z can be used to match the start - and end of the subject in both modes, and if all branches of a pattern - start with \A it is always anchored, whether PCRE_MULTILINE is set or - not. - - -FULL STOP (PERIOD, DOT) - - Outside a character class, a dot in the pattern matches any one charac- - ter in the subject, including a non-printing character, but not (by - default) newline. In UTF-8 mode, a dot matches any UTF-8 character, - which might be more than one byte long, except (by default) for new- - line. If the PCRE_DOTALL option is set, dots match newlines as well. - The handling of dot is entirely independent of the handling of circum- - flex and dollar, the only relationship being that they both involve - newline characters. Dot has no special meaning in a character class. - - -MATCHING A SINGLE BYTE - - Outside a character class, the escape sequence \C matches any one byte, - both in and out of UTF-8 mode. Unlike a dot, it always matches a new- - line. The feature is provided in Perl in order to match individual - bytes in UTF-8 mode. Because it breaks up UTF-8 characters into indi- - vidual bytes, what remains in the string may be a malformed UTF-8 - string. For this reason it is best avoided. - - PCRE does not allow \C to appear in lookbehind assertions (see below), - because in UTF-8 mode it makes it impossible to calculate the length of - the lookbehind. - - -SQUARE BRACKETS - - An opening square bracket introduces a character class, terminated by a - closing square bracket. A closing square bracket on its own is not spe- - cial. If a closing square bracket is required as a member of the class, - it should be the first data character in the class (after an initial - circumflex, if present) or escaped with a backslash. - - A character class matches a single character in the subject. In UTF-8 - mode, the character may occupy more than one byte. A matched character - must be in the set of characters defined by the class, unless the first - character in the class definition is a circumflex, in which case the - subject character must not be in the set defined by the class. If a - circumflex is actually required as a member of the class, ensure it is - not the first character, or escape it with a backslash. - - For example, the character class [aeiou] matches any lower case vowel, - while [^aeiou] matches any character that is not a lower case vowel. - Note that a circumflex is just a convenient notation for specifying the - characters which are in the class by enumerating those that are not. It - is not an assertion: it still consumes a character from the subject - string, and fails if the current pointer is at the end of the string. - - In UTF-8 mode, characters with values greater than 255 can be included - in a class as a literal string of bytes, or by using the \x{ escaping - mechanism. - - When caseless matching is set, any letters in a class represent both - their upper case and lower case versions, so for example, a caseless - [aeiou] matches "A" as well as "a", and a caseless [^aeiou] does not - match "A", whereas a caseful version would. PCRE does not support the - concept of case for characters with values greater than 255. - - The newline character is never treated in any special way in character - classes, whatever the setting of the PCRE_DOTALL or PCRE_MULTILINE - options is. A class such as [^a] will always match a newline. - - The minus (hyphen) character can be used to specify a range of charac- - ters in a character class. For example, [d-m] matches any letter - between d and m, inclusive. If a minus character is required in a - class, it must be escaped with a backslash or appear in a position - where it cannot be interpreted as indicating a range, typically as the - first or last character in the class. - - It is not possible to have the literal character "]" as the end charac- - ter of a range. A pattern such as [W-]46] is interpreted as a class of - two characters ("W" and "-") followed by a literal string "46]", so it - would match "W46]" or "-46]". However, if the "]" is escaped with a - backslash it is interpreted as the end of range, so [W-\]46] is inter- - preted as a single class containing a range followed by two separate - characters. The octal or hexadecimal representation of "]" can also be - used to end a range. - - Ranges operate in the collating sequence of character values. They can - also be used for characters specified numerically, for example - [\000-\037]. In UTF-8 mode, ranges can include characters whose values - are greater than 255, for example [\x{100}-\x{2ff}]. - - If a range that includes letters is used when caseless matching is set, - it matches the letters in either case. For example, [W-c] is equivalent - to [][\^_`wxyzabc], matched caselessly, and if character tables for the - "fr" locale are in use, [\xc8-\xcb] matches accented E characters in - both cases. - - The character types \d, \D, \s, \S, \w, and \W may also appear in a - character class, and add the characters that they match to the class. - For example, [\dABCDEF] matches any hexadecimal digit. A circumflex can - conveniently be used with the upper case character types to specify a - more restricted set of characters than the matching lower case type. - For example, the class [^\W_] matches any letter or digit, but not - underscore. - - All non-alphameric characters other than \, -, ^ (at the start) and the - terminating ] are non-special in character classes, but it does no harm - if they are escaped. - - -POSIX CHARACTER CLASSES - - Perl supports the POSIX notation for character classes, which uses - names enclosed by [: and :] within the enclosing square brackets. PCRE - also supports this notation. For example, - - [01[:alpha:]%] - - matches "0", "1", any alphabetic character, or "%". The supported class - names are - - alnum letters and digits - alpha letters - ascii character codes 0 - 127 - blank space or tab only - cntrl control characters - digit decimal digits (same as \d) - graph printing characters, excluding space - lower lower case letters - print printing characters, including space - punct printing characters, excluding letters and digits - space white space (not quite the same as \s) - upper upper case letters - word "word" characters (same as \w) - xdigit hexadecimal digits - - The "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), - and space (32). Notice that this list includes the VT character (code - 11). This makes "space" different to \s, which does not include VT (for - Perl compatibility). - - The name "word" is a Perl extension, and "blank" is a GNU extension - from Perl 5.8. Another Perl extension is negation, which is indicated - by a ^ character after the colon. For example, - - [12[:^digit:]] - - matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the - POSIX syntax [.ch.] and [=ch=] where "ch" is a "collating element", but - these are not supported, and an error is given if they are encountered. - - In UTF-8 mode, characters with values greater than 255 do not match any - of the POSIX character classes. - - -VERTICAL BAR - - Vertical bar characters are used to separate alternative patterns. For - example, the pattern - - gilbert|sullivan - - matches either "gilbert" or "sullivan". Any number of alternatives may - appear, and an empty alternative is permitted (matching the empty - string). The matching process tries each alternative in turn, from - left to right, and the first one that succeeds is used. If the alterna- - tives are within a subpattern (defined below), "succeeds" means match- - ing the rest of the main pattern as well as the alternative in the sub- - pattern. - - -INTERNAL OPTION SETTING - - The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and - PCRE_EXTENDED options can be changed from within the pattern by a - sequence of Perl option letters enclosed between "(?" and ")". The - option letters are - - i for PCRE_CASELESS - m for PCRE_MULTILINE - s for PCRE_DOTALL - x for PCRE_EXTENDED - - For example, (?im) sets caseless, multiline matching. It is also possi- - ble to unset these options by preceding the letter with a hyphen, and a - combined setting and unsetting such as (?im-sx), which sets PCRE_CASE- - LESS and PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, - is also permitted. If a letter appears both before and after the - hyphen, the option is unset. - - When an option change occurs at top level (that is, not inside subpat- - tern parentheses), the change applies to the remainder of the pattern - that follows. If the change is placed right at the start of a pattern, - PCRE extracts it into the global options (and it will therefore show up - in data extracted by the pcre_fullinfo() function). - - An option change within a subpattern affects only that part of the cur- - rent pattern that follows it, so - - (a(?i)b)c - - matches abc and aBc and no other strings (assuming PCRE_CASELESS is not - used). By this means, options can be made to have different settings - in different parts of the pattern. Any changes made in one alternative - do carry on into subsequent branches within the same subpattern. For - example, - - (a(?i)b|c) - - matches "ab", "aB", "c", and "C", even though when matching "C" the - first branch is abandoned before the option setting. This is because - the effects of option settings happen at compile time. There would be - some very weird behaviour otherwise. - - The PCRE-specific options PCRE_UNGREEDY and PCRE_EXTRA can be changed - in the same way as the Perl-compatible options by using the characters - U and X respectively. The (?X) flag setting is special in that it must - always occur earlier in the pattern than any of the additional features - it turns on, even when it is at top level. It is best put at the start. - - -SUBPATTERNS - - Subpatterns are delimited by parentheses (round brackets), which can be - nested. Marking part of a pattern as a subpattern does two things: - - 1. It localizes a set of alternatives. For example, the pattern - - cat(aract|erpillar|) - - matches one of the words "cat", "cataract", or "caterpillar". Without - the parentheses, it would match "cataract", "erpillar" or the empty - string. - - 2. It sets up the subpattern as a capturing subpattern (as defined - above). When the whole pattern matches, that portion of the subject - string that matched the subpattern is passed back to the caller via the - ovector argument of pcre_exec(). Opening parentheses are counted from - left to right (starting from 1) to obtain the numbers of the capturing - subpatterns. - - For example, if the string "the red king" is matched against the pat- - tern - - the ((red|white) (king|queen)) - - the captured substrings are "red king", "red", and "king", and are num- - bered 1, 2, and 3, respectively. - - The fact that plain parentheses fulfil two functions is not always - helpful. There are often times when a grouping subpattern is required - without a capturing requirement. If an opening parenthesis is followed - by a question mark and a colon, the subpattern does not do any captur- - ing, and is not counted when computing the number of any subsequent - capturing subpatterns. For example, if the string "the white queen" is - matched against the pattern - - the ((?:red|white) (king|queen)) - - the captured substrings are "white queen" and "queen", and are numbered - 1 and 2. The maximum number of capturing subpatterns is 65535, and the - maximum depth of nesting of all subpatterns, both capturing and non- - capturing, is 200. - - As a convenient shorthand, if any option settings are required at the - start of a non-capturing subpattern, the option letters may appear - between the "?" and the ":". Thus the two patterns - - (?i:saturday|sunday) - (?:(?i)saturday|sunday) - - match exactly the same set of strings. Because alternative branches are - tried from left to right, and options are not reset until the end of - the subpattern is reached, an option setting in one branch does affect - subsequent branches, so the above patterns match "SUNDAY" as well as - "Saturday". - - -NAMED SUBPATTERNS - - Identifying capturing parentheses by number is simple, but it can be - very hard to keep track of the numbers in complicated regular expres- - sions. Furthermore, if an expression is modified, the numbers may - change. To help with the difficulty, PCRE supports the naming of sub- - patterns, something that Perl does not provide. The Python syntax - (?P<name>...) is used. Names consist of alphanumeric characters and - underscores, and must be unique within a pattern. - - Named capturing parentheses are still allocated numbers as well as - names. The PCRE API provides function calls for extracting the name-to- - number translation table from a compiled pattern. For further details - see the pcreapi documentation. - - -REPETITION - - Repetition is specified by quantifiers, which can follow any of the - following items: - - a literal data character - the . metacharacter - the \C escape sequence - escapes such as \d that match single characters - a character class - a back reference (see next section) - a parenthesized subpattern (unless it is an assertion) - - The general repetition quantifier specifies a minimum and maximum num- - ber of permitted matches, by giving the two numbers in curly brackets - (braces), separated by a comma. The numbers must be less than 65536, - and the first must be less than or equal to the second. For example: - - z{2,4} - - matches "zz", "zzz", or "zzzz". A closing brace on its own is not a - special character. If the second number is omitted, but the comma is - present, there is no upper limit; if the second number and the comma - are both omitted, the quantifier specifies an exact number of required - matches. Thus - - [aeiou]{3,} - - matches at least 3 successive vowels, but may match many more, while - - \d{8} - - matches exactly 8 digits. An opening curly bracket that appears in a - position where a quantifier is not allowed, or one that does not match - the syntax of a quantifier, is taken as a literal character. For exam- - ple, {,6} is not a quantifier, but a literal string of four characters. - - In UTF-8 mode, quantifiers apply to UTF-8 characters rather than to - individual bytes. Thus, for example, \x{100}{2} matches two UTF-8 char- - acters, each of which is represented by a two-byte sequence. - - The quantifier {0} is permitted, causing the expression to behave as if - the previous item and the quantifier were not present. - - For convenience (and historical compatibility) the three most common - quantifiers have single-character abbreviations: - - * is equivalent to {0,} - + is equivalent to {1,} - ? is equivalent to {0,1} - - It is possible to construct infinite loops by following a subpattern - that can match no characters with a quantifier that has no upper limit, - for example: - - (a?)* - - Earlier versions of Perl and PCRE used to give an error at compile time - for such patterns. However, because there are cases where this can be - useful, such patterns are now accepted, but if any repetition of the - subpattern does in fact match no characters, the loop is forcibly bro- - ken. - - By default, the quantifiers are "greedy", that is, they match as much - as possible (up to the maximum number of permitted times), without - causing the rest of the pattern to fail. The classic example of where - this gives problems is in trying to match comments in C programs. These - appear between the sequences /* and */ and within the sequence, indi- - vidual * and / characters may appear. An attempt to match C comments by - applying the pattern - - /\*.*\*/ - - to the string - - /* first command */ not comment /* second comment */ - - fails, because it matches the entire string owing to the greediness of - the .* item. - - However, if a quantifier is followed by a question mark, it ceases to - be greedy, and instead matches the minimum number of times possible, so - the pattern - - /\*.*?\*/ - - does the right thing with the C comments. The meaning of the various - quantifiers is not otherwise changed, just the preferred number of - matches. Do not confuse this use of question mark with its use as a - quantifier in its own right. Because it has two uses, it can sometimes - appear doubled, as in - - \d??\d - - which matches one digit by preference, but can match two if that is the - only way the rest of the pattern matches. - - If the PCRE_UNGREEDY option is set (an option which is not available in - Perl), the quantifiers are not greedy by default, but individual ones - can be made greedy by following them with a question mark. In other - words, it inverts the default behaviour. - - When a parenthesized subpattern is quantified with a minimum repeat - count that is greater than 1 or with a limited maximum, more store is - required for the compiled pattern, in proportion to the size of the - minimum or maximum. - - If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equiv- - alent to Perl's /s) is set, thus allowing the . to match newlines, the - pattern is implicitly anchored, because whatever follows will be tried - against every character position in the subject string, so there is no - point in retrying the overall match at any position after the first. - PCRE normally treats such a pattern as though it were preceded by \A. - - In cases where it is known that the subject string contains no new- - lines, it is worth setting PCRE_DOTALL in order to obtain this opti- - mization, or alternatively using ^ to indicate anchoring explicitly. - - However, there is one situation where the optimization cannot be used. - When .* is inside capturing parentheses that are the subject of a - backreference elsewhere in the pattern, a match at the start may fail, - and a later one succeed. Consider, for example: - - (.*)abc\1 - - If the subject is "xyz123abc123" the match point is the fourth charac- - ter. For this reason, such a pattern is not implicitly anchored. - - When a capturing subpattern is repeated, the value captured is the sub- - string that matched the final iteration. For example, after - - (tweedle[dume]{3}\s*)+ - - has matched "tweedledum tweedledee" the value of the captured substring - is "tweedledee". However, if there are nested capturing subpatterns, - the corresponding captured values may have been set in previous itera- - tions. For example, after - - /(a|(b))+/ - - matches "aba" the value of the second captured substring is "b". - - -ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS - - With both maximizing and minimizing repetition, failure of what follows - normally causes the repeated item to be re-evaluated to see if a dif- - ferent number of repeats allows the rest of the pattern to match. Some- - times it is useful to prevent this, either to change the nature of the - match, or to cause it fail earlier than it otherwise might, when the - author of the pattern knows there is no point in carrying on. - - Consider, for example, the pattern \d+foo when applied to the subject - line - - 123456bar - - After matching all 6 digits and then failing to match "foo", the normal - action of the matcher is to try again with only 5 digits matching the - \d+ item, and then with 4, and so on, before ultimately failing. - "Atomic grouping" (a term taken from Jeffrey Friedl's book) provides - the means for specifying that once a subpattern has matched, it is not - to be re-evaluated in this way. - - If we use atomic grouping for the previous example, the matcher would - give up immediately on failing to match "foo" the first time. The nota- - tion is a kind of special parenthesis, starting with (?> as in this - example: - - (?>\d+)foo - - This kind of parenthesis "locks up" the part of the pattern it con- - tains once it has matched, and a failure further into the pattern is - prevented from backtracking into it. Backtracking past it to previous - items, however, works as normal. - - An alternative description is that a subpattern of this type matches - the string of characters that an identical standalone pattern would - match, if anchored at the current point in the subject string. - - Atomic grouping subpatterns are not capturing subpatterns. Simple cases - such as the above example can be thought of as a maximizing repeat that - must swallow everything it can. So, while both \d+ and \d+? are pre- - pared to adjust the number of digits they match in order to make the - rest of the pattern match, (?>\d+) can only match an entire sequence of - digits. - - Atomic groups in general can of course contain arbitrarily complicated - subpatterns, and can be nested. However, when the subpattern for an - atomic group is just a single repeated item, as in the example above, a - simpler notation, called a "possessive quantifier" can be used. This - consists of an additional + character following a quantifier. Using - this notation, the previous example can be rewritten as - - \d++bar - - Possessive quantifiers are always greedy; the setting of the - PCRE_UNGREEDY option is ignored. They are a convenient notation for the - simpler forms of atomic group. However, there is no difference in the - meaning or processing of a possessive quantifier and the equivalent - atomic group. - - The possessive quantifier syntax is an extension to the Perl syntax. It - originates in Sun's Java package. - - When a pattern contains an unlimited repeat inside a subpattern that - can itself be repeated an unlimited number of times, the use of an - atomic group is the only way to avoid some failing matches taking a - very long time indeed. The pattern - - (\D+|<\d+>)*[!?] - - matches an unlimited number of substrings that either consist of non- - digits, or digits enclosed in <>, followed by either ! or ?. When it - matches, it runs quickly. However, if it is applied to - - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - - it takes a long time before reporting failure. This is because the - string can be divided between the two repeats in a large number of - ways, and all have to be tried. (The example used [!?] rather than a - single character at the end, because both PCRE and Perl have an opti- - mization that allows for fast failure when a single character is used. - They remember the last single character that is required for a match, - and fail early if it is not present in the string.) If the pattern is - changed to - - ((?>\D+)|<\d+>)*[!?] - - sequences of non-digits cannot be broken, and failure happens quickly. - - -BACK REFERENCES - - Outside a character class, a backslash followed by a digit greater than - 0 (and possibly further digits) is a back reference to a capturing sub- - pattern earlier (that is, to its left) in the pattern, provided there - have been that many previous capturing left parentheses. - - However, if the decimal number following the backslash is less than 10, - it is always taken as a back reference, and causes an error only if - there are not that many capturing left parentheses in the entire pat- - tern. In other words, the parentheses that are referenced need not be - to the left of the reference for numbers less than 10. See the section - entitled "Backslash" above for further details of the handling of dig- - its following a backslash. - - A back reference matches whatever actually matched the capturing sub- - pattern in the current subject string, rather than anything matching - the subpattern itself (see "Subpatterns as subroutines" below for a way - of doing that). So the pattern - - (sens|respons)e and \1ibility - - matches "sense and sensibility" and "response and responsibility", but - not "sense and responsibility". If caseful matching is in force at the - time of the back reference, the case of letters is relevant. For exam- - ple, - - ((?i)rah)\s+\1 - - matches "rah rah" and "RAH RAH", but not "RAH rah", even though the - original capturing subpattern is matched caselessly. - - Back references to named subpatterns use the Python syntax (?P=name). - We could rewrite the above example as follows: - - (?<p1>(?i)rah)\s+(?P=p1) - - There may be more than one back reference to the same subpattern. If a - subpattern has not actually been used in a particular match, any back - references to it always fail. For example, the pattern - - (a|(bc))\2 - - always fails if it starts to match "a" rather than "bc". Because there - may be many capturing parentheses in a pattern, all digits following - the backslash are taken as part of a potential back reference number. - If the pattern continues with a digit character, some delimiter must be - used to terminate the back reference. If the PCRE_EXTENDED option is - set, this can be whitespace. Otherwise an empty comment can be used. - - A back reference that occurs inside the parentheses to which it refers - fails when the subpattern is first used, so, for example, (a\1) never - matches. However, such references can be useful inside repeated sub- - patterns. For example, the pattern - - (a|b\1)+ - - matches any number of "a"s and also "aba", "ababbaa" etc. At each iter- - ation of the subpattern, the back reference matches the character - string corresponding to the previous iteration. In order for this to - work, the pattern must be such that the first iteration does not need - to match the back reference. This can be done using alternation, as in - the example above, or by a quantifier with a minimum of zero. - - -ASSERTIONS - - An assertion is a test on the characters following or preceding the - current matching point that does not actually consume any characters. - The simple assertions coded as \b, \B, \A, \G, \Z, \z, ^ and $ are - described above. More complicated assertions are coded as subpatterns. - There are two kinds: those that look ahead of the current position in - the subject string, and those that look behind it. - - An assertion subpattern is matched in the normal way, except that it - does not cause the current matching position to be changed. Lookahead - assertions start with (?= for positive assertions and (?! for negative - assertions. For example, - - \w+(?=;) - - matches a word followed by a semicolon, but does not include the semi- - colon in the match, and - - foo(?!bar) - - matches any occurrence of "foo" that is not followed by "bar". Note - that the apparently similar pattern - - (?!foo)bar - - does not find an occurrence of "bar" that is preceded by something - other than "foo"; it finds any occurrence of "bar" whatsoever, because - the assertion (?!foo) is always true when the next three characters are - "bar". A lookbehind assertion is needed to achieve this effect. - - If you want to force a matching failure at some point in a pattern, the - most convenient way to do it is with (?!) because an empty string - always matches, so an assertion that requires there not to be an empty - string must always fail. - - Lookbehind assertions start with (?<= for positive assertions and (?<! - for negative assertions. For example, - - (?<!foo)bar - - does find an occurrence of "bar" that is not preceded by "foo". The - contents of a lookbehind assertion are restricted such that all the - strings it matches must have a fixed length. However, if there are sev- - eral alternatives, they do not all have to have the same fixed length. - Thus - - (?<=bullock|donkey) - - is permitted, but - - (?<!dogs?|cats?) - - causes an error at compile time. Branches that match different length - strings are permitted only at the top level of a lookbehind assertion. - This is an extension compared with Perl (at least for 5.8), which - requires all branches to match the same length of string. An assertion - such as - - (?<=ab(c|de)) - - is not permitted, because its single top-level branch can match two - different lengths, but it is acceptable if rewritten to use two top- - level branches: - - (?<=abc|abde) - - The implementation of lookbehind assertions is, for each alternative, - to temporarily move the current position back by the fixed width and - then try to match. If there are insufficient characters before the cur- - rent position, the match is deemed to fail. - - PCRE does not allow the \C escape (which matches a single byte in UTF-8 - mode) to appear in lookbehind assertions, because it makes it impossi- - ble to calculate the length of the lookbehind. - - Atomic groups can be used in conjunction with lookbehind assertions to - specify efficient matching at the end of the subject string. Consider a - simple pattern such as - - abcd$ - - when applied to a long string that does not match. Because matching - proceeds from left to right, PCRE will look for each "a" in the subject - and then see if what follows matches the rest of the pattern. If the - pattern is specified as - - ^.*abcd$ - - the initial .* matches the entire string at first, but when this fails - (because there is no following "a"), it backtracks to match all but the - last character, then all but the last two characters, and so on. Once - again the search for "a" covers the entire string, from right to left, - so we are no better off. However, if the pattern is written as - - ^(?>.*)(?<=abcd) - - or, equivalently, - - ^.*+(?<=abcd) - - there can be no backtracking for the .* item; it can match only the - entire string. The subsequent lookbehind assertion does a single test - on the last four characters. If it fails, the match fails immediately. - For long strings, this approach makes a significant difference to the - processing time. - - Several assertions (of any sort) may occur in succession. For example, - - (?<=\d{3})(?<!999)foo - - matches "foo" preceded by three digits that are not "999". Notice that - each of the assertions is applied independently at the same point in - the subject string. First there is a check that the previous three - characters are all digits, and then there is a check that the same - three characters are not "999". This pattern does not match "foo" pre- - ceded by six characters, the first of which are digits and the last - three of which are not "999". For example, it doesn't match "123abc- - foo". A pattern to do that is - - (?<=\d{3}...)(?<!999)foo - - This time the first assertion looks at the preceding six characters, - checking that the first three are digits, and then the second assertion - checks that the preceding three characters are not "999". - - Assertions can be nested in any combination. For example, - - (?<=(?<!foo)bar)baz - - matches an occurrence of "baz" that is preceded by "bar" which in turn - is not preceded by "foo", while - - (?<=\d{3}(?!999)...)foo - - is another pattern which matches "foo" preceded by three digits and any - three characters that are not "999". - - Assertion subpatterns are not capturing subpatterns, and may not be - repeated, because it makes no sense to assert the same thing several - times. If any kind of assertion contains capturing subpatterns within - it, these are counted for the purposes of numbering the capturing sub- - patterns in the whole pattern. However, substring capturing is carried - out only for positive assertions, because it does not make sense for - negative assertions. - - -CONDITIONAL SUBPATTERNS - - It is possible to cause the matching process to obey a subpattern con- - ditionally or to choose between two alternative subpatterns, depending - on the result of an assertion, or whether a previous capturing - subpattern matched or not. The two possible forms of conditional sub- - pattern are - - (?(condition)yes-pattern) - (?(condition)yes-pattern|no-pattern) - - If the condition is satisfied, the yes-pattern is used; otherwise the - no-pattern (if present) is used. If there are more than two alterna- - tives in the subpattern, a compile-time error occurs. - - There are three kinds of condition. If the text between the parentheses - consists of a sequence of digits, the condition is satisfied if the - capturing subpattern of that number has previously matched. The number - must be greater than zero. Consider the following pattern, which con- - tains non-significant white space to make it more readable (assume the - PCRE_EXTENDED option) and to divide it into three parts for ease of - discussion: - - ( \( )? [^()]+ (?(1) \) ) - - The first part matches an optional opening parenthesis, and if that - character is present, sets it as the first captured substring. The sec- - ond part matches one or more characters that are not parentheses. The - third part is a conditional subpattern that tests whether the first set - of parentheses matched or not. If they did, that is, if subject started - with an opening parenthesis, the condition is true, and so the yes-pat- - tern is executed and a closing parenthesis is required. Otherwise, - since no-pattern is not present, the subpattern matches nothing. In - other words, this pattern matches a sequence of non-parentheses, - optionally enclosed in parentheses. - - If the condition is the string (R), it is satisfied if a recursive call - to the pattern or subpattern has been made. At "top level", the condi- - tion is false. This is a PCRE extension. Recursive patterns are - described in the next section. - - If the condition is not a sequence of digits or (R), it must be an - assertion. This may be a positive or negative lookahead or lookbehind - assertion. Consider this pattern, again containing non-significant - white space, and with the two alternatives on the second line: - - (?(?=[^a-z]*[a-z]) - \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) - - The condition is a positive lookahead assertion that matches an - optional sequence of non-letters followed by a letter. In other words, - it tests for the presence of at least one letter in the subject. If a - letter is found, the subject is matched against the first alternative; - otherwise it is matched against the second. This pattern matches - strings in one of the two forms dd-aaa-dd or dd-dd-dd, where aaa are - letters and dd are digits. - - -COMMENTS - - The sequence (?# marks the start of a comment which continues up to the - next closing parenthesis. Nested parentheses are not permitted. The - characters that make up a comment play no part in the pattern matching - at all. - - If the PCRE_EXTENDED option is set, an unescaped # character outside a - character class introduces a comment that continues up to the next new- - line character in the pattern. - - -RECURSIVE PATTERNS - - Consider the problem of matching a string in parentheses, allowing for - unlimited nested parentheses. Without the use of recursion, the best - that can be done is to use a pattern that matches up to some fixed - depth of nesting. It is not possible to handle an arbitrary nesting - depth. Perl has provided an experimental facility that allows regular - expressions to recurse (amongst other things). It does this by interpo- - lating Perl code in the expression at run time, and the code can refer - to the expression itself. A Perl pattern to solve the parentheses prob- - lem can be created like this: - - $re = qr{\( (?: (?>[^()]+) | (?p{$re}) )* \)}x; - - The (?p{...}) item interpolates Perl code at run time, and in this case - refers recursively to the pattern in which it appears. Obviously, PCRE - cannot support the interpolation of Perl code. Instead, it supports - some special syntax for recursion of the entire pattern, and also for - individual subpattern recursion. - - The special item that consists of (? followed by a number greater than - zero and a closing parenthesis is a recursive call of the subpattern of - the given number, provided that it occurs inside that subpattern. (If - not, it is a "subroutine" call, which is described in the next sec- - tion.) The special item (?R) is a recursive call of the entire regular - expression. - - For example, this PCRE pattern solves the nested parentheses problem - (assume the PCRE_EXTENDED option is set so that white space is - ignored): - - \( ( (?>[^()]+) | (?R) )* \) - - First it matches an opening parenthesis. Then it matches any number of - substrings which can either be a sequence of non-parentheses, or a - recursive match of the pattern itself (that is a correctly parenthe- - sized substring). Finally there is a closing parenthesis. - - If this were part of a larger pattern, you would not want to recurse - the entire pattern, so instead you could use this: - - ( \( ( (?>[^()]+) | (?1) )* \) ) - - We have put the pattern into parentheses, and caused the recursion to - refer to them instead of the whole pattern. In a larger pattern, keep- - ing track of parenthesis numbers can be tricky. It may be more conve- - nient to use named parentheses instead. For this, PCRE uses (?P>name), - which is an extension to the Python syntax that PCRE uses for named - parentheses (Perl does not provide named parentheses). We could rewrite - the above example as follows: - - (?P<pn> \( ( (?>[^()]+) | (?P>pn) )* \) ) - - This particular example pattern contains nested unlimited repeats, and - so the use of atomic grouping for matching strings of non-parentheses - is important when applying the pattern to strings that do not match. - For example, when this pattern is applied to - - (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() - - it yields "no match" quickly. However, if atomic grouping is not used, - the match runs for a very long time indeed because there are so many - different ways the + and * repeats can carve up the subject, and all - have to be tested before failure can be reported. - - At the end of a match, the values set for any capturing subpatterns are - those from the outermost level of the recursion at which the subpattern - value is set. If you want to obtain intermediate values, a callout - function can be used (see below and the pcrecallout documentation). If - the pattern above is matched against - - (ab(cd)ef) - - the value for the capturing parentheses is "ef", which is the last - value taken on at the top level. If additional parentheses are added, - giving - - \( ( ( (?>[^()]+) | (?R) )* ) \) - ^ ^ - ^ ^ - - the string they capture is "ab(cd)ef", the contents of the top level - parentheses. If there are more than 15 capturing parentheses in a pat- - tern, PCRE has to obtain extra memory to store data during a recursion, - which it does by using pcre_malloc, freeing it via pcre_free after- - wards. If no memory can be obtained, the match fails with the - PCRE_ERROR_NOMEMORY error. - - Do not confuse the (?R) item with the condition (R), which tests for - recursion. Consider this pattern, which matches text in angle brack- - ets, allowing for arbitrary nesting. Only digits are allowed in nested - brackets (that is, when recursing), whereas any characters are permit- - ted at the outer level. - - < (?: (?(R) \d++ | [^<>]*+) | (?R)) * > - - In this pattern, (?(R) is the start of a conditional subpattern, with - two different alternatives for the recursive and non-recursive cases. - The (?R) item is the actual recursive call. - - -SUBPATTERNS AS SUBROUTINES - - If the syntax for a recursive subpattern reference (either by number or - by name) is used outside the parentheses to which it refers, it oper- - ates like a subroutine in a programming language. An earlier example - pointed out that the pattern - - (sens|respons)e and \1ibility - - matches "sense and sensibility" and "response and responsibility", but - not "sense and responsibility". If instead the pattern - - (sens|respons)e and (?1)ibility - - is used, it does match "sense and responsibility" as well as the other - two strings. Such references must, however, follow the subpattern to - which they refer. - - -CALLOUTS - - Perl has a feature whereby using the sequence (?{...}) causes arbitrary - Perl code to be obeyed in the middle of matching a regular expression. - This makes it possible, amongst other things, to extract different sub- - strings that match the same pair of parentheses when there is a repeti- - tion. - - PCRE provides a similar feature, but of course it cannot obey arbitrary - Perl code. The feature is called "callout". The caller of PCRE provides - an external function by putting its entry point in the global variable - pcre_callout. By default, this variable contains NULL, which disables - all calling out. - - Within a regular expression, (?C) indicates the points at which the - external function is to be called. If you want to identify different - callout points, you can put a number less than 256 after the letter C. - The default value is zero. For example, this pattern has two callout - points: - - (?C1)abc(?C2)def - - During matching, when PCRE reaches a callout point (and pcre_callout is - set), the external function is called. It is provided with the number - of the callout, and, optionally, one item of data originally supplied - by the caller of pcre_exec(). The callout function may cause matching - to backtrack, or to fail altogether. A complete description of the - interface to the callout function is given in the pcrecallout documen- - tation. - -Last updated: 03 February 2003 -Copyright (c) 1997-2003 University of Cambridge. ------------------------------------------------------------------------------ - -PCRE(3) PCRE(3) - - - -NAME - PCRE - Perl-compatible regular expressions - -PCRE PERFORMANCE - - Certain items that may appear in regular expression patterns are more - efficient than others. It is more efficient to use a character class - like [aeiou] than a set of alternatives such as (a|e|i|o|u). In gen- - eral, the simplest construction that provides the required behaviour is - usually the most efficient. Jeffrey Friedl's book contains a lot of - discussion about optimizing regular expressions for efficient perfor- - mance. - - When a pattern begins with .* not in parentheses, or in parentheses - that are not the subject of a backreference, and the PCRE_DOTALL option - is set, the pattern is implicitly anchored by PCRE, since it can match - only at the start of a subject string. However, if PCRE_DOTALL is not - set, PCRE cannot make this optimization, because the . metacharacter - does not then match a newline, and if the subject string contains new- - lines, the pattern may match from the character immediately following - one of them instead of from the very start. For example, the pattern - - .*second - - matches the subject "first\nand second" (where \n stands for a newline - character), with the match starting at the seventh character. In order - to do this, PCRE has to retry the match starting after every newline in - the subject. - - If you are using such a pattern with subject strings that do not con- - tain newlines, the best performance is obtained by setting PCRE_DOTALL, - or starting the pattern with ^.* to indicate explicit anchoring. That - saves PCRE from having to scan along the subject looking for a newline - to restart at. - - Beware of patterns that contain nested indefinite repeats. These can - take a long time to run when applied to a string that does not match. - Consider the pattern fragment - - (a+)* - - This can match "aaaa" in 33 different ways, and this number increases - very rapidly as the string gets longer. (The * repeat can match 0, 1, - 2, 3, or 4 times, and for each of those cases other than 0, the + - repeats can match different numbers of times.) When the remainder of - the pattern is such that the entire match is going to fail, PCRE has in - principle to try every possible variation, and this can take an - extremely long time. - - An optimization catches some of the more simple cases such as - - (a+)*b - - where a literal character follows. Before embarking on the standard - matching procedure, PCRE checks that there is a "b" later in the sub- - ject string, and if there is not, it fails the match immediately. How- - ever, when there is no following literal this optimization cannot be - used. You can see the difference by comparing the behaviour of - - (a+)*\d - - with the pattern above. The former gives a failure almost instantly - when applied to a whole line of "a" characters, whereas the latter - takes an appreciable time with strings longer than about 20 characters. - -Last updated: 03 February 2003 -Copyright (c) 1997-2003 University of Cambridge. ------------------------------------------------------------------------------ - -PCRE(3) PCRE(3) - - - -NAME - PCRE - Perl-compatible regular expressions. - -SYNOPSIS OF POSIX API - #include <pcreposix.h> - - int regcomp(regex_t *preg, const char *pattern, - int cflags); - - int regexec(regex_t *preg, const char *string, - size_t nmatch, regmatch_t pmatch[], int eflags); - - size_t regerror(int errcode, const regex_t *preg, - char *errbuf, size_t errbuf_size); - - void regfree(regex_t *preg); - - -DESCRIPTION - - This set of functions provides a POSIX-style API to the PCRE regular - expression package. See the pcreapi documentation for a description of - the native API, which contains additional functionality. - - The functions described here are just wrapper functions that ultimately - call the PCRE native API. Their prototypes are defined in the - pcreposix.h header file, and on Unix systems the library itself is - called pcreposix.a, so can be accessed by adding -lpcreposix to the - command for linking an application which uses them. Because the POSIX - functions call the native ones, it is also necessary to add -lpcre. - - I have implemented only those option bits that can be reasonably mapped - to PCRE native options. In addition, the options REG_EXTENDED and - REG_NOSUB are defined with the value zero. They have no effect, but - since programs that are written to the POSIX interface often use them, - this makes it easier to slot in PCRE as a replacement library. Other - POSIX options are not even defined. - - When PCRE is called via these functions, it is only the API that is - POSIX-like in style. The syntax and semantics of the regular expres- - sions themselves are still those of Perl, subject to the setting of - various PCRE options, as described below. "POSIX-like in style" means - that the API approximates to the POSIX definition; it is not fully - POSIX-compatible, and in multi-byte encoding domains it is probably - even less compatible. - - The header for these functions is supplied as pcreposix.h to avoid any - potential clash with other POSIX libraries. It can, of course, be - renamed or aliased as regex.h, which is the "correct" name. It provides - two structure types, regex_t for compiled internal forms, and reg- - match_t for returning captured substrings. It also defines some con- - stants whose names start with "REG_"; these are used for setting - options and identifying error codes. - - -COMPILING A PATTERN - - The function regcomp() is called to compile a pattern into an internal - form. The pattern is a C string terminated by a binary zero, and is - passed in the argument pattern. The preg argument is a pointer to a - regex_t structure which is used as a base for storing information about - the compiled expression. - - The argument cflags is either zero, or contains one or more of the bits - defined by the following macros: - - REG_ICASE - - The PCRE_CASELESS option is set when the expression is passed for com- - pilation to the native function. - - REG_NEWLINE - - The PCRE_MULTILINE option is set when the expression is passed for com- - pilation to the native function. Note that this does not mimic the - defined POSIX behaviour for REG_NEWLINE (see the following section). - - In the absence of these flags, no options are passed to the native - function. This means the the regex is compiled with PCRE default - semantics. In particular, the way it handles newline characters in the - subject string is the Perl way, not the POSIX way. Note that setting - PCRE_MULTILINE has only some of the effects specified for REG_NEWLINE. - It does not affect the way newlines are matched by . (they aren't) or - by a negative class such as [^a] (they are). - - The yield of regcomp() is zero on success, and non-zero otherwise. The - preg structure is filled in on success, and one member of the structure - is public: re_nsub contains the number of capturing subpatterns in the - regular expression. Various error codes are defined in the header file. - - -MATCHING NEWLINE CHARACTERS - - This area is not simple, because POSIX and Perl take different views of - things. It is not possible to get PCRE to obey POSIX semantics, but - then PCRE was never intended to be a POSIX engine. The following table - lists the different possibilities for matching newline characters in - PCRE: - - Default Change with - - . matches newline no PCRE_DOTALL - newline matches [^a] yes not changeable - $ matches \n at end yes PCRE_DOLLARENDONLY - $ matches \n in middle no PCRE_MULTILINE - ^ matches \n in middle no PCRE_MULTILINE - - This is the equivalent table for POSIX: - - Default Change with - - . matches newline yes REG_NEWLINE - newline matches [^a] yes REG_NEWLINE - $ matches \n at end no REG_NEWLINE - $ matches \n in middle no REG_NEWLINE - ^ matches \n in middle no REG_NEWLINE - - PCRE's behaviour is the same as Perl's, except that there is no equiva- - lent for PCRE_DOLLARENDONLY in Perl. In both PCRE and Perl, there is no - way to stop newline from matching [^a]. - - The default POSIX newline handling can be obtained by setting - PCRE_DOTALL and PCRE_DOLLARENDONLY, but there is no way to make PCRE - behave exactly as for the REG_NEWLINE action. - - -MATCHING A PATTERN - - The function regexec() is called to match a pre-compiled pattern preg - against a given string, which is terminated by a zero byte, subject to - the options in eflags. These can be: - - REG_NOTBOL - - The PCRE_NOTBOL option is set when calling the underlying PCRE matching - function. - - REG_NOTEOL - - The PCRE_NOTEOL option is set when calling the underlying PCRE matching - function. - - The portion of the string that was matched, and also any captured sub- - strings, are returned via the pmatch argument, which points to an array - of nmatch structures of type regmatch_t, containing the members rm_so - and rm_eo. These contain the offset to the first character of each sub- - string and the offset to the first character after the end of each sub- - string, respectively. The 0th element of the vector relates to the - entire portion of string that was matched; subsequent elements relate - to the capturing subpatterns of the regular expression. Unused entries - in the array have both structure members set to -1. - - A successful match yields a zero return; various error codes are - defined in the header file, of which REG_NOMATCH is the "expected" - failure code. - - -ERROR MESSAGES - - The regerror() function maps a non-zero errorcode from either regcomp() - or regexec() to a printable message. If preg is not NULL, the error - should have arisen from the use of that structure. A message terminated - by a binary zero is placed in errbuf. The length of the message, - including the zero, is limited to errbuf_size. The yield of the func- - tion is the size of buffer needed to hold the whole message. - - -STORAGE - - Compiling a regular expression causes memory to be allocated and asso- - ciated with the preg structure. The function regfree() frees all such - memory, after which preg may no longer be used as a compiled expres- - sion. - - -AUTHOR - - Philip Hazel <ph10@cam.ac.uk> - University Computing Service, - Cambridge CB2 3QG, England. - -Last updated: 03 February 2003 -Copyright (c) 1997-2003 University of Cambridge. ------------------------------------------------------------------------------ - -PCRE(3) PCRE(3) - - - -NAME - PCRE - Perl-compatible regular expressions - -PCRE SAMPLE PROGRAM - - A simple, complete demonstration program, to get you started with using - PCRE, is supplied in the file pcredemo.c in the PCRE distribution. - - The program compiles the regular expression that is its first argument, - and matches it against the subject string in its second argument. No - PCRE options are set, and default character tables are used. If match- - ing succeeds, the program outputs the portion of the subject that - matched, together with the contents of any captured substrings. - - If the -g option is given on the command line, the program then goes on - to check for further matches of the same regular expression in the same - subject string. The logic is a little bit tricky because of the possi- - bility of matching an empty string. Comments in the code explain what - is going on. - - On a Unix system that has PCRE installed in /usr/local, you can compile - the demonstration program using a command like this: - - gcc -o pcredemo pcredemo.c -I/usr/local/include \ - -L/usr/local/lib -lpcre - - Then you can run simple tests like this: - - ./pcredemo 'cat|dog' 'the cat sat on the mat' - ./pcredemo -g 'cat|dog' 'the dog sat on the cat' - - Note that there is a much more comprehensive test program, called - pcretest, which supports many more facilities for testing regular - expressions and the PCRE library. The pcredemo program is provided as a - simple coding example. - - On some operating systems (e.g. Solaris) you may get an error like this - when you try to run pcredemo: - - ld.so.1: a.out: fatal: libpcre.so.0: open failed: No such file or - directory - - This is caused by the way shared library support works on those sys- - tems. You need to add - - -R/usr/local/lib - - to the compile command to get round this problem. - -Last updated: 28 January 2003 -Copyright (c) 1997-2003 University of Cambridge. ------------------------------------------------------------------------------ - diff --git a/external-libs/pcre/doc/pcre_compile.3 b/external-libs/pcre/doc/pcre_compile.3 deleted file mode 100644 index a8273151..00000000 --- a/external-libs/pcre/doc/pcre_compile.3 +++ /dev/null @@ -1,59 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B pcre *pcre_compile(const char *\fIpattern\fR, int \fIoptions\fR, -.ti +5n -.B const char **\fIerrptr\fR, int *\fIerroffset\fR, -.ti +5n -.B const unsigned char *\fItableptr\fR); - -.SH DESCRIPTION -.rs -.sp -This function compiles a regular expression into an internal form. Its -arguments are: - - \fIpattern\fR A zero-terminated string containing the - regular expression to be compiled - \fIoptions\fR Zero or more option bits - \fIerrptr\fR Where to put an error message - \fIerroffset\fR Offset in pattern where error was found - \fItableptr\fR Pointer to character tables, or NULL to - use the built-in default - -The option bits are: - - PCRE_ANCHORED Force pattern anchoring - PCRE_CASELESS Do caseless matching - PCRE_DOLLAR_ENDONLY $ not to match newline at end - PCRE_DOTALL . matches anything including NL - PCRE_EXTENDED Ignore whitespace and # comments - PCRE_EXTRA PCRE extra features - (not much use currently) - PCRE_MULTILINE ^ and $ match newlines within data - PCRE_NO_AUTO_CAPTURE Disable numbered capturing paren- - theses (named ones available) - PCRE_UNGREEDY Invert greediness of quantifiers - PCRE_UTF8 Run in UTF-8 mode - PCRE_NO_UTF8_CHECK Do not check the pattern for UTF-8 - validity (only relevant if - PCRE_UTF8 is set) - -PCRE must be compiled with UTF-8 support in order to use PCRE_UTF8 -(or PCRE_NO_UTF8_CHECK). - -The yield of the function is a pointer to a private data structure that -contains the compiled pattern, or NULL if an error was detected. - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_config.3 b/external-libs/pcre/doc/pcre_config.3 deleted file mode 100644 index 3a0e6998..00000000 --- a/external-libs/pcre/doc/pcre_config.3 +++ /dev/null @@ -1,45 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B int pcre_config(int \fIwhat\fR, void *\fIwhere\fR); - -.SH DESCRIPTION -.rs -.sp -This function makes it possible for a client program to find out which optional -features are available in the version of the PCRE library it is using. Its -arguments are as follows: - - \fIwhat\fR A code specifying what information is required - \fIwhere\fR Points to where to put the data - -The available codes are: - - PCRE_CONFIG_LINK_SIZE Internal link size: 2, 3, or 4 - PCRE_CONFIG_MATCH_LIMIT Internal resource limit - PCRE_CONFIG_NEWLINE Value of the newline character - PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - Threshold of return slots, above - which \fBmalloc()\fR is used by - the POSIX API - PCRE_CONFIG_STACKRECURSE Recursion implementation (1=stack 0=heap) - PCRE_CONFIG_UTF8 Availability of UTF-8 support (1=yes 0=no) - -The function yields 0 on success or PCRE_ERROR_BADOPTION otherwise. - -There is a complete description of the PCRE native API in the -.\" HREF -\fBpcreapi\fR -.\" -page, and a description of the POSIX API in the -.\" HREF -\fBpcreposix\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_copy_named_substring.3 b/external-libs/pcre/doc/pcre_copy_named_substring.3 deleted file mode 100644 index 915bd0a5..00000000 --- a/external-libs/pcre/doc/pcre_copy_named_substring.3 +++ /dev/null @@ -1,40 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B int pcre_copy_named_substring(const pcre *\fIcode\fR, -.ti +5n -.B const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, const char *\fIstringname\fR, -.ti +5n -.B char *\fIbuffer\fR, int \fIbuffersize\fR); - -.SH DESCRIPTION -.rs -.sp -This is a convenience function for extracting a captured substring, identified -by name, into a given buffer. The arguments are: - - \fIcode\fR Pattern that was successfully matched - \fIsubject\fR Subject that has been successfully matched - \fIovector\fR Offset vector that \fBpcre_exec()\fR used - \fIstringcount\fR Value returned by \fBpcre_exec()\fR - \fIstringname\fR Name of the required substring - \fIbuffer\fR Buffer to receive the string - \fIbuffersize\fR Size of buffer - -The yield is the length of the substring, PCRE_ERROR_NOMEMORY if the buffer was -too small, or PCRE_ERROR_NOSUBSTRING if the string name is invalid. - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_copy_substring.3 b/external-libs/pcre/doc/pcre_copy_substring.3 deleted file mode 100644 index d61b99bf..00000000 --- a/external-libs/pcre/doc/pcre_copy_substring.3 +++ /dev/null @@ -1,37 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B int pcre_copy_substring(const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, int \fIstringnumber\fR, char *\fIbuffer\fR, -.ti +5n -.B int \fIbuffersize\fR); - -.SH DESCRIPTION -.rs -.sp -This is a convenience function for extracting a captured substring into a given -buffer. The arguments are: - - \fIsubject\fR Subject that has been successfully matched - \fIovector\fR Offset vector that \fBpcre_exec()\fR used - \fIstringcount\fR Value returned by \fBpcre_exec()\fR - \fIstringnumber\fR Number of the required substring - \fIbuffer\fR Buffer to receive the string - \fIbuffersize\fR Size of buffer - -The yield is the legnth of the string, PCRE_ERROR_NOMEMORY if the buffer was -too small, or PCRE_ERROR_NOSUBSTRING if the string number is invalid. - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_exec.3 b/external-libs/pcre/doc/pcre_exec.3 deleted file mode 100644 index 0d6c3805..00000000 --- a/external-libs/pcre/doc/pcre_exec.3 +++ /dev/null @@ -1,48 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B int pcre_exec(const pcre *\fIcode\fR, "const pcre_extra *\fIextra\fR," -.ti +5n -.B "const char *\fIsubject\fR," int \fIlength\fR, int \fIstartoffset\fR, -.ti +5n -.B int \fIoptions\fR, int *\fIovector\fR, int \fIovecsize\fR); - -.SH DESCRIPTION -.rs -.sp -This function matches a compiled regular expression against a given subject -string, and returns offsets to capturing subexpressions. Its arguments are: - - \fIcode\fR Points to the compiled pattern - \fIextra\fR Points to an associated \fBpcre_extra\fR structure, - or is NULL - \fIsubject\fR Points to the subject string - \fIlength\fR Length of the subject string, in bytes - \fIstartoffset\fR Offset in bytes in the subject at which to - start matching - \fIoptions\fR Option bits - \fIovector\fR Points to a vector of ints for result offsets - \fIovecsize\fR Size of the vector (a multiple of 3) - -The options are: - - PCRE_ANCHORED Match only at the first position - PCRE_NOTBOL Subject is not the beginning of a line - PCRE_NOTEOL Subject is not the end of a line - PCRE_NOTEMPTY An empty string is not a valid match - PCRE_NO_UTF8_CHECK Do not check the subject for UTF-8 - validity (only relevant if PCRE_UTF8 - was set at compile time) - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_free_substring.3 b/external-libs/pcre/doc/pcre_free_substring.3 deleted file mode 100644 index 3fcaf117..00000000 --- a/external-libs/pcre/doc/pcre_free_substring.3 +++ /dev/null @@ -1,24 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B void pcre_free_substring(const char *\fIstringptr\fR); - -.SH DESCRIPTION -.rs -.sp -This is a convenience function for freeing the store obtained by a previous -call to \fBpcre_get_substring()\fR or \fBpcre_get_named_substring()\fR. Its -only argument is a pointer to the string. - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_free_substring_list.3 b/external-libs/pcre/doc/pcre_free_substring_list.3 deleted file mode 100644 index 73d5993d..00000000 --- a/external-libs/pcre/doc/pcre_free_substring_list.3 +++ /dev/null @@ -1,24 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B void pcre_free_substring_list(const char **\fIstringptr\fR); - -.SH DESCRIPTION -.rs -.sp -This is a convenience function for freeing the store obtained by a previous -call to \fBpcre_get_substring_list()\fR. Its only argument is a pointer to the -list of string pointers. - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_fullinfo.3 b/external-libs/pcre/doc/pcre_fullinfo.3 deleted file mode 100644 index 06de985f..00000000 --- a/external-libs/pcre/doc/pcre_fullinfo.3 +++ /dev/null @@ -1,53 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B int pcre_fullinfo(const pcre *\fIcode\fR, "const pcre_extra *\fIextra\fR," -.ti +5n -.B int \fIwhat\fR, void *\fIwhere\fR); - -.SH DESCRIPTION -.rs -.sp -This function returns information about a compiled pattern. Its arguments are: - - \fIcode\fR Compiled regular expression - \fIextra\fR Result of \fBpcre_study()\fR or NULL - \fIwhat\fR What information is required - \fIwhere\fR Where to put the information - -The following information is available: - - PCRE_INFO_BACKREFMAX Number of highest back reference - PCRE_INFO_CAPTURECOUNT Number of capturing subpatterns - PCRE_INFO_FIRSTBYTE Fixed first byte for a match, or - -1 for start of string - or after newline, or - -2 otherwise - PCRE_INFO_FIRSTTABLE Table of first bytes - (after studying) - PCRE_INFO_LASTLITERAL Literal last byte required - PCRE_INFO_NAMECOUNT Number of named subpatterns - PCRE_INFO_NAMEENTRYSIZE Size of name table entry - PCRE_INFO_NAMETABLE Pointer to name table - PCRE_INFO_OPTIONS Options used for compilation - PCRE_INFO_SIZE Size of compiled pattern - -The yield of the function is zero on success or: - - PCRE_ERROR_NULL the argument \fIcode\fR was NULL - the argument \fIwhere\fR was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found - PCRE_ERROR_BADOPTION the value of \fIwhat\fR was invalid - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_get_named_substring.3 b/external-libs/pcre/doc/pcre_get_named_substring.3 deleted file mode 100644 index 6d3f80ea..00000000 --- a/external-libs/pcre/doc/pcre_get_named_substring.3 +++ /dev/null @@ -1,40 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B int pcre_get_named_substring(const pcre *\fIcode\fR, -.ti +5n -.B const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, const char *\fIstringname\fR, -.ti +5n -.B const char **\fIstringptr\fR); - -.SH DESCRIPTION -.rs -.sp -This is a convenience function for extracting a captured substring by name. The -arguments are: - - \fIcode\fR Compiled pattern - \fIsubject\fR Subject that has been successfully matched - \fIovector\fR Offset vector that \fBpcre_exec()\fR used - \fIstringcount\fR Value returned by \fBpcre_exec()\fR - \fIstringname\fR Name of the required substring - \fIstringptr\fR Where to put the string pointer - -The yield is the length of the extracted substring, PCRE_ERROR_NOMEMORY if -sufficient memory could not be obtained, or PCRE_ERROR_NOSUBSTRING if the -string name is invalid. - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_get_stringnumber.3 b/external-libs/pcre/doc/pcre_get_stringnumber.3 deleted file mode 100644 index f6c9357f..00000000 --- a/external-libs/pcre/doc/pcre_get_stringnumber.3 +++ /dev/null @@ -1,31 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B int pcre_get_stringnumber(const pcre *\fIcode\fR, -.ti +5n -.B const char *\fIname\fR); - -.SH DESCRIPTION -.rs -.sp -This convenience function finds the number of a named substring capturing -parenthesis in a compiled pattern. Its arguments are: - - \fIcode\fR Compiled regular expression - \fIname\fR Name whose number is required - -The yield of the function is the number of the parenthesis if the name is -found, or PCRE_ERROR_NOSUBSTRING otherwise. - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_get_substring.3 b/external-libs/pcre/doc/pcre_get_substring.3 deleted file mode 100644 index 4c92c9c5..00000000 --- a/external-libs/pcre/doc/pcre_get_substring.3 +++ /dev/null @@ -1,37 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B int pcre_get_substring(const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, int \fIstringnumber\fR, -.ti +5n -.B const char **\fIstringptr\fR); - -.SH DESCRIPTION -.rs -.sp -This is a convenience function for extracting a captured substring. The -arguments are: - - \fIsubject\fR Subject that has been successfully matched - \fIovector\fR Offset vector that \fBpcre_exec()\fR used - \fIstringcount\fR Value returned by \fBpcre_exec()\fR - \fIstringnumber\fR Number of the required substring - \fIstringptr\fR Where to put the string pointer - -The yield is the length of the substring, PCRE_ERROR_NOMEMORY if sufficient -memory could not be obtained, or PCRE_ERROR_NOSUBSTRING if the string number is -invalid. - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_get_substring_list.3 b/external-libs/pcre/doc/pcre_get_substring_list.3 deleted file mode 100644 index 69090e1b..00000000 --- a/external-libs/pcre/doc/pcre_get_substring_list.3 +++ /dev/null @@ -1,33 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B int pcre_get_substring_list(const char *\fIsubject\fR, -.ti +5n -.B int *\fIovector\fR, int \fIstringcount\fR, "const char ***\fIlistptr\fR);" - -.SH DESCRIPTION -.rs -.sp -This is a convenience function for extracting a list of all the captured -substrings. The arguments are: - - \fIsubject\fR Subject that has been successfully matched - \fIovector\fR Offset vector that \fBpcre_exec\fR used - \fIstringcount\fR Value returned by \fBpcre_exec\fR - \fIlistptr\fR Where to put a pointer to the list - -The yield is zero on success or PCRE_ERROR_NOMEMORY if sufficient memory could -not be obtained. - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_info.3 b/external-libs/pcre/doc/pcre_info.3 deleted file mode 100644 index c4970764..00000000 --- a/external-libs/pcre/doc/pcre_info.3 +++ /dev/null @@ -1,23 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B int pcre_info(const pcre *\fIcode\fR, int *\fIoptptr\fR, int -.B *\fIfirstcharptr\fR); - -.SH DESCRIPTION -.rs -.sp -This function is obsolete. You should be using \fBpcre_fullinfo()\fR instead. - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_maketables.3 b/external-libs/pcre/doc/pcre_maketables.3 deleted file mode 100644 index 7d459ed4..00000000 --- a/external-libs/pcre/doc/pcre_maketables.3 +++ /dev/null @@ -1,26 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B const unsigned char *pcre_maketables(void); - -.SH DESCRIPTION -.rs -.sp -This function builds a set of character tables which can be passed to -\fBpcre_compile()\fR to override PCRE's internal, built-in tables (which were -made by \fBpcre_maketables()\fR when PCRE was compiled). You might want to do -this if you are using a non-standard locale. The function yields a pointer to -the tables. - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_study.3 b/external-libs/pcre/doc/pcre_study.3 deleted file mode 100644 index 69ff20e4..00000000 --- a/external-libs/pcre/doc/pcre_study.3 +++ /dev/null @@ -1,36 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B pcre_extra *pcre_study(const pcre *\fIcode\fR, int \fIoptions\fR, -.ti +5n -.B const char **\fIerrptr\fR); - -.SH DESCRIPTION -.rs -.sp -This function studies a compiled pattern, to see if additional information can -be extracted that might speed up matching. Its arguments are: - - \fIcode\fR A compiled regular expression - \fIoptions\fR Options for \fBpcre_study()\fR - \fIerrptr\fR Where to put an error message - -If the function returns NULL, either it could not find any additional -information, or there was an error. You can tell the difference by looking at -the error value. It is NULL in first case. - -There are currently no options defined; the value of the second argument should -always be zero. - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcre_version.3 b/external-libs/pcre/doc/pcre_version.3 deleted file mode 100644 index 6f981224..00000000 --- a/external-libs/pcre/doc/pcre_version.3 +++ /dev/null @@ -1,23 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B char *pcre_version(void); - -.SH DESCRIPTION -.rs -.sp -This function returns a character string that gives the version number of the -PCRE library, and its date of release. - -There is a complete description of the PCRE API in the -.\" HREF -\fBpcreapi\fR -.\" -page. diff --git a/external-libs/pcre/doc/pcreapi.3 b/external-libs/pcre/doc/pcreapi.3 deleted file mode 100644 index 4c7d43c3..00000000 --- a/external-libs/pcre/doc/pcreapi.3 +++ /dev/null @@ -1,1082 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH SYNOPSIS OF PCRE API -.rs -.sp -.B #include <pcre.h> -.PP -.SM -.br -.B pcre *pcre_compile(const char *\fIpattern\fR, int \fIoptions\fR, -.ti +5n -.B const char **\fIerrptr\fR, int *\fIerroffset\fR, -.ti +5n -.B const unsigned char *\fItableptr\fR); -.PP -.br -.B pcre_extra *pcre_study(const pcre *\fIcode\fR, int \fIoptions\fR, -.ti +5n -.B const char **\fIerrptr\fR); -.PP -.br -.B int pcre_exec(const pcre *\fIcode\fR, "const pcre_extra *\fIextra\fR," -.ti +5n -.B "const char *\fIsubject\fR," int \fIlength\fR, int \fIstartoffset\fR, -.ti +5n -.B int \fIoptions\fR, int *\fIovector\fR, int \fIovecsize\fR); -.PP -.br -.B int pcre_copy_named_substring(const pcre *\fIcode\fR, -.ti +5n -.B const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, const char *\fIstringname\fR, -.ti +5n -.B char *\fIbuffer\fR, int \fIbuffersize\fR); -.PP -.br -.B int pcre_copy_substring(const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, int \fIstringnumber\fR, char *\fIbuffer\fR, -.ti +5n -.B int \fIbuffersize\fR); -.PP -.br -.B int pcre_get_named_substring(const pcre *\fIcode\fR, -.ti +5n -.B const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, const char *\fIstringname\fR, -.ti +5n -.B const char **\fIstringptr\fR); -.PP -.br -.B int pcre_get_stringnumber(const pcre *\fIcode\fR, -.ti +5n -.B const char *\fIname\fR); -.PP -.br -.B int pcre_get_substring(const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, int \fIstringnumber\fR, -.ti +5n -.B const char **\fIstringptr\fR); -.PP -.br -.B int pcre_get_substring_list(const char *\fIsubject\fR, -.ti +5n -.B int *\fIovector\fR, int \fIstringcount\fR, "const char ***\fIlistptr\fR);" -.PP -.br -.B void pcre_free_substring(const char *\fIstringptr\fR); -.PP -.br -.B void pcre_free_substring_list(const char **\fIstringptr\fR); -.PP -.br -.B const unsigned char *pcre_maketables(void); -.PP -.br -.B int pcre_fullinfo(const pcre *\fIcode\fR, "const pcre_extra *\fIextra\fR," -.ti +5n -.B int \fIwhat\fR, void *\fIwhere\fR); -.PP -.br -.B int pcre_info(const pcre *\fIcode\fR, int *\fIoptptr\fR, int -.B *\fIfirstcharptr\fR); -.PP -.br -.B int pcre_config(int \fIwhat\fR, void *\fIwhere\fR); -.PP -.br -.B char *pcre_version(void); -.PP -.br -.B void *(*pcre_malloc)(size_t); -.PP -.br -.B void (*pcre_free)(void *); -.PP -.br -.B void *(*pcre_stack_malloc)(size_t); -.PP -.br -.B void (*pcre_stack_free)(void *); -.PP -.br -.B int (*pcre_callout)(pcre_callout_block *); - -.SH PCRE API -.rs -.sp -PCRE has its own native API, which is described in this document. There is also -a set of wrapper functions that correspond to the POSIX regular expression API. -These are described in the \fBpcreposix\fR documentation. - -The native API function prototypes are defined in the header file \fBpcre.h\fR, -and on Unix systems the library itself is called \fBlibpcre.a\fR, so can be -accessed by adding \fB-lpcre\fR to the command for linking an application which -calls it. The header file defines the macros PCRE_MAJOR and PCRE_MINOR to -contain the major and minor release numbers for the library. Applications can -use these to include support for different releases. - -The functions \fBpcre_compile()\fR, \fBpcre_study()\fR, and \fBpcre_exec()\fR -are used for compiling and matching regular expressions. A sample program that -demonstrates the simplest way of using them is given in the file -\fIpcredemo.c\fR. The \fBpcresample\fR documentation describes how to run it. - -There are convenience functions for extracting captured substrings from a -matched subject string. They are: - - \fBpcre_copy_substring()\fR - \fBpcre_copy_named_substring()\fR - \fBpcre_get_substring()\fR - \fBpcre_get_named_substring()\fR - \fBpcre_get_substring_list()\fR - -\fBpcre_free_substring()\fR and \fBpcre_free_substring_list()\fR are also -provided, to free the memory used for extracted strings. - -The function \fBpcre_maketables()\fR is used (optionally) to build a set of -character tables in the current locale for passing to \fBpcre_compile()\fR. - -The function \fBpcre_fullinfo()\fR is used to find out information about a -compiled pattern; \fBpcre_info()\fR is an obsolete version which returns only -some of the available information, but is retained for backwards compatibility. -The function \fBpcre_version()\fR returns a pointer to a string containing the -version of PCRE and its date of release. - -The global variables \fBpcre_malloc\fR and \fBpcre_free\fR initially contain -the entry points of the standard \fBmalloc()\fR and \fBfree()\fR functions -respectively. PCRE calls the memory management functions via these variables, -so a calling program can replace them if it wishes to intercept the calls. This -should be done before calling any PCRE functions. - -The global variables \fBpcre_stack_malloc\fR and \fBpcre_stack_free\fR are also -indirections to memory management functions. These special functions are used -only when PCRE is compiled to use the heap for remembering data, instead of -recursive function calls. This is a non-standard way of building PCRE, for use -in environments that have limited stacks. Because of the greater use of memory -management, it runs more slowly. Separate functions are provided so that -special-purpose external code can be used for this case. When used, these -functions are always called in a stack-like manner (last obtained, first -freed), and always for memory blocks of the same size. - -The global variable \fBpcre_callout\fR initially contains NULL. It can be set -by the caller to a "callout" function, which PCRE will then call at specified -points during a matching operation. Details are given in the \fBpcrecallout\fR -documentation. - -.SH MULTITHREADING -.rs -.sp -The PCRE functions can be used in multi-threading applications, with the -proviso that the memory management functions pointed to by \fBpcre_malloc\fR, -\fBpcre_free\fR, \fBpcre_stack_malloc\fR, and \fBpcre_stack_free\fR, and the -callout function pointed to by \fBpcre_callout\fR, are shared by all threads. - -The compiled form of a regular expression is not altered during matching, so -the same compiled pattern can safely be used by several threads at once. - -.SH CHECKING BUILD-TIME OPTIONS -.rs -.sp -.B int pcre_config(int \fIwhat\fR, void *\fIwhere\fR); -.PP -The function \fBpcre_config()\fR makes it possible for a PCRE client to -discover which optional features have been compiled into the PCRE library. The -.\" HREF -\fBpcrebuild\fR -.\" -documentation has more details about these optional features. - -The first argument for \fBpcre_config()\fR is an integer, specifying which -information is required; the second argument is a pointer to a variable into -which the information is placed. The following information is available: - - PCRE_CONFIG_UTF8 - -The output is an integer that is set to one if UTF-8 support is available; -otherwise it is set to zero. - - PCRE_CONFIG_NEWLINE - -The output is an integer that is set to the value of the code that is used for -the newline character. It is either linefeed (10) or carriage return (13), and -should normally be the standard character for your operating system. - - PCRE_CONFIG_LINK_SIZE - -The output is an integer that contains the number of bytes used for internal -linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values -allow larger regular expressions to be compiled, at the expense of slower -matching. The default value of 2 is sufficient for all but the most massive -patterns, since it allows the compiled pattern to be up to 64K in size. - - PCRE_CONFIG_POSIX_MALLOC_THRESHOLD - -The output is an integer that contains the threshold above which the POSIX -interface uses \fBmalloc()\fR for output vectors. Further details are given in -the \fBpcreposix\fR documentation. - - PCRE_CONFIG_MATCH_LIMIT - -The output is an integer that gives the default limit for the number of -internal matching function calls in a \fBpcre_exec()\fR execution. Further -details are given with \fBpcre_exec()\fR below. - - PCRE_CONFIG_STACKRECURSE - -The output is an integer that is set to one if internal recursion is -implemented by recursive function calls that use the stack to remember their -state. This is the usual way that PCRE is compiled. The output is zero if PCRE -was compiled to use blocks of data on the heap instead of recursive function -calls. In this case, \fBpcre_stack_malloc\fR and \fBpcre_stack_free\fR are -called to manage memory blocks on the heap, thus avoiding the use of the stack. - -.SH COMPILING A PATTERN -.rs -.sp -.B pcre *pcre_compile(const char *\fIpattern\fR, int \fIoptions\fR, -.ti +5n -.B const char **\fIerrptr\fR, int *\fIerroffset\fR, -.ti +5n -.B const unsigned char *\fItableptr\fR); -.PP - -The function \fBpcre_compile()\fR is called to compile a pattern into an -internal form. The pattern is a C string terminated by a binary zero, and -is passed in the argument \fIpattern\fR. A pointer to a single block of memory -that is obtained via \fBpcre_malloc\fR is returned. This contains the compiled -code and related data. The \fBpcre\fR type is defined for the returned block; -this is a typedef for a structure whose contents are not externally defined. It -is up to the caller to free the memory when it is no longer required. - -Although the compiled code of a PCRE regex is relocatable, that is, it does not -depend on memory location, the complete \fBpcre\fR data block is not -fully relocatable, because it contains a copy of the \fItableptr\fR argument, -which is an address (see below). - -The \fIoptions\fR argument contains independent bits that affect the -compilation. It should be zero if no options are required. Some of the options, -in particular, those that are compatible with Perl, can also be set and unset -from within the pattern (see the detailed description of regular expressions -in the \fBpcrepattern\fR documentation). For these options, the contents of the -\fIoptions\fR argument specifies their initial settings at the start of -compilation and execution. The PCRE_ANCHORED option can be set at the time of -matching as well as at compile time. - -If \fIerrptr\fR is NULL, \fBpcre_compile()\fR returns NULL immediately. -Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fR returns -NULL, and sets the variable pointed to by \fIerrptr\fR to point to a textual -error message. The offset from the start of the pattern to the character where -the error was discovered is placed in the variable pointed to by -\fIerroffset\fR, which must not be NULL. If it is, an immediate error is given. - -If the final argument, \fItableptr\fR, is NULL, PCRE uses a default set of -character tables which are built when it is compiled, using the default C -locale. Otherwise, \fItableptr\fR must be the result of a call to -\fBpcre_maketables()\fR. See the section on locale support below. - -This code fragment shows a typical straightforward call to \fBpcre_compile()\fR: - - pcre *re; - const char *error; - int erroffset; - re = pcre_compile( - "^A.*Z", /* the pattern */ - 0, /* default options */ - &error, /* for error message */ - &erroffset, /* for error offset */ - NULL); /* use default character tables */ - -The following option bits are defined: - - PCRE_ANCHORED - -If this bit is set, the pattern is forced to be "anchored", that is, it is -constrained to match only at the first matching point in the string which is -being searched (the "subject string"). This effect can also be achieved by -appropriate constructs in the pattern itself, which is the only way to do it in -Perl. - - PCRE_CASELESS - -If this bit is set, letters in the pattern match both upper and lower case -letters. It is equivalent to Perl's /i option, and it can be changed within a -pattern by a (?i) option setting. - - PCRE_DOLLAR_ENDONLY - -If this bit is set, a dollar metacharacter in the pattern matches only at the -end of the subject string. Without this option, a dollar also matches -immediately before the final character if it is a newline (but not before any -other newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is -set. There is no equivalent to this option in Perl, and no way to set it within -a pattern. - - PCRE_DOTALL - -If this bit is set, a dot metacharater in the pattern matches all characters, -including newlines. Without it, newlines are excluded. This option is -equivalent to Perl's /s option, and it can be changed within a pattern by a -(?s) option setting. A negative class such as [^a] always matches a newline -character, independent of the setting of this option. - - PCRE_EXTENDED - -If this bit is set, whitespace data characters in the pattern are totally -ignored except when escaped or inside a character class. Whitespace does not -include the VT character (code 11). In addition, characters between an -unescaped # outside a character class and the next newline character, -inclusive, are also ignored. This is equivalent to Perl's /x option, and it can -be changed within a pattern by a (?x) option setting. - -This option makes it possible to include comments inside complicated patterns. -Note, however, that this applies only to data characters. Whitespace characters -may never appear within special character sequences in a pattern, for example -within the sequence (?( which introduces a conditional subpattern. - - PCRE_EXTRA - -This option was invented in order to turn on additional functionality of PCRE -that is incompatible with Perl, but it is currently of very little use. When -set, any backslash in a pattern that is followed by a letter that has no -special meaning causes an error, thus reserving these combinations for future -expansion. By default, as in Perl, a backslash followed by a letter with no -special meaning is treated as a literal. There are at present no other features -controlled by this option. It can also be set by a (?X) option setting within a -pattern. - - PCRE_MULTILINE - -By default, PCRE treats the subject string as consisting of a single "line" of -characters (even if it actually contains several newlines). The "start of line" -metacharacter (^) matches only at the start of the string, while the "end of -line" metacharacter ($) matches only at the end of the string, or before a -terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as -Perl. - -When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs -match immediately following or immediately before any newline in the subject -string, respectively, as well as at the very start and end. This is equivalent -to Perl's /m option, and it can be changed within a pattern by a (?m) option -setting. If there are no "\\n" characters in a subject string, or no -occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect. - - PCRE_NO_AUTO_CAPTURE - -If this option is set, it disables the use of numbered capturing parentheses in -the pattern. Any opening parenthesis that is not followed by ? behaves as if it -were followed by ?: but named parentheses can still be used for capturing (and -they acquire numbers in the usual way). There is no equivalent of this option -in Perl. - - PCRE_UNGREEDY - -This option inverts the "greediness" of the quantifiers so that they are not -greedy by default, but become greedy if followed by "?". It is not compatible -with Perl. It can also be set by a (?U) option setting within the pattern. - - PCRE_UTF8 - -This option causes PCRE to regard both the pattern and the subject as strings -of UTF-8 characters instead of single-byte character strings. However, it is -available only if PCRE has been built to include UTF-8 support. If not, the use -of this option provokes an error. Details of how this option changes the -behaviour of PCRE are given in the -.\" HTML <a href="pcre.html#utf8support"> -.\" </a> -section on UTF-8 support -.\" -in the main -.\" HREF -\fBpcre\fR -.\" -page. - - PCRE_NO_UTF8_CHECK - -When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is -automatically checked. If an invalid UTF-8 sequence of bytes is found, -\fBpcre_compile()\fR returns an error. If you already know that your pattern is -valid, and you want to skip this check for performance reasons, you can set the -PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid -UTF-8 string as a pattern is undefined. It may cause your program to crash. -Note that there is a similar option for suppressing the checking of subject -strings passed to \fBpcre_exec()\fR. - - -.SH STUDYING A PATTERN -.rs -.sp -.B pcre_extra *pcre_study(const pcre *\fIcode\fR, int \fIoptions\fR, -.ti +5n -.B const char **\fIerrptr\fR); -.PP -When a pattern is going to be used several times, it is worth spending more -time analyzing it in order to speed up the time taken for matching. The -function \fBpcre_study()\fR takes a pointer to a compiled pattern as its first -argument. If studing the pattern produces additional information that will help -speed up matching, \fBpcre_study()\fR returns a pointer to a \fBpcre_extra\fR -block, in which the \fIstudy_data\fR field points to the results of the study. - -The returned value from a \fBpcre_study()\fR can be passed directly to -\fBpcre_exec()\fR. However, the \fBpcre_extra\fR block also contains other -fields that can be set by the caller before the block is passed; these are -described below. If studying the pattern does not produce any additional -information, \fBpcre_study()\fR returns NULL. In that circumstance, if the -calling program wants to pass some of the other fields to \fBpcre_exec()\fR, it -must set up its own \fBpcre_extra\fR block. - -The second argument contains option bits. At present, no options are defined -for \fBpcre_study()\fR, and this argument should always be zero. - -The third argument for \fBpcre_study()\fR is a pointer for an error message. If -studying succeeds (even if no data is returned), the variable it points to is -set to NULL. Otherwise it points to a textual error message. You should -therefore test the error pointer for NULL after calling \fBpcre_study()\fR, to -be sure that it has run successfully. - -This is a typical call to \fBpcre_study\fR(): - - pcre_extra *pe; - pe = pcre_study( - re, /* result of pcre_compile() */ - 0, /* no options exist */ - &error); /* set to NULL or points to a message */ - -At present, studying a pattern is useful only for non-anchored patterns that do -not have a single fixed starting character. A bitmap of possible starting -characters is created. - -.\" HTML <a name="localesupport"></a> -.SH LOCALE SUPPORT -.rs -.sp -PCRE handles caseless matching, and determines whether characters are letters, -digits, or whatever, by reference to a set of tables. When running in UTF-8 -mode, this applies only to characters with codes less than 256. The library -contains a default set of tables that is created in the default C locale when -PCRE is compiled. This is used when the final argument of \fBpcre_compile()\fR -is NULL, and is sufficient for many applications. - -An alternative set of tables can, however, be supplied. Such tables are built -by calling the \fBpcre_maketables()\fR function, which has no arguments, in the -relevant locale. The result can then be passed to \fBpcre_compile()\fR as often -as necessary. For example, to build and use tables that are appropriate for the -French locale (where accented characters with codes greater than 128 are -treated as letters), the following code could be used: - - setlocale(LC_CTYPE, "fr"); - tables = pcre_maketables(); - re = pcre_compile(..., tables); - -The tables are built in memory that is obtained via \fBpcre_malloc\fR. The -pointer that is passed to \fBpcre_compile\fR is saved with the compiled -pattern, and the same tables are used via this pointer by \fBpcre_study()\fR -and \fBpcre_exec()\fR. Thus, for any single pattern, compilation, studying and -matching all happen in the same locale, but different patterns can be compiled -in different locales. It is the caller's responsibility to ensure that the -memory containing the tables remains available for as long as it is needed. - -.SH INFORMATION ABOUT A PATTERN -.rs -.sp -.B int pcre_fullinfo(const pcre *\fIcode\fR, "const pcre_extra *\fIextra\fR," -.ti +5n -.B int \fIwhat\fR, void *\fIwhere\fR); -.PP -The \fBpcre_fullinfo()\fR function returns information about a compiled -pattern. It replaces the obsolete \fBpcre_info()\fR function, which is -nevertheless retained for backwards compability (and is documented below). - -The first argument for \fBpcre_fullinfo()\fR is a pointer to the compiled -pattern. The second argument is the result of \fBpcre_study()\fR, or NULL if -the pattern was not studied. The third argument specifies which piece of -information is required, and the fourth argument is a pointer to a variable -to receive the data. The yield of the function is zero for success, or one of -the following negative numbers: - - PCRE_ERROR_NULL the argument \fIcode\fR was NULL - the argument \fIwhere\fR was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found - PCRE_ERROR_BADOPTION the value of \fIwhat\fR was invalid - -Here is a typical call of \fBpcre_fullinfo()\fR, to obtain the length of the -compiled pattern: - - int rc; - unsigned long int length; - rc = pcre_fullinfo( - re, /* result of pcre_compile() */ - pe, /* result of pcre_study(), or NULL */ - PCRE_INFO_SIZE, /* what is required */ - &length); /* where to put the data */ - -The possible values for the third argument are defined in \fBpcre.h\fR, and are -as follows: - - PCRE_INFO_BACKREFMAX - -Return the number of the highest back reference in the pattern. The fourth -argument should point to an \fBint\fR variable. Zero is returned if there are -no back references. - - PCRE_INFO_CAPTURECOUNT - -Return the number of capturing subpatterns in the pattern. The fourth argument -should point to an \fbint\fR variable. - - PCRE_INFO_FIRSTBYTE - -Return information about the first byte of any matched string, for a -non-anchored pattern. (This option used to be called PCRE_INFO_FIRSTCHAR; the -old name is still recognized for backwards compatibility.) - -If there is a fixed first byte, e.g. from a pattern such as (cat|cow|coyote), -it is returned in the integer pointed to by \fIwhere\fR. Otherwise, if either - -(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch -starts with "^", or - -(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set -(if it were set, the pattern would be anchored), - --1 is returned, indicating that the pattern matches only at the start of a -subject string or after any newline within the string. Otherwise -2 is -returned. For anchored patterns, -2 is returned. - - PCRE_INFO_FIRSTTABLE - -If the pattern was studied, and this resulted in the construction of a 256-bit -table indicating a fixed set of bytes for the first byte in any matching -string, a pointer to the table is returned. Otherwise NULL is returned. The -fourth argument should point to an \fBunsigned char *\fR variable. - - PCRE_INFO_LASTLITERAL - -Return the value of the rightmost literal byte that must exist in any matched -string, other than at its start, if such a byte has been recorded. The fourth -argument should point to an \fBint\fR variable. If there is no such byte, -1 is -returned. For anchored patterns, a last literal byte is recorded only if it -follows something of variable length. For example, for the pattern -/^a\\d+z\\d+/ the returned value is "z", but for /^a\\dz\\d/ the returned value -is -1. - - PCRE_INFO_NAMECOUNT - PCRE_INFO_NAMEENTRYSIZE - PCRE_INFO_NAMETABLE - -PCRE supports the use of named as well as numbered capturing parentheses. The -names are just an additional way of identifying the parentheses, which still -acquire a number. A caller that wants to extract data from a named subpattern -must convert the name to a number in order to access the correct pointers in -the output vector (described with \fBpcre_exec()\fR below). In order to do -this, it must first use these three values to obtain the name-to-number mapping -table for the pattern. - -The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives -the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each -entry; both of these return an \fBint\fR value. The entry size depends on the -length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first -entry of the table (a pointer to \fBchar\fR). The first two bytes of each entry -are the number of the capturing parenthesis, most significant byte first. The -rest of the entry is the corresponding name, zero terminated. The names are in -alphabetical order. For example, consider the following pattern (assume -PCRE_EXTENDED is set, so white space - including newlines - is ignored): - - (?P<date> (?P<year>(\\d\\d)?\\d\\d) - - (?P<month>\\d\\d) - (?P<day>\\d\\d) ) - -There are four named subpatterns, so the table has four entries, and each entry -in the table is eight bytes long. The table is as follows, with non-printing -bytes shows in hex, and undefined bytes shown as ??: - - 00 01 d a t e 00 ?? - 00 05 d a y 00 ?? ?? - 00 04 m o n t h 00 - 00 02 y e a r 00 ?? - -When writing code to extract data from named subpatterns, remember that the -length of each entry may be different for each compiled pattern. - - PCRE_INFO_OPTIONS - -Return a copy of the options with which the pattern was compiled. The fourth -argument should point to an \fBunsigned long int\fR variable. These option bits -are those specified in the call to \fBpcre_compile()\fR, modified by any -top-level option settings within the pattern itself. - -A pattern is automatically anchored by PCRE if all of its top-level -alternatives begin with one of the following: - - ^ unless PCRE_MULTILINE is set - \\A always - \\G always - .* if PCRE_DOTALL is set and there are no back - references to the subpattern in which .* appears - -For such patterns, the PCRE_ANCHORED bit is set in the options returned by -\fBpcre_fullinfo()\fR. - - PCRE_INFO_SIZE - -Return the size of the compiled pattern, that is, the value that was passed as -the argument to \fBpcre_malloc()\fR when PCRE was getting memory in which to -place the compiled data. The fourth argument should point to a \fBsize_t\fR -variable. - - PCRE_INFO_STUDYSIZE - -Returns the size of the data block pointed to by the \fIstudy_data\fR field in -a \fBpcre_extra\fR block. That is, it is the value that was passed to -\fBpcre_malloc()\fR when PCRE was getting memory into which to place the data -created by \fBpcre_study()\fR. The fourth argument should point to a -\fBsize_t\fR variable. - -.SH OBSOLETE INFO FUNCTION -.rs -.sp -.B int pcre_info(const pcre *\fIcode\fR, int *\fIoptptr\fR, int -.B *\fIfirstcharptr\fR); -.PP -The \fBpcre_info()\fR function is now obsolete because its interface is too -restrictive to return all the available data about a compiled pattern. New -programs should use \fBpcre_fullinfo()\fR instead. The yield of -\fBpcre_info()\fR is the number of capturing subpatterns, or one of the -following negative numbers: - - PCRE_ERROR_NULL the argument \fIcode\fR was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found - -If the \fIoptptr\fR argument is not NULL, a copy of the options with which the -pattern was compiled is placed in the integer it points to (see -PCRE_INFO_OPTIONS above). - -If the pattern is not anchored and the \fIfirstcharptr\fR argument is not NULL, -it is used to pass back information about the first character of any matched -string (see PCRE_INFO_FIRSTBYTE above). - -.SH MATCHING A PATTERN -.rs -.sp -.B int pcre_exec(const pcre *\fIcode\fR, "const pcre_extra *\fIextra\fR," -.ti +5n -.B "const char *\fIsubject\fR," int \fIlength\fR, int \fIstartoffset\fR, -.ti +5n -.B int \fIoptions\fR, int *\fIovector\fR, int \fIovecsize\fR); -.PP -The function \fBpcre_exec()\fR is called to match a subject string against a -pre-compiled pattern, which is passed in the \fIcode\fR argument. If the -pattern has been studied, the result of the study should be passed in the -\fIextra\fR argument. - -Here is an example of a simple call to \fBpcre_exec()\fR: - - int rc; - int ovector[30]; - rc = pcre_exec( - re, /* result of pcre_compile() */ - NULL, /* we didn't study the pattern */ - "some string", /* the subject string */ - 11, /* the length of the subject string */ - 0, /* start at offset 0 in the subject */ - 0, /* default options */ - ovector, /* vector for substring information */ - 30); /* number of elements in the vector */ - -If the \fIextra\fR argument is not NULL, it must point to a \fBpcre_extra\fR -data block. The \fBpcre_study()\fR function returns such a block (when it -doesn't return NULL), but you can also create one for yourself, and pass -additional information in it. The fields in the block are as follows: - - unsigned long int \fIflags\fR; - void *\fIstudy_data\fR; - unsigned long int \fImatch_limit\fR; - void *\fIcallout_data\fR; - -The \fIflags\fR field is a bitmap that specifies which of the other fields -are set. The flag bits are: - - PCRE_EXTRA_STUDY_DATA - PCRE_EXTRA_MATCH_LIMIT - PCRE_EXTRA_CALLOUT_DATA - -Other flag bits should be set to zero. The \fIstudy_data\fR field is set in the -\fBpcre_extra\fR block that is returned by \fBpcre_study()\fR, together with -the appropriate flag bit. You should not set this yourself, but you can add to -the block by setting the other fields. - -The \fImatch_limit\fR field provides a means of preventing PCRE from using up a -vast amount of resources when running patterns that are not going to match, -but which have a very large number of possibilities in their search trees. The -classic example is the use of nested unlimited repeats. Internally, PCRE uses a -function called \fBmatch()\fR which it calls repeatedly (sometimes -recursively). The limit is imposed on the number of times this function is -called during a match, which has the effect of limiting the amount of recursion -and backtracking that can take place. For patterns that are not anchored, the -count starts from zero for each position in the subject string. - -The default limit for the library can be set when PCRE is built; the default -default is 10 million, which handles all but the most extreme cases. You can -reduce the default by suppling \fBpcre_exec()\fR with a \fRpcre_extra\fR block -in which \fImatch_limit\fR is set to a smaller value, and -PCRE_EXTRA_MATCH_LIMIT is set in the \fIflags\fR field. If the limit is -exceeded, \fBpcre_exec()\fR returns PCRE_ERROR_MATCHLIMIT. - -The \fIpcre_callout\fR field is used in conjunction with the "callout" feature, -which is described in the \fBpcrecallout\fR documentation. - -The PCRE_ANCHORED option can be passed in the \fIoptions\fR argument, whose -unused bits must be zero. This limits \fBpcre_exec()\fR to matching at the -first matching position. However, if a pattern was compiled with PCRE_ANCHORED, -or turned out to be anchored by virtue of its contents, it cannot be made -unachored at matching time. - -When PCRE_UTF8 was set at compile time, the validity of the subject as a UTF-8 -string is automatically checked, and the value of \fIstartoffset\fR is also -checked to ensure that it points to the start of a UTF-8 character. If an -invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fR returns the error -PCRE_ERROR_BADUTF8. If \fIstartoffset\fR contains an invalid value, -PCRE_ERROR_BADUTF8_OFFSET is returned. - -If you already know that your subject is valid, and you want to skip these -checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when -calling \fBpcre_exec()\fR. You might want to do this for the second and -subsequent calls to \fBpcre_exec()\fR if you are making repeated calls to find -all the matches in a single subject string. However, you should be sure that -the value of \fIstartoffset\fR points to the start of a UTF-8 character. When -PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a -subject, or a value of \fIstartoffset\fR that does not point to the start of a -UTF-8 character, is undefined. Your program may crash. - -There are also three further options that can be set only at matching time: - - PCRE_NOTBOL - -The first character of the string is not the beginning of a line, so the -circumflex metacharacter should not match before it. Setting this without -PCRE_MULTILINE (at compile time) causes circumflex never to match. - - PCRE_NOTEOL - -The end of the string is not the end of a line, so the dollar metacharacter -should not match it nor (except in multiline mode) a newline immediately before -it. Setting this without PCRE_MULTILINE (at compile time) causes dollar never -to match. - - PCRE_NOTEMPTY - -An empty string is not considered to be a valid match if this option is set. If -there are alternatives in the pattern, they are tried. If all the alternatives -match the empty string, the entire match fails. For example, if the pattern - - a?b? - -is applied to a string not beginning with "a" or "b", it matches the empty -string at the start of the subject. With PCRE_NOTEMPTY set, this match is not -valid, so PCRE searches further into the string for occurrences of "a" or "b". - -Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case -of a pattern match of the empty string within its \fBsplit()\fR function, and -when using the /g modifier. It is possible to emulate Perl's behaviour after -matching a null string by first trying the match again at the same offset with -PCRE_NOTEMPTY set, and then if that fails by advancing the starting offset (see -below) and trying an ordinary match again. - -The subject string is passed to \fBpcre_exec()\fR as a pointer in -\fIsubject\fR, a length in \fIlength\fR, and a starting byte offset in -\fIstartoffset\fR. Unlike the pattern string, the subject may contain binary -zero bytes. When the starting offset is zero, the search for a match starts at -the beginning of the subject, and this is by far the most common case. - -If the pattern was compiled with the PCRE_UTF8 option, the subject must be a -sequence of bytes that is a valid UTF-8 string, and the starting offset must -point to the beginning of a UTF-8 character. If an invalid UTF-8 string or -offset is passed, an error (either PCRE_ERROR_BADUTF8 or -PCRE_ERROR_BADUTF8_OFFSET) is returned, unless the option PCRE_NO_UTF8_CHECK is -set, in which case PCRE's behaviour is not defined. - -A non-zero starting offset is useful when searching for another match in the -same subject by calling \fBpcre_exec()\fR again after a previous success. -Setting \fIstartoffset\fR differs from just passing over a shortened string and -setting PCRE_NOTBOL in the case of a pattern that begins with any kind of -lookbehind. For example, consider the pattern - - \\Biss\\B - -which finds occurrences of "iss" in the middle of words. (\\B matches only if -the current position in the subject is not a word boundary.) When applied to -the string "Mississipi" the first call to \fBpcre_exec()\fR finds the first -occurrence. If \fBpcre_exec()\fR is called again with just the remainder of the -subject, namely "issipi", it does not match, because \\B is always false at the -start of the subject, which is deemed to be a word boundary. However, if -\fBpcre_exec()\fR is passed the entire string again, but with \fIstartoffset\fR -set to 4, it finds the second occurrence of "iss" because it is able to look -behind the starting point to discover that it is preceded by a letter. - -If a non-zero starting offset is passed when the pattern is anchored, one -attempt to match at the given offset is tried. This can only succeed if the -pattern does not require the match to be at the start of the subject. - -In general, a pattern matches a certain portion of the subject, and in -addition, further substrings from the subject may be picked out by parts of the -pattern. Following the usage in Jeffrey Friedl's book, this is called -"capturing" in what follows, and the phrase "capturing subpattern" is used for -a fragment of a pattern that picks out a substring. PCRE supports several other -kinds of parenthesized subpattern that do not cause substrings to be captured. - -Captured substrings are returned to the caller via a vector of integer offsets -whose address is passed in \fIovector\fR. The number of elements in the vector -is passed in \fIovecsize\fR. The first two-thirds of the vector is used to pass -back captured substrings, each substring using a pair of integers. The -remaining third of the vector is used as workspace by \fBpcre_exec()\fR while -matching capturing subpatterns, and is not available for passing back -information. The length passed in \fIovecsize\fR should always be a multiple of -three. If it is not, it is rounded down. - -When a match has been successful, information about captured substrings is -returned in pairs of integers, starting at the beginning of \fIovector\fR, and -continuing up to two-thirds of its length at the most. The first element of a -pair is set to the offset of the first character in a substring, and the second -is set to the offset of the first character after the end of a substring. The -first pair, \fIovector[0]\fR and \fIovector[1]\fR, identify the portion of the -subject string matched by the entire pattern. The next pair is used for the -first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fR -is the number of pairs that have been set. If there are no capturing -subpatterns, the return value from a successful match is 1, indicating that -just the first pair of offsets has been set. - -Some convenience functions are provided for extracting the captured substrings -as separate strings. These are described in the following section. - -It is possible for an capturing subpattern number \fIn+1\fR to match some -part of the subject when subpattern \fIn\fR has not been used at all. For -example, if the string "abc" is matched against the pattern (a|(z))(bc) -subpatterns 1 and 3 are matched, but 2 is not. When this happens, both offset -values corresponding to the unused subpattern are set to -1. - -If a capturing subpattern is matched repeatedly, it is the last portion of the -string that it matched that gets returned. - -If the vector is too small to hold all the captured substrings, it is used as -far as possible (up to two-thirds of its length), and the function returns a -value of zero. In particular, if the substring offsets are not of interest, -\fBpcre_exec()\fR may be called with \fIovector\fR passed as NULL and -\fIovecsize\fR as zero. However, if the pattern contains back references and -the \fIovector\fR isn't big enough to remember the related substrings, PCRE has -to get additional memory for use during matching. Thus it is usually advisable -to supply an \fIovector\fR. - -Note that \fBpcre_info()\fR can be used to find out how many capturing -subpatterns there are in a compiled pattern. The smallest size for -\fIovector\fR that will allow for \fIn\fR captured substrings, in addition to -the offsets of the substring matched by the whole pattern, is (\fIn\fR+1)*3. - -If \fBpcre_exec()\fR fails, it returns a negative number. The following are -defined in the header file: - - PCRE_ERROR_NOMATCH (-1) - -The subject string did not match the pattern. - - PCRE_ERROR_NULL (-2) - -Either \fIcode\fR or \fIsubject\fR was passed as NULL, or \fIovector\fR was -NULL and \fIovecsize\fR was not zero. - - PCRE_ERROR_BADOPTION (-3) - -An unrecognized bit was set in the \fIoptions\fR argument. - - PCRE_ERROR_BADMAGIC (-4) - -PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch -the case when it is passed a junk pointer. This is the error it gives when the -magic number isn't present. - - PCRE_ERROR_UNKNOWN_NODE (-5) - -While running the pattern match, an unknown item was encountered in the -compiled pattern. This error could be caused by a bug in PCRE or by overwriting -of the compiled pattern. - - PCRE_ERROR_NOMEMORY (-6) - -If a pattern contains back references, but the \fIovector\fR that is passed to -\fBpcre_exec()\fR is not big enough to remember the referenced substrings, PCRE -gets a block of memory at the start of matching to use for this purpose. If the -call via \fBpcre_malloc()\fR fails, this error is given. The memory is freed at -the end of matching. - - PCRE_ERROR_NOSUBSTRING (-7) - -This error is used by the \fBpcre_copy_substring()\fR, -\fBpcre_get_substring()\fR, and \fBpcre_get_substring_list()\fR functions (see -below). It is never returned by \fBpcre_exec()\fR. - - PCRE_ERROR_MATCHLIMIT (-8) - -The recursion and backtracking limit, as specified by the \fImatch_limit\fR -field in a \fBpcre_extra\fR structure (or defaulted) was reached. See the -description above. - - PCRE_ERROR_CALLOUT (-9) - -This error is never generated by \fBpcre_exec()\fR itself. It is provided for -use by callout functions that want to yield a distinctive error code. See the -\fBpcrecallout\fR documentation for details. - - PCRE_ERROR_BADUTF8 (-10) - -A string that contains an invalid UTF-8 byte sequence was passed as a subject. - - PCRE_ERROR_BADUTF8_OFFSET (-11) - -The UTF-8 byte sequence that was passed as a subject was valid, but the value -of \fIstartoffset\fR did not point to the beginning of a UTF-8 character. - -.SH EXTRACTING CAPTURED SUBSTRINGS BY NUMBER -.rs -.sp -.B int pcre_copy_substring(const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, int \fIstringnumber\fR, char *\fIbuffer\fR, -.ti +5n -.B int \fIbuffersize\fR); -.PP -.br -.B int pcre_get_substring(const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, int \fIstringnumber\fR, -.ti +5n -.B const char **\fIstringptr\fR); -.PP -.br -.B int pcre_get_substring_list(const char *\fIsubject\fR, -.ti +5n -.B int *\fIovector\fR, int \fIstringcount\fR, "const char ***\fIlistptr\fR);" -.PP -Captured substrings can be accessed directly by using the offsets returned by -\fBpcre_exec()\fR in \fIovector\fR. For convenience, the functions -\fBpcre_copy_substring()\fR, \fBpcre_get_substring()\fR, and -\fBpcre_get_substring_list()\fR are provided for extracting captured substrings -as new, separate, zero-terminated strings. These functions identify substrings -by number. The next section describes functions for extracting named -substrings. A substring that contains a binary zero is correctly extracted and -has a further zero added on the end, but the result is not, of course, -a C string. - -The first three arguments are the same for all three of these functions: -\fIsubject\fR is the subject string which has just been successfully matched, -\fIovector\fR is a pointer to the vector of integer offsets that was passed to -\fBpcre_exec()\fR, and \fIstringcount\fR is the number of substrings that were -captured by the match, including the substring that matched the entire regular -expression. This is the value returned by \fBpcre_exec\fR if it is greater than -zero. If \fBpcre_exec()\fR returned zero, indicating that it ran out of space -in \fIovector\fR, the value passed as \fIstringcount\fR should be the size of -the vector divided by three. - -The functions \fBpcre_copy_substring()\fR and \fBpcre_get_substring()\fR -extract a single substring, whose number is given as \fIstringnumber\fR. A -value of zero extracts the substring that matched the entire pattern, while -higher values extract the captured substrings. For \fBpcre_copy_substring()\fR, -the string is placed in \fIbuffer\fR, whose length is given by -\fIbuffersize\fR, while for \fBpcre_get_substring()\fR a new block of memory is -obtained via \fBpcre_malloc\fR, and its address is returned via -\fIstringptr\fR. The yield of the function is the length of the string, not -including the terminating zero, or one of - - PCRE_ERROR_NOMEMORY (-6) - -The buffer was too small for \fBpcre_copy_substring()\fR, or the attempt to get -memory failed for \fBpcre_get_substring()\fR. - - PCRE_ERROR_NOSUBSTRING (-7) - -There is no substring whose number is \fIstringnumber\fR. - -The \fBpcre_get_substring_list()\fR function extracts all available substrings -and builds a list of pointers to them. All this is done in a single block of -memory which is obtained via \fBpcre_malloc\fR. The address of the memory block -is returned via \fIlistptr\fR, which is also the start of the list of string -pointers. The end of the list is marked by a NULL pointer. The yield of the -function is zero if all went well, or - - PCRE_ERROR_NOMEMORY (-6) - -if the attempt to get the memory block failed. - -When any of these functions encounter a substring that is unset, which can -happen when capturing subpattern number \fIn+1\fR matches some part of the -subject, but subpattern \fIn\fR has not been used at all, they return an empty -string. This can be distinguished from a genuine zero-length substring by -inspecting the appropriate offset in \fIovector\fR, which is negative for unset -substrings. - -The two convenience functions \fBpcre_free_substring()\fR and -\fBpcre_free_substring_list()\fR can be used to free the memory returned by -a previous call of \fBpcre_get_substring()\fR or -\fBpcre_get_substring_list()\fR, respectively. They do nothing more than call -the function pointed to by \fBpcre_free\fR, which of course could be called -directly from a C program. However, PCRE is used in some situations where it is -linked via a special interface to another programming language which cannot use -\fBpcre_free\fR directly; it is for these cases that the functions are -provided. - -.SH EXTRACTING CAPTURED SUBSTRINGS BY NAME -.rs -.sp -.B int pcre_copy_named_substring(const pcre *\fIcode\fR, -.ti +5n -.B const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, const char *\fIstringname\fR, -.ti +5n -.B char *\fIbuffer\fR, int \fIbuffersize\fR); -.PP -.br -.B int pcre_get_stringnumber(const pcre *\fIcode\fR, -.ti +5n -.B const char *\fIname\fR); -.PP -.br -.B int pcre_get_named_substring(const pcre *\fIcode\fR, -.ti +5n -.B const char *\fIsubject\fR, int *\fIovector\fR, -.ti +5n -.B int \fIstringcount\fR, const char *\fIstringname\fR, -.ti +5n -.B const char **\fIstringptr\fR); -.PP -To extract a substring by name, you first have to find associated number. This -can be done by calling \fBpcre_get_stringnumber()\fR. The first argument is the -compiled pattern, and the second is the name. For example, for this pattern - - ab(?<xxx>\\d+)... - -the number of the subpattern called "xxx" is 1. Given the number, you can then -extract the substring directly, or use one of the functions described in the -previous section. For convenience, there are also two functions that do the -whole job. - -Most of the arguments of \fIpcre_copy_named_substring()\fR and -\fIpcre_get_named_substring()\fR are the same as those for the functions that -extract by number, and so are not re-described here. There are just two -differences. - -First, instead of a substring number, a substring name is given. Second, there -is an extra argument, given at the start, which is a pointer to the compiled -pattern. This is needed in order to gain access to the name-to-number -translation table. - -These functions call \fBpcre_get_stringnumber()\fR, and if it succeeds, they -then call \fIpcre_copy_substring()\fR or \fIpcre_get_substring()\fR, as -appropriate. - -.in 0 -Last updated: 09 December 2003 -.br -Copyright (c) 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/pcrebuild.3 b/external-libs/pcre/doc/pcrebuild.3 deleted file mode 100644 index a91782c0..00000000 --- a/external-libs/pcre/doc/pcrebuild.3 +++ /dev/null @@ -1,145 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH PCRE BUILD-TIME OPTIONS -.rs -.sp -This document describes the optional features of PCRE that can be selected when -the library is compiled. They are all selected, or deselected, by providing -options to the \fBconfigure\fR script which is run before the \fBmake\fR -command. The complete list of options for \fBconfigure\fR (which includes the -standard ones such as the selection of the installation directory) can be -obtained by running - - ./configure --help - -The following sections describe certain options whose names begin with --enable -or --disable. These settings specify changes to the defaults for the -\fBconfigure\fR command. Because of the way that \fBconfigure\fR works, ---enable and --disable always come in pairs, so the complementary option always -exists as well, but as it specifies the default, it is not described. - -.SH UTF-8 SUPPORT -.rs -.sp -To build PCRE with support for UTF-8 character strings, add - - --enable-utf8 - -to the \fBconfigure\fR command. Of itself, this does not make PCRE treat -strings as UTF-8. As well as compiling PCRE with this option, you also have -have to set the PCRE_UTF8 option when you call the \fBpcre_compile()\fR -function. - -.SH CODE VALUE OF NEWLINE -.rs -.sp -By default, PCRE treats character 10 (linefeed) as the newline character. This -is the normal newline character on Unix-like systems. You can compile PCRE to -use character 13 (carriage return) instead by adding - - --enable-newline-is-cr - -to the \fBconfigure\fR command. For completeness there is also a ---enable-newline-is-lf option, which explicitly specifies linefeed as the -newline character. - -.SH BUILDING SHARED AND STATIC LIBRARIES -.rs -.sp -The PCRE building process uses \fBlibtool\fR to build both shared and static -Unix libraries by default. You can suppress one of these by adding one of - - --disable-shared - --disable-static - -to the \fBconfigure\fR command, as required. - -.SH POSIX MALLOC USAGE -.rs -.sp -When PCRE is called through the POSIX interface (see the \fBpcreposix\fR -documentation), additional working storage is required for holding the pointers -to capturing substrings because PCRE requires three integers per substring, -whereas the POSIX interface provides only two. If the number of expected -substrings is small, the wrapper function uses space on the stack, because this -is faster than using \fBmalloc()\fR for each call. The default threshold above -which the stack is no longer used is 10; it can be changed by adding a setting -such as - - --with-posix-malloc-threshold=20 - -to the \fBconfigure\fR command. - -.SH LIMITING PCRE RESOURCE USAGE -.rs -.sp -Internally, PCRE has a function called \fBmatch()\fR which it calls repeatedly -(possibly recursively) when performing a matching operation. By limiting the -number of times this function may be called, a limit can be placed on the -resources used by a single call to \fBpcre_exec()\fR. The limit can be changed -at run time, as described in the \fBpcreapi\fR documentation. The default is 10 -million, but this can be changed by adding a setting such as - - --with-match-limit=500000 - -to the \fBconfigure\fR command. - -.SH HANDLING VERY LARGE PATTERNS -.rs -.sp -Within a compiled pattern, offset values are used to point from one part to -another (for example, from an opening parenthesis to an alternation -metacharacter). By default two-byte values are used for these offsets, leading -to a maximum size for a compiled pattern of around 64K. This is sufficient to -handle all but the most gigantic patterns. Nevertheless, some people do want to -process enormous patterns, so it is possible to compile PCRE to use three-byte -or four-byte offsets by adding a setting such as - - --with-link-size=3 - -to the \fBconfigure\fR command. The value given must be 2, 3, or 4. Using -longer offsets slows down the operation of PCRE because it has to load -additional bytes when handling them. - -If you build PCRE with an increased link size, test 2 (and test 5 if you are -using UTF-8) will fail. Part of the output of these tests is a representation -of the compiled pattern, and this changes with the link size. - -.SH AVOIDING EXCESSIVE STACK USAGE -.rs -.sp -PCRE implements backtracking while matching by making recursive calls to an -internal function called \fBmatch()\fR. In environments where the size of the -stack is limited, this can severely limit PCRE's operation. (The Unix -environment does not usually suffer from this problem.) An alternative approach -that uses memory from the heap to remember data, instead of using recursive -function calls, has been implemented to work round this problem. If you want to -build a version of PCRE that works this way, add - - --disable-stack-for-recursion - -to the \fBconfigure\fR command. With this configuration, PCRE will use the -\fBpcre_stack_malloc\fR and \fBpcre_stack_free\fR variables to call memory -management functions. Separate functions are provided because the usage is very -predictable: the block sizes requested are always the same, and the blocks are -always freed in reverse order. A calling program might be able to implement -optimized functions that perform better than the standard \fBmalloc()\fR and -\fBfree()\fR functions. PCRE runs noticeably more slowly when built in this -way. - -.SH USING EBCDIC CODE -.rs -.sp -PCRE assumes by default that it will run in an environment where the character -code is ASCII (or UTF-8, which is a superset of ASCII). PCRE can, however, be -compiled to run in an EBCDIC environment by adding - - --enable-ebcdic - -to the \fBconfigure\fR command. - -.in 0 -Last updated: 09 December 2003 -.br -Copyright (c) 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/pcrecallout.3 b/external-libs/pcre/doc/pcrecallout.3 deleted file mode 100644 index bfbb66b2..00000000 --- a/external-libs/pcre/doc/pcrecallout.3 +++ /dev/null @@ -1,92 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH PCRE CALLOUTS -.rs -.sp -.B int (*pcre_callout)(pcre_callout_block *); -.PP -PCRE provides a feature called "callout", which is a means of temporarily -passing control to the caller of PCRE in the middle of pattern matching. The -caller of PCRE provides an external function by putting its entry point in the -global variable \fIpcre_callout\fR. By default, this variable contains NULL, -which disables all calling out. - -Within a regular expression, (?C) indicates the points at which the external -function is to be called. Different callout points can be identified by putting -a number less than 256 after the letter C. The default value is zero. -For example, this pattern has two callout points: - - (?C1)\dabc(?C2)def - -During matching, when PCRE reaches a callout point (and \fIpcre_callout\fR is -set), the external function is called. Its only argument is a pointer to a -\fBpcre_callout\fR block. This contains the following variables: - - int \fIversion\fR; - int \fIcallout_number\fR; - int *\fIoffset_vector\fR; - const char *\fIsubject\fR; - int \fIsubject_length\fR; - int \fIstart_match\fR; - int \fIcurrent_position\fR; - int \fIcapture_top\fR; - int \fIcapture_last\fR; - void *\fIcallout_data\fR; - -The \fIversion\fR field is an integer containing the version number of the -block format. The current version is zero. The version number may change in -future if additional fields are added, but the intention is never to remove any -of the existing fields. - -The \fIcallout_number\fR field contains the number of the callout, as compiled -into the pattern (that is, the number after ?C). - -The \fIoffset_vector\fR field is a pointer to the vector of offsets that was -passed by the caller to \fBpcre_exec()\fR. The contents can be inspected in -order to extract substrings that have been matched so far, in the same way as -for extracting substrings after a match has completed. - -The \fIsubject\fR and \fIsubject_length\fR fields contain copies the values -that were passed to \fBpcre_exec()\fR. - -The \fIstart_match\fR field contains the offset within the subject at which the -current match attempt started. If the pattern is not anchored, the callout -function may be called several times for different starting points. - -The \fIcurrent_position\fR field contains the offset within the subject of the -current match pointer. - -The \fIcapture_top\fR field contains one more than the number of the highest -numbered captured substring so far. If no substrings have been captured, -the value of \fIcapture_top\fR is one. - -The \fIcapture_last\fR field contains the number of the most recently captured -substring. - -The \fIcallout_data\fR field contains a value that is passed to -\fBpcre_exec()\fR by the caller specifically so that it can be passed back in -callouts. It is passed in the \fIpcre_callout\fR field of the \fBpcre_extra\fR -data structure. If no such data was passed, the value of \fIcallout_data\fR in -a \fBpcre_callout\fR block is NULL. There is a description of the -\fBpcre_extra\fR structure in the \fBpcreapi\fR documentation. - - -.SH RETURN VALUES -.rs -.sp -The callout function returns an integer. If the value is zero, matching -proceeds as normal. If the value is greater than zero, matching fails at the -current point, but backtracking to test other possibilities goes ahead, just as -if a lookahead assertion had failed. If the value is less than zero, the match -is abandoned, and \fBpcre_exec()\fR returns the value. - -Negative values should normally be chosen from the set of PCRE_ERROR_xxx -values. In particular, PCRE_ERROR_NOMATCH forces a standard "no match" failure. -The error number PCRE_ERROR_CALLOUT is reserved for use by callout functions; -it will never be used by PCRE itself. - -.in 0 -Last updated: 21 January 2003 -.br -Copyright (c) 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/pcrecompat.3 b/external-libs/pcre/doc/pcrecompat.3 deleted file mode 100644 index e358f607..00000000 --- a/external-libs/pcre/doc/pcrecompat.3 +++ /dev/null @@ -1,107 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH DIFFERENCES FROM PERL -.rs -.sp -This document describes the differences in the ways that PCRE and Perl handle -regular expressions. The differences described here are with respect to Perl -5.8. - -1. PCRE does not have full UTF-8 support. Details of what it does have are -given in the -.\" HTML <a href="pcre.html#utf8support"> -.\" </a> -section on UTF-8 support -.\" -in the main -.\" HREF -\fBpcre\fR -.\" -page. - -2. PCRE does not allow repeat quantifiers on lookahead assertions. Perl permits -them, but they do not mean what you might think. For example, (?!a){3} does -not assert that the next three characters are not "a". It just asserts that the -next character is not "a" three times. - -3. Capturing subpatterns that occur inside negative lookahead assertions are -counted, but their entries in the offsets vector are never set. Perl sets its -numerical variables from any such patterns that are matched before the -assertion fails to match something (thereby succeeding), but only if the -negative lookahead assertion contains just one branch. - -4. Though binary zero characters are supported in the subject string, they are -not allowed in a pattern string because it is passed as a normal C string, -terminated by zero. The escape sequence "\\0" can be used in the pattern to -represent a binary zero. - -5. The following Perl escape sequences are not supported: \\l, \\u, \\L, -\\U, \\P, \\p, \\N, and \\X. In fact these are implemented by Perl's general -string-handling and are not part of its pattern matching engine. If any of -these are encountered by PCRE, an error is generated. - -6. PCRE does support the \\Q...\\E escape for quoting substrings. Characters in -between are treated as literals. This is slightly different from Perl in that $ -and @ are also handled as literals inside the quotes. In Perl, they cause -variable interpolation (but of course PCRE does not have variables). Note the -following examples: - - Pattern PCRE matches Perl matches - - \\Qabc$xyz\\E abc$xyz abc followed by the - contents of $xyz - \\Qabc\\$xyz\\E abc\\$xyz abc\\$xyz - \\Qabc\\E\\$\\Qxyz\\E abc$xyz abc$xyz - -The \\Q...\\E sequence is recognized both inside and outside character classes. - -7. Fairly obviously, PCRE does not support the (?{code}) and (?p{code}) -constructions. However, there is some experimental support for recursive -patterns using the non-Perl items (?R), (?number) and (?P>name). Also, the PCRE -"callout" feature allows an external function to be called during pattern -matching. - -8. There are some differences that are concerned with the settings of captured -strings when part of a pattern is repeated. For example, matching "aba" against -the pattern /^(a(b)?)+$/ in Perl leaves $2 unset, but in PCRE it is set to "b". - -9. PCRE provides some extensions to the Perl regular expression facilities: - -(a) Although lookbehind assertions must match fixed length strings, each -alternative branch of a lookbehind assertion can match a different length of -string. Perl requires them all to have the same length. - -(b) If PCRE_DOLLAR_ENDONLY is set and PCRE_MULTILINE is not set, the $ -meta-character matches only at the very end of the string. - -(c) If PCRE_EXTRA is set, a backslash followed by a letter with no special -meaning is faulted. - -(d) If PCRE_UNGREEDY is set, the greediness of the repetition quantifiers is -inverted, that is, by default they are not greedy, but if followed by a -question mark they are. - -(e) PCRE_ANCHORED can be used to force a pattern to be tried only at the first -matching position in the subject string. - -(f) The PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NO_AUTO_CAPTURE -options for \fBpcre_exec()\fR have no Perl equivalents. - -(g) The (?R), (?number), and (?P>name) constructs allows for recursive pattern -matching (Perl can do this using the (?p{code}) construct, which PCRE cannot -support.) - -(h) PCRE supports named capturing substrings, using the Python syntax. - -(i) PCRE supports the possessive quantifier "++" syntax, taken from Sun's Java -package. - -(j) The (R) condition, for testing recursion, is a PCRE extension. - -(k) The callout facility is PCRE-specific. - -.in 0 -Last updated: 09 December 2003 -.br -Copyright (c) 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/pcregrep.1 b/external-libs/pcre/doc/pcregrep.1 deleted file mode 100644 index c40dc054..00000000 --- a/external-libs/pcre/doc/pcregrep.1 +++ /dev/null @@ -1,130 +0,0 @@ -.TH PCREGREP 1 -.SH NAME -pcregrep - a grep with Perl-compatible regular expressions. -.SH SYNOPSIS -.B pcregrep [-Vcfhilnrsuvx] [long options] [pattern] [file1 file2 ...] - -.SH DESCRIPTION -.rs -.sp -\fBpcregrep\fR searches files for character patterns, in the same way as other -grep commands do, but it uses the PCRE regular expression library to support -patterns that are compatible with the regular expressions of Perl 5. See -.\" HREF -\fBpcrepattern\fR -.\" -for a full description of syntax and semantics of the regular expressions that -PCRE supports. - -A pattern must be specified on the command line unless the \fB-f\fR option is -used (see below). - -If no files are specified, \fBpcregrep\fR reads the standard input. By default, -each line that matches the pattern is copied to the standard output, and if -there is more than one file, the file name is printed before each line of -output. However, there are options that can change how \fBpcregrep\fR behaves. - -Lines are limited to BUFSIZ characters. BUFSIZ is defined in \fB<stdio.h>\fR. -The newline character is removed from the end of each line before it is matched -against the pattern. - -.SH OPTIONS -.rs -.sp -.TP 10 -\fB-V\fR -Write the version number of the PCRE library being used to the standard error -stream. -.TP -\fB-c\fR -Do not print individual lines; instead just print a count of the number of -lines that would otherwise have been printed. If several files are given, a -count is printed for each of them. -.TP -\fB-f\fR\fIfilename\fR -Read a number of patterns from the file, one per line, and match all of them -against each line of input. A line is output if any of the patterns match it. -When \fB-f\fR is used, no pattern is taken from the command line; all arguments -are treated as file names. There is a maximum of 100 patterns. Trailing white -space is removed, and blank lines are ignored. An empty file contains no -patterns and therefore matches nothing. -.TP -\fB-h\fR -Suppress printing of filenames when searching multiple files. -.TP -\fB-i\fR -Ignore upper/lower case distinctions during comparisons. -.TP -\fB-l\fR -Instead of printing lines from the files, just print the names of the files -containing lines that would have been printed. Each file name is printed -once, on a separate line. -.TP -\fB-n\fR -Precede each line by its line number in the file. -.TP -\fB-r\fR -If any file is a directory, recursively scan the files it contains. Without -\fB-r\fR a directory is scanned as a normal file. -.TP -\fB-s\fR -Work silently, that is, display nothing except error messages. -The exit status indicates whether any matches were found. -.TP -\fB-u\fR -Operate in UTF-8 mode. This option is available only if PCRE has been compiled -with UTF-8 support. Both the pattern and each subject line are assumed to be -valid strings of UTF-8 characters. -.TP -\fB-v\fR -Invert the sense of the match, so that lines which do \fInot\fR match the -pattern are now the ones that are found. -.TP -\fB-x\fR -Force the pattern to be anchored (it must start matching at the beginning of -the line) and in addition, require it to match the entire line. This is -equivalent to having ^ and $ characters at the start and end of each -alternative branch in the regular expression. - -.SH LONG OPTIONS -.rs -.sp -Long forms of all the options are available, as in GNU grep. They are shown in -the following table: - - -c --count - -h --no-filename - -i --ignore-case - -l --files-with-matches - -n --line-number - -r --recursive - -s --no-messages - -u --utf-8 - -V --version - -v --invert-match - -x --line-regex - -x --line-regexp - -In addition, --file=\fIfilename\fR is equivalent to -f\fIfilename\fR, and ---help shows the list of options and then exits. - -.SH DIAGNOSTICS -.rs -.sp -Exit status is 0 if any matches were found, 1 if no matches were found, and 2 -for syntax errors or inacessible files (even if matches were found). - - -.SH AUTHOR -.rs -.sp -Philip Hazel <ph10@cam.ac.uk> -.br -University Computing Service -.br -Cambridge CB2 3QG, England. - -.in 0 -Last updated: 03 February 2003 -.br -Copyright (c) 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/pcregrep.txt b/external-libs/pcre/doc/pcregrep.txt deleted file mode 100644 index aae8928f..00000000 --- a/external-libs/pcre/doc/pcregrep.txt +++ /dev/null @@ -1,124 +0,0 @@ -PCREGREP(1) PCREGREP(1) - - - -NAME - pcregrep - a grep with Perl-compatible regular expressions. - -SYNOPSIS - pcregrep [-Vcfhilnrsuvx] [long options] [pattern] [file1 file2 ...] - - -DESCRIPTION - - pcregrep searches files for character patterns, in the same way as - other grep commands do, but it uses the PCRE regular expression library - to support patterns that are compatible with the regular expressions of - Perl 5. See pcrepattern for a full description of syntax and semantics - of the regular expressions that PCRE supports. - - A pattern must be specified on the command line unless the -f option is - used (see below). - - If no files are specified, pcregrep reads the standard input. By - default, each line that matches the pattern is copied to the standard - output, and if there is more than one file, the file name is printed - before each line of output. However, there are options that can change - how pcregrep behaves. - - Lines are limited to BUFSIZ characters. BUFSIZ is defined in <stdio.h>. - The newline character is removed from the end of each line before it is - matched against the pattern. - - -OPTIONS - - - -V Write the version number of the PCRE library being used to - the standard error stream. - - -c Do not print individual lines; instead just print a count of - the number of lines that would otherwise have been printed. - If several files are given, a count is printed for each of - them. - - -ffilename - Read a number of patterns from the file, one per line, and - match all of them against each line of input. A line is out- - put if any of the patterns match it. When -f is used, no - pattern is taken from the command line; all arguments are - treated as file names. There is a maximum of 100 patterns. - Trailing white space is removed, and blank lines are ignored. - An empty file contains no patterns and therefore matches - nothing. - - -h Suppress printing of filenames when searching multiple files. - - -i Ignore upper/lower case distinctions during comparisons. - - -l Instead of printing lines from the files, just print the - names of the files containing lines that would have been - printed. Each file name is printed once, on a separate line. - - -n Precede each line by its line number in the file. - - -r If any file is a directory, recursively scan the files it - contains. Without -r a directory is scanned as a normal file. - - -s Work silently, that is, display nothing except error mes- - sages. The exit status indicates whether any matches were - found. - - -u Operate in UTF-8 mode. This option is available only if PCRE - has been compiled with UTF-8 support. Both the pattern and - each subject line are assumed to be valid strings of UTF-8 - characters. - - -v Invert the sense of the match, so that lines which do not - match the pattern are now the ones that are found. - - -x Force the pattern to be anchored (it must start matching at - the beginning of the line) and in addition, require it to - match the entire line. This is equivalent to having ^ and $ - characters at the start and end of each alternative branch in - the regular expression. - - -LONG OPTIONS - - Long forms of all the options are available, as in GNU grep. They are - shown in the following table: - - -c --count - -h --no-filename - -i --ignore-case - -l --files-with-matches - -n --line-number - -r --recursive - -s --no-messages - -u --utf-8 - -V --version - -v --invert-match - -x --line-regex - -x --line-regexp - - In addition, --file=filename is equivalent to -ffilename, and --help - shows the list of options and then exits. - - -DIAGNOSTICS - - Exit status is 0 if any matches were found, 1 if no matches were found, - and 2 for syntax errors or inacessible files (even if matches were - found). - - - -AUTHOR - - Philip Hazel <ph10@cam.ac.uk> - University Computing Service - Cambridge CB2 3QG, England. - -Last updated: 03 February 2003 -Copyright (c) 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/pcrepattern.3 b/external-libs/pcre/doc/pcrepattern.3 deleted file mode 100644 index 101aa311..00000000 --- a/external-libs/pcre/doc/pcrepattern.3 +++ /dev/null @@ -1,1231 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH PCRE REGULAR EXPRESSION DETAILS -.rs -.sp -The syntax and semantics of the regular expressions supported by PCRE are -described below. Regular expressions are also described in the Perl -documentation and in a number of other books, some of which have copious -examples. Jeffrey Friedl's "Mastering Regular Expressions", published by -O'Reilly, covers them in great detail. The description here is intended as -reference documentation. - -The basic operation of PCRE is on strings of bytes. However, there is also -support for UTF-8 character strings. To use this support you must build PCRE to -include UTF-8 support, and then call \fBpcre_compile()\fR with the PCRE_UTF8 -option. How this affects the pattern matching is mentioned in several places -below. There is also a summary of UTF-8 features in the -.\" HTML <a href="pcre.html#utf8support"> -.\" </a> -section on UTF-8 support -.\" -in the main -.\" HREF -\fBpcre\fR -.\" -page. - -A regular expression is a pattern that is matched against a subject string from -left to right. Most characters stand for themselves in a pattern, and match the -corresponding characters in the subject. As a trivial example, the pattern - - The quick brown fox - -matches a portion of a subject string that is identical to itself. The power of -regular expressions comes from the ability to include alternatives and -repetitions in the pattern. These are encoded in the pattern by the use of -\fImeta-characters\fR, which do not stand for themselves but instead are -interpreted in some special way. - -There are two different sets of meta-characters: those that are recognized -anywhere in the pattern except within square brackets, and those that are -recognized in square brackets. Outside square brackets, the meta-characters are -as follows: - - \\ general escape character with several uses - ^ assert start of string (or line, in multiline mode) - $ assert end of string (or line, in multiline mode) - . match any character except newline (by default) - [ start character class definition - | start of alternative branch - ( start subpattern - ) end subpattern - ? extends the meaning of ( - also 0 or 1 quantifier - also quantifier minimizer - * 0 or more quantifier - + 1 or more quantifier - also "possessive quantifier" - { start min/max quantifier - -Part of a pattern that is in square brackets is called a "character class". In -a character class the only meta-characters are: - - \\ general escape character - ^ negate the class, but only if the first character - - indicates character range - [ POSIX character class (only if followed by POSIX - syntax) - ] terminates the character class - -The following sections describe the use of each of the meta-characters. - -.SH BACKSLASH -.rs -.sp -The backslash character has several uses. Firstly, if it is followed by a -non-alphameric character, it takes away any special meaning that character may -have. This use of backslash as an escape character applies both inside and -outside character classes. - -For example, if you want to match a * character, you write \\* in the pattern. -This escaping action applies whether or not the following character would -otherwise be interpreted as a meta-character, so it is always safe to precede a -non-alphameric with backslash to specify that it stands for itself. In -particular, if you want to match a backslash, you write \\\\. - -If a pattern is compiled with the PCRE_EXTENDED option, whitespace in the -pattern (other than in a character class) and characters between a # outside -a character class and the next newline character are ignored. An escaping -backslash can be used to include a whitespace or # character as part of the -pattern. - -If you want to remove the special meaning from a sequence of characters, you -can do so by putting them between \\Q and \\E. This is different from Perl in -that $ and @ are handled as literals in \\Q...\\E sequences in PCRE, whereas in -Perl, $ and @ cause variable interpolation. Note the following examples: - - Pattern PCRE matches Perl matches - - \\Qabc$xyz\\E abc$xyz abc followed by the - contents of $xyz - \\Qabc\\$xyz\\E abc\\$xyz abc\\$xyz - \\Qabc\\E\\$\\Qxyz\\E abc$xyz abc$xyz - -The \\Q...\\E sequence is recognized both inside and outside character classes. - -A second use of backslash provides a way of encoding non-printing characters -in patterns in a visible manner. There is no restriction on the appearance of -non-printing characters, apart from the binary zero that terminates a pattern, -but when a pattern is being prepared by text editing, it is usually easier to -use one of the following escape sequences than the binary character it -represents: - - \\a alarm, that is, the BEL character (hex 07) - \\cx "control-x", where x is any character - \\e escape (hex 1B) - \\f formfeed (hex 0C) - \\n newline (hex 0A) - \\r carriage return (hex 0D) - \\t tab (hex 09) - \\ddd character with octal code ddd, or backreference - \\xhh character with hex code hh - \\x{hhh..} character with hex code hhh... (UTF-8 mode only) - -The precise effect of \\cx is as follows: if x is a lower case letter, it -is converted to upper case. Then bit 6 of the character (hex 40) is inverted. -Thus \\cz becomes hex 1A, but \\c{ becomes hex 3B, while \\c; becomes hex -7B. - -After \\x, from zero to two hexadecimal digits are read (letters can be in -upper or lower case). In UTF-8 mode, any number of hexadecimal digits may -appear between \\x{ and }, but the value of the character code must be less -than 2**31 (that is, the maximum hexadecimal value is 7FFFFFFF). If characters -other than hexadecimal digits appear between \\x{ and }, or if there is no -terminating }, this form of escape is not recognized. Instead, the initial -\\x will be interpreted as a basic hexadecimal escape, with no following -digits, giving a byte whose value is zero. - -Characters whose value is less than 256 can be defined by either of the two -syntaxes for \\x when PCRE is in UTF-8 mode. There is no difference in the -way they are handled. For example, \\xdc is exactly the same as \\x{dc}. - -After \\0 up to two further octal digits are read. In both cases, if there -are fewer than two digits, just those that are present are used. Thus the -sequence \\0\\x\\07 specifies two binary zeros followed by a BEL character -(code value 7). Make sure you supply two digits after the initial zero if the -character that follows is itself an octal digit. - -The handling of a backslash followed by a digit other than 0 is complicated. -Outside a character class, PCRE reads it and any following digits as a decimal -number. If the number is less than 10, or if there have been at least that many -previous capturing left parentheses in the expression, the entire sequence is -taken as a \fIback reference\fR. A description of how this works is given -later, following the discussion of parenthesized subpatterns. - -Inside a character class, or if the decimal number is greater than 9 and there -have not been that many capturing subpatterns, PCRE re-reads up to three octal -digits following the backslash, and generates a single byte from the least -significant 8 bits of the value. Any subsequent digits stand for themselves. -For example: - - \\040 is another way of writing a space - \\40 is the same, provided there are fewer than 40 - previous capturing subpatterns - \\7 is always a back reference - \\11 might be a back reference, or another way of - writing a tab - \\011 is always a tab - \\0113 is a tab followed by the character "3" - \\113 might be a back reference, otherwise the - character with octal code 113 - \\377 might be a back reference, otherwise - the byte consisting entirely of 1 bits - \\81 is either a back reference, or a binary zero - followed by the two characters "8" and "1" - -Note that octal values of 100 or greater must not be introduced by a leading -zero, because no more than three octal digits are ever read. - -All the sequences that define a single byte value or a single UTF-8 character -(in UTF-8 mode) can be used both inside and outside character classes. In -addition, inside a character class, the sequence \\b is interpreted as the -backspace character (hex 08). Outside a character class it has a different -meaning (see below). - -The third use of backslash is for specifying generic character types: - - \\d any decimal digit - \\D any character that is not a decimal digit - \\s any whitespace character - \\S any character that is not a whitespace character - \\w any "word" character - \\W any "non-word" character - -Each pair of escape sequences partitions the complete set of characters into -two disjoint sets. Any given character matches one, and only one, of each pair. - -In UTF-8 mode, characters with values greater than 255 never match \\d, \\s, or -\\w, and always match \\D, \\S, and \\W. - -For compatibility with Perl, \\s does not match the VT character (code 11). -This makes it different from the the POSIX "space" class. The \\s characters -are HT (9), LF (10), FF (12), CR (13), and space (32). - -A "word" character is any letter or digit or the underscore character, that is, -any character which can be part of a Perl "word". The definition of letters and -digits is controlled by PCRE's character tables, and may vary if locale- -specific matching is taking place (see -.\" HTML <a href="pcreapi.html#localesupport"> -.\" </a> -"Locale support" -.\" -in the -.\" HREF -\fBpcreapi\fR -.\" -page). For example, in the "fr" (French) locale, some character codes greater -than 128 are used for accented letters, and these are matched by \\w. - -These character type sequences can appear both inside and outside character -classes. They each match one character of the appropriate type. If the current -matching point is at the end of the subject string, all of them fail, since -there is no character to match. - -The fourth use of backslash is for certain simple assertions. An assertion -specifies a condition that has to be met at a particular point in a match, -without consuming any characters from the subject string. The use of -subpatterns for more complicated assertions is described below. The backslashed -assertions are - - \\b matches at a word boundary - \\B matches when not at a word boundary - \\A matches at start of subject - \\Z matches at end of subject or before newline at end - \\z matches at end of subject - \\G matches at first matching position in subject - -These assertions may not appear in character classes (but note that \\b has a -different meaning, namely the backspace character, inside a character class). - -A word boundary is a position in the subject string where the current character -and the previous character do not both match \\w or \\W (i.e. one matches -\\w and the other matches \\W), or the start or end of the string if the -first or last character matches \\w, respectively. - -The \\A, \\Z, and \\z assertions differ from the traditional circumflex and -dollar (described below) in that they only ever match at the very start and end -of the subject string, whatever options are set. Thus, they are independent of -multiline mode. - -They are not affected by the PCRE_NOTBOL or PCRE_NOTEOL options. If the -\fIstartoffset\fR argument of \fBpcre_exec()\fR is non-zero, indicating that -matching is to start at a point other than the beginning of the subject, \\A -can never match. The difference between \\Z and \\z is that \\Z matches before -a newline that is the last character of the string as well as at the end of the -string, whereas \\z matches only at the end. - -The \\G assertion is true only when the current matching position is at the -start point of the match, as specified by the \fIstartoffset\fR argument of -\fBpcre_exec()\fR. It differs from \\A when the value of \fIstartoffset\fR is -non-zero. By calling \fBpcre_exec()\fR multiple times with appropriate -arguments, you can mimic Perl's /g option, and it is in this kind of -implementation where \\G can be useful. - -Note, however, that PCRE's interpretation of \\G, as the start of the current -match, is subtly different from Perl's, which defines it as the end of the -previous match. In Perl, these can be different when the previously matched -string was empty. Because PCRE does just one match at a time, it cannot -reproduce this behaviour. - -If all the alternatives of a pattern begin with \\G, the expression is anchored -to the starting match position, and the "anchored" flag is set in the compiled -regular expression. - -.SH CIRCUMFLEX AND DOLLAR -.rs -.sp -Outside a character class, in the default matching mode, the circumflex -character is an assertion which is true only if the current matching point is -at the start of the subject string. If the \fIstartoffset\fR argument of -\fBpcre_exec()\fR is non-zero, circumflex can never match if the PCRE_MULTILINE -option is unset. Inside a character class, circumflex has an entirely different -meaning (see below). - -Circumflex need not be the first character of the pattern if a number of -alternatives are involved, but it should be the first thing in each alternative -in which it appears if the pattern is ever to match that branch. If all -possible alternatives start with a circumflex, that is, if the pattern is -constrained to match only at the start of the subject, it is said to be an -"anchored" pattern. (There are also other constructs that can cause a pattern -to be anchored.) - -A dollar character is an assertion which is true only if the current matching -point is at the end of the subject string, or immediately before a newline -character that is the last character in the string (by default). Dollar need -not be the last character of the pattern if a number of alternatives are -involved, but it should be the last item in any branch in which it appears. -Dollar has no special meaning in a character class. - -The meaning of dollar can be changed so that it matches only at the very end of -the string, by setting the PCRE_DOLLAR_ENDONLY option at compile time. This -does not affect the \\Z assertion. - -The meanings of the circumflex and dollar characters are changed if the -PCRE_MULTILINE option is set. When this is the case, they match immediately -after and immediately before an internal newline character, respectively, in -addition to matching at the start and end of the subject string. For example, -the pattern /^abc$/ matches the subject string "def\\nabc" in multiline mode, -but not otherwise. Consequently, patterns that are anchored in single line mode -because all branches start with ^ are not anchored in multiline mode, and a -match for circumflex is possible when the \fIstartoffset\fR argument of -\fBpcre_exec()\fR is non-zero. The PCRE_DOLLAR_ENDONLY option is ignored if -PCRE_MULTILINE is set. - -Note that the sequences \\A, \\Z, and \\z can be used to match the start and -end of the subject in both modes, and if all branches of a pattern start with -\\A it is always anchored, whether PCRE_MULTILINE is set or not. - -.SH FULL STOP (PERIOD, DOT) -.rs -.sp -Outside a character class, a dot in the pattern matches any one character in -the subject, including a non-printing character, but not (by default) newline. -In UTF-8 mode, a dot matches any UTF-8 character, which might be more than one -byte long, except (by default) for newline. If the PCRE_DOTALL option is set, -dots match newlines as well. The handling of dot is entirely independent of the -handling of circumflex and dollar, the only relationship being that they both -involve newline characters. Dot has no special meaning in a character class. - -.SH MATCHING A SINGLE BYTE -.rs -.sp -Outside a character class, the escape sequence \\C matches any one byte, both -in and out of UTF-8 mode. Unlike a dot, it always matches a newline. The -feature is provided in Perl in order to match individual bytes in UTF-8 mode. -Because it breaks up UTF-8 characters into individual bytes, what remains in -the string may be a malformed UTF-8 string. For this reason it is best avoided. - -PCRE does not allow \\C to appear in lookbehind assertions (see below), because -in UTF-8 mode it makes it impossible to calculate the length of the lookbehind. - -.SH SQUARE BRACKETS -.rs -.sp -An opening square bracket introduces a character class, terminated by a closing -square bracket. A closing square bracket on its own is not special. If a -closing square bracket is required as a member of the class, it should be the -first data character in the class (after an initial circumflex, if present) or -escaped with a backslash. - -A character class matches a single character in the subject. In UTF-8 mode, the -character may occupy more than one byte. A matched character must be in the set -of characters defined by the class, unless the first character in the class -definition is a circumflex, in which case the subject character must not be in -the set defined by the class. If a circumflex is actually required as a member -of the class, ensure it is not the first character, or escape it with a -backslash. - -For example, the character class [aeiou] matches any lower case vowel, while -[^aeiou] matches any character that is not a lower case vowel. Note that a -circumflex is just a convenient notation for specifying the characters which -are in the class by enumerating those that are not. It is not an assertion: it -still consumes a character from the subject string, and fails if the current -pointer is at the end of the string. - -In UTF-8 mode, characters with values greater than 255 can be included in a -class as a literal string of bytes, or by using the \\x{ escaping mechanism. - -When caseless matching is set, any letters in a class represent both their -upper case and lower case versions, so for example, a caseless [aeiou] matches -"A" as well as "a", and a caseless [^aeiou] does not match "A", whereas a -caseful version would. PCRE does not support the concept of case for characters -with values greater than 255. - -The newline character is never treated in any special way in character classes, -whatever the setting of the PCRE_DOTALL or PCRE_MULTILINE options is. A class -such as [^a] will always match a newline. - -The minus (hyphen) character can be used to specify a range of characters in a -character class. For example, [d-m] matches any letter between d and m, -inclusive. If a minus character is required in a class, it must be escaped with -a backslash or appear in a position where it cannot be interpreted as -indicating a range, typically as the first or last character in the class. - -It is not possible to have the literal character "]" as the end character of a -range. A pattern such as [W-]46] is interpreted as a class of two characters -("W" and "-") followed by a literal string "46]", so it would match "W46]" or -"-46]". However, if the "]" is escaped with a backslash it is interpreted as -the end of range, so [W-\\]46] is interpreted as a single class containing a -range followed by two separate characters. The octal or hexadecimal -representation of "]" can also be used to end a range. - -Ranges operate in the collating sequence of character values. They can also be -used for characters specified numerically, for example [\\000-\\037]. In UTF-8 -mode, ranges can include characters whose values are greater than 255, for -example [\\x{100}-\\x{2ff}]. - -If a range that includes letters is used when caseless matching is set, it -matches the letters in either case. For example, [W-c] is equivalent to -[][\\^_`wxyzabc], matched caselessly, and if character tables for the "fr" -locale are in use, [\\xc8-\\xcb] matches accented E characters in both cases. - -The character types \\d, \\D, \\s, \\S, \\w, and \\W may also appear in a -character class, and add the characters that they match to the class. For -example, [\\dABCDEF] matches any hexadecimal digit. A circumflex can -conveniently be used with the upper case character types to specify a more -restricted set of characters than the matching lower case type. For example, -the class [^\\W_] matches any letter or digit, but not underscore. - -All non-alphameric characters other than \\, -, ^ (at the start) and the -terminating ] are non-special in character classes, but it does no harm if they -are escaped. - -.SH POSIX CHARACTER CLASSES -.rs -.sp -Perl supports the POSIX notation for character classes, which uses names -enclosed by [: and :] within the enclosing square brackets. PCRE also supports -this notation. For example, - - [01[:alpha:]%] - -matches "0", "1", any alphabetic character, or "%". The supported class names -are - - alnum letters and digits - alpha letters - ascii character codes 0 - 127 - blank space or tab only - cntrl control characters - digit decimal digits (same as \\d) - graph printing characters, excluding space - lower lower case letters - print printing characters, including space - punct printing characters, excluding letters and digits - space white space (not quite the same as \\s) - upper upper case letters - word "word" characters (same as \\w) - xdigit hexadecimal digits - -The "space" characters are HT (9), LF (10), VT (11), FF (12), CR (13), and -space (32). Notice that this list includes the VT character (code 11). This -makes "space" different to \\s, which does not include VT (for Perl -compatibility). - -The name "word" is a Perl extension, and "blank" is a GNU extension from Perl -5.8. Another Perl extension is negation, which is indicated by a ^ character -after the colon. For example, - - [12[:^digit:]] - -matches "1", "2", or any non-digit. PCRE (and Perl) also recognize the POSIX -syntax [.ch.] and [=ch=] where "ch" is a "collating element", but these are not -supported, and an error is given if they are encountered. - -In UTF-8 mode, characters with values greater than 255 do not match any of -the POSIX character classes. - -.SH VERTICAL BAR -.rs -.sp -Vertical bar characters are used to separate alternative patterns. For example, -the pattern - - gilbert|sullivan - -matches either "gilbert" or "sullivan". Any number of alternatives may appear, -and an empty alternative is permitted (matching the empty string). -The matching process tries each alternative in turn, from left to right, -and the first one that succeeds is used. If the alternatives are within a -subpattern (defined below), "succeeds" means matching the rest of the main -pattern as well as the alternative in the subpattern. - -.SH INTERNAL OPTION SETTING -.rs -.sp -The settings of the PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, and -PCRE_EXTENDED options can be changed from within the pattern by a sequence of -Perl option letters enclosed between "(?" and ")". The option letters are - - i for PCRE_CASELESS - m for PCRE_MULTILINE - s for PCRE_DOTALL - x for PCRE_EXTENDED - -For example, (?im) sets caseless, multiline matching. It is also possible to -unset these options by preceding the letter with a hyphen, and a combined -setting and unsetting such as (?im-sx), which sets PCRE_CASELESS and -PCRE_MULTILINE while unsetting PCRE_DOTALL and PCRE_EXTENDED, is also -permitted. If a letter appears both before and after the hyphen, the option is -unset. - -When an option change occurs at top level (that is, not inside subpattern -parentheses), the change applies to the remainder of the pattern that follows. -If the change is placed right at the start of a pattern, PCRE extracts it into -the global options (and it will therefore show up in data extracted by the -\fBpcre_fullinfo()\fR function). - -An option change within a subpattern affects only that part of the current -pattern that follows it, so - - (a(?i)b)c - -matches abc and aBc and no other strings (assuming PCRE_CASELESS is not used). -By this means, options can be made to have different settings in different -parts of the pattern. Any changes made in one alternative do carry on -into subsequent branches within the same subpattern. For example, - - (a(?i)b|c) - -matches "ab", "aB", "c", and "C", even though when matching "C" the first -branch is abandoned before the option setting. This is because the effects of -option settings happen at compile time. There would be some very weird -behaviour otherwise. - -The PCRE-specific options PCRE_UNGREEDY and PCRE_EXTRA can be changed in the -same way as the Perl-compatible options by using the characters U and X -respectively. The (?X) flag setting is special in that it must always occur -earlier in the pattern than any of the additional features it turns on, even -when it is at top level. It is best put at the start. - -.SH SUBPATTERNS -.rs -.sp -Subpatterns are delimited by parentheses (round brackets), which can be nested. -Marking part of a pattern as a subpattern does two things: - -1. It localizes a set of alternatives. For example, the pattern - - cat(aract|erpillar|) - -matches one of the words "cat", "cataract", or "caterpillar". Without the -parentheses, it would match "cataract", "erpillar" or the empty string. - -2. It sets up the subpattern as a capturing subpattern (as defined above). -When the whole pattern matches, that portion of the subject string that matched -the subpattern is passed back to the caller via the \fIovector\fR argument of -\fBpcre_exec()\fR. Opening parentheses are counted from left to right (starting -from 1) to obtain the numbers of the capturing subpatterns. - -For example, if the string "the red king" is matched against the pattern - - the ((red|white) (king|queen)) - -the captured substrings are "red king", "red", and "king", and are numbered 1, -2, and 3, respectively. - -The fact that plain parentheses fulfil two functions is not always helpful. -There are often times when a grouping subpattern is required without a -capturing requirement. If an opening parenthesis is followed by a question mark -and a colon, the subpattern does not do any capturing, and is not counted when -computing the number of any subsequent capturing subpatterns. For example, if -the string "the white queen" is matched against the pattern - - the ((?:red|white) (king|queen)) - -the captured substrings are "white queen" and "queen", and are numbered 1 and -2. The maximum number of capturing subpatterns is 65535, and the maximum depth -of nesting of all subpatterns, both capturing and non-capturing, is 200. - -As a convenient shorthand, if any option settings are required at the start of -a non-capturing subpattern, the option letters may appear between the "?" and -the ":". Thus the two patterns - - (?i:saturday|sunday) - (?:(?i)saturday|sunday) - -match exactly the same set of strings. Because alternative branches are tried -from left to right, and options are not reset until the end of the subpattern -is reached, an option setting in one branch does affect subsequent branches, so -the above patterns match "SUNDAY" as well as "Saturday". - -.SH NAMED SUBPATTERNS -.rs -.sp -Identifying capturing parentheses by number is simple, but it can be very hard -to keep track of the numbers in complicated regular expressions. Furthermore, -if an expression is modified, the numbers may change. To help with the -difficulty, PCRE supports the naming of subpatterns, something that Perl does -not provide. The Python syntax (?P<name>...) is used. Names consist of -alphanumeric characters and underscores, and must be unique within a pattern. - -Named capturing parentheses are still allocated numbers as well as names. The -PCRE API provides function calls for extracting the name-to-number translation -table from a compiled pattern. For further details see the -.\" HREF -\fBpcreapi\fR -.\" -documentation. - -.SH REPETITION -.rs -.sp -Repetition is specified by quantifiers, which can follow any of the following -items: - - a literal data character - the . metacharacter - the \\C escape sequence - escapes such as \\d that match single characters - a character class - a back reference (see next section) - a parenthesized subpattern (unless it is an assertion) - -The general repetition quantifier specifies a minimum and maximum number of -permitted matches, by giving the two numbers in curly brackets (braces), -separated by a comma. The numbers must be less than 65536, and the first must -be less than or equal to the second. For example: - - z{2,4} - -matches "zz", "zzz", or "zzzz". A closing brace on its own is not a special -character. If the second number is omitted, but the comma is present, there is -no upper limit; if the second number and the comma are both omitted, the -quantifier specifies an exact number of required matches. Thus - - [aeiou]{3,} - -matches at least 3 successive vowels, but may match many more, while - - \\d{8} - -matches exactly 8 digits. An opening curly bracket that appears in a position -where a quantifier is not allowed, or one that does not match the syntax of a -quantifier, is taken as a literal character. For example, {,6} is not a -quantifier, but a literal string of four characters. - -In UTF-8 mode, quantifiers apply to UTF-8 characters rather than to individual -bytes. Thus, for example, \\x{100}{2} matches two UTF-8 characters, each of -which is represented by a two-byte sequence. - -The quantifier {0} is permitted, causing the expression to behave as if the -previous item and the quantifier were not present. - -For convenience (and historical compatibility) the three most common -quantifiers have single-character abbreviations: - - * is equivalent to {0,} - + is equivalent to {1,} - ? is equivalent to {0,1} - -It is possible to construct infinite loops by following a subpattern that can -match no characters with a quantifier that has no upper limit, for example: - - (a?)* - -Earlier versions of Perl and PCRE used to give an error at compile time for -such patterns. However, because there are cases where this can be useful, such -patterns are now accepted, but if any repetition of the subpattern does in fact -match no characters, the loop is forcibly broken. - -By default, the quantifiers are "greedy", that is, they match as much as -possible (up to the maximum number of permitted times), without causing the -rest of the pattern to fail. The classic example of where this gives problems -is in trying to match comments in C programs. These appear between the -sequences /* and */ and within the sequence, individual * and / characters may -appear. An attempt to match C comments by applying the pattern - - /\\*.*\\*/ - -to the string - - /* first command */ not comment /* second comment */ - -fails, because it matches the entire string owing to the greediness of the .* -item. - -However, if a quantifier is followed by a question mark, it ceases to be -greedy, and instead matches the minimum number of times possible, so the -pattern - - /\\*.*?\\*/ - -does the right thing with the C comments. The meaning of the various -quantifiers is not otherwise changed, just the preferred number of matches. -Do not confuse this use of question mark with its use as a quantifier in its -own right. Because it has two uses, it can sometimes appear doubled, as in - - \\d??\\d - -which matches one digit by preference, but can match two if that is the only -way the rest of the pattern matches. - -If the PCRE_UNGREEDY option is set (an option which is not available in Perl), -the quantifiers are not greedy by default, but individual ones can be made -greedy by following them with a question mark. In other words, it inverts the -default behaviour. - -When a parenthesized subpattern is quantified with a minimum repeat count that -is greater than 1 or with a limited maximum, more store is required for the -compiled pattern, in proportion to the size of the minimum or maximum. - -If a pattern starts with .* or .{0,} and the PCRE_DOTALL option (equivalent -to Perl's /s) is set, thus allowing the . to match newlines, the pattern is -implicitly anchored, because whatever follows will be tried against every -character position in the subject string, so there is no point in retrying the -overall match at any position after the first. PCRE normally treats such a -pattern as though it were preceded by \\A. - -In cases where it is known that the subject string contains no newlines, it is -worth setting PCRE_DOTALL in order to obtain this optimization, or -alternatively using ^ to indicate anchoring explicitly. - -However, there is one situation where the optimization cannot be used. When .* -is inside capturing parentheses that are the subject of a backreference -elsewhere in the pattern, a match at the start may fail, and a later one -succeed. Consider, for example: - - (.*)abc\\1 - -If the subject is "xyz123abc123" the match point is the fourth character. For -this reason, such a pattern is not implicitly anchored. - -When a capturing subpattern is repeated, the value captured is the substring -that matched the final iteration. For example, after - - (tweedle[dume]{3}\\s*)+ - -has matched "tweedledum tweedledee" the value of the captured substring is -"tweedledee". However, if there are nested capturing subpatterns, the -corresponding captured values may have been set in previous iterations. For -example, after - - /(a|(b))+/ - -matches "aba" the value of the second captured substring is "b". - -.SH ATOMIC GROUPING AND POSSESSIVE QUANTIFIERS -.rs -.sp -With both maximizing and minimizing repetition, failure of what follows -normally causes the repeated item to be re-evaluated to see if a different -number of repeats allows the rest of the pattern to match. Sometimes it is -useful to prevent this, either to change the nature of the match, or to cause -it fail earlier than it otherwise might, when the author of the pattern knows -there is no point in carrying on. - -Consider, for example, the pattern \\d+foo when applied to the subject line - - 123456bar - -After matching all 6 digits and then failing to match "foo", the normal -action of the matcher is to try again with only 5 digits matching the \\d+ -item, and then with 4, and so on, before ultimately failing. "Atomic grouping" -(a term taken from Jeffrey Friedl's book) provides the means for specifying -that once a subpattern has matched, it is not to be re-evaluated in this way. - -If we use atomic grouping for the previous example, the matcher would give up -immediately on failing to match "foo" the first time. The notation is a kind of -special parenthesis, starting with (?> as in this example: - - (?>\\d+)foo - -This kind of parenthesis "locks up" the part of the pattern it contains once -it has matched, and a failure further into the pattern is prevented from -backtracking into it. Backtracking past it to previous items, however, works as -normal. - -An alternative description is that a subpattern of this type matches the string -of characters that an identical standalone pattern would match, if anchored at -the current point in the subject string. - -Atomic grouping subpatterns are not capturing subpatterns. Simple cases such as -the above example can be thought of as a maximizing repeat that must swallow -everything it can. So, while both \\d+ and \\d+? are prepared to adjust the -number of digits they match in order to make the rest of the pattern match, -(?>\\d+) can only match an entire sequence of digits. - -Atomic groups in general can of course contain arbitrarily complicated -subpatterns, and can be nested. However, when the subpattern for an atomic -group is just a single repeated item, as in the example above, a simpler -notation, called a "possessive quantifier" can be used. This consists of an -additional + character following a quantifier. Using this notation, the -previous example can be rewritten as - - \\d++bar - -Possessive quantifiers are always greedy; the setting of the PCRE_UNGREEDY -option is ignored. They are a convenient notation for the simpler forms of -atomic group. However, there is no difference in the meaning or processing of a -possessive quantifier and the equivalent atomic group. - -The possessive quantifier syntax is an extension to the Perl syntax. It -originates in Sun's Java package. - -When a pattern contains an unlimited repeat inside a subpattern that can itself -be repeated an unlimited number of times, the use of an atomic group is the -only way to avoid some failing matches taking a very long time indeed. The -pattern - - (\\D+|<\\d+>)*[!?] - -matches an unlimited number of substrings that either consist of non-digits, or -digits enclosed in <>, followed by either ! or ?. When it matches, it runs -quickly. However, if it is applied to - - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -it takes a long time before reporting failure. This is because the string can -be divided between the two repeats in a large number of ways, and all have to -be tried. (The example used [!?] rather than a single character at the end, -because both PCRE and Perl have an optimization that allows for fast failure -when a single character is used. They remember the last single character that -is required for a match, and fail early if it is not present in the string.) -If the pattern is changed to - - ((?>\\D+)|<\\d+>)*[!?] - -sequences of non-digits cannot be broken, and failure happens quickly. - -.SH BACK REFERENCES -.rs -.sp -Outside a character class, a backslash followed by a digit greater than 0 (and -possibly further digits) is a back reference to a capturing subpattern earlier -(that is, to its left) in the pattern, provided there have been that many -previous capturing left parentheses. - -However, if the decimal number following the backslash is less than 10, it is -always taken as a back reference, and causes an error only if there are not -that many capturing left parentheses in the entire pattern. In other words, the -parentheses that are referenced need not be to the left of the reference for -numbers less than 10. See the section entitled "Backslash" above for further -details of the handling of digits following a backslash. - -A back reference matches whatever actually matched the capturing subpattern in -the current subject string, rather than anything matching the subpattern -itself (see -.\" HTML <a href="#subpatternsassubroutines"> -.\" </a> -"Subpatterns as subroutines" -.\" -below for a way of doing that). So the pattern - - (sens|respons)e and \\1ibility - -matches "sense and sensibility" and "response and responsibility", but not -"sense and responsibility". If caseful matching is in force at the time of the -back reference, the case of letters is relevant. For example, - - ((?i)rah)\\s+\\1 - -matches "rah rah" and "RAH RAH", but not "RAH rah", even though the original -capturing subpattern is matched caselessly. - -Back references to named subpatterns use the Python syntax (?P=name). We could -rewrite the above example as follows: - - (?<p1>(?i)rah)\\s+(?P=p1) - -There may be more than one back reference to the same subpattern. If a -subpattern has not actually been used in a particular match, any back -references to it always fail. For example, the pattern - - (a|(bc))\\2 - -always fails if it starts to match "a" rather than "bc". Because there may be -many capturing parentheses in a pattern, all digits following the backslash are -taken as part of a potential back reference number. If the pattern continues -with a digit character, some delimiter must be used to terminate the back -reference. If the PCRE_EXTENDED option is set, this can be whitespace. -Otherwise an empty comment can be used. - -A back reference that occurs inside the parentheses to which it refers fails -when the subpattern is first used, so, for example, (a\\1) never matches. -However, such references can be useful inside repeated subpatterns. For -example, the pattern - - (a|b\\1)+ - -matches any number of "a"s and also "aba", "ababbaa" etc. At each iteration of -the subpattern, the back reference matches the character string corresponding -to the previous iteration. In order for this to work, the pattern must be such -that the first iteration does not need to match the back reference. This can be -done using alternation, as in the example above, or by a quantifier with a -minimum of zero. - -.SH ASSERTIONS -.rs -.sp -An assertion is a test on the characters following or preceding the current -matching point that does not actually consume any characters. The simple -assertions coded as \\b, \\B, \\A, \\G, \\Z, \\z, ^ and $ are described above. -More complicated assertions are coded as subpatterns. There are two kinds: -those that look ahead of the current position in the subject string, and those -that look behind it. - -An assertion subpattern is matched in the normal way, except that it does not -cause the current matching position to be changed. Lookahead assertions start -with (?= for positive assertions and (?! for negative assertions. For example, - - \\w+(?=;) - -matches a word followed by a semicolon, but does not include the semicolon in -the match, and - - foo(?!bar) - -matches any occurrence of "foo" that is not followed by "bar". Note that the -apparently similar pattern - - (?!foo)bar - -does not find an occurrence of "bar" that is preceded by something other than -"foo"; it finds any occurrence of "bar" whatsoever, because the assertion -(?!foo) is always true when the next three characters are "bar". A -lookbehind assertion is needed to achieve this effect. - -If you want to force a matching failure at some point in a pattern, the most -convenient way to do it is with (?!) because an empty string always matches, so -an assertion that requires there not to be an empty string must always fail. - -Lookbehind assertions start with (?<= for positive assertions and (?<! for -negative assertions. For example, - - (?<!foo)bar - -does find an occurrence of "bar" that is not preceded by "foo". The contents of -a lookbehind assertion are restricted such that all the strings it matches must -have a fixed length. However, if there are several alternatives, they do not -all have to have the same fixed length. Thus - - (?<=bullock|donkey) - -is permitted, but - - (?<!dogs?|cats?) - -causes an error at compile time. Branches that match different length strings -are permitted only at the top level of a lookbehind assertion. This is an -extension compared with Perl (at least for 5.8), which requires all branches to -match the same length of string. An assertion such as - - (?<=ab(c|de)) - -is not permitted, because its single top-level branch can match two different -lengths, but it is acceptable if rewritten to use two top-level branches: - - (?<=abc|abde) - -The implementation of lookbehind assertions is, for each alternative, to -temporarily move the current position back by the fixed width and then try to -match. If there are insufficient characters before the current position, the -match is deemed to fail. - -PCRE does not allow the \\C escape (which matches a single byte in UTF-8 mode) -to appear in lookbehind assertions, because it makes it impossible to calculate -the length of the lookbehind. - -Atomic groups can be used in conjunction with lookbehind assertions to specify -efficient matching at the end of the subject string. Consider a simple pattern -such as - - abcd$ - -when applied to a long string that does not match. Because matching proceeds -from left to right, PCRE will look for each "a" in the subject and then see if -what follows matches the rest of the pattern. If the pattern is specified as - - ^.*abcd$ - -the initial .* matches the entire string at first, but when this fails (because -there is no following "a"), it backtracks to match all but the last character, -then all but the last two characters, and so on. Once again the search for "a" -covers the entire string, from right to left, so we are no better off. However, -if the pattern is written as - - ^(?>.*)(?<=abcd) - -or, equivalently, - - ^.*+(?<=abcd) - -there can be no backtracking for the .* item; it can match only the entire -string. The subsequent lookbehind assertion does a single test on the last four -characters. If it fails, the match fails immediately. For long strings, this -approach makes a significant difference to the processing time. - -Several assertions (of any sort) may occur in succession. For example, - - (?<=\\d{3})(?<!999)foo - -matches "foo" preceded by three digits that are not "999". Notice that each of -the assertions is applied independently at the same point in the subject -string. First there is a check that the previous three characters are all -digits, and then there is a check that the same three characters are not "999". -This pattern does \fInot\fR match "foo" preceded by six characters, the first -of which are digits and the last three of which are not "999". For example, it -doesn't match "123abcfoo". A pattern to do that is - - (?<=\\d{3}...)(?<!999)foo - -This time the first assertion looks at the preceding six characters, checking -that the first three are digits, and then the second assertion checks that the -preceding three characters are not "999". - -Assertions can be nested in any combination. For example, - - (?<=(?<!foo)bar)baz - -matches an occurrence of "baz" that is preceded by "bar" which in turn is not -preceded by "foo", while - - (?<=\\d{3}(?!999)...)foo - -is another pattern which matches "foo" preceded by three digits and any three -characters that are not "999". - -Assertion subpatterns are not capturing subpatterns, and may not be repeated, -because it makes no sense to assert the same thing several times. If any kind -of assertion contains capturing subpatterns within it, these are counted for -the purposes of numbering the capturing subpatterns in the whole pattern. -However, substring capturing is carried out only for positive assertions, -because it does not make sense for negative assertions. - -.SH CONDITIONAL SUBPATTERNS -.rs -.sp -It is possible to cause the matching process to obey a subpattern -conditionally or to choose between two alternative subpatterns, depending on -the result of an assertion, or whether a previous capturing subpattern matched -or not. The two possible forms of conditional subpattern are - - (?(condition)yes-pattern) - (?(condition)yes-pattern|no-pattern) - -If the condition is satisfied, the yes-pattern is used; otherwise the -no-pattern (if present) is used. If there are more than two alternatives in the -subpattern, a compile-time error occurs. - -There are three kinds of condition. If the text between the parentheses -consists of a sequence of digits, the condition is satisfied if the capturing -subpattern of that number has previously matched. The number must be greater -than zero. Consider the following pattern, which contains non-significant white -space to make it more readable (assume the PCRE_EXTENDED option) and to divide -it into three parts for ease of discussion: - - ( \\( )? [^()]+ (?(1) \\) ) - -The first part matches an optional opening parenthesis, and if that -character is present, sets it as the first captured substring. The second part -matches one or more characters that are not parentheses. The third part is a -conditional subpattern that tests whether the first set of parentheses matched -or not. If they did, that is, if subject started with an opening parenthesis, -the condition is true, and so the yes-pattern is executed and a closing -parenthesis is required. Otherwise, since no-pattern is not present, the -subpattern matches nothing. In other words, this pattern matches a sequence of -non-parentheses, optionally enclosed in parentheses. - -If the condition is the string (R), it is satisfied if a recursive call to the -pattern or subpattern has been made. At "top level", the condition is false. -This is a PCRE extension. Recursive patterns are described in the next section. - -If the condition is not a sequence of digits or (R), it must be an assertion. -This may be a positive or negative lookahead or lookbehind assertion. Consider -this pattern, again containing non-significant white space, and with the two -alternatives on the second line: - - (?(?=[^a-z]*[a-z]) - \\d{2}-[a-z]{3}-\\d{2} | \\d{2}-\\d{2}-\\d{2} ) - -The condition is a positive lookahead assertion that matches an optional -sequence of non-letters followed by a letter. In other words, it tests for the -presence of at least one letter in the subject. If a letter is found, the -subject is matched against the first alternative; otherwise it is matched -against the second. This pattern matches strings in one of the two forms -dd-aaa-dd or dd-dd-dd, where aaa are letters and dd are digits. - -.SH COMMENTS -.rs -.sp -The sequence (?# marks the start of a comment which continues up to the next -closing parenthesis. Nested parentheses are not permitted. The characters -that make up a comment play no part in the pattern matching at all. - -If the PCRE_EXTENDED option is set, an unescaped # character outside a -character class introduces a comment that continues up to the next newline -character in the pattern. - -.SH RECURSIVE PATTERNS -.rs -.sp -Consider the problem of matching a string in parentheses, allowing for -unlimited nested parentheses. Without the use of recursion, the best that can -be done is to use a pattern that matches up to some fixed depth of nesting. It -is not possible to handle an arbitrary nesting depth. Perl has provided an -experimental facility that allows regular expressions to recurse (amongst other -things). It does this by interpolating Perl code in the expression at run time, -and the code can refer to the expression itself. A Perl pattern to solve the -parentheses problem can be created like this: - - $re = qr{\\( (?: (?>[^()]+) | (?p{$re}) )* \\)}x; - -The (?p{...}) item interpolates Perl code at run time, and in this case refers -recursively to the pattern in which it appears. Obviously, PCRE cannot support -the interpolation of Perl code. Instead, it supports some special syntax for -recursion of the entire pattern, and also for individual subpattern recursion. - -The special item that consists of (? followed by a number greater than zero and -a closing parenthesis is a recursive call of the subpattern of the given -number, provided that it occurs inside that subpattern. (If not, it is a -"subroutine" call, which is described in the next section.) The special item -(?R) is a recursive call of the entire regular expression. - -For example, this PCRE pattern solves the nested parentheses problem (assume -the PCRE_EXTENDED option is set so that white space is ignored): - - \\( ( (?>[^()]+) | (?R) )* \\) - -First it matches an opening parenthesis. Then it matches any number of -substrings which can either be a sequence of non-parentheses, or a recursive -match of the pattern itself (that is a correctly parenthesized substring). -Finally there is a closing parenthesis. - -If this were part of a larger pattern, you would not want to recurse the entire -pattern, so instead you could use this: - - ( \\( ( (?>[^()]+) | (?1) )* \\) ) - -We have put the pattern into parentheses, and caused the recursion to refer to -them instead of the whole pattern. In a larger pattern, keeping track of -parenthesis numbers can be tricky. It may be more convenient to use named -parentheses instead. For this, PCRE uses (?P>name), which is an extension to -the Python syntax that PCRE uses for named parentheses (Perl does not provide -named parentheses). We could rewrite the above example as follows: - - (?P<pn> \\( ( (?>[^()]+) | (?P>pn) )* \\) ) - -This particular example pattern contains nested unlimited repeats, and so the -use of atomic grouping for matching strings of non-parentheses is important -when applying the pattern to strings that do not match. For example, when this -pattern is applied to - - (aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa() - -it yields "no match" quickly. However, if atomic grouping is not used, -the match runs for a very long time indeed because there are so many different -ways the + and * repeats can carve up the subject, and all have to be tested -before failure can be reported. - -At the end of a match, the values set for any capturing subpatterns are those -from the outermost level of the recursion at which the subpattern value is set. -If you want to obtain intermediate values, a callout function can be used (see -below and the -.\" HREF -\fBpcrecallout\fR -.\" -documentation). If the pattern above is matched against - - (ab(cd)ef) - -the value for the capturing parentheses is "ef", which is the last value taken -on at the top level. If additional parentheses are added, giving - - \\( ( ( (?>[^()]+) | (?R) )* ) \\) - ^ ^ - ^ ^ - -the string they capture is "ab(cd)ef", the contents of the top level -parentheses. If there are more than 15 capturing parentheses in a pattern, PCRE -has to obtain extra memory to store data during a recursion, which it does by -using \fBpcre_malloc\fR, freeing it via \fBpcre_free\fR afterwards. If no -memory can be obtained, the match fails with the PCRE_ERROR_NOMEMORY error. - -Do not confuse the (?R) item with the condition (R), which tests for recursion. -Consider this pattern, which matches text in angle brackets, allowing for -arbitrary nesting. Only digits are allowed in nested brackets (that is, when -recursing), whereas any characters are permitted at the outer level. - - < (?: (?(R) \\d++ | [^<>]*+) | (?R)) * > - -In this pattern, (?(R) is the start of a conditional subpattern, with two -different alternatives for the recursive and non-recursive cases. The (?R) item -is the actual recursive call. - -.\" HTML <a name="subpatternsassubroutines"></a> -.SH SUBPATTERNS AS SUBROUTINES -.rs -.sp -If the syntax for a recursive subpattern reference (either by number or by -name) is used outside the parentheses to which it refers, it operates like a -subroutine in a programming language. An earlier example pointed out that the -pattern - - (sens|respons)e and \\1ibility - -matches "sense and sensibility" and "response and responsibility", but not -"sense and responsibility". If instead the pattern - - (sens|respons)e and (?1)ibility - -is used, it does match "sense and responsibility" as well as the other two -strings. Such references must, however, follow the subpattern to which they -refer. - -.SH CALLOUTS -.rs -.sp -Perl has a feature whereby using the sequence (?{...}) causes arbitrary Perl -code to be obeyed in the middle of matching a regular expression. This makes it -possible, amongst other things, to extract different substrings that match the -same pair of parentheses when there is a repetition. - -PCRE provides a similar feature, but of course it cannot obey arbitrary Perl -code. The feature is called "callout". The caller of PCRE provides an external -function by putting its entry point in the global variable \fIpcre_callout\fR. -By default, this variable contains NULL, which disables all calling out. - -Within a regular expression, (?C) indicates the points at which the external -function is to be called. If you want to identify different callout points, you -can put a number less than 256 after the letter C. The default value is zero. -For example, this pattern has two callout points: - - (?C1)\dabc(?C2)def - -During matching, when PCRE reaches a callout point (and \fIpcre_callout\fR is -set), the external function is called. It is provided with the number of the -callout, and, optionally, one item of data originally supplied by the caller of -\fBpcre_exec()\fR. The callout function may cause matching to backtrack, or to -fail altogether. A complete description of the interface to the callout -function is given in the -.\" HREF -\fBpcrecallout\fR -.\" -documentation. - -.in 0 -Last updated: 03 February 2003 -.br -Copyright (c) 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/pcreperform.3 b/external-libs/pcre/doc/pcreperform.3 deleted file mode 100644 index 52a332fc..00000000 --- a/external-libs/pcre/doc/pcreperform.3 +++ /dev/null @@ -1,66 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH PCRE PERFORMANCE -.rs -.sp -Certain items that may appear in regular expression patterns are more efficient -than others. It is more efficient to use a character class like [aeiou] than a -set of alternatives such as (a|e|i|o|u). In general, the simplest construction -that provides the required behaviour is usually the most efficient. Jeffrey -Friedl's book contains a lot of discussion about optimizing regular expressions -for efficient performance. - -When a pattern begins with .* not in parentheses, or in parentheses that are -not the subject of a backreference, and the PCRE_DOTALL option is set, the -pattern is implicitly anchored by PCRE, since it can match only at the start of -a subject string. However, if PCRE_DOTALL is not set, PCRE cannot make this -optimization, because the . metacharacter does not then match a newline, and if -the subject string contains newlines, the pattern may match from the character -immediately following one of them instead of from the very start. For example, -the pattern - - .*second - -matches the subject "first\\nand second" (where \\n stands for a newline -character), with the match starting at the seventh character. In order to do -this, PCRE has to retry the match starting after every newline in the subject. - -If you are using such a pattern with subject strings that do not contain -newlines, the best performance is obtained by setting PCRE_DOTALL, or starting -the pattern with ^.* to indicate explicit anchoring. That saves PCRE from -having to scan along the subject looking for a newline to restart at. - -Beware of patterns that contain nested indefinite repeats. These can take a -long time to run when applied to a string that does not match. Consider the -pattern fragment - - (a+)* - -This can match "aaaa" in 33 different ways, and this number increases very -rapidly as the string gets longer. (The * repeat can match 0, 1, 2, 3, or 4 -times, and for each of those cases other than 0, the + repeats can match -different numbers of times.) When the remainder of the pattern is such that the -entire match is going to fail, PCRE has in principle to try every possible -variation, and this can take an extremely long time. - -An optimization catches some of the more simple cases such as - - (a+)*b - -where a literal character follows. Before embarking on the standard matching -procedure, PCRE checks that there is a "b" later in the subject string, and if -there is not, it fails the match immediately. However, when there is no -following literal this optimization cannot be used. You can see the difference -by comparing the behaviour of - - (a+)*\\d - -with the pattern above. The former gives a failure almost instantly when -applied to a whole line of "a" characters, whereas the latter takes an -appreciable time with strings longer than about 20 characters. - -.in 0 -Last updated: 03 February 2003 -.br -Copyright (c) 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/pcreposix.3 b/external-libs/pcre/doc/pcreposix.3 deleted file mode 100644 index 5198630f..00000000 --- a/external-libs/pcre/doc/pcreposix.3 +++ /dev/null @@ -1,194 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions. -.SH SYNOPSIS OF POSIX API -.B #include <pcreposix.h> -.PP -.SM -.br -.B int regcomp(regex_t *\fIpreg\fR, const char *\fIpattern\fR, -.ti +5n -.B int \fIcflags\fR); -.PP -.br -.B int regexec(regex_t *\fIpreg\fR, const char *\fIstring\fR, -.ti +5n -.B size_t \fInmatch\fR, regmatch_t \fIpmatch\fR[], int \fIeflags\fR); -.PP -.br -.B size_t regerror(int \fIerrcode\fR, const regex_t *\fIpreg\fR, -.ti +5n -.B char *\fIerrbuf\fR, size_t \fIerrbuf_size\fR); -.PP -.br -.B void regfree(regex_t *\fIpreg\fR); - -.SH DESCRIPTION -.rs -.sp -This set of functions provides a POSIX-style API to the PCRE regular expression -package. See the -.\" HREF -\fBpcreapi\fR -.\" -documentation for a description of the native API, which contains additional -functionality. - -The functions described here are just wrapper functions that ultimately call -the PCRE native API. Their prototypes are defined in the \fBpcreposix.h\fR -header file, and on Unix systems the library itself is called -\fBpcreposix.a\fR, so can be accessed by adding \fB-lpcreposix\fR to the -command for linking an application which uses them. Because the POSIX functions -call the native ones, it is also necessary to add \fR-lpcre\fR. - -I have implemented only those option bits that can be reasonably mapped to PCRE -native options. In addition, the options REG_EXTENDED and REG_NOSUB are defined -with the value zero. They have no effect, but since programs that are written -to the POSIX interface often use them, this makes it easier to slot in PCRE as -a replacement library. Other POSIX options are not even defined. - -When PCRE is called via these functions, it is only the API that is POSIX-like -in style. The syntax and semantics of the regular expressions themselves are -still those of Perl, subject to the setting of various PCRE options, as -described below. "POSIX-like in style" means that the API approximates to the -POSIX definition; it is not fully POSIX-compatible, and in multi-byte encoding -domains it is probably even less compatible. - -The header for these functions is supplied as \fBpcreposix.h\fR to avoid any -potential clash with other POSIX libraries. It can, of course, be renamed or -aliased as \fBregex.h\fR, which is the "correct" name. It provides two -structure types, \fIregex_t\fR for compiled internal forms, and -\fIregmatch_t\fR for returning captured substrings. It also defines some -constants whose names start with "REG_"; these are used for setting options and -identifying error codes. - -.SH COMPILING A PATTERN -.rs -.sp -The function \fBregcomp()\fR is called to compile a pattern into an -internal form. The pattern is a C string terminated by a binary zero, and -is passed in the argument \fIpattern\fR. The \fIpreg\fR argument is a pointer -to a regex_t structure which is used as a base for storing information about -the compiled expression. - -The argument \fIcflags\fR is either zero, or contains one or more of the bits -defined by the following macros: - - REG_ICASE - -The PCRE_CASELESS option is set when the expression is passed for compilation -to the native function. - - REG_NEWLINE - -The PCRE_MULTILINE option is set when the expression is passed for compilation -to the native function. Note that this does \fInot\fR mimic the defined POSIX -behaviour for REG_NEWLINE (see the following section). - -In the absence of these flags, no options are passed to the native function. -This means the the regex is compiled with PCRE default semantics. In -particular, the way it handles newline characters in the subject string is the -Perl way, not the POSIX way. Note that setting PCRE_MULTILINE has only -\fIsome\fR of the effects specified for REG_NEWLINE. It does not affect the way -newlines are matched by . (they aren't) or by a negative class such as [^a] -(they are). - -The yield of \fBregcomp()\fR is zero on success, and non-zero otherwise. The -\fIpreg\fR structure is filled in on success, and one member of the structure -is public: \fIre_nsub\fR contains the number of capturing subpatterns in -the regular expression. Various error codes are defined in the header file. - -.SH MATCHING NEWLINE CHARACTERS -.rs -.sp -This area is not simple, because POSIX and Perl take different views of things. -It is not possible to get PCRE to obey POSIX semantics, but then PCRE was never -intended to be a POSIX engine. The following table lists the different -possibilities for matching newline characters in PCRE: - - Default Change with - - . matches newline no PCRE_DOTALL - newline matches [^a] yes not changeable - $ matches \\n at end yes PCRE_DOLLARENDONLY - $ matches \\n in middle no PCRE_MULTILINE - ^ matches \\n in middle no PCRE_MULTILINE - -This is the equivalent table for POSIX: - - Default Change with - - . matches newline yes REG_NEWLINE - newline matches [^a] yes REG_NEWLINE - $ matches \\n at end no REG_NEWLINE - $ matches \\n in middle no REG_NEWLINE - ^ matches \\n in middle no REG_NEWLINE - -PCRE's behaviour is the same as Perl's, except that there is no equivalent for -PCRE_DOLLARENDONLY in Perl. In both PCRE and Perl, there is no way to stop -newline from matching [^a]. - -The default POSIX newline handling can be obtained by setting PCRE_DOTALL and -PCRE_DOLLARENDONLY, but there is no way to make PCRE behave exactly as for the -REG_NEWLINE action. - -.SH MATCHING A PATTERN -.rs -.sp -The function \fBregexec()\fR is called to match a pre-compiled pattern -\fIpreg\fR against a given \fIstring\fR, which is terminated by a zero byte, -subject to the options in \fIeflags\fR. These can be: - - REG_NOTBOL - -The PCRE_NOTBOL option is set when calling the underlying PCRE matching -function. - - REG_NOTEOL - -The PCRE_NOTEOL option is set when calling the underlying PCRE matching -function. - -The portion of the string that was matched, and also any captured substrings, -are returned via the \fIpmatch\fR argument, which points to an array of -\fInmatch\fR structures of type \fIregmatch_t\fR, containing the members -\fIrm_so\fR and \fIrm_eo\fR. These contain the offset to the first character of -each substring and the offset to the first character after the end of each -substring, respectively. The 0th element of the vector relates to the entire -portion of \fIstring\fR that was matched; subsequent elements relate to the -capturing subpatterns of the regular expression. Unused entries in the array -have both structure members set to -1. - -A successful match yields a zero return; various error codes are defined in the -header file, of which REG_NOMATCH is the "expected" failure code. - -.SH ERROR MESSAGES -.rs -.sp -The \fBregerror()\fR function maps a non-zero errorcode from either -\fBregcomp()\fR or \fBregexec()\fR to a printable message. If \fIpreg\fR is not -NULL, the error should have arisen from the use of that structure. A message -terminated by a binary zero is placed in \fIerrbuf\fR. The length of the -message, including the zero, is limited to \fIerrbuf_size\fR. The yield of the -function is the size of buffer needed to hold the whole message. - -.SH STORAGE -.rs -.sp -Compiling a regular expression causes memory to be allocated and associated -with the \fIpreg\fR structure. The function \fBregfree()\fR frees all such -memory, after which \fIpreg\fR may no longer be used as a compiled expression. - -.SH AUTHOR -.rs -.sp -Philip Hazel <ph10@cam.ac.uk> -.br -University Computing Service, -.br -Cambridge CB2 3QG, England. - -.in 0 -Last updated: 03 February 2003 -.br -Copyright (c) 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/pcresample.3 b/external-libs/pcre/doc/pcresample.3 deleted file mode 100644 index 02a7a548..00000000 --- a/external-libs/pcre/doc/pcresample.3 +++ /dev/null @@ -1,52 +0,0 @@ -.TH PCRE 3 -.SH NAME -PCRE - Perl-compatible regular expressions -.SH PCRE SAMPLE PROGRAM -.rs -.sp -A simple, complete demonstration program, to get you started with using PCRE, -is supplied in the file \fIpcredemo.c\fR in the PCRE distribution. - -The program compiles the regular expression that is its first argument, and -matches it against the subject string in its second argument. No PCRE options -are set, and default character tables are used. If matching succeeds, the -program outputs the portion of the subject that matched, together with the -contents of any captured substrings. - -If the -g option is given on the command line, the program then goes on to -check for further matches of the same regular expression in the same subject -string. The logic is a little bit tricky because of the possibility of matching -an empty string. Comments in the code explain what is going on. - -On a Unix system that has PCRE installed in \fI/usr/local\fR, you can compile -the demonstration program using a command like this: - - gcc -o pcredemo pcredemo.c -I/usr/local/include \\ - -L/usr/local/lib -lpcre - -Then you can run simple tests like this: - - ./pcredemo 'cat|dog' 'the cat sat on the mat' - ./pcredemo -g 'cat|dog' 'the dog sat on the cat' - -Note that there is a much more comprehensive test program, called -\fBpcretest\fR, which supports many more facilities for testing regular -expressions and the PCRE library. The \fBpcredemo\fR program is provided as a -simple coding example. - -On some operating systems (e.g. Solaris) you may get an error like this when -you try to run \fBpcredemo\fR: - - ld.so.1: a.out: fatal: libpcre.so.0: open failed: No such file or directory - -This is caused by the way shared library support works on those systems. You -need to add - - -R/usr/local/lib - -to the compile command to get round this problem. - -.in 0 -Last updated: 28 January 2003 -.br -Copyright (c) 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/pcretest.1 b/external-libs/pcre/doc/pcretest.1 deleted file mode 100644 index f3d69c83..00000000 --- a/external-libs/pcre/doc/pcretest.1 +++ /dev/null @@ -1,364 +0,0 @@ -.TH PCRETEST 1 -.SH NAME -pcretest - a program for testing Perl-compatible regular expressions. -.SH SYNOPSIS -.B pcretest "[-d] [-i] [-m] [-o osize] [-p] [-t] [source] [destination]" - -\fBpcretest\fR was written as a test program for the PCRE regular expression -library itself, but it can also be used for experimenting with regular -expressions. This document describes the features of the test program; for -details of the regular expressions themselves, see the -.\" HREF -\fBpcrepattern\fR -.\" -documentation. For details of PCRE and its options, see the -.\" HREF -\fBpcreapi\fR -.\" -documentation. - -.SH OPTIONS -.rs -.sp -.TP 10 -\fB-C\fR -Output the version number of the PCRE library, and all available information -about the optional features that are included, and then exit. -.TP 10 -\fB-d\fR -Behave as if each regex had the \fB/D\fR modifier (see below); the internal -form is output after compilation. -.TP 10 -\fB-i\fR -Behave as if each regex had the \fB/I\fR modifier; information about the -compiled pattern is given after compilation. -.TP 10 -\fB-m\fR -Output the size of each compiled pattern after it has been compiled. This is -equivalent to adding /M to each regular expression. For compatibility with -earlier versions of pcretest, \fB-s\fR is a synonym for \fB-m\fR. -.TP 10 -\fB-o\fR \fIosize\fR -Set the number of elements in the output vector that is used when calling PCRE -to be \fIosize\fR. The default value is 45, which is enough for 14 capturing -subexpressions. The vector size can be changed for individual matching calls by -including \\O in the data line (see below). -.TP 10 -\fB-p\fR -Behave as if each regex has \fB/P\fR modifier; the POSIX wrapper API is used -to call PCRE. None of the other options has any effect when \fB-p\fR is set. -.TP 10 -\fB-t\fR -Run each compile, study, and match many times with a timer, and output -resulting time per compile or match (in milliseconds). Do not set \fB-t\fR with -\fB-m\fR, because you will then get the size output 20000 times and the timing -will be distorted. - -.SH DESCRIPTION -.rs -.sp -If \fBpcretest\fR is given two filename arguments, it reads from the first and -writes to the second. If it is given only one filename argument, it reads from -that file and writes to stdout. Otherwise, it reads from stdin and writes to -stdout, and prompts for each line of input, using "re>" to prompt for regular -expressions, and "data>" to prompt for data lines. - -The program handles any number of sets of input on a single input file. Each -set starts with a regular expression, and continues with any number of data -lines to be matched against the pattern. - -Each line is matched separately and independently. If you want to do -multiple-line matches, you have to use the \\n escape sequence in a single line -of input to encode the newline characters. The maximum length of data line is -30,000 characters. - -An empty line signals the end of the data lines, at which point a new regular -expression is read. The regular expressions are given enclosed in any -non-alphameric delimiters other than backslash, for example - - /(a|bc)x+yz/ - -White space before the initial delimiter is ignored. A regular expression may -be continued over several input lines, in which case the newline characters are -included within it. It is possible to include the delimiter within the pattern -by escaping it, for example - - /abc\\/def/ - -If you do so, the escape and the delimiter form part of the pattern, but since -delimiters are always non-alphameric, this does not affect its interpretation. -If the terminating delimiter is immediately followed by a backslash, for -example, - - /abc/\\ - -then a backslash is added to the end of the pattern. This is done to provide a -way of testing the error condition that arises if a pattern finishes with a -backslash, because - - /abc\\/ - -is interpreted as the first line of a pattern that starts with "abc/", causing -pcretest to read the next line as a continuation of the regular expression. - -.SH PATTERN MODIFIERS -.rs -.sp -The pattern may be followed by \fBi\fR, \fBm\fR, \fBs\fR, or \fBx\fR to set the -PCRE_CASELESS, PCRE_MULTILINE, PCRE_DOTALL, or PCRE_EXTENDED options, -respectively. For example: - - /caseless/i - -These modifier letters have the same effect as they do in Perl. There are -others that set PCRE options that do not correspond to anything in Perl: -\fB/A\fR, \fB/E\fR, \fB/N\fR, \fB/U\fR, and \fB/X\fR set PCRE_ANCHORED, -PCRE_DOLLAR_ENDONLY, PCRE_NO_AUTO_CAPTURE, PCRE_UNGREEDY, and PCRE_EXTRA -respectively. - -Searching for all possible matches within each subject string can be requested -by the \fB/g\fR or \fB/G\fR modifier. After finding a match, PCRE is called -again to search the remainder of the subject string. The difference between -\fB/g\fR and \fB/G\fR is that the former uses the \fIstartoffset\fR argument to -\fBpcre_exec()\fR to start searching at a new point within the entire string -(which is in effect what Perl does), whereas the latter passes over a shortened -substring. This makes a difference to the matching process if the pattern -begins with a lookbehind assertion (including \\b or \\B). - -If any call to \fBpcre_exec()\fR in a \fB/g\fR or \fB/G\fR sequence matches an -empty string, the next call is done with the PCRE_NOTEMPTY and PCRE_ANCHORED -flags set in order to search for another, non-empty, match at the same point. -If this second match fails, the start offset is advanced by one, and the normal -match is retried. This imitates the way Perl handles such cases when using the -\fB/g\fR modifier or the \fBsplit()\fR function. - -There are a number of other modifiers for controlling the way \fBpcretest\fR -operates. - -The \fB/+\fR modifier requests that as well as outputting the substring that -matched the entire pattern, pcretest should in addition output the remainder of -the subject string. This is useful for tests where the subject contains -multiple copies of the same substring. - -The \fB/L\fR modifier must be followed directly by the name of a locale, for -example, - - /pattern/Lfr - -For this reason, it must be the last modifier letter. The given locale is set, -\fBpcre_maketables()\fR is called to build a set of character tables for the -locale, and this is then passed to \fBpcre_compile()\fR when compiling the -regular expression. Without an \fB/L\fR modifier, NULL is passed as the tables -pointer; that is, \fB/L\fR applies only to the expression on which it appears. - -The \fB/I\fR modifier requests that \fBpcretest\fR output information about the -compiled expression (whether it is anchored, has a fixed first character, and -so on). It does this by calling \fBpcre_fullinfo()\fR after compiling an -expression, and outputting the information it gets back. If the pattern is -studied, the results of that are also output. - -The \fB/D\fR modifier is a PCRE debugging feature, which also assumes \fB/I\fR. -It causes the internal form of compiled regular expressions to be output after -compilation. If the pattern was studied, the information returned is also -output. - -The \fB/S\fR modifier causes \fBpcre_study()\fR to be called after the -expression has been compiled, and the results used when the expression is -matched. - -The \fB/M\fR modifier causes the size of memory block used to hold the compiled -pattern to be output. - -The \fB/P\fR modifier causes \fBpcretest\fR to call PCRE via the POSIX wrapper -API rather than its native API. When this is done, all other modifiers except -\fB/i\fR, \fB/m\fR, and \fB/+\fR are ignored. REG_ICASE is set if \fB/i\fR is -present, and REG_NEWLINE is set if \fB/m\fR is present. The wrapper functions -force PCRE_DOLLAR_ENDONLY always, and PCRE_DOTALL unless REG_NEWLINE is set. - -The \fB/8\fR modifier causes \fBpcretest\fR to call PCRE with the PCRE_UTF8 -option set. This turns on support for UTF-8 character handling in PCRE, -provided that it was compiled with this support enabled. This modifier also -causes any non-printing characters in output strings to be printed using the -\\x{hh...} notation if they are valid UTF-8 sequences. - -If the \fB/?\fR modifier is used with \fB/8\fR, it causes \fBpcretest\fR to -call \fBpcre_compile()\fR with the PCRE_NO_UTF8_CHECK option, to suppress the -checking of the string for UTF-8 validity. - -.SH CALLOUTS -.rs -.sp -If the pattern contains any callout requests, \fBpcretest\fR's callout function -will be called. By default, it displays the callout number, and the start and -current positions in the text at the callout time. For example, the output - - --->pqrabcdef - 0 ^ ^ - -indicates that callout number 0 occurred for a match attempt starting at the -fourth character of the subject string, when the pointer was at the seventh -character. The callout function returns zero (carry on matching) by default. - -Inserting callouts may be helpful when using \fBpcretest\fR to check -complicated regular expressions. For further information about callouts, see -the -.\" HREF -\fBpcrecallout\fR -.\" -documentation. - -For testing the PCRE library, additional control of callout behaviour is -available via escape sequences in the data, as described in the following -section. In particular, it is possible to pass in a number as callout data (the -default is zero). If the callout function receives a non-zero number, it -returns that value instead of zero. - -.SH DATA LINES -.rs -.sp -Before each data line is passed to \fBpcre_exec()\fR, leading and trailing -whitespace is removed, and it is then scanned for \\ escapes. Some of these are -pretty esoteric features, intended for checking out some of the more -complicated features of PCRE. If you are just testing "ordinary" regular -expressions, you probably don't need any of these. The following escapes are -recognized: - - \\a alarm (= BEL) - \\b backspace - \\e escape - \\f formfeed - \\n newline - \\r carriage return - \\t tab - \\v vertical tab - \\nnn octal character (up to 3 octal digits) - \\xhh hexadecimal character (up to 2 hex digits) - \\x{hh...} hexadecimal character, any number of digits - in UTF-8 mode - \\A pass the PCRE_ANCHORED option to \fBpcre_exec()\fR - \\B pass the PCRE_NOTBOL option to \fBpcre_exec()\fR - \\Cdd call pcre_copy_substring() for substring dd - after a successful match (any decimal number - less than 32) - \\Cname call pcre_copy_named_substring() for substring - "name" after a successful match (name termin- - ated by next non alphanumeric character) - \\C+ show the current captured substrings at callout - time - \\C- do not supply a callout function - \\C!n return 1 instead of 0 when callout number n is - reached - \\C!n!m return 1 instead of 0 when callout number n is - reached for the nth time - \\C*n pass the number n (may be negative) as callout - data - \\Gdd call pcre_get_substring() for substring dd - after a successful match (any decimal number - less than 32) - \\Gname call pcre_get_named_substring() for substring - "name" after a successful match (name termin- - ated by next non-alphanumeric character) - \\L call pcre_get_substringlist() after a - successful match - \\M discover the minimum MATCH_LIMIT setting - \\N pass the PCRE_NOTEMPTY option to \fBpcre_exec()\fR - \\Odd set the size of the output vector passed to - \fBpcre_exec()\fR to dd (any number of decimal - digits) - \\S output details of memory get/free calls during matching - \\Z pass the PCRE_NOTEOL option to \fBpcre_exec()\fR - \\? pass the PCRE_NO_UTF8_CHECK option to - \fBpcre_exec()\fR - -If \\M is present, \fBpcretest\fR calls \fBpcre_exec()\fR several times, with -different values in the \fImatch_limit\fR field of the \fBpcre_extra\fR data -structure, until it finds the minimum number that is needed for -\fBpcre_exec()\fR to complete. This number is a measure of the amount of -recursion and backtracking that takes place, and checking it out can be -instructive. For most simple matches, the number is quite small, but for -patterns with very large numbers of matching possibilities, it can become large -very quickly with increasing length of subject string. - -When \\O is used, it may be higher or lower than the size set by the \fB-O\fR -option (or defaulted to 45); \\O applies only to the call of \fBpcre_exec()\fR -for the line in which it appears. - -A backslash followed by anything else just escapes the anything else. If the -very last character is a backslash, it is ignored. This gives a way of passing -an empty line as data, since a real empty line terminates the data input. - -If \fB/P\fR was present on the regex, causing the POSIX wrapper API to be used, -only \fB\B\fR, and \fB\Z\fR have any effect, causing REG_NOTBOL and REG_NOTEOL -to be passed to \fBregexec()\fR respectively. - -The use of \\x{hh...} to represent UTF-8 characters is not dependent on the use -of the \fB/8\fR modifier on the pattern. It is recognized always. There may be -any number of hexadecimal digits inside the braces. The result is from one to -six bytes, encoded according to the UTF-8 rules. - -.SH OUTPUT FROM PCRETEST -.rs -.sp -When a match succeeds, pcretest outputs the list of captured substrings that -\fBpcre_exec()\fR returns, starting with number 0 for the string that matched -the whole pattern. Here is an example of an interactive pcretest run. - - $ pcretest - PCRE version 4.00 08-Jan-2003 - - re> /^abc(\\d+)/ - data> abc123 - 0: abc123 - 1: 123 - data> xyz - No match - -If the strings contain any non-printing characters, they are output as \\0x -escapes, or as \\x{...} escapes if the \fB/8\fR modifier was present on the -pattern. If the pattern has the \fB/+\fR modifier, then the output for -substring 0 is followed by the the rest of the subject string, identified by -"0+" like this: - - re> /cat/+ - data> cataract - 0: cat - 0+ aract - -If the pattern has the \fB/g\fR or \fB/G\fR modifier, the results of successive -matching attempts are output in sequence, like this: - - re> /\\Bi(\\w\\w)/g - data> Mississippi - 0: iss - 1: ss - 0: iss - 1: ss - 0: ipp - 1: pp - -"No match" is output only if the first match attempt fails. - -If any of the sequences \fB\\C\fR, \fB\\G\fR, or \fB\\L\fR are present in a -data line that is successfully matched, the substrings extracted by the -convenience functions are output with C, G, or L after the string number -instead of a colon. This is in addition to the normal full list. The string -length (that is, the return from the extraction function) is given in -parentheses after each string for \fB\\C\fR and \fB\\G\fR. - -Note that while patterns can be continued over several lines (a plain ">" -prompt is used for continuations), data lines may not. However newlines can be -included in data by means of the \\n escape. - -.SH AUTHOR -.rs -.sp -Philip Hazel <ph10@cam.ac.uk> -.br -University Computing Service, -.br -Cambridge CB2 3QG, England. - -.in 0 -Last updated: 09 December 2003 -.br -Copyright (c) 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/pcretest.txt b/external-libs/pcre/doc/pcretest.txt deleted file mode 100644 index 0e9cd138..00000000 --- a/external-libs/pcre/doc/pcretest.txt +++ /dev/null @@ -1,357 +0,0 @@ -PCRETEST(1) PCRETEST(1) - - - -NAME - pcretest - a program for testing Perl-compatible regular expressions. - -SYNOPSIS - pcretest [-d] [-i] [-m] [-o osize] [-p] [-t] [source] [destination] - - pcretest was written as a test program for the PCRE regular expression - library itself, but it can also be used for experimenting with regular - expressions. This document describes the features of the test program; - for details of the regular expressions themselves, see the pcrepattern - documentation. For details of PCRE and its options, see the pcreapi - documentation. - - -OPTIONS - - - -C Output the version number of the PCRE library, and all avail- - able information about the optional features that are - included, and then exit. - - -d Behave as if each regex had the /D modifier (see below); the - internal form is output after compilation. - - -i Behave as if each regex had the /I modifier; information - about the compiled pattern is given after compilation. - - -m Output the size of each compiled pattern after it has been - compiled. This is equivalent to adding /M to each regular - expression. For compatibility with earlier versions of - pcretest, -s is a synonym for -m. - - -o osize Set the number of elements in the output vector that is used - when calling PCRE to be osize. The default value is 45, which - is enough for 14 capturing subexpressions. The vector size - can be changed for individual matching calls by including \O - in the data line (see below). - - -p Behave as if each regex has /P modifier; the POSIX wrapper - API is used to call PCRE. None of the other options has any - effect when -p is set. - - -t Run each compile, study, and match many times with a timer, - and output resulting time per compile or match (in millisec- - onds). Do not set -t with -m, because you will then get the - size output 20000 times and the timing will be distorted. - - -DESCRIPTION - - If pcretest is given two filename arguments, it reads from the first - and writes to the second. If it is given only one filename argument, it - reads from that file and writes to stdout. Otherwise, it reads from - stdin and writes to stdout, and prompts for each line of input, using - "re>" to prompt for regular expressions, and "data>" to prompt for data - lines. - - The program handles any number of sets of input on a single input file. - Each set starts with a regular expression, and continues with any num- - ber of data lines to be matched against the pattern. - - Each line is matched separately and independently. If you want to do - multiple-line matches, you have to use the \n escape sequence in a sin- - gle line of input to encode the newline characters. The maximum length - of data line is 30,000 characters. - - An empty line signals the end of the data lines, at which point a new - regular expression is read. The regular expressions are given enclosed - in any non-alphameric delimiters other than backslash, for example - - /(a|bc)x+yz/ - - White space before the initial delimiter is ignored. A regular expres- - sion may be continued over several input lines, in which case the new- - line characters are included within it. It is possible to include the - delimiter within the pattern by escaping it, for example - - /abc\/def/ - - If you do so, the escape and the delimiter form part of the pattern, - but since delimiters are always non-alphameric, this does not affect - its interpretation. If the terminating delimiter is immediately fol- - lowed by a backslash, for example, - - /abc/\ - - then a backslash is added to the end of the pattern. This is done to - provide a way of testing the error condition that arises if a pattern - finishes with a backslash, because - - /abc\/ - - is interpreted as the first line of a pattern that starts with "abc/", - causing pcretest to read the next line as a continuation of the regular - expression. - - -PATTERN MODIFIERS - - The pattern may be followed by i, m, s, or x to set the PCRE_CASELESS, - PCRE_MULTILINE, PCRE_DOTALL, or PCRE_EXTENDED options, respectively. - For example: - - /caseless/i - - These modifier letters have the same effect as they do in Perl. There - are others that set PCRE options that do not correspond to anything in - Perl: /A, /E, /N, /U, and /X set PCRE_ANCHORED, PCRE_DOLLAR_ENDONLY, - PCRE_NO_AUTO_CAPTURE, PCRE_UNGREEDY, and PCRE_EXTRA respectively. - - Searching for all possible matches within each subject string can be - requested by the /g or /G modifier. After finding a match, PCRE is - called again to search the remainder of the subject string. The differ- - ence between /g and /G is that the former uses the startoffset argument - to pcre_exec() to start searching at a new point within the entire - string (which is in effect what Perl does), whereas the latter passes - over a shortened substring. This makes a difference to the matching - process if the pattern begins with a lookbehind assertion (including \b - or \B). - - If any call to pcre_exec() in a /g or /G sequence matches an empty - string, the next call is done with the PCRE_NOTEMPTY and PCRE_ANCHORED - flags set in order to search for another, non-empty, match at the same - point. If this second match fails, the start offset is advanced by - one, and the normal match is retried. This imitates the way Perl han- - dles such cases when using the /g modifier or the split() function. - - There are a number of other modifiers for controlling the way pcretest - operates. - - The /+ modifier requests that as well as outputting the substring that - matched the entire pattern, pcretest should in addition output the - remainder of the subject string. This is useful for tests where the - subject contains multiple copies of the same substring. - - The /L modifier must be followed directly by the name of a locale, for - example, - - /pattern/Lfr - - For this reason, it must be the last modifier letter. The given locale - is set, pcre_maketables() is called to build a set of character tables - for the locale, and this is then passed to pcre_compile() when compil- - ing the regular expression. Without an /L modifier, NULL is passed as - the tables pointer; that is, /L applies only to the expression on which - it appears. - - The /I modifier requests that pcretest output information about the - compiled expression (whether it is anchored, has a fixed first charac- - ter, and so on). It does this by calling pcre_fullinfo() after compil- - ing an expression, and outputting the information it gets back. If the - pattern is studied, the results of that are also output. - - The /D modifier is a PCRE debugging feature, which also assumes /I. It - causes the internal form of compiled regular expressions to be output - after compilation. If the pattern was studied, the information returned - is also output. - - The /S modifier causes pcre_study() to be called after the expression - has been compiled, and the results used when the expression is matched. - - The /M modifier causes the size of memory block used to hold the com- - piled pattern to be output. - - The /P modifier causes pcretest to call PCRE via the POSIX wrapper API - rather than its native API. When this is done, all other modifiers - except /i, /m, and /+ are ignored. REG_ICASE is set if /i is present, - and REG_NEWLINE is set if /m is present. The wrapper functions force - PCRE_DOLLAR_ENDONLY always, and PCRE_DOTALL unless REG_NEWLINE is set. - - The /8 modifier causes pcretest to call PCRE with the PCRE_UTF8 option - set. This turns on support for UTF-8 character handling in PCRE, pro- - vided that it was compiled with this support enabled. This modifier - also causes any non-printing characters in output strings to be printed - using the \x{hh...} notation if they are valid UTF-8 sequences. - - If the /? modifier is used with /8, it causes pcretest to call - pcre_compile() with the PCRE_NO_UTF8_CHECK option, to suppress the - checking of the string for UTF-8 validity. - - -CALLOUTS - - If the pattern contains any callout requests, pcretest's callout func- - tion will be called. By default, it displays the callout number, and - the start and current positions in the text at the callout time. For - example, the output - - --->pqrabcdef - 0 ^ ^ - - indicates that callout number 0 occurred for a match attempt starting - at the fourth character of the subject string, when the pointer was at - the seventh character. The callout function returns zero (carry on - matching) by default. - - Inserting callouts may be helpful when using pcretest to check compli- - cated regular expressions. For further information about callouts, see - the pcrecallout documentation. - - For testing the PCRE library, additional control of callout behaviour - is available via escape sequences in the data, as described in the fol- - lowing section. In particular, it is possible to pass in a number as - callout data (the default is zero). If the callout function receives a - non-zero number, it returns that value instead of zero. - - -DATA LINES - - Before each data line is passed to pcre_exec(), leading and trailing - whitespace is removed, and it is then scanned for \ escapes. Some of - these are pretty esoteric features, intended for checking out some of - the more complicated features of PCRE. If you are just testing "ordi- - nary" regular expressions, you probably don't need any of these. The - following escapes are recognized: - - \a alarm (= BEL) - \b backspace - \e escape - \f formfeed - \n newline - \r carriage return - \t tab - \v vertical tab - \nnn octal character (up to 3 octal digits) - \xhh hexadecimal character (up to 2 hex digits) - \x{hh...} hexadecimal character, any number of digits - in UTF-8 mode - \A pass the PCRE_ANCHORED option to pcre_exec() - \B pass the PCRE_NOTBOL option to pcre_exec() - \Cdd call pcre_copy_substring() for substring dd - after a successful match (any decimal number - less than 32) - \Cname call pcre_copy_named_substring() for substring - "name" after a successful match (name termin- - ated by next non alphanumeric character) - \C+ show the current captured substrings at callout - time - \C- do not supply a callout function - \C!n return 1 instead of 0 when callout number n is - reached - \C!n!m return 1 instead of 0 when callout number n is - reached for the nth time - \C*n pass the number n (may be negative) as callout - data - \Gdd call pcre_get_substring() for substring dd - after a successful match (any decimal number - less than 32) - \Gname call pcre_get_named_substring() for substring - "name" after a successful match (name termin- - ated by next non-alphanumeric character) - \L call pcre_get_substringlist() after a - successful match - \M discover the minimum MATCH_LIMIT setting - \N pass the PCRE_NOTEMPTY option to pcre_exec() - \Odd set the size of the output vector passed to - pcre_exec() to dd (any number of decimal - digits) - \S output details of memory get/free calls during matching - \Z pass the PCRE_NOTEOL option to pcre_exec() - \? pass the PCRE_NO_UTF8_CHECK option to - pcre_exec() - - If \M is present, pcretest calls pcre_exec() several times, with dif- - ferent values in the match_limit field of the pcre_extra data struc- - ture, until it finds the minimum number that is needed for pcre_exec() - to complete. This number is a measure of the amount of recursion and - backtracking that takes place, and checking it out can be instructive. - For most simple matches, the number is quite small, but for patterns - with very large numbers of matching possibilities, it can become large - very quickly with increasing length of subject string. - - When \O is used, it may be higher or lower than the size set by the -O - option (or defaulted to 45); \O applies only to the call of pcre_exec() - for the line in which it appears. - - A backslash followed by anything else just escapes the anything else. - If the very last character is a backslash, it is ignored. This gives a - way of passing an empty line as data, since a real empty line termi- - nates the data input. - - If /P was present on the regex, causing the POSIX wrapper API to be - used, only 0 causing REG_NOTBOL and REG_NOTEOL to be passed to - regexec() respectively. - - The use of \x{hh...} to represent UTF-8 characters is not dependent on - the use of the /8 modifier on the pattern. It is recognized always. - There may be any number of hexadecimal digits inside the braces. The - result is from one to six bytes, encoded according to the UTF-8 rules. - - -OUTPUT FROM PCRETEST - - When a match succeeds, pcretest outputs the list of captured substrings - that pcre_exec() returns, starting with number 0 for the string that - matched the whole pattern. Here is an example of an interactive - pcretest run. - - $ pcretest - PCRE version 4.00 08-Jan-2003 - - re> /^abc(\d+)/ - data> abc123 - 0: abc123 - 1: 123 - data> xyz - No match - - If the strings contain any non-printing characters, they are output as - \0x escapes, or as \x{...} escapes if the /8 modifier was present on - the pattern. If the pattern has the /+ modifier, then the output for - substring 0 is followed by the the rest of the subject string, identi- - fied by "0+" like this: - - re> /cat/+ - data> cataract - 0: cat - 0+ aract - - If the pattern has the /g or /G modifier, the results of successive - matching attempts are output in sequence, like this: - - re> /\Bi(\w\w)/g - data> Mississippi - 0: iss - 1: ss - 0: iss - 1: ss - 0: ipp - 1: pp - - "No match" is output only if the first match attempt fails. - - If any of the sequences \C, \G, or \L are present in a data line that - is successfully matched, the substrings extracted by the convenience - functions are output with C, G, or L after the string number instead of - a colon. This is in addition to the normal full list. The string length - (that is, the return from the extraction function) is given in paren- - theses after each string for \C and \G. - - Note that while patterns can be continued over several lines (a plain - ">" prompt is used for continuations), data lines may not. However new- - lines can be included in data by means of the \n escape. - - -AUTHOR - - Philip Hazel <ph10@cam.ac.uk> - University Computing Service, - Cambridge CB2 3QG, England. - -Last updated: 09 December 2003 -Copyright (c) 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/perltest.txt b/external-libs/pcre/doc/perltest.txt deleted file mode 100644 index 9ea9d932..00000000 --- a/external-libs/pcre/doc/perltest.txt +++ /dev/null @@ -1,34 +0,0 @@ -The perltest program --------------------- - -The perltest program tests Perl's regular expressions; it has the same -specification as pcretest, and so can be given identical input, except that -input patterns can be followed only by Perl's lower case modifiers and /+ (as -used by pcretest), which is recognized and handled by the program. - -The data lines are processed as Perl double-quoted strings, so if they contain -" \ $ or @ characters, these have to be escaped. For this reason, all such -characters in testinput1 and testinput3 are escaped so that they can be used -for perltest as well as for pcretest, and the special upper case modifiers such -as /A that pcretest recognizes are not used in these files. The output should -be identical, apart from the initial identifying banner. - -The perltest script can also test UTF-8 features. It works as is for Perl 5.8 -or higher. It recognizes the special modifier /8 that pcretest uses to invoke -UTF-8 functionality. The testinput5 file can be fed to perltest to run UTF-8 -tests. - -For Perl 5.6, perltest won't work unmodified for the UTF-8 tests. You need to -uncomment the "use utf8" lines that it contains. It is best to do this on a -copy of the script, because for non-UTF-8 tests, these lines should remain -commented out. - -The testinput2 and testinput4 files are not suitable for feeding to perltest, -since they do make use of the special upper case modifiers and escapes that -pcretest uses to test some features of PCRE. The first of these files also -contains malformed regular expressions, in order to check that PCRE diagnoses -them correctly. Similarly, testinput6 tests UTF-8 features that do not relate -to Perl. - -Philip Hazel <ph10@cam.ac.uk> -August 2002 diff --git a/external-libs/pcre/install-sh b/external-libs/pcre/install-sh deleted file mode 100644 index e9de2384..00000000 --- a/external-libs/pcre/install-sh +++ /dev/null @@ -1,251 +0,0 @@ -#!/bin/sh -# -# install - install a program, script, or datafile -# This comes from X11R5 (mit/util/scripts/install.sh). -# -# Copyright 1991 by the Massachusetts Institute of Technology -# -# Permission to use, copy, modify, distribute, and sell this software and its -# documentation for any purpose is hereby granted without fee, provided that -# the above copyright notice appear in all copies and that both that -# copyright notice and this permission notice appear in supporting -# documentation, and that the name of M.I.T. not be used in advertising or -# publicity pertaining to distribution of the software without specific, -# written prior permission. M.I.T. makes no representations about the -# suitability of this software for any purpose. It is provided "as is" -# without express or implied warranty. -# -# Calling this script install-sh is preferred over install.sh, to prevent -# `make' implicit rules from creating a file called install from it -# when there is no Makefile. -# -# This script is compatible with the BSD install script, but was written -# from scratch. It can only install one file at a time, a restriction -# shared with many OS's install programs. - - -# set DOITPROG to echo to test this script - -# Don't use :- since 4.3BSD and earlier shells don't like it. -doit="${DOITPROG-}" - - -# put in absolute paths if you don't have them in your path; or use env. vars. - -mvprog="${MVPROG-mv}" -cpprog="${CPPROG-cp}" -chmodprog="${CHMODPROG-chmod}" -chownprog="${CHOWNPROG-chown}" -chgrpprog="${CHGRPPROG-chgrp}" -stripprog="${STRIPPROG-strip}" -rmprog="${RMPROG-rm}" -mkdirprog="${MKDIRPROG-mkdir}" - -transformbasename="" -transform_arg="" -instcmd="$mvprog" -chmodcmd="$chmodprog 0755" -chowncmd="" -chgrpcmd="" -stripcmd="" -rmcmd="$rmprog -f" -mvcmd="$mvprog" -src="" -dst="" -dir_arg="" - -while [ x"$1" != x ]; do - case $1 in - -c) instcmd="$cpprog" - shift - continue;; - - -d) dir_arg=true - shift - continue;; - - -m) chmodcmd="$chmodprog $2" - shift - shift - continue;; - - -o) chowncmd="$chownprog $2" - shift - shift - continue;; - - -g) chgrpcmd="$chgrpprog $2" - shift - shift - continue;; - - -s) stripcmd="$stripprog" - shift - continue;; - - -t=*) transformarg=`echo $1 | sed 's/-t=//'` - shift - continue;; - - -b=*) transformbasename=`echo $1 | sed 's/-b=//'` - shift - continue;; - - *) if [ x"$src" = x ] - then - src=$1 - else - # this colon is to work around a 386BSD /bin/sh bug - : - dst=$1 - fi - shift - continue;; - esac -done - -if [ x"$src" = x ] -then - echo "install: no input file specified" - exit 1 -else - true -fi - -if [ x"$dir_arg" != x ]; then - dst=$src - src="" - - if [ -d $dst ]; then - instcmd=: - chmodcmd="" - else - instcmd=mkdir - fi -else - -# Waiting for this to be detected by the "$instcmd $src $dsttmp" command -# might cause directories to be created, which would be especially bad -# if $src (and thus $dsttmp) contains '*'. - - if [ -f $src -o -d $src ] - then - true - else - echo "install: $src does not exist" - exit 1 - fi - - if [ x"$dst" = x ] - then - echo "install: no destination specified" - exit 1 - else - true - fi - -# If destination is a directory, append the input filename; if your system -# does not like double slashes in filenames, you may need to add some logic - - if [ -d $dst ] - then - dst="$dst"/`basename $src` - else - true - fi -fi - -## this sed command emulates the dirname command -dstdir=`echo $dst | sed -e 's,[^/]*$,,;s,/$,,;s,^$,.,'` - -# Make sure that the destination directory exists. -# this part is taken from Noah Friedman's mkinstalldirs script - -# Skip lots of stat calls in the usual case. -if [ ! -d "$dstdir" ]; then -defaultIFS=' -' -IFS="${IFS-${defaultIFS}}" - -oIFS="${IFS}" -# Some sh's can't handle IFS=/ for some reason. -IFS='%' -set - `echo ${dstdir} | sed -e 's@/@%@g' -e 's@^%@/@'` -IFS="${oIFS}" - -pathcomp='' - -while [ $# -ne 0 ] ; do - pathcomp="${pathcomp}${1}" - shift - - if [ ! -d "${pathcomp}" ] ; - then - $mkdirprog "${pathcomp}" - else - true - fi - - pathcomp="${pathcomp}/" -done -fi - -if [ x"$dir_arg" != x ] -then - $doit $instcmd $dst && - - if [ x"$chowncmd" != x ]; then $doit $chowncmd $dst; else true ; fi && - if [ x"$chgrpcmd" != x ]; then $doit $chgrpcmd $dst; else true ; fi && - if [ x"$stripcmd" != x ]; then $doit $stripcmd $dst; else true ; fi && - if [ x"$chmodcmd" != x ]; then $doit $chmodcmd $dst; else true ; fi -else - -# If we're going to rename the final executable, determine the name now. - - if [ x"$transformarg" = x ] - then - dstfile=`basename $dst` - else - dstfile=`basename $dst $transformbasename | - sed $transformarg`$transformbasename - fi - -# don't allow the sed command to completely eliminate the filename - - if [ x"$dstfile" = x ] - then - dstfile=`basename $dst` - else - true - fi - -# Make a temp file name in the proper directory. - - dsttmp=$dstdir/#inst.$$# - -# Move or copy the file name to the temp name - - $doit $instcmd $src $dsttmp && - - trap "rm -f ${dsttmp}" 0 && - -# and set any options; do chmod last to preserve setuid bits - -# If any of these fail, we abort the whole thing. If we want to -# ignore errors from any of these, just make sure not to ignore -# errors from the above "$doit $instcmd $src $dsttmp" command. - - if [ x"$chowncmd" != x ]; then $doit $chowncmd $dsttmp; else true;fi && - if [ x"$chgrpcmd" != x ]; then $doit $chgrpcmd $dsttmp; else true;fi && - if [ x"$stripcmd" != x ]; then $doit $stripcmd $dsttmp; else true;fi && - if [ x"$chmodcmd" != x ]; then $doit $chmodcmd $dsttmp; else true;fi && - -# Now rename the file to the real destination. - - $doit $rmcmd -f $dstdir/$dstfile && - $doit $mvcmd $dsttmp $dstdir/$dstfile - -fi && - - -exit 0 diff --git a/external-libs/pcre/libpcre.def b/external-libs/pcre/libpcre.def deleted file mode 100644 index 2b35d10b..00000000 --- a/external-libs/pcre/libpcre.def +++ /dev/null @@ -1,19 +0,0 @@ -LIBRARY libpcre -EXPORTS -pcre_malloc -pcre_free -pcre_config -pcre_callout -pcre_compile -pcre_copy_substring -pcre_exec -pcre_get_substring -pcre_get_stringnumber -pcre_get_substring_list -pcre_free_substring -pcre_free_substring_list -pcre_info -pcre_fullinfo -pcre_maketables -pcre_study -pcre_version diff --git a/external-libs/pcre/libpcreposix.def b/external-libs/pcre/libpcreposix.def deleted file mode 100644 index 57234400..00000000 --- a/external-libs/pcre/libpcreposix.def +++ /dev/null @@ -1,24 +0,0 @@ -LIBRARY libpcreposix -EXPORTS -pcre_malloc -pcre_free -pcre_config -pcre_callout -pcre_compile -pcre_copy_substring -pcre_exec -pcre_get_substring -pcre_get_stringnumber -pcre_get_substring_list -pcre_free_substring -pcre_free_substring_list -pcre_info -pcre_fullinfo -pcre_maketables -pcre_study -pcre_version - -regcomp -regexec -regerror -regfree diff --git a/external-libs/pcre/ltmain.sh b/external-libs/pcre/ltmain.sh deleted file mode 100644 index de848c62..00000000 --- a/external-libs/pcre/ltmain.sh +++ /dev/null @@ -1,5069 +0,0 @@ -# ltmain.sh - Provide generalized library-building support services. -# NOTE: Changing this file will not affect anything until you rerun configure. -# -# Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001 -# Free Software Foundation, Inc. -# Originally by Gordon Matzigkeit <gord@gnu.ai.mit.edu>, 1996 -# -# This program is free software; you can redistribute it and/or modify -# it under the terms of the GNU General Public License as published by -# the Free Software Foundation; either version 2 of the License, or -# (at your option) any later version. -# -# This program is distributed in the hope that it will be useful, but -# WITHOUT ANY WARRANTY; without even the implied warranty of -# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU -# General Public License for more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, write to the Free Software -# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. -# -# As a special exception to the GNU General Public License, if you -# distribute this file as part of a program that contains a -# configuration script generated by Autoconf, you may include it under -# the same distribution terms that you use for the rest of that program. - -# Check that we have a working $echo. -if test "X$1" = X--no-reexec; then - # Discard the --no-reexec flag, and continue. - shift -elif test "X$1" = X--fallback-echo; then - # Avoid inline document here, it may be left over - : -elif test "X`($echo '\t') 2>/dev/null`" = 'X\t'; then - # Yippee, $echo works! - : -else - # Restart under the correct shell, and then maybe $echo will work. - exec $SHELL "$0" --no-reexec ${1+"$@"} -fi - -if test "X$1" = X--fallback-echo; then - # used as fallback echo - shift - cat <<EOF -$* -EOF - exit 0 -fi - -# Modification by PH (18-Feb-2003) to ensure that ${SED} is always set -# (it is not set on my system). - -case "X${SED}" in - X) SED=sed ;; -esac - -# The name of this program. -progname=`$echo "$0" | ${SED} 's%^.*/%%'` -modename="$progname" - -# Constants. -PROGRAM=ltmain.sh -PACKAGE=libtool -VERSION=1.4.3 -TIMESTAMP=" (1.922.2.110 2002/10/23 01:39:54)" - -default_mode= -help="Try \`$progname --help' for more information." -magic="%%%MAGIC variable%%%" -mkdir="mkdir" -mv="mv -f" -rm="rm -f" - -# Sed substitution that helps us do robust quoting. It backslashifies -# metacharacters that are still active within double-quoted strings. -Xsed="${SED}"' -e 1s/^X//' -sed_quote_subst='s/\([\\`\\"$\\\\]\)/\\\1/g' -# test EBCDIC or ASCII -case `echo A|od -x` in - *[Cc]1*) # EBCDIC based system - SP2NL="tr '\100' '\n'" - NL2SP="tr '\r\n' '\100\100'" - ;; - *) # Assume ASCII based system - SP2NL="tr '\040' '\012'" - NL2SP="tr '\015\012' '\040\040'" - ;; -esac - -# NLS nuisances. -# Only set LANG and LC_ALL to C if already set. -# These must not be set unconditionally because not all systems understand -# e.g. LANG=C (notably SCO). -# We save the old values to restore during execute mode. -if test "${LC_ALL+set}" = set; then - save_LC_ALL="$LC_ALL"; LC_ALL=C; export LC_ALL -fi -if test "${LANG+set}" = set; then - save_LANG="$LANG"; LANG=C; export LANG -fi - -# Make sure IFS has a sensible default -: ${IFS=" "} - -if test "$build_libtool_libs" != yes && test "$build_old_libs" != yes; then - echo "$modename: not configured to build any kind of library" 1>&2 - echo "Fatal configuration error. See the $PACKAGE docs for more information." 1>&2 - exit 1 -fi - -# Global variables. -mode=$default_mode -nonopt= -prev= -prevopt= -run= -show="$echo" -show_help= -execute_dlfiles= -lo2o="s/\\.lo\$/.${objext}/" -o2lo="s/\\.${objext}\$/.lo/" - -# Parse our command line options once, thoroughly. -while test $# -gt 0 -do - arg="$1" - shift - - case $arg in - -*=*) optarg=`$echo "X$arg" | $Xsed -e 's/[-_a-zA-Z0-9]*=//'` ;; - *) optarg= ;; - esac - - # If the previous option needs an argument, assign it. - if test -n "$prev"; then - case $prev in - execute_dlfiles) - execute_dlfiles="$execute_dlfiles $arg" - ;; - *) - eval "$prev=\$arg" - ;; - esac - - prev= - prevopt= - continue - fi - - # Have we seen a non-optional argument yet? - case $arg in - --help) - show_help=yes - ;; - - --version) - echo "$PROGRAM (GNU $PACKAGE) $VERSION$TIMESTAMP" - exit 0 - ;; - - --config) - ${SED} -e '1,/^# ### BEGIN LIBTOOL CONFIG/d' -e '/^# ### END LIBTOOL CONFIG/,$d' $0 - exit 0 - ;; - - --debug) - echo "$progname: enabling shell trace mode" - set -x - ;; - - --dry-run | -n) - run=: - ;; - - --features) - echo "host: $host" - if test "$build_libtool_libs" = yes; then - echo "enable shared libraries" - else - echo "disable shared libraries" - fi - if test "$build_old_libs" = yes; then - echo "enable static libraries" - else - echo "disable static libraries" - fi - exit 0 - ;; - - --finish) mode="finish" ;; - - --mode) prevopt="--mode" prev=mode ;; - --mode=*) mode="$optarg" ;; - - --preserve-dup-deps) duplicate_deps="yes" ;; - - --quiet | --silent) - show=: - ;; - - -dlopen) - prevopt="-dlopen" - prev=execute_dlfiles - ;; - - -*) - $echo "$modename: unrecognized option \`$arg'" 1>&2 - $echo "$help" 1>&2 - exit 1 - ;; - - *) - nonopt="$arg" - break - ;; - esac -done - -if test -n "$prevopt"; then - $echo "$modename: option \`$prevopt' requires an argument" 1>&2 - $echo "$help" 1>&2 - exit 1 -fi - -# If this variable is set in any of the actions, the command in it -# will be execed at the end. This prevents here-documents from being -# left over by shells. -exec_cmd= - -if test -z "$show_help"; then - - # Infer the operation mode. - if test -z "$mode"; then - case $nonopt in - *cc | *++ | gcc* | *-gcc* | xlc*) - mode=link - for arg - do - case $arg in - -c) - mode=compile - break - ;; - esac - done - ;; - *db | *dbx | *strace | *truss) - mode=execute - ;; - *install*|cp|mv) - mode=install - ;; - *rm) - mode=uninstall - ;; - *) - # If we have no mode, but dlfiles were specified, then do execute mode. - test -n "$execute_dlfiles" && mode=execute - - # Just use the default operation mode. - if test -z "$mode"; then - if test -n "$nonopt"; then - $echo "$modename: warning: cannot infer operation mode from \`$nonopt'" 1>&2 - else - $echo "$modename: warning: cannot infer operation mode without MODE-ARGS" 1>&2 - fi - fi - ;; - esac - fi - - # Only execute mode is allowed to have -dlopen flags. - if test -n "$execute_dlfiles" && test "$mode" != execute; then - $echo "$modename: unrecognized option \`-dlopen'" 1>&2 - $echo "$help" 1>&2 - exit 1 - fi - - # Change the help message to a mode-specific one. - generic_help="$help" - help="Try \`$modename --help --mode=$mode' for more information." - - # These modes are in order of execution frequency so that they run quickly. - case $mode in - # libtool compile mode - compile) - modename="$modename: compile" - # Get the compilation command and the source file. - base_compile= - prev= - lastarg= - srcfile="$nonopt" - suppress_output= - - user_target=no - for arg - do - case $prev in - "") ;; - xcompiler) - # Aesthetically quote the previous argument. - prev= - lastarg=`$echo "X$arg" | $Xsed -e "$sed_quote_subst"` - - case $arg in - # Double-quote args containing other shell metacharacters. - # Many Bourne shells cannot handle close brackets correctly - # in scan sets, so we specify it separately. - *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") - arg="\"$arg\"" - ;; - esac - - # Add the previous argument to base_compile. - if test -z "$base_compile"; then - base_compile="$lastarg" - else - base_compile="$base_compile $lastarg" - fi - continue - ;; - esac - - # Accept any command-line options. - case $arg in - -o) - if test "$user_target" != "no"; then - $echo "$modename: you cannot specify \`-o' more than once" 1>&2 - exit 1 - fi - user_target=next - ;; - - -static) - build_old_libs=yes - continue - ;; - - -prefer-pic) - pic_mode=yes - continue - ;; - - -prefer-non-pic) - pic_mode=no - continue - ;; - - -Xcompiler) - prev=xcompiler - continue - ;; - - -Wc,*) - args=`$echo "X$arg" | $Xsed -e "s/^-Wc,//"` - lastarg= - save_ifs="$IFS"; IFS=',' - for arg in $args; do - IFS="$save_ifs" - - # Double-quote args containing other shell metacharacters. - # Many Bourne shells cannot handle close brackets correctly - # in scan sets, so we specify it separately. - case $arg in - *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") - arg="\"$arg\"" - ;; - esac - lastarg="$lastarg $arg" - done - IFS="$save_ifs" - lastarg=`$echo "X$lastarg" | $Xsed -e "s/^ //"` - - # Add the arguments to base_compile. - if test -z "$base_compile"; then - base_compile="$lastarg" - else - base_compile="$base_compile $lastarg" - fi - continue - ;; - esac - - case $user_target in - next) - # The next one is the -o target name - user_target=yes - continue - ;; - yes) - # We got the output file - user_target=set - libobj="$arg" - continue - ;; - esac - - # Accept the current argument as the source file. - lastarg="$srcfile" - srcfile="$arg" - - # Aesthetically quote the previous argument. - - # Backslashify any backslashes, double quotes, and dollar signs. - # These are the only characters that are still specially - # interpreted inside of double-quoted scrings. - lastarg=`$echo "X$lastarg" | $Xsed -e "$sed_quote_subst"` - - # Double-quote args containing other shell metacharacters. - # Many Bourne shells cannot handle close brackets correctly - # in scan sets, so we specify it separately. - case $lastarg in - *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") - lastarg="\"$lastarg\"" - ;; - esac - - # Add the previous argument to base_compile. - if test -z "$base_compile"; then - base_compile="$lastarg" - else - base_compile="$base_compile $lastarg" - fi - done - - case $user_target in - set) - ;; - no) - # Get the name of the library object. - libobj=`$echo "X$srcfile" | $Xsed -e 's%^.*/%%'` - ;; - *) - $echo "$modename: you must specify a target with \`-o'" 1>&2 - exit 1 - ;; - esac - - # Recognize several different file suffixes. - # If the user specifies -o file.o, it is replaced with file.lo - xform='[cCFSfmso]' - case $libobj in - *.ada) xform=ada ;; - *.adb) xform=adb ;; - *.ads) xform=ads ;; - *.asm) xform=asm ;; - *.c++) xform=c++ ;; - *.cc) xform=cc ;; - *.cpp) xform=cpp ;; - *.cxx) xform=cxx ;; - *.f90) xform=f90 ;; - *.for) xform=for ;; - esac - - libobj=`$echo "X$libobj" | $Xsed -e "s/\.$xform$/.lo/"` - - case $libobj in - *.lo) obj=`$echo "X$libobj" | $Xsed -e "$lo2o"` ;; - *) - $echo "$modename: cannot determine name of library object from \`$libobj'" 1>&2 - exit 1 - ;; - esac - - if test -z "$base_compile"; then - $echo "$modename: you must specify a compilation command" 1>&2 - $echo "$help" 1>&2 - exit 1 - fi - - # Delete any leftover library objects. - if test "$build_old_libs" = yes; then - removelist="$obj $libobj" - else - removelist="$libobj" - fi - - $run $rm $removelist - trap "$run $rm $removelist; exit 1" 1 2 15 - - # On Cygwin there's no "real" PIC flag so we must build both object types - case $host_os in - cygwin* | mingw* | pw32* | os2*) - pic_mode=default - ;; - esac - if test "$pic_mode" = no && test "$deplibs_check_method" != pass_all; then - # non-PIC code in shared libraries is not supported - pic_mode=default - fi - - # Calculate the filename of the output object if compiler does - # not support -o with -c - if test "$compiler_c_o" = no; then - output_obj=`$echo "X$srcfile" | $Xsed -e 's%^.*/%%' -e 's%\.[^.]*$%%'`.${objext} - lockfile="$output_obj.lock" - removelist="$removelist $output_obj $lockfile" - trap "$run $rm $removelist; exit 1" 1 2 15 - else - need_locks=no - lockfile= - fi - - # Lock this critical section if it is needed - # We use this script file to make the link, it avoids creating a new file - if test "$need_locks" = yes; then - until $run ln "$0" "$lockfile" 2>/dev/null; do - $show "Waiting for $lockfile to be removed" - sleep 2 - done - elif test "$need_locks" = warn; then - if test -f "$lockfile"; then - echo "\ -*** ERROR, $lockfile exists and contains: -`cat $lockfile 2>/dev/null` - -This indicates that another process is trying to use the same -temporary object file, and libtool could not work around it because -your compiler does not support \`-c' and \`-o' together. If you -repeat this compilation, it may succeed, by chance, but you had better -avoid parallel builds (make -j) in this platform, or get a better -compiler." - - $run $rm $removelist - exit 1 - fi - echo $srcfile > "$lockfile" - fi - - if test -n "$fix_srcfile_path"; then - eval srcfile=\"$fix_srcfile_path\" - fi - - # Only build a PIC object if we are building libtool libraries. - if test "$build_libtool_libs" = yes; then - # Without this assignment, base_compile gets emptied. - fbsd_hideous_sh_bug=$base_compile - - if test "$pic_mode" != no; then - # All platforms use -DPIC, to notify preprocessed assembler code. - command="$base_compile $srcfile $pic_flag -DPIC" - else - # Don't build PIC code - command="$base_compile $srcfile" - fi - if test "$build_old_libs" = yes; then - lo_libobj="$libobj" - dir=`$echo "X$libobj" | $Xsed -e 's%/[^/]*$%%'` - if test "X$dir" = "X$libobj"; then - dir="$objdir" - else - dir="$dir/$objdir" - fi - libobj="$dir/"`$echo "X$libobj" | $Xsed -e 's%^.*/%%'` - - if test -d "$dir"; then - $show "$rm $libobj" - $run $rm $libobj - else - $show "$mkdir $dir" - $run $mkdir $dir - status=$? - if test $status -ne 0 && test ! -d $dir; then - exit $status - fi - fi - fi - if test "$compiler_o_lo" = yes; then - output_obj="$libobj" - command="$command -o $output_obj" - elif test "$compiler_c_o" = yes; then - output_obj="$obj" - command="$command -o $output_obj" - fi - - $run $rm "$output_obj" - $show "$command" - if $run eval "$command"; then : - else - test -n "$output_obj" && $run $rm $removelist - exit 1 - fi - - if test "$need_locks" = warn && - test x"`cat $lockfile 2>/dev/null`" != x"$srcfile"; then - echo "\ -*** ERROR, $lockfile contains: -`cat $lockfile 2>/dev/null` - -but it should contain: -$srcfile - -This indicates that another process is trying to use the same -temporary object file, and libtool could not work around it because -your compiler does not support \`-c' and \`-o' together. If you -repeat this compilation, it may succeed, by chance, but you had better -avoid parallel builds (make -j) in this platform, or get a better -compiler." - - $run $rm $removelist - exit 1 - fi - - # Just move the object if needed, then go on to compile the next one - if test x"$output_obj" != x"$libobj"; then - $show "$mv $output_obj $libobj" - if $run $mv $output_obj $libobj; then : - else - error=$? - $run $rm $removelist - exit $error - fi - fi - - # If we have no pic_flag, then copy the object into place and finish. - if (test -z "$pic_flag" || test "$pic_mode" != default) && - test "$build_old_libs" = yes; then - # Rename the .lo from within objdir to obj - if test -f $obj; then - $show $rm $obj - $run $rm $obj - fi - - $show "$mv $libobj $obj" - if $run $mv $libobj $obj; then : - else - error=$? - $run $rm $removelist - exit $error - fi - - xdir=`$echo "X$obj" | $Xsed -e 's%/[^/]*$%%'` - if test "X$xdir" = "X$obj"; then - xdir="." - else - xdir="$xdir" - fi - baseobj=`$echo "X$obj" | $Xsed -e "s%.*/%%"` - libobj=`$echo "X$baseobj" | $Xsed -e "$o2lo"` - # Now arrange that obj and lo_libobj become the same file - $show "(cd $xdir && $LN_S $baseobj $libobj)" - if $run eval '(cd $xdir && $LN_S $baseobj $libobj)'; then - # Unlock the critical section if it was locked - if test "$need_locks" != no; then - $run $rm "$lockfile" - fi - exit 0 - else - error=$? - $run $rm $removelist - exit $error - fi - fi - - # Allow error messages only from the first compilation. - suppress_output=' >/dev/null 2>&1' - fi - - # Only build a position-dependent object if we build old libraries. - if test "$build_old_libs" = yes; then - if test "$pic_mode" != yes; then - # Don't build PIC code - command="$base_compile $srcfile" - else - # All platforms use -DPIC, to notify preprocessed assembler code. - command="$base_compile $srcfile $pic_flag -DPIC" - fi - if test "$compiler_c_o" = yes; then - command="$command -o $obj" - output_obj="$obj" - fi - - # Suppress compiler output if we already did a PIC compilation. - command="$command$suppress_output" - $run $rm "$output_obj" - $show "$command" - if $run eval "$command"; then : - else - $run $rm $removelist - exit 1 - fi - - if test "$need_locks" = warn && - test x"`cat $lockfile 2>/dev/null`" != x"$srcfile"; then - echo "\ -*** ERROR, $lockfile contains: -`cat $lockfile 2>/dev/null` - -but it should contain: -$srcfile - -This indicates that another process is trying to use the same -temporary object file, and libtool could not work around it because -your compiler does not support \`-c' and \`-o' together. If you -repeat this compilation, it may succeed, by chance, but you had better -avoid parallel builds (make -j) in this platform, or get a better -compiler." - - $run $rm $removelist - exit 1 - fi - - # Just move the object if needed - if test x"$output_obj" != x"$obj"; then - $show "$mv $output_obj $obj" - if $run $mv $output_obj $obj; then : - else - error=$? - $run $rm $removelist - exit $error - fi - fi - - # Create an invalid libtool object if no PIC, so that we do not - # accidentally link it into a program. - if test "$build_libtool_libs" != yes; then - $show "echo timestamp > $libobj" - $run eval "echo timestamp > \$libobj" || exit $? - else - # Move the .lo from within objdir - $show "$mv $libobj $lo_libobj" - if $run $mv $libobj $lo_libobj; then : - else - error=$? - $run $rm $removelist - exit $error - fi - fi - fi - - # Unlock the critical section if it was locked - if test "$need_locks" != no; then - $run $rm "$lockfile" - fi - - exit 0 - ;; - - # libtool link mode - link | relink) - modename="$modename: link" - case $host in - *-*-cygwin* | *-*-mingw* | *-*-pw32* | *-*-os2*) - # It is impossible to link a dll without this setting, and - # we shouldn't force the makefile maintainer to figure out - # which system we are compiling for in order to pass an extra - # flag for every libtool invokation. - # allow_undefined=no - - # FIXME: Unfortunately, there are problems with the above when trying - # to make a dll which has undefined symbols, in which case not - # even a static library is built. For now, we need to specify - # -no-undefined on the libtool link line when we can be certain - # that all symbols are satisfied, otherwise we get a static library. - allow_undefined=yes - ;; - *) - allow_undefined=yes - ;; - esac - libtool_args="$nonopt" - compile_command="$nonopt" - finalize_command="$nonopt" - - compile_rpath= - finalize_rpath= - compile_shlibpath= - finalize_shlibpath= - convenience= - old_convenience= - deplibs= - old_deplibs= - compiler_flags= - linker_flags= - dllsearchpath= - lib_search_path=`pwd` - - avoid_version=no - dlfiles= - dlprefiles= - dlself=no - export_dynamic=no - export_symbols= - export_symbols_regex= - generated= - libobjs= - ltlibs= - module=no - no_install=no - objs= - prefer_static_libs=no - preload=no - prev= - prevarg= - release= - rpath= - xrpath= - perm_rpath= - temp_rpath= - thread_safe=no - vinfo= - - # We need to know -static, to get the right output filenames. - for arg - do - case $arg in - -all-static | -static) - if test "X$arg" = "X-all-static"; then - if test "$build_libtool_libs" = yes && test -z "$link_static_flag"; then - $echo "$modename: warning: complete static linking is impossible in this configuration" 1>&2 - fi - if test -n "$link_static_flag"; then - dlopen_self=$dlopen_self_static - fi - else - if test -z "$pic_flag" && test -n "$link_static_flag"; then - dlopen_self=$dlopen_self_static - fi - fi - build_libtool_libs=no - build_old_libs=yes - prefer_static_libs=yes - break - ;; - esac - done - - # See if our shared archives depend on static archives. - test -n "$old_archive_from_new_cmds" && build_old_libs=yes - - # Go through the arguments, transforming them on the way. - while test $# -gt 0; do - arg="$1" - shift - case $arg in - *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") - qarg=\"`$echo "X$arg" | $Xsed -e "$sed_quote_subst"`\" ### testsuite: skip nested quoting test - ;; - *) qarg=$arg ;; - esac - libtool_args="$libtool_args $qarg" - - # If the previous option needs an argument, assign it. - if test -n "$prev"; then - case $prev in - output) - compile_command="$compile_command @OUTPUT@" - finalize_command="$finalize_command @OUTPUT@" - ;; - esac - - case $prev in - dlfiles|dlprefiles) - if test "$preload" = no; then - # Add the symbol object into the linking commands. - compile_command="$compile_command @SYMFILE@" - finalize_command="$finalize_command @SYMFILE@" - preload=yes - fi - case $arg in - *.la | *.lo) ;; # We handle these cases below. - force) - if test "$dlself" = no; then - dlself=needless - export_dynamic=yes - fi - prev= - continue - ;; - self) - if test "$prev" = dlprefiles; then - dlself=yes - elif test "$prev" = dlfiles && test "$dlopen_self" != yes; then - dlself=yes - else - dlself=needless - export_dynamic=yes - fi - prev= - continue - ;; - *) - if test "$prev" = dlfiles; then - dlfiles="$dlfiles $arg" - else - dlprefiles="$dlprefiles $arg" - fi - prev= - continue - ;; - esac - ;; - expsyms) - export_symbols="$arg" - if test ! -f "$arg"; then - $echo "$modename: symbol file \`$arg' does not exist" - exit 1 - fi - prev= - continue - ;; - expsyms_regex) - export_symbols_regex="$arg" - prev= - continue - ;; - release) - release="-$arg" - prev= - continue - ;; - rpath | xrpath) - # We need an absolute path. - case $arg in - [\\/]* | [A-Za-z]:[\\/]*) ;; - *) - $echo "$modename: only absolute run-paths are allowed" 1>&2 - exit 1 - ;; - esac - if test "$prev" = rpath; then - case "$rpath " in - *" $arg "*) ;; - *) rpath="$rpath $arg" ;; - esac - else - case "$xrpath " in - *" $arg "*) ;; - *) xrpath="$xrpath $arg" ;; - esac - fi - prev= - continue - ;; - xcompiler) - compiler_flags="$compiler_flags $qarg" - prev= - compile_command="$compile_command $qarg" - finalize_command="$finalize_command $qarg" - continue - ;; - xlinker) - linker_flags="$linker_flags $qarg" - compiler_flags="$compiler_flags $wl$qarg" - prev= - compile_command="$compile_command $wl$qarg" - finalize_command="$finalize_command $wl$qarg" - continue - ;; - *) - eval "$prev=\"\$arg\"" - prev= - continue - ;; - esac - fi # test -n $prev - - prevarg="$arg" - - case $arg in - -all-static) - if test -n "$link_static_flag"; then - compile_command="$compile_command $link_static_flag" - finalize_command="$finalize_command $link_static_flag" - fi - continue - ;; - - -allow-undefined) - # FIXME: remove this flag sometime in the future. - $echo "$modename: \`-allow-undefined' is deprecated because it is the default" 1>&2 - continue - ;; - - -avoid-version) - avoid_version=yes - continue - ;; - - -dlopen) - prev=dlfiles - continue - ;; - - -dlpreopen) - prev=dlprefiles - continue - ;; - - -export-dynamic) - export_dynamic=yes - continue - ;; - - -export-symbols | -export-symbols-regex) - if test -n "$export_symbols" || test -n "$export_symbols_regex"; then - $echo "$modename: more than one -exported-symbols argument is not allowed" - exit 1 - fi - if test "X$arg" = "X-export-symbols"; then - prev=expsyms - else - prev=expsyms_regex - fi - continue - ;; - - # The native IRIX linker understands -LANG:*, -LIST:* and -LNO:* - # so, if we see these flags be careful not to treat them like -L - -L[A-Z][A-Z]*:*) - case $with_gcc/$host in - no/*-*-irix* | no/*-*-nonstopux*) - compile_command="$compile_command $arg" - finalize_command="$finalize_command $arg" - ;; - esac - continue - ;; - - -L*) - dir=`$echo "X$arg" | $Xsed -e 's/^-L//'` - # We need an absolute path. - case $dir in - [\\/]* | [A-Za-z]:[\\/]*) ;; - *) - absdir=`cd "$dir" && pwd` - if test -z "$absdir"; then - $echo "$modename: cannot determine absolute directory name of \`$dir'" 1>&2 - exit 1 - fi - dir="$absdir" - ;; - esac - case "$deplibs " in - *" -L$dir "*) ;; - *) - deplibs="$deplibs -L$dir" - lib_search_path="$lib_search_path $dir" - ;; - esac - case $host in - *-*-cygwin* | *-*-mingw* | *-*-pw32* | *-*-os2*) - case :$dllsearchpath: in - *":$dir:"*) ;; - *) dllsearchpath="$dllsearchpath:$dir";; - esac - ;; - esac - continue - ;; - - -l*) - if test "X$arg" = "X-lc" || test "X$arg" = "X-lm"; then - case $host in - *-*-cygwin* | *-*-pw32* | *-*-beos*) - # These systems don't actually have a C or math library (as such) - continue - ;; - *-*-mingw* | *-*-os2*) - # These systems don't actually have a C library (as such) - test "X$arg" = "X-lc" && continue - ;; - *-*-openbsd* | *-*-freebsd*) - # Do not include libc due to us having libc/libc_r. - test "X$arg" = "X-lc" && continue - ;; - esac - elif test "X$arg" = "X-lc_r"; then - case $host in - *-*-openbsd* | *-*-freebsd*) - # Do not include libc_r directly, use -pthread flag. - continue - ;; - esac - fi - deplibs="$deplibs $arg" - continue - ;; - - -module) - module=yes - continue - ;; - - -no-fast-install) - fast_install=no - continue - ;; - - -no-install) - case $host in - *-*-cygwin* | *-*-mingw* | *-*-pw32* | *-*-os2*) - # The PATH hackery in wrapper scripts is required on Windows - # in order for the loader to find any dlls it needs. - $echo "$modename: warning: \`-no-install' is ignored for $host" 1>&2 - $echo "$modename: warning: assuming \`-no-fast-install' instead" 1>&2 - fast_install=no - ;; - *) no_install=yes ;; - esac - continue - ;; - - -no-undefined) - allow_undefined=no - continue - ;; - - -o) prev=output ;; - - -release) - prev=release - continue - ;; - - -rpath) - prev=rpath - continue - ;; - - -R) - prev=xrpath - continue - ;; - - -R*) - dir=`$echo "X$arg" | $Xsed -e 's/^-R//'` - # We need an absolute path. - case $dir in - [\\/]* | [A-Za-z]:[\\/]*) ;; - *) - $echo "$modename: only absolute run-paths are allowed" 1>&2 - exit 1 - ;; - esac - case "$xrpath " in - *" $dir "*) ;; - *) xrpath="$xrpath $dir" ;; - esac - continue - ;; - - -static) - # The effects of -static are defined in a previous loop. - # We used to do the same as -all-static on platforms that - # didn't have a PIC flag, but the assumption that the effects - # would be equivalent was wrong. It would break on at least - # Digital Unix and AIX. - continue - ;; - - -thread-safe) - thread_safe=yes - continue - ;; - - -version-info) - prev=vinfo - continue - ;; - - -Wc,*) - args=`$echo "X$arg" | $Xsed -e "$sed_quote_subst" -e 's/^-Wc,//'` - arg= - save_ifs="$IFS"; IFS=',' - for flag in $args; do - IFS="$save_ifs" - case $flag in - *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") - flag="\"$flag\"" - ;; - esac - arg="$arg $wl$flag" - compiler_flags="$compiler_flags $flag" - done - IFS="$save_ifs" - arg=`$echo "X$arg" | $Xsed -e "s/^ //"` - ;; - - -Wl,*) - args=`$echo "X$arg" | $Xsed -e "$sed_quote_subst" -e 's/^-Wl,//'` - arg= - save_ifs="$IFS"; IFS=',' - for flag in $args; do - IFS="$save_ifs" - case $flag in - *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") - flag="\"$flag\"" - ;; - esac - arg="$arg $wl$flag" - compiler_flags="$compiler_flags $wl$flag" - linker_flags="$linker_flags $flag" - done - IFS="$save_ifs" - arg=`$echo "X$arg" | $Xsed -e "s/^ //"` - ;; - - -Xcompiler) - prev=xcompiler - continue - ;; - - -Xlinker) - prev=xlinker - continue - ;; - - # Some other compiler flag. - -* | +*) - # Unknown arguments in both finalize_command and compile_command need - # to be aesthetically quoted because they are evaled later. - arg=`$echo "X$arg" | $Xsed -e "$sed_quote_subst"` - case $arg in - *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") - arg="\"$arg\"" - ;; - esac - ;; - - *.lo | *.$objext) - # A library or standard object. - if test "$prev" = dlfiles; then - # This file was specified with -dlopen. - if test "$build_libtool_libs" = yes && test "$dlopen_support" = yes; then - dlfiles="$dlfiles $arg" - prev= - continue - else - # If libtool objects are unsupported, then we need to preload. - prev=dlprefiles - fi - fi - - if test "$prev" = dlprefiles; then - # Preload the old-style object. - dlprefiles="$dlprefiles "`$echo "X$arg" | $Xsed -e "$lo2o"` - prev= - else - case $arg in - *.lo) libobjs="$libobjs $arg" ;; - *) objs="$objs $arg" ;; - esac - fi - ;; - - *.$libext) - # An archive. - deplibs="$deplibs $arg" - old_deplibs="$old_deplibs $arg" - continue - ;; - - *.la) - # A libtool-controlled library. - - if test "$prev" = dlfiles; then - # This library was specified with -dlopen. - dlfiles="$dlfiles $arg" - prev= - elif test "$prev" = dlprefiles; then - # The library was specified with -dlpreopen. - dlprefiles="$dlprefiles $arg" - prev= - else - deplibs="$deplibs $arg" - fi - continue - ;; - - # Some other compiler argument. - *) - # Unknown arguments in both finalize_command and compile_command need - # to be aesthetically quoted because they are evaled later. - arg=`$echo "X$arg" | $Xsed -e "$sed_quote_subst"` - case $arg in - *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*|"") - arg="\"$arg\"" - ;; - esac - ;; - esac # arg - - # Now actually substitute the argument into the commands. - if test -n "$arg"; then - compile_command="$compile_command $arg" - finalize_command="$finalize_command $arg" - fi - done # argument parsing loop - - if test -n "$prev"; then - $echo "$modename: the \`$prevarg' option requires an argument" 1>&2 - $echo "$help" 1>&2 - exit 1 - fi - - if test "$export_dynamic" = yes && test -n "$export_dynamic_flag_spec"; then - eval arg=\"$export_dynamic_flag_spec\" - compile_command="$compile_command $arg" - finalize_command="$finalize_command $arg" - fi - - # calculate the name of the file, without its directory - outputname=`$echo "X$output" | $Xsed -e 's%^.*/%%'` - libobjs_save="$libobjs" - - if test -n "$shlibpath_var"; then - # get the directories listed in $shlibpath_var - eval shlib_search_path=\`\$echo \"X\${$shlibpath_var}\" \| \$Xsed -e \'s/:/ /g\'\` - else - shlib_search_path= - fi - eval sys_lib_search_path=\"$sys_lib_search_path_spec\" - eval sys_lib_dlsearch_path=\"$sys_lib_dlsearch_path_spec\" - - output_objdir=`$echo "X$output" | $Xsed -e 's%/[^/]*$%%'` - if test "X$output_objdir" = "X$output"; then - output_objdir="$objdir" - else - output_objdir="$output_objdir/$objdir" - fi - # Create the object directory. - if test ! -d $output_objdir; then - $show "$mkdir $output_objdir" - $run $mkdir $output_objdir - status=$? - if test $status -ne 0 && test ! -d $output_objdir; then - exit $status - fi - fi - - # Determine the type of output - case $output in - "") - $echo "$modename: you must specify an output file" 1>&2 - $echo "$help" 1>&2 - exit 1 - ;; - *.$libext) linkmode=oldlib ;; - *.lo | *.$objext) linkmode=obj ;; - *.la) linkmode=lib ;; - *) linkmode=prog ;; # Anything else should be a program. - esac - - specialdeplibs= - libs= - # Find all interdependent deplibs by searching for libraries - # that are linked more than once (e.g. -la -lb -la) - for deplib in $deplibs; do - if test "X$duplicate_deps" = "Xyes" ; then - case "$libs " in - *" $deplib "*) specialdeplibs="$specialdeplibs $deplib" ;; - esac - fi - libs="$libs $deplib" - done - deplibs= - newdependency_libs= - newlib_search_path= - need_relink=no # whether we're linking any uninstalled libtool libraries - notinst_deplibs= # not-installed libtool libraries - notinst_path= # paths that contain not-installed libtool libraries - case $linkmode in - lib) - passes="conv link" - for file in $dlfiles $dlprefiles; do - case $file in - *.la) ;; - *) - $echo "$modename: libraries can \`-dlopen' only libtool libraries: $file" 1>&2 - exit 1 - ;; - esac - done - ;; - prog) - compile_deplibs= - finalize_deplibs= - alldeplibs=no - newdlfiles= - newdlprefiles= - passes="conv scan dlopen dlpreopen link" - ;; - *) passes="conv" - ;; - esac - for pass in $passes; do - if test $linkmode = prog; then - # Determine which files to process - case $pass in - dlopen) - libs="$dlfiles" - save_deplibs="$deplibs" # Collect dlpreopened libraries - deplibs= - ;; - dlpreopen) libs="$dlprefiles" ;; - link) libs="$deplibs %DEPLIBS% $dependency_libs" ;; - esac - fi - for deplib in $libs; do - lib= - found=no - case $deplib in - -l*) - if test $linkmode = oldlib && test $linkmode = obj; then - $echo "$modename: warning: \`-l' is ignored for archives/objects: $deplib" 1>&2 - continue - fi - if test $pass = conv; then - deplibs="$deplib $deplibs" - continue - fi - name=`$echo "X$deplib" | $Xsed -e 's/^-l//'` - for searchdir in $newlib_search_path $lib_search_path $sys_lib_search_path $shlib_search_path; do - # Search the libtool library - lib="$searchdir/lib${name}.la" - if test -f "$lib"; then - found=yes - break - fi - done - if test "$found" != yes; then - # deplib doesn't seem to be a libtool library - if test "$linkmode,$pass" = "prog,link"; then - compile_deplibs="$deplib $compile_deplibs" - finalize_deplibs="$deplib $finalize_deplibs" - else - deplibs="$deplib $deplibs" - test $linkmode = lib && newdependency_libs="$deplib $newdependency_libs" - fi - continue - fi - ;; # -l - -L*) - case $linkmode in - lib) - deplibs="$deplib $deplibs" - test $pass = conv && continue - newdependency_libs="$deplib $newdependency_libs" - newlib_search_path="$newlib_search_path "`$echo "X$deplib" | $Xsed -e 's/^-L//'` - ;; - prog) - if test $pass = conv; then - deplibs="$deplib $deplibs" - continue - fi - if test $pass = scan; then - deplibs="$deplib $deplibs" - newlib_search_path="$newlib_search_path "`$echo "X$deplib" | $Xsed -e 's/^-L//'` - else - compile_deplibs="$deplib $compile_deplibs" - finalize_deplibs="$deplib $finalize_deplibs" - fi - ;; - *) - $echo "$modename: warning: \`-L' is ignored for archives/objects: $deplib" 1>&2 - ;; - esac # linkmode - continue - ;; # -L - -R*) - if test $pass = link; then - dir=`$echo "X$deplib" | $Xsed -e 's/^-R//'` - # Make sure the xrpath contains only unique directories. - case "$xrpath " in - *" $dir "*) ;; - *) xrpath="$xrpath $dir" ;; - esac - fi - deplibs="$deplib $deplibs" - continue - ;; - *.la) lib="$deplib" ;; - *.$libext) - if test $pass = conv; then - deplibs="$deplib $deplibs" - continue - fi - case $linkmode in - lib) - if test "$deplibs_check_method" != pass_all; then - echo - echo "*** Warning: Trying to link with static lib archive $deplib." - echo "*** I have the capability to make that library automatically link in when" - echo "*** you link to this library. But I can only do this if you have a" - echo "*** shared version of the library, which you do not appear to have" - echo "*** because the file extensions .$libext of this argument makes me believe" - echo "*** that it is just a static archive that I should not used here." - else - echo - echo "*** Warning: Linking the shared library $output against the" - echo "*** static library $deplib is not portable!" - deplibs="$deplib $deplibs" - fi - continue - ;; - prog) - if test $pass != link; then - deplibs="$deplib $deplibs" - else - compile_deplibs="$deplib $compile_deplibs" - finalize_deplibs="$deplib $finalize_deplibs" - fi - continue - ;; - esac # linkmode - ;; # *.$libext - *.lo | *.$objext) - if test $pass = dlpreopen || test "$dlopen_support" != yes || test "$build_libtool_libs" = no; then - # If there is no dlopen support or we're linking statically, - # we need to preload. - newdlprefiles="$newdlprefiles $deplib" - compile_deplibs="$deplib $compile_deplibs" - finalize_deplibs="$deplib $finalize_deplibs" - else - newdlfiles="$newdlfiles $deplib" - fi - continue - ;; - %DEPLIBS%) - alldeplibs=yes - continue - ;; - esac # case $deplib - if test $found = yes || test -f "$lib"; then : - else - $echo "$modename: cannot find the library \`$lib'" 1>&2 - exit 1 - fi - - # Check to see that this really is a libtool archive. - if (${SED} -e '2q' $lib | egrep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then : - else - $echo "$modename: \`$lib' is not a valid libtool archive" 1>&2 - exit 1 - fi - - ladir=`$echo "X$lib" | $Xsed -e 's%/[^/]*$%%'` - test "X$ladir" = "X$lib" && ladir="." - - dlname= - dlopen= - dlpreopen= - libdir= - library_names= - old_library= - # If the library was installed with an old release of libtool, - # it will not redefine variable installed. - installed=yes - - # Read the .la file - case $lib in - */* | *\\*) . $lib ;; - *) . ./$lib ;; - esac - - if test "$linkmode,$pass" = "lib,link" || - test "$linkmode,$pass" = "prog,scan" || - { test $linkmode = oldlib && test $linkmode = obj; }; then - # Add dl[pre]opened files of deplib - test -n "$dlopen" && dlfiles="$dlfiles $dlopen" - test -n "$dlpreopen" && dlprefiles="$dlprefiles $dlpreopen" - fi - - if test $pass = conv; then - # Only check for convenience libraries - deplibs="$lib $deplibs" - if test -z "$libdir"; then - if test -z "$old_library"; then - $echo "$modename: cannot find name of link library for \`$lib'" 1>&2 - exit 1 - fi - # It is a libtool convenience library, so add in its objects. - convenience="$convenience $ladir/$objdir/$old_library" - old_convenience="$old_convenience $ladir/$objdir/$old_library" - tmp_libs= - for deplib in $dependency_libs; do - deplibs="$deplib $deplibs" - if test "X$duplicate_deps" = "Xyes" ; then - case "$tmp_libs " in - *" $deplib "*) specialdeplibs="$specialdeplibs $deplib" ;; - esac - fi - tmp_libs="$tmp_libs $deplib" - done - elif test $linkmode != prog && test $linkmode != lib; then - $echo "$modename: \`$lib' is not a convenience library" 1>&2 - exit 1 - fi - continue - fi # $pass = conv - - # Get the name of the library we link against. - linklib= - for l in $old_library $library_names; do - linklib="$l" - done - if test -z "$linklib"; then - $echo "$modename: cannot find name of link library for \`$lib'" 1>&2 - exit 1 - fi - - # This library was specified with -dlopen. - if test $pass = dlopen; then - if test -z "$libdir"; then - $echo "$modename: cannot -dlopen a convenience library: \`$lib'" 1>&2 - exit 1 - fi - if test -z "$dlname" || test "$dlopen_support" != yes || test "$build_libtool_libs" = no; then - # If there is no dlname, no dlopen support or we're linking - # statically, we need to preload. - dlprefiles="$dlprefiles $lib" - else - newdlfiles="$newdlfiles $lib" - fi - continue - fi # $pass = dlopen - - # We need an absolute path. - case $ladir in - [\\/]* | [A-Za-z]:[\\/]*) abs_ladir="$ladir" ;; - *) - abs_ladir=`cd "$ladir" && pwd` - if test -z "$abs_ladir"; then - $echo "$modename: warning: cannot determine absolute directory name of \`$ladir'" 1>&2 - $echo "$modename: passing it literally to the linker, although it might fail" 1>&2 - abs_ladir="$ladir" - fi - ;; - esac - laname=`$echo "X$lib" | $Xsed -e 's%^.*/%%'` - - # Find the relevant object directory and library name. - if test "X$installed" = Xyes; then - if test ! -f "$libdir/$linklib" && test -f "$abs_ladir/$linklib"; then - $echo "$modename: warning: library \`$lib' was moved." 1>&2 - dir="$ladir" - absdir="$abs_ladir" - libdir="$abs_ladir" - else - dir="$libdir" - absdir="$libdir" - fi - else - dir="$ladir/$objdir" - absdir="$abs_ladir/$objdir" - # Remove this search path later - notinst_path="$notinst_path $abs_ladir" - fi # $installed = yes - name=`$echo "X$laname" | $Xsed -e 's/\.la$//' -e 's/^lib//'` - - # This library was specified with -dlpreopen. - if test $pass = dlpreopen; then - if test -z "$libdir"; then - $echo "$modename: cannot -dlpreopen a convenience library: \`$lib'" 1>&2 - exit 1 - fi - # Prefer using a static library (so that no silly _DYNAMIC symbols - # are required to link). - if test -n "$old_library"; then - newdlprefiles="$newdlprefiles $dir/$old_library" - # Otherwise, use the dlname, so that lt_dlopen finds it. - elif test -n "$dlname"; then - newdlprefiles="$newdlprefiles $dir/$dlname" - else - newdlprefiles="$newdlprefiles $dir/$linklib" - fi - fi # $pass = dlpreopen - - if test -z "$libdir"; then - # Link the convenience library - if test $linkmode = lib; then - deplibs="$dir/$old_library $deplibs" - elif test "$linkmode,$pass" = "prog,link"; then - compile_deplibs="$dir/$old_library $compile_deplibs" - finalize_deplibs="$dir/$old_library $finalize_deplibs" - else - deplibs="$lib $deplibs" - fi - continue - fi - - if test $linkmode = prog && test $pass != link; then - newlib_search_path="$newlib_search_path $ladir" - deplibs="$lib $deplibs" - - linkalldeplibs=no - if test "$link_all_deplibs" != no || test -z "$library_names" || - test "$build_libtool_libs" = no; then - linkalldeplibs=yes - fi - - tmp_libs= - for deplib in $dependency_libs; do - case $deplib in - -L*) newlib_search_path="$newlib_search_path "`$echo "X$deplib" | $Xsed -e 's/^-L//'`;; ### testsuite: skip nested quoting test - esac - # Need to link against all dependency_libs? - if test $linkalldeplibs = yes; then - deplibs="$deplib $deplibs" - else - # Need to hardcode shared library paths - # or/and link against static libraries - newdependency_libs="$deplib $newdependency_libs" - fi - if test "X$duplicate_deps" = "Xyes" ; then - case "$tmp_libs " in - *" $deplib "*) specialdeplibs="$specialdeplibs $deplib" ;; - esac - fi - tmp_libs="$tmp_libs $deplib" - done # for deplib - continue - fi # $linkmode = prog... - - link_static=no # Whether the deplib will be linked statically - if test -n "$library_names" && - { test "$prefer_static_libs" = no || test -z "$old_library"; }; then - # Link against this shared library - - if test "$linkmode,$pass" = "prog,link" || - { test $linkmode = lib && test $hardcode_into_libs = yes; }; then - # Hardcode the library path. - # Skip directories that are in the system default run-time - # search path. - case " $sys_lib_dlsearch_path " in - *" $absdir "*) ;; - *) - case "$compile_rpath " in - *" $absdir "*) ;; - *) compile_rpath="$compile_rpath $absdir" - esac - ;; - esac - case " $sys_lib_dlsearch_path " in - *" $libdir "*) ;; - *) - case "$finalize_rpath " in - *" $libdir "*) ;; - *) finalize_rpath="$finalize_rpath $libdir" - esac - ;; - esac - if test $linkmode = prog; then - # We need to hardcode the library path - if test -n "$shlibpath_var"; then - # Make sure the rpath contains only unique directories. - case "$temp_rpath " in - *" $dir "*) ;; - *" $absdir "*) ;; - *) temp_rpath="$temp_rpath $dir" ;; - esac - fi - fi - fi # $linkmode,$pass = prog,link... - - if test "$alldeplibs" = yes && - { test "$deplibs_check_method" = pass_all || - { test "$build_libtool_libs" = yes && - test -n "$library_names"; }; }; then - # We only need to search for static libraries - continue - fi - - if test "$installed" = no; then - notinst_deplibs="$notinst_deplibs $lib" - need_relink=yes - fi - - if test -n "$old_archive_from_expsyms_cmds"; then - # figure out the soname - set dummy $library_names - realname="$2" - shift; shift - libname=`eval \\$echo \"$libname_spec\"` - # use dlname if we got it. it's perfectly good, no? - if test -n "$dlname"; then - soname="$dlname" - elif test -n "$soname_spec"; then - # bleh windows - case $host in - *cygwin*) - major=`expr $current - $age` - versuffix="-$major" - ;; - esac - eval soname=\"$soname_spec\" - else - soname="$realname" - fi - - # Make a new name for the extract_expsyms_cmds to use - soroot="$soname" - soname=`echo $soroot | ${SED} -e 's/^.*\///'` - newlib="libimp-`echo $soname | ${SED} 's/^lib//;s/\.dll$//'`.a" - - # If the library has no export list, then create one now - if test -f "$output_objdir/$soname-def"; then : - else - $show "extracting exported symbol list from \`$soname'" - save_ifs="$IFS"; IFS='~' - eval cmds=\"$extract_expsyms_cmds\" - for cmd in $cmds; do - IFS="$save_ifs" - $show "$cmd" - $run eval "$cmd" || exit $? - done - IFS="$save_ifs" - fi - - # Create $newlib - if test -f "$output_objdir/$newlib"; then :; else - $show "generating import library for \`$soname'" - save_ifs="$IFS"; IFS='~' - eval cmds=\"$old_archive_from_expsyms_cmds\" - for cmd in $cmds; do - IFS="$save_ifs" - $show "$cmd" - $run eval "$cmd" || exit $? - done - IFS="$save_ifs" - fi - # make sure the library variables are pointing to the new library - dir=$output_objdir - linklib=$newlib - fi # test -n $old_archive_from_expsyms_cmds - - if test $linkmode = prog || test "$mode" != relink; then - add_shlibpath= - add_dir= - add= - lib_linked=yes - case $hardcode_action in - immediate | unsupported) - if test "$hardcode_direct" = no; then - add="$dir/$linklib" - elif test "$hardcode_minus_L" = no; then - case $host in - *-*-sunos*) add_shlibpath="$dir" ;; - esac - add_dir="-L$dir" - add="-l$name" - elif test "$hardcode_shlibpath_var" = no; then - add_shlibpath="$dir" - add="-l$name" - else - lib_linked=no - fi - ;; - relink) - if test "$hardcode_direct" = yes; then - add="$dir/$linklib" - elif test "$hardcode_minus_L" = yes; then - add_dir="-L$dir" - add="-l$name" - elif test "$hardcode_shlibpath_var" = yes; then - add_shlibpath="$dir" - add="-l$name" - else - lib_linked=no - fi - ;; - *) lib_linked=no ;; - esac - - if test "$lib_linked" != yes; then - $echo "$modename: configuration error: unsupported hardcode properties" - exit 1 - fi - - if test -n "$add_shlibpath"; then - case :$compile_shlibpath: in - *":$add_shlibpath:"*) ;; - *) compile_shlibpath="$compile_shlibpath$add_shlibpath:" ;; - esac - fi - if test $linkmode = prog; then - test -n "$add_dir" && compile_deplibs="$add_dir $compile_deplibs" - test -n "$add" && compile_deplibs="$add $compile_deplibs" - else - test -n "$add_dir" && deplibs="$add_dir $deplibs" - test -n "$add" && deplibs="$add $deplibs" - if test "$hardcode_direct" != yes && \ - test "$hardcode_minus_L" != yes && \ - test "$hardcode_shlibpath_var" = yes; then - case :$finalize_shlibpath: in - *":$libdir:"*) ;; - *) finalize_shlibpath="$finalize_shlibpath$libdir:" ;; - esac - fi - fi - fi - - if test $linkmode = prog || test "$mode" = relink; then - add_shlibpath= - add_dir= - add= - # Finalize command for both is simple: just hardcode it. - if test "$hardcode_direct" = yes; then - add="$libdir/$linklib" - elif test "$hardcode_minus_L" = yes; then - add_dir="-L$libdir" - add="-l$name" - elif test "$hardcode_shlibpath_var" = yes; then - case :$finalize_shlibpath: in - *":$libdir:"*) ;; - *) finalize_shlibpath="$finalize_shlibpath$libdir:" ;; - esac - add="-l$name" - else - # We cannot seem to hardcode it, guess we'll fake it. - add_dir="-L$libdir" - add="-l$name" - fi - - if test $linkmode = prog; then - test -n "$add_dir" && finalize_deplibs="$add_dir $finalize_deplibs" - test -n "$add" && finalize_deplibs="$add $finalize_deplibs" - else - test -n "$add_dir" && deplibs="$add_dir $deplibs" - test -n "$add" && deplibs="$add $deplibs" - fi - fi - elif test $linkmode = prog; then - if test "$alldeplibs" = yes && - { test "$deplibs_check_method" = pass_all || - { test "$build_libtool_libs" = yes && - test -n "$library_names"; }; }; then - # We only need to search for static libraries - continue - fi - - # Try to link the static library - # Here we assume that one of hardcode_direct or hardcode_minus_L - # is not unsupported. This is valid on all known static and - # shared platforms. - if test "$hardcode_direct" != unsupported; then - test -n "$old_library" && linklib="$old_library" - compile_deplibs="$dir/$linklib $compile_deplibs" - finalize_deplibs="$dir/$linklib $finalize_deplibs" - else - compile_deplibs="-l$name -L$dir $compile_deplibs" - finalize_deplibs="-l$name -L$dir $finalize_deplibs" - fi - elif test "$build_libtool_libs" = yes; then - # Not a shared library - if test "$deplibs_check_method" != pass_all; then - # We're trying link a shared library against a static one - # but the system doesn't support it. - - # Just print a warning and add the library to dependency_libs so - # that the program can be linked against the static library. - echo - echo "*** Warning: This system can not link to static lib archive $lib." - echo "*** I have the capability to make that library automatically link in when" - echo "*** you link to this library. But I can only do this if you have a" - echo "*** shared version of the library, which you do not appear to have." - if test "$module" = yes; then - echo "*** But as you try to build a module library, libtool will still create " - echo "*** a static module, that should work as long as the dlopening application" - echo "*** is linked with the -dlopen flag to resolve symbols at runtime." - if test -z "$global_symbol_pipe"; then - echo - echo "*** However, this would only work if libtool was able to extract symbol" - echo "*** lists from a program, using \`nm' or equivalent, but libtool could" - echo "*** not find such a program. So, this module is probably useless." - echo "*** \`nm' from GNU binutils and a full rebuild may help." - fi - if test "$build_old_libs" = no; then - build_libtool_libs=module - build_old_libs=yes - else - build_libtool_libs=no - fi - fi - else - convenience="$convenience $dir/$old_library" - old_convenience="$old_convenience $dir/$old_library" - deplibs="$dir/$old_library $deplibs" - link_static=yes - fi - fi # link shared/static library? - - if test $linkmode = lib; then - if test -n "$dependency_libs" && - { test $hardcode_into_libs != yes || test $build_old_libs = yes || - test $link_static = yes; }; then - # Extract -R from dependency_libs - temp_deplibs= - for libdir in $dependency_libs; do - case $libdir in - -R*) temp_xrpath=`$echo "X$libdir" | $Xsed -e 's/^-R//'` - case " $xrpath " in - *" $temp_xrpath "*) ;; - *) xrpath="$xrpath $temp_xrpath";; - esac;; - *) temp_deplibs="$temp_deplibs $libdir";; - esac - done - dependency_libs="$temp_deplibs" - fi - - newlib_search_path="$newlib_search_path $absdir" - # Link against this library - test "$link_static" = no && newdependency_libs="$abs_ladir/$laname $newdependency_libs" - # ... and its dependency_libs - tmp_libs= - for deplib in $dependency_libs; do - newdependency_libs="$deplib $newdependency_libs" - if test "X$duplicate_deps" = "Xyes" ; then - case "$tmp_libs " in - *" $deplib "*) specialdeplibs="$specialdeplibs $deplib" ;; - esac - fi - tmp_libs="$tmp_libs $deplib" - done - - if test $link_all_deplibs != no; then - # Add the search paths of all dependency libraries - for deplib in $dependency_libs; do - case $deplib in - -L*) path="$deplib" ;; - *.la) - dir=`$echo "X$deplib" | $Xsed -e 's%/[^/]*$%%'` - test "X$dir" = "X$deplib" && dir="." - # We need an absolute path. - case $dir in - [\\/]* | [A-Za-z]:[\\/]*) absdir="$dir" ;; - *) - absdir=`cd "$dir" && pwd` - if test -z "$absdir"; then - $echo "$modename: warning: cannot determine absolute directory name of \`$dir'" 1>&2 - absdir="$dir" - fi - ;; - esac - if grep "^installed=no" $deplib > /dev/null; then - path="-L$absdir/$objdir" - else - eval libdir=`${SED} -n -e 's/^libdir=\(.*\)$/\1/p' $deplib` - if test -z "$libdir"; then - $echo "$modename: \`$deplib' is not a valid libtool archive" 1>&2 - exit 1 - fi - if test "$absdir" != "$libdir"; then - $echo "$modename: warning: \`$deplib' seems to be moved" 1>&2 - fi - path="-L$absdir" - fi - ;; - *) continue ;; - esac - case " $deplibs " in - *" $path "*) ;; - *) deplibs="$deplibs $path" ;; - esac - done - fi # link_all_deplibs != no - fi # linkmode = lib - done # for deplib in $libs - if test $pass = dlpreopen; then - # Link the dlpreopened libraries before other libraries - for deplib in $save_deplibs; do - deplibs="$deplib $deplibs" - done - fi - if test $pass != dlopen; then - test $pass != scan && dependency_libs="$newdependency_libs" - if test $pass != conv; then - # Make sure lib_search_path contains only unique directories. - lib_search_path= - for dir in $newlib_search_path; do - case "$lib_search_path " in - *" $dir "*) ;; - *) lib_search_path="$lib_search_path $dir" ;; - esac - done - newlib_search_path= - fi - - if test "$linkmode,$pass" != "prog,link"; then - vars="deplibs" - else - vars="compile_deplibs finalize_deplibs" - fi - for var in $vars dependency_libs; do - # Add libraries to $var in reverse order - eval tmp_libs=\"\$$var\" - new_libs= - for deplib in $tmp_libs; do - case $deplib in - -L*) new_libs="$deplib $new_libs" ;; - *) - case " $specialdeplibs " in - *" $deplib "*) new_libs="$deplib $new_libs" ;; - *) - case " $new_libs " in - *" $deplib "*) ;; - *) new_libs="$deplib $new_libs" ;; - esac - ;; - esac - ;; - esac - done - tmp_libs= - for deplib in $new_libs; do - case $deplib in - -L*) - case " $tmp_libs " in - *" $deplib "*) ;; - *) tmp_libs="$tmp_libs $deplib" ;; - esac - ;; - *) tmp_libs="$tmp_libs $deplib" ;; - esac - done - eval $var=\"$tmp_libs\" - done # for var - fi - if test "$pass" = "conv" && - { test "$linkmode" = "lib" || test "$linkmode" = "prog"; }; then - libs="$deplibs" # reset libs - deplibs= - fi - done # for pass - if test $linkmode = prog; then - dlfiles="$newdlfiles" - dlprefiles="$newdlprefiles" - fi - - case $linkmode in - oldlib) - if test -n "$dlfiles$dlprefiles" || test "$dlself" != no; then - $echo "$modename: warning: \`-dlopen' is ignored for archives" 1>&2 - fi - - if test -n "$rpath"; then - $echo "$modename: warning: \`-rpath' is ignored for archives" 1>&2 - fi - - if test -n "$xrpath"; then - $echo "$modename: warning: \`-R' is ignored for archives" 1>&2 - fi - - if test -n "$vinfo"; then - $echo "$modename: warning: \`-version-info' is ignored for archives" 1>&2 - fi - - if test -n "$release"; then - $echo "$modename: warning: \`-release' is ignored for archives" 1>&2 - fi - - if test -n "$export_symbols" || test -n "$export_symbols_regex"; then - $echo "$modename: warning: \`-export-symbols' is ignored for archives" 1>&2 - fi - - # Now set the variables for building old libraries. - build_libtool_libs=no - oldlibs="$output" - objs="$objs$old_deplibs" - ;; - - lib) - # Make sure we only generate libraries of the form `libNAME.la'. - case $outputname in - lib*) - name=`$echo "X$outputname" | $Xsed -e 's/\.la$//' -e 's/^lib//'` - eval libname=\"$libname_spec\" - ;; - *) - if test "$module" = no; then - $echo "$modename: libtool library \`$output' must begin with \`lib'" 1>&2 - $echo "$help" 1>&2 - exit 1 - fi - if test "$need_lib_prefix" != no; then - # Add the "lib" prefix for modules if required - name=`$echo "X$outputname" | $Xsed -e 's/\.la$//'` - eval libname=\"$libname_spec\" - else - libname=`$echo "X$outputname" | $Xsed -e 's/\.la$//'` - fi - ;; - esac - - if test -n "$objs"; then - if test "$deplibs_check_method" != pass_all; then - $echo "$modename: cannot build libtool library \`$output' from non-libtool objects on this host:$objs" 2>&1 - exit 1 - else - echo - echo "*** Warning: Linking the shared library $output against the non-libtool" - echo "*** objects $objs is not portable!" - libobjs="$libobjs $objs" - fi - fi - - if test "$dlself" != no; then - $echo "$modename: warning: \`-dlopen self' is ignored for libtool libraries" 1>&2 - fi - - set dummy $rpath - if test $# -gt 2; then - $echo "$modename: warning: ignoring multiple \`-rpath's for a libtool library" 1>&2 - fi - install_libdir="$2" - - oldlibs= - if test -z "$rpath"; then - if test "$build_libtool_libs" = yes; then - # Building a libtool convenience library. - libext=al - oldlibs="$output_objdir/$libname.$libext $oldlibs" - build_libtool_libs=convenience - build_old_libs=yes - fi - - if test -n "$vinfo"; then - $echo "$modename: warning: \`-version-info' is ignored for convenience libraries" 1>&2 - fi - - if test -n "$release"; then - $echo "$modename: warning: \`-release' is ignored for convenience libraries" 1>&2 - fi - else - - # Parse the version information argument. - save_ifs="$IFS"; IFS=':' - set dummy $vinfo 0 0 0 - IFS="$save_ifs" - - if test -n "$8"; then - $echo "$modename: too many parameters to \`-version-info'" 1>&2 - $echo "$help" 1>&2 - exit 1 - fi - - current="$2" - revision="$3" - age="$4" - - # Check that each of the things are valid numbers. - case $current in - 0 | [1-9] | [1-9][0-9] | [1-9][0-9][0-9]) ;; - *) - $echo "$modename: CURRENT \`$current' is not a nonnegative integer" 1>&2 - $echo "$modename: \`$vinfo' is not valid version information" 1>&2 - exit 1 - ;; - esac - - case $revision in - 0 | [1-9] | [1-9][0-9] | [1-9][0-9][0-9]) ;; - *) - $echo "$modename: REVISION \`$revision' is not a nonnegative integer" 1>&2 - $echo "$modename: \`$vinfo' is not valid version information" 1>&2 - exit 1 - ;; - esac - - case $age in - 0 | [1-9] | [1-9][0-9] | [1-9][0-9][0-9]) ;; - *) - $echo "$modename: AGE \`$age' is not a nonnegative integer" 1>&2 - $echo "$modename: \`$vinfo' is not valid version information" 1>&2 - exit 1 - ;; - esac - - if test $age -gt $current; then - $echo "$modename: AGE \`$age' is greater than the current interface number \`$current'" 1>&2 - $echo "$modename: \`$vinfo' is not valid version information" 1>&2 - exit 1 - fi - - # Calculate the version variables. - major= - versuffix= - verstring= - case $version_type in - none) ;; - - darwin) - # Like Linux, but with the current version available in - # verstring for coding it into the library header - major=.`expr $current - $age` - versuffix="$major.$age.$revision" - # Darwin ld doesn't like 0 for these options... - minor_current=`expr $current + 1` - verstring="-compatibility_version $minor_current -current_version $minor_current.$revision" - ;; - - freebsd-aout) - major=".$current" - versuffix=".$current.$revision"; - ;; - - freebsd-elf) - major=".$current" - versuffix=".$current"; - ;; - - irix | nonstopux) - major=`expr $current - $age + 1` - - case $version_type in - nonstopux) verstring_prefix=nonstopux ;; - *) verstring_prefix=sgi ;; - esac - verstring="$verstring_prefix$major.$revision" - - # Add in all the interfaces that we are compatible with. - loop=$revision - while test $loop != 0; do - iface=`expr $revision - $loop` - loop=`expr $loop - 1` - verstring="$verstring_prefix$major.$iface:$verstring" - done - - # Before this point, $major must not contain `.'. - major=.$major - versuffix="$major.$revision" - ;; - - linux) - major=.`expr $current - $age` - versuffix="$major.$age.$revision" - ;; - - osf) - major=.`expr $current - $age` - versuffix=".$current.$age.$revision" - verstring="$current.$age.$revision" - - # Add in all the interfaces that we are compatible with. - loop=$age - while test $loop != 0; do - iface=`expr $current - $loop` - loop=`expr $loop - 1` - verstring="$verstring:${iface}.0" - done - - # Make executables depend on our current version. - verstring="$verstring:${current}.0" - ;; - - sunos) - major=".$current" - versuffix=".$current.$revision" - ;; - - windows) - # Use '-' rather than '.', since we only want one - # extension on DOS 8.3 filesystems. - major=`expr $current - $age` - versuffix="-$major" - ;; - - *) - $echo "$modename: unknown library version type \`$version_type'" 1>&2 - echo "Fatal configuration error. See the $PACKAGE docs for more information." 1>&2 - exit 1 - ;; - esac - - # Clear the version info if we defaulted, and they specified a release. - if test -z "$vinfo" && test -n "$release"; then - major= - verstring="0.0" - case $version_type in - darwin) - # we can't check for "0.0" in archive_cmds due to quoting - # problems, so we reset it completely - verstring="" - ;; - *) - verstring="0.0" - ;; - esac - if test "$need_version" = no; then - versuffix= - else - versuffix=".0.0" - fi - fi - - # Remove version info from name if versioning should be avoided - if test "$avoid_version" = yes && test "$need_version" = no; then - major= - versuffix= - verstring="" - fi - - # Check to see if the archive will have undefined symbols. - if test "$allow_undefined" = yes; then - if test "$allow_undefined_flag" = unsupported; then - $echo "$modename: warning: undefined symbols not allowed in $host shared libraries" 1>&2 - build_libtool_libs=no - build_old_libs=yes - fi - else - # Don't allow undefined symbols. - allow_undefined_flag="$no_undefined_flag" - fi - fi - - if test "$mode" != relink; then - # Remove our outputs. - $show "${rm}r $output_objdir/$outputname $output_objdir/$libname.* $output_objdir/${libname}${release}.*" - $run ${rm}r $output_objdir/$outputname $output_objdir/$libname.* $output_objdir/${libname}${release}.* - fi - - # Now set the variables for building old libraries. - if test "$build_old_libs" = yes && test "$build_libtool_libs" != convenience ; then - oldlibs="$oldlibs $output_objdir/$libname.$libext" - - # Transform .lo files to .o files. - oldobjs="$objs "`$echo "X$libobjs" | $SP2NL | $Xsed -e '/\.'${libext}'$/d' -e "$lo2o" | $NL2SP` - fi - - # Eliminate all temporary directories. - for path in $notinst_path; do - lib_search_path=`echo "$lib_search_path " | ${SED} -e 's% $path % %g'` - deplibs=`echo "$deplibs " | ${SED} -e 's% -L$path % %g'` - dependency_libs=`echo "$dependency_libs " | ${SED} -e 's% -L$path % %g'` - done - - if test -n "$xrpath"; then - # If the user specified any rpath flags, then add them. - temp_xrpath= - for libdir in $xrpath; do - temp_xrpath="$temp_xrpath -R$libdir" - case "$finalize_rpath " in - *" $libdir "*) ;; - *) finalize_rpath="$finalize_rpath $libdir" ;; - esac - done - if test $hardcode_into_libs != yes || test $build_old_libs = yes; then - dependency_libs="$temp_xrpath $dependency_libs" - fi - fi - - # Make sure dlfiles contains only unique files that won't be dlpreopened - old_dlfiles="$dlfiles" - dlfiles= - for lib in $old_dlfiles; do - case " $dlprefiles $dlfiles " in - *" $lib "*) ;; - *) dlfiles="$dlfiles $lib" ;; - esac - done - - # Make sure dlprefiles contains only unique files - old_dlprefiles="$dlprefiles" - dlprefiles= - for lib in $old_dlprefiles; do - case "$dlprefiles " in - *" $lib "*) ;; - *) dlprefiles="$dlprefiles $lib" ;; - esac - done - - if test "$build_libtool_libs" = yes; then - if test -n "$rpath"; then - case $host in - *-*-cygwin* | *-*-mingw* | *-*-pw32* | *-*-os2* | *-*-beos*) - # these systems don't actually have a c library (as such)! - ;; - *-*-rhapsody* | *-*-darwin1.[012]) - # Rhapsody C library is in the System framework - deplibs="$deplibs -framework System" - ;; - *-*-netbsd*) - # Don't link with libc until the a.out ld.so is fixed. - ;; - *-*-openbsd* | *-*-freebsd*) - # Do not include libc due to us having libc/libc_r. - ;; - *) - # Add libc to deplibs on all other systems if necessary. - if test $build_libtool_need_lc = "yes"; then - deplibs="$deplibs -lc" - fi - ;; - esac - fi - - # Transform deplibs into only deplibs that can be linked in shared. - name_save=$name - libname_save=$libname - release_save=$release - versuffix_save=$versuffix - major_save=$major - # I'm not sure if I'm treating the release correctly. I think - # release should show up in the -l (ie -lgmp5) so we don't want to - # add it in twice. Is that correct? - release="" - versuffix="" - major="" - newdeplibs= - droppeddeps=no - case $deplibs_check_method in - pass_all) - # Don't check for shared/static. Everything works. - # This might be a little naive. We might want to check - # whether the library exists or not. But this is on - # osf3 & osf4 and I'm not really sure... Just - # implementing what was already the behaviour. - newdeplibs=$deplibs - ;; - test_compile) - # This code stresses the "libraries are programs" paradigm to its - # limits. Maybe even breaks it. We compile a program, linking it - # against the deplibs as a proxy for the library. Then we can check - # whether they linked in statically or dynamically with ldd. - $rm conftest.c - cat > conftest.c <<EOF - int main() { return 0; } -EOF - $rm conftest - $CC -o conftest conftest.c $deplibs - if test $? -eq 0 ; then - ldd_output=`ldd conftest` - for i in $deplibs; do - name="`expr $i : '-l\(.*\)'`" - # If $name is empty we are operating on a -L argument. - if test -n "$name" && test "$name" != "0"; then - libname=`eval \\$echo \"$libname_spec\"` - deplib_matches=`eval \\$echo \"$library_names_spec\"` - set dummy $deplib_matches - deplib_match=$2 - if test `expr "$ldd_output" : ".*$deplib_match"` -ne 0 ; then - newdeplibs="$newdeplibs $i" - else - droppeddeps=yes - echo - echo "*** Warning: dynamic linker does not accept needed library $i." - echo "*** I have the capability to make that library automatically link in when" - echo "*** you link to this library. But I can only do this if you have a" - echo "*** shared version of the library, which I believe you do not have" - echo "*** because a test_compile did reveal that the linker did not use it for" - echo "*** its dynamic dependency list that programs get resolved with at runtime." - fi - else - newdeplibs="$newdeplibs $i" - fi - done - else - # Error occured in the first compile. Let's try to salvage - # the situation: Compile a separate program for each library. - for i in $deplibs; do - name="`expr $i : '-l\(.*\)'`" - # If $name is empty we are operating on a -L argument. - if test -n "$name" && test "$name" != "0"; then - $rm conftest - $CC -o conftest conftest.c $i - # Did it work? - if test $? -eq 0 ; then - ldd_output=`ldd conftest` - libname=`eval \\$echo \"$libname_spec\"` - deplib_matches=`eval \\$echo \"$library_names_spec\"` - set dummy $deplib_matches - deplib_match=$2 - if test `expr "$ldd_output" : ".*$deplib_match"` -ne 0 ; then - newdeplibs="$newdeplibs $i" - else - droppeddeps=yes - echo - echo "*** Warning: dynamic linker does not accept needed library $i." - echo "*** I have the capability to make that library automatically link in when" - echo "*** you link to this library. But I can only do this if you have a" - echo "*** shared version of the library, which you do not appear to have" - echo "*** because a test_compile did reveal that the linker did not use this one" - echo "*** as a dynamic dependency that programs can get resolved with at runtime." - fi - else - droppeddeps=yes - echo - echo "*** Warning! Library $i is needed by this library but I was not able to" - echo "*** make it link in! You will probably need to install it or some" - echo "*** library that it depends on before this library will be fully" - echo "*** functional. Installing it before continuing would be even better." - fi - else - newdeplibs="$newdeplibs $i" - fi - done - fi - ;; - file_magic*) - set dummy $deplibs_check_method - file_magic_regex=`expr "$deplibs_check_method" : "$2 \(.*\)"` - for a_deplib in $deplibs; do - name="`expr $a_deplib : '-l\(.*\)'`" - # If $name is empty we are operating on a -L argument. - if test -n "$name" && test "$name" != "0"; then - libname=`eval \\$echo \"$libname_spec\"` - for i in $lib_search_path $sys_lib_search_path $shlib_search_path; do - potential_libs=`ls $i/$libname[.-]* 2>/dev/null` - for potent_lib in $potential_libs; do - # Follow soft links. - if ls -lLd "$potent_lib" 2>/dev/null \ - | grep " -> " >/dev/null; then - continue - fi - # The statement above tries to avoid entering an - # endless loop below, in case of cyclic links. - # We might still enter an endless loop, since a link - # loop can be closed while we follow links, - # but so what? - potlib="$potent_lib" - while test -h "$potlib" 2>/dev/null; do - potliblink=`ls -ld $potlib | ${SED} 's/.* -> //'` - case $potliblink in - [\\/]* | [A-Za-z]:[\\/]*) potlib="$potliblink";; - *) potlib=`$echo "X$potlib" | $Xsed -e 's,[^/]*$,,'`"$potliblink";; - esac - done - if eval $file_magic_cmd \"\$potlib\" 2>/dev/null \ - | ${SED} 10q \ - | egrep "$file_magic_regex" > /dev/null; then - newdeplibs="$newdeplibs $a_deplib" - a_deplib="" - break 2 - fi - done - done - if test -n "$a_deplib" ; then - droppeddeps=yes - echo - echo "*** Warning: linker path does not have real file for library $a_deplib." - echo "*** I have the capability to make that library automatically link in when" - echo "*** you link to this library. But I can only do this if you have a" - echo "*** shared version of the library, which you do not appear to have" - echo "*** because I did check the linker path looking for a file starting" - if test -z "$potlib" ; then - echo "*** with $libname but no candidates were found. (...for file magic test)" - else - echo "*** with $libname and none of the candidates passed a file format test" - echo "*** using a file magic. Last file checked: $potlib" - fi - fi - else - # Add a -L argument. - newdeplibs="$newdeplibs $a_deplib" - fi - done # Gone through all deplibs. - ;; - match_pattern*) - set dummy $deplibs_check_method - match_pattern_regex=`expr "$deplibs_check_method" : "$2 \(.*\)"` - for a_deplib in $deplibs; do - name="`expr $a_deplib : '-l\(.*\)'`" - # If $name is empty we are operating on a -L argument. - if test -n "$name" && test "$name" != "0"; then - libname=`eval \\$echo \"$libname_spec\"` - for i in $lib_search_path $sys_lib_search_path $shlib_search_path; do - potential_libs=`ls $i/$libname[.-]* 2>/dev/null` - for potent_lib in $potential_libs; do - potlib="$potent_lib" # see symlink-check below in file_magic test - if eval echo \"$potent_lib\" 2>/dev/null \ - | ${SED} 10q \ - | egrep "$match_pattern_regex" > /dev/null; then - newdeplibs="$newdeplibs $a_deplib" - a_deplib="" - break 2 - fi - done - done - if test -n "$a_deplib" ; then - droppeddeps=yes - echo - echo "*** Warning: linker path does not have real file for library $a_deplib." - echo "*** I have the capability to make that library automatically link in when" - echo "*** you link to this library. But I can only do this if you have a" - echo "*** shared version of the library, which you do not appear to have" - echo "*** because I did check the linker path looking for a file starting" - if test -z "$potlib" ; then - echo "*** with $libname but no candidates were found. (...for regex pattern test)" - else - echo "*** with $libname and none of the candidates passed a file format test" - echo "*** using a regex pattern. Last file checked: $potlib" - fi - fi - else - # Add a -L argument. - newdeplibs="$newdeplibs $a_deplib" - fi - done # Gone through all deplibs. - ;; - none | unknown | *) - newdeplibs="" - if $echo "X $deplibs" | $Xsed -e 's/ -lc$//' \ - -e 's/ -[LR][^ ]*//g' -e 's/[ ]//g' | - grep . >/dev/null; then - echo - if test "X$deplibs_check_method" = "Xnone"; then - echo "*** Warning: inter-library dependencies are not supported in this platform." - else - echo "*** Warning: inter-library dependencies are not known to be supported." - fi - echo "*** All declared inter-library dependencies are being dropped." - droppeddeps=yes - fi - ;; - esac - versuffix=$versuffix_save - major=$major_save - release=$release_save - libname=$libname_save - name=$name_save - - case $host in - *-*-rhapsody* | *-*-darwin1.[012]) - # On Rhapsody replace the C library is the System framework - newdeplibs=`$echo "X $newdeplibs" | $Xsed -e 's/ -lc / -framework System /'` - ;; - esac - - if test "$droppeddeps" = yes; then - if test "$module" = yes; then - echo - echo "*** Warning: libtool could not satisfy all declared inter-library" - echo "*** dependencies of module $libname. Therefore, libtool will create" - echo "*** a static module, that should work as long as the dlopening" - echo "*** application is linked with the -dlopen flag." - if test -z "$global_symbol_pipe"; then - echo - echo "*** However, this would only work if libtool was able to extract symbol" - echo "*** lists from a program, using \`nm' or equivalent, but libtool could" - echo "*** not find such a program. So, this module is probably useless." - echo "*** \`nm' from GNU binutils and a full rebuild may help." - fi - if test "$build_old_libs" = no; then - oldlibs="$output_objdir/$libname.$libext" - build_libtool_libs=module - build_old_libs=yes - else - build_libtool_libs=no - fi - else - echo "*** The inter-library dependencies that have been dropped here will be" - echo "*** automatically added whenever a program is linked with this library" - echo "*** or is declared to -dlopen it." - - if test $allow_undefined = no; then - echo - echo "*** Since this library must not contain undefined symbols," - echo "*** because either the platform does not support them or" - echo "*** it was explicitly requested with -no-undefined," - echo "*** libtool will only create a static version of it." - if test "$build_old_libs" = no; then - oldlibs="$output_objdir/$libname.$libext" - build_libtool_libs=module - build_old_libs=yes - else - build_libtool_libs=no - fi - fi - fi - fi - # Done checking deplibs! - deplibs=$newdeplibs - fi - - # All the library-specific variables (install_libdir is set above). - library_names= - old_library= - dlname= - - # Test again, we may have decided not to build it any more - if test "$build_libtool_libs" = yes; then - if test $hardcode_into_libs = yes; then - # Hardcode the library paths - hardcode_libdirs= - dep_rpath= - rpath="$finalize_rpath" - test "$mode" != relink && rpath="$compile_rpath$rpath" - for libdir in $rpath; do - if test -n "$hardcode_libdir_flag_spec"; then - if test -n "$hardcode_libdir_separator"; then - if test -z "$hardcode_libdirs"; then - hardcode_libdirs="$libdir" - else - # Just accumulate the unique libdirs. - case $hardcode_libdir_separator$hardcode_libdirs$hardcode_libdir_separator in - *"$hardcode_libdir_separator$libdir$hardcode_libdir_separator"*) - ;; - *) - hardcode_libdirs="$hardcode_libdirs$hardcode_libdir_separator$libdir" - ;; - esac - fi - else - eval flag=\"$hardcode_libdir_flag_spec\" - dep_rpath="$dep_rpath $flag" - fi - elif test -n "$runpath_var"; then - case "$perm_rpath " in - *" $libdir "*) ;; - *) perm_rpath="$perm_rpath $libdir" ;; - esac - fi - done - # Substitute the hardcoded libdirs into the rpath. - if test -n "$hardcode_libdir_separator" && - test -n "$hardcode_libdirs"; then - libdir="$hardcode_libdirs" - eval dep_rpath=\"$hardcode_libdir_flag_spec\" - fi - if test -n "$runpath_var" && test -n "$perm_rpath"; then - # We should set the runpath_var. - rpath= - for dir in $perm_rpath; do - rpath="$rpath$dir:" - done - eval "$runpath_var='$rpath\$$runpath_var'; export $runpath_var" - fi - test -n "$dep_rpath" && deplibs="$dep_rpath $deplibs" - fi - - shlibpath="$finalize_shlibpath" - test "$mode" != relink && shlibpath="$compile_shlibpath$shlibpath" - if test -n "$shlibpath"; then - eval "$shlibpath_var='$shlibpath\$$shlibpath_var'; export $shlibpath_var" - fi - - # Get the real and link names of the library. - eval library_names=\"$library_names_spec\" - set dummy $library_names - realname="$2" - shift; shift - - if test -n "$soname_spec"; then - eval soname=\"$soname_spec\" - else - soname="$realname" - fi - test -z "$dlname" && dlname=$soname - - lib="$output_objdir/$realname" - for link - do - linknames="$linknames $link" - done - - # Ensure that we have .o objects for linkers which dislike .lo - # (e.g. aix) in case we are running --disable-static - for obj in $libobjs; do - xdir=`$echo "X$obj" | $Xsed -e 's%/[^/]*$%%'` - if test "X$xdir" = "X$obj"; then - xdir="." - else - xdir="$xdir" - fi - baseobj=`$echo "X$obj" | $Xsed -e 's%^.*/%%'` - oldobj=`$echo "X$baseobj" | $Xsed -e "$lo2o"` - if test ! -f $xdir/$oldobj; then - $show "(cd $xdir && ${LN_S} $baseobj $oldobj)" - $run eval '(cd $xdir && ${LN_S} $baseobj $oldobj)' || exit $? - fi - done - - # Use standard objects if they are pic - test -z "$pic_flag" && libobjs=`$echo "X$libobjs" | $SP2NL | $Xsed -e "$lo2o" | $NL2SP` - - # Prepare the list of exported symbols - if test -z "$export_symbols"; then - if test "$always_export_symbols" = yes || test -n "$export_symbols_regex"; then - $show "generating symbol list for \`$libname.la'" - export_symbols="$output_objdir/$libname.exp" - $run $rm $export_symbols - eval cmds=\"$export_symbols_cmds\" - save_ifs="$IFS"; IFS='~' - for cmd in $cmds; do - IFS="$save_ifs" - $show "$cmd" - $run eval "$cmd" || exit $? - done - IFS="$save_ifs" - if test -n "$export_symbols_regex"; then - $show "egrep -e \"$export_symbols_regex\" \"$export_symbols\" > \"${export_symbols}T\"" - $run eval 'egrep -e "$export_symbols_regex" "$export_symbols" > "${export_symbols}T"' - $show "$mv \"${export_symbols}T\" \"$export_symbols\"" - $run eval '$mv "${export_symbols}T" "$export_symbols"' - fi - fi - fi - - if test -n "$export_symbols" && test -n "$include_expsyms"; then - $run eval '$echo "X$include_expsyms" | $SP2NL >> "$export_symbols"' - fi - - if test -n "$convenience"; then - if test -n "$whole_archive_flag_spec"; then - eval libobjs=\"\$libobjs $whole_archive_flag_spec\" - else - gentop="$output_objdir/${outputname}x" - $show "${rm}r $gentop" - $run ${rm}r "$gentop" - $show "mkdir $gentop" - $run mkdir "$gentop" - status=$? - if test $status -ne 0 && test ! -d "$gentop"; then - exit $status - fi - generated="$generated $gentop" - - for xlib in $convenience; do - # Extract the objects. - case $xlib in - [\\/]* | [A-Za-z]:[\\/]*) xabs="$xlib" ;; - *) xabs=`pwd`"/$xlib" ;; - esac - xlib=`$echo "X$xlib" | $Xsed -e 's%^.*/%%'` - xdir="$gentop/$xlib" - - $show "${rm}r $xdir" - $run ${rm}r "$xdir" - $show "mkdir $xdir" - $run mkdir "$xdir" - status=$? - if test $status -ne 0 && test ! -d "$xdir"; then - exit $status - fi - $show "(cd $xdir && $AR x $xabs)" - $run eval "(cd \$xdir && $AR x \$xabs)" || exit $? - - libobjs="$libobjs "`find $xdir -name \*.o -print -o -name \*.lo -print | $NL2SP` - done - fi - fi - - if test "$thread_safe" = yes && test -n "$thread_safe_flag_spec"; then - eval flag=\"$thread_safe_flag_spec\" - linker_flags="$linker_flags $flag" - fi - - # Make a backup of the uninstalled library when relinking - if test "$mode" = relink; then - $run eval '(cd $output_objdir && $rm ${realname}U && $mv $realname ${realname}U)' || exit $? - fi - - # Do each of the archive commands. - if test -n "$export_symbols" && test -n "$archive_expsym_cmds"; then - eval cmds=\"$archive_expsym_cmds\" - else - save_deplibs="$deplibs" - for conv in $convenience; do - tmp_deplibs= - for test_deplib in $deplibs; do - if test "$test_deplib" != "$conv"; then - tmp_deplibs="$tmp_deplibs $test_deplib" - fi - done - deplibs="$tmp_deplibs" - done - eval cmds=\"$archive_cmds\" - deplibs="$save_deplibs" - fi - save_ifs="$IFS"; IFS='~' - for cmd in $cmds; do - IFS="$save_ifs" - $show "$cmd" - $run eval "$cmd" || exit $? - done - IFS="$save_ifs" - - # Restore the uninstalled library and exit - if test "$mode" = relink; then - $run eval '(cd $output_objdir && $rm ${realname}T && $mv $realname ${realname}T && $mv "$realname"U $realname)' || exit $? - exit 0 - fi - - # Create links to the real library. - for linkname in $linknames; do - if test "$realname" != "$linkname"; then - $show "(cd $output_objdir && $rm $linkname && $LN_S $realname $linkname)" - $run eval '(cd $output_objdir && $rm $linkname && $LN_S $realname $linkname)' || exit $? - fi - done - - # If -module or -export-dynamic was specified, set the dlname. - if test "$module" = yes || test "$export_dynamic" = yes; then - # On all known operating systems, these are identical. - dlname="$soname" - fi - fi - ;; - - obj) - if test -n "$deplibs"; then - $echo "$modename: warning: \`-l' and \`-L' are ignored for objects" 1>&2 - fi - - if test -n "$dlfiles$dlprefiles" || test "$dlself" != no; then - $echo "$modename: warning: \`-dlopen' is ignored for objects" 1>&2 - fi - - if test -n "$rpath"; then - $echo "$modename: warning: \`-rpath' is ignored for objects" 1>&2 - fi - - if test -n "$xrpath"; then - $echo "$modename: warning: \`-R' is ignored for objects" 1>&2 - fi - - if test -n "$vinfo"; then - $echo "$modename: warning: \`-version-info' is ignored for objects" 1>&2 - fi - - if test -n "$release"; then - $echo "$modename: warning: \`-release' is ignored for objects" 1>&2 - fi - - case $output in - *.lo) - if test -n "$objs$old_deplibs"; then - $echo "$modename: cannot build library object \`$output' from non-libtool objects" 1>&2 - exit 1 - fi - libobj="$output" - obj=`$echo "X$output" | $Xsed -e "$lo2o"` - ;; - *) - libobj= - obj="$output" - ;; - esac - - # Delete the old objects. - $run $rm $obj $libobj - - # Objects from convenience libraries. This assumes - # single-version convenience libraries. Whenever we create - # different ones for PIC/non-PIC, this we'll have to duplicate - # the extraction. - reload_conv_objs= - gentop= - # reload_cmds runs $LD directly, so let us get rid of - # -Wl from whole_archive_flag_spec - wl= - - if test -n "$convenience"; then - if test -n "$whole_archive_flag_spec"; then - eval reload_conv_objs=\"\$reload_objs $whole_archive_flag_spec\" - else - gentop="$output_objdir/${obj}x" - $show "${rm}r $gentop" - $run ${rm}r "$gentop" - $show "mkdir $gentop" - $run mkdir "$gentop" - status=$? - if test $status -ne 0 && test ! -d "$gentop"; then - exit $status - fi - generated="$generated $gentop" - - for xlib in $convenience; do - # Extract the objects. - case $xlib in - [\\/]* | [A-Za-z]:[\\/]*) xabs="$xlib" ;; - *) xabs=`pwd`"/$xlib" ;; - esac - xlib=`$echo "X$xlib" | $Xsed -e 's%^.*/%%'` - xdir="$gentop/$xlib" - - $show "${rm}r $xdir" - $run ${rm}r "$xdir" - $show "mkdir $xdir" - $run mkdir "$xdir" - status=$? - if test $status -ne 0 && test ! -d "$xdir"; then - exit $status - fi - $show "(cd $xdir && $AR x $xabs)" - $run eval "(cd \$xdir && $AR x \$xabs)" || exit $? - - reload_conv_objs="$reload_objs "`find $xdir -name \*.o -print -o -name \*.lo -print | $NL2SP` - done - fi - fi - - # Create the old-style object. - reload_objs="$objs$old_deplibs "`$echo "X$libobjs" | $SP2NL | $Xsed -e '/\.'${libext}$'/d' -e '/\.lib$/d' -e "$lo2o" | $NL2SP`" $reload_conv_objs" ### testsuite: skip nested quoting test - - output="$obj" - eval cmds=\"$reload_cmds\" - save_ifs="$IFS"; IFS='~' - for cmd in $cmds; do - IFS="$save_ifs" - $show "$cmd" - $run eval "$cmd" || exit $? - done - IFS="$save_ifs" - - # Exit if we aren't doing a library object file. - if test -z "$libobj"; then - if test -n "$gentop"; then - $show "${rm}r $gentop" - $run ${rm}r $gentop - fi - - exit 0 - fi - - if test "$build_libtool_libs" != yes; then - if test -n "$gentop"; then - $show "${rm}r $gentop" - $run ${rm}r $gentop - fi - - # Create an invalid libtool object if no PIC, so that we don't - # accidentally link it into a program. - $show "echo timestamp > $libobj" - $run eval "echo timestamp > $libobj" || exit $? - exit 0 - fi - - if test -n "$pic_flag" || test "$pic_mode" != default; then - # Only do commands if we really have different PIC objects. - reload_objs="$libobjs $reload_conv_objs" - output="$libobj" - eval cmds=\"$reload_cmds\" - save_ifs="$IFS"; IFS='~' - for cmd in $cmds; do - IFS="$save_ifs" - $show "$cmd" - $run eval "$cmd" || exit $? - done - IFS="$save_ifs" - else - # Just create a symlink. - $show $rm $libobj - $run $rm $libobj - xdir=`$echo "X$libobj" | $Xsed -e 's%/[^/]*$%%'` - if test "X$xdir" = "X$libobj"; then - xdir="." - else - xdir="$xdir" - fi - baseobj=`$echo "X$libobj" | $Xsed -e 's%^.*/%%'` - oldobj=`$echo "X$baseobj" | $Xsed -e "$lo2o"` - $show "(cd $xdir && $LN_S $oldobj $baseobj)" - $run eval '(cd $xdir && $LN_S $oldobj $baseobj)' || exit $? - fi - - if test -n "$gentop"; then - $show "${rm}r $gentop" - $run ${rm}r $gentop - fi - - exit 0 - ;; - - prog) - case $host in - *cygwin*) output=`echo $output | ${SED} -e 's,.exe$,,;s,$,.exe,'` ;; - esac - if test -n "$vinfo"; then - $echo "$modename: warning: \`-version-info' is ignored for programs" 1>&2 - fi - - if test -n "$release"; then - $echo "$modename: warning: \`-release' is ignored for programs" 1>&2 - fi - - if test "$preload" = yes; then - if test "$dlopen_support" = unknown && test "$dlopen_self" = unknown && - test "$dlopen_self_static" = unknown; then - $echo "$modename: warning: \`AC_LIBTOOL_DLOPEN' not used. Assuming no dlopen support." - fi - fi - - case $host in - *-*-rhapsody* | *-*-darwin1.[012]) - # On Rhapsody replace the C library is the System framework - compile_deplibs=`$echo "X $compile_deplibs" | $Xsed -e 's/ -lc / -framework System /'` - finalize_deplibs=`$echo "X $finalize_deplibs" | $Xsed -e 's/ -lc / -framework System /'` - case $host in - *darwin*) - # Don't allow lazy linking, it breaks C++ global constructors - compile_command="$compile_command ${wl}-bind_at_load" - finalize_command="$finalize_command ${wl}-bind_at_load" - ;; - esac - ;; - esac - - compile_command="$compile_command $compile_deplibs" - finalize_command="$finalize_command $finalize_deplibs" - - if test -n "$rpath$xrpath"; then - # If the user specified any rpath flags, then add them. - for libdir in $rpath $xrpath; do - # This is the magic to use -rpath. - case "$finalize_rpath " in - *" $libdir "*) ;; - *) finalize_rpath="$finalize_rpath $libdir" ;; - esac - done - fi - - # Now hardcode the library paths - rpath= - hardcode_libdirs= - for libdir in $compile_rpath $finalize_rpath; do - if test -n "$hardcode_libdir_flag_spec"; then - if test -n "$hardcode_libdir_separator"; then - if test -z "$hardcode_libdirs"; then - hardcode_libdirs="$libdir" - else - # Just accumulate the unique libdirs. - case $hardcode_libdir_separator$hardcode_libdirs$hardcode_libdir_separator in - *"$hardcode_libdir_separator$libdir$hardcode_libdir_separator"*) - ;; - *) - hardcode_libdirs="$hardcode_libdirs$hardcode_libdir_separator$libdir" - ;; - esac - fi - else - eval flag=\"$hardcode_libdir_flag_spec\" - rpath="$rpath $flag" - fi - elif test -n "$runpath_var"; then - case "$perm_rpath " in - *" $libdir "*) ;; - *) perm_rpath="$perm_rpath $libdir" ;; - esac - fi - case $host in - *-*-cygwin* | *-*-mingw* | *-*-pw32* | *-*-os2*) - case :$dllsearchpath: in - *":$libdir:"*) ;; - *) dllsearchpath="$dllsearchpath:$libdir";; - esac - ;; - esac - done - # Substitute the hardcoded libdirs into the rpath. - if test -n "$hardcode_libdir_separator" && - test -n "$hardcode_libdirs"; then - libdir="$hardcode_libdirs" - eval rpath=\" $hardcode_libdir_flag_spec\" - fi - compile_rpath="$rpath" - - rpath= - hardcode_libdirs= - for libdir in $finalize_rpath; do - if test -n "$hardcode_libdir_flag_spec"; then - if test -n "$hardcode_libdir_separator"; then - if test -z "$hardcode_libdirs"; then - hardcode_libdirs="$libdir" - else - # Just accumulate the unique libdirs. - case $hardcode_libdir_separator$hardcode_libdirs$hardcode_libdir_separator in - *"$hardcode_libdir_separator$libdir$hardcode_libdir_separator"*) - ;; - *) - hardcode_libdirs="$hardcode_libdirs$hardcode_libdir_separator$libdir" - ;; - esac - fi - else - eval flag=\"$hardcode_libdir_flag_spec\" - rpath="$rpath $flag" - fi - elif test -n "$runpath_var"; then - case "$finalize_perm_rpath " in - *" $libdir "*) ;; - *) finalize_perm_rpath="$finalize_perm_rpath $libdir" ;; - esac - fi - done - # Substitute the hardcoded libdirs into the rpath. - if test -n "$hardcode_libdir_separator" && - test -n "$hardcode_libdirs"; then - libdir="$hardcode_libdirs" - eval rpath=\" $hardcode_libdir_flag_spec\" - fi - finalize_rpath="$rpath" - - if test -n "$libobjs" && test "$build_old_libs" = yes; then - # Transform all the library objects into standard objects. - compile_command=`$echo "X$compile_command" | $SP2NL | $Xsed -e "$lo2o" | $NL2SP` - finalize_command=`$echo "X$finalize_command" | $SP2NL | $Xsed -e "$lo2o" | $NL2SP` - fi - - dlsyms= - if test -n "$dlfiles$dlprefiles" || test "$dlself" != no; then - if test -n "$NM" && test -n "$global_symbol_pipe"; then - dlsyms="${outputname}S.c" - else - $echo "$modename: not configured to extract global symbols from dlpreopened files" 1>&2 - fi - fi - - if test -n "$dlsyms"; then - case $dlsyms in - "") ;; - *.c) - # Discover the nlist of each of the dlfiles. - nlist="$output_objdir/${outputname}.nm" - - $show "$rm $nlist ${nlist}S ${nlist}T" - $run $rm "$nlist" "${nlist}S" "${nlist}T" - - # Parse the name list into a source file. - $show "creating $output_objdir/$dlsyms" - - test -z "$run" && $echo > "$output_objdir/$dlsyms" "\ -/* $dlsyms - symbol resolution table for \`$outputname' dlsym emulation. */ -/* Generated by $PROGRAM - GNU $PACKAGE $VERSION$TIMESTAMP */ - -#ifdef __cplusplus -extern \"C\" { -#endif - -/* Prevent the only kind of declaration conflicts we can make. */ -#define lt_preloaded_symbols some_other_symbol - -/* External symbol declarations for the compiler. */\ -" - - if test "$dlself" = yes; then - $show "generating symbol list for \`$output'" - - test -z "$run" && $echo ': @PROGRAM@ ' > "$nlist" - - # Add our own program objects to the symbol list. - progfiles=`$echo "X$objs$old_deplibs" | $SP2NL | $Xsed -e "$lo2o" | $NL2SP` - for arg in $progfiles; do - $show "extracting global C symbols from \`$arg'" - $run eval "$NM $arg | $global_symbol_pipe >> '$nlist'" - done - - if test -n "$exclude_expsyms"; then - $run eval 'egrep -v " ($exclude_expsyms)$" "$nlist" > "$nlist"T' - $run eval '$mv "$nlist"T "$nlist"' - fi - - if test -n "$export_symbols_regex"; then - $run eval 'egrep -e "$export_symbols_regex" "$nlist" > "$nlist"T' - $run eval '$mv "$nlist"T "$nlist"' - fi - - # Prepare the list of exported symbols - if test -z "$export_symbols"; then - export_symbols="$output_objdir/$output.exp" - $run $rm $export_symbols - $run eval "${SED} -n -e '/^: @PROGRAM@$/d' -e 's/^.* \(.*\)$/\1/p' "'< "$nlist" > "$export_symbols"' - else - $run eval "${SED} -e 's/\([][.*^$]\)/\\\1/g' -e 's/^/ /' -e 's/$/$/'"' < "$export_symbols" > "$output_objdir/$output.exp"' - $run eval 'grep -f "$output_objdir/$output.exp" < "$nlist" > "$nlist"T' - $run eval 'mv "$nlist"T "$nlist"' - fi - fi - - for arg in $dlprefiles; do - $show "extracting global C symbols from \`$arg'" - name=`echo "$arg" | ${SED} -e 's%^.*/%%'` - $run eval 'echo ": $name " >> "$nlist"' - $run eval "$NM $arg | $global_symbol_pipe >> '$nlist'" - done - - if test -z "$run"; then - # Make sure we have at least an empty file. - test -f "$nlist" || : > "$nlist" - - if test -n "$exclude_expsyms"; then - egrep -v " ($exclude_expsyms)$" "$nlist" > "$nlist"T - $mv "$nlist"T "$nlist" - fi - - # Try sorting and uniquifying the output. - if grep -v "^: " < "$nlist" | - if sort -k 3 </dev/null >/dev/null 2>&1; then - sort -k 3 - else - sort +2 - fi | - uniq > "$nlist"S; then - : - else - grep -v "^: " < "$nlist" > "$nlist"S - fi - - if test -f "$nlist"S; then - eval "$global_symbol_to_cdecl"' < "$nlist"S >> "$output_objdir/$dlsyms"' - else - echo '/* NONE */' >> "$output_objdir/$dlsyms" - fi - - $echo >> "$output_objdir/$dlsyms" "\ - -#undef lt_preloaded_symbols - -#if defined (__STDC__) && __STDC__ -# define lt_ptr void * -#else -# define lt_ptr char * -# define const -#endif - -/* The mapping between symbol names and symbols. */ -const struct { - const char *name; - lt_ptr address; -} -lt_preloaded_symbols[] = -{\ -" - - eval "$global_symbol_to_c_name_address" < "$nlist" >> "$output_objdir/$dlsyms" - - $echo >> "$output_objdir/$dlsyms" "\ - {0, (lt_ptr) 0} -}; - -/* This works around a problem in FreeBSD linker */ -#ifdef FREEBSD_WORKAROUND -static const void *lt_preloaded_setup() { - return lt_preloaded_symbols; -} -#endif - -#ifdef __cplusplus -} -#endif\ -" - fi - - pic_flag_for_symtable= - case $host in - # compiling the symbol table file with pic_flag works around - # a FreeBSD bug that causes programs to crash when -lm is - # linked before any other PIC object. But we must not use - # pic_flag when linking with -static. The problem exists in - # FreeBSD 2.2.6 and is fixed in FreeBSD 3.1. - *-*-freebsd2*|*-*-freebsd3.0*|*-*-freebsdelf3.0*) - case "$compile_command " in - *" -static "*) ;; - *) pic_flag_for_symtable=" $pic_flag -DPIC -DFREEBSD_WORKAROUND";; - esac;; - *-*-hpux*) - case "$compile_command " in - *" -static "*) ;; - *) pic_flag_for_symtable=" $pic_flag -DPIC";; - esac - esac - - # Now compile the dynamic symbol file. - $show "(cd $output_objdir && $CC -c$no_builtin_flag$pic_flag_for_symtable \"$dlsyms\")" - $run eval '(cd $output_objdir && $CC -c$no_builtin_flag$pic_flag_for_symtable "$dlsyms")' || exit $? - - # Clean up the generated files. - $show "$rm $output_objdir/$dlsyms $nlist ${nlist}S ${nlist}T" - $run $rm "$output_objdir/$dlsyms" "$nlist" "${nlist}S" "${nlist}T" - - # Transform the symbol file into the correct name. - compile_command=`$echo "X$compile_command" | $Xsed -e "s%@SYMFILE@%$output_objdir/${outputname}S.${objext}%"` - finalize_command=`$echo "X$finalize_command" | $Xsed -e "s%@SYMFILE@%$output_objdir/${outputname}S.${objext}%"` - ;; - *) - $echo "$modename: unknown suffix for \`$dlsyms'" 1>&2 - exit 1 - ;; - esac - else - # We keep going just in case the user didn't refer to - # lt_preloaded_symbols. The linker will fail if global_symbol_pipe - # really was required. - - # Nullify the symbol file. - compile_command=`$echo "X$compile_command" | $Xsed -e "s% @SYMFILE@%%"` - finalize_command=`$echo "X$finalize_command" | $Xsed -e "s% @SYMFILE@%%"` - fi - - if test $need_relink = no || test "$build_libtool_libs" != yes; then - # Replace the output file specification. - compile_command=`$echo "X$compile_command" | $Xsed -e 's%@OUTPUT@%'"$output"'%g'` - link_command="$compile_command$compile_rpath" - - # We have no uninstalled library dependencies, so finalize right now. - $show "$link_command" - $run eval "$link_command" - status=$? - - # Delete the generated files. - if test -n "$dlsyms"; then - $show "$rm $output_objdir/${outputname}S.${objext}" - $run $rm "$output_objdir/${outputname}S.${objext}" - fi - - exit $status - fi - - if test -n "$shlibpath_var"; then - # We should set the shlibpath_var - rpath= - for dir in $temp_rpath; do - case $dir in - [\\/]* | [A-Za-z]:[\\/]*) - # Absolute path. - rpath="$rpath$dir:" - ;; - *) - # Relative path: add a thisdir entry. - rpath="$rpath\$thisdir/$dir:" - ;; - esac - done - temp_rpath="$rpath" - fi - - if test -n "$compile_shlibpath$finalize_shlibpath"; then - compile_command="$shlibpath_var=\"$compile_shlibpath$finalize_shlibpath\$$shlibpath_var\" $compile_command" - fi - if test -n "$finalize_shlibpath"; then - finalize_command="$shlibpath_var=\"$finalize_shlibpath\$$shlibpath_var\" $finalize_command" - fi - - compile_var= - finalize_var= - if test -n "$runpath_var"; then - if test -n "$perm_rpath"; then - # We should set the runpath_var. - rpath= - for dir in $perm_rpath; do - rpath="$rpath$dir:" - done - compile_var="$runpath_var=\"$rpath\$$runpath_var\" " - fi - if test -n "$finalize_perm_rpath"; then - # We should set the runpath_var. - rpath= - for dir in $finalize_perm_rpath; do - rpath="$rpath$dir:" - done - finalize_var="$runpath_var=\"$rpath\$$runpath_var\" " - fi - fi - - if test "$no_install" = yes; then - # We don't need to create a wrapper script. - link_command="$compile_var$compile_command$compile_rpath" - # Replace the output file specification. - link_command=`$echo "X$link_command" | $Xsed -e 's%@OUTPUT@%'"$output"'%g'` - # Delete the old output file. - $run $rm $output - # Link the executable and exit - $show "$link_command" - $run eval "$link_command" || exit $? - exit 0 - fi - - if test "$hardcode_action" = relink; then - # Fast installation is not supported - link_command="$compile_var$compile_command$compile_rpath" - relink_command="$finalize_var$finalize_command$finalize_rpath" - - $echo "$modename: warning: this platform does not like uninstalled shared libraries" 1>&2 - $echo "$modename: \`$output' will be relinked during installation" 1>&2 - else - if test "$fast_install" != no; then - link_command="$finalize_var$compile_command$finalize_rpath" - if test "$fast_install" = yes; then - relink_command=`$echo "X$compile_var$compile_command$compile_rpath" | $Xsed -e 's%@OUTPUT@%\$progdir/\$file%g'` - else - # fast_install is set to needless - relink_command= - fi - else - link_command="$compile_var$compile_command$compile_rpath" - relink_command="$finalize_var$finalize_command$finalize_rpath" - fi - fi - - # Replace the output file specification. - link_command=`$echo "X$link_command" | $Xsed -e 's%@OUTPUT@%'"$output_objdir/$outputname"'%g'` - - # Delete the old output files. - $run $rm $output $output_objdir/$outputname $output_objdir/lt-$outputname - - $show "$link_command" - $run eval "$link_command" || exit $? - - # Now create the wrapper script. - $show "creating $output" - - # Quote the relink command for shipping. - if test -n "$relink_command"; then - # Preserve any variables that may affect compiler behavior - for var in $variables_saved_for_relink; do - if eval test -z \"\${$var+set}\"; then - relink_command="{ test -z \"\${$var+set}\" || unset $var || { $var=; export $var; }; }; $relink_command" - elif eval var_value=\$$var; test -z "$var_value"; then - relink_command="$var=; export $var; $relink_command" - else - var_value=`$echo "X$var_value" | $Xsed -e "$sed_quote_subst"` - relink_command="$var=\"$var_value\"; export $var; $relink_command" - fi - done - relink_command="(cd `pwd`; $relink_command)" - relink_command=`$echo "X$relink_command" | $Xsed -e "$sed_quote_subst"` - fi - - # Quote $echo for shipping. - if test "X$echo" = "X$SHELL $0 --fallback-echo"; then - case $0 in - [\\/]* | [A-Za-z]:[\\/]*) qecho="$SHELL $0 --fallback-echo";; - *) qecho="$SHELL `pwd`/$0 --fallback-echo";; - esac - qecho=`$echo "X$qecho" | $Xsed -e "$sed_quote_subst"` - else - qecho=`$echo "X$echo" | $Xsed -e "$sed_quote_subst"` - fi - - # Only actually do things if our run command is non-null. - if test -z "$run"; then - # win32 will think the script is a binary if it has - # a .exe suffix, so we strip it off here. - case $output in - *.exe) output=`echo $output|${SED} 's,.exe$,,'` ;; - esac - # test for cygwin because mv fails w/o .exe extensions - case $host in - *cygwin*) exeext=.exe ;; - *) exeext= ;; - esac - $rm $output - trap "$rm $output; exit 1" 1 2 15 - - $echo > $output "\ -#! $SHELL - -# $output - temporary wrapper script for $objdir/$outputname -# Generated by $PROGRAM - GNU $PACKAGE $VERSION$TIMESTAMP -# -# The $output program cannot be directly executed until all the libtool -# libraries that it depends on are installed. -# -# This wrapper script should never be moved out of the build directory. -# If it is, it will not operate correctly. - -# Sed substitution that helps us do robust quoting. It backslashifies -# metacharacters that are still active within double-quoted strings. -Xsed="${SED}"' -e 1s/^X//' -sed_quote_subst='$sed_quote_subst' - -# The HP-UX ksh and POSIX shell print the target directory to stdout -# if CDPATH is set. -if test \"\${CDPATH+set}\" = set; then CDPATH=:; export CDPATH; fi - -relink_command=\"$relink_command\" - -# This environment variable determines our operation mode. -if test \"\$libtool_install_magic\" = \"$magic\"; then - # install mode needs the following variable: - notinst_deplibs='$notinst_deplibs' -else - # When we are sourced in execute mode, \$file and \$echo are already set. - if test \"\$libtool_execute_magic\" != \"$magic\"; then - echo=\"$qecho\" - file=\"\$0\" - # Make sure echo works. - if test \"X\$1\" = X--no-reexec; then - # Discard the --no-reexec flag, and continue. - shift - elif test \"X\`(\$echo '\t') 2>/dev/null\`\" = 'X\t'; then - # Yippee, \$echo works! - : - else - # Restart under the correct shell, and then maybe \$echo will work. - exec $SHELL \"\$0\" --no-reexec \${1+\"\$@\"} - fi - fi\ -" - $echo >> $output "\ - - # Find the directory that this script lives in. - thisdir=\`\$echo \"X\$file\" | \$Xsed -e 's%/[^/]*$%%'\` - test \"x\$thisdir\" = \"x\$file\" && thisdir=. - - # Follow symbolic links until we get to the real thisdir. - file=\`ls -ld \"\$file\" | ${SED} -n 's/.*-> //p'\` - while test -n \"\$file\"; do - destdir=\`\$echo \"X\$file\" | \$Xsed -e 's%/[^/]*\$%%'\` - - # If there was a directory component, then change thisdir. - if test \"x\$destdir\" != \"x\$file\"; then - case \"\$destdir\" in - [\\\\/]* | [A-Za-z]:[\\\\/]*) thisdir=\"\$destdir\" ;; - *) thisdir=\"\$thisdir/\$destdir\" ;; - esac - fi - - file=\`\$echo \"X\$file\" | \$Xsed -e 's%^.*/%%'\` - file=\`ls -ld \"\$thisdir/\$file\" | ${SED} -n 's/.*-> //p'\` - done - - # Try to get the absolute directory name. - absdir=\`cd \"\$thisdir\" && pwd\` - test -n \"\$absdir\" && thisdir=\"\$absdir\" -" - - if test "$fast_install" = yes; then - echo >> $output "\ - program=lt-'$outputname'$exeext - progdir=\"\$thisdir/$objdir\" - - if test ! -f \"\$progdir/\$program\" || \\ - { file=\`ls -1dt \"\$progdir/\$program\" \"\$progdir/../\$program\" 2>/dev/null | ${SED} 1q\`; \\ - test \"X\$file\" != \"X\$progdir/\$program\"; }; then - - file=\"\$\$-\$program\" - - if test ! -d \"\$progdir\"; then - $mkdir \"\$progdir\" - else - $rm \"\$progdir/\$file\" - fi" - - echo >> $output "\ - - # relink executable if necessary - if test -n \"\$relink_command\"; then - if relink_command_output=\`eval \$relink_command 2>&1\`; then : - else - $echo \"\$relink_command_output\" >&2 - $rm \"\$progdir/\$file\" - exit 1 - fi - fi - - $mv \"\$progdir/\$file\" \"\$progdir/\$program\" 2>/dev/null || - { $rm \"\$progdir/\$program\"; - $mv \"\$progdir/\$file\" \"\$progdir/\$program\"; } - $rm \"\$progdir/\$file\" - fi" - else - echo >> $output "\ - program='$outputname' - progdir=\"\$thisdir/$objdir\" -" - fi - - echo >> $output "\ - - if test -f \"\$progdir/\$program\"; then" - - # Export our shlibpath_var if we have one. - if test "$shlibpath_overrides_runpath" = yes && test -n "$shlibpath_var" && test -n "$temp_rpath"; then - $echo >> $output "\ - # Add our own library path to $shlibpath_var - $shlibpath_var=\"$temp_rpath\$$shlibpath_var\" - - # Some systems cannot cope with colon-terminated $shlibpath_var - # The second colon is a workaround for a bug in BeOS R4 ${SED} - $shlibpath_var=\`\$echo \"X\$$shlibpath_var\" | \$Xsed -e 's/::*\$//'\` - - export $shlibpath_var -" - fi - - # fixup the dll searchpath if we need to. - if test -n "$dllsearchpath"; then - $echo >> $output "\ - # Add the dll search path components to the executable PATH - PATH=$dllsearchpath:\$PATH -" - fi - - $echo >> $output "\ - if test \"\$libtool_execute_magic\" != \"$magic\"; then - # Run the actual program with our arguments. -" - case $host in - # win32 systems need to use the prog path for dll - # lookup to work - *-*-cygwin* | *-*-pw32*) - $echo >> $output "\ - exec \$progdir/\$program \${1+\"\$@\"} -" - ;; - - # Backslashes separate directories on plain windows - *-*-mingw | *-*-os2*) - $echo >> $output "\ - exec \$progdir\\\\\$program \${1+\"\$@\"} -" - ;; - - *) - $echo >> $output "\ - # Export the path to the program. - PATH=\"\$progdir:\$PATH\" - export PATH - - exec \$program \${1+\"\$@\"} -" - ;; - esac - $echo >> $output "\ - \$echo \"\$0: cannot exec \$program \${1+\"\$@\"}\" - exit 1 - fi - else - # The program doesn't exist. - \$echo \"\$0: error: \$progdir/\$program does not exist\" 1>&2 - \$echo \"This script is just a wrapper for \$program.\" 1>&2 - echo \"See the $PACKAGE documentation for more information.\" 1>&2 - exit 1 - fi -fi\ -" - chmod +x $output - fi - exit 0 - ;; - esac - - # See if we need to build an old-fashioned archive. - for oldlib in $oldlibs; do - - if test "$build_libtool_libs" = convenience; then - oldobjs="$libobjs_save" - addlibs="$convenience" - build_libtool_libs=no - else - if test "$build_libtool_libs" = module; then - oldobjs="$libobjs_save" - build_libtool_libs=no - else - oldobjs="$objs$old_deplibs "`$echo "X$libobjs_save" | $SP2NL | $Xsed -e '/\.'${libext}'$/d' -e '/\.lib$/d' -e "$lo2o" | $NL2SP` - fi - addlibs="$old_convenience" - fi - - if test -n "$addlibs"; then - gentop="$output_objdir/${outputname}x" - $show "${rm}r $gentop" - $run ${rm}r "$gentop" - $show "mkdir $gentop" - $run mkdir "$gentop" - status=$? - if test $status -ne 0 && test ! -d "$gentop"; then - exit $status - fi - generated="$generated $gentop" - - # Add in members from convenience archives. - for xlib in $addlibs; do - # Extract the objects. - case $xlib in - [\\/]* | [A-Za-z]:[\\/]*) xabs="$xlib" ;; - *) xabs=`pwd`"/$xlib" ;; - esac - xlib=`$echo "X$xlib" | $Xsed -e 's%^.*/%%'` - xdir="$gentop/$xlib" - - $show "${rm}r $xdir" - $run ${rm}r "$xdir" - $show "mkdir $xdir" - $run mkdir "$xdir" - status=$? - if test $status -ne 0 && test ! -d "$xdir"; then - exit $status - fi - $show "(cd $xdir && $AR x $xabs)" - $run eval "(cd \$xdir && $AR x \$xabs)" || exit $? - - oldobjs="$oldobjs "`find $xdir -name \*.${objext} -print -o -name \*.lo -print | $NL2SP` - done - fi - - # Do each command in the archive commands. - if test -n "$old_archive_from_new_cmds" && test "$build_libtool_libs" = yes; then - eval cmds=\"$old_archive_from_new_cmds\" - else - # Ensure that we have .o objects in place in case we decided - # not to build a shared library, and have fallen back to building - # static libs even though --disable-static was passed! - for oldobj in $oldobjs; do - if test ! -f $oldobj; then - xdir=`$echo "X$oldobj" | $Xsed -e 's%/[^/]*$%%'` - if test "X$xdir" = "X$oldobj"; then - xdir="." - else - xdir="$xdir" - fi - baseobj=`$echo "X$oldobj" | $Xsed -e 's%^.*/%%'` - obj=`$echo "X$baseobj" | $Xsed -e "$o2lo"` - $show "(cd $xdir && ${LN_S} $obj $baseobj)" - $run eval '(cd $xdir && ${LN_S} $obj $baseobj)' || exit $? - fi - done - - eval cmds=\"$old_archive_cmds\" - fi - save_ifs="$IFS"; IFS='~' - for cmd in $cmds; do - IFS="$save_ifs" - $show "$cmd" - $run eval "$cmd" || exit $? - done - IFS="$save_ifs" - done - - if test -n "$generated"; then - $show "${rm}r$generated" - $run ${rm}r$generated - fi - - # Now create the libtool archive. - case $output in - *.la) - old_library= - test "$build_old_libs" = yes && old_library="$libname.$libext" - $show "creating $output" - - # Preserve any variables that may affect compiler behavior - for var in $variables_saved_for_relink; do - if eval test -z \"\${$var+set}\"; then - relink_command="{ test -z \"\${$var+set}\" || unset $var || { $var=; export $var; }; }; $relink_command" - elif eval var_value=\$$var; test -z "$var_value"; then - relink_command="$var=; export $var; $relink_command" - else - var_value=`$echo "X$var_value" | $Xsed -e "$sed_quote_subst"` - relink_command="$var=\"$var_value\"; export $var; $relink_command" - fi - done - # Quote the link command for shipping. - relink_command="(cd `pwd`; $SHELL $0 --mode=relink $libtool_args)" - relink_command=`$echo "X$relink_command" | $Xsed -e "$sed_quote_subst"` - - # Only create the output if not a dry run. - if test -z "$run"; then - for installed in no yes; do - if test "$installed" = yes; then - if test -z "$install_libdir"; then - break - fi - output="$output_objdir/$outputname"i - # Replace all uninstalled libtool libraries with the installed ones - newdependency_libs= - for deplib in $dependency_libs; do - case $deplib in - *.la) - name=`$echo "X$deplib" | $Xsed -e 's%^.*/%%'` - eval libdir=`${SED} -n -e 's/^libdir=\(.*\)$/\1/p' $deplib` - if test -z "$libdir"; then - $echo "$modename: \`$deplib' is not a valid libtool archive" 1>&2 - exit 1 - fi - newdependency_libs="$newdependency_libs $libdir/$name" - ;; - *) newdependency_libs="$newdependency_libs $deplib" ;; - esac - done - dependency_libs="$newdependency_libs" - newdlfiles= - for lib in $dlfiles; do - name=`$echo "X$lib" | $Xsed -e 's%^.*/%%'` - eval libdir=`${SED} -n -e 's/^libdir=\(.*\)$/\1/p' $lib` - if test -z "$libdir"; then - $echo "$modename: \`$lib' is not a valid libtool archive" 1>&2 - exit 1 - fi - newdlfiles="$newdlfiles $libdir/$name" - done - dlfiles="$newdlfiles" - newdlprefiles= - for lib in $dlprefiles; do - name=`$echo "X$lib" | $Xsed -e 's%^.*/%%'` - eval libdir=`${SED} -n -e 's/^libdir=\(.*\)$/\1/p' $lib` - if test -z "$libdir"; then - $echo "$modename: \`$lib' is not a valid libtool archive" 1>&2 - exit 1 - fi - newdlprefiles="$newdlprefiles $libdir/$name" - done - dlprefiles="$newdlprefiles" - fi - $rm $output - # place dlname in correct position for cygwin - tdlname=$dlname - case $host,$output,$installed,$module,$dlname in - *cygwin*,*lai,yes,no,*.dll) tdlname=../bin/$dlname ;; - esac - $echo > $output "\ -# $outputname - a libtool library file -# Generated by $PROGRAM - GNU $PACKAGE $VERSION$TIMESTAMP -# -# Please DO NOT delete this file! -# It is necessary for linking the library. - -# The name that we can dlopen(3). -dlname='$tdlname' - -# Names of this library. -library_names='$library_names' - -# The name of the static archive. -old_library='$old_library' - -# Libraries that this one depends upon. -dependency_libs='$dependency_libs' - -# Version information for $libname. -current=$current -age=$age -revision=$revision - -# Is this an already installed library? -installed=$installed - -# Files to dlopen/dlpreopen -dlopen='$dlfiles' -dlpreopen='$dlprefiles' - -# Directory that this library needs to be installed in: -libdir='$install_libdir'" - if test "$installed" = no && test $need_relink = yes; then - $echo >> $output "\ -relink_command=\"$relink_command\"" - fi - done - fi - - # Do a symbolic link so that the libtool archive can be found in - # LD_LIBRARY_PATH before the program is installed. - $show "(cd $output_objdir && $rm $outputname && $LN_S ../$outputname $outputname)" - $run eval '(cd $output_objdir && $rm $outputname && $LN_S ../$outputname $outputname)' || exit $? - ;; - esac - exit 0 - ;; - - # libtool install mode - install) - modename="$modename: install" - - # There may be an optional sh(1) argument at the beginning of - # install_prog (especially on Windows NT). - if test "$nonopt" = "$SHELL" || test "$nonopt" = /bin/sh || - # Allow the use of GNU shtool's install command. - $echo "X$nonopt" | $Xsed | grep shtool > /dev/null; then - # Aesthetically quote it. - arg=`$echo "X$nonopt" | $Xsed -e "$sed_quote_subst"` - case $arg in - *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*) - arg="\"$arg\"" - ;; - esac - install_prog="$arg " - arg="$1" - shift - else - install_prog= - arg="$nonopt" - fi - - # The real first argument should be the name of the installation program. - # Aesthetically quote it. - arg=`$echo "X$arg" | $Xsed -e "$sed_quote_subst"` - case $arg in - *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*) - arg="\"$arg\"" - ;; - esac - install_prog="$install_prog$arg" - - # We need to accept at least all the BSD install flags. - dest= - files= - opts= - prev= - install_type= - isdir=no - stripme= - for arg - do - if test -n "$dest"; then - files="$files $dest" - dest="$arg" - continue - fi - - case $arg in - -d) isdir=yes ;; - -f) prev="-f" ;; - -g) prev="-g" ;; - -m) prev="-m" ;; - -o) prev="-o" ;; - -s) - stripme=" -s" - continue - ;; - -*) ;; - - *) - # If the previous option needed an argument, then skip it. - if test -n "$prev"; then - prev= - else - dest="$arg" - continue - fi - ;; - esac - - # Aesthetically quote the argument. - arg=`$echo "X$arg" | $Xsed -e "$sed_quote_subst"` - case $arg in - *[\[\~\#\^\&\*\(\)\{\}\|\;\<\>\?\'\ \ ]*|*]*) - arg="\"$arg\"" - ;; - esac - install_prog="$install_prog $arg" - done - - if test -z "$install_prog"; then - $echo "$modename: you must specify an install program" 1>&2 - $echo "$help" 1>&2 - exit 1 - fi - - if test -n "$prev"; then - $echo "$modename: the \`$prev' option requires an argument" 1>&2 - $echo "$help" 1>&2 - exit 1 - fi - - if test -z "$files"; then - if test -z "$dest"; then - $echo "$modename: no file or destination specified" 1>&2 - else - $echo "$modename: you must specify a destination" 1>&2 - fi - $echo "$help" 1>&2 - exit 1 - fi - - # Strip any trailing slash from the destination. - dest=`$echo "X$dest" | $Xsed -e 's%/$%%'` - - # Check to see that the destination is a directory. - test -d "$dest" && isdir=yes - if test "$isdir" = yes; then - destdir="$dest" - destname= - else - destdir=`$echo "X$dest" | $Xsed -e 's%/[^/]*$%%'` - test "X$destdir" = "X$dest" && destdir=. - destname=`$echo "X$dest" | $Xsed -e 's%^.*/%%'` - - # Not a directory, so check to see that there is only one file specified. - set dummy $files - if test $# -gt 2; then - $echo "$modename: \`$dest' is not a directory" 1>&2 - $echo "$help" 1>&2 - exit 1 - fi - fi - case $destdir in - [\\/]* | [A-Za-z]:[\\/]*) ;; - *) - for file in $files; do - case $file in - *.lo) ;; - *) - $echo "$modename: \`$destdir' must be an absolute directory name" 1>&2 - $echo "$help" 1>&2 - exit 1 - ;; - esac - done - ;; - esac - - # This variable tells wrapper scripts just to set variables rather - # than running their programs. - libtool_install_magic="$magic" - - staticlibs= - future_libdirs= - current_libdirs= - for file in $files; do - - # Do each installation. - case $file in - *.$libext) - # Do the static libraries later. - staticlibs="$staticlibs $file" - ;; - - *.la) - # Check to see that this really is a libtool archive. - if (${SED} -e '2q' $file | egrep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then : - else - $echo "$modename: \`$file' is not a valid libtool archive" 1>&2 - $echo "$help" 1>&2 - exit 1 - fi - - library_names= - old_library= - relink_command= - # If there is no directory component, then add one. - case $file in - */* | *\\*) . $file ;; - *) . ./$file ;; - esac - - # Add the libdir to current_libdirs if it is the destination. - if test "X$destdir" = "X$libdir"; then - case "$current_libdirs " in - *" $libdir "*) ;; - *) current_libdirs="$current_libdirs $libdir" ;; - esac - else - # Note the libdir as a future libdir. - case "$future_libdirs " in - *" $libdir "*) ;; - *) future_libdirs="$future_libdirs $libdir" ;; - esac - fi - - dir=`$echo "X$file" | $Xsed -e 's%/[^/]*$%%'`/ - test "X$dir" = "X$file/" && dir= - dir="$dir$objdir" - - if test -n "$relink_command"; then - $echo "$modename: warning: relinking \`$file'" 1>&2 - $show "$relink_command" - if $run eval "$relink_command"; then : - else - $echo "$modename: error: relink \`$file' with the above command before installing it" 1>&2 - continue - fi - fi - - # See the names of the shared library. - set dummy $library_names - if test -n "$2"; then - realname="$2" - shift - shift - - srcname="$realname" - test -n "$relink_command" && srcname="$realname"T - - # Install the shared library and build the symlinks. - $show "$install_prog $dir/$srcname $destdir/$realname" - $run eval "$install_prog $dir/$srcname $destdir/$realname" || exit $? - if test -n "$stripme" && test -n "$striplib"; then - $show "$striplib $destdir/$realname" - $run eval "$striplib $destdir/$realname" || exit $? - fi - - if test $# -gt 0; then - # Delete the old symlinks, and create new ones. - for linkname - do - if test "$linkname" != "$realname"; then - $show "(cd $destdir && $rm $linkname && $LN_S $realname $linkname)" - $run eval "(cd $destdir && $rm $linkname && $LN_S $realname $linkname)" - fi - done - fi - - # Do each command in the postinstall commands. - lib="$destdir/$realname" - eval cmds=\"$postinstall_cmds\" - save_ifs="$IFS"; IFS='~' - for cmd in $cmds; do - IFS="$save_ifs" - $show "$cmd" - $run eval "$cmd" || exit $? - done - IFS="$save_ifs" - fi - - # Install the pseudo-library for information purposes. - name=`$echo "X$file" | $Xsed -e 's%^.*/%%'` - instname="$dir/$name"i - $show "$install_prog $instname $destdir/$name" - $run eval "$install_prog $instname $destdir/$name" || exit $? - - # Maybe install the static library, too. - test -n "$old_library" && staticlibs="$staticlibs $dir/$old_library" - ;; - - *.lo) - # Install (i.e. copy) a libtool object. - - # Figure out destination file name, if it wasn't already specified. - if test -n "$destname"; then - destfile="$destdir/$destname" - else - destfile=`$echo "X$file" | $Xsed -e 's%^.*/%%'` - destfile="$destdir/$destfile" - fi - - # Deduce the name of the destination old-style object file. - case $destfile in - *.lo) - staticdest=`$echo "X$destfile" | $Xsed -e "$lo2o"` - ;; - *.$objext) - staticdest="$destfile" - destfile= - ;; - *) - $echo "$modename: cannot copy a libtool object to \`$destfile'" 1>&2 - $echo "$help" 1>&2 - exit 1 - ;; - esac - - # Install the libtool object if requested. - if test -n "$destfile"; then - $show "$install_prog $file $destfile" - $run eval "$install_prog $file $destfile" || exit $? - fi - - # Install the old object if enabled. - if test "$build_old_libs" = yes; then - # Deduce the name of the old-style object file. - staticobj=`$echo "X$file" | $Xsed -e "$lo2o"` - - $show "$install_prog $staticobj $staticdest" - $run eval "$install_prog \$staticobj \$staticdest" || exit $? - fi - exit 0 - ;; - - *) - # Figure out destination file name, if it wasn't already specified. - if test -n "$destname"; then - destfile="$destdir/$destname" - else - destfile=`$echo "X$file" | $Xsed -e 's%^.*/%%'` - destfile="$destdir/$destfile" - fi - - # Do a test to see if this is really a libtool program. - case $host in - *cygwin*|*mingw*) - wrapper=`echo $file | ${SED} -e 's,.exe$,,'` - ;; - *) - wrapper=$file - ;; - esac - if (${SED} -e '4q' $wrapper | egrep "^# Generated by .*$PACKAGE")>/dev/null 2>&1; then - notinst_deplibs= - relink_command= - - # If there is no directory component, then add one. - case $file in - */* | *\\*) . $wrapper ;; - *) . ./$wrapper ;; - esac - - # Check the variables that should have been set. - if test -z "$notinst_deplibs"; then - $echo "$modename: invalid libtool wrapper script \`$wrapper'" 1>&2 - exit 1 - fi - - finalize=yes - for lib in $notinst_deplibs; do - # Check to see that each library is installed. - libdir= - if test -f "$lib"; then - # If there is no directory component, then add one. - case $lib in - */* | *\\*) . $lib ;; - *) . ./$lib ;; - esac - fi - libfile="$libdir/"`$echo "X$lib" | $Xsed -e 's%^.*/%%g'` ### testsuite: skip nested quoting test - if test -n "$libdir" && test ! -f "$libfile"; then - $echo "$modename: warning: \`$lib' has not been installed in \`$libdir'" 1>&2 - finalize=no - fi - done - - relink_command= - # If there is no directory component, then add one. - case $file in - */* | *\\*) . $wrapper ;; - *) . ./$wrapper ;; - esac - - outputname= - if test "$fast_install" = no && test -n "$relink_command"; then - if test "$finalize" = yes && test -z "$run"; then - tmpdir="/tmp" - test -n "$TMPDIR" && tmpdir="$TMPDIR" - tmpdir="$tmpdir/libtool-$$" - if $mkdir -p "$tmpdir" && chmod 700 "$tmpdir"; then : - else - $echo "$modename: error: cannot create temporary directory \`$tmpdir'" 1>&2 - continue - fi - file=`$echo "X$file" | $Xsed -e 's%^.*/%%'` - outputname="$tmpdir/$file" - # Replace the output file specification. - relink_command=`$echo "X$relink_command" | $Xsed -e 's%@OUTPUT@%'"$outputname"'%g'` - - $show "$relink_command" - if $run eval "$relink_command"; then : - else - $echo "$modename: error: relink \`$file' with the above command before installing it" 1>&2 - ${rm}r "$tmpdir" - continue - fi - file="$outputname" - else - $echo "$modename: warning: cannot relink \`$file'" 1>&2 - fi - else - # Install the binary that we compiled earlier. - file=`$echo "X$file" | $Xsed -e "s%\([^/]*\)$%$objdir/\1%"` - fi - fi - - # remove .exe since cygwin /usr/bin/install will append another - # one anyways - case $install_prog,$host in - /usr/bin/install*,*cygwin*) - case $file:$destfile in - *.exe:*.exe) - # this is ok - ;; - *.exe:*) - destfile=$destfile.exe - ;; - *:*.exe) - destfile=`echo $destfile | ${SED} -e 's,.exe$,,'` - ;; - esac - ;; - esac - $show "$install_prog$stripme $file $destfile" - $run eval "$install_prog\$stripme \$file \$destfile" || exit $? - test -n "$outputname" && ${rm}r "$tmpdir" - ;; - esac - done - - for file in $staticlibs; do - name=`$echo "X$file" | $Xsed -e 's%^.*/%%'` - - # Set up the ranlib parameters. - oldlib="$destdir/$name" - - $show "$install_prog $file $oldlib" - $run eval "$install_prog \$file \$oldlib" || exit $? - - if test -n "$stripme" && test -n "$striplib"; then - $show "$old_striplib $oldlib" - $run eval "$old_striplib $oldlib" || exit $? - fi - - # Do each command in the postinstall commands. - eval cmds=\"$old_postinstall_cmds\" - save_ifs="$IFS"; IFS='~' - for cmd in $cmds; do - IFS="$save_ifs" - $show "$cmd" - $run eval "$cmd" || exit $? - done - IFS="$save_ifs" - done - - if test -n "$future_libdirs"; then - $echo "$modename: warning: remember to run \`$progname --finish$future_libdirs'" 1>&2 - fi - - if test -n "$current_libdirs"; then - # Maybe just do a dry run. - test -n "$run" && current_libdirs=" -n$current_libdirs" - exec_cmd='$SHELL $0 --finish$current_libdirs' - else - exit 0 - fi - ;; - - # libtool finish mode - finish) - modename="$modename: finish" - libdirs="$nonopt" - admincmds= - - if test -n "$finish_cmds$finish_eval" && test -n "$libdirs"; then - for dir - do - libdirs="$libdirs $dir" - done - - for libdir in $libdirs; do - if test -n "$finish_cmds"; then - # Do each command in the finish commands. - eval cmds=\"$finish_cmds\" - save_ifs="$IFS"; IFS='~' - for cmd in $cmds; do - IFS="$save_ifs" - $show "$cmd" - $run eval "$cmd" || admincmds="$admincmds - $cmd" - done - IFS="$save_ifs" - fi - if test -n "$finish_eval"; then - # Do the single finish_eval. - eval cmds=\"$finish_eval\" - $run eval "$cmds" || admincmds="$admincmds - $cmds" - fi - done - fi - - # Exit here if they wanted silent mode. - test "$show" = ":" && exit 0 - - echo "----------------------------------------------------------------------" - echo "Libraries have been installed in:" - for libdir in $libdirs; do - echo " $libdir" - done - echo - echo "If you ever happen to want to link against installed libraries" - echo "in a given directory, LIBDIR, you must either use libtool, and" - echo "specify the full pathname of the library, or use the \`-LLIBDIR'" - echo "flag during linking and do at least one of the following:" - if test -n "$shlibpath_var"; then - echo " - add LIBDIR to the \`$shlibpath_var' environment variable" - echo " during execution" - fi - if test -n "$runpath_var"; then - echo " - add LIBDIR to the \`$runpath_var' environment variable" - echo " during linking" - fi - if test -n "$hardcode_libdir_flag_spec"; then - libdir=LIBDIR - eval flag=\"$hardcode_libdir_flag_spec\" - - echo " - use the \`$flag' linker flag" - fi - if test -n "$admincmds"; then - echo " - have your system administrator run these commands:$admincmds" - fi - if test -f /etc/ld.so.conf; then - echo " - have your system administrator add LIBDIR to \`/etc/ld.so.conf'" - fi - echo - echo "See any operating system documentation about shared libraries for" - echo "more information, such as the ld(1) and ld.so(8) manual pages." - echo "----------------------------------------------------------------------" - exit 0 - ;; - - # libtool execute mode - execute) - modename="$modename: execute" - - # The first argument is the command name. - cmd="$nonopt" - if test -z "$cmd"; then - $echo "$modename: you must specify a COMMAND" 1>&2 - $echo "$help" - exit 1 - fi - - # Handle -dlopen flags immediately. - for file in $execute_dlfiles; do - if test ! -f "$file"; then - $echo "$modename: \`$file' is not a file" 1>&2 - $echo "$help" 1>&2 - exit 1 - fi - - dir= - case $file in - *.la) - # Check to see that this really is a libtool archive. - if (${SED} -e '2q' $file | egrep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then : - else - $echo "$modename: \`$lib' is not a valid libtool archive" 1>&2 - $echo "$help" 1>&2 - exit 1 - fi - - # Read the libtool library. - dlname= - library_names= - - # If there is no directory component, then add one. - case $file in - */* | *\\*) . $file ;; - *) . ./$file ;; - esac - - # Skip this library if it cannot be dlopened. - if test -z "$dlname"; then - # Warn if it was a shared library. - test -n "$library_names" && $echo "$modename: warning: \`$file' was not linked with \`-export-dynamic'" - continue - fi - - dir=`$echo "X$file" | $Xsed -e 's%/[^/]*$%%'` - test "X$dir" = "X$file" && dir=. - - if test -f "$dir/$objdir/$dlname"; then - dir="$dir/$objdir" - else - $echo "$modename: cannot find \`$dlname' in \`$dir' or \`$dir/$objdir'" 1>&2 - exit 1 - fi - ;; - - *.lo) - # Just add the directory containing the .lo file. - dir=`$echo "X$file" | $Xsed -e 's%/[^/]*$%%'` - test "X$dir" = "X$file" && dir=. - ;; - - *) - $echo "$modename: warning \`-dlopen' is ignored for non-libtool libraries and objects" 1>&2 - continue - ;; - esac - - # Get the absolute pathname. - absdir=`cd "$dir" && pwd` - test -n "$absdir" && dir="$absdir" - - # Now add the directory to shlibpath_var. - if eval "test -z \"\$$shlibpath_var\""; then - eval "$shlibpath_var=\"\$dir\"" - else - eval "$shlibpath_var=\"\$dir:\$$shlibpath_var\"" - fi - done - - # This variable tells wrapper scripts just to set shlibpath_var - # rather than running their programs. - libtool_execute_magic="$magic" - - # Check if any of the arguments is a wrapper script. - args= - for file - do - case $file in - -*) ;; - *) - # Do a test to see if this is really a libtool program. - if (${SED} -e '4q' $file | egrep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then - # If there is no directory component, then add one. - case $file in - */* | *\\*) . $file ;; - *) . ./$file ;; - esac - - # Transform arg to wrapped name. - file="$progdir/$program" - fi - ;; - esac - # Quote arguments (to preserve shell metacharacters). - file=`$echo "X$file" | $Xsed -e "$sed_quote_subst"` - args="$args \"$file\"" - done - - if test -z "$run"; then - if test -n "$shlibpath_var"; then - # Export the shlibpath_var. - eval "export $shlibpath_var" - fi - - # Restore saved enviroment variables - if test "${save_LC_ALL+set}" = set; then - LC_ALL="$save_LC_ALL"; export LC_ALL - fi - if test "${save_LANG+set}" = set; then - LANG="$save_LANG"; export LANG - fi - - # Now prepare to actually exec the command. - exec_cmd="\$cmd$args" - else - # Display what would be done. - if test -n "$shlibpath_var"; then - eval "\$echo \"\$shlibpath_var=\$$shlibpath_var\"" - $echo "export $shlibpath_var" - fi - $echo "$cmd$args" - exit 0 - fi - ;; - - # libtool clean and uninstall mode - clean | uninstall) - modename="$modename: $mode" - rm="$nonopt" - files= - rmforce= - exit_status=0 - - # This variable tells wrapper scripts just to set variables rather - # than running their programs. - libtool_install_magic="$magic" - - for arg - do - case $arg in - -f) rm="$rm $arg"; rmforce=yes ;; - -*) rm="$rm $arg" ;; - *) files="$files $arg" ;; - esac - done - - if test -z "$rm"; then - $echo "$modename: you must specify an RM program" 1>&2 - $echo "$help" 1>&2 - exit 1 - fi - - rmdirs= - - for file in $files; do - dir=`$echo "X$file" | $Xsed -e 's%/[^/]*$%%'` - if test "X$dir" = "X$file"; then - dir=. - objdir="$objdir" - else - objdir="$dir/$objdir" - fi - name=`$echo "X$file" | $Xsed -e 's%^.*/%%'` - test $mode = uninstall && objdir="$dir" - - # Remember objdir for removal later, being careful to avoid duplicates - if test $mode = clean; then - case " $rmdirs " in - *" $objdir "*) ;; - *) rmdirs="$rmdirs $objdir" ;; - esac - fi - - # Don't error if the file doesn't exist and rm -f was used. - if (test -L "$file") >/dev/null 2>&1 \ - || (test -h "$file") >/dev/null 2>&1 \ - || test -f "$file"; then - : - elif test -d "$file"; then - exit_status=1 - continue - elif test "$rmforce" = yes; then - continue - fi - - rmfiles="$file" - - case $name in - *.la) - # Possibly a libtool archive, so verify it. - if (${SED} -e '2q' $file | egrep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then - . $dir/$name - - # Delete the libtool libraries and symlinks. - for n in $library_names; do - rmfiles="$rmfiles $objdir/$n" - done - test -n "$old_library" && rmfiles="$rmfiles $objdir/$old_library" - test $mode = clean && rmfiles="$rmfiles $objdir/$name $objdir/${name}i" - - if test $mode = uninstall; then - if test -n "$library_names"; then - # Do each command in the postuninstall commands. - eval cmds=\"$postuninstall_cmds\" - save_ifs="$IFS"; IFS='~' - for cmd in $cmds; do - IFS="$save_ifs" - $show "$cmd" - $run eval "$cmd" - if test $? != 0 && test "$rmforce" != yes; then - exit_status=1 - fi - done - IFS="$save_ifs" - fi - - if test -n "$old_library"; then - # Do each command in the old_postuninstall commands. - eval cmds=\"$old_postuninstall_cmds\" - save_ifs="$IFS"; IFS='~' - for cmd in $cmds; do - IFS="$save_ifs" - $show "$cmd" - $run eval "$cmd" - if test $? != 0 && test "$rmforce" != yes; then - exit_status=1 - fi - done - IFS="$save_ifs" - fi - # FIXME: should reinstall the best remaining shared library. - fi - fi - ;; - - *.lo) - if test "$build_old_libs" = yes; then - oldobj=`$echo "X$name" | $Xsed -e "$lo2o"` - rmfiles="$rmfiles $dir/$oldobj" - fi - ;; - - *) - # Do a test to see if this is a libtool program. - if test $mode = clean && - (${SED} -e '4q' $file | egrep "^# Generated by .*$PACKAGE") >/dev/null 2>&1; then - relink_command= - . $dir/$file - - rmfiles="$rmfiles $objdir/$name $objdir/${name}S.${objext}" - if test "$fast_install" = yes && test -n "$relink_command"; then - rmfiles="$rmfiles $objdir/lt-$name" - fi - fi - ;; - esac - $show "$rm $rmfiles" - $run $rm $rmfiles || exit_status=1 - done - - # Try to remove the ${objdir}s in the directories where we deleted files - for dir in $rmdirs; do - if test -d "$dir"; then - $show "rmdir $dir" - $run rmdir $dir >/dev/null 2>&1 - fi - done - - exit $exit_status - ;; - - "") - $echo "$modename: you must specify a MODE" 1>&2 - $echo "$generic_help" 1>&2 - exit 1 - ;; - esac - - if test -z "$exec_cmd"; then - $echo "$modename: invalid operation mode \`$mode'" 1>&2 - $echo "$generic_help" 1>&2 - exit 1 - fi -fi # test -z "$show_help" - -if test -n "$exec_cmd"; then - eval exec $exec_cmd - exit 1 -fi - -# We need to display help for each of the modes. -case $mode in -"") $echo \ -"Usage: $modename [OPTION]... [MODE-ARG]... - -Provide generalized library-building support services. - - --config show all configuration variables - --debug enable verbose shell tracing --n, --dry-run display commands without modifying any files - --features display basic configuration information and exit - --finish same as \`--mode=finish' - --help display this help message and exit - --mode=MODE use operation mode MODE [default=inferred from MODE-ARGS] - --quiet same as \`--silent' - --silent don't print informational messages - --version print version information - -MODE must be one of the following: - - clean remove files from the build directory - compile compile a source file into a libtool object - execute automatically set library path, then run a program - finish complete the installation of libtool libraries - install install libraries or executables - link create a library or an executable - uninstall remove libraries from an installed directory - -MODE-ARGS vary depending on the MODE. Try \`$modename --help --mode=MODE' for -a more detailed description of MODE." - exit 0 - ;; - -clean) - $echo \ -"Usage: $modename [OPTION]... --mode=clean RM [RM-OPTION]... FILE... - -Remove files from the build directory. - -RM is the name of the program to use to delete files associated with each FILE -(typically \`/bin/rm'). RM-OPTIONS are options (such as \`-f') to be passed -to RM. - -If FILE is a libtool library, object or program, all the files associated -with it are deleted. Otherwise, only FILE itself is deleted using RM." - ;; - -compile) - $echo \ -"Usage: $modename [OPTION]... --mode=compile COMPILE-COMMAND... SOURCEFILE - -Compile a source file into a libtool library object. - -This mode accepts the following additional options: - - -o OUTPUT-FILE set the output file name to OUTPUT-FILE - -prefer-pic try to building PIC objects only - -prefer-non-pic try to building non-PIC objects only - -static always build a \`.o' file suitable for static linking - -COMPILE-COMMAND is a command to be used in creating a \`standard' object file -from the given SOURCEFILE. - -The output file name is determined by removing the directory component from -SOURCEFILE, then substituting the C source code suffix \`.c' with the -library object suffix, \`.lo'." - ;; - -execute) - $echo \ -"Usage: $modename [OPTION]... --mode=execute COMMAND [ARGS]... - -Automatically set library path, then run a program. - -This mode accepts the following additional options: - - -dlopen FILE add the directory containing FILE to the library path - -This mode sets the library path environment variable according to \`-dlopen' -flags. - -If any of the ARGS are libtool executable wrappers, then they are translated -into their corresponding uninstalled binary, and any of their required library -directories are added to the library path. - -Then, COMMAND is executed, with ARGS as arguments." - ;; - -finish) - $echo \ -"Usage: $modename [OPTION]... --mode=finish [LIBDIR]... - -Complete the installation of libtool libraries. - -Each LIBDIR is a directory that contains libtool libraries. - -The commands that this mode executes may require superuser privileges. Use -the \`--dry-run' option if you just want to see what would be executed." - ;; - -install) - $echo \ -"Usage: $modename [OPTION]... --mode=install INSTALL-COMMAND... - -Install executables or libraries. - -INSTALL-COMMAND is the installation command. The first component should be -either the \`install' or \`cp' program. - -The rest of the components are interpreted as arguments to that command (only -BSD-compatible install options are recognized)." - ;; - -link) - $echo \ -"Usage: $modename [OPTION]... --mode=link LINK-COMMAND... - -Link object files or libraries together to form another library, or to -create an executable program. - -LINK-COMMAND is a command using the C compiler that you would use to create -a program from several object files. - -The following components of LINK-COMMAND are treated specially: - - -all-static do not do any dynamic linking at all - -avoid-version do not add a version suffix if possible - -dlopen FILE \`-dlpreopen' FILE if it cannot be dlopened at runtime - -dlpreopen FILE link in FILE and add its symbols to lt_preloaded_symbols - -export-dynamic allow symbols from OUTPUT-FILE to be resolved with dlsym(3) - -export-symbols SYMFILE - try to export only the symbols listed in SYMFILE - -export-symbols-regex REGEX - try to export only the symbols matching REGEX - -LLIBDIR search LIBDIR for required installed libraries - -lNAME OUTPUT-FILE requires the installed library libNAME - -module build a library that can dlopened - -no-fast-install disable the fast-install mode - -no-install link a not-installable executable - -no-undefined declare that a library does not refer to external symbols - -o OUTPUT-FILE create OUTPUT-FILE from the specified objects - -release RELEASE specify package release information - -rpath LIBDIR the created library will eventually be installed in LIBDIR - -R[ ]LIBDIR add LIBDIR to the runtime path of programs and libraries - -static do not do any dynamic linking of libtool libraries - -version-info CURRENT[:REVISION[:AGE]] - specify library version info [each variable defaults to 0] - -All other options (arguments beginning with \`-') are ignored. - -Every other argument is treated as a filename. Files ending in \`.la' are -treated as uninstalled libtool libraries, other files are standard or library -object files. - -If the OUTPUT-FILE ends in \`.la', then a libtool library is created, -only library objects (\`.lo' files) may be specified, and \`-rpath' is -required, except when creating a convenience library. - -If OUTPUT-FILE ends in \`.a' or \`.lib', then a standard library is created -using \`ar' and \`ranlib', or on Windows using \`lib'. - -If OUTPUT-FILE ends in \`.lo' or \`.${objext}', then a reloadable object file -is created, otherwise an executable program is created." - ;; - -uninstall) - $echo \ -"Usage: $modename [OPTION]... --mode=uninstall RM [RM-OPTION]... FILE... - -Remove libraries from an installation directory. - -RM is the name of the program to use to delete files associated with each FILE -(typically \`/bin/rm'). RM-OPTIONS are options (such as \`-f') to be passed -to RM. - -If FILE is a libtool library, all the files associated with it are deleted. -Otherwise, only FILE itself is deleted using RM." - ;; - -*) - $echo "$modename: invalid operation mode \`$mode'" 1>&2 - $echo "$help" 1>&2 - exit 1 - ;; -esac - -echo -$echo "Try \`$modename --help' for more information about other modes." - -exit 0 - -# Local Variables: -# mode:shell-script -# sh-indentation:2 -# End: diff --git a/external-libs/pcre/makevp.bat b/external-libs/pcre/makevp.bat deleted file mode 100644 index 10bd2487..00000000 --- a/external-libs/pcre/makevp.bat +++ /dev/null @@ -1,25 +0,0 @@ -@echo off - -REM This file was contributed by Alexander Tokarev for building PCRE for use -REM with Virtual Pascal. It has not been tested with the latest PCRE release. - -REM CHANGE THIS FOR YOUR BORLAND C++ COMPILER PATH - -SET BORLAND=c:\usr\apps\bcc55 - -sh configure - -bcc32 -DDFTABLES -DSTATIC -DVPCOMPAT -I%BORLAND%\include -L%BORLAND%\lib dftables.c - -dftables > chartables.c - -bcc32 -c -RT- -y- -v- -u- -P- -O2 -5 -DSTATIC -DVPCOMPAT -UDFTABLES -I%BORLAND%\include get.c maketables.c pcre.c study.c - -tlib %BORLAND%\lib\cw32.lib *calloc *del *strncmp *memcpy *memmove *memset -tlib pcre.lib +get.obj +maketables.obj +pcre.obj +study.obj +calloc.obj +del.obj +strncmp.obj +memcpy.obj +memmove.obj +memset.obj - -del *.obj *.exe *.tds *.bak >nul 2>nul - -echo --- -echo Now the library should be complete. Please check all messages above. -echo Don't care for warnings, it's OK. diff --git a/external-libs/pcre/mkinstalldirs b/external-libs/pcre/mkinstalldirs deleted file mode 100644 index 70f983f5..00000000 --- a/external-libs/pcre/mkinstalldirs +++ /dev/null @@ -1,40 +0,0 @@ -#! /bin/sh -# mkinstalldirs --- make directory hierarchy -# Author: Noah Friedman <friedman@prep.ai.mit.edu> -# Created: 1993-05-16 -# Public domain - -# $Id: mkinstalldirs,v 1.12.2.1 1998/12/26 17:32:14 bje Exp $ - -errstatus=0 - -for file -do - set fnord `echo ":$file" | sed -ne 's/^:\//#/;s/^://;s/\// /g;s/^#/\//;p'` - shift - - pathcomp= - for d - do - pathcomp="$pathcomp$d" - case "$pathcomp" in - -* ) pathcomp=./$pathcomp ;; - esac - - if test ! -d "$pathcomp"; then - echo "mkdir $pathcomp" - - mkdir "$pathcomp" || lasterr=$? - - if test ! -d "$pathcomp"; then - errstatus=$lasterr - fi - fi - - pathcomp="$pathcomp/" - done -done - -exit $errstatus - -# mkinstalldirs ends here diff --git a/external-libs/pcre/pcre.def b/external-libs/pcre/pcre.def deleted file mode 100644 index 4f6c4bff..00000000 --- a/external-libs/pcre/pcre.def +++ /dev/null @@ -1,22 +0,0 @@ -EXPORTS - -pcre_malloc DATA -pcre_free DATA - -pcre_compile -pcre_copy_substring -pcre_exec -pcre_get_substring -pcre_get_substring_list -pcre_free_substring -pcre_free_substring_list -pcre_info -pcre_fullinfo -pcre_maketables -pcre_study -pcre_version - -regcomp -regexec -regerror -regfree diff --git a/external-libs/pcre/pcre.in b/external-libs/pcre/pcre.in deleted file mode 100644 index 5ad0d2ea..00000000 --- a/external-libs/pcre/pcre.in +++ /dev/null @@ -1,193 +0,0 @@ -/************************************************* -* Perl-Compatible Regular Expressions * -*************************************************/ - -/* Copyright (c) 1997-2003 University of Cambridge */ - -#ifndef _PCRE_H -#define _PCRE_H - -/* The file pcre.h is build by "configure". Do not edit it; instead -make changes to pcre.in. */ - -#define PCRE_MAJOR @PCRE_MAJOR@ -#define PCRE_MINOR @PCRE_MINOR@ -#define PCRE_DATE @PCRE_DATE@ - -/* Win32 uses DLL by default */ - -#ifdef _WIN32 -# ifdef PCRE_DEFINITION -# ifdef DLL_EXPORT -# define PCRE_DATA_SCOPE __declspec(dllexport) -# endif -# else -# ifndef PCRE_STATIC -# define PCRE_DATA_SCOPE extern __declspec(dllimport) -# endif -# endif -#endif -#ifndef PCRE_DATA_SCOPE -# define PCRE_DATA_SCOPE extern -#endif - -/* Have to include stdlib.h in order to ensure that size_t is defined; -it is needed here for malloc. */ - -#include <stdlib.h> - -/* Allow for C++ users */ - -#ifdef __cplusplus -extern "C" { -#endif - -/* Options */ - -#define PCRE_CASELESS 0x0001 -#define PCRE_MULTILINE 0x0002 -#define PCRE_DOTALL 0x0004 -#define PCRE_EXTENDED 0x0008 -#define PCRE_ANCHORED 0x0010 -#define PCRE_DOLLAR_ENDONLY 0x0020 -#define PCRE_EXTRA 0x0040 -#define PCRE_NOTBOL 0x0080 -#define PCRE_NOTEOL 0x0100 -#define PCRE_UNGREEDY 0x0200 -#define PCRE_NOTEMPTY 0x0400 -#define PCRE_UTF8 0x0800 -#define PCRE_NO_AUTO_CAPTURE 0x1000 -#define PCRE_NO_UTF8_CHECK 0x2000 - -/* Exec-time and get/set-time error codes */ - -#define PCRE_ERROR_NOMATCH (-1) -#define PCRE_ERROR_NULL (-2) -#define PCRE_ERROR_BADOPTION (-3) -#define PCRE_ERROR_BADMAGIC (-4) -#define PCRE_ERROR_UNKNOWN_NODE (-5) -#define PCRE_ERROR_NOMEMORY (-6) -#define PCRE_ERROR_NOSUBSTRING (-7) -#define PCRE_ERROR_MATCHLIMIT (-8) -#define PCRE_ERROR_CALLOUT (-9) /* Never used by PCRE itself */ -#define PCRE_ERROR_BADUTF8 (-10) -#define PCRE_ERROR_BADUTF8_OFFSET (-11) - -/* Request types for pcre_fullinfo() */ - -#define PCRE_INFO_OPTIONS 0 -#define PCRE_INFO_SIZE 1 -#define PCRE_INFO_CAPTURECOUNT 2 -#define PCRE_INFO_BACKREFMAX 3 -#define PCRE_INFO_FIRSTBYTE 4 -#define PCRE_INFO_FIRSTCHAR 4 /* For backwards compatibility */ -#define PCRE_INFO_FIRSTTABLE 5 -#define PCRE_INFO_LASTLITERAL 6 -#define PCRE_INFO_NAMEENTRYSIZE 7 -#define PCRE_INFO_NAMECOUNT 8 -#define PCRE_INFO_NAMETABLE 9 -#define PCRE_INFO_STUDYSIZE 10 - -/* Request types for pcre_config() */ - -#define PCRE_CONFIG_UTF8 0 -#define PCRE_CONFIG_NEWLINE 1 -#define PCRE_CONFIG_LINK_SIZE 2 -#define PCRE_CONFIG_POSIX_MALLOC_THRESHOLD 3 -#define PCRE_CONFIG_MATCH_LIMIT 4 -#define PCRE_CONFIG_STACKRECURSE 5 - -/* Bit flags for the pcre_extra structure */ - -#define PCRE_EXTRA_STUDY_DATA 0x0001 -#define PCRE_EXTRA_MATCH_LIMIT 0x0002 -#define PCRE_EXTRA_CALLOUT_DATA 0x0004 - -/* Types */ - -struct real_pcre; /* declaration; the definition is private */ -typedef struct real_pcre pcre; - -/* The structure for passing additional data to pcre_exec(). This is defined in -such as way as to be extensible. */ - -typedef struct pcre_extra { - unsigned long int flags; /* Bits for which fields are set */ - void *study_data; /* Opaque data from pcre_study() */ - unsigned long int match_limit; /* Maximum number of calls to match() */ - void *callout_data; /* Data passed back in callouts */ -} pcre_extra; - -/* The structure for passing out data via the pcre_callout_function. We use a -structure so that new fields can be added on the end in future versions, -without changing the API of the function, thereby allowing old clients to work -without modification. */ - -typedef struct pcre_callout_block { - int version; /* Identifies version of block */ - /* ------------------------ Version 0 ------------------------------- */ - int callout_number; /* Number compiled into pattern */ - int *offset_vector; /* The offset vector */ - const char *subject; /* The subject being matched */ - int subject_length; /* The length of the subject */ - int start_match; /* Offset to start of this match attempt */ - int current_position; /* Where we currently are */ - int capture_top; /* Max current capture */ - int capture_last; /* Most recently closed capture */ - void *callout_data; /* Data passed in with the call */ - /* ------------------------------------------------------------------ */ -} pcre_callout_block; - -/* Indirection for store get and free functions. These can be set to -alternative malloc/free functions if required. Special ones are used in the -non-recursive case for "frames". There is also an optional callout function -that is triggered by the (?) regex item. Some magic is required for Win32 DLL; -it is null on other OS. For Virtual Pascal, these have to be different again. -*/ - -#ifndef VPCOMPAT -PCRE_DATA_SCOPE void *(*pcre_malloc)(size_t); -PCRE_DATA_SCOPE void (*pcre_free)(void *); -PCRE_DATA_SCOPE void *(*pcre_stack_malloc)(size_t); -PCRE_DATA_SCOPE void (*pcre_stack_free)(void *); -PCRE_DATA_SCOPE int (*pcre_callout)(pcre_callout_block *); -#else /* VPCOMPAT */ -extern void *pcre_malloc(size_t); -extern void pcre_free(void *); -extern void *pcre_stack_malloc(size_t); -extern void pcre_stack_free(void *); -extern int pcre_callout(pcre_callout_block *); -#endif /* VPCOMPAT */ - -/* Exported PCRE functions */ - -extern pcre *pcre_compile(const char *, int, const char **, - int *, const unsigned char *); -extern int pcre_config(int, void *); -extern int pcre_copy_named_substring(const pcre *, const char *, - int *, int, const char *, char *, int); -extern int pcre_copy_substring(const char *, int *, int, int, - char *, int); -extern int pcre_exec(const pcre *, const pcre_extra *, - const char *, int, int, int, int *, int); -extern void pcre_free_substring(const char *); -extern void pcre_free_substring_list(const char **); -extern int pcre_fullinfo(const pcre *, const pcre_extra *, int, - void *); -extern int pcre_get_named_substring(const pcre *, const char *, - int *, int, const char *, const char **); -extern int pcre_get_stringnumber(const pcre *, const char *); -extern int pcre_get_substring(const char *, int *, int, int, - const char **); -extern int pcre_get_substring_list(const char *, int *, int, - const char ***); -extern int pcre_info(const pcre *, int *, int *); -extern const unsigned char *pcre_maketables(void); -extern pcre_extra *pcre_study(const pcre *, int, const char **); -extern const char *pcre_version(void); - -#ifdef __cplusplus -} /* extern "C" */ -#endif - -#endif /* End of pcre.h */ diff --git a/external-libs/pcre/testdata/testinput1 b/external-libs/pcre/testdata/testinput1 deleted file mode 100644 index c4b99c66..00000000 --- a/external-libs/pcre/testdata/testinput1 +++ /dev/null @@ -1,3841 +0,0 @@ -/the quick brown fox/ - the quick brown fox - The quick brown FOX - What do you know about the quick brown fox? - What do you know about THE QUICK BROWN FOX? - -/The quick brown fox/i - the quick brown fox - The quick brown FOX - What do you know about the quick brown fox? - What do you know about THE QUICK BROWN FOX? - -/abcd\t\n\r\f\a\e\071\x3b\$\\\?caxyz/ - abcd\t\n\r\f\a\e9;\$\\?caxyz - -/a*abc?xyz+pqr{3}ab{2,}xy{4,5}pq{0,6}AB{0,}zz/ - abxyzpqrrrabbxyyyypqAzz - abxyzpqrrrabbxyyyypqAzz - aabxyzpqrrrabbxyyyypqAzz - aaabxyzpqrrrabbxyyyypqAzz - aaaabxyzpqrrrabbxyyyypqAzz - abcxyzpqrrrabbxyyyypqAzz - aabcxyzpqrrrabbxyyyypqAzz - aaabcxyzpqrrrabbxyyyypAzz - aaabcxyzpqrrrabbxyyyypqAzz - aaabcxyzpqrrrabbxyyyypqqAzz - aaabcxyzpqrrrabbxyyyypqqqAzz - aaabcxyzpqrrrabbxyyyypqqqqAzz - aaabcxyzpqrrrabbxyyyypqqqqqAzz - aaabcxyzpqrrrabbxyyyypqqqqqqAzz - aaaabcxyzpqrrrabbxyyyypqAzz - abxyzzpqrrrabbxyyyypqAzz - aabxyzzzpqrrrabbxyyyypqAzz - aaabxyzzzzpqrrrabbxyyyypqAzz - aaaabxyzzzzpqrrrabbxyyyypqAzz - abcxyzzpqrrrabbxyyyypqAzz - aabcxyzzzpqrrrabbxyyyypqAzz - aaabcxyzzzzpqrrrabbxyyyypqAzz - aaaabcxyzzzzpqrrrabbxyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyyyypqAzz - aaabcxyzpqrrrabbxyyyypABzz - aaabcxyzpqrrrabbxyyyypABBzz - >>>aaabxyzpqrrrabbxyyyypqAzz - >aaaabxyzpqrrrabbxyyyypqAzz - >>>>abcxyzpqrrrabbxyyyypqAzz - *** Failers - abxyzpqrrabbxyyyypqAzz - abxyzpqrrrrabbxyyyypqAzz - abxyzpqrrrabxyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyypqAzz - aaabcxyzpqrrrabbxyyyypqqqqqqqAzz - -/^(abc){1,2}zz/ - abczz - abcabczz - *** Failers - zz - abcabcabczz - >>abczz - -/^(b+?|a){1,2}?c/ - bc - bbc - bbbc - bac - bbac - aac - abbbbbbbbbbbc - bbbbbbbbbbbac - *** Failers - aaac - abbbbbbbbbbbac - -/^(b+|a){1,2}c/ - bc - bbc - bbbc - bac - bbac - aac - abbbbbbbbbbbc - bbbbbbbbbbbac - *** Failers - aaac - abbbbbbbbbbbac - -/^(b+|a){1,2}?bc/ - bbc - -/^(b*|ba){1,2}?bc/ - babc - bbabc - bababc - *** Failers - bababbc - babababc - -/^(ba|b*){1,2}?bc/ - babc - bbabc - bababc - *** Failers - bababbc - babababc - -/^\ca\cA\c[\c{\c:/ - \x01\x01\e;z - -/^[ab\]cde]/ - athing - bthing - ]thing - cthing - dthing - ething - *** Failers - fthing - [thing - \\thing - -/^[]cde]/ - ]thing - cthing - dthing - ething - *** Failers - athing - fthing - -/^[^ab\]cde]/ - fthing - [thing - \\thing - *** Failers - athing - bthing - ]thing - cthing - dthing - ething - -/^[^]cde]/ - athing - fthing - *** Failers - ]thing - cthing - dthing - ething - -/^\/ - - -/^/ - - -/^[0-9]+$/ - 0 - 1 - 2 - 3 - 4 - 5 - 6 - 7 - 8 - 9 - 10 - 100 - *** Failers - abc - -/^.*nter/ - enter - inter - uponter - -/^xxx[0-9]+$/ - xxx0 - xxx1234 - *** Failers - xxx - -/^.+[0-9][0-9][0-9]$/ - x123 - xx123 - 123456 - *** Failers - 123 - x1234 - -/^.+?[0-9][0-9][0-9]$/ - x123 - xx123 - 123456 - *** Failers - 123 - x1234 - -/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ - abc!pqr=apquxz.ixr.zzz.ac.uk - *** Failers - !pqr=apquxz.ixr.zzz.ac.uk - abc!=apquxz.ixr.zzz.ac.uk - abc!pqr=apquxz:ixr.zzz.ac.uk - abc!pqr=apquxz.ixr.zzz.ac.ukk - -/:/ - Well, we need a colon: somewhere - *** Fail if we don't - -/([\da-f:]+)$/i - 0abc - abc - fed - E - :: - 5f03:12C0::932e - fed def - Any old stuff - *** Failers - 0zzz - gzzz - fed\x20 - Any old rubbish - -/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ - .1.2.3 - A.12.123.0 - *** Failers - .1.2.3333 - 1.2.3 - 1234.2.3 - -/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ - 1 IN SOA non-sp1 non-sp2( - 1 IN SOA non-sp1 non-sp2 ( - *** Failers - 1IN SOA non-sp1 non-sp2( - -/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ - a. - Z. - 2. - ab-c.pq-r. - sxk.zzz.ac.uk. - x-.y-. - *** Failers - -abc.peq. - -/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ - *.a - *.b0-a - *.c3-b.c - *.c-a.b-c - *** Failers - *.0 - *.a- - *.a-b.c- - *.c-a.0-c - -/^(?=ab(de))(abd)(e)/ - abde - -/^(?!(ab)de|x)(abd)(f)/ - abdf - -/^(?=(ab(cd)))(ab)/ - abcd - -/^[\da-f](\.[\da-f])*$/i - a.b.c.d - A.B.C.D - a.b.c.1.2.3.C - -/^\".*\"\s*(;.*)?$/ - \"1234\" - \"abcd\" ; - \"\" ; rhubarb - *** Failers - \"1234\" : things - -/^$/ - \ - *** Failers - -/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x - ab c - *** Failers - abc - ab cde - -/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ - ab c - *** Failers - abc - ab cde - -/^ a\ b[c ]d $/x - a bcd - a b d - *** Failers - abcd - ab d - -/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ - abcdefhijklm - -/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ - abcdefhijklm - -/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ - a+ Z0+\x08\n\x1d\x12 - -/^[.^$|()*+?{,}]+/ - .^\$(*+)|{?,?} - -/^a*\w/ - z - az - aaaz - a - aa - aaaa - a+ - aa+ - -/^a*?\w/ - z - az - aaaz - a - aa - aaaa - a+ - aa+ - -/^a+\w/ - az - aaaz - aa - aaaa - aa+ - -/^a+?\w/ - az - aaaz - aa - aaaa - aa+ - -/^\d{8}\w{2,}/ - 1234567890 - 12345678ab - 12345678__ - *** Failers - 1234567 - -/^[aeiou\d]{4,5}$/ - uoie - 1234 - 12345 - aaaaa - *** Failers - 123456 - -/^[aeiou\d]{4,5}?/ - uoie - 1234 - 12345 - aaaaa - 123456 - -/\A(abc|def)=(\1){2,3}\Z/ - abc=abcabc - def=defdefdef - *** Failers - abc=defdef - -/^(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\11*(\3\4)\1(?#)2$/ - abcdefghijkcda2 - abcdefghijkkkkcda2 - -/(cat(a(ract|tonic)|erpillar)) \1()2(3)/ - cataract cataract23 - catatonic catatonic23 - caterpillar caterpillar23 - - -/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ - From abcd Mon Sep 01 12:33:02 1997 - -/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ - From abcd Mon Sep 01 12:33:02 1997 - From abcd Mon Sep 1 12:33:02 1997 - *** Failers - From abcd Sep 01 12:33:02 1997 - -/^12.34/s - 12\n34 - 12\r34 - -/\w+(?=\t)/ - the quick brown\t fox - -/foo(?!bar)(.*)/ - foobar is foolish see? - -/(?:(?!foo)...|^.{0,2})bar(.*)/ - foobar crowbar etc - barrel - 2barrel - A barrel - -/^(\D*)(?=\d)(?!123)/ - abc456 - *** Failers - abc123 - -/^1234(?# test newlines - inside)/ - 1234 - -/^1234 #comment in extended re - /x - 1234 - -/#rhubarb - abcd/x - abcd - -/^abcd#rhubarb/x - abcd - -/^(a)\1{2,3}(.)/ - aaab - aaaab - aaaaab - aaaaaab - -/(?!^)abc/ - the abc - *** Failers - abc - -/(?=^)abc/ - abc - *** Failers - the abc - -/^[ab]{1,3}(ab*|b)/ - aabbbbb - -/^[ab]{1,3}?(ab*|b)/ - aabbbbb - -/^[ab]{1,3}?(ab*?|b)/ - aabbbbb - -/^[ab]{1,3}(ab*?|b)/ - aabbbbb - -/ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional leading comment -(?: (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # one word, optionally followed by.... -(?: -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... -\( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) | # comments, or... - -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -# quoted strings -)* -< (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # leading < -(?: @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* - -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* , (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -)* # further okay, if led by comma -: # closing colon -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* )? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address spec -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* > # trailing > -# name and address -) (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional trailing comment -/x - Alan Other <user\@dom.ain> - <user\@dom.ain> - user\@dom.ain - \"A. Other\" <user.1234\@dom.ain> (a comment) - A. Other <user.1234\@dom.ain> (a comment) - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - A missing angle <user\@some.where - *** Failers - The quick brown fox - -/[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional leading comment -(?: -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -# leading word -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces -(?: -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -| -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -) # "special" comment or quoted string -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" -)* -< -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# < -(?: -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -(?: , -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -)* # additional domains -: -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address spec -> # > -# name and address -) -/x - Alan Other <user\@dom.ain> - <user\@dom.ain> - user\@dom.ain - \"A. Other\" <user.1234\@dom.ain> (a comment) - A. Other <user.1234\@dom.ain> (a comment) - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - A missing angle <user\@some.where - *** Failers - The quick brown fox - -/abc\0def\00pqr\000xyz\0000AB/ - abc\0def\00pqr\000xyz\0000AB - abc456 abc\0def\00pqr\000xyz\0000ABCDE - -/abc\x0def\x00pqr\x000xyz\x0000AB/ - abc\x0def\x00pqr\x000xyz\x0000AB - abc456 abc\x0def\x00pqr\x000xyz\x0000ABCDE - -/^[\000-\037]/ - \0A - \01B - \037C - -/\0*/ - \0\0\0\0 - -/A\x0{2,3}Z/ - The A\x0\x0Z - An A\0\x0\0Z - *** Failers - A\0Z - A\0\x0\0\x0Z - -/^(cow|)\1(bell)/ - cowcowbell - bell - *** Failers - cowbell - -/^\s/ - \040abc - \x0cabc - \nabc - \rabc - \tabc - *** Failers - abc - -/^a b -
c/x - abc - -/^(a|)\1*b/ - ab - aaaab - b - *** Failers - acb - -/^(a|)\1+b/ - aab - aaaab - b - *** Failers - ab - -/^(a|)\1?b/ - ab - aab - b - *** Failers - acb - -/^(a|)\1{2}b/ - aaab - b - *** Failers - ab - aab - aaaab - -/^(a|)\1{2,3}b/ - aaab - aaaab - b - *** Failers - ab - aab - aaaaab - -/ab{1,3}bc/ - abbbbc - abbbc - abbc - *** Failers - abc - abbbbbc - -/([^.]*)\.([^:]*):[T ]+(.*)/ - track1.title:TBlah blah blah - -/([^.]*)\.([^:]*):[T ]+(.*)/i - track1.title:TBlah blah blah - -/([^.]*)\.([^:]*):[t ]+(.*)/i - track1.title:TBlah blah blah - -/^[W-c]+$/ - WXY_^abc - *** Failers - wxy - -/^[W-c]+$/i - WXY_^abc - wxy_^ABC - -/^[\x3f-\x5F]+$/i - WXY_^abc - wxy_^ABC - -/^abc$/m - abc - qqq\nabc - abc\nzzz - qqq\nabc\nzzz - -/^abc$/ - abc - *** Failers - qqq\nabc - abc\nzzz - qqq\nabc\nzzz - -/\Aabc\Z/m - abc - abc\n - *** Failers - qqq\nabc - abc\nzzz - qqq\nabc\nzzz - -/\A(.)*\Z/s - abc\ndef - -/\A(.)*\Z/m - *** Failers - abc\ndef - -/(?:b)|(?::+)/ - b::c - c::b - -/[-az]+/ - az- - *** Failers - b - -/[az-]+/ - za- - *** Failers - b - -/[a\-z]+/ - a-z - *** Failers - b - -/[a-z]+/ - abcdxyz - -/[\d-]+/ - 12-34 - *** Failers - aaa - -/[\d-z]+/ - 12-34z - *** Failers - aaa - -/\x5c/ - \\ - -/\x20Z/ - the Zoo - *** Failers - Zulu - -/(abc)\1/i - abcabc - ABCabc - abcABC - -/ab{3cd/ - ab{3cd - -/ab{3,cd/ - ab{3,cd - -/ab{3,4a}cd/ - ab{3,4a}cd - -/{4,5a}bc/ - {4,5a}bc - -/^a.b/ - a\rb - *** Failers - a\nb - -/abc$/ - abc - abc\n - *** Failers - abc\ndef - -/(abc)\123/ - abc\x53 - -/(abc)\223/ - abc\x93 - -/(abc)\323/ - abc\xd3 - -/(abc)\500/ - abc\x40 - abc\100 - -/(abc)\5000/ - abc\x400 - abc\x40\x30 - abc\1000 - abc\100\x30 - abc\100\060 - abc\100\60 - -/abc\81/ - abc\081 - abc\0\x38\x31 - -/abc\91/ - abc\091 - abc\0\x39\x31 - -/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)\12\123/ - abcdefghijkllS - -/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/ - abcdefghijk\12S - -/ab\gdef/ - abgdef - -/a{0}bc/ - bc - -/(a|(bc)){0,0}?xyz/ - xyz - -/abc[\10]de/ - abc\010de - -/abc[\1]de/ - abc\1de - -/(abc)[\1]de/ - abc\1de - -/(?s)a.b/ - a\nb - -/^([^a])([^\b])([^c]*)([^d]{3,4})/ - baNOTccccd - baNOTcccd - baNOTccd - bacccd - *** Failers - anything - b\bc - baccd - -/[^a]/ - Abc - -/[^a]/i - Abc - -/[^a]+/ - AAAaAbc - -/[^a]+/i - AAAaAbc - -/[^a]+/ - bbb\nccc - -/[^k]$/ - abc - *** Failers - abk - -/[^k]{2,3}$/ - abc - kbc - kabc - *** Failers - abk - akb - akk - -/^\d{8,}\@.+[^k]$/ - 12345678\@a.b.c.d - 123456789\@x.y.z - *** Failers - 12345678\@x.y.uk - 1234567\@a.b.c.d - -/(a)\1{8,}/ - aaaaaaaaa - aaaaaaaaaa - *** Failers - aaaaaaa - -/[^a]/ - aaaabcd - aaAabcd - -/[^a]/i - aaaabcd - aaAabcd - -/[^az]/ - aaaabcd - aaAabcd - -/[^az]/i - aaaabcd - aaAabcd - -/\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377/ - \000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377 - -/P[^*]TAIRE[^*]{1,6}?LL/ - xxxxxxxxxxxPSTAIREISLLxxxxxxxxx - -/P[^*]TAIRE[^*]{1,}?LL/ - xxxxxxxxxxxPSTAIREISLLxxxxxxxxx - -/(\.\d\d[1-9]?)\d+/ - 1.230003938 - 1.875000282 - 1.235 - -/(\.\d\d((?=0)|\d(?=\d)))/ - 1.230003938 - 1.875000282 - *** Failers - 1.235 - -/a(?)b/ - ab - -/\b(foo)\s+(\w+)/i - Food is on the foo table - -/foo(.*)bar/ - The food is under the bar in the barn. - -/foo(.*?)bar/ - The food is under the bar in the barn. - -/(.*)(\d*)/ - I have 2 numbers: 53147 - -/(.*)(\d+)/ - I have 2 numbers: 53147 - -/(.*?)(\d*)/ - I have 2 numbers: 53147 - -/(.*?)(\d+)/ - I have 2 numbers: 53147 - -/(.*)(\d+)$/ - I have 2 numbers: 53147 - -/(.*?)(\d+)$/ - I have 2 numbers: 53147 - -/(.*)\b(\d+)$/ - I have 2 numbers: 53147 - -/(.*\D)(\d+)$/ - I have 2 numbers: 53147 - -/^\D*(?!123)/ - ABC123 - -/^(\D*)(?=\d)(?!123)/ - ABC445 - *** Failers - ABC123 - -/^[W-]46]/ - W46]789 - -46]789 - *** Failers - Wall - Zebra - 42 - [abcd] - ]abcd[ - -/^[W-\]46]/ - W46]789 - Wall - Zebra - Xylophone - 42 - [abcd] - ]abcd[ - \\backslash - *** Failers - -46]789 - well - -/\d\d\/\d\d\/\d\d\d\d/ - 01/01/2000 - -/word (?:[a-zA-Z0-9]+ ){0,10}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark - -/word (?:[a-zA-Z0-9]+ ){0,300}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope - -/^(a){0,0}/ - bcd - abc - aab - -/^(a){0,1}/ - bcd - abc - aab - -/^(a){0,2}/ - bcd - abc - aab - -/^(a){0,3}/ - bcd - abc - aab - aaa - -/^(a){0,}/ - bcd - abc - aab - aaa - aaaaaaaa - -/^(a){1,1}/ - bcd - abc - aab - -/^(a){1,2}/ - bcd - abc - aab - -/^(a){1,3}/ - bcd - abc - aab - aaa - -/^(a){1,}/ - bcd - abc - aab - aaa - aaaaaaaa - -/.*\.gif/ - borfle\nbib.gif\nno - -/.{0,}\.gif/ - borfle\nbib.gif\nno - -/.*\.gif/m - borfle\nbib.gif\nno - -/.*\.gif/s - borfle\nbib.gif\nno - -/.*\.gif/ms - borfle\nbib.gif\nno - -/.*$/ - borfle\nbib.gif\nno - -/.*$/m - borfle\nbib.gif\nno - -/.*$/s - borfle\nbib.gif\nno - -/.*$/ms - borfle\nbib.gif\nno - -/.*$/ - borfle\nbib.gif\nno\n - -/.*$/m - borfle\nbib.gif\nno\n - -/.*$/s - borfle\nbib.gif\nno\n - -/.*$/ms - borfle\nbib.gif\nno\n - -/(.*X|^B)/ - abcde\n1234Xyz - BarFoo - *** Failers - abcde\nBar - -/(.*X|^B)/m - abcde\n1234Xyz - BarFoo - abcde\nBar - -/(.*X|^B)/s - abcde\n1234Xyz - BarFoo - *** Failers - abcde\nBar - -/(.*X|^B)/ms - abcde\n1234Xyz - BarFoo - abcde\nBar - -/(?s)(.*X|^B)/ - abcde\n1234Xyz - BarFoo - *** Failers - abcde\nBar - -/(?s:.*X|^B)/ - abcde\n1234Xyz - BarFoo - *** Failers - abcde\nBar - -/^.*B/ - **** Failers - abc\nB - -/(?s)^.*B/ - abc\nB - -/(?m)^.*B/ - abc\nB - -/(?ms)^.*B/ - abc\nB - -/(?ms)^B/ - abc\nB - -/(?s)B$/ - B\n - -/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/ - 123456654321 - -/^\d\d\d\d\d\d\d\d\d\d\d\d/ - 123456654321 - -/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/ - 123456654321 - -/^[abc]{12}/ - abcabcabcabc - -/^[a-c]{12}/ - abcabcabcabc - -/^(a|b|c){12}/ - abcabcabcabc - -/^[abcdefghijklmnopqrstuvwxy0123456789]/ - n - *** Failers - z - -/abcde{0,0}/ - abcd - *** Failers - abce - -/ab[cd]{0,0}e/ - abe - *** Failers - abcde - -/ab(c){0,0}d/ - abd - *** Failers - abcd - -/a(b*)/ - a - ab - abbbb - *** Failers - bbbbb - -/ab\d{0}e/ - abe - *** Failers - ab1e - -/"([^\\"]+|\\.)*"/ - the \"quick\" brown fox - \"the \\\"quick\\\" brown fox\" - -/.*?/g+ - abc - -/\b/g+ - abc - -/\b/+g - abc - -//g - abc - -/<tr([\w\W\s\d][^<>]{0,})><TD([\w\W\s\d][^<>]{0,})>([\d]{0,}\.)(.*)((<BR>([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is - <TR BGCOLOR='#DBE9E9'><TD align=left valign=top>43.<a href='joblist.cfm?JobID=94 6735&Keyword='>Word Processor<BR>(N-1286)</a></TD><TD align=left valign=top>Lega lstaff.com</TD><TD align=left valign=top>CA - Statewide</TD></TR> - -/a[^a]b/ - acb - a\nb - -/a.b/ - acb - *** Failers - a\nb - -/a[^a]b/s - acb - a\nb - -/a.b/s - acb - a\nb - -/^(b+?|a){1,2}?c/ - bac - bbac - bbbac - bbbbac - bbbbbac - -/^(b+|a){1,2}?c/ - bac - bbac - bbbac - bbbbac - bbbbbac - -/(?!\A)x/m - x\nb\n - a\bx\n - -/\x0{ab}/ - \0{ab} - -/(A|B)*?CD/ - CD - -/(A|B)*CD/ - CD - -/(AB)*?\1/ - ABABAB - -/(AB)*\1/ - ABABAB - -/(?<!bar)foo/ - foo - catfood - arfootle - rfoosh - *** Failers - barfoo - towbarfoo - -/\w{3}(?<!bar)foo/ - catfood - *** Failers - foo - barfoo - towbarfoo - -/(?<=(foo)a)bar/ - fooabar - *** Failers - bar - foobbar - -/\Aabc\z/m - abc - *** Failers - abc\n - qqq\nabc - abc\nzzz - qqq\nabc\nzzz - -"(?>.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ - -"(?>.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo - -/(?>(\.\d\d[1-9]?))\d+/ - 1.230003938 - 1.875000282 - *** Failers - 1.235 - -/^((?>\w+)|(?>\s+))*$/ - now is the time for all good men to come to the aid of the party - *** Failers - this is not a line with only words and spaces! - -/(\d+)(\w)/ - 12345a - 12345+ - -/((?>\d+))(\w)/ - 12345a - *** Failers - 12345+ - -/(?>a+)b/ - aaab - -/((?>a+)b)/ - aaab - -/(?>(a+))b/ - aaab - -/(?>b)+/ - aaabbbccc - -/(?>a+|b+|c+)*c/ - aaabbbbccccd - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - -/\(((?>[^()]+)|\([^()]+\))+\)/ - (abc) - (abc(def)xyz) - *** Failers - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/a(?-i)b/i - ab - Ab - *** Failers - aB - AB - -/(a (?x)b c)d e/ - a bcd e - *** Failers - a b cd e - abcd e - a bcde - -/(a b(?x)c d (?-x)e f)/ - a bcde f - *** Failers - abcdef - -/(a(?i)b)c/ - abc - aBc - *** Failers - abC - aBC - Abc - ABc - ABC - AbC - -/a(?i:b)c/ - abc - aBc - *** Failers - ABC - abC - aBC - -/a(?i:b)*c/ - aBc - aBBc - *** Failers - aBC - aBBC - -/a(?=b(?i)c)\w\wd/ - abcd - abCd - *** Failers - aBCd - abcD - -/(?s-i:more.*than).*million/i - more than million - more than MILLION - more \n than Million - *** Failers - MORE THAN MILLION - more \n than \n million - -/(?:(?s-i)more.*than).*million/i - more than million - more than MILLION - more \n than Million - *** Failers - MORE THAN MILLION - more \n than \n million - -/(?>a(?i)b+)+c/ - abc - aBbc - aBBc - *** Failers - Abc - abAb - abbC - -/(?=a(?i)b)\w\wc/ - abc - aBc - *** Failers - Ab - abC - aBC - -/(?<=a(?i)b)(\w\w)c/ - abxxc - aBxxc - *** Failers - Abxxc - ABxxc - abxxC - -/(?:(a)|b)(?(1)A|B)/ - aA - bB - *** Failers - aB - bA - -/^(a)?(?(1)a|b)+$/ - aa - b - bb - *** Failers - ab - -/^(?(?=abc)\w{3}:|\d\d)$/ - abc: - 12 - *** Failers - 123 - xyz - -/^(?(?!abc)\d\d|\w{3}:)$/ - abc: - 12 - *** Failers - 123 - xyz - -/(?(?<=foo)bar|cat)/ - foobar - cat - fcat - focat - *** Failers - foocat - -/(?(?<!foo)cat|bar)/ - foobar - cat - fcat - focat - *** Failers - foocat - -/( \( )? [^()]+ (?(1) \) |) /x - abcd - (abcd) - the quick (abcd) fox - (abcd - -/( \( )? [^()]+ (?(1) \) ) /x - abcd - (abcd) - the quick (abcd) fox - (abcd - -/^(?(2)a|(1)(2))+$/ - 12 - 12a - 12aa - *** Failers - 1234 - -/((?i)blah)\s+\1/ - blah blah - BLAH BLAH - Blah Blah - blaH blaH - *** Failers - blah BLAH - Blah blah - blaH blah - -/((?i)blah)\s+(?i:\1)/ - blah blah - BLAH BLAH - Blah Blah - blaH blaH - blah BLAH - Blah blah - blaH blah - -/(?>a*)*/ - a - aa - aaaa - -/(abc|)+/ - abc - abcabc - abcabcabc - xyz - -/([a]*)*/ - a - aaaaa - -/([ab]*)*/ - a - b - ababab - aaaabcde - bbbb - -/([^a]*)*/ - b - bbbb - aaa - -/([^ab]*)*/ - cccc - abab - -/([a]*?)*/ - a - aaaa - -/([ab]*?)*/ - a - b - abab - baba - -/([^a]*?)*/ - b - bbbb - aaa - -/([^ab]*?)*/ - c - cccc - baba - -/(?>a*)*/ - a - aaabcde - -/((?>a*))*/ - aaaaa - aabbaa - -/((?>a*?))*/ - aaaaa - aabbaa - -/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x - 12-sep-98 - 12-09-98 - *** Failers - sep-12-98 - -/(?<=(foo))bar\1/ - foobarfoo - foobarfootling - *** Failers - foobar - barfoo - -/(?i:saturday|sunday)/ - saturday - sunday - Saturday - Sunday - SATURDAY - SUNDAY - SunDay - -/(a(?i)bc|BB)x/ - abcx - aBCx - bbx - BBx - *** Failers - abcX - aBCX - bbX - BBX - -/^([ab](?i)[cd]|[ef])/ - ac - aC - bD - elephant - Europe - frog - France - *** Failers - Africa - -/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ - ab - aBd - xy - xY - zebra - Zambesi - *** Failers - aCD - XY - -/(?<=foo\n)^bar/m - foo\nbar - *** Failers - bar - baz\nbar - -/(?<=(?<!foo)bar)baz/ - barbaz - barbarbaz - koobarbaz - *** Failers - baz - foobarbaz - -/The case of aaaaaa is missed out below because I think Perl 5.005_02 gets/ -/it wrong; it sets $1 to aaa rather than aa. Compare the following test,/ -/where it does set $1 to aa when matching aaaaaa./ - -/^(a\1?){4}$/ - a - aa - aaa - aaaa - aaaaa - aaaaaaa - aaaaaaaa - aaaaaaaaa - aaaaaaaaaa - aaaaaaaaaaa - aaaaaaaaaaaa - aaaaaaaaaaaaa - aaaaaaaaaaaaaa - aaaaaaaaaaaaaaa - aaaaaaaaaaaaaaaa - -/^(a\1?)(a\1?)(a\2?)(a\3?)$/ - a - aa - aaa - aaaa - aaaaa - aaaaaa - aaaaaaa - aaaaaaaa - aaaaaaaaa - aaaaaaaaaa - aaaaaaaaaaa - aaaaaaaaaaaa - aaaaaaaaaaaaa - aaaaaaaaaaaaaa - aaaaaaaaaaaaaaa - aaaaaaaaaaaaaaaa - -/The following tests are taken from the Perl 5.005 test suite; some of them/ -/are compatible with 5.004, but I'd rather not have to sort them out./ - -/abc/ - abc - xabcy - ababc - *** Failers - xbc - axc - abx - -/ab*c/ - abc - -/ab*bc/ - abc - abbc - abbbbc - -/.{1}/ - abbbbc - -/.{3,4}/ - abbbbc - -/ab{0,}bc/ - abbbbc - -/ab+bc/ - abbc - *** Failers - abc - abq - -/ab{1,}bc/ - -/ab+bc/ - abbbbc - -/ab{1,}bc/ - abbbbc - -/ab{1,3}bc/ - abbbbc - -/ab{3,4}bc/ - abbbbc - -/ab{4,5}bc/ - *** Failers - abq - abbbbc - -/ab?bc/ - abbc - abc - -/ab{0,1}bc/ - abc - -/ab?bc/ - -/ab?c/ - abc - -/ab{0,1}c/ - abc - -/^abc$/ - abc - *** Failers - abbbbc - abcc - -/^abc/ - abcc - -/^abc$/ - -/abc$/ - aabc - *** Failers - aabc - aabcd - -/^/ - abc - -/$/ - abc - -/a.c/ - abc - axc - -/a.*c/ - axyzc - -/a[bc]d/ - abd - *** Failers - axyzd - abc - -/a[b-d]e/ - ace - -/a[b-d]/ - aac - -/a[-b]/ - a- - -/a[b-]/ - a- - -/a]/ - a] - -/a[]]b/ - a]b - -/a[^bc]d/ - aed - *** Failers - abd - abd - -/a[^-b]c/ - adc - -/a[^]b]c/ - adc - *** Failers - a-c - a]c - -/\ba\b/ - a- - -a - -a- - -/\by\b/ - *** Failers - xy - yz - xyz - -/\Ba\B/ - *** Failers - a- - -a - -a- - -/\By\b/ - xy - -/\by\B/ - yz - -/\By\B/ - xyz - -/\w/ - a - -/\W/ - - - *** Failers - - - a - -/a\sb/ - a b - -/a\Sb/ - a-b - *** Failers - a-b - a b - -/\d/ - 1 - -/\D/ - - - *** Failers - - - 1 - -/[\w]/ - a - -/[\W]/ - - - *** Failers - - - a - -/a[\s]b/ - a b - -/a[\S]b/ - a-b - *** Failers - a-b - a b - -/[\d]/ - 1 - -/[\D]/ - - - *** Failers - - - 1 - -/ab|cd/ - abc - abcd - -/()ef/ - def - -/$b/ - -/a\(b/ - a(b - -/a\(*b/ - ab - a((b - -/a\\b/ - a\b - -/((a))/ - abc - -/(a)b(c)/ - abc - -/a+b+c/ - aabbabc - -/a{1,}b{1,}c/ - aabbabc - -/a.+?c/ - abcabc - -/(a+|b)*/ - ab - -/(a+|b){0,}/ - ab - -/(a+|b)+/ - ab - -/(a+|b){1,}/ - ab - -/(a+|b)?/ - ab - -/(a+|b){0,1}/ - ab - -/[^ab]*/ - cde - -/abc/ - *** Failers - b - - -/a*/ - - -/([abc])*d/ - abbbcd - -/([abc])*bcd/ - abcd - -/a|b|c|d|e/ - e - -/(a|b|c|d|e)f/ - ef - -/abcd*efg/ - abcdefg - -/ab*/ - xabyabbbz - xayabbbz - -/(ab|cd)e/ - abcde - -/[abhgefdc]ij/ - hij - -/^(ab|cd)e/ - -/(abc|)ef/ - abcdef - -/(a|b)c*d/ - abcd - -/(ab|ab*)bc/ - abc - -/a([bc]*)c*/ - abc - -/a([bc]*)(c*d)/ - abcd - -/a([bc]+)(c*d)/ - abcd - -/a([bc]*)(c+d)/ - abcd - -/a[bcd]*dcdcde/ - adcdcde - -/a[bcd]+dcdcde/ - *** Failers - abcde - adcdcde - -/(ab|a)b*c/ - abc - -/((a)(b)c)(d)/ - abcd - -/[a-zA-Z_][a-zA-Z0-9_]*/ - alpha - -/^a(bc+|b[eh])g|.h$/ - abh - -/(bc+d$|ef*g.|h?i(j|k))/ - effgz - ij - reffgz - *** Failers - effg - bcdd - -/((((((((((a))))))))))/ - a - -/((((((((((a))))))))))\10/ - aa - -/(((((((((a)))))))))/ - a - -/multiple words of text/ - *** Failers - aa - uh-uh - -/multiple words/ - multiple words, yeah - -/(.*)c(.*)/ - abcde - -/\((.*), (.*)\)/ - (a, b) - -/[k]/ - -/abcd/ - abcd - -/a(bc)d/ - abcd - -/a[-]?c/ - ac - -/(abc)\1/ - abcabc - -/([a-c]*)\1/ - abcabc - -/(a)|\1/ - a - *** Failers - ab - x - -/(([a-c])b*?\2)*/ - ababbbcbc - -/(([a-c])b*?\2){3}/ - ababbbcbc - -/((\3|b)\2(a)x)+/ - aaaxabaxbaaxbbax - -/((\3|b)\2(a)){2,}/ - bbaababbabaaaaabbaaaabba - -/abc/i - ABC - XABCY - ABABC - *** Failers - aaxabxbaxbbx - XBC - AXC - ABX - -/ab*c/i - ABC - -/ab*bc/i - ABC - ABBC - -/ab*?bc/i - ABBBBC - -/ab{0,}?bc/i - ABBBBC - -/ab+?bc/i - ABBC - -/ab+bc/i - *** Failers - ABC - ABQ - -/ab{1,}bc/i - -/ab+bc/i - ABBBBC - -/ab{1,}?bc/i - ABBBBC - -/ab{1,3}?bc/i - ABBBBC - -/ab{3,4}?bc/i - ABBBBC - -/ab{4,5}?bc/i - *** Failers - ABQ - ABBBBC - -/ab??bc/i - ABBC - ABC - -/ab{0,1}?bc/i - ABC - -/ab??bc/i - -/ab??c/i - ABC - -/ab{0,1}?c/i - ABC - -/^abc$/i - ABC - *** Failers - ABBBBC - ABCC - -/^abc/i - ABCC - -/^abc$/i - -/abc$/i - AABC - -/^/i - ABC - -/$/i - ABC - -/a.c/i - ABC - AXC - -/a.*?c/i - AXYZC - -/a.*c/i - *** Failers - AABC - AXYZD - -/a[bc]d/i - ABD - -/a[b-d]e/i - ACE - *** Failers - ABC - ABD - -/a[b-d]/i - AAC - -/a[-b]/i - A- - -/a[b-]/i - A- - -/a]/i - A] - -/a[]]b/i - A]B - -/a[^bc]d/i - AED - -/a[^-b]c/i - ADC - *** Failers - ABD - A-C - -/a[^]b]c/i - ADC - -/ab|cd/i - ABC - ABCD - -/()ef/i - DEF - -/$b/i - *** Failers - A]C - B - -/a\(b/i - A(B - -/a\(*b/i - AB - A((B - -/a\\b/i - A\B - -/((a))/i - ABC - -/(a)b(c)/i - ABC - -/a+b+c/i - AABBABC - -/a{1,}b{1,}c/i - AABBABC - -/a.+?c/i - ABCABC - -/a.*?c/i - ABCABC - -/a.{0,5}?c/i - ABCABC - -/(a+|b)*/i - AB - -/(a+|b){0,}/i - AB - -/(a+|b)+/i - AB - -/(a+|b){1,}/i - AB - -/(a+|b)?/i - AB - -/(a+|b){0,1}/i - AB - -/(a+|b){0,1}?/i - AB - -/[^ab]*/i - CDE - -/abc/i - -/a*/i - - -/([abc])*d/i - ABBBCD - -/([abc])*bcd/i - ABCD - -/a|b|c|d|e/i - E - -/(a|b|c|d|e)f/i - EF - -/abcd*efg/i - ABCDEFG - -/ab*/i - XABYABBBZ - XAYABBBZ - -/(ab|cd)e/i - ABCDE - -/[abhgefdc]ij/i - HIJ - -/^(ab|cd)e/i - ABCDE - -/(abc|)ef/i - ABCDEF - -/(a|b)c*d/i - ABCD - -/(ab|ab*)bc/i - ABC - -/a([bc]*)c*/i - ABC - -/a([bc]*)(c*d)/i - ABCD - -/a([bc]+)(c*d)/i - ABCD - -/a([bc]*)(c+d)/i - ABCD - -/a[bcd]*dcdcde/i - ADCDCDE - -/a[bcd]+dcdcde/i - -/(ab|a)b*c/i - ABC - -/((a)(b)c)(d)/i - ABCD - -/[a-zA-Z_][a-zA-Z0-9_]*/i - ALPHA - -/^a(bc+|b[eh])g|.h$/i - ABH - -/(bc+d$|ef*g.|h?i(j|k))/i - EFFGZ - IJ - REFFGZ - *** Failers - ADCDCDE - EFFG - BCDD - -/((((((((((a))))))))))/i - A - -/((((((((((a))))))))))\10/i - AA - -/(((((((((a)))))))))/i - A - -/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a))))))))))/i - A - -/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))/i - C - -/multiple words of text/i - *** Failers - AA - UH-UH - -/multiple words/i - MULTIPLE WORDS, YEAH - -/(.*)c(.*)/i - ABCDE - -/\((.*), (.*)\)/i - (A, B) - -/[k]/i - -/abcd/i - ABCD - -/a(bc)d/i - ABCD - -/a[-]?c/i - AC - -/(abc)\1/i - ABCABC - -/([a-c]*)\1/i - ABCABC - -/a(?!b)./ - abad - -/a(?=d)./ - abad - -/a(?=c|d)./ - abad - -/a(?:b|c|d)(.)/ - ace - -/a(?:b|c|d)*(.)/ - ace - -/a(?:b|c|d)+?(.)/ - ace - acdbcdbe - -/a(?:b|c|d)+(.)/ - acdbcdbe - -/a(?:b|c|d){2}(.)/ - acdbcdbe - -/a(?:b|c|d){4,5}(.)/ - acdbcdbe - -/a(?:b|c|d){4,5}?(.)/ - acdbcdbe - -/((foo)|(bar))*/ - foobar - -/a(?:b|c|d){6,7}(.)/ - acdbcdbe - -/a(?:b|c|d){6,7}?(.)/ - acdbcdbe - -/a(?:b|c|d){5,6}(.)/ - acdbcdbe - -/a(?:b|c|d){5,6}?(.)/ - acdbcdbe - -/a(?:b|c|d){5,7}(.)/ - acdbcdbe - -/a(?:b|c|d){5,7}?(.)/ - acdbcdbe - -/a(?:b|(c|e){1,2}?|d)+?(.)/ - ace - -/^(.+)?B/ - AB - -/^([^a-z])|(\^)$/ - . - -/^[<>]&/ - <&OUT - -/^(a\1?){4}$/ - aaaaaaaaaa - *** Failers - AB - aaaaaaaaa - aaaaaaaaaaa - -/^(a(?(1)\1)){4}$/ - aaaaaaaaaa - *** Failers - aaaaaaaaa - aaaaaaaaaaa - -/(?:(f)(o)(o)|(b)(a)(r))*/ - foobar - -/(?<=a)b/ - ab - *** Failers - cb - b - -/(?<!c)b/ - ab - b - b - -/(?:..)*a/ - aba - -/(?:..)*?a/ - aba - -/^(?:b|a(?=(.)))*\1/ - abc - -/^(){3,5}/ - abc - -/^(a+)*ax/ - aax - -/^((a|b)+)*ax/ - aax - -/^((a|bc)+)*ax/ - aax - -/(a|x)*ab/ - cab - -/(a)*ab/ - cab - -/(?:(?i)a)b/ - ab - -/((?i)a)b/ - ab - -/(?:(?i)a)b/ - Ab - -/((?i)a)b/ - Ab - -/(?:(?i)a)b/ - *** Failers - cb - aB - -/((?i)a)b/ - -/(?i:a)b/ - ab - -/((?i:a))b/ - ab - -/(?i:a)b/ - Ab - -/((?i:a))b/ - Ab - -/(?i:a)b/ - *** Failers - aB - aB - -/((?i:a))b/ - -/(?:(?-i)a)b/i - ab - -/((?-i)a)b/i - ab - -/(?:(?-i)a)b/i - aB - -/((?-i)a)b/i - aB - -/(?:(?-i)a)b/i - *** Failers - aB - Ab - -/((?-i)a)b/i - -/(?:(?-i)a)b/i - aB - -/((?-i)a)b/i - aB - -/(?:(?-i)a)b/i - *** Failers - Ab - AB - -/((?-i)a)b/i - -/(?-i:a)b/i - ab - -/((?-i:a))b/i - ab - -/(?-i:a)b/i - aB - -/((?-i:a))b/i - aB - -/(?-i:a)b/i - *** Failers - AB - Ab - -/((?-i:a))b/i - -/(?-i:a)b/i - aB - -/((?-i:a))b/i - aB - -/(?-i:a)b/i - *** Failers - Ab - AB - -/((?-i:a))b/i - -/((?-i:a.))b/i - *** Failers - AB - a\nB - -/((?s-i:a.))b/i - a\nB - -/(?:c|d)(?:)(?:a(?:)(?:b)(?:b(?:))(?:b(?:)(?:b)))/ - cabbbb - -/(?:c|d)(?:)(?:aaaaaaaa(?:)(?:bbbbbbbb)(?:bbbbbbbb(?:))(?:bbbbbbbb(?:)(?:bbbbbbbb)))/ - caaaaaaaabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb - -/(ab)\d\1/i - Ab4ab - ab4Ab - -/foo\w*\d{4}baz/ - foobar1234baz - -/x(~~)*(?:(?:F)?)?/ - x~~ - -/^a(?#xxx){3}c/ - aaac - -/^a (?#xxx) (?#yyy) {3}c/x - aaac - -/(?<![cd])b/ - *** Failers - B\nB - dbcb - -/(?<![cd])[ab]/ - dbaacb - -/(?<!(c|d))b/ - -/(?<!(c|d))[ab]/ - dbaacb - -/(?<!cd)[ab]/ - cdaccb - -/^(?:a?b?)*$/ - *** Failers - dbcb - a-- - -/((?s)^a(.))((?m)^b$)/ - a\nb\nc\n - -/((?m)^b$)/ - a\nb\nc\n - -/(?m)^b/ - a\nb\n - -/(?m)^(b)/ - a\nb\n - -/((?m)^b)/ - a\nb\n - -/\n((?m)^b)/ - a\nb\n - -/((?s).)c(?!.)/ - a\nb\nc\n - a\nb\nc\n - -/((?s)b.)c(?!.)/ - a\nb\nc\n - a\nb\nc\n - -/^b/ - -/()^b/ - *** Failers - a\nb\nc\n - a\nb\nc\n - -/((?m)^b)/ - a\nb\nc\n - -/(?(1)a|b)/ - -/(?(1)b|a)/ - a - -/(x)?(?(1)a|b)/ - *** Failers - a - a - -/(x)?(?(1)b|a)/ - a - -/()?(?(1)b|a)/ - a - -/()(?(1)b|a)/ - -/()?(?(1)a|b)/ - a - -/^(\()?blah(?(1)(\)))$/ - (blah) - blah - *** Failers - a - blah) - (blah - -/^(\(+)?blah(?(1)(\)))$/ - (blah) - blah - *** Failers - blah) - (blah - -/(?(?!a)a|b)/ - -/(?(?!a)b|a)/ - a - -/(?(?=a)b|a)/ - *** Failers - a - a - -/(?(?=a)a|b)/ - a - -/(?=(a+?))(\1ab)/ - aaab - -/^(?=(a+?))\1ab/ - -/(\w+:)+/ - one: - -/$(?<=^(a))/ - a - -/(?=(a+?))(\1ab)/ - aaab - -/^(?=(a+?))\1ab/ - *** Failers - aaab - aaab - -/([\w:]+::)?(\w+)$/ - abcd - xy:z:::abcd - -/^[^bcd]*(c+)/ - aexycd - -/(a*)b+/ - caab - -/([\w:]+::)?(\w+)$/ - abcd - xy:z:::abcd - *** Failers - abcd: - abcd: - -/^[^bcd]*(c+)/ - aexycd - -/(>a+)ab/ - -/(?>a+)b/ - aaab - -/([[:]+)/ - a:[b]: - -/([[=]+)/ - a=[b]= - -/([[.]+)/ - a.[b]. - -/((?>a+)b)/ - aaab - -/(?>(a+))b/ - aaab - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - -/a\Z/ - *** Failers - aaab - a\nb\n - -/b\Z/ - a\nb\n - -/b\z/ - -/b\Z/ - a\nb - -/b\z/ - a\nb - *** Failers - -/^(?>(?(1)\.|())[^\W_](?>[a-z0-9-]*[^\W_])?)+$/ - a - abc - a-b - 0-9 - a.b - 5.6.7 - the.quick.brown.fox - a100.b200.300c - 12-ab.1245 - *** Failers - \ - .a - -a - a- - a. - a_b - a.- - a.. - ab..bc - the.quick.brown.fox- - the.quick.brown.fox. - the.quick.brown.fox_ - the.quick.brown.fox+ - -/(?>.*)(?<=(abcd|wxyz))/ - alphabetabcd - endingwxyz - *** Failers - a rather long string that doesn't end with one of them - -/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark - -/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope - -/(?<=\d{3}(?!999))foo/ - 999foo - 123999foo - *** Failers - 123abcfoo - -/(?<=(?!...999)\d{3})foo/ - 999foo - 123999foo - *** Failers - 123abcfoo - -/(?<=\d{3}(?!999)...)foo/ - 123abcfoo - 123456foo - *** Failers - 123999foo - -/(?<=\d{3}...)(?<!999)foo/ - 123abcfoo - 123456foo - *** Failers - 123999foo - -/<a[\s]+href[\s]*=[\s]* # find <a href= - ([\"\'])? # find single or double quote - (?(1) (.*?)\1 | ([^\s]+)) # if quote found, match up to next matching - # quote, otherwise match up to next space -/isx - <a href=abcd xyz - <a href=\"abcd xyz pqr\" cats - <a href=\'abcd xyz pqr\' cats - -/<a\s+href\s*=\s* # find <a href= - (["'])? # find single or double quote - (?(1) (.*?)\1 | (\S+)) # if quote found, match up to next matching - # quote, otherwise match up to next space -/isx - <a href=abcd xyz - <a href=\"abcd xyz pqr\" cats - <a href = \'abcd xyz pqr\' cats - -/<a\s+href(?>\s*)=(?>\s*) # find <a href= - (["'])? # find single or double quote - (?(1) (.*?)\1 | (\S+)) # if quote found, match up to next matching - # quote, otherwise match up to next space -/isx - <a href=abcd xyz - <a href=\"abcd xyz pqr\" cats - <a href = \'abcd xyz pqr\' cats - -/((Z)+|A)*/ - ZABCDEFG - -/(Z()|A)*/ - ZABCDEFG - -/(Z(())|A)*/ - ZABCDEFG - -/((?>Z)+|A)*/ - ZABCDEFG - -/((?>)+|A)*/ - ZABCDEFG - -/a*/g - abbab - -/^[a-\d]/ - abcde - -things - 0digit - *** Failers - bcdef - -/^[\d-a]/ - abcde - -things - 0digit - *** Failers - bcdef - -/[[:space:]]+/ - > \x09\x0a\x0c\x0d\x0b< - -/[[:blank:]]+/ - > \x09\x0a\x0c\x0d\x0b< - -/[\s]+/ - > \x09\x0a\x0c\x0d\x0b< - -/\s+/ - > \x09\x0a\x0c\x0d\x0b< - -/a b/x - ab - -/(?!\A)x/m - a\nxb\n - -/(?!^)x/m - a\nxb\n - -/abc\Qabc\Eabc/ - abcabcabc - -/abc\Q(*+|\Eabc/ - abc(*+|abc - -/ abc\Q abc\Eabc/x - abc abcabc - *** Failers - abcabcabc - -/abc#comment - \Q#not comment - literal\E/x - abc#not comment\n literal - -/abc#comment - \Q#not comment - literal/x - abc#not comment\n literal - -/abc#comment - \Q#not comment - literal\E #more comment - /x - abc#not comment\n literal - -/abc#comment - \Q#not comment - literal\E #more comment/x - abc#not comment\n literal - -/\Qabc\$xyz\E/ - abc\\\$xyz - -/\Qabc\E\$\Qxyz\E/ - abc\$xyz - -/\Gabc/ - abc - *** Failers - xyzabc - -/\Gabc./g - abc1abc2xyzabc3 - -/abc./g - abc1abc2xyzabc3 - -/a(?x: b c )d/ - XabcdY - *** Failers - Xa b c d Y - -/((?x)x y z | a b c)/ - XabcY - AxyzB - -/(?i)AB(?-i)C/ - XabCY - *** Failers - XabcY - -/((?i)AB(?-i)C|D)E/ - abCE - DE - *** Failers - abcE - abCe - dE - De - -/(.*)\d+\1/ - abc123abc - abc123bc - -/(.*)\d+\1/s - abc123abc - abc123bc - -/((.*))\d+\1/ - abc123abc - abc123bc - -/-- This tests for an IPv6 address in the form where it can have up to --/ -/-- eight components, one and only one of which is empty. This must be --/ -/-- an internal component. --/ - -/^(?!:) # colon disallowed at start - (?: # start of item - (?: [0-9a-f]{1,4} | # 1-4 hex digits or - (?(1)0 | () ) ) # if null previously matched, fail; else null - : # followed by colon - ){1,7} # end item; 1-7 of them required - [0-9a-f]{1,4} $ # final hex number at end of string - (?(1)|.) # check that there was an empty component - /xi - a123::a123 - a123:b342::abcd - a123:b342::324e:abcd - a123:ddde:b342::324e:abcd - a123:ddde:b342::324e:dcba:abcd - a123:ddde:9999:b342::324e:dcba:abcd - *** Failers - 1:2:3:4:5:6:7:8 - a123:bce:ddde:9999:b342::324e:dcba:abcd - a123::9999:b342::324e:dcba:abcd - abcde:2:3:4:5:6:7:8 - ::1 - abcd:fee0:123:: - :1 - 1: - -/[z\Qa-d]\E]/ - z - a - - - d - ] - *** Failers - b - -/[\z\C]/ - z - C - -/\M/ - M - -/(a+)*b/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/(?i)reg(?:ul(?:[a]|ae)r|ex)/ - REGular - regulaer - Regex - regulr - -/[--]+/ - - - - - -/(?<=Z)X./ - \x84XAZXB - -/ End of testinput1 / diff --git a/external-libs/pcre/testdata/testinput2 b/external-libs/pcre/testdata/testinput2 deleted file mode 100644 index 710bcc99..00000000 --- a/external-libs/pcre/testdata/testinput2 +++ /dev/null @@ -1,1259 +0,0 @@ -/(a)b|/ - -/abc/ - abc - defabc - \Aabc - *** Failers - \Adefabc - ABC - -/^abc/ - abc - \Aabc - *** Failers - defabc - \Adefabc - -/a+bc/ - -/a*bc/ - -/a{3}bc/ - -/(abc|a+z)/ - -/^abc$/ - abc - *** Failers - def\nabc - -/ab\gdef/X - -/(?X)ab\gdef/X - -/x{5,4}/ - -/z{65536}/ - -/[abcd/ - -/(?X)[\B]/ - -/[z-a]/ - -/^*/ - -/(abc/ - -/(?# abc/ - -/(?z)abc/ - -/.*b/ - -/.*?b/ - -/cat|dog|elephant/ - this sentence eventually mentions a cat - this sentences rambles on and on for a while and then reaches elephant - -/cat|dog|elephant/S - this sentence eventually mentions a cat - this sentences rambles on and on for a while and then reaches elephant - -/cat|dog|elephant/iS - this sentence eventually mentions a CAT cat - this sentences rambles on and on for a while to elephant ElePhant - -/a|[bcd]/S - -/(a|[^\dZ])/S - -/(a|b)*[\s]/S - -/(ab\2)/ - -/{4,5}abc/ - -/(a)(b)(c)\2/ - abcb - \O0abcb - \O3abcb - \O6abcb - \O9abcb - \O12abcb - -/(a)bc|(a)(b)\2/ - abc - \O0abc - \O3abc - \O6abc - aba - \O0aba - \O3aba - \O6aba - \O9aba - \O12aba - -/abc$/E - abc - *** Failers - abc\n - abc\ndef - -/(a)(b)(c)(d)(e)\6/ - -/the quick brown fox/ - the quick brown fox - this is a line with the quick brown fox - -/the quick brown fox/A - the quick brown fox - *** Failers - this is a line with the quick brown fox - -/ab(?z)cd/ - -/^abc|def/ - abcdef - abcdef\B - -/.*((abc)$|(def))/ - defabc - \Zdefabc - -/abc/P - abc - *** Failers - -/^abc|def/P - abcdef - abcdef\B - -/.*((abc)$|(def))/P - defabc - \Zdefabc - -/the quick brown fox/P - the quick brown fox - *** Failers - The Quick Brown Fox - -/the quick brown fox/Pi - the quick brown fox - The Quick Brown Fox - -/abc.def/P - *** Failers - abc\ndef - -/abc$/P - abc - abc\n - -/(abc)\2/P - -/(abc\1)/P - abc - -/)/ - -/a[]b/ - -/[^aeiou ]{3,}/ - co-processors, and for - -/<.*>/ - abc<def>ghi<klm>nop - -/<.*?>/ - abc<def>ghi<klm>nop - -/<.*>/U - abc<def>ghi<klm>nop - -/(?U)<.*>/ - abc<def>ghi<klm>nop - -/<.*?>/U - abc<def>ghi<klm>nop - -/={3,}/U - abc========def - -/(?U)={3,}?/ - abc========def - -/(?<!bar|cattle)foo/ - foo - catfoo - *** Failers - the barfoo - and cattlefoo - -/(?<=a+)b/ - -/(?<=aaa|b{0,3})b/ - -/(?<!(foo)a\1)bar/ - -/(?i)abc/ - -/(a|(?m)a)/ - -/(?i)^1234/ - -/(^b|(?i)^d)/ - -/(?s).*/ - -/[abcd]/S - -/(?i)[abcd]/S - -/(?m)[xy]|(b|c)/S - -/(^a|^b)/m - -/(?i)(^a|^b)/m - -/(a)(?(1)a|b|c)/ - -/(?(?=a)a|b|c)/ - -/(?(1a)/ - -/(?(?i))/ - -/(?(abc))/ - -/(?(?<ab))/ - -/((?s)blah)\s+\1/ - -/((?i)blah)\s+\1/ - -/((?i)b)/DS - -/(a*b|(?i:c*(?-i)d))/S - -/a$/ - a - a\n - *** Failers - \Za - \Za\n - -/a$/m - a - a\n - \Za\n - *** Failers - \Za - -/\Aabc/m - -/^abc/m - -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/ - aaaaabbbbbcccccdef - -/(?<=foo)[ab]/S - -/(?<!foo)(alpha|omega)/S - -/(?!alphabet)[ab]/S - -/(?<=foo\n)^bar/m - -/(?>^abc)/m - abc - def\nabc - *** Failers - defabc - -/(?<=ab(c+)d)ef/ - -/(?<=ab(?<=c+)d)ef/ - -/(?<=ab(c|de)f)g/ - -/The next three are in testinput2 because they have variable length branches/ - -/(?<=bullock|donkey)-cart/ - the bullock-cart - a donkey-cart race - *** Failers - cart - horse-and-cart - -/(?<=ab(?i)x|y|z)/ - -/(?>.*)(?<=(abcd)|(xyz))/ - alphabetabcd - endingxyz - -/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/ - abxyZZ - abXyZZ - ZZZ - zZZ - bZZ - BZZ - *** Failers - ZZ - abXYZZ - zzz - bzz - -/(?<!(foo)a)bar/ - bar - foobbar - *** Failers - fooabar - -/This one is here because Perl 5.005_02 doesn't fail it/ - -/^(a)?(?(1)a|b)+$/ - *** Failers - a - -/This one is here because I think Perl 5.005_02 gets the setting of $1 wrong/ - -/^(a\1?){4}$/ - aaaaaa - -/These are syntax tests from Perl 5.005/ - -/a[b-a]/ - -/a[]b/ - -/a[/ - -/*a/ - -/(*)b/ - -/abc)/ - -/(abc/ - -/a**/ - -/)(/ - -/\1/ - -/\2/ - -/(a)|\2/ - -/a[b-a]/i - -/a[]b/i - -/a[/i - -/*a/i - -/(*)b/i - -/abc)/i - -/(abc/i - -/a**/i - -/)(/i - -/:(?:/ - -/(?<%)b/ - -/a(?{)b/ - -/a(?{{})b/ - -/a(?{}})b/ - -/a(?{"{"})b/ - -/a(?{"{"}})b/ - -/(?(1?)a|b)/ - -/(?(1)a|b|c)/ - -/[a[:xyz:/ - -/(?<=x+)y/ - -/a{37,17}/ - -/abc/\ - -/abc/\P - -/abc/\i - -/(a)bc(d)/ - abcd - abcd\C2 - abcd\C5 - -/(.{20})/ - abcdefghijklmnopqrstuvwxyz - abcdefghijklmnopqrstuvwxyz\C1 - abcdefghijklmnopqrstuvwxyz\G1 - -/(.{15})/ - abcdefghijklmnopqrstuvwxyz - abcdefghijklmnopqrstuvwxyz\C1\G1 - -/(.{16})/ - abcdefghijklmnopqrstuvwxyz - abcdefghijklmnopqrstuvwxyz\C1\G1\L - -/^(a|(bc))de(f)/ - adef\G1\G2\G3\G4\L - bcdef\G1\G2\G3\G4\L - adefghijk\C0 - -/^abc\00def/ - abc\00def\L\C0 - -/word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)?)?)?)?)?)?)?)?)?otherword/M - -/.*X/D - -/.*X/Ds - -/(.*X|^B)/D - -/(.*X|^B)/Ds - -/(?s)(.*X|^B)/D - -/(?s:.*X|^B)/D - -/\Biss\B/+ - Mississippi - -/\Biss\B/+P - Mississippi - -/iss/G+ - Mississippi - -/\Biss\B/G+ - Mississippi - -/\Biss\B/g+ - Mississippi - *** Failers - Mississippi\A - -/(?<=[Ms])iss/g+ - Mississippi - -/(?<=[Ms])iss/G+ - Mississippi - -/^iss/g+ - ississippi - -/.*iss/g+ - abciss\nxyzisspqr - -/.i./+g - Mississippi - Mississippi\A - Missouri river - Missouri river\A - -/^.is/+g - Mississippi - -/^ab\n/g+ - ab\nab\ncd - -/^ab\n/mg+ - ab\nab\ncd - -/abc/ - -/abc|bac/ - -/(abc|bac)/ - -/(abc|(c|dc))/ - -/(abc|(d|de)c)/ - -/a*/ - -/a+/ - -/(baa|a+)/ - -/a{0,3}/ - -/baa{3,}/ - -/"([^\\"]+|\\.)*"/ - -/(abc|ab[cd])/ - -/(a|.)/ - -/a|ba|\w/ - -/abc(?=pqr)/ - -/...(?<=abc)/ - -/abc(?!pqr)/ - -/ab./ - -/ab[xyz]/ - -/abc*/ - -/ab.c*/ - -/a.c*/ - -/.c*/ - -/ac*/ - -/(a.c*|b.c*)/ - -/a.c*|aba/ - -/.+a/ - -/(?=abcda)a.*/ - -/(?=a)a.*/ - -/a(b)*/ - -/a\d*/ - -/ab\d*/ - -/a(\d)*/ - -/abcde{0,0}/ - -/ab\d+/ - -/a(?(1)b)/ - -/a(?(1)bag|big)/ - -/a(?(1)bag|big)*/ - -/a(?(1)bag|big)+/ - -/a(?(1)b..|b..)/ - -/ab\d{0}e/ - -/a?b?/ - a - b - ab - \ - *** Failers - \N - -/|-/ - abcd - -abc - \Nab-c - *** Failers - \Nabc - -/a*(b+)(z)(z)/P - aaaabbbbzzzz - aaaabbbbzzzz\O0 - aaaabbbbzzzz\O1 - aaaabbbbzzzz\O2 - aaaabbbbzzzz\O3 - aaaabbbbzzzz\O4 - aaaabbbbzzzz\O5 - -/^.?abcd/S - -/\( # ( at start - (?: # Non-capturing bracket - (?>[^()]+) # Either a sequence of non-brackets (no backtracking) - | # Or - (?R) # Recurse - i.e. nested bracketed string - )* # Zero or more contents - \) # Closing ) - /x - (abcd) - (abcd)xyz - xyz(abcd) - (ab(xy)cd)pqr - (ab(xycd)pqr - () abc () - 12(abcde(fsh)xyz(foo(bar))lmno)89 - *** Failers - abcd - abcd) - (abcd - -/\( ( (?>[^()]+) | (?R) )* \) /xg - (ab(xy)cd)pqr - 1(abcd)(x(y)z)pqr - -/\( (?: (?>[^()]+) | (?R) ) \) /x - (abcd) - (ab(xy)cd) - (a(b(c)d)e) - ((ab)) - *** Failers - () - -/\( (?: (?>[^()]+) | (?R) )? \) /x - () - 12(abcde(fsh)xyz(foo(bar))lmno)89 - -/\( ( (?>[^()]+) | (?R) )* \) /x - (ab(xy)cd) - -/\( ( ( (?>[^()]+) | (?R) )* ) \) /x - (ab(xy)cd) - -/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /x - (ab(xy)cd) - (123ab(xy)cd) - -/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /x - (ab(xy)cd) - (123ab(xy)cd) - -/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /x - (ab(xy)cd) - -/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /x - (abcd(xyz<p>qrs)123) - -/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /x - (ab(cd)ef) - (ab(cd(ef)gh)ij) - -/^[[:alnum:]]/D - -/^[[:alpha:]]/D - -/^[[:ascii:]]/D - -/^[[:blank:]]/D - -/^[[:cntrl:]]/D - -/^[[:digit:]]/D - -/^[[:graph:]]/D - -/^[[:lower:]]/D - -/^[[:print:]]/D - -/^[[:punct:]]/D - -/^[[:space:]]/D - -/^[[:upper:]]/D - -/^[[:xdigit:]]/D - -/^[[:word:]]/D - -/^[[:^cntrl:]]/D - -/^[12[:^digit:]]/D - -/^[[:^blank:]]/D - -/[01[:alpha:]%]/D - -/[[.ch.]]/ - -/[[=ch=]]/ - -/[[:rhubarb:]]/ - -/[[:upper:]]/i - A - a - -/[[:lower:]]/i - A - a - -/((?-i)[[:lower:]])[[:lower:]]/i - ab - aB - *** Failers - Ab - AB - -/[\200-\410]/ - -/^(?(0)f|b)oo/ - -/This one's here because of the large output vector needed/ - -/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/ - \O900 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC - -/This one's here because Perl does this differently and PCRE can't at present/ - -/(main(O)?)+/ - mainmain - mainOmain - -/These are all cases where Perl does it differently (nested captures)/ - -/^(a(b)?)+$/ - aba - -/^(aa(bb)?)+$/ - aabbaa - -/^(aa|aa(bb))+$/ - aabbaa - -/^(aa(bb)??)+$/ - aabbaa - -/^(?:aa(bb)?)+$/ - aabbaa - -/^(aa(b(b))?)+$/ - aabbaa - -/^(?:aa(b(b))?)+$/ - aabbaa - -/^(?:aa(b(?:b))?)+$/ - aabbaa - -/^(?:aa(bb(?:b))?)+$/ - aabbbaa - -/^(?:aa(b(?:bb))?)+$/ - aabbbaa - -/^(?:aa(?:b(b))?)+$/ - aabbaa - -/^(?:aa(?:b(bb))?)+$/ - aabbbaa - -/^(aa(b(bb))?)+$/ - aabbbaa - -/^(aa(bb(bb))?)+$/ - aabbbbaa - -/--------------------------------------------------------------------/ - -/#/xMD - -/a#/xMD - -/[\s]/D - -/[\S]/D - -/a(?i)b/D - ab - aB - *** Failers - AB - -/(a(?i)b)/D - ab - aB - *** Failers - AB - -/ (?i)abc/xD - -/#this is a comment - (?i)abc/xD - -/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D - -/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D - -/\Q\E/D - \ - -/\Q\Ex/D - -/ \Q\E/D - -/a\Q\E/D - abc - bca - bac - -/a\Q\Eb/D - abc - -/\Q\Eabc/D - -/x*+\w/D - *** Failers - xxxxx - -/x?+/D - -/x++/D - -/x{1,3}+/D - -/(x)*+/D - -/^(\w++|\s++)*$/ - now is the time for all good men to come to the aid of the party - *** Failers - this is not a line with only words and spaces! - -/(\d++)(\w)/ - 12345a - *** Failers - 12345+ - -/a++b/ - aaab - -/(a++b)/ - aaab - -/(a++)b/ - aaab - -/([^()]++|\([^()]*\))+/ - ((abc(ade)ufh()()x - -/\(([^()]++|\([^()]+\))+\)/ - (abc) - (abc(def)xyz) - *** Failers - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/(abc){1,3}+/D - -/a+?+/ - -/a{2,3}?+b/ - -/(?U)a+?+/ - -/a{2,3}?+b/U - -/x(?U)a++b/D - xaaaab - -/(?U)xa++b/D - xaaaab - -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/D - -/^x(?U)a+b/D - -/^x(?U)(a+)b/D - -/[.x.]/ - -/[=x=]/ - -/[:x:]/ - -/\l/ - -/\L/ - -/\N{name}/ - -/\pP/ - -/\PP/ - -/\p{prop}/ - -/\P{prop}/ - -/\u/ - -/\U/ - -/\X/ - -/[/ - -/[a-/ - -/[[:space:]/ - -/[\s]/DM - -/[[:space:]]/DM - -/[[:space:]abcde]/DM - -/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x - <> - <abcd> - <abc <123> hij> - <abc <def> hij> - <abc<>def> - <abc<> - *** Failers - <abc - -|8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|DM - -|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|DM - -/(.*)\d+\1/I - -/(.*)\d+/I - -/(.*)\d+\1/Is - -/(.*)\d+/Is - -/(.*(xyz))\d+\2/I - -/((.*))\d+\1/I - abc123bc - -/a[b]/I - -/(?=a).*/I - -/(?=abc).xyz/iI - -/(?=abc)(?i).xyz/I - -/(?=a)(?=b)/I - -/(?=.)a/I - -/((?=abcda)a)/I - -/((?=abcda)ab)/I - -/()a/I - -/(?(1)ab|ac)/I - -/(?(1)abz|acz)/I - -/(?(1)abz)/I - -/(?(1)abz)123/I - -/(a)+/I - -/(a){2,3}/I - -/(a)*/I - -/[a]/I - -/[ab]/I - -/[ab]/IS - -/[^a]/I - -/\d456/I - -/\d456/IS - -/a^b/I - -/^a/mI - abcde - xy\nabc - *** Failers - xyabc - -/c|abc/I - -/(?i)[ab]/IS - -/[ab](?i)cd/IS - -/abc(?C)def/ - abcdef - 1234abcdef - *** Failers - abcxyz - abcxyzf - -/abc(?C)de(?C1)f/ - 123abcdef - -/(?C1)\dabc(?C2)def/ - 1234abcdef - *** Failers - abcdef - -/(?C255)ab/ - -/(?C256)ab/ - -/(?Cab)xx/ - -/(?C12vr)x/ - -/abc(?C)def/ - *** Failers - \x83\x0\x61bcdef - -/(abc)(?C)de(?C1)f/ - 123abcdef - 123abcdef\C+ - 123abcdef\C- - *** Failers - 123abcdef\C!1 - -/(?C0)(abc(?C1))*/ - abcabcabc - abcabc\C!1!3 - *** Failers - abcabcabc\C!1!3 - -/(\d{3}(?C))*/ - 123\C+ - 123456\C+ - 123456789\C+ - -/((xyz)(?C)p|(?C1)xyzabc)/ - xyzabc\C+ - -/(X)((xyz)(?C)p|(?C1)xyzabc)/ - Xxyzabc\C+ - -/(?=(abc))(?C)abcdef/ - abcdef\C+ - -/(?!(abc)(?C1)d)(?C2)abcxyz/ - abcxyz\C+ - -/(?<=(abc)(?C))xyz/ - abcxyz\C+ - -/(?C)abc/ - -/(?C)^abc/ - -/(?C)a|b/S - -/(?R)/ - -/(a|(?R))/ - -/(ab|(bc|(de|(?R))))/ - -/x(ab|(bc|(de|(?R))))/ - xab - xbc - xde - xxab - xxxab - *** Failers - xyab - -/(ab|(bc|(de|(?1))))/ - -/x(ab|(bc|(de|(?1)x)x)x)/ - -/^([^()]|\((?1)*\))*$/ - abc - a(b)c - a(b(c))d - *** Failers) - a(b(c)d - -/^>abc>([^()]|\((?1)*\))*<xyz<$/ - >abc>123<xyz< - >abc>1(2)3<xyz< - >abc>(1(2)3)<xyz< - -/(a(?1)b)/D - -/(a(?1)+b)/D - -/^\W*(?:((.)\W*(?1)\W*\2|)|((.)\W*(?3)\W*\4|\W*.\W*))\W*$/i - 1221 - Satan, oscillate my metallic sonatas! - A man, a plan, a canal: Panama! - Able was I ere I saw Elba. - *** Failers - The quick brown fox - -/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/ - 12 - (((2+2)*-3)-7) - -12 - *** Failers - ((2+2)*-3)-7) - -/^(x(y|(?1){2})z)/ - xyz - xxyzxyzz - *** Failers - xxyzz - xxyzxyzxyzz - -/((< (?: (?(R) \d++ | [^<>]*+) | (?2)) * >))/x - <> - <abcd> - <abc <123> hij> - <abc <def> hij> - <abc<>def> - <abc<> - *** Failers - <abc - -/(?1)/ - -/((?2)(abc)/ - -/^(abc)def(?1)/ - abcdefabc - -/^(a|b|c)=(?1)+/ - a=a - a=b - a=bc - -/^(a|b|c)=((?1))+/ - a=a - a=b - a=bc - -/a(?P<name1>b|c)d(?P<longername2>e)/D - abde - acde - -/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/D - -/(?P<a>a)...(?P=a)bbb(?P>a)d/D - -/^\W*(?:(?P<one>(?P<two>.)\W*(?P>one)\W*(?P=two)|)|(?P<three>(?P<four>.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/i - 1221 - Satan, oscillate my metallic sonatas! - A man, a plan, a canal: Panama! - Able was I ere I saw Elba. - *** Failers - The quick brown fox - -/((?(R)a|b))\1(?1)?/ - bb - bbaa - -/(.*)a/sI - -/(.*)a\1/sI - -/(.*)a(b)\2/sI - -/((.*)a|(.*)b)z/sI - -/((.*)a|(.*)b)z\1/sI - -/((.*)a|(.*)b)z\2/sI - -/((.*)a|(.*)b)z\3/sI - -/((.*)a|^(.*)b)z\3/sI - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/sI - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/sI - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/sI - -/(a)(bc)/ND - abc - -/(?P<one>a)(bc)/ND - abc - -/(a)(?P<named>bc)/ND - -/(a+)*zz/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\M - aaaaaaaaaaaaaz\M - -/(aaa(?C1)bbb|ab)/ - aaabbb - aaabbb\C*0 - aaabbb\C*1 - aaabbb\C*-1 - -/ab(?P<one>cd)ef(?P<two>gh)/ - abcdefgh - abcdefgh\C1\Gtwo - abcdefgh\Cone\Ctwo - abcdefgh\Cthree - -/(?P<Tes>)(?P<Test>)/D - -/(?P<Test>)(?P<Tes>)/D - -/(?P<Z>zz)(?P<A>aa)/ - zzaa\CZ - zzaa\CA - -/(?P<x>eks)(?P<x>eccs)/ - -/(?P<abc>abc(?P<def>def)(?P<abc>xyz))/ - -"\[((?P<elem>\d+)(,(?P>elem))*)\]" - [10,20,30,5,5,4,4,2,43,23,4234] - *** Failers - [] - -"\[((?P<elem>\d+)(,(?P>elem))*)?\]" - [10,20,30,5,5,4,4,2,43,23,4234] - [] - -/(a(b(?2)c))?/D - -/(a(b(?2)c))*/D - -/(a(b(?2)c)){0,2}/D - -/[ab]{1}+/D - -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/i - Baby Bjorn Active Carrier - With free SHIPPING!! - -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/iS - Baby Bjorn Active Carrier - With free SHIPPING!! - -/a*.*b/SD - -/(a|b)*.?c/SD - -/ End of testinput2 / diff --git a/external-libs/pcre/testdata/testinput3 b/external-libs/pcre/testdata/testinput3 deleted file mode 100644 index c2abdbfd..00000000 --- a/external-libs/pcre/testdata/testinput3 +++ /dev/null @@ -1,65 +0,0 @@ -/^[\w]+/ - *** Failers - cole - -/^[\w]+/Lfr_FR - cole - -/^[\w]+/ - *** Failers - cole - -/^[\W]+/ - cole - -/^[\W]+/Lfr_FR - *** Failers - cole - -/[\b]/ - \b - *** Failers - a - -/[\b]/Lfr_FR - \b - *** Failers - a - -/^\w+/ - *** Failers - cole - -/^\w+/Lfr_FR - cole - -/(.+)\b(.+)/ - cole - -/(.+)\b(.+)/Lfr_FR - *** Failers - cole - -/cole/i - cole - *** Failers - cole - -/cole/iLfr_FR - cole - cole - -/\w/IS - -/\w/ISLfr_FR - -/^[\xc8-\xc9]/iLfr_FR - cole - cole - -/^[\xc8-\xc9]/Lfr_FR - cole - *** Failers - cole - -/ End of testinput3 / diff --git a/external-libs/pcre/testdata/testinput4 b/external-libs/pcre/testdata/testinput4 deleted file mode 100644 index f9212150..00000000 --- a/external-libs/pcre/testdata/testinput4 +++ /dev/null @@ -1,517 +0,0 @@ -/-- Do not use the \x{} construct except with patterns that have the --/ -/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ -/-- that option is set. However, the latest Perls recognize them always. --/ - -/a.b/8 - acb - a\x7fb - a\x{100}b - *** Failers - a\nb - -/a(.{3})b/8 - a\x{4000}xyb - a\x{4000}\x7fyb - a\x{4000}\x{100}yb - *** Failers - a\x{4000}b - ac\ncb - -/a(.*?)(.)/ - a\xc0\x88b - -/a(.*?)(.)/8 - a\x{100}b - -/a(.*)(.)/ - a\xc0\x88b - -/a(.*)(.)/8 - a\x{100}b - -/a(.)(.)/ - a\xc0\x92bcd - -/a(.)(.)/8 - a\x{240}bcd - -/a(.?)(.)/ - a\xc0\x92bcd - -/a(.?)(.)/8 - a\x{240}bcd - -/a(.??)(.)/ - a\xc0\x92bcd - -/a(.??)(.)/8 - a\x{240}bcd - -/a(.{3})b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - *** Failers - a\x{1234}b - ac\ncb - -/a(.{3,})b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - a\x{1234}\x{4321}\x{3412}\x{3421}b - *** Failers - a\x{1234}b - -/a(.{3,}?)b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - a\x{1234}\x{4321}\x{3412}\x{3421}b - *** Failers - a\x{1234}b - -/a(.{3,5})b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - a\x{1234}\x{4321}\x{3412}\x{3421}b - axbxxbcdefghijb - axxxxxbcdefghijb - *** Failers - a\x{1234}b - axxxxxxbcdefghijb - -/a(.{3,5}?)b/8 - a\x{1234}xyb - a\x{1234}\x{4321}yb - a\x{1234}\x{4321}\x{3412}b - axxxxbcdefghijb - a\x{1234}\x{4321}\x{3412}\x{3421}b - axbxxbcdefghijb - axxxxxbcdefghijb - *** Failers - a\x{1234}b - axxxxxxbcdefghijb - -/^[a\x{c0}]/8 - *** Failers - \x{100} - -/(?<=aXb)cd/8 - aXbcd - -/(?<=a\x{100}b)cd/8 - a\x{100}bcd - -/(?<=a\x{100000}b)cd/8 - a\x{100000}bcd - -/(?:\x{100}){3}b/8 - \x{100}\x{100}\x{100}b - *** Failers - \x{100}\x{100}b - -/\x{ab}/8 - \x{ab} - \xc2\xab - *** Failers - \x00{ab} - -/(?<=(.))X/8 - WXYZ - \x{256}XYZ - *** Failers - XYZ - -/X(\C{3})/8 - X\x{1234} - -/X(\C{4})/8 - X\x{1234}YZ - -/X\C*/8 - XYZabcdce - -/X\C*?/8 - XYZabcde - -/X\C{3,5}/8 - Xabcdefg - X\x{1234} - X\x{1234}YZ - X\x{1234}\x{512} - X\x{1234}\x{512}YZ - -/X\C{3,5}?/8 - Xabcdefg - X\x{1234} - X\x{1234}YZ - X\x{1234}\x{512} - -/[^a]+/8g - bcd - \x{100}aY\x{256}Z - -/^[^a]{2}/8 - \x{100}bc - -/^[^a]{2,}/8 - \x{100}bcAa - -/^[^a]{2,}?/8 - \x{100}bca - -/[^a]+/8ig - bcd - \x{100}aY\x{256}Z - -/^[^a]{2}/8i - \x{100}bc - -/^[^a]{2,}/8i - \x{100}bcAa - -/^[^a]{2,}?/8i - \x{100}bca - -/\x{100}{0,0}/8 - abcd - -/\x{100}?/8 - abcd - \x{100}\x{100} - -/\x{100}{0,3}/8 - \x{100}\x{100} - \x{100}\x{100}\x{100}\x{100} - -/\x{100}*/8 - abce - \x{100}\x{100}\x{100}\x{100} - -/\x{100}{1,1}/8 - abcd\x{100}\x{100}\x{100}\x{100} - -/\x{100}{1,3}/8 - abcd\x{100}\x{100}\x{100}\x{100} - -/\x{100}+/8 - abcd\x{100}\x{100}\x{100}\x{100} - -/\x{100}{3}/8 - abcd\x{100}\x{100}\x{100}XX - -/\x{100}{3,5}/8 - abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX - -/\x{100}{3,}/8 - abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX - -/(?<=a\x{100}{2}b)X/8+ - Xyyya\x{100}\x{100}bXzzz - -/\D*/8 - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/\D*/8 - \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - -/\D/8 - 1X2 - 1\x{100}2 - -/>\S/8 - > >X Y - > >\x{100} Y - -/\W/8 - A.B - A\x{100}B - -/\d/8 - \x{100}3 - -/\s/8 - \x{100} X - -/\w/8 - \x{100}X - -/\D+/8 - 12abcd34 - *** Failers - 1234 - -/\D{2,3}/8 - 12abcd34 - 12ab34 - *** Failers - 1234 - 12a34 - -/\D{2,3}?/8 - 12abcd34 - 12ab34 - *** Failers - 1234 - 12a34 - -/\d+/8 - 12abcd34 - *** Failers - -/\d{2,3}/8 - 12abcd34 - 1234abcd - *** Failers - 1.4 - -/\d{2,3}?/8 - 12abcd34 - 1234abcd - *** Failers - 1.4 - -/\S+/8 - 12abcd34 - *** Failers - \ \ - -/\S{2,3}/8 - 12abcd34 - 1234abcd - *** Failers - \ \ - -/\S{2,3}?/8 - 12abcd34 - 1234abcd - *** Failers - \ \ - -/>\s+</8+ - 12> <34 - *** Failers - -/>\s{2,3}</8+ - ab> <cd - ab> <ce - *** Failers - ab> <cd - -/>\s{2,3}?</8+ - ab> <cd - ab> <ce - *** Failers - ab> <cd - -/\w+/8 - 12 34 - *** Failers - +++=*! - -/\w{2,3}/8 - ab cd - abcd ce - *** Failers - a.b.c - -/\w{2,3}?/8 - ab cd - abcd ce - *** Failers - a.b.c - -/\W+/8 - 12====34 - *** Failers - abcd - -/\W{2,3}/8 - ab====cd - ab==cd - *** Failers - a.b.c - -/\W{2,3}?/8 - ab====cd - ab==cd - *** Failers - a.b.c - -/[\x{100}]/8 - \x{100} - Z\x{100} - \x{100}Z - *** Failers - -/[Z\x{100}]/8 - Z\x{100} - \x{100} - \x{100}Z - *** Failers - -/[\x{100}\x{200}]/8 - ab\x{100}cd - ab\x{200}cd - *** Failers - -/[\x{100}-\x{200}]/8 - ab\x{100}cd - ab\x{200}cd - ab\x{111}cd - *** Failers - -/[z-\x{200}]/8 - ab\x{100}cd - ab\x{200}cd - ab\x{111}cd - abzcd - ab|cd - *** Failers - -/[Q\x{100}\x{200}]/8 - ab\x{100}cd - ab\x{200}cd - Q? - *** Failers - -/[Q\x{100}-\x{200}]/8 - ab\x{100}cd - ab\x{200}cd - ab\x{111}cd - Q? - *** Failers - -/[Qz-\x{200}]/8 - ab\x{100}cd - ab\x{200}cd - ab\x{111}cd - abzcd - ab|cd - Q? - *** Failers - -/[\x{100}\x{200}]{1,3}/8 - ab\x{100}cd - ab\x{200}cd - ab\x{200}\x{100}\x{200}\x{100}cd - *** Failers - -/[\x{100}\x{200}]{1,3}?/8 - ab\x{100}cd - ab\x{200}cd - ab\x{200}\x{100}\x{200}\x{100}cd - *** Failers - -/[Q\x{100}\x{200}]{1,3}/8 - ab\x{100}cd - ab\x{200}cd - ab\x{200}\x{100}\x{200}\x{100}cd - *** Failers - -/[Q\x{100}\x{200}]{1,3}?/8 - ab\x{100}cd - ab\x{200}cd - ab\x{200}\x{100}\x{200}\x{100}cd - *** Failers - -/(?<=[\x{100}\x{200}])X/8 - abc\x{200}X - abc\x{100}X - *** Failers - X - -/(?<=[Q\x{100}\x{200}])X/8 - abc\x{200}X - abc\x{100}X - abQX - *** Failers - X - -/(?<=[\x{100}\x{200}]{3})X/8 - abc\x{100}\x{200}\x{100}X - *** Failers - abc\x{200}X - X - -/[^\x{100}\x{200}]X/8 - AX - \x{150}X - \x{500}X - *** Failers - \x{100}X - \x{200}X - -/[^Q\x{100}\x{200}]X/8 - AX - \x{150}X - \x{500}X - *** Failers - \x{100}X - \x{200}X - QX - -/[^\x{100}-\x{200}]X/8 - AX - \x{500}X - *** Failers - \x{100}X - \x{150}X - \x{200}X - -/a\Cb/ - aXb - a\nb - -/a\Cb/8 - aXb - a\nb - *** Failers - a\x{100}b - -/[z-\x{100}]/8i - z - Z - \x{100} - *** Failers - \x{101} - y - -/[\xFF]/ - >\xff< - -/[\xff]/8 - >\x{ff}< - -/[^\xFF]/ - XYZ - -/[^\xff]/8 - XYZ - \x{123} - -/^[ac]*b/8 - xb - -/^[ac\x{100}]*b/8 - xb - -/^[^x]*b/8i - xb - -/^[^x]*b/8 - xb - -/^\d*b/8 - xb - -/(|a)/g8 - catac - a\x{256}a - -/ End of testinput4 / diff --git a/external-libs/pcre/testdata/testinput5 b/external-libs/pcre/testdata/testinput5 deleted file mode 100644 index f71dc8d6..00000000 --- a/external-libs/pcre/testdata/testinput5 +++ /dev/null @@ -1,258 +0,0 @@ -/\x{100}/8DM - -/\x{1000}/8DM - -/\x{10000}/8DM - -/\x{100000}/8DM - -/\x{1000000}/8DM - -/\x{4000000}/8DM - -/\x{7fffFFFF}/8DM - -/[\x{ff}]/8DM - -/[\x{100}]/8DM - -/\x{ffffffff}/8 - -/\x{100000000}/8 - -/^\x{100}a\x{1234}/8 - \x{100}a\x{1234}bcd - -/\x80/8D - -/\xff/8D - -/\x{0041}\x{2262}\x{0391}\x{002e}/D8 - \x{0041}\x{2262}\x{0391}\x{002e} - -/\x{D55c}\x{ad6d}\x{C5B4}/D8 - \x{D55c}\x{ad6d}\x{C5B4} - -/\x{65e5}\x{672c}\x{8a9e}/D8 - \x{65e5}\x{672c}\x{8a9e} - -/\x{80}/D8 - -/\x{084}/D8 - -/\x{104}/D8 - -/\x{861}/D8 - -/\x{212ab}/D8 - -/.{3,5}X/D8 - \x{212ab}\x{212ab}\x{212ab}\x{861}X - - -/.{3,5}?/D8 - \x{212ab}\x{212ab}\x{212ab}\x{861} - -/-- These tests are here rather than in testinput4 because Perl 5.6 has --/ -/-- some problems with UTF-8 support, in the area of \x{..} where the --/ -/-- value is < 255. It grumbles about invalid UTF-8 strings. --/ - -/^[a\x{c0}]b/8 - \x{c0}b - -/^([a\x{c0}]*?)aa/8 - a\x{c0}aaaa/ - -/^([a\x{c0}]*?)aa/8 - a\x{c0}aaaa/ - a\x{c0}a\x{c0}aaa/ - -/^([a\x{c0}]*)aa/8 - a\x{c0}aaaa/ - a\x{c0}a\x{c0}aaa/ - -/^([a\x{c0}]*)a\x{c0}/8 - a\x{c0}aaaa/ - a\x{c0}a\x{c0}aaa/ - -/-- --/ - -/(?<=\C)X/8 - Should produce an error diagnostic - -/-- This one is here not because it's different to Perl, but because the --/ -/-- way the captured single-byte is displayed. (In Perl it becomes a --/ -/-- character, and you can't tell the difference.) --/ - -/X(\C)(.*)/8 - X\x{1234} - X\nabc - -/^[ab]/8D - bar - *** Failers - c - \x{ff} - \x{100} - -/^[^ab]/8D - c - \x{ff} - \x{100} - *** Failers - aaa - -/[^ab\xC0-\xF0]/8SD - \x{f1} - \x{bf} - \x{100} - \x{1000} - *** Failers - \x{c0} - \x{f0} - -/Ā{3,4}/8SD - \x{100}\x{100}\x{100}\x{100\x{100} - -/(\x{100}+|x)/8SD - -/(\x{100}*a|x)/8SD - -/(\x{100}{0,2}a|x)/8SD - -/(\x{100}{1,2}a|x)/8SD - -/\x{100}*(\d+|"(?1)")/8 - 1234 - "1234" - \x{100}1234 - "\x{100}1234" - \x{100}\x{100}12ab - \x{100}\x{100}"12" - *** Failers - \x{100}\x{100}abcd - -/\x{100}/8D - -/\x{100}*/8D - -/a\x{100}*/8D - -/ab\x{100}*/8D - -/a\x{100}\x{101}*/8D - -/a\x{100}\x{101}+/8D - -/\x{100}*A/8D - A - -/\x{100}*\d(?R)/8D - -/[^\x{c4}]/D - -/[^\x{c4}]/8D - -/[\x{100}]/8DM - \x{100} - Z\x{100} - \x{100}Z - *** Failers - -/[Z\x{100}]/8DM - Z\x{100} - \x{100} - \x{100}Z - *** Failers - -/[\x{200}-\x{100}]/8 - -/[Ā-Ą]/8 - \x{100} - \x{104} - *** Failers - \x{105} - \x{ff} - -/[z-\x{100}]/8D - -/[z-\x{100}]/8Di - -/[z\Qa-d]Ā\E]/8D - \x{100} - Ā - -/[\xFF]/D - >\xff< - -/[\xff]/D8 - >\x{ff}< - -/[^\xFF]/D - -/[^\xff]/8D - -/[Ä-Ü]/8 - Ö # Matches without Study - \x{d6} - -/[Ä-Ü]/8S - Ö <-- Same with Study - \x{d6} - -/[\x{c4}-\x{dc}]/8 - Ö # Matches without Study - \x{d6} - -/[\x{c4}-\x{dc}]/8S - Ö <-- Same with Study - \x{d6} - -/[]/8 - -//8 - -/xxx/8 - -/xxx/8?D - -/abc/8 - ] - - - \? - -/anything/8 - \xc0\x80 - \xc1\x8f - \xe0\x9f\x80 - \xf0\x8f\x80\x80 - \xf8\x87\x80\x80\x80 - \xfc\x83\x80\x80\x80\x80 - \xfe\x80\x80\x80\x80\x80 - \xff\x80\x80\x80\x80\x80 - \xc3\x8f - \xe0\xaf\x80 - \xe1\x80\x80 - \xf0\x9f\x80\x80 - \xf1\x8f\x80\x80 - \xf8\x88\x80\x80\x80 - \xf9\x87\x80\x80\x80 - \xfc\x84\x80\x80\x80\x80 - \xfd\x83\x80\x80\x80\x80 - -/\x{100}abc(xyz(?1))/8D - -/[^\x{100}]abc(xyz(?1))/8D - -/[ab\x{100}]abc(xyz(?1))/8D - -/(\x{100}(b(?2)c))?/D8 - -/(\x{100}(b(?2)c)){0,2}/D8 - -/(\x{100}(b(?1)c))?/D8 - -/(\x{100}(b(?1)c)){0,2}/D8 - -/ End of testinput5 / diff --git a/external-libs/pcre/testdata/testoutput1 b/external-libs/pcre/testdata/testoutput1 deleted file mode 100644 index d1e03b0e..00000000 --- a/external-libs/pcre/testdata/testoutput1 +++ /dev/null @@ -1,6274 +0,0 @@ -PCRE version 4.5 01-December-2003 - -/the quick brown fox/ - the quick brown fox - 0: the quick brown fox - The quick brown FOX -No match - What do you know about the quick brown fox? - 0: the quick brown fox - What do you know about THE QUICK BROWN FOX? -No match - -/The quick brown fox/i - the quick brown fox - 0: the quick brown fox - The quick brown FOX - 0: The quick brown FOX - What do you know about the quick brown fox? - 0: the quick brown fox - What do you know about THE QUICK BROWN FOX? - 0: THE QUICK BROWN FOX - -/abcd\t\n\r\f\a\e\071\x3b\$\\\?caxyz/ - abcd\t\n\r\f\a\e9;\$\\?caxyz - 0: abcd\x09\x0a\x0d\x0c\x07\x1b9;$\?caxyz - -/a*abc?xyz+pqr{3}ab{2,}xy{4,5}pq{0,6}AB{0,}zz/ - abxyzpqrrrabbxyyyypqAzz - 0: abxyzpqrrrabbxyyyypqAzz - abxyzpqrrrabbxyyyypqAzz - 0: abxyzpqrrrabbxyyyypqAzz - aabxyzpqrrrabbxyyyypqAzz - 0: aabxyzpqrrrabbxyyyypqAzz - aaabxyzpqrrrabbxyyyypqAzz - 0: aaabxyzpqrrrabbxyyyypqAzz - aaaabxyzpqrrrabbxyyyypqAzz - 0: aaaabxyzpqrrrabbxyyyypqAzz - abcxyzpqrrrabbxyyyypqAzz - 0: abcxyzpqrrrabbxyyyypqAzz - aabcxyzpqrrrabbxyyyypqAzz - 0: aabcxyzpqrrrabbxyyyypqAzz - aaabcxyzpqrrrabbxyyyypAzz - 0: aaabcxyzpqrrrabbxyyyypAzz - aaabcxyzpqrrrabbxyyyypqAzz - 0: aaabcxyzpqrrrabbxyyyypqAzz - aaabcxyzpqrrrabbxyyyypqqAzz - 0: aaabcxyzpqrrrabbxyyyypqqAzz - aaabcxyzpqrrrabbxyyyypqqqAzz - 0: aaabcxyzpqrrrabbxyyyypqqqAzz - aaabcxyzpqrrrabbxyyyypqqqqAzz - 0: aaabcxyzpqrrrabbxyyyypqqqqAzz - aaabcxyzpqrrrabbxyyyypqqqqqAzz - 0: aaabcxyzpqrrrabbxyyyypqqqqqAzz - aaabcxyzpqrrrabbxyyyypqqqqqqAzz - 0: aaabcxyzpqrrrabbxyyyypqqqqqqAzz - aaaabcxyzpqrrrabbxyyyypqAzz - 0: aaaabcxyzpqrrrabbxyyyypqAzz - abxyzzpqrrrabbxyyyypqAzz - 0: abxyzzpqrrrabbxyyyypqAzz - aabxyzzzpqrrrabbxyyyypqAzz - 0: aabxyzzzpqrrrabbxyyyypqAzz - aaabxyzzzzpqrrrabbxyyyypqAzz - 0: aaabxyzzzzpqrrrabbxyyyypqAzz - aaaabxyzzzzpqrrrabbxyyyypqAzz - 0: aaaabxyzzzzpqrrrabbxyyyypqAzz - abcxyzzpqrrrabbxyyyypqAzz - 0: abcxyzzpqrrrabbxyyyypqAzz - aabcxyzzzpqrrrabbxyyyypqAzz - 0: aabcxyzzzpqrrrabbxyyyypqAzz - aaabcxyzzzzpqrrrabbxyyyypqAzz - 0: aaabcxyzzzzpqrrrabbxyyyypqAzz - aaaabcxyzzzzpqrrrabbxyyyypqAzz - 0: aaaabcxyzzzzpqrrrabbxyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyyypqAzz - 0: aaaabcxyzzzzpqrrrabbbxyyyypqAzz - aaaabcxyzzzzpqrrrabbbxyyyyypqAzz - 0: aaaabcxyzzzzpqrrrabbbxyyyyypqAzz - aaabcxyzpqrrrabbxyyyypABzz - 0: aaabcxyzpqrrrabbxyyyypABzz - aaabcxyzpqrrrabbxyyyypABBzz - 0: aaabcxyzpqrrrabbxyyyypABBzz - >>>aaabxyzpqrrrabbxyyyypqAzz - 0: aaabxyzpqrrrabbxyyyypqAzz - >aaaabxyzpqrrrabbxyyyypqAzz - 0: aaaabxyzpqrrrabbxyyyypqAzz - >>>>abcxyzpqrrrabbxyyyypqAzz - 0: abcxyzpqrrrabbxyyyypqAzz - *** Failers -No match - abxyzpqrrabbxyyyypqAzz -No match - abxyzpqrrrrabbxyyyypqAzz -No match - abxyzpqrrrabxyyyypqAzz -No match - aaaabcxyzzzzpqrrrabbbxyyyyyypqAzz -No match - aaaabcxyzzzzpqrrrabbbxyyypqAzz -No match - aaabcxyzpqrrrabbxyyyypqqqqqqqAzz -No match - -/^(abc){1,2}zz/ - abczz - 0: abczz - 1: abc - abcabczz - 0: abcabczz - 1: abc - *** Failers -No match - zz -No match - abcabcabczz -No match - >>abczz -No match - -/^(b+?|a){1,2}?c/ - bc - 0: bc - 1: b - bbc - 0: bbc - 1: b - bbbc - 0: bbbc - 1: bb - bac - 0: bac - 1: a - bbac - 0: bbac - 1: a - aac - 0: aac - 1: a - abbbbbbbbbbbc - 0: abbbbbbbbbbbc - 1: bbbbbbbbbbb - bbbbbbbbbbbac - 0: bbbbbbbbbbbac - 1: a - *** Failers -No match - aaac -No match - abbbbbbbbbbbac -No match - -/^(b+|a){1,2}c/ - bc - 0: bc - 1: b - bbc - 0: bbc - 1: bb - bbbc - 0: bbbc - 1: bbb - bac - 0: bac - 1: a - bbac - 0: bbac - 1: a - aac - 0: aac - 1: a - abbbbbbbbbbbc - 0: abbbbbbbbbbbc - 1: bbbbbbbbbbb - bbbbbbbbbbbac - 0: bbbbbbbbbbbac - 1: a - *** Failers -No match - aaac -No match - abbbbbbbbbbbac -No match - -/^(b+|a){1,2}?bc/ - bbc - 0: bbc - 1: b - -/^(b*|ba){1,2}?bc/ - babc - 0: babc - 1: ba - bbabc - 0: bbabc - 1: ba - bababc - 0: bababc - 1: ba - *** Failers -No match - bababbc -No match - babababc -No match - -/^(ba|b*){1,2}?bc/ - babc - 0: babc - 1: ba - bbabc - 0: bbabc - 1: ba - bababc - 0: bababc - 1: ba - *** Failers -No match - bababbc -No match - babababc -No match - -/^\ca\cA\c[\c{\c:/ - \x01\x01\e;z - 0: \x01\x01\x1b;z - -/^[ab\]cde]/ - athing - 0: a - bthing - 0: b - ]thing - 0: ] - cthing - 0: c - dthing - 0: d - ething - 0: e - *** Failers -No match - fthing -No match - [thing -No match - \\thing -No match - -/^[]cde]/ - ]thing - 0: ] - cthing - 0: c - dthing - 0: d - ething - 0: e - *** Failers -No match - athing -No match - fthing -No match - -/^[^ab\]cde]/ - fthing - 0: f - [thing - 0: [ - \\thing - 0: \ - *** Failers - 0: * - athing -No match - bthing -No match - ]thing -No match - cthing -No match - dthing -No match - ething -No match - -/^[^]cde]/ - athing - 0: a - fthing - 0: f - *** Failers - 0: * - ]thing -No match - cthing -No match - dthing -No match - ething -No match - -/^\/ - - 0: \x81 - -/^/ - - 0: \xff - -/^[0-9]+$/ - 0 - 0: 0 - 1 - 0: 1 - 2 - 0: 2 - 3 - 0: 3 - 4 - 0: 4 - 5 - 0: 5 - 6 - 0: 6 - 7 - 0: 7 - 8 - 0: 8 - 9 - 0: 9 - 10 - 0: 10 - 100 - 0: 100 - *** Failers -No match - abc -No match - -/^.*nter/ - enter - 0: enter - inter - 0: inter - uponter - 0: uponter - -/^xxx[0-9]+$/ - xxx0 - 0: xxx0 - xxx1234 - 0: xxx1234 - *** Failers -No match - xxx -No match - -/^.+[0-9][0-9][0-9]$/ - x123 - 0: x123 - xx123 - 0: xx123 - 123456 - 0: 123456 - *** Failers -No match - 123 -No match - x1234 - 0: x1234 - -/^.+?[0-9][0-9][0-9]$/ - x123 - 0: x123 - xx123 - 0: xx123 - 123456 - 0: 123456 - *** Failers -No match - 123 -No match - x1234 - 0: x1234 - -/^([^!]+)!(.+)=apquxz\.ixr\.zzz\.ac\.uk$/ - abc!pqr=apquxz.ixr.zzz.ac.uk - 0: abc!pqr=apquxz.ixr.zzz.ac.uk - 1: abc - 2: pqr - *** Failers -No match - !pqr=apquxz.ixr.zzz.ac.uk -No match - abc!=apquxz.ixr.zzz.ac.uk -No match - abc!pqr=apquxz:ixr.zzz.ac.uk -No match - abc!pqr=apquxz.ixr.zzz.ac.ukk -No match - -/:/ - Well, we need a colon: somewhere - 0: : - *** Fail if we don't -No match - -/([\da-f:]+)$/i - 0abc - 0: 0abc - 1: 0abc - abc - 0: abc - 1: abc - fed - 0: fed - 1: fed - E - 0: E - 1: E - :: - 0: :: - 1: :: - 5f03:12C0::932e - 0: 5f03:12C0::932e - 1: 5f03:12C0::932e - fed def - 0: def - 1: def - Any old stuff - 0: ff - 1: ff - *** Failers -No match - 0zzz -No match - gzzz -No match - fed\x20 -No match - Any old rubbish -No match - -/^.*\.(\d{1,3})\.(\d{1,3})\.(\d{1,3})$/ - .1.2.3 - 0: .1.2.3 - 1: 1 - 2: 2 - 3: 3 - A.12.123.0 - 0: A.12.123.0 - 1: 12 - 2: 123 - 3: 0 - *** Failers -No match - .1.2.3333 -No match - 1.2.3 -No match - 1234.2.3 -No match - -/^(\d+)\s+IN\s+SOA\s+(\S+)\s+(\S+)\s*\(\s*$/ - 1 IN SOA non-sp1 non-sp2( - 0: 1 IN SOA non-sp1 non-sp2( - 1: 1 - 2: non-sp1 - 3: non-sp2 - 1 IN SOA non-sp1 non-sp2 ( - 0: 1 IN SOA non-sp1 non-sp2 ( - 1: 1 - 2: non-sp1 - 3: non-sp2 - *** Failers -No match - 1IN SOA non-sp1 non-sp2( -No match - -/^[a-zA-Z\d][a-zA-Z\d\-]*(\.[a-zA-Z\d][a-zA-z\d\-]*)*\.$/ - a. - 0: a. - Z. - 0: Z. - 2. - 0: 2. - ab-c.pq-r. - 0: ab-c.pq-r. - 1: .pq-r - sxk.zzz.ac.uk. - 0: sxk.zzz.ac.uk. - 1: .uk - x-.y-. - 0: x-.y-. - 1: .y- - *** Failers -No match - -abc.peq. -No match - -/^\*\.[a-z]([a-z\-\d]*[a-z\d]+)?(\.[a-z]([a-z\-\d]*[a-z\d]+)?)*$/ - *.a - 0: *.a - *.b0-a - 0: *.b0-a - 1: 0-a - *.c3-b.c - 0: *.c3-b.c - 1: 3-b - 2: .c - *.c-a.b-c - 0: *.c-a.b-c - 1: -a - 2: .b-c - 3: -c - *** Failers -No match - *.0 -No match - *.a- -No match - *.a-b.c- -No match - *.c-a.0-c -No match - -/^(?=ab(de))(abd)(e)/ - abde - 0: abde - 1: de - 2: abd - 3: e - -/^(?!(ab)de|x)(abd)(f)/ - abdf - 0: abdf - 1: <unset> - 2: abd - 3: f - -/^(?=(ab(cd)))(ab)/ - abcd - 0: ab - 1: abcd - 2: cd - 3: ab - -/^[\da-f](\.[\da-f])*$/i - a.b.c.d - 0: a.b.c.d - 1: .d - A.B.C.D - 0: A.B.C.D - 1: .D - a.b.c.1.2.3.C - 0: a.b.c.1.2.3.C - 1: .C - -/^\".*\"\s*(;.*)?$/ - \"1234\" - 0: "1234" - \"abcd\" ; - 0: "abcd" ; - 1: ; - \"\" ; rhubarb - 0: "" ; rhubarb - 1: ; rhubarb - *** Failers -No match - \"1234\" : things -No match - -/^$/ - \ - 0: - *** Failers -No match - -/ ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/x - ab c - 0: ab c - *** Failers -No match - abc -No match - ab cde -No match - -/(?x) ^ a (?# begins with a) b\sc (?# then b c) $ (?# then end)/ - ab c - 0: ab c - *** Failers -No match - abc -No match - ab cde -No match - -/^ a\ b[c ]d $/x - a bcd - 0: a bcd - a b d - 0: a b d - *** Failers -No match - abcd -No match - ab d -No match - -/^(a(b(c)))(d(e(f)))(h(i(j)))(k(l(m)))$/ - abcdefhijklm - 0: abcdefhijklm - 1: abc - 2: bc - 3: c - 4: def - 5: ef - 6: f - 7: hij - 8: ij - 9: j -10: klm -11: lm -12: m - -/^(?:a(b(c)))(?:d(e(f)))(?:h(i(j)))(?:k(l(m)))$/ - abcdefhijklm - 0: abcdefhijklm - 1: bc - 2: c - 3: ef - 4: f - 5: ij - 6: j - 7: lm - 8: m - -/^[\w][\W][\s][\S][\d][\D][\b][\n][\c]][\022]/ - a+ Z0+\x08\n\x1d\x12 - 0: a+ Z0+\x08\x0a\x1d\x12 - -/^[.^$|()*+?{,}]+/ - .^\$(*+)|{?,?} - 0: .^$(*+)|{?,?} - -/^a*\w/ - z - 0: z - az - 0: az - aaaz - 0: aaaz - a - 0: a - aa - 0: aa - aaaa - 0: aaaa - a+ - 0: a - aa+ - 0: aa - -/^a*?\w/ - z - 0: z - az - 0: a - aaaz - 0: a - a - 0: a - aa - 0: a - aaaa - 0: a - a+ - 0: a - aa+ - 0: a - -/^a+\w/ - az - 0: az - aaaz - 0: aaaz - aa - 0: aa - aaaa - 0: aaaa - aa+ - 0: aa - -/^a+?\w/ - az - 0: az - aaaz - 0: aa - aa - 0: aa - aaaa - 0: aa - aa+ - 0: aa - -/^\d{8}\w{2,}/ - 1234567890 - 0: 1234567890 - 12345678ab - 0: 12345678ab - 12345678__ - 0: 12345678__ - *** Failers -No match - 1234567 -No match - -/^[aeiou\d]{4,5}$/ - uoie - 0: uoie - 1234 - 0: 1234 - 12345 - 0: 12345 - aaaaa - 0: aaaaa - *** Failers -No match - 123456 -No match - -/^[aeiou\d]{4,5}?/ - uoie - 0: uoie - 1234 - 0: 1234 - 12345 - 0: 1234 - aaaaa - 0: aaaa - 123456 - 0: 1234 - -/\A(abc|def)=(\1){2,3}\Z/ - abc=abcabc - 0: abc=abcabc - 1: abc - 2: abc - def=defdefdef - 0: def=defdefdef - 1: def - 2: def - *** Failers -No match - abc=defdef -No match - -/^(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\11*(\3\4)\1(?#)2$/ - abcdefghijkcda2 - 0: abcdefghijkcda2 - 1: a - 2: b - 3: c - 4: d - 5: e - 6: f - 7: g - 8: h - 9: i -10: j -11: k -12: cd - abcdefghijkkkkcda2 - 0: abcdefghijkkkkcda2 - 1: a - 2: b - 3: c - 4: d - 5: e - 6: f - 7: g - 8: h - 9: i -10: j -11: k -12: cd - -/(cat(a(ract|tonic)|erpillar)) \1()2(3)/ - cataract cataract23 - 0: cataract cataract23 - 1: cataract - 2: aract - 3: ract - 4: - 5: 3 - catatonic catatonic23 - 0: catatonic catatonic23 - 1: catatonic - 2: atonic - 3: tonic - 4: - 5: 3 - caterpillar caterpillar23 - 0: caterpillar caterpillar23 - 1: caterpillar - 2: erpillar - 3: <unset> - 4: - 5: 3 - - -/^From +([^ ]+) +[a-zA-Z][a-zA-Z][a-zA-Z] +[a-zA-Z][a-zA-Z][a-zA-Z] +[0-9]?[0-9] +[0-9][0-9]:[0-9][0-9]/ - From abcd Mon Sep 01 12:33:02 1997 - 0: From abcd Mon Sep 01 12:33 - 1: abcd - -/^From\s+\S+\s+([a-zA-Z]{3}\s+){2}\d{1,2}\s+\d\d:\d\d/ - From abcd Mon Sep 01 12:33:02 1997 - 0: From abcd Mon Sep 01 12:33 - 1: Sep - From abcd Mon Sep 1 12:33:02 1997 - 0: From abcd Mon Sep 1 12:33 - 1: Sep - *** Failers -No match - From abcd Sep 01 12:33:02 1997 -No match - -/^12.34/s - 12\n34 - 0: 12\x0a34 - 12\r34 - 0: 12\x0d34 - -/\w+(?=\t)/ - the quick brown\t fox - 0: brown - -/foo(?!bar)(.*)/ - foobar is foolish see? - 0: foolish see? - 1: lish see? - -/(?:(?!foo)...|^.{0,2})bar(.*)/ - foobar crowbar etc - 0: rowbar etc - 1: etc - barrel - 0: barrel - 1: rel - 2barrel - 0: 2barrel - 1: rel - A barrel - 0: A barrel - 1: rel - -/^(\D*)(?=\d)(?!123)/ - abc456 - 0: abc - 1: abc - *** Failers -No match - abc123 -No match - -/^1234(?# test newlines - inside)/ - 1234 - 0: 1234 - -/^1234 #comment in extended re - /x - 1234 - 0: 1234 - -/#rhubarb - abcd/x - abcd - 0: abcd - -/^abcd#rhubarb/x - abcd - 0: abcd - -/^(a)\1{2,3}(.)/ - aaab - 0: aaab - 1: a - 2: b - aaaab - 0: aaaab - 1: a - 2: b - aaaaab - 0: aaaaa - 1: a - 2: a - aaaaaab - 0: aaaaa - 1: a - 2: a - -/(?!^)abc/ - the abc - 0: abc - *** Failers -No match - abc -No match - -/(?=^)abc/ - abc - 0: abc - *** Failers -No match - the abc -No match - -/^[ab]{1,3}(ab*|b)/ - aabbbbb - 0: aabb - 1: b - -/^[ab]{1,3}?(ab*|b)/ - aabbbbb - 0: aabbbbb - 1: abbbbb - -/^[ab]{1,3}?(ab*?|b)/ - aabbbbb - 0: aa - 1: a - -/^[ab]{1,3}(ab*?|b)/ - aabbbbb - 0: aabb - 1: b - -/ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional leading comment -(?: (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # one word, optionally followed by.... -(?: -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] | # atom and space parts, or... -\( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) | # comments, or... - -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -# quoted strings -)* -< (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # leading < -(?: @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* - -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* , (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -)* # further okay, if led by comma -: # closing colon -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* )? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) # initial word -(?: (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -" (?: # opening quote... -[^\\\x80-\xff\n\015"] # Anything except backslash and quote -| # or -\\ [^\x80-\xff] # Escaped something (something != CR) -)* " # closing quote -) )* # further okay, if led by a period -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* @ (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # initial subdomain -(?: # -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* \. # if led by a period... -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* (?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| \[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) # ...further okay -)* -# address spec -(?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* > # trailing > -# name and address -) (?: [\040\t] | \( -(?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] | \( (?: [^\\\x80-\xff\n\015()] | \\ [^\x80-\xff] )* \) )* -\) )* # optional trailing comment -/x - Alan Other <user\@dom.ain> - 0: Alan Other <user@dom.ain> - <user\@dom.ain> - 0: user@dom.ain - user\@dom.ain - 0: user@dom.ain - \"A. Other\" <user.1234\@dom.ain> (a comment) - 0: "A. Other" <user.1234@dom.ain> (a comment) - A. Other <user.1234\@dom.ain> (a comment) - 0: Other <user.1234@dom.ain> (a comment) - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay - A missing angle <user\@some.where - 0: user@some.where - *** Failers -No match - The quick brown fox -No match - -/[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional leading comment -(?: -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address -| # or -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -# leading word -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # "normal" atoms and or spaces -(?: -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -| -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -) # "special" comment or quoted string -[^()<>@,;:".\\\[\]\x80-\xff\000-\010\012-\037] * # more "normal" -)* -< -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# < -(?: -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -(?: , -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -)* # additional domains -: -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)? # optional route -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -# Atom -| # or -" # " -[^\\\x80-\xff\n\015"] * # normal -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015"] * )* # ( special normal* )* -" # " -# Quoted string -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# additional words -)* -@ -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -(?: -\. -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -(?: -[^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]+ # some number of atom characters... -(?![^(\040)<>@,;:".\\\[\]\000-\037\x80-\xff]) # ..not followed by something that could be part of an atom -| -\[ # [ -(?: [^\\\x80-\xff\n\015\[\]] | \\ [^\x80-\xff] )* # stuff -\] # ] -) -[\040\t]* # Nab whitespace. -(?: -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: # ( -(?: \\ [^\x80-\xff] | -\( # ( -[^\\\x80-\xff\n\015()] * # normal* -(?: \\ [^\x80-\xff] [^\\\x80-\xff\n\015()] * )* # (special normal*)* -\) # ) -) # special -[^\\\x80-\xff\n\015()] * # normal* -)* # )* -\) # ) -[\040\t]* )* # If comment found, allow more spaces. -# optional trailing comments -)* -# address spec -> # > -# name and address -) -/x - Alan Other <user\@dom.ain> - 0: Alan Other <user@dom.ain> - <user\@dom.ain> - 0: user@dom.ain - user\@dom.ain - 0: user@dom.ain - \"A. Other\" <user.1234\@dom.ain> (a comment) - 0: "A. Other" <user.1234@dom.ain> - A. Other <user.1234\@dom.ain> (a comment) - 0: Other <user.1234@dom.ain> - \"/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/\"\@x400-re.lay - 0: "/s=user/ou=host/o=place/prmd=uu.yy/admd= /c=gb/"@x400-re.lay - A missing angle <user\@some.where - 0: user@some.where - *** Failers -No match - The quick brown fox -No match - -/abc\0def\00pqr\000xyz\0000AB/ - abc\0def\00pqr\000xyz\0000AB - 0: abc\x00def\x00pqr\x00xyz\x000AB - abc456 abc\0def\00pqr\000xyz\0000ABCDE - 0: abc\x00def\x00pqr\x00xyz\x000AB - -/abc\x0def\x00pqr\x000xyz\x0000AB/ - abc\x0def\x00pqr\x000xyz\x0000AB - 0: abc\x0def\x00pqr\x000xyz\x0000AB - abc456 abc\x0def\x00pqr\x000xyz\x0000ABCDE - 0: abc\x0def\x00pqr\x000xyz\x0000AB - -/^[\000-\037]/ - \0A - 0: \x00 - \01B - 0: \x01 - \037C - 0: \x1f - -/\0*/ - \0\0\0\0 - 0: \x00\x00\x00\x00 - -/A\x0{2,3}Z/ - The A\x0\x0Z - 0: A\x00\x00Z - An A\0\x0\0Z - 0: A\x00\x00\x00Z - *** Failers -No match - A\0Z -No match - A\0\x0\0\x0Z -No match - -/^(cow|)\1(bell)/ - cowcowbell - 0: cowcowbell - 1: cow - 2: bell - bell - 0: bell - 1: - 2: bell - *** Failers -No match - cowbell -No match - -/^\s/ - \040abc - 0: - \x0cabc - 0: \x0c - \nabc - 0: \x0a - \rabc - 0: \x0d - \tabc - 0: \x09 - *** Failers -No match - abc -No match - -/^a b -
c/x - abc - 0: abc - -/^(a|)\1*b/ - ab - 0: ab - 1: a - aaaab - 0: aaaab - 1: a - b - 0: b - 1: - *** Failers -No match - acb -No match - -/^(a|)\1+b/ - aab - 0: aab - 1: a - aaaab - 0: aaaab - 1: a - b - 0: b - 1: - *** Failers -No match - ab -No match - -/^(a|)\1?b/ - ab - 0: ab - 1: a - aab - 0: aab - 1: a - b - 0: b - 1: - *** Failers -No match - acb -No match - -/^(a|)\1{2}b/ - aaab - 0: aaab - 1: a - b - 0: b - 1: - *** Failers -No match - ab -No match - aab -No match - aaaab -No match - -/^(a|)\1{2,3}b/ - aaab - 0: aaab - 1: a - aaaab - 0: aaaab - 1: a - b - 0: b - 1: - *** Failers -No match - ab -No match - aab -No match - aaaaab -No match - -/ab{1,3}bc/ - abbbbc - 0: abbbbc - abbbc - 0: abbbc - abbc - 0: abbc - *** Failers -No match - abc -No match - abbbbbc -No match - -/([^.]*)\.([^:]*):[T ]+(.*)/ - track1.title:TBlah blah blah - 0: track1.title:TBlah blah blah - 1: track1 - 2: title - 3: Blah blah blah - -/([^.]*)\.([^:]*):[T ]+(.*)/i - track1.title:TBlah blah blah - 0: track1.title:TBlah blah blah - 1: track1 - 2: title - 3: Blah blah blah - -/([^.]*)\.([^:]*):[t ]+(.*)/i - track1.title:TBlah blah blah - 0: track1.title:TBlah blah blah - 1: track1 - 2: title - 3: Blah blah blah - -/^[W-c]+$/ - WXY_^abc - 0: WXY_^abc - *** Failers -No match - wxy -No match - -/^[W-c]+$/i - WXY_^abc - 0: WXY_^abc - wxy_^ABC - 0: wxy_^ABC - -/^[\x3f-\x5F]+$/i - WXY_^abc - 0: WXY_^abc - wxy_^ABC - 0: wxy_^ABC - -/^abc$/m - abc - 0: abc - qqq\nabc - 0: abc - abc\nzzz - 0: abc - qqq\nabc\nzzz - 0: abc - -/^abc$/ - abc - 0: abc - *** Failers -No match - qqq\nabc -No match - abc\nzzz -No match - qqq\nabc\nzzz -No match - -/\Aabc\Z/m - abc - 0: abc - abc\n - 0: abc - *** Failers -No match - qqq\nabc -No match - abc\nzzz -No match - qqq\nabc\nzzz -No match - -/\A(.)*\Z/s - abc\ndef - 0: abc\x0adef - 1: f - -/\A(.)*\Z/m - *** Failers - 0: *** Failers - 1: s - abc\ndef -No match - -/(?:b)|(?::+)/ - b::c - 0: b - c::b - 0: :: - -/[-az]+/ - az- - 0: az- - *** Failers - 0: a - b -No match - -/[az-]+/ - za- - 0: za- - *** Failers - 0: a - b -No match - -/[a\-z]+/ - a-z - 0: a-z - *** Failers - 0: a - b -No match - -/[a-z]+/ - abcdxyz - 0: abcdxyz - -/[\d-]+/ - 12-34 - 0: 12-34 - *** Failers -No match - aaa -No match - -/[\d-z]+/ - 12-34z - 0: 12-34z - *** Failers -No match - aaa -No match - -/\x5c/ - \\ - 0: \ - -/\x20Z/ - the Zoo - 0: Z - *** Failers -No match - Zulu -No match - -/(abc)\1/i - abcabc - 0: abcabc - 1: abc - ABCabc - 0: ABCabc - 1: ABC - abcABC - 0: abcABC - 1: abc - -/ab{3cd/ - ab{3cd - 0: ab{3cd - -/ab{3,cd/ - ab{3,cd - 0: ab{3,cd - -/ab{3,4a}cd/ - ab{3,4a}cd - 0: ab{3,4a}cd - -/{4,5a}bc/ - {4,5a}bc - 0: {4,5a}bc - -/^a.b/ - a\rb - 0: a\x0db - *** Failers -No match - a\nb -No match - -/abc$/ - abc - 0: abc - abc\n - 0: abc - *** Failers -No match - abc\ndef -No match - -/(abc)\123/ - abc\x53 - 0: abcS - 1: abc - -/(abc)\223/ - abc\x93 - 0: abc\x93 - 1: abc - -/(abc)\323/ - abc\xd3 - 0: abc\xd3 - 1: abc - -/(abc)\500/ - abc\x40 - 0: abc@ - 1: abc - abc\100 - 0: abc@ - 1: abc - -/(abc)\5000/ - abc\x400 - 0: abc@0 - 1: abc - abc\x40\x30 - 0: abc@0 - 1: abc - abc\1000 - 0: abc@0 - 1: abc - abc\100\x30 - 0: abc@0 - 1: abc - abc\100\060 - 0: abc@0 - 1: abc - abc\100\60 - 0: abc@0 - 1: abc - -/abc\81/ - abc\081 - 0: abc\x0081 - abc\0\x38\x31 - 0: abc\x0081 - -/abc\91/ - abc\091 - 0: abc\x0091 - abc\0\x39\x31 - 0: abc\x0091 - -/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)(l)\12\123/ - abcdefghijkllS - 0: abcdefghijkllS - 1: a - 2: b - 3: c - 4: d - 5: e - 6: f - 7: g - 8: h - 9: i -10: j -11: k -12: l - -/(a)(b)(c)(d)(e)(f)(g)(h)(i)(j)(k)\12\123/ - abcdefghijk\12S - 0: abcdefghijk\x0aS - 1: a - 2: b - 3: c - 4: d - 5: e - 6: f - 7: g - 8: h - 9: i -10: j -11: k - -/ab\gdef/ - abgdef - 0: abgdef - -/a{0}bc/ - bc - 0: bc - -/(a|(bc)){0,0}?xyz/ - xyz - 0: xyz - -/abc[\10]de/ - abc\010de - 0: abc\x08de - -/abc[\1]de/ - abc\1de - 0: abc\x01de - -/(abc)[\1]de/ - abc\1de - 0: abc\x01de - 1: abc - -/(?s)a.b/ - a\nb - 0: a\x0ab - -/^([^a])([^\b])([^c]*)([^d]{3,4})/ - baNOTccccd - 0: baNOTcccc - 1: b - 2: a - 3: NOT - 4: cccc - baNOTcccd - 0: baNOTccc - 1: b - 2: a - 3: NOT - 4: ccc - baNOTccd - 0: baNOTcc - 1: b - 2: a - 3: NO - 4: Tcc - bacccd - 0: baccc - 1: b - 2: a - 3: - 4: ccc - *** Failers - 0: *** Failers - 1: * - 2: * - 3: * Fail - 4: ers - anything -No match - b\bc -No match - baccd -No match - -/[^a]/ - Abc - 0: A - -/[^a]/i - Abc - 0: b - -/[^a]+/ - AAAaAbc - 0: AAA - -/[^a]+/i - AAAaAbc - 0: bc - -/[^a]+/ - bbb\nccc - 0: bbb\x0accc - -/[^k]$/ - abc - 0: c - *** Failers - 0: s - abk -No match - -/[^k]{2,3}$/ - abc - 0: abc - kbc - 0: bc - kabc - 0: abc - *** Failers - 0: ers - abk -No match - akb -No match - akk -No match - -/^\d{8,}\@.+[^k]$/ - 12345678\@a.b.c.d - 0: 12345678@a.b.c.d - 123456789\@x.y.z - 0: 123456789@x.y.z - *** Failers -No match - 12345678\@x.y.uk -No match - 1234567\@a.b.c.d -No match - -/(a)\1{8,}/ - aaaaaaaaa - 0: aaaaaaaaa - 1: a - aaaaaaaaaa - 0: aaaaaaaaaa - 1: a - *** Failers -No match - aaaaaaa -No match - -/[^a]/ - aaaabcd - 0: b - aaAabcd - 0: A - -/[^a]/i - aaaabcd - 0: b - aaAabcd - 0: b - -/[^az]/ - aaaabcd - 0: b - aaAabcd - 0: A - -/[^az]/i - aaaabcd - 0: b - aaAabcd - 0: b - -/\000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377/ - \000\001\002\003\004\005\006\007\010\011\012\013\014\015\016\017\020\021\022\023\024\025\026\027\030\031\032\033\034\035\036\037\040\041\042\043\044\045\046\047\050\051\052\053\054\055\056\057\060\061\062\063\064\065\066\067\070\071\072\073\074\075\076\077\100\101\102\103\104\105\106\107\110\111\112\113\114\115\116\117\120\121\122\123\124\125\126\127\130\131\132\133\134\135\136\137\140\141\142\143\144\145\146\147\150\151\152\153\154\155\156\157\160\161\162\163\164\165\166\167\170\171\172\173\174\175\176\177\200\201\202\203\204\205\206\207\210\211\212\213\214\215\216\217\220\221\222\223\224\225\226\227\230\231\232\233\234\235\236\237\240\241\242\243\244\245\246\247\250\251\252\253\254\255\256\257\260\261\262\263\264\265\266\267\270\271\272\273\274\275\276\277\300\301\302\303\304\305\306\307\310\311\312\313\314\315\316\317\320\321\322\323\324\325\326\327\330\331\332\333\334\335\336\337\340\341\342\343\344\345\346\347\350\351\352\353\354\355\356\357\360\361\362\363\364\365\366\367\370\371\372\373\374\375\376\377 - 0: \x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff - -/P[^*]TAIRE[^*]{1,6}?LL/ - xxxxxxxxxxxPSTAIREISLLxxxxxxxxx - 0: PSTAIREISLL - -/P[^*]TAIRE[^*]{1,}?LL/ - xxxxxxxxxxxPSTAIREISLLxxxxxxxxx - 0: PSTAIREISLL - -/(\.\d\d[1-9]?)\d+/ - 1.230003938 - 0: .230003938 - 1: .23 - 1.875000282 - 0: .875000282 - 1: .875 - 1.235 - 0: .235 - 1: .23 - -/(\.\d\d((?=0)|\d(?=\d)))/ - 1.230003938 - 0: .23 - 1: .23 - 2: - 1.875000282 - 0: .875 - 1: .875 - 2: 5 - *** Failers -No match - 1.235 -No match - -/a(?)b/ - ab - 0: ab - -/\b(foo)\s+(\w+)/i - Food is on the foo table - 0: foo table - 1: foo - 2: table - -/foo(.*)bar/ - The food is under the bar in the barn. - 0: food is under the bar in the bar - 1: d is under the bar in the - -/foo(.*?)bar/ - The food is under the bar in the barn. - 0: food is under the bar - 1: d is under the - -/(.*)(\d*)/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: 53147 - 2: - -/(.*)(\d+)/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: 5314 - 2: 7 - -/(.*?)(\d*)/ - I have 2 numbers: 53147 - 0: - 1: - 2: - -/(.*?)(\d+)/ - I have 2 numbers: 53147 - 0: I have 2 - 1: I have - 2: 2 - -/(.*)(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: 5314 - 2: 7 - -/(.*?)(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: - 2: 53147 - -/(.*)\b(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: - 2: 53147 - -/(.*\D)(\d+)$/ - I have 2 numbers: 53147 - 0: I have 2 numbers: 53147 - 1: I have 2 numbers: - 2: 53147 - -/^\D*(?!123)/ - ABC123 - 0: AB - -/^(\D*)(?=\d)(?!123)/ - ABC445 - 0: ABC - 1: ABC - *** Failers -No match - ABC123 -No match - -/^[W-]46]/ - W46]789 - 0: W46] - -46]789 - 0: -46] - *** Failers -No match - Wall -No match - Zebra -No match - 42 -No match - [abcd] -No match - ]abcd[ -No match - -/^[W-\]46]/ - W46]789 - 0: W - Wall - 0: W - Zebra - 0: Z - Xylophone - 0: X - 42 - 0: 4 - [abcd] - 0: [ - ]abcd[ - 0: ] - \\backslash - 0: \ - *** Failers -No match - -46]789 -No match - well -No match - -/\d\d\/\d\d\/\d\d\d\d/ - 01/01/2000 - 0: 01/01/2000 - -/word (?:[a-zA-Z0-9]+ ){0,10}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark -No match - -/word (?:[a-zA-Z0-9]+ ){0,300}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope -No match - -/^(a){0,0}/ - bcd - 0: - abc - 0: - aab - 0: - -/^(a){0,1}/ - bcd - 0: - abc - 0: a - 1: a - aab - 0: a - 1: a - -/^(a){0,2}/ - bcd - 0: - abc - 0: a - 1: a - aab - 0: aa - 1: a - -/^(a){0,3}/ - bcd - 0: - abc - 0: a - 1: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: a - -/^(a){0,}/ - bcd - 0: - abc - 0: a - 1: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: a - aaaaaaaa - 0: aaaaaaaa - 1: a - -/^(a){1,1}/ - bcd -No match - abc - 0: a - 1: a - aab - 0: a - 1: a - -/^(a){1,2}/ - bcd -No match - abc - 0: a - 1: a - aab - 0: aa - 1: a - -/^(a){1,3}/ - bcd -No match - abc - 0: a - 1: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: a - -/^(a){1,}/ - bcd -No match - abc - 0: a - 1: a - aab - 0: aa - 1: a - aaa - 0: aaa - 1: a - aaaaaaaa - 0: aaaaaaaa - 1: a - -/.*\.gif/ - borfle\nbib.gif\nno - 0: bib.gif - -/.{0,}\.gif/ - borfle\nbib.gif\nno - 0: bib.gif - -/.*\.gif/m - borfle\nbib.gif\nno - 0: bib.gif - -/.*\.gif/s - borfle\nbib.gif\nno - 0: borfle\x0abib.gif - -/.*\.gif/ms - borfle\nbib.gif\nno - 0: borfle\x0abib.gif - -/.*$/ - borfle\nbib.gif\nno - 0: no - -/.*$/m - borfle\nbib.gif\nno - 0: borfle - -/.*$/s - borfle\nbib.gif\nno - 0: borfle\x0abib.gif\x0ano - -/.*$/ms - borfle\nbib.gif\nno - 0: borfle\x0abib.gif\x0ano - -/.*$/ - borfle\nbib.gif\nno\n - 0: no - -/.*$/m - borfle\nbib.gif\nno\n - 0: borfle - -/.*$/s - borfle\nbib.gif\nno\n - 0: borfle\x0abib.gif\x0ano\x0a - -/.*$/ms - borfle\nbib.gif\nno\n - 0: borfle\x0abib.gif\x0ano\x0a - -/(.*X|^B)/ - abcde\n1234Xyz - 0: 1234X - 1: 1234X - BarFoo - 0: B - 1: B - *** Failers -No match - abcde\nBar -No match - -/(.*X|^B)/m - abcde\n1234Xyz - 0: 1234X - 1: 1234X - BarFoo - 0: B - 1: B - abcde\nBar - 0: B - 1: B - -/(.*X|^B)/s - abcde\n1234Xyz - 0: abcde\x0a1234X - 1: abcde\x0a1234X - BarFoo - 0: B - 1: B - *** Failers -No match - abcde\nBar -No match - -/(.*X|^B)/ms - abcde\n1234Xyz - 0: abcde\x0a1234X - 1: abcde\x0a1234X - BarFoo - 0: B - 1: B - abcde\nBar - 0: B - 1: B - -/(?s)(.*X|^B)/ - abcde\n1234Xyz - 0: abcde\x0a1234X - 1: abcde\x0a1234X - BarFoo - 0: B - 1: B - *** Failers -No match - abcde\nBar -No match - -/(?s:.*X|^B)/ - abcde\n1234Xyz - 0: abcde\x0a1234X - BarFoo - 0: B - *** Failers -No match - abcde\nBar -No match - -/^.*B/ - **** Failers -No match - abc\nB -No match - -/(?s)^.*B/ - abc\nB - 0: abc\x0aB - -/(?m)^.*B/ - abc\nB - 0: B - -/(?ms)^.*B/ - abc\nB - 0: abc\x0aB - -/(?ms)^B/ - abc\nB - 0: B - -/(?s)B$/ - B\n - 0: B - -/^[0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9][0-9]/ - 123456654321 - 0: 123456654321 - -/^\d\d\d\d\d\d\d\d\d\d\d\d/ - 123456654321 - 0: 123456654321 - -/^[\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d][\d]/ - 123456654321 - 0: 123456654321 - -/^[abc]{12}/ - abcabcabcabc - 0: abcabcabcabc - -/^[a-c]{12}/ - abcabcabcabc - 0: abcabcabcabc - -/^(a|b|c){12}/ - abcabcabcabc - 0: abcabcabcabc - 1: c - -/^[abcdefghijklmnopqrstuvwxy0123456789]/ - n - 0: n - *** Failers -No match - z -No match - -/abcde{0,0}/ - abcd - 0: abcd - *** Failers -No match - abce -No match - -/ab[cd]{0,0}e/ - abe - 0: abe - *** Failers -No match - abcde -No match - -/ab(c){0,0}d/ - abd - 0: abd - *** Failers -No match - abcd -No match - -/a(b*)/ - a - 0: a - 1: - ab - 0: ab - 1: b - abbbb - 0: abbbb - 1: bbbb - *** Failers - 0: a - 1: - bbbbb -No match - -/ab\d{0}e/ - abe - 0: abe - *** Failers -No match - ab1e -No match - -/"([^\\"]+|\\.)*"/ - the \"quick\" brown fox - 0: "quick" - 1: quick - \"the \\\"quick\\\" brown fox\" - 0: "the \"quick\" brown fox" - 1: brown fox - -/.*?/g+ - abc - 0: - 0+ abc - 0: a - 0+ bc - 0: - 0+ bc - 0: b - 0+ c - 0: - 0+ c - 0: c - 0+ - 0: - 0+ - -/\b/g+ - abc - 0: - 0+ abc - 0: - 0+ - -/\b/+g - abc - 0: - 0+ abc - 0: - 0+ - -//g - abc - 0: - 0: - 0: - 0: - -/<tr([\w\W\s\d][^<>]{0,})><TD([\w\W\s\d][^<>]{0,})>([\d]{0,}\.)(.*)((<BR>([\w\W\s\d][^<>]{0,})|[\s]{0,}))<\/a><\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><TD([\w\W\s\d][^<>]{0,})>([\w\W\s\d][^<>]{0,})<\/TD><\/TR>/is - <TR BGCOLOR='#DBE9E9'><TD align=left valign=top>43.<a href='joblist.cfm?JobID=94 6735&Keyword='>Word Processor<BR>(N-1286)</a></TD><TD align=left valign=top>Lega lstaff.com</TD><TD align=left valign=top>CA - Statewide</TD></TR> - 0: <TR BGCOLOR='#DBE9E9'><TD align=left valign=top>43.<a href='joblist.cfm?JobID=94 6735&Keyword='>Word Processor<BR>(N-1286)</a></TD><TD align=left valign=top>Lega lstaff.com</TD><TD align=left valign=top>CA - Statewide</TD></TR> - 1: BGCOLOR='#DBE9E9' - 2: align=left valign=top - 3: 43. - 4: <a href='joblist.cfm?JobID=94 6735&Keyword='>Word Processor<BR>(N-1286) - 5: - 6: - 7: <unset> - 8: align=left valign=top - 9: Lega lstaff.com -10: align=left valign=top -11: CA - Statewide - -/a[^a]b/ - acb - 0: acb - a\nb - 0: a\x0ab - -/a.b/ - acb - 0: acb - *** Failers -No match - a\nb -No match - -/a[^a]b/s - acb - 0: acb - a\nb - 0: a\x0ab - -/a.b/s - acb - 0: acb - a\nb - 0: a\x0ab - -/^(b+?|a){1,2}?c/ - bac - 0: bac - 1: a - bbac - 0: bbac - 1: a - bbbac - 0: bbbac - 1: a - bbbbac - 0: bbbbac - 1: a - bbbbbac - 0: bbbbbac - 1: a - -/^(b+|a){1,2}?c/ - bac - 0: bac - 1: a - bbac - 0: bbac - 1: a - bbbac - 0: bbbac - 1: a - bbbbac - 0: bbbbac - 1: a - bbbbbac - 0: bbbbbac - 1: a - -/(?!\A)x/m - x\nb\n -No match - a\bx\n - 0: x - -/\x0{ab}/ - \0{ab} - 0: \x00{ab} - -/(A|B)*?CD/ - CD - 0: CD - -/(A|B)*CD/ - CD - 0: CD - -/(AB)*?\1/ - ABABAB - 0: ABAB - 1: AB - -/(AB)*\1/ - ABABAB - 0: ABABAB - 1: AB - -/(?<!bar)foo/ - foo - 0: foo - catfood - 0: foo - arfootle - 0: foo - rfoosh - 0: foo - *** Failers -No match - barfoo -No match - towbarfoo -No match - -/\w{3}(?<!bar)foo/ - catfood - 0: catfoo - *** Failers -No match - foo -No match - barfoo -No match - towbarfoo -No match - -/(?<=(foo)a)bar/ - fooabar - 0: bar - 1: foo - *** Failers -No match - bar -No match - foobbar -No match - -/\Aabc\z/m - abc - 0: abc - *** Failers -No match - abc\n -No match - qqq\nabc -No match - abc\nzzz -No match - qqq\nabc\nzzz -No match - -"(?>.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/it/you/see/ -No match - -"(?>.*/)foo" - /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo - 0: /this/is/a/very/long/line/in/deed/with/very/many/slashes/in/and/foo - -/(?>(\.\d\d[1-9]?))\d+/ - 1.230003938 - 0: .230003938 - 1: .23 - 1.875000282 - 0: .875000282 - 1: .875 - *** Failers -No match - 1.235 -No match - -/^((?>\w+)|(?>\s+))*$/ - now is the time for all good men to come to the aid of the party - 0: now is the time for all good men to come to the aid of the party - 1: party - *** Failers -No match - this is not a line with only words and spaces! -No match - -/(\d+)(\w)/ - 12345a - 0: 12345a - 1: 12345 - 2: a - 12345+ - 0: 12345 - 1: 1234 - 2: 5 - -/((?>\d+))(\w)/ - 12345a - 0: 12345a - 1: 12345 - 2: a - *** Failers -No match - 12345+ -No match - -/(?>a+)b/ - aaab - 0: aaab - -/((?>a+)b)/ - aaab - 0: aaab - 1: aaab - -/(?>(a+))b/ - aaab - 0: aaab - 1: aaa - -/(?>b)+/ - aaabbbccc - 0: bbb - -/(?>a+|b+|c+)*c/ - aaabbbbccccd - 0: aaabbbbc - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - 0: abc(ade)ufh()()x - 1: x - -/\(((?>[^()]+)|\([^()]+\))+\)/ - (abc) - 0: (abc) - 1: abc - (abc(def)xyz) - 0: (abc(def)xyz) - 1: xyz - *** Failers -No match - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - -/a(?-i)b/i - ab - 0: ab - Ab - 0: Ab - *** Failers -No match - aB -No match - AB -No match - -/(a (?x)b c)d e/ - a bcd e - 0: a bcd e - 1: a bc - *** Failers -No match - a b cd e -No match - abcd e -No match - a bcde -No match - -/(a b(?x)c d (?-x)e f)/ - a bcde f - 0: a bcde f - 1: a bcde f - *** Failers -No match - abcdef -No match - -/(a(?i)b)c/ - abc - 0: abc - 1: ab - aBc - 0: aBc - 1: aB - *** Failers -No match - abC -No match - aBC -No match - Abc -No match - ABc -No match - ABC -No match - AbC -No match - -/a(?i:b)c/ - abc - 0: abc - aBc - 0: aBc - *** Failers -No match - ABC -No match - abC -No match - aBC -No match - -/a(?i:b)*c/ - aBc - 0: aBc - aBBc - 0: aBBc - *** Failers -No match - aBC -No match - aBBC -No match - -/a(?=b(?i)c)\w\wd/ - abcd - 0: abcd - abCd - 0: abCd - *** Failers -No match - aBCd -No match - abcD -No match - -/(?s-i:more.*than).*million/i - more than million - 0: more than million - more than MILLION - 0: more than MILLION - more \n than Million - 0: more \x0a than Million - *** Failers -No match - MORE THAN MILLION -No match - more \n than \n million -No match - -/(?:(?s-i)more.*than).*million/i - more than million - 0: more than million - more than MILLION - 0: more than MILLION - more \n than Million - 0: more \x0a than Million - *** Failers -No match - MORE THAN MILLION -No match - more \n than \n million -No match - -/(?>a(?i)b+)+c/ - abc - 0: abc - aBbc - 0: aBbc - aBBc - 0: aBBc - *** Failers -No match - Abc -No match - abAb -No match - abbC -No match - -/(?=a(?i)b)\w\wc/ - abc - 0: abc - aBc - 0: aBc - *** Failers -No match - Ab -No match - abC -No match - aBC -No match - -/(?<=a(?i)b)(\w\w)c/ - abxxc - 0: xxc - 1: xx - aBxxc - 0: xxc - 1: xx - *** Failers -No match - Abxxc -No match - ABxxc -No match - abxxC -No match - -/(?:(a)|b)(?(1)A|B)/ - aA - 0: aA - 1: a - bB - 0: bB - *** Failers -No match - aB -No match - bA -No match - -/^(a)?(?(1)a|b)+$/ - aa - 0: aa - 1: a - b - 0: b - bb - 0: bb - *** Failers -No match - ab -No match - -/^(?(?=abc)\w{3}:|\d\d)$/ - abc: - 0: abc: - 12 - 0: 12 - *** Failers -No match - 123 -No match - xyz -No match - -/^(?(?!abc)\d\d|\w{3}:)$/ - abc: - 0: abc: - 12 - 0: 12 - *** Failers -No match - 123 -No match - xyz -No match - -/(?(?<=foo)bar|cat)/ - foobar - 0: bar - cat - 0: cat - fcat - 0: cat - focat - 0: cat - *** Failers -No match - foocat -No match - -/(?(?<!foo)cat|bar)/ - foobar - 0: bar - cat - 0: cat - fcat - 0: cat - focat - 0: cat - *** Failers -No match - foocat -No match - -/( \( )? [^()]+ (?(1) \) |) /x - abcd - 0: abcd - (abcd) - 0: (abcd) - 1: ( - the quick (abcd) fox - 0: the quick - (abcd - 0: abcd - -/( \( )? [^()]+ (?(1) \) ) /x - abcd - 0: abcd - (abcd) - 0: (abcd) - 1: ( - the quick (abcd) fox - 0: the quick - (abcd - 0: abcd - -/^(?(2)a|(1)(2))+$/ - 12 - 0: 12 - 1: 1 - 2: 2 - 12a - 0: 12a - 1: 1 - 2: 2 - 12aa - 0: 12aa - 1: 1 - 2: 2 - *** Failers -No match - 1234 -No match - -/((?i)blah)\s+\1/ - blah blah - 0: blah blah - 1: blah - BLAH BLAH - 0: BLAH BLAH - 1: BLAH - Blah Blah - 0: Blah Blah - 1: Blah - blaH blaH - 0: blaH blaH - 1: blaH - *** Failers -No match - blah BLAH -No match - Blah blah -No match - blaH blah -No match - -/((?i)blah)\s+(?i:\1)/ - blah blah - 0: blah blah - 1: blah - BLAH BLAH - 0: BLAH BLAH - 1: BLAH - Blah Blah - 0: Blah Blah - 1: Blah - blaH blaH - 0: blaH blaH - 1: blaH - blah BLAH - 0: blah BLAH - 1: blah - Blah blah - 0: Blah blah - 1: Blah - blaH blah - 0: blaH blah - 1: blaH - -/(?>a*)*/ - a - 0: a - aa - 0: aa - aaaa - 0: aaaa - -/(abc|)+/ - abc - 0: abc - 1: - abcabc - 0: abcabc - 1: - abcabcabc - 0: abcabcabc - 1: - xyz - 0: - 1: - -/([a]*)*/ - a - 0: a - 1: - aaaaa - 0: aaaaa - 1: - -/([ab]*)*/ - a - 0: a - 1: - b - 0: b - 1: - ababab - 0: ababab - 1: - aaaabcde - 0: aaaab - 1: - bbbb - 0: bbbb - 1: - -/([^a]*)*/ - b - 0: b - 1: - bbbb - 0: bbbb - 1: - aaa - 0: - 1: - -/([^ab]*)*/ - cccc - 0: cccc - 1: - abab - 0: - 1: - -/([a]*?)*/ - a - 0: - 1: - aaaa - 0: - 1: - -/([ab]*?)*/ - a - 0: - 1: - b - 0: - 1: - abab - 0: - 1: - baba - 0: - 1: - -/([^a]*?)*/ - b - 0: - 1: - bbbb - 0: - 1: - aaa - 0: - 1: - -/([^ab]*?)*/ - c - 0: - 1: - cccc - 0: - 1: - baba - 0: - 1: - -/(?>a*)*/ - a - 0: a - aaabcde - 0: aaa - -/((?>a*))*/ - aaaaa - 0: aaaaa - 1: - aabbaa - 0: aa - 1: - -/((?>a*?))*/ - aaaaa - 0: - 1: - aabbaa - 0: - 1: - -/(?(?=[^a-z]+[a-z]) \d{2}-[a-z]{3}-\d{2} | \d{2}-\d{2}-\d{2} ) /x - 12-sep-98 - 0: 12-sep-98 - 12-09-98 - 0: 12-09-98 - *** Failers -No match - sep-12-98 -No match - -/(?<=(foo))bar\1/ - foobarfoo - 0: barfoo - 1: foo - foobarfootling - 0: barfoo - 1: foo - *** Failers -No match - foobar -No match - barfoo -No match - -/(?i:saturday|sunday)/ - saturday - 0: saturday - sunday - 0: sunday - Saturday - 0: Saturday - Sunday - 0: Sunday - SATURDAY - 0: SATURDAY - SUNDAY - 0: SUNDAY - SunDay - 0: SunDay - -/(a(?i)bc|BB)x/ - abcx - 0: abcx - 1: abc - aBCx - 0: aBCx - 1: aBC - bbx - 0: bbx - 1: bb - BBx - 0: BBx - 1: BB - *** Failers -No match - abcX -No match - aBCX -No match - bbX -No match - BBX -No match - -/^([ab](?i)[cd]|[ef])/ - ac - 0: ac - 1: ac - aC - 0: aC - 1: aC - bD - 0: bD - 1: bD - elephant - 0: e - 1: e - Europe - 0: E - 1: E - frog - 0: f - 1: f - France - 0: F - 1: F - *** Failers -No match - Africa -No match - -/^(ab|a(?i)[b-c](?m-i)d|x(?i)y|z)/ - ab - 0: ab - 1: ab - aBd - 0: aBd - 1: aBd - xy - 0: xy - 1: xy - xY - 0: xY - 1: xY - zebra - 0: z - 1: z - Zambesi - 0: Z - 1: Z - *** Failers -No match - aCD -No match - XY -No match - -/(?<=foo\n)^bar/m - foo\nbar - 0: bar - *** Failers -No match - bar -No match - baz\nbar -No match - -/(?<=(?<!foo)bar)baz/ - barbaz - 0: baz - barbarbaz - 0: baz - koobarbaz - 0: baz - *** Failers -No match - baz -No match - foobarbaz -No match - -/The case of aaaaaa is missed out below because I think Perl 5.005_02 gets/ -/it wrong; it sets $1 to aaa rather than aa. Compare the following test,/ -No match -/where it does set $1 to aa when matching aaaaaa./ -No match - -/^(a\1?){4}$/ - a -No match - aa -No match - aaa -No match - aaaa - 0: aaaa - 1: a - aaaaa - 0: aaaaa - 1: a - aaaaaaa - 0: aaaaaaa - 1: a - aaaaaaaa -No match - aaaaaaaaa -No match - aaaaaaaaaa - 0: aaaaaaaaaa - 1: aaaa - aaaaaaaaaaa -No match - aaaaaaaaaaaa -No match - aaaaaaaaaaaaa -No match - aaaaaaaaaaaaaa -No match - aaaaaaaaaaaaaaa -No match - aaaaaaaaaaaaaaaa -No match - -/^(a\1?)(a\1?)(a\2?)(a\3?)$/ - a -No match - aa -No match - aaa -No match - aaaa - 0: aaaa - 1: a - 2: a - 3: a - 4: a - aaaaa - 0: aaaaa - 1: a - 2: aa - 3: a - 4: a - aaaaaa - 0: aaaaaa - 1: a - 2: aa - 3: a - 4: aa - aaaaaaa - 0: aaaaaaa - 1: a - 2: aa - 3: aaa - 4: a - aaaaaaaa -No match - aaaaaaaaa -No match - aaaaaaaaaa - 0: aaaaaaaaaa - 1: a - 2: aa - 3: aaa - 4: aaaa - aaaaaaaaaaa -No match - aaaaaaaaaaaa -No match - aaaaaaaaaaaaa -No match - aaaaaaaaaaaaaa -No match - aaaaaaaaaaaaaaa -No match - aaaaaaaaaaaaaaaa -No match - -/The following tests are taken from the Perl 5.005 test suite; some of them/ -/are compatible with 5.004, but I'd rather not have to sort them out./ -No match - -/abc/ - abc - 0: abc - xabcy - 0: abc - ababc - 0: abc - *** Failers -No match - xbc -No match - axc -No match - abx -No match - -/ab*c/ - abc - 0: abc - -/ab*bc/ - abc - 0: abc - abbc - 0: abbc - abbbbc - 0: abbbbc - -/.{1}/ - abbbbc - 0: a - -/.{3,4}/ - abbbbc - 0: abbb - -/ab{0,}bc/ - abbbbc - 0: abbbbc - -/ab+bc/ - abbc - 0: abbc - *** Failers -No match - abc -No match - abq -No match - -/ab{1,}bc/ - -/ab+bc/ - abbbbc - 0: abbbbc - -/ab{1,}bc/ - abbbbc - 0: abbbbc - -/ab{1,3}bc/ - abbbbc - 0: abbbbc - -/ab{3,4}bc/ - abbbbc - 0: abbbbc - -/ab{4,5}bc/ - *** Failers -No match - abq -No match - abbbbc -No match - -/ab?bc/ - abbc - 0: abbc - abc - 0: abc - -/ab{0,1}bc/ - abc - 0: abc - -/ab?bc/ - -/ab?c/ - abc - 0: abc - -/ab{0,1}c/ - abc - 0: abc - -/^abc$/ - abc - 0: abc - *** Failers -No match - abbbbc -No match - abcc -No match - -/^abc/ - abcc - 0: abc - -/^abc$/ - -/abc$/ - aabc - 0: abc - *** Failers -No match - aabc - 0: abc - aabcd -No match - -/^/ - abc - 0: - -/$/ - abc - 0: - -/a.c/ - abc - 0: abc - axc - 0: axc - -/a.*c/ - axyzc - 0: axyzc - -/a[bc]d/ - abd - 0: abd - *** Failers -No match - axyzd -No match - abc -No match - -/a[b-d]e/ - ace - 0: ace - -/a[b-d]/ - aac - 0: ac - -/a[-b]/ - a- - 0: a- - -/a[b-]/ - a- - 0: a- - -/a]/ - a] - 0: a] - -/a[]]b/ - a]b - 0: a]b - -/a[^bc]d/ - aed - 0: aed - *** Failers -No match - abd -No match - abd -No match - -/a[^-b]c/ - adc - 0: adc - -/a[^]b]c/ - adc - 0: adc - *** Failers -No match - a-c - 0: a-c - a]c -No match - -/\ba\b/ - a- - 0: a - -a - 0: a - -a- - 0: a - -/\by\b/ - *** Failers -No match - xy -No match - yz -No match - xyz -No match - -/\Ba\B/ - *** Failers - 0: a - a- -No match - -a -No match - -a- -No match - -/\By\b/ - xy - 0: y - -/\by\B/ - yz - 0: y - -/\By\B/ - xyz - 0: y - -/\w/ - a - 0: a - -/\W/ - - - 0: - - *** Failers - 0: * - - - 0: - - a -No match - -/a\sb/ - a b - 0: a b - -/a\Sb/ - a-b - 0: a-b - *** Failers -No match - a-b - 0: a-b - a b -No match - -/\d/ - 1 - 0: 1 - -/\D/ - - - 0: - - *** Failers - 0: * - - - 0: - - 1 -No match - -/[\w]/ - a - 0: a - -/[\W]/ - - - 0: - - *** Failers - 0: * - - - 0: - - a -No match - -/a[\s]b/ - a b - 0: a b - -/a[\S]b/ - a-b - 0: a-b - *** Failers -No match - a-b - 0: a-b - a b -No match - -/[\d]/ - 1 - 0: 1 - -/[\D]/ - - - 0: - - *** Failers - 0: * - - - 0: - - 1 -No match - -/ab|cd/ - abc - 0: ab - abcd - 0: ab - -/()ef/ - def - 0: ef - 1: - -/$b/ - -/a\(b/ - a(b - 0: a(b - -/a\(*b/ - ab - 0: ab - a((b - 0: a((b - -/a\\b/ - a\b -No match - -/((a))/ - abc - 0: a - 1: a - 2: a - -/(a)b(c)/ - abc - 0: abc - 1: a - 2: c - -/a+b+c/ - aabbabc - 0: abc - -/a{1,}b{1,}c/ - aabbabc - 0: abc - -/a.+?c/ - abcabc - 0: abc - -/(a+|b)*/ - ab - 0: ab - 1: b - -/(a+|b){0,}/ - ab - 0: ab - 1: b - -/(a+|b)+/ - ab - 0: ab - 1: b - -/(a+|b){1,}/ - ab - 0: ab - 1: b - -/(a+|b)?/ - ab - 0: a - 1: a - -/(a+|b){0,1}/ - ab - 0: a - 1: a - -/[^ab]*/ - cde - 0: cde - -/abc/ - *** Failers -No match - b -No match - - -/a*/ - - -/([abc])*d/ - abbbcd - 0: abbbcd - 1: c - -/([abc])*bcd/ - abcd - 0: abcd - 1: a - -/a|b|c|d|e/ - e - 0: e - -/(a|b|c|d|e)f/ - ef - 0: ef - 1: e - -/abcd*efg/ - abcdefg - 0: abcdefg - -/ab*/ - xabyabbbz - 0: ab - xayabbbz - 0: a - -/(ab|cd)e/ - abcde - 0: cde - 1: cd - -/[abhgefdc]ij/ - hij - 0: hij - -/^(ab|cd)e/ - -/(abc|)ef/ - abcdef - 0: ef - 1: - -/(a|b)c*d/ - abcd - 0: bcd - 1: b - -/(ab|ab*)bc/ - abc - 0: abc - 1: a - -/a([bc]*)c*/ - abc - 0: abc - 1: bc - -/a([bc]*)(c*d)/ - abcd - 0: abcd - 1: bc - 2: d - -/a([bc]+)(c*d)/ - abcd - 0: abcd - 1: bc - 2: d - -/a([bc]*)(c+d)/ - abcd - 0: abcd - 1: b - 2: cd - -/a[bcd]*dcdcde/ - adcdcde - 0: adcdcde - -/a[bcd]+dcdcde/ - *** Failers -No match - abcde -No match - adcdcde -No match - -/(ab|a)b*c/ - abc - 0: abc - 1: ab - -/((a)(b)c)(d)/ - abcd - 0: abcd - 1: abc - 2: a - 3: b - 4: d - -/[a-zA-Z_][a-zA-Z0-9_]*/ - alpha - 0: alpha - -/^a(bc+|b[eh])g|.h$/ - abh - 0: bh - -/(bc+d$|ef*g.|h?i(j|k))/ - effgz - 0: effgz - 1: effgz - ij - 0: ij - 1: ij - 2: j - reffgz - 0: effgz - 1: effgz - *** Failers -No match - effg -No match - bcdd -No match - -/((((((((((a))))))))))/ - a - 0: a - 1: a - 2: a - 3: a - 4: a - 5: a - 6: a - 7: a - 8: a - 9: a -10: a - -/((((((((((a))))))))))\10/ - aa - 0: aa - 1: a - 2: a - 3: a - 4: a - 5: a - 6: a - 7: a - 8: a - 9: a -10: a - -/(((((((((a)))))))))/ - a - 0: a - 1: a - 2: a - 3: a - 4: a - 5: a - 6: a - 7: a - 8: a - 9: a - -/multiple words of text/ - *** Failers -No match - aa -No match - uh-uh -No match - -/multiple words/ - multiple words, yeah - 0: multiple words - -/(.*)c(.*)/ - abcde - 0: abcde - 1: ab - 2: de - -/\((.*), (.*)\)/ - (a, b) - 0: (a, b) - 1: a - 2: b - -/[k]/ - -/abcd/ - abcd - 0: abcd - -/a(bc)d/ - abcd - 0: abcd - 1: bc - -/a[-]?c/ - ac - 0: ac - -/(abc)\1/ - abcabc - 0: abcabc - 1: abc - -/([a-c]*)\1/ - abcabc - 0: abcabc - 1: abc - -/(a)|\1/ - a - 0: a - 1: a - *** Failers - 0: a - 1: a - ab - 0: a - 1: a - x -No match - -/(([a-c])b*?\2)*/ - ababbbcbc - 0: ababb - 1: bb - 2: b - -/(([a-c])b*?\2){3}/ - ababbbcbc - 0: ababbbcbc - 1: cbc - 2: c - -/((\3|b)\2(a)x)+/ - aaaxabaxbaaxbbax - 0: bbax - 1: bbax - 2: b - 3: a - -/((\3|b)\2(a)){2,}/ - bbaababbabaaaaabbaaaabba - 0: bbaaaabba - 1: bba - 2: b - 3: a - -/abc/i - ABC - 0: ABC - XABCY - 0: ABC - ABABC - 0: ABC - *** Failers -No match - aaxabxbaxbbx -No match - XBC -No match - AXC -No match - ABX -No match - -/ab*c/i - ABC - 0: ABC - -/ab*bc/i - ABC - 0: ABC - ABBC - 0: ABBC - -/ab*?bc/i - ABBBBC - 0: ABBBBC - -/ab{0,}?bc/i - ABBBBC - 0: ABBBBC - -/ab+?bc/i - ABBC - 0: ABBC - -/ab+bc/i - *** Failers -No match - ABC -No match - ABQ -No match - -/ab{1,}bc/i - -/ab+bc/i - ABBBBC - 0: ABBBBC - -/ab{1,}?bc/i - ABBBBC - 0: ABBBBC - -/ab{1,3}?bc/i - ABBBBC - 0: ABBBBC - -/ab{3,4}?bc/i - ABBBBC - 0: ABBBBC - -/ab{4,5}?bc/i - *** Failers -No match - ABQ -No match - ABBBBC -No match - -/ab??bc/i - ABBC - 0: ABBC - ABC - 0: ABC - -/ab{0,1}?bc/i - ABC - 0: ABC - -/ab??bc/i - -/ab??c/i - ABC - 0: ABC - -/ab{0,1}?c/i - ABC - 0: ABC - -/^abc$/i - ABC - 0: ABC - *** Failers -No match - ABBBBC -No match - ABCC -No match - -/^abc/i - ABCC - 0: ABC - -/^abc$/i - -/abc$/i - AABC - 0: ABC - -/^/i - ABC - 0: - -/$/i - ABC - 0: - -/a.c/i - ABC - 0: ABC - AXC - 0: AXC - -/a.*?c/i - AXYZC - 0: AXYZC - -/a.*c/i - *** Failers -No match - AABC - 0: AABC - AXYZD -No match - -/a[bc]d/i - ABD - 0: ABD - -/a[b-d]e/i - ACE - 0: ACE - *** Failers -No match - ABC -No match - ABD -No match - -/a[b-d]/i - AAC - 0: AC - -/a[-b]/i - A- - 0: A- - -/a[b-]/i - A- - 0: A- - -/a]/i - A] - 0: A] - -/a[]]b/i - A]B - 0: A]B - -/a[^bc]d/i - AED - 0: AED - -/a[^-b]c/i - ADC - 0: ADC - *** Failers -No match - ABD -No match - A-C -No match - -/a[^]b]c/i - ADC - 0: ADC - -/ab|cd/i - ABC - 0: AB - ABCD - 0: AB - -/()ef/i - DEF - 0: EF - 1: - -/$b/i - *** Failers -No match - A]C -No match - B -No match - -/a\(b/i - A(B - 0: A(B - -/a\(*b/i - AB - 0: AB - A((B - 0: A((B - -/a\\b/i - A\B -No match - -/((a))/i - ABC - 0: A - 1: A - 2: A - -/(a)b(c)/i - ABC - 0: ABC - 1: A - 2: C - -/a+b+c/i - AABBABC - 0: ABC - -/a{1,}b{1,}c/i - AABBABC - 0: ABC - -/a.+?c/i - ABCABC - 0: ABC - -/a.*?c/i - ABCABC - 0: ABC - -/a.{0,5}?c/i - ABCABC - 0: ABC - -/(a+|b)*/i - AB - 0: AB - 1: B - -/(a+|b){0,}/i - AB - 0: AB - 1: B - -/(a+|b)+/i - AB - 0: AB - 1: B - -/(a+|b){1,}/i - AB - 0: AB - 1: B - -/(a+|b)?/i - AB - 0: A - 1: A - -/(a+|b){0,1}/i - AB - 0: A - 1: A - -/(a+|b){0,1}?/i - AB - 0: - -/[^ab]*/i - CDE - 0: CDE - -/abc/i - -/a*/i - - -/([abc])*d/i - ABBBCD - 0: ABBBCD - 1: C - -/([abc])*bcd/i - ABCD - 0: ABCD - 1: A - -/a|b|c|d|e/i - E - 0: E - -/(a|b|c|d|e)f/i - EF - 0: EF - 1: E - -/abcd*efg/i - ABCDEFG - 0: ABCDEFG - -/ab*/i - XABYABBBZ - 0: AB - XAYABBBZ - 0: A - -/(ab|cd)e/i - ABCDE - 0: CDE - 1: CD - -/[abhgefdc]ij/i - HIJ - 0: HIJ - -/^(ab|cd)e/i - ABCDE -No match - -/(abc|)ef/i - ABCDEF - 0: EF - 1: - -/(a|b)c*d/i - ABCD - 0: BCD - 1: B - -/(ab|ab*)bc/i - ABC - 0: ABC - 1: A - -/a([bc]*)c*/i - ABC - 0: ABC - 1: BC - -/a([bc]*)(c*d)/i - ABCD - 0: ABCD - 1: BC - 2: D - -/a([bc]+)(c*d)/i - ABCD - 0: ABCD - 1: BC - 2: D - -/a([bc]*)(c+d)/i - ABCD - 0: ABCD - 1: B - 2: CD - -/a[bcd]*dcdcde/i - ADCDCDE - 0: ADCDCDE - -/a[bcd]+dcdcde/i - -/(ab|a)b*c/i - ABC - 0: ABC - 1: AB - -/((a)(b)c)(d)/i - ABCD - 0: ABCD - 1: ABC - 2: A - 3: B - 4: D - -/[a-zA-Z_][a-zA-Z0-9_]*/i - ALPHA - 0: ALPHA - -/^a(bc+|b[eh])g|.h$/i - ABH - 0: BH - -/(bc+d$|ef*g.|h?i(j|k))/i - EFFGZ - 0: EFFGZ - 1: EFFGZ - IJ - 0: IJ - 1: IJ - 2: J - REFFGZ - 0: EFFGZ - 1: EFFGZ - *** Failers -No match - ADCDCDE -No match - EFFG -No match - BCDD -No match - -/((((((((((a))))))))))/i - A - 0: A - 1: A - 2: A - 3: A - 4: A - 5: A - 6: A - 7: A - 8: A - 9: A -10: A - -/((((((((((a))))))))))\10/i - AA - 0: AA - 1: A - 2: A - 3: A - 4: A - 5: A - 6: A - 7: A - 8: A - 9: A -10: A - -/(((((((((a)))))))))/i - A - 0: A - 1: A - 2: A - 3: A - 4: A - 5: A - 6: A - 7: A - 8: A - 9: A - -/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a))))))))))/i - A - 0: A - 1: A - -/(?:(?:(?:(?:(?:(?:(?:(?:(?:(a|b|c))))))))))/i - C - 0: C - 1: C - -/multiple words of text/i - *** Failers -No match - AA -No match - UH-UH -No match - -/multiple words/i - MULTIPLE WORDS, YEAH - 0: MULTIPLE WORDS - -/(.*)c(.*)/i - ABCDE - 0: ABCDE - 1: AB - 2: DE - -/\((.*), (.*)\)/i - (A, B) - 0: (A, B) - 1: A - 2: B - -/[k]/i - -/abcd/i - ABCD - 0: ABCD - -/a(bc)d/i - ABCD - 0: ABCD - 1: BC - -/a[-]?c/i - AC - 0: AC - -/(abc)\1/i - ABCABC - 0: ABCABC - 1: ABC - -/([a-c]*)\1/i - ABCABC - 0: ABCABC - 1: ABC - -/a(?!b)./ - abad - 0: ad - -/a(?=d)./ - abad - 0: ad - -/a(?=c|d)./ - abad - 0: ad - -/a(?:b|c|d)(.)/ - ace - 0: ace - 1: e - -/a(?:b|c|d)*(.)/ - ace - 0: ace - 1: e - -/a(?:b|c|d)+?(.)/ - ace - 0: ace - 1: e - acdbcdbe - 0: acd - 1: d - -/a(?:b|c|d)+(.)/ - acdbcdbe - 0: acdbcdbe - 1: e - -/a(?:b|c|d){2}(.)/ - acdbcdbe - 0: acdb - 1: b - -/a(?:b|c|d){4,5}(.)/ - acdbcdbe - 0: acdbcdb - 1: b - -/a(?:b|c|d){4,5}?(.)/ - acdbcdbe - 0: acdbcd - 1: d - -/((foo)|(bar))*/ - foobar - 0: foobar - 1: bar - 2: foo - 3: bar - -/a(?:b|c|d){6,7}(.)/ - acdbcdbe - 0: acdbcdbe - 1: e - -/a(?:b|c|d){6,7}?(.)/ - acdbcdbe - 0: acdbcdbe - 1: e - -/a(?:b|c|d){5,6}(.)/ - acdbcdbe - 0: acdbcdbe - 1: e - -/a(?:b|c|d){5,6}?(.)/ - acdbcdbe - 0: acdbcdb - 1: b - -/a(?:b|c|d){5,7}(.)/ - acdbcdbe - 0: acdbcdbe - 1: e - -/a(?:b|c|d){5,7}?(.)/ - acdbcdbe - 0: acdbcdb - 1: b - -/a(?:b|(c|e){1,2}?|d)+?(.)/ - ace - 0: ace - 1: c - 2: e - -/^(.+)?B/ - AB - 0: AB - 1: A - -/^([^a-z])|(\^)$/ - . - 0: . - 1: . - -/^[<>]&/ - <&OUT - 0: <& - -/^(a\1?){4}$/ - aaaaaaaaaa - 0: aaaaaaaaaa - 1: aaaa - *** Failers -No match - AB -No match - aaaaaaaaa -No match - aaaaaaaaaaa -No match - -/^(a(?(1)\1)){4}$/ - aaaaaaaaaa - 0: aaaaaaaaaa - 1: aaaa - *** Failers -No match - aaaaaaaaa -No match - aaaaaaaaaaa -No match - -/(?:(f)(o)(o)|(b)(a)(r))*/ - foobar - 0: foobar - 1: f - 2: o - 3: o - 4: b - 5: a - 6: r - -/(?<=a)b/ - ab - 0: b - *** Failers -No match - cb -No match - b -No match - -/(?<!c)b/ - ab - 0: b - b - 0: b - b - 0: b - -/(?:..)*a/ - aba - 0: aba - -/(?:..)*?a/ - aba - 0: a - -/^(?:b|a(?=(.)))*\1/ - abc - 0: ab - 1: b - -/^(){3,5}/ - abc - 0: - 1: - -/^(a+)*ax/ - aax - 0: aax - 1: a - -/^((a|b)+)*ax/ - aax - 0: aax - 1: a - 2: a - -/^((a|bc)+)*ax/ - aax - 0: aax - 1: a - 2: a - -/(a|x)*ab/ - cab - 0: ab - -/(a)*ab/ - cab - 0: ab - -/(?:(?i)a)b/ - ab - 0: ab - -/((?i)a)b/ - ab - 0: ab - 1: a - -/(?:(?i)a)b/ - Ab - 0: Ab - -/((?i)a)b/ - Ab - 0: Ab - 1: A - -/(?:(?i)a)b/ - *** Failers -No match - cb -No match - aB -No match - -/((?i)a)b/ - -/(?i:a)b/ - ab - 0: ab - -/((?i:a))b/ - ab - 0: ab - 1: a - -/(?i:a)b/ - Ab - 0: Ab - -/((?i:a))b/ - Ab - 0: Ab - 1: A - -/(?i:a)b/ - *** Failers -No match - aB -No match - aB -No match - -/((?i:a))b/ - -/(?:(?-i)a)b/i - ab - 0: ab - -/((?-i)a)b/i - ab - 0: ab - 1: a - -/(?:(?-i)a)b/i - aB - 0: aB - -/((?-i)a)b/i - aB - 0: aB - 1: a - -/(?:(?-i)a)b/i - *** Failers -No match - aB - 0: aB - Ab -No match - -/((?-i)a)b/i - -/(?:(?-i)a)b/i - aB - 0: aB - -/((?-i)a)b/i - aB - 0: aB - 1: a - -/(?:(?-i)a)b/i - *** Failers -No match - Ab -No match - AB -No match - -/((?-i)a)b/i - -/(?-i:a)b/i - ab - 0: ab - -/((?-i:a))b/i - ab - 0: ab - 1: a - -/(?-i:a)b/i - aB - 0: aB - -/((?-i:a))b/i - aB - 0: aB - 1: a - -/(?-i:a)b/i - *** Failers -No match - AB -No match - Ab -No match - -/((?-i:a))b/i - -/(?-i:a)b/i - aB - 0: aB - -/((?-i:a))b/i - aB - 0: aB - 1: a - -/(?-i:a)b/i - *** Failers -No match - Ab -No match - AB -No match - -/((?-i:a))b/i - -/((?-i:a.))b/i - *** Failers -No match - AB -No match - a\nB -No match - -/((?s-i:a.))b/i - a\nB - 0: a\x0aB - 1: a\x0a - -/(?:c|d)(?:)(?:a(?:)(?:b)(?:b(?:))(?:b(?:)(?:b)))/ - cabbbb - 0: cabbbb - -/(?:c|d)(?:)(?:aaaaaaaa(?:)(?:bbbbbbbb)(?:bbbbbbbb(?:))(?:bbbbbbbb(?:)(?:bbbbbbbb)))/ - caaaaaaaabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb - 0: caaaaaaaabbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb - -/(ab)\d\1/i - Ab4ab - 0: Ab4ab - 1: Ab - ab4Ab - 0: ab4Ab - 1: ab - -/foo\w*\d{4}baz/ - foobar1234baz - 0: foobar1234baz - -/x(~~)*(?:(?:F)?)?/ - x~~ - 0: x~~ - 1: ~~ - -/^a(?#xxx){3}c/ - aaac - 0: aaac - -/^a (?#xxx) (?#yyy) {3}c/x - aaac - 0: aaac - -/(?<![cd])b/ - *** Failers -No match - B\nB -No match - dbcb -No match - -/(?<![cd])[ab]/ - dbaacb - 0: a - -/(?<!(c|d))b/ - -/(?<!(c|d))[ab]/ - dbaacb - 0: a - -/(?<!cd)[ab]/ - cdaccb - 0: b - -/^(?:a?b?)*$/ - *** Failers -No match - dbcb -No match - a-- -No match - -/((?s)^a(.))((?m)^b$)/ - a\nb\nc\n - 0: a\x0ab - 1: a\x0a - 2: \x0a - 3: b - -/((?m)^b$)/ - a\nb\nc\n - 0: b - 1: b - -/(?m)^b/ - a\nb\n - 0: b - -/(?m)^(b)/ - a\nb\n - 0: b - 1: b - -/((?m)^b)/ - a\nb\n - 0: b - 1: b - -/\n((?m)^b)/ - a\nb\n - 0: \x0ab - 1: b - -/((?s).)c(?!.)/ - a\nb\nc\n - 0: \x0ac - 1: \x0a - a\nb\nc\n - 0: \x0ac - 1: \x0a - -/((?s)b.)c(?!.)/ - a\nb\nc\n - 0: b\x0ac - 1: b\x0a - a\nb\nc\n - 0: b\x0ac - 1: b\x0a - -/^b/ - -/()^b/ - *** Failers -No match - a\nb\nc\n -No match - a\nb\nc\n -No match - -/((?m)^b)/ - a\nb\nc\n - 0: b - 1: b - -/(?(1)a|b)/ - -/(?(1)b|a)/ - a - 0: a - -/(x)?(?(1)a|b)/ - *** Failers -No match - a -No match - a -No match - -/(x)?(?(1)b|a)/ - a - 0: a - -/()?(?(1)b|a)/ - a - 0: a - -/()(?(1)b|a)/ - -/()?(?(1)a|b)/ - a - 0: a - 1: - -/^(\()?blah(?(1)(\)))$/ - (blah) - 0: (blah) - 1: ( - 2: ) - blah - 0: blah - *** Failers -No match - a -No match - blah) -No match - (blah -No match - -/^(\(+)?blah(?(1)(\)))$/ - (blah) - 0: (blah) - 1: ( - 2: ) - blah - 0: blah - *** Failers -No match - blah) -No match - (blah -No match - -/(?(?!a)a|b)/ - -/(?(?!a)b|a)/ - a - 0: a - -/(?(?=a)b|a)/ - *** Failers -No match - a -No match - a -No match - -/(?(?=a)a|b)/ - a - 0: a - -/(?=(a+?))(\1ab)/ - aaab - 0: aab - 1: a - 2: aab - -/^(?=(a+?))\1ab/ - -/(\w+:)+/ - one: - 0: one: - 1: one: - -/$(?<=^(a))/ - a - 0: - 1: a - -/(?=(a+?))(\1ab)/ - aaab - 0: aab - 1: a - 2: aab - -/^(?=(a+?))\1ab/ - *** Failers -No match - aaab -No match - aaab -No match - -/([\w:]+::)?(\w+)$/ - abcd - 0: abcd - 1: <unset> - 2: abcd - xy:z:::abcd - 0: xy:z:::abcd - 1: xy:z::: - 2: abcd - -/^[^bcd]*(c+)/ - aexycd - 0: aexyc - 1: c - -/(a*)b+/ - caab - 0: aab - 1: aa - -/([\w:]+::)?(\w+)$/ - abcd - 0: abcd - 1: <unset> - 2: abcd - xy:z:::abcd - 0: xy:z:::abcd - 1: xy:z::: - 2: abcd - *** Failers - 0: Failers - 1: <unset> - 2: Failers - abcd: -No match - abcd: -No match - -/^[^bcd]*(c+)/ - aexycd - 0: aexyc - 1: c - -/(>a+)ab/ - -/(?>a+)b/ - aaab - 0: aaab - -/([[:]+)/ - a:[b]: - 0: :[ - 1: :[ - -/([[=]+)/ - a=[b]= - 0: =[ - 1: =[ - -/([[.]+)/ - a.[b]. - 0: .[ - 1: .[ - -/((?>a+)b)/ - aaab - 0: aaab - 1: aaab - -/(?>(a+))b/ - aaab - 0: aaab - 1: aaa - -/((?>[^()]+)|\([^()]*\))+/ - ((abc(ade)ufh()()x - 0: abc(ade)ufh()()x - 1: x - -/a\Z/ - *** Failers -No match - aaab -No match - a\nb\n -No match - -/b\Z/ - a\nb\n - 0: b - -/b\z/ - -/b\Z/ - a\nb - 0: b - -/b\z/ - a\nb - 0: b - *** Failers -No match - -/^(?>(?(1)\.|())[^\W_](?>[a-z0-9-]*[^\W_])?)+$/ - a - 0: a - 1: - abc - 0: abc - 1: - a-b - 0: a-b - 1: - 0-9 - 0: 0-9 - 1: - a.b - 0: a.b - 1: - 5.6.7 - 0: 5.6.7 - 1: - the.quick.brown.fox - 0: the.quick.brown.fox - 1: - a100.b200.300c - 0: a100.b200.300c - 1: - 12-ab.1245 - 0: 12-ab.1245 - 1: - *** Failers -No match - \ -No match - .a -No match - -a -No match - a- -No match - a. -No match - a_b -No match - a.- -No match - a.. -No match - ab..bc -No match - the.quick.brown.fox- -No match - the.quick.brown.fox. -No match - the.quick.brown.fox_ -No match - the.quick.brown.fox+ -No match - -/(?>.*)(?<=(abcd|wxyz))/ - alphabetabcd - 0: alphabetabcd - 1: abcd - endingwxyz - 0: endingwxyz - 1: wxyz - *** Failers -No match - a rather long string that doesn't end with one of them -No match - -/word (?>(?:(?!otherword)[a-zA-Z0-9]+ ){0,30})otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark otherword - 0: word cat dog elephant mussel cow horse canary baboon snake shark otherword - word cat dog elephant mussel cow horse canary baboon snake shark -No match - -/word (?>[a-zA-Z0-9]+ ){0,30}otherword/ - word cat dog elephant mussel cow horse canary baboon snake shark the quick brown fox and the lazy dog and several other words getting close to thirty by now I hope -No match - -/(?<=\d{3}(?!999))foo/ - 999foo - 0: foo - 123999foo - 0: foo - *** Failers -No match - 123abcfoo -No match - -/(?<=(?!...999)\d{3})foo/ - 999foo - 0: foo - 123999foo - 0: foo - *** Failers -No match - 123abcfoo -No match - -/(?<=\d{3}(?!999)...)foo/ - 123abcfoo - 0: foo - 123456foo - 0: foo - *** Failers -No match - 123999foo -No match - -/(?<=\d{3}...)(?<!999)foo/ - 123abcfoo - 0: foo - 123456foo - 0: foo - *** Failers -No match - 123999foo -No match - -/<a[\s]+href[\s]*=[\s]* # find <a href= - ([\"\'])? # find single or double quote - (?(1) (.*?)\1 | ([^\s]+)) # if quote found, match up to next matching - # quote, otherwise match up to next space -/isx - <a href=abcd xyz - 0: <a href=abcd - 1: <unset> - 2: <unset> - 3: abcd - <a href=\"abcd xyz pqr\" cats - 0: <a href="abcd xyz pqr" - 1: " - 2: abcd xyz pqr - <a href=\'abcd xyz pqr\' cats - 0: <a href='abcd xyz pqr' - 1: ' - 2: abcd xyz pqr - -/<a\s+href\s*=\s* # find <a href= - (["'])? # find single or double quote - (?(1) (.*?)\1 | (\S+)) # if quote found, match up to next matching - # quote, otherwise match up to next space -/isx - <a href=abcd xyz - 0: <a href=abcd - 1: <unset> - 2: <unset> - 3: abcd - <a href=\"abcd xyz pqr\" cats - 0: <a href="abcd xyz pqr" - 1: " - 2: abcd xyz pqr - <a href = \'abcd xyz pqr\' cats - 0: <a href = 'abcd xyz pqr' - 1: ' - 2: abcd xyz pqr - -/<a\s+href(?>\s*)=(?>\s*) # find <a href= - (["'])? # find single or double quote - (?(1) (.*?)\1 | (\S+)) # if quote found, match up to next matching - # quote, otherwise match up to next space -/isx - <a href=abcd xyz - 0: <a href=abcd - 1: <unset> - 2: <unset> - 3: abcd - <a href=\"abcd xyz pqr\" cats - 0: <a href="abcd xyz pqr" - 1: " - 2: abcd xyz pqr - <a href = \'abcd xyz pqr\' cats - 0: <a href = 'abcd xyz pqr' - 1: ' - 2: abcd xyz pqr - -/((Z)+|A)*/ - ZABCDEFG - 0: ZA - 1: A - 2: Z - -/(Z()|A)*/ - ZABCDEFG - 0: ZA - 1: A - 2: - -/(Z(())|A)*/ - ZABCDEFG - 0: ZA - 1: A - 2: - 3: - -/((?>Z)+|A)*/ - ZABCDEFG - 0: ZA - 1: A - -/((?>)+|A)*/ - ZABCDEFG - 0: - 1: - -/a*/g - abbab - 0: a - 0: - 0: - 0: a - 0: - 0: - -/^[a-\d]/ - abcde - 0: a - -things - 0: - - 0digit - 0: 0 - *** Failers -No match - bcdef -No match - -/^[\d-a]/ - abcde - 0: a - -things - 0: - - 0digit - 0: 0 - *** Failers -No match - bcdef -No match - -/[[:space:]]+/ - > \x09\x0a\x0c\x0d\x0b< - 0: \x09\x0a\x0c\x0d\x0b - -/[[:blank:]]+/ - > \x09\x0a\x0c\x0d\x0b< - 0: \x09 - -/[\s]+/ - > \x09\x0a\x0c\x0d\x0b< - 0: \x09\x0a\x0c\x0d - -/\s+/ - > \x09\x0a\x0c\x0d\x0b< - 0: \x09\x0a\x0c\x0d - -/a b/x - ab -No match - -/(?!\A)x/m - a\nxb\n - 0: x - -/(?!^)x/m - a\nxb\n -No match - -/abc\Qabc\Eabc/ - abcabcabc - 0: abcabcabc - -/abc\Q(*+|\Eabc/ - abc(*+|abc - 0: abc(*+|abc - -/ abc\Q abc\Eabc/x - abc abcabc - 0: abc abcabc - *** Failers -No match - abcabcabc -No match - -/abc#comment - \Q#not comment - literal\E/x - abc#not comment\n literal - 0: abc#not comment\x0a literal - -/abc#comment - \Q#not comment - literal/x - abc#not comment\n literal - 0: abc#not comment\x0a literal - -/abc#comment - \Q#not comment - literal\E #more comment - /x - abc#not comment\n literal - 0: abc#not comment\x0a literal - -/abc#comment - \Q#not comment - literal\E #more comment/x - abc#not comment\n literal - 0: abc#not comment\x0a literal - -/\Qabc\$xyz\E/ - abc\\\$xyz - 0: abc\$xyz - -/\Qabc\E\$\Qxyz\E/ - abc\$xyz - 0: abc$xyz - -/\Gabc/ - abc - 0: abc - *** Failers -No match - xyzabc -No match - -/\Gabc./g - abc1abc2xyzabc3 - 0: abc1 - 0: abc2 - -/abc./g - abc1abc2xyzabc3 - 0: abc1 - 0: abc2 - 0: abc3 - -/a(?x: b c )d/ - XabcdY - 0: abcd - *** Failers -No match - Xa b c d Y -No match - -/((?x)x y z | a b c)/ - XabcY - 0: abc - 1: abc - AxyzB - 0: xyz - 1: xyz - -/(?i)AB(?-i)C/ - XabCY - 0: abC - *** Failers -No match - XabcY -No match - -/((?i)AB(?-i)C|D)E/ - abCE - 0: abCE - 1: abC - DE - 0: DE - 1: D - *** Failers -No match - abcE -No match - abCe -No match - dE -No match - De -No match - -/(.*)\d+\1/ - abc123abc - 0: abc123abc - 1: abc - abc123bc - 0: bc123bc - 1: bc - -/(.*)\d+\1/s - abc123abc - 0: abc123abc - 1: abc - abc123bc - 0: bc123bc - 1: bc - -/((.*))\d+\1/ - abc123abc - 0: abc123abc - 1: abc - 2: abc - abc123bc - 0: bc123bc - 1: bc - 2: bc - -/-- This tests for an IPv6 address in the form where it can have up to --/ -/-- eight components, one and only one of which is empty. This must be --/ -No match -/-- an internal component. --/ -No match - -/^(?!:) # colon disallowed at start - (?: # start of item - (?: [0-9a-f]{1,4} | # 1-4 hex digits or - (?(1)0 | () ) ) # if null previously matched, fail; else null - : # followed by colon - ){1,7} # end item; 1-7 of them required - [0-9a-f]{1,4} $ # final hex number at end of string - (?(1)|.) # check that there was an empty component - /xi - a123::a123 - 0: a123::a123 - 1: - a123:b342::abcd - 0: a123:b342::abcd - 1: - a123:b342::324e:abcd - 0: a123:b342::324e:abcd - 1: - a123:ddde:b342::324e:abcd - 0: a123:ddde:b342::324e:abcd - 1: - a123:ddde:b342::324e:dcba:abcd - 0: a123:ddde:b342::324e:dcba:abcd - 1: - a123:ddde:9999:b342::324e:dcba:abcd - 0: a123:ddde:9999:b342::324e:dcba:abcd - 1: - *** Failers -No match - 1:2:3:4:5:6:7:8 -No match - a123:bce:ddde:9999:b342::324e:dcba:abcd -No match - a123::9999:b342::324e:dcba:abcd -No match - abcde:2:3:4:5:6:7:8 -No match - ::1 -No match - abcd:fee0:123:: -No match - :1 -No match - 1: -No match - -/[z\Qa-d]\E]/ - z - 0: z - a - 0: a - - - 0: - - d - 0: d - ] - 0: ] - *** Failers - 0: a - b -No match - -/[\z\C]/ - z - 0: z - C - 0: C - -/\M/ - M - 0: M - -/(a+)*b/ - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - -/(?i)reg(?:ul(?:[a]|ae)r|ex)/ - REGular - 0: REGular - regulaer - 0: regulaer - Regex - 0: Regex - regulr - 0: regul\xe4r - -/[--]+/ - - 0: \xc5\xe6\xe5\xe4\xe0 - - 0: \xc5\xe6\xe5\xe4\xff - - 0: \xc5\xe6\xe5\xe4\xc0 - - 0: \xc5\xe6\xe5\xe4\xdf - -/(?<=Z)X./ - \x84XAZXB - 0: XB - -/ End of testinput1 / diff --git a/external-libs/pcre/testdata/testoutput2 b/external-libs/pcre/testdata/testoutput2 deleted file mode 100644 index ea28ccf1..00000000 --- a/external-libs/pcre/testdata/testoutput2 +++ /dev/null @@ -1,4575 +0,0 @@ -PCRE version 4.5 01-December-2003 - -/(a)b|/ -Capturing subpattern count = 1 -No options -No first char -No need char - -/abc/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - abc - 0: abc - defabc - 0: abc - \Aabc - 0: abc - *** Failers -No match - \Adefabc -No match - ABC -No match - -/^abc/ -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - abc - 0: abc - \Aabc - 0: abc - *** Failers -No match - defabc -No match - \Adefabc -No match - -/a+bc/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/a*bc/ -Capturing subpattern count = 0 -No options -No first char -Need char = 'c' - -/a{3}bc/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/(abc|a+z)/ -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/^abc$/ -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - abc - 0: abc - *** Failers -No match - def\nabc -No match - -/ab\gdef/X -Failed: unrecognized character follows \ at offset 3 - -/(?X)ab\gdef/X -Failed: unrecognized character follows \ at offset 7 - -/x{5,4}/ -Failed: numbers out of order in {} quantifier at offset 5 - -/z{65536}/ -Failed: number too big in {} quantifier at offset 7 - -/[abcd/ -Failed: missing terminating ] for character class at offset 5 - -/(?X)[\B]/ -Failed: invalid escape sequence in character class at offset 6 - -/[z-a]/ -Failed: range out of order in character class at offset 3 - -/^*/ -Failed: nothing to repeat at offset 1 - -/(abc/ -Failed: missing ) at offset 4 - -/(?# abc/ -Failed: missing ) after comment at offset 7 - -/(?z)abc/ -Failed: unrecognized character after (? at offset 2 - -/.*b/ -Capturing subpattern count = 0 -No options -First char at start or follows \n -Need char = 'b' - -/.*?b/ -Capturing subpattern count = 0 -No options -First char at start or follows \n -Need char = 'b' - -/cat|dog|elephant/ -Capturing subpattern count = 0 -No options -No first char -No need char - this sentence eventually mentions a cat - 0: cat - this sentences rambles on and on for a while and then reaches elephant - 0: elephant - -/cat|dog|elephant/S -Capturing subpattern count = 0 -No options -No first char -No need char -Starting character set: c d e - this sentence eventually mentions a cat - 0: cat - this sentences rambles on and on for a while and then reaches elephant - 0: elephant - -/cat|dog|elephant/iS -Capturing subpattern count = 0 -Options: caseless -No first char -No need char -Starting character set: C D E c d e - this sentence eventually mentions a CAT cat - 0: CAT - this sentences rambles on and on for a while to elephant ElePhant - 0: elephant - -/a|[bcd]/S -Capturing subpattern count = 0 -No options -No first char -No need char -Starting character set: a b c d - -/(a|[^\dZ])/S -Capturing subpattern count = 1 -No options -No first char -No need char -Starting character set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a - \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 - \x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / : ; < = > - ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y [ \ ] ^ _ ` a b c d - e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f \x80 \x81 \x82 \x83 - \x84 \x85 \x86 \x87 \x88 \x89 \x8a \x8b \x8c \x8d \x8e \x8f \x90 \x91 \x92 - \x93 \x94 \x95 \x96 \x97 \x98 \x99 \x9a \x9b \x9c \x9d \x9e \x9f \xa0 \xa1 - \xa2 \xa3 \xa4 \xa5 \xa6 \xa7 \xa8 \xa9 \xaa \xab \xac \xad \xae \xaf \xb0 - \xb1 \xb2 \xb3 \xb4 \xb5 \xb6 \xb7 \xb8 \xb9 \xba \xbb \xbc \xbd \xbe \xbf - \xc0 \xc1 \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce - \xcf \xd0 \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd - \xde \xdf \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec - \xed \xee \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb - \xfc \xfd \xfe \xff - -/(a|b)*[\s]/S -Capturing subpattern count = 1 -No options -No first char -No need char -Starting character set: \x09 \x0a \x0c \x0d \x20 a b - -/(ab\2)/ -Failed: reference to non-existent subpattern at offset 6 - -/{4,5}abc/ -Failed: nothing to repeat at offset 4 - -/(a)(b)(c)\2/ -Capturing subpattern count = 3 -Max back reference = 2 -No options -First char = 'a' -Need char = 'c' - abcb - 0: abcb - 1: a - 2: b - 3: c - \O0abcb -Matched, but too many substrings - \O3abcb -Matched, but too many substrings - 0: abcb - \O6abcb -Matched, but too many substrings - 0: abcb - 1: a - \O9abcb -Matched, but too many substrings - 0: abcb - 1: a - 2: b - \O12abcb - 0: abcb - 1: a - 2: b - 3: c - -/(a)bc|(a)(b)\2/ -Capturing subpattern count = 3 -Max back reference = 2 -No options -First char = 'a' -No need char - abc - 0: abc - 1: a - \O0abc -Matched, but too many substrings - \O3abc -Matched, but too many substrings - 0: abc - \O6abc - 0: abc - 1: a - aba - 0: aba - 1: <unset> - 2: a - 3: b - \O0aba -Matched, but too many substrings - \O3aba -Matched, but too many substrings - 0: aba - \O6aba -Matched, but too many substrings - 0: aba - 1: <unset> - \O9aba -Matched, but too many substrings - 0: aba - 1: <unset> - 2: a - \O12aba - 0: aba - 1: <unset> - 2: a - 3: b - -/abc$/E -Capturing subpattern count = 0 -Options: dollar_endonly -First char = 'a' -Need char = 'c' - abc - 0: abc - *** Failers -No match - abc\n -No match - abc\ndef -No match - -/(a)(b)(c)(d)(e)\6/ -Failed: reference to non-existent subpattern at offset 17 - -/the quick brown fox/ -Capturing subpattern count = 0 -No options -First char = 't' -Need char = 'x' - the quick brown fox - 0: the quick brown fox - this is a line with the quick brown fox - 0: the quick brown fox - -/the quick brown fox/A -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - the quick brown fox - 0: the quick brown fox - *** Failers -No match - this is a line with the quick brown fox -No match - -/ab(?z)cd/ -Failed: unrecognized character after (? at offset 4 - -/^abc|def/ -Capturing subpattern count = 0 -No options -No first char -No need char - abcdef - 0: abc - abcdef\B - 0: def - -/.*((abc)$|(def))/ -Capturing subpattern count = 3 -No options -First char at start or follows \n -No need char - defabc - 0: defabc - 1: abc - 2: abc - \Zdefabc - 0: def - 1: def - 2: <unset> - 3: def - -/abc/P - abc - 0: abc - *** Failers -No match: POSIX code 17: match failed - -/^abc|def/P - abcdef - 0: abc - abcdef\B - 0: def - -/.*((abc)$|(def))/P - defabc - 0: defabc - 1: abc - 2: abc - \Zdefabc - 0: def - 1: def - 3: def - -/the quick brown fox/P - the quick brown fox - 0: the quick brown fox - *** Failers -No match: POSIX code 17: match failed - The Quick Brown Fox -No match: POSIX code 17: match failed - -/the quick brown fox/Pi - the quick brown fox - 0: the quick brown fox - The Quick Brown Fox - 0: The Quick Brown Fox - -/abc.def/P - *** Failers -No match: POSIX code 17: match failed - abc\ndef -No match: POSIX code 17: match failed - -/abc$/P - abc - 0: abc - abc\n - 0: abc - -/(abc)\2/P -Failed: POSIX code 15: bad back reference at offset 7 - -/(abc\1)/P - abc -No match: POSIX code 17: match failed - -/)/ -Failed: unmatched parentheses at offset 0 - -/a[]b/ -Failed: missing terminating ] for character class at offset 4 - -/[^aeiou ]{3,}/ -Capturing subpattern count = 0 -No options -No first char -No need char - co-processors, and for - 0: -pr - -/<.*>/ -Capturing subpattern count = 0 -No options -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def>ghi<klm> - -/<.*?>/ -Capturing subpattern count = 0 -No options -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def> - -/<.*>/U -Capturing subpattern count = 0 -Options: ungreedy -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def> - -/(?U)<.*>/ -Capturing subpattern count = 0 -Options: ungreedy -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def> - -/<.*?>/U -Capturing subpattern count = 0 -Options: ungreedy -First char = '<' -Need char = '>' - abc<def>ghi<klm>nop - 0: <def>ghi<klm> - -/={3,}/U -Capturing subpattern count = 0 -Options: ungreedy -First char = '=' -Need char = '=' - abc========def - 0: === - -/(?U)={3,}?/ -Capturing subpattern count = 0 -Options: ungreedy -First char = '=' -Need char = '=' - abc========def - 0: ======== - -/(?<!bar|cattle)foo/ -Capturing subpattern count = 0 -No options -First char = 'f' -Need char = 'o' - foo - 0: foo - catfoo - 0: foo - *** Failers -No match - the barfoo -No match - and cattlefoo -No match - -/(?<=a+)b/ -Failed: lookbehind assertion is not fixed length at offset 6 - -/(?<=aaa|b{0,3})b/ -Failed: lookbehind assertion is not fixed length at offset 14 - -/(?<!(foo)a\1)bar/ -Failed: lookbehind assertion is not fixed length at offset 12 - -/(?i)abc/ -Capturing subpattern count = 0 -Options: caseless -First char = 'a' (caseless) -Need char = 'c' (caseless) - -/(a|(?m)a)/ -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/(?i)^1234/ -Capturing subpattern count = 0 -Options: anchored caseless -No first char -No need char - -/(^b|(?i)^d)/ -Capturing subpattern count = 1 -Options: anchored -Case state changes -No first char -No need char - -/(?s).*/ -Capturing subpattern count = 0 -Options: anchored dotall -No first char -No need char - -/[abcd]/S -Capturing subpattern count = 0 -No options -No first char -No need char -Starting character set: a b c d - -/(?i)[abcd]/S -Capturing subpattern count = 0 -Options: caseless -No first char -No need char -Starting character set: A B C D a b c d - -/(?m)[xy]|(b|c)/S -Capturing subpattern count = 1 -Options: multiline -No first char -No need char -Starting character set: b c x y - -/(^a|^b)/m -Capturing subpattern count = 1 -Options: multiline -First char at start or follows \n -No need char - -/(?i)(^a|^b)/m -Capturing subpattern count = 1 -Options: caseless multiline -First char at start or follows \n -No need char - -/(a)(?(1)a|b|c)/ -Failed: conditional group contains more than two branches at offset 13 - -/(?(?=a)a|b|c)/ -Failed: conditional group contains more than two branches at offset 12 - -/(?(1a)/ -Failed: malformed number after (?( at offset 4 - -/(?(?i))/ -Failed: assertion expected after (?( at offset 3 - -/(?(abc))/ -Failed: assertion expected after (?( at offset 3 - -/(?(?<ab))/ -Failed: unrecognized character after (?< at offset 5 - -/((?s)blah)\s+\1/ -Capturing subpattern count = 1 -Max back reference = 1 -No options -First char = 'b' -Need char = 'h' - -/((?i)blah)\s+\1/ -Capturing subpattern count = 1 -Max back reference = 1 -No options -Case state changes -First char = 'b' (caseless) -Need char = 'h' (caseless) - -/((?i)b)/DS ------------------------------------------------------------------- - 0 16 Bra 0 - 3 8 Bra 1 - 6 01 Opt - 8 1 b - 11 8 Ket - 14 00 Opt - 16 16 Ket - 19 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -Case state changes -First char = 'b' (caseless) -No need char -Study returned NULL - -/(a*b|(?i:c*(?-i)d))/S -Capturing subpattern count = 1 -No options -Case state changes -No first char -No need char -Starting character set: C a b c d - -/a$/ -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - a - 0: a - a\n - 0: a - *** Failers -No match - \Za -No match - \Za\n -No match - -/a$/m -Capturing subpattern count = 0 -Options: multiline -First char = 'a' -No need char - a - 0: a - a\n - 0: a - \Za\n - 0: a - *** Failers -No match - \Za -No match - -/\Aabc/m -Capturing subpattern count = 0 -Options: anchored multiline -No first char -No need char - -/^abc/m -Capturing subpattern count = 0 -Options: multiline -First char at start or follows \n -Need char = 'c' - -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/ -Capturing subpattern count = 5 -Options: anchored -No first char -No need char - aaaaabbbbbcccccdef - 0: aaaaabbbbbcccccdef - 1: aaaaabbbbbcccccdef - 2: aaaaa - 3: b - 4: bbbbccccc - 5: def - -/(?<=foo)[ab]/S -Capturing subpattern count = 0 -No options -No first char -No need char -Starting character set: a b - -/(?<!foo)(alpha|omega)/S -Capturing subpattern count = 1 -No options -No first char -Need char = 'a' -Starting character set: a o - -/(?!alphabet)[ab]/S -Capturing subpattern count = 0 -No options -No first char -No need char -Starting character set: a b - -/(?<=foo\n)^bar/m -Capturing subpattern count = 0 -Options: multiline -First char at start or follows \n -Need char = 'r' - -/(?>^abc)/m -Capturing subpattern count = 0 -Options: multiline -First char at start or follows \n -Need char = 'c' - abc - 0: abc - def\nabc - 0: abc - *** Failers -No match - defabc -No match - -/(?<=ab(c+)d)ef/ -Failed: lookbehind assertion is not fixed length at offset 11 - -/(?<=ab(?<=c+)d)ef/ -Failed: lookbehind assertion is not fixed length at offset 12 - -/(?<=ab(c|de)f)g/ -Failed: lookbehind assertion is not fixed length at offset 13 - -/The next three are in testinput2 because they have variable length branches/ -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 's' - -/(?<=bullock|donkey)-cart/ -Capturing subpattern count = 0 -No options -First char = '-' -Need char = 't' - the bullock-cart - 0: -cart - a donkey-cart race - 0: -cart - *** Failers -No match - cart -No match - horse-and-cart -No match - -/(?<=ab(?i)x|y|z)/ -Capturing subpattern count = 0 -No options -Case state changes -No first char -No need char - -/(?>.*)(?<=(abcd)|(xyz))/ -Capturing subpattern count = 2 -No options -First char at start or follows \n -No need char - alphabetabcd - 0: alphabetabcd - 1: abcd - endingxyz - 0: endingxyz - 1: <unset> - 2: xyz - -/(?<=ab(?i)x(?-i)y|(?i)z|b)ZZ/ -Capturing subpattern count = 0 -No options -Case state changes -First char = 'Z' -Need char = 'Z' - abxyZZ - 0: ZZ - abXyZZ - 0: ZZ - ZZZ - 0: ZZ - zZZ - 0: ZZ - bZZ - 0: ZZ - BZZ - 0: ZZ - *** Failers -No match - ZZ -No match - abXYZZ -No match - zzz -No match - bzz -No match - -/(?<!(foo)a)bar/ -Capturing subpattern count = 1 -No options -First char = 'b' -Need char = 'r' - bar - 0: bar - foobbar - 0: bar - *** Failers -No match - fooabar -No match - -/This one is here because Perl 5.005_02 doesn't fail it/ -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 't' - -/^(a)?(?(1)a|b)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - *** Failers -No match - a -No match - -/This one is here because I think Perl 5.005_02 gets the setting of $1 wrong/ -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 'g' - -/^(a\1?){4}$/ -Capturing subpattern count = 1 -Max back reference = 1 -Options: anchored -No first char -No need char - aaaaaa - 0: aaaaaa - 1: aa - -/These are syntax tests from Perl 5.005/ -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = '5' - -/a[b-a]/ -Failed: range out of order in character class at offset 4 - -/a[]b/ -Failed: missing terminating ] for character class at offset 4 - -/a[/ -Failed: missing terminating ] for character class at offset 2 - -/*a/ -Failed: nothing to repeat at offset 0 - -/(*)b/ -Failed: nothing to repeat at offset 1 - -/abc)/ -Failed: unmatched parentheses at offset 3 - -/(abc/ -Failed: missing ) at offset 4 - -/a**/ -Failed: nothing to repeat at offset 2 - -/)(/ -Failed: unmatched parentheses at offset 0 - -/\1/ -Failed: reference to non-existent subpattern at offset 2 - -/\2/ -Failed: reference to non-existent subpattern at offset 2 - -/(a)|\2/ -Failed: reference to non-existent subpattern at offset 6 - -/a[b-a]/i -Failed: range out of order in character class at offset 4 - -/a[]b/i -Failed: missing terminating ] for character class at offset 4 - -/a[/i -Failed: missing terminating ] for character class at offset 2 - -/*a/i -Failed: nothing to repeat at offset 0 - -/(*)b/i -Failed: nothing to repeat at offset 1 - -/abc)/i -Failed: unmatched parentheses at offset 3 - -/(abc/i -Failed: missing ) at offset 4 - -/a**/i -Failed: nothing to repeat at offset 2 - -/)(/i -Failed: unmatched parentheses at offset 0 - -/:(?:/ -Failed: missing ) at offset 4 - -/(?<%)b/ -Failed: unrecognized character after (?< at offset 3 - -/a(?{)b/ -Failed: unrecognized character after (? at offset 3 - -/a(?{{})b/ -Failed: unrecognized character after (? at offset 3 - -/a(?{}})b/ -Failed: unrecognized character after (? at offset 3 - -/a(?{"{"})b/ -Failed: unrecognized character after (? at offset 3 - -/a(?{"{"}})b/ -Failed: unrecognized character after (? at offset 3 - -/(?(1?)a|b)/ -Failed: malformed number after (?( at offset 4 - -/(?(1)a|b|c)/ -Failed: conditional group contains more than two branches at offset 10 - -/[a[:xyz:/ -Failed: missing terminating ] for character class at offset 8 - -/(?<=x+)y/ -Failed: lookbehind assertion is not fixed length at offset 6 - -/a{37,17}/ -Failed: numbers out of order in {} quantifier at offset 7 - -/abc/\ -Failed: \ at end of pattern at offset 4 - -/abc/\P -Failed: POSIX code 9: bad escape sequence at offset 4 - -/abc/\i -Failed: \ at end of pattern at offset 4 - -/(a)bc(d)/ -Capturing subpattern count = 2 -No options -First char = 'a' -Need char = 'd' - abcd - 0: abcd - 1: a - 2: d - abcd\C2 - 0: abcd - 1: a - 2: d - 2C d (1) - abcd\C5 - 0: abcd - 1: a - 2: d -copy substring 5 failed -7 - -/(.{20})/ -Capturing subpattern count = 1 -No options -No first char -No need char - abcdefghijklmnopqrstuvwxyz - 0: abcdefghijklmnopqrst - 1: abcdefghijklmnopqrst - abcdefghijklmnopqrstuvwxyz\C1 - 0: abcdefghijklmnopqrst - 1: abcdefghijklmnopqrst -copy substring 1 failed -6 - abcdefghijklmnopqrstuvwxyz\G1 - 0: abcdefghijklmnopqrst - 1: abcdefghijklmnopqrst - 1G abcdefghijklmnopqrst (20) - -/(.{15})/ -Capturing subpattern count = 1 -No options -No first char -No need char - abcdefghijklmnopqrstuvwxyz - 0: abcdefghijklmno - 1: abcdefghijklmno - abcdefghijklmnopqrstuvwxyz\C1\G1 - 0: abcdefghijklmno - 1: abcdefghijklmno - 1C abcdefghijklmno (15) - 1G abcdefghijklmno (15) - -/(.{16})/ -Capturing subpattern count = 1 -No options -No first char -No need char - abcdefghijklmnopqrstuvwxyz - 0: abcdefghijklmnop - 1: abcdefghijklmnop - abcdefghijklmnopqrstuvwxyz\C1\G1\L - 0: abcdefghijklmnop - 1: abcdefghijklmnop -copy substring 1 failed -6 - 1G abcdefghijklmnop (16) - 0L abcdefghijklmnop - 1L abcdefghijklmnop - -/^(a|(bc))de(f)/ -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - adef\G1\G2\G3\G4\L - 0: adef - 1: a - 2: <unset> - 3: f - 1G a (1) - 2G (0) - 3G f (1) -get substring 4 failed -7 - 0L adef - 1L a - 2L - 3L f - bcdef\G1\G2\G3\G4\L - 0: bcdef - 1: bc - 2: bc - 3: f - 1G bc (2) - 2G bc (2) - 3G f (1) -get substring 4 failed -7 - 0L bcdef - 1L bc - 2L bc - 3L f - adefghijk\C0 - 0: adef - 1: a - 2: <unset> - 3: f - 0C adef (4) - -/^abc\00def/ -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - abc\00def\L\C0 - 0: abc\x00def - 0C abc (7) - 0L abc - -/word ((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ )((?:[a-zA-Z0-9]+ -)?)?)?)?)?)?)?)?)?otherword/M -Memory allocation (code space): 428 -Capturing subpattern count = 8 -No options -First char = 'w' -Need char = 'd' - -/.*X/D ------------------------------------------------------------------- - 0 8 Bra 0 - 3 Any* - 5 1 X - 8 8 Ket - 11 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char at start or follows \n -Need char = 'X' - -/.*X/Ds ------------------------------------------------------------------- - 0 8 Bra 0 - 3 Any* - 5 1 X - 8 8 Ket - 11 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored dotall -No first char -Need char = 'X' - -/(.*X|^B)/D ------------------------------------------------------------------- - 0 21 Bra 0 - 3 8 Bra 1 - 6 Any* - 8 1 X - 11 7 Alt - 14 ^ - 15 1 B - 18 15 Ket - 21 21 Ket - 24 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char at start or follows \n -No need char - -/(.*X|^B)/Ds ------------------------------------------------------------------- - 0 21 Bra 0 - 3 8 Bra 1 - 6 Any* - 8 1 X - 11 7 Alt - 14 ^ - 15 1 B - 18 15 Ket - 21 21 Ket - 24 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: anchored dotall -No first char -No need char - -/(?s)(.*X|^B)/D ------------------------------------------------------------------- - 0 21 Bra 0 - 3 8 Bra 1 - 6 Any* - 8 1 X - 11 7 Alt - 14 ^ - 15 1 B - 18 15 Ket - 21 21 Ket - 24 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: anchored dotall -No first char -No need char - -/(?s:.*X|^B)/D ------------------------------------------------------------------- - 0 27 Bra 0 - 3 10 Bra 0 - 6 04 Opt - 8 Any* - 10 1 X - 13 9 Alt - 16 04 Opt - 18 ^ - 19 1 B - 22 19 Ket - 25 00 Opt - 27 27 Ket - 30 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char at start or follows \n -No need char - -/\Biss\B/+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - -/\Biss\B/+P - Mississippi - 0: iss - 0+ issippi - -/iss/G+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - -/\Biss\B/G+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - -/\Biss\B/g+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - *** Failers -No match - Mississippi\A -No match - -/(?<=[Ms])iss/g+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - 0: iss - 0+ ippi - -/(?<=[Ms])iss/G+ -Capturing subpattern count = 0 -No options -First char = 'i' -Need char = 's' - Mississippi - 0: iss - 0+ issippi - -/^iss/g+ -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - ississippi - 0: iss - 0+ issippi - -/.*iss/g+ -Capturing subpattern count = 0 -No options -First char at start or follows \n -Need char = 's' - abciss\nxyzisspqr - 0: abciss - 0+ \x0axyzisspqr - 0: xyziss - 0+ pqr - -/.i./+g -Capturing subpattern count = 0 -No options -No first char -Need char = 'i' - Mississippi - 0: Mis - 0+ sissippi - 0: sis - 0+ sippi - 0: sip - 0+ pi - Mississippi\A - 0: Mis - 0+ sissippi - 0: sis - 0+ sippi - 0: sip - 0+ pi - Missouri river - 0: Mis - 0+ souri river - 0: ri - 0+ river - 0: riv - 0+ er - Missouri river\A - 0: Mis - 0+ souri river - -/^.is/+g -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - Mississippi - 0: Mis - 0+ sissippi - -/^ab\n/g+ -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - ab\nab\ncd - 0: ab\x0a - 0+ ab\x0acd - -/^ab\n/mg+ -Capturing subpattern count = 0 -Options: multiline -First char at start or follows \n -Need char = 10 - ab\nab\ncd - 0: ab\x0a - 0+ ab\x0acd - 0: ab\x0a - 0+ cd - -/abc/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/abc|bac/ -Capturing subpattern count = 0 -No options -No first char -Need char = 'c' - -/(abc|bac)/ -Capturing subpattern count = 1 -No options -No first char -Need char = 'c' - -/(abc|(c|dc))/ -Capturing subpattern count = 2 -No options -No first char -Need char = 'c' - -/(abc|(d|de)c)/ -Capturing subpattern count = 2 -No options -No first char -Need char = 'c' - -/a*/ -Capturing subpattern count = 0 -No options -No first char -No need char - -/a+/ -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/(baa|a+)/ -Capturing subpattern count = 1 -No options -No first char -Need char = 'a' - -/a{0,3}/ -Capturing subpattern count = 0 -No options -No first char -No need char - -/baa{3,}/ -Capturing subpattern count = 0 -No options -First char = 'b' -Need char = 'a' - -/"([^\\"]+|\\.)*"/ -Capturing subpattern count = 1 -No options -First char = '"' -Need char = '"' - -/(abc|ab[cd])/ -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/(a|.)/ -Capturing subpattern count = 1 -No options -No first char -No need char - -/a|ba|\w/ -Capturing subpattern count = 0 -No options -No first char -No need char - -/abc(?=pqr)/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'r' - -/...(?<=abc)/ -Capturing subpattern count = 0 -No options -No first char -No need char - -/abc(?!pqr)/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/ab./ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/ab[xyz]/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/abc*/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/ab.c*/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/a.c*/ -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/.c*/ -Capturing subpattern count = 0 -No options -No first char -No need char - -/ac*/ -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/(a.c*|b.c*)/ -Capturing subpattern count = 1 -No options -No first char -No need char - -/a.c*|aba/ -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/.+a/ -Capturing subpattern count = 0 -No options -No first char -Need char = 'a' - -/(?=abcda)a.*/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'a' - -/(?=a)a.*/ -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/a(b)*/ -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/a\d*/ -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/ab\d*/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/a(\d)*/ -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/abcde{0,0}/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'd' - -/ab\d+/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/a(?(1)b)/ -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/a(?(1)bag|big)/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'g' - -/a(?(1)bag|big)*/ -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/a(?(1)bag|big)+/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'g' - -/a(?(1)b..|b..)/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/ab\d{0}e/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'e' - -/a?b?/ -Capturing subpattern count = 0 -No options -No first char -No need char - a - 0: a - b - 0: b - ab - 0: ab - \ - 0: - *** Failers - 0: - \N -No match - -/|-/ -Capturing subpattern count = 0 -No options -No first char -No need char - abcd - 0: - -abc - 0: - \Nab-c - 0: - - *** Failers - 0: - \Nabc -No match - -/a*(b+)(z)(z)/P - aaaabbbbzzzz - 0: aaaabbbbzz - 1: bbbb - 2: z - 3: z - aaaabbbbzzzz\O0 - aaaabbbbzzzz\O1 - 0: aaaabbbbzz - aaaabbbbzzzz\O2 - 0: aaaabbbbzz - 1: bbbb - aaaabbbbzzzz\O3 - 0: aaaabbbbzz - 1: bbbb - 2: z - aaaabbbbzzzz\O4 - 0: aaaabbbbzz - 1: bbbb - 2: z - 3: z - aaaabbbbzzzz\O5 - 0: aaaabbbbzz - 1: bbbb - 2: z - 3: z - -/^.?abcd/S -Capturing subpattern count = 0 -Options: anchored -No first char -Need char = 'd' -Study returned NULL - -/\( # ( at start - (?: # Non-capturing bracket - (?>[^()]+) # Either a sequence of non-brackets (no backtracking) - | # Or - (?R) # Recurse - i.e. nested bracketed string - )* # Zero or more contents - \) # Closing ) - /x -Capturing subpattern count = 0 -Options: extended -First char = '(' -Need char = ')' - (abcd) - 0: (abcd) - (abcd)xyz - 0: (abcd) - xyz(abcd) - 0: (abcd) - (ab(xy)cd)pqr - 0: (ab(xy)cd) - (ab(xycd)pqr - 0: (xycd) - () abc () - 0: () - 12(abcde(fsh)xyz(foo(bar))lmno)89 - 0: (abcde(fsh)xyz(foo(bar))lmno) - *** Failers -No match - abcd -No match - abcd) -No match - (abcd -No match - -/\( ( (?>[^()]+) | (?R) )* \) /xg -Capturing subpattern count = 1 -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd)pqr - 0: (ab(xy)cd) - 1: cd - 1(abcd)(x(y)z)pqr - 0: (abcd) - 1: abcd - 0: (x(y)z) - 1: z - -/\( (?: (?>[^()]+) | (?R) ) \) /x -Capturing subpattern count = 0 -Options: extended -First char = '(' -Need char = ')' - (abcd) - 0: (abcd) - (ab(xy)cd) - 0: (xy) - (a(b(c)d)e) - 0: (c) - ((ab)) - 0: ((ab)) - *** Failers -No match - () -No match - -/\( (?: (?>[^()]+) | (?R) )? \) /x -Capturing subpattern count = 0 -Options: extended -First char = '(' -Need char = ')' - () - 0: () - 12(abcde(fsh)xyz(foo(bar))lmno)89 - 0: (fsh) - -/\( ( (?>[^()]+) | (?R) )* \) /x -Capturing subpattern count = 1 -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: cd - -/\( ( ( (?>[^()]+) | (?R) )* ) \) /x -Capturing subpattern count = 2 -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: ab(xy)cd - 2: cd - -/\( (123)? ( ( (?>[^()]+) | (?R) )* ) \) /x -Capturing subpattern count = 3 -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: <unset> - 2: ab(xy)cd - 3: cd - (123ab(xy)cd) - 0: (123ab(xy)cd) - 1: 123 - 2: ab(xy)cd - 3: cd - -/\( ( (123)? ( (?>[^()]+) | (?R) )* ) \) /x -Capturing subpattern count = 3 -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: ab(xy)cd - 2: <unset> - 3: cd - (123ab(xy)cd) - 0: (123ab(xy)cd) - 1: 123ab(xy)cd - 2: 123 - 3: cd - -/\( (((((((((( ( (?>[^()]+) | (?R) )* )))))))))) \) /x -Capturing subpattern count = 11 -Options: extended -First char = '(' -Need char = ')' - (ab(xy)cd) - 0: (ab(xy)cd) - 1: ab(xy)cd - 2: ab(xy)cd - 3: ab(xy)cd - 4: ab(xy)cd - 5: ab(xy)cd - 6: ab(xy)cd - 7: ab(xy)cd - 8: ab(xy)cd - 9: ab(xy)cd -10: ab(xy)cd -11: cd - -/\( ( ( (?>[^()<>]+) | ((?>[^()]+)) | (?R) )* ) \) /x -Capturing subpattern count = 3 -Options: extended -First char = '(' -Need char = ')' - (abcd(xyz<p>qrs)123) - 0: (abcd(xyz<p>qrs)123) - 1: abcd(xyz<p>qrs)123 - 2: 123 - 3: <unset> - -/\( ( ( (?>[^()]+) | ((?R)) )* ) \) /x -Capturing subpattern count = 3 -Options: extended -First char = '(' -Need char = ')' - (ab(cd)ef) - 0: (ab(cd)ef) - 1: ab(cd)ef - 2: ef - 3: (cd) - (ab(cd(ef)gh)ij) - 0: (ab(cd(ef)gh)ij) - 1: ab(cd(ef)gh)ij - 2: ij - 3: (cd(ef)gh) - -/^[[:alnum:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [0-9A-Za-z] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:alpha:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [A-Za-z] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:ascii:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x00-\x7f] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:blank:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x09 ] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:cntrl:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x00-\x1f\x7f] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:digit:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [0-9] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:graph:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [!-~] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:lower:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [a-z] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:print:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [ -~] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:punct:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [!-/:-@[-`{-~] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:space:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x09-\x0d ] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:upper:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [A-Z] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:xdigit:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [0-9A-Fa-f] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:word:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [0-9A-Z_a-z] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^cntrl:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [ -~\x80-\xff] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[12[:^digit:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x00-/1-2:-\xff] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/^[[:^blank:]]/D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x00-\x08\x0a-\x1f!-\xff] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/[01[:alpha:]%]/D ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [%0-1A-Za-z] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[[.ch.]]/ -Failed: POSIX collating elements are not supported at offset 1 - -/[[=ch=]]/ -Failed: POSIX collating elements are not supported at offset 1 - -/[[:rhubarb:]]/ -Failed: unknown POSIX class name at offset 3 - -/[[:upper:]]/i -Capturing subpattern count = 0 -Options: caseless -No first char -No need char - A - 0: A - a - 0: a - -/[[:lower:]]/i -Capturing subpattern count = 0 -Options: caseless -No first char -No need char - A - 0: A - a - 0: a - -/((?-i)[[:lower:]])[[:lower:]]/i -Capturing subpattern count = 1 -Options: caseless -Case state changes -No first char -No need char - ab - 0: ab - 1: a - aB - 0: aB - 1: a - *** Failers - 0: ai - 1: a - Ab -No match - AB -No match - -/[\200-\410]/ -Failed: range out of order in character class at offset 9 - -/^(?(0)f|b)oo/ -Failed: invalid condition (?(0) at offset 5 - -/This one's here because of the large output vector needed/ -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 'd' - -/(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\d+(?:\s|$))(\w+)\s+(\270)/ -Capturing subpattern count = 271 -Max back reference = 270 -No options -No first char -No need char - \O900 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC - 0: 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 ABC ABC - 1: 1 - 2: 2 - 3: 3 - 4: 4 - 5: 5 - 6: 6 - 7: 7 - 8: 8 - 9: 9 -10: 10 -11: 11 -12: 12 -13: 13 -14: 14 -15: 15 -16: 16 -17: 17 -18: 18 -19: 19 -20: 20 -21: 21 -22: 22 -23: 23 -24: 24 -25: 25 -26: 26 -27: 27 -28: 28 -29: 29 -30: 30 -31: 31 -32: 32 -33: 33 -34: 34 -35: 35 -36: 36 -37: 37 -38: 38 -39: 39 -40: 40 -41: 41 -42: 42 -43: 43 -44: 44 -45: 45 -46: 46 -47: 47 -48: 48 -49: 49 -50: 50 -51: 51 -52: 52 -53: 53 -54: 54 -55: 55 -56: 56 -57: 57 -58: 58 -59: 59 -60: 60 -61: 61 -62: 62 -63: 63 -64: 64 -65: 65 -66: 66 -67: 67 -68: 68 -69: 69 -70: 70 -71: 71 -72: 72 -73: 73 -74: 74 -75: 75 -76: 76 -77: 77 -78: 78 -79: 79 -80: 80 -81: 81 -82: 82 -83: 83 -84: 84 -85: 85 -86: 86 -87: 87 -88: 88 -89: 89 -90: 90 -91: 91 -92: 92 -93: 93 -94: 94 -95: 95 -96: 96 -97: 97 -98: 98 -99: 99 -100: 100 -101: 101 -102: 102 -103: 103 -104: 104 -105: 105 -106: 106 -107: 107 -108: 108 -109: 109 -110: 110 -111: 111 -112: 112 -113: 113 -114: 114 -115: 115 -116: 116 -117: 117 -118: 118 -119: 119 -120: 120 -121: 121 -122: 122 -123: 123 -124: 124 -125: 125 -126: 126 -127: 127 -128: 128 -129: 129 -130: 130 -131: 131 -132: 132 -133: 133 -134: 134 -135: 135 -136: 136 -137: 137 -138: 138 -139: 139 -140: 140 -141: 141 -142: 142 -143: 143 -144: 144 -145: 145 -146: 146 -147: 147 -148: 148 -149: 149 -150: 150 -151: 151 -152: 152 -153: 153 -154: 154 -155: 155 -156: 156 -157: 157 -158: 158 -159: 159 -160: 160 -161: 161 -162: 162 -163: 163 -164: 164 -165: 165 -166: 166 -167: 167 -168: 168 -169: 169 -170: 170 -171: 171 -172: 172 -173: 173 -174: 174 -175: 175 -176: 176 -177: 177 -178: 178 -179: 179 -180: 180 -181: 181 -182: 182 -183: 183 -184: 184 -185: 185 -186: 186 -187: 187 -188: 188 -189: 189 -190: 190 -191: 191 -192: 192 -193: 193 -194: 194 -195: 195 -196: 196 -197: 197 -198: 198 -199: 199 -200: 200 -201: 201 -202: 202 -203: 203 -204: 204 -205: 205 -206: 206 -207: 207 -208: 208 -209: 209 -210: 210 -211: 211 -212: 212 -213: 213 -214: 214 -215: 215 -216: 216 -217: 217 -218: 218 -219: 219 -220: 220 -221: 221 -222: 222 -223: 223 -224: 224 -225: 225 -226: 226 -227: 227 -228: 228 -229: 229 -230: 230 -231: 231 -232: 232 -233: 233 -234: 234 -235: 235 -236: 236 -237: 237 -238: 238 -239: 239 -240: 240 -241: 241 -242: 242 -243: 243 -244: 244 -245: 245 -246: 246 -247: 247 -248: 248 -249: 249 -250: 250 -251: 251 -252: 252 -253: 253 -254: 254 -255: 255 -256: 256 -257: 257 -258: 258 -259: 259 -260: 260 -261: 261 -262: 262 -263: 263 -264: 264 -265: 265 -266: 266 -267: 267 -268: 268 -269: 269 -270: ABC -271: ABC - -/This one's here because Perl does this differently and PCRE can't at present/ -Capturing subpattern count = 0 -No options -First char = 'T' -Need char = 't' - -/(main(O)?)+/ -Capturing subpattern count = 2 -No options -First char = 'm' -Need char = 'n' - mainmain - 0: mainmain - 1: main - mainOmain - 0: mainOmain - 1: main - 2: O - -/These are all cases where Perl does it differently (nested captures)/ -Capturing subpattern count = 1 -No options -First char = 'T' -Need char = 's' - -/^(a(b)?)+$/ -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aba - 0: aba - 1: a - 2: b - -/^(aa(bb)?)+$/ -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - -/^(aa|aa(bb))+$/ -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - -/^(aa(bb)??)+$/ -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - -/^(?:aa(bb)?)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: bb - -/^(aa(b(b))?)+$/ -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: aa - 2: bb - 3: b - -/^(?:aa(b(b))?)+$/ -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: bb - 2: b - -/^(?:aa(b(?:b))?)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: bb - -/^(?:aa(bb(?:b))?)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: bbb - -/^(?:aa(b(?:bb))?)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: bbb - -/^(?:aa(?:b(b))?)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbaa - 0: aabbaa - 1: b - -/^(?:aa(?:b(bb))?)+$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: bb - -/^(aa(b(bb))?)+$/ -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - aabbbaa - 0: aabbbaa - 1: aa - 2: bbb - 3: bb - -/^(aa(bb(bb))?)+$/ -Capturing subpattern count = 3 -Options: anchored -No first char -No need char - aabbbbaa - 0: aabbbbaa - 1: aa - 2: bbbb - 3: bb - -/--------------------------------------------------------------------/ -Capturing subpattern count = 0 -No options -First char = '-' -Need char = '-' - -/#/xMD -Memory allocation (code space): 7 ------------------------------------------------------------------- - 0 3 Bra 0 - 3 3 Ket - 6 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: extended -No first char -No need char - -/a#/xMD -Memory allocation (code space): 13 ------------------------------------------------------------------- - 0 6 Bra 0 - 3 1 a - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: extended -First char = 'a' -No need char - -/[\s]/D ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x09-\x0a\x0c-\x0d ] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[\S]/D ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x00-\x08\x0b\x0e-\x1f!-\xff] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/a(?i)b/D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 1 a - 6 01 Opt - 8 1 b - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -Case state changes -First char = 'a' -Need char = 'b' (caseless) - ab - 0: ab - aB - 0: aB - *** Failers -No match - AB -No match - -/(a(?i)b)/D ------------------------------------------------------------------- - 0 19 Bra 0 - 3 11 Bra 1 - 6 1 a - 9 01 Opt - 11 1 b - 14 11 Ket - 17 00 Opt - 19 19 Ket - 22 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -Case state changes -First char = 'a' -Need char = 'b' (caseless) - ab - 0: ab - 1: ab - aB - 0: aB - 1: aB - *** Failers -No match - AB -No match - -/ (?i)abc/xD ------------------------------------------------------------------- - 0 8 Bra 0 - 3 3 abc - 8 8 Ket - 11 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless extended -First char = 'a' (caseless) -Need char = 'c' (caseless) - -/#this is a comment - (?i)abc/xD ------------------------------------------------------------------- - 0 8 Bra 0 - 3 3 abc - 8 8 Ket - 11 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless extended -First char = 'a' (caseless) -Need char = 'c' (caseless) - -/123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D ------------------------------------------------------------------- - 0 307 Bra 0 - 3 250 1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 -255 50 12345678901234567890123456789012345678901234567890 -307 307 Ket -310 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '1' -Need char = '0' - -/\Q123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890/D ------------------------------------------------------------------- - 0 307 Bra 0 - 3 250 1234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890 -255 50 12345678901234567890123456789012345678901234567890 -307 307 Ket -310 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '1' -Need char = '0' - -/\Q\E/D ------------------------------------------------------------------- - 0 3 Bra 0 - 3 3 Ket - 6 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - \ - 0: - -/\Q\Ex/D ------------------------------------------------------------------- - 0 6 Bra 0 - 3 1 x - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'x' -No need char - -/ \Q\E/D ------------------------------------------------------------------- - 0 6 Bra 0 - 3 1 - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = ' ' -No need char - -/a\Q\E/D ------------------------------------------------------------------- - 0 6 Bra 0 - 3 1 a - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - abc - 0: a - bca - 0: a - bac - 0: a - -/a\Q\Eb/D ------------------------------------------------------------------- - 0 9 Bra 0 - 3 1 a - 6 1 b - 9 9 Ket - 12 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - abc - 0: ab - -/\Q\Eabc/D ------------------------------------------------------------------- - 0 8 Bra 0 - 3 3 abc - 8 8 Ket - 11 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/x*+\w/D ------------------------------------------------------------------- - 0 12 Bra 0 - 3 5 Once - 6 x* - 8 5 Ket - 11 \w - 12 12 Ket - 15 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - *** Failers - 0: F - xxxxx -No match - -/x?+/D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 5 Once - 6 x? - 8 5 Ket - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/x++/D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 5 Once - 6 x+ - 8 5 Ket - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'x' -No need char - -/x{1,3}+/D ------------------------------------------------------------------- - 0 16 Bra 0 - 3 10 Once - 6 1 x - 9 x{,2} - 13 10 Ket - 16 16 Ket - 19 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'x' -No need char - -/(x)*+/D ------------------------------------------------------------------- - 0 19 Bra 0 - 3 13 Once - 6 Brazero - 7 6 Bra 1 - 10 1 x - 13 6 KetRmax - 16 13 Ket - 19 19 Ket - 22 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -No first char -No need char - -/^(\w++|\s++)*$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - now is the time for all good men to come to the aid of the party - 0: now is the time for all good men to come to the aid of the party - 1: party - *** Failers -No match - this is not a line with only words and spaces! -No match - -/(\d++)(\w)/ -Capturing subpattern count = 2 -No options -No first char -No need char - 12345a - 0: 12345a - 1: 12345 - 2: a - *** Failers -No match - 12345+ -No match - -/a++b/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - aaab - 0: aaab - -/(a++b)/ -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - aaab - 0: aaab - 1: aaab - -/(a++)b/ -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - aaab - 0: aaab - 1: aaa - -/([^()]++|\([^()]*\))+/ -Capturing subpattern count = 1 -No options -No first char -No need char - ((abc(ade)ufh()()x - 0: abc(ade)ufh()()x - 1: x - -/\(([^()]++|\([^()]+\))+\)/ -Capturing subpattern count = 1 -No options -First char = '(' -Need char = ')' - (abc) - 0: (abc) - 1: abc - (abc(def)xyz) - 0: (abc(def)xyz) - 1: xyz - *** Failers -No match - ((()aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa -No match - -/(abc){1,3}+/D ------------------------------------------------------------------- - 0 50 Bra 0 - 3 44 Once - 6 8 Bra 1 - 9 3 abc - 14 8 Ket - 17 Brazero - 18 26 Bra 0 - 21 8 Bra 1 - 24 3 abc - 29 8 Ket - 32 Brazero - 33 8 Bra 1 - 36 3 abc - 41 8 Ket - 44 26 Ket - 47 44 Ket - 50 50 Ket - 53 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'c' - -/a+?+/ -Failed: nothing to repeat at offset 3 - -/a{2,3}?+b/ -Failed: nothing to repeat at offset 7 - -/(?U)a+?+/ -Failed: nothing to repeat at offset 7 - -/a{2,3}?+b/U -Failed: nothing to repeat at offset 7 - -/x(?U)a++b/D ------------------------------------------------------------------- - 0 17 Bra 0 - 3 1 x - 6 5 Once - 9 a+ - 11 5 Ket - 14 1 b - 17 17 Ket - 20 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 'x' -Need char = 'b' - xaaaab - 0: xaaaab - -/(?U)xa++b/D ------------------------------------------------------------------- - 0 17 Bra 0 - 3 1 x - 6 5 Once - 9 a+ - 11 5 Ket - 14 1 b - 17 17 Ket - 20 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: ungreedy -First char = 'x' -Need char = 'b' - xaaaab - 0: xaaaab - -/^((a+)(?U)([ab]+)(?-U)([bc]+)(\w*))/D ------------------------------------------------------------------- - 0 106 Bra 0 - 3 ^ - 4 99 Bra 1 - 7 5 Bra 2 - 10 a+ - 12 5 Ket - 15 37 Bra 3 - 18 [a-b]+? - 52 37 Ket - 55 37 Bra 4 - 58 [b-c]+ - 92 37 Ket - 95 5 Bra 5 - 98 \w* -100 5 Ket -103 99 Ket -106 106 Ket -109 End ------------------------------------------------------------------- -Capturing subpattern count = 5 -Options: anchored -No first char -No need char - -/^x(?U)a+b/D ------------------------------------------------------------------- - 0 12 Bra 0 - 3 ^ - 4 1 x - 7 a+? - 9 1 b - 12 12 Ket - 15 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored -No first char -Need char = 'b' - -/^x(?U)(a+)b/D ------------------------------------------------------------------- - 0 18 Bra 0 - 3 ^ - 4 1 x - 7 5 Bra 1 - 10 a+? - 12 5 Ket - 15 1 b - 18 18 Ket - 21 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: anchored -No first char -Need char = 'b' - -/[.x.]/ -Failed: POSIX collating elements are not supported at offset 0 - -/[=x=]/ -Failed: POSIX collating elements are not supported at offset 0 - -/[:x:]/ -Failed: POSIX named classes are supported only within a class at offset 0 - -/\l/ -Failed: PCRE does not support \L, \l, \N, \P, \p, \U, \u, or \X at offset 1 - -/\L/ -Failed: PCRE does not support \L, \l, \N, \P, \p, \U, \u, or \X at offset 1 - -/\N{name}/ -Failed: PCRE does not support \L, \l, \N, \P, \p, \U, \u, or \X at offset 1 - -/\pP/ -Failed: PCRE does not support \L, \l, \N, \P, \p, \U, \u, or \X at offset 1 - -/\PP/ -Failed: PCRE does not support \L, \l, \N, \P, \p, \U, \u, or \X at offset 1 - -/\p{prop}/ -Failed: PCRE does not support \L, \l, \N, \P, \p, \U, \u, or \X at offset 1 - -/\P{prop}/ -Failed: PCRE does not support \L, \l, \N, \P, \p, \U, \u, or \X at offset 1 - -/\u/ -Failed: PCRE does not support \L, \l, \N, \P, \p, \U, \u, or \X at offset 1 - -/\U/ -Failed: PCRE does not support \L, \l, \N, \P, \p, \U, \u, or \X at offset 1 - -/\X/ -Failed: PCRE does not support \L, \l, \N, \P, \p, \U, \u, or \X at offset 1 - -/[/ -Failed: missing terminating ] for character class at offset 1 - -/[a-/ -Failed: missing terminating ] for character class at offset 3 - -/[[:space:]/ -Failed: missing terminating ] for character class at offset 10 - -/[\s]/DM -Memory allocation (code space): 40 ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x09-\x0a\x0c-\x0d ] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[[:space:]]/DM -Memory allocation (code space): 40 ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x09-\x0d ] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[[:space:]abcde]/DM -Memory allocation (code space): 40 ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x09-\x0d a-e] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/< (?: (?(R) \d++ | [^<>]*+) | (?R)) * >/x -Capturing subpattern count = 0 -Options: extended -First char = '<' -Need char = '>' - <> - 0: <> - <abcd> - 0: <abcd> - <abc <123> hij> - 0: <abc <123> hij> - <abc <def> hij> - 0: <def> - <abc<>def> - 0: <abc<>def> - <abc<> - 0: <> - *** Failers -No match - <abc -No match - -|8J\$WE\<\.rX\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|DM -Memory allocation (code space): 421 ------------------------------------------------------------------- - 0 417 Bra 0 - 3 250 8J$WE<.rX+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E: -255 159 x9'c[%z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X -416 \b -417 417 Ket -420 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '8' -Need char = 'X' - -|\$\<\.X\+ix\[d1b\!H\#\?vV0vrK\:ZH1\=2M\>iV\;\?aPhFB\<\*vW\@QW\@sO9\}cfZA\-i\'w\%hKd6gt1UJP\,15_\#QY\$M\^Mss_U\/\]\&LK9\[5vQub\^w\[KDD\<EjmhUZ\?\.akp2dF\>qmj\;2\}YWFdYx\.Ap\]hjCPTP\(n28k\+3\;o\&WXqs\/gOXdr\$\:r\'do0\;b4c\(f_Gr\=\"\\4\)\[01T7ajQJvL\$W\~mL_sS\/4h\:x\*\[ZN\=KLs\&L5zX\/\/\>it\,o\:aU\(\;Z\>pW\&T7oP\'2K\^E\:x9\'c\[\%z\-\,64JQ5AeH_G\#KijUKghQw\^\\vea3a\?kka_G\$8\#\`\*kynsxzBLru\'\]k_\[7FrVx\}\^\=\$blx\>s\-N\%j\;D\*aZDnsw\:YKZ\%Q\.Kne9\#hP\?\+b3\(SOvL\,\^\;\&u5\@\?5C5Bhb\=m\-vEh_L15Jl\]U\)0RP6\{q\%L\^_z5E\'Dw6X\b|DM -Memory allocation (code space): 416 ------------------------------------------------------------------- - 0 412 Bra 0 - 3 250 $<.X+ix[d1b!H#?vV0vrK:ZH1=2M>iV;?aPhFB<*vW@QW@sO9}cfZA-i'w%hKd6gt1UJP,15_#QY$M^Mss_U/]&LK9[5vQub^w[KDD<EjmhUZ?.akp2dF>qmj;2}YWFdYx.Ap]hjCPTP(n28k+3;o&WXqs/gOXdr$:r'do0;b4c(f_Gr="\4)[01T7ajQJvL$W~mL_sS/4h:x*[ZN=KLs&L5zX//>it,o:aU(;Z>pW&T7oP'2K^E:x9'c[ -255 154 %z-,64JQ5AeH_G#KijUKghQw^\vea3a?kka_G$8#`*kynsxzBLru']k_[7FrVx}^=$blx>s-N%j;D*aZDnsw:YKZ%Q.Kne9#hP?+b3(SOvL,^;&u5@?5C5Bhb=m-vEh_L15Jl]U)0RP6{q%L^_z5E'Dw6X -411 \b -412 412 Ket -415 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = '$' -Need char = 'X' - -/(.*)\d+\1/I -Capturing subpattern count = 1 -Max back reference = 1 -No options -No first char -No need char - -/(.*)\d+/I -Capturing subpattern count = 1 -No options -First char at start or follows \n -No need char - -/(.*)\d+\1/Is -Capturing subpattern count = 1 -Max back reference = 1 -Options: dotall -No first char -No need char - -/(.*)\d+/Is -Capturing subpattern count = 1 -Options: anchored dotall -No first char -No need char - -/(.*(xyz))\d+\2/I -Capturing subpattern count = 2 -Max back reference = 2 -No options -First char at start or follows \n -Need char = 'z' - -/((.*))\d+\1/I -Capturing subpattern count = 2 -Max back reference = 1 -No options -No first char -No need char - abc123bc - 0: bc123bc - 1: bc - 2: bc - -/a[b]/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/(?=a).*/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/(?=abc).xyz/iI -Capturing subpattern count = 0 -Options: caseless -First char = 'a' (caseless) -Need char = 'z' (caseless) - -/(?=abc)(?i).xyz/I -Capturing subpattern count = 0 -No options -Case state changes -First char = 'a' -Need char = 'z' (caseless) - -/(?=a)(?=b)/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/(?=.)a/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/((?=abcda)a)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'a' - -/((?=abcda)ab)/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - -/()a/I -Capturing subpattern count = 1 -No options -No first char -Need char = 'a' - -/(?(1)ab|ac)/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/(?(1)abz|acz)/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'z' - -/(?(1)abz)/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/(?(1)abz)123/I -Capturing subpattern count = 0 -No options -No first char -Need char = '3' - -/(a)+/I -Capturing subpattern count = 1 -No options -First char = 'a' -No need char - -/(a){2,3}/I -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'a' - -/(a)*/I -Capturing subpattern count = 1 -No options -No first char -No need char - -/[a]/I -Capturing subpattern count = 0 -No options -First char = 'a' -No need char - -/[ab]/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/[ab]/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Starting character set: a b - -/[^a]/I -Capturing subpattern count = 0 -No options -No first char -No need char - -/\d456/I -Capturing subpattern count = 0 -No options -No first char -Need char = '6' - -/\d456/IS -Capturing subpattern count = 0 -No options -No first char -Need char = '6' -Starting character set: 0 1 2 3 4 5 6 7 8 9 - -/a^b/I -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/^a/mI -Capturing subpattern count = 0 -Options: multiline -First char at start or follows \n -Need char = 'a' - abcde - 0: a - xy\nabc - 0: a - *** Failers -No match - xyabc -No match - -/c|abc/I -Capturing subpattern count = 0 -No options -No first char -Need char = 'c' - -/(?i)[ab]/IS -Capturing subpattern count = 0 -Options: caseless -No first char -No need char -Starting character set: A B a b - -/[ab](?i)cd/IS -Capturing subpattern count = 0 -No options -Case state changes -No first char -Need char = 'd' (caseless) -Starting character set: a b - -/abc(?C)def/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'f' - abcdef ---->abcdef - 0 ^ ^ - 0: abcdef - 1234abcdef ---->1234abcdef - 0 ^ ^ - 0: abcdef - *** Failers -No match - abcxyz -No match - abcxyzf ---->abcxyzf - 0 ^ ^ -No match - -/abc(?C)de(?C1)f/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'f' - 123abcdef ---->123abcdef - 0 ^ ^ - 1 ^ ^ - 0: abcdef - -/(?C1)\dabc(?C2)def/ -Capturing subpattern count = 0 -No options -No first char -Need char = 'f' - 1234abcdef ---->1234abcdef - 1 ^ - 1 ^ - 1 ^ - 1 ^ - 2 ^ ^ - 0: 4abcdef - *** Failers -No match - abcdef ---->abcdef - 1 ^ - 1 ^ - 1 ^ - 1 ^ - 1 ^ - 1 ^ -No match - -/(?C255)ab/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'b' - -/(?C256)ab/ -Failed: number after (?C is > 255 at offset 6 - -/(?Cab)xx/ -Failed: closing ) for (?C expected at offset 3 - -/(?C12vr)x/ -Failed: closing ) for (?C expected at offset 5 - -/abc(?C)def/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'f' - *** Failers -No match - \x83\x0\x61bcdef ---->\x83\x00abcdef - 0 ^ ^ - 0: abcdef - -/(abc)(?C)de(?C1)f/ -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'f' - 123abcdef ---->123abcdef - 0 ^ ^ - 1 ^ ^ - 0: abcdef - 1: abc - 123abcdef\C+ -Callout 0: last capture = 1 - 0: <unset> - 1: abc ---->123abcdef - ^ ^ -Callout 1: last capture = 1 - 0: <unset> - 1: abc ---->123abcdef - ^ ^ - 0: abcdef - 1: abc - 123abcdef\C- - 0: abcdef - 1: abc - *** Failers -No match - 123abcdef\C!1 ---->123abcdef - 0 ^ ^ - 1 ^ ^ -No match - -/(?C0)(abc(?C1))*/ -Capturing subpattern count = 1 -No options -No first char -No need char - abcabcabc ---->abcabcabc - 0 ^ - 1 ^ ^ - 1 ^ ^ - 1 ^ ^ - 0: abcabcabc - 1: abc - abcabc\C!1!3 ---->abcabc - 0 ^ - 1 ^ ^ - 1 ^ ^ - 0: abcabc - 1: abc - *** Failers ---->*** Failers - 0 ^ - 0: - abcabcabc\C!1!3 ---->abcabcabc - 0 ^ - 1 ^ ^ - 1 ^ ^ - 1 ^ ^ - 0: abcabc - 1: abc - -/(\d{3}(?C))*/ -Capturing subpattern count = 1 -No options -No first char -No need char - 123\C+ -Callout 0: last capture = -1 - 0: <unset> ---->123 - ^ ^ - 0: 123 - 1: 123 - 123456\C+ -Callout 0: last capture = -1 - 0: <unset> ---->123456 - ^ ^ -Callout 0: last capture = 1 - 0: <unset> - 1: 123 ---->123456 - ^ ^ - 0: 123456 - 1: 456 - 123456789\C+ -Callout 0: last capture = -1 - 0: <unset> ---->123456789 - ^ ^ -Callout 0: last capture = 1 - 0: <unset> - 1: 123 ---->123456789 - ^ ^ -Callout 0: last capture = 1 - 0: <unset> - 1: 456 ---->123456789 - ^ ^ - 0: 123456789 - 1: 789 - -/((xyz)(?C)p|(?C1)xyzabc)/ -Capturing subpattern count = 2 -No options -First char = 'x' -No need char - xyzabc\C+ -Callout 0: last capture = 2 - 0: <unset> - 1: <unset> - 2: xyz ---->xyzabc - ^ ^ -Callout 1: last capture = -1 - 0: <unset> ---->xyzabc - ^ - 0: xyzabc - 1: xyzabc - -/(X)((xyz)(?C)p|(?C1)xyzabc)/ -Capturing subpattern count = 3 -No options -First char = 'X' -Need char = 'x' - Xxyzabc\C+ -Callout 0: last capture = 3 - 0: <unset> - 1: X - 2: <unset> - 3: xyz ---->Xxyzabc - ^ ^ -Callout 1: last capture = 1 - 0: <unset> - 1: X ---->Xxyzabc - ^^ - 0: Xxyzabc - 1: X - 2: xyzabc - -/(?=(abc))(?C)abcdef/ -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'f' - abcdef\C+ -Callout 0: last capture = 1 - 0: <unset> - 1: abc ---->abcdef - ^ - 0: abcdef - 1: abc - -/(?!(abc)(?C1)d)(?C2)abcxyz/ -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'z' - abcxyz\C+ -Callout 1: last capture = 1 - 0: <unset> - 1: abc ---->abcxyz - ^ ^ -Callout 2: last capture = -1 - 0: <unset> ---->abcxyz - ^ - 0: abcxyz - -/(?<=(abc)(?C))xyz/ -Capturing subpattern count = 1 -No options -First char = 'x' -Need char = 'z' - abcxyz\C+ -Callout 0: last capture = 1 - 0: <unset> - 1: abc ---->abcxyz - ^ - 0: xyz - 1: abc - -/(?C)abc/ -Capturing subpattern count = 0 -No options -First char = 'a' -Need char = 'c' - -/(?C)^abc/ -Capturing subpattern count = 0 -Options: anchored -No first char -No need char - -/(?C)a|b/S -Capturing subpattern count = 0 -No options -No first char -No need char -Starting character set: a b - -/(?R)/ -Failed: recursive call could loop indefinitely at offset 3 - -/(a|(?R))/ -Failed: recursive call could loop indefinitely at offset 6 - -/(ab|(bc|(de|(?R))))/ -Failed: recursive call could loop indefinitely at offset 15 - -/x(ab|(bc|(de|(?R))))/ -Capturing subpattern count = 3 -No options -First char = 'x' -No need char - xab - 0: xab - 1: ab - xbc - 0: xbc - 1: bc - 2: bc - xde - 0: xde - 1: de - 2: de - 3: de - xxab - 0: xxab - 1: xab - 2: xab - 3: xab - xxxab - 0: xxxab - 1: xxab - 2: xxab - 3: xxab - *** Failers -No match - xyab -No match - -/(ab|(bc|(de|(?1))))/ -Failed: recursive call could loop indefinitely at offset 15 - -/x(ab|(bc|(de|(?1)x)x)x)/ -Failed: recursive call could loop indefinitely at offset 16 - -/^([^()]|\((?1)*\))*$/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - abc - 0: abc - 1: c - a(b)c - 0: a(b)c - 1: c - a(b(c))d - 0: a(b(c))d - 1: d - *** Failers) -No match - a(b(c)d -No match - -/^>abc>([^()]|\((?1)*\))*<xyz<$/ -Capturing subpattern count = 1 -Options: anchored -No first char -Need char = '<' - >abc>123<xyz< - 0: >abc>123<xyz< - 1: 3 - >abc>1(2)3<xyz< - 0: >abc>1(2)3<xyz< - 1: 3 - >abc>(1(2)3)<xyz< - 0: >abc>(1(2)3)<xyz< - 1: (1(2)3) - -/(a(?1)b)/D ------------------------------------------------------------------- - 0 18 Bra 0 - 3 12 Bra 1 - 6 1 a - 9 3 Recurse - 12 1 b - 15 12 Ket - 18 18 Ket - 21 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - -/(a(?1)+b)/D ------------------------------------------------------------------- - 0 24 Bra 0 - 3 18 Bra 1 - 6 1 a - 9 6 Bra 0 - 12 3 Recurse - 15 6 KetRmax - 18 1 b - 21 18 Ket - 24 24 Ket - 27 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - -/^\W*(?:((.)\W*(?1)\W*\2|)|((.)\W*(?3)\W*\4|\W*.\W*))\W*$/i -Capturing subpattern count = 4 -Max back reference = 4 -Options: anchored caseless -No first char -No need char - 1221 - 0: 1221 - 1: 1221 - 2: 1 - Satan, oscillate my metallic sonatas! - 0: Satan, oscillate my metallic sonatas! - 1: <unset> - 2: <unset> - 3: Satan, oscillate my metallic sonatas - 4: S - A man, a plan, a canal: Panama! - 0: A man, a plan, a canal: Panama! - 1: <unset> - 2: <unset> - 3: A man, a plan, a canal: Panama - 4: A - Able was I ere I saw Elba. - 0: Able was I ere I saw Elba. - 1: <unset> - 2: <unset> - 3: Able was I ere I saw Elba - 4: A - *** Failers -No match - The quick brown fox -No match - -/^(\d+|\((?1)([+*-])(?1)\)|-(?1))$/ -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - 12 - 0: 12 - 1: 12 - (((2+2)*-3)-7) - 0: (((2+2)*-3)-7) - 1: (((2+2)*-3)-7) - 2: - - -12 - 0: -12 - 1: -12 - *** Failers -No match - ((2+2)*-3)-7) -No match - -/^(x(y|(?1){2})z)/ -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - xyz - 0: xyz - 1: xyz - 2: y - xxyzxyzz - 0: xxyzxyzz - 1: xxyzxyzz - 2: xyzxyz - *** Failers -No match - xxyzz -No match - xxyzxyzxyzz -No match - -/((< (?: (?(R) \d++ | [^<>]*+) | (?2)) * >))/x -Capturing subpattern count = 2 -Options: extended -First char = '<' -Need char = '>' - <> - 0: <> - 1: <> - 2: <> - <abcd> - 0: <abcd> - 1: <abcd> - 2: <abcd> - <abc <123> hij> - 0: <abc <123> hij> - 1: <abc <123> hij> - 2: <abc <123> hij> - <abc <def> hij> - 0: <def> - 1: <def> - 2: <def> - <abc<>def> - 0: <abc<>def> - 1: <abc<>def> - 2: <abc<>def> - <abc<> - 0: <> - 1: <> - 2: <> - *** Failers -No match - <abc -No match - -/(?1)/ -Failed: reference to non-existent subpattern at offset 3 - -/((?2)(abc)/ -Failed: reference to non-existent subpattern at offset 4 - -/^(abc)def(?1)/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - abcdefabc - 0: abcdefabc - 1: abc - -/^(a|b|c)=(?1)+/ -Capturing subpattern count = 1 -Options: anchored -No first char -No need char - a=a - 0: a=a - 1: a - a=b - 0: a=b - 1: a - a=bc - 0: a=bc - 1: a - -/^(a|b|c)=((?1))+/ -Capturing subpattern count = 2 -Options: anchored -No first char -No need char - a=a - 0: a=a - 1: a - 2: a - a=b - 0: a=b - 1: a - 2: b - a=bc - 0: a=bc - 1: a - 2: c - -/a(?P<name1>b|c)d(?P<longername2>e)/D ------------------------------------------------------------------- - 0 33 Bra 0 - 3 1 a - 6 6 Bra 1 - 9 1 b - 12 6 Alt - 15 1 c - 18 12 Ket - 21 1 d - 24 6 Bra 2 - 27 1 e - 30 6 Ket - 33 33 Ket - 36 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Named capturing subpatterns: - longername2 2 - name1 1 -No options -First char = 'a' -Need char = 'e' - abde - 0: abde - 1: b - 2: e - acde - 0: acde - 1: c - 2: e - -/(?:a(?P<c>c(?P<d>d)))(?P<a>a)/D ------------------------------------------------------------------- - 0 39 Bra 0 - 3 24 Bra 0 - 6 1 a - 9 15 Bra 1 - 12 1 c - 15 6 Bra 2 - 18 1 d - 21 6 Ket - 24 15 Ket - 27 24 Ket - 30 6 Bra 3 - 33 1 a - 36 6 Ket - 39 39 Ket - 42 End ------------------------------------------------------------------- -Capturing subpattern count = 3 -Named capturing subpatterns: - a 3 - c 1 - d 2 -No options -First char = 'a' -Need char = 'a' - -/(?P<a>a)...(?P=a)bbb(?P>a)d/D ------------------------------------------------------------------- - 0 29 Bra 0 - 3 6 Bra 1 - 6 1 a - 9 6 Ket - 12 Any - 13 Any - 14 Any - 15 \1 - 18 3 bbb - 23 3 Recurse - 26 1 d - 29 29 Ket - 32 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Max back reference = 1 -Named capturing subpatterns: - a 1 -No options -First char = 'a' -Need char = 'd' - -/^\W*(?:(?P<one>(?P<two>.)\W*(?P>one)\W*(?P=two)|)|(?P<three>(?P<four>.)\W*(?P>three)\W*(?P=four)|\W*.\W*))\W*$/i -Capturing subpattern count = 4 -Max back reference = 4 -Named capturing subpatterns: - four 4 - one 1 - three 3 - two 2 -Options: anchored caseless -No first char -No need char - 1221 - 0: 1221 - 1: 1221 - 2: 1 - Satan, oscillate my metallic sonatas! - 0: Satan, oscillate my metallic sonatas! - 1: <unset> - 2: <unset> - 3: Satan, oscillate my metallic sonatas - 4: S - A man, a plan, a canal: Panama! - 0: A man, a plan, a canal: Panama! - 1: <unset> - 2: <unset> - 3: A man, a plan, a canal: Panama - 4: A - Able was I ere I saw Elba. - 0: Able was I ere I saw Elba. - 1: <unset> - 2: <unset> - 3: Able was I ere I saw Elba - 4: A - *** Failers -No match - The quick brown fox -No match - -/((?(R)a|b))\1(?1)?/ -Capturing subpattern count = 1 -Max back reference = 1 -No options -No first char -No need char - bb - 0: bb - 1: b - bbaa - 0: bba - 1: b - -/(.*)a/sI -Capturing subpattern count = 1 -Options: anchored dotall -No first char -Need char = 'a' - -/(.*)a\1/sI -Capturing subpattern count = 1 -Max back reference = 1 -Options: dotall -No first char -Need char = 'a' - -/(.*)a(b)\2/sI -Capturing subpattern count = 2 -Max back reference = 2 -Options: anchored dotall -No first char -Need char = 'b' - -/((.*)a|(.*)b)z/sI -Capturing subpattern count = 3 -Options: anchored dotall -No first char -Need char = 'z' - -/((.*)a|(.*)b)z\1/sI -Capturing subpattern count = 3 -Max back reference = 1 -Options: dotall -No first char -Need char = 'z' - -/((.*)a|(.*)b)z\2/sI -Capturing subpattern count = 3 -Max back reference = 2 -Options: dotall -No first char -Need char = 'z' - -/((.*)a|(.*)b)z\3/sI -Capturing subpattern count = 3 -Max back reference = 3 -Options: dotall -No first char -Need char = 'z' - -/((.*)a|^(.*)b)z\3/sI -Capturing subpattern count = 3 -Max back reference = 3 -Options: anchored dotall -No first char -Need char = 'z' - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a/sI -Capturing subpattern count = 31 -Options: anchored dotall -No first char -No need char - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\31/sI -Capturing subpattern count = 31 -Max back reference = 31 -Options: dotall -No first char -No need char - -/(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)|(.*)a\32/sI -Capturing subpattern count = 32 -Max back reference = 32 -Options: dotall -No first char -No need char - -/(a)(bc)/ND ------------------------------------------------------------------- - 0 22 Bra 0 - 3 6 Bra 0 - 6 1 a - 9 6 Ket - 12 7 Bra 0 - 15 2 bc - 19 7 Ket - 22 22 Ket - 25 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: -First char = 'a' -Need char = 'c' - abc - 0: abc - -/(?P<one>a)(bc)/ND ------------------------------------------------------------------- - 0 22 Bra 0 - 3 6 Bra 1 - 6 1 a - 9 6 Ket - 12 7 Bra 0 - 15 2 bc - 19 7 Ket - 22 22 Ket - 25 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Named capturing subpatterns: - one 1 -Options: -First char = 'a' -Need char = 'c' - abc - 0: abc - 1: a - -/(a)(?P<named>bc)/ND ------------------------------------------------------------------- - 0 22 Bra 0 - 3 6 Bra 0 - 6 1 a - 9 6 Ket - 12 7 Bra 1 - 15 2 bc - 19 7 Ket - 22 22 Ket - 25 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Named capturing subpatterns: - named 1 -Options: -First char = 'a' -Need char = 'c' - -/(a+)*zz/ -Capturing subpattern count = 1 -No options -No first char -Need char = 'z' - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazzbbbbbb\M -Minimum match limit = 8 - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaazz - 1: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - aaaaaaaaaaaaaz\M -Minimum match limit = 32768 -No match - -/(aaa(?C1)bbb|ab)/ -Capturing subpattern count = 1 -No options -First char = 'a' -Need char = 'b' - aaabbb ---->aaabbb - 1 ^ ^ - 0: aaabbb - 1: aaabbb - aaabbb\C*0 ---->aaabbb - 1 ^ ^ - 0: aaabbb - 1: aaabbb - aaabbb\C*1 ---->aaabbb - 1 ^ ^ -Callout data = 1 - 0: ab - 1: ab - aaabbb\C*-1 ---->aaabbb - 1 ^ ^ -Callout data = -1 -No match - -/ab(?P<one>cd)ef(?P<two>gh)/ -Capturing subpattern count = 2 -Named capturing subpatterns: - one 1 - two 2 -No options -First char = 'a' -Need char = 'h' - abcdefgh - 0: abcdefgh - 1: cd - 2: gh - abcdefgh\C1\Gtwo - 0: abcdefgh - 1: cd - 2: gh - 1C cd (2) - 2G gh (2) - abcdefgh\Cone\Ctwo - 0: abcdefgh - 1: cd - 2: gh - 1C cd (2) - 2C gh (2) - abcdefgh\Cthree -no parentheses with name "three" - 0: abcdefgh - 1: cd - 2: gh - -/(?P<Tes>)(?P<Test>)/D ------------------------------------------------------------------- - 0 15 Bra 0 - 3 3 Bra 1 - 6 3 Ket - 9 3 Bra 2 - 12 3 Ket - 15 15 Ket - 18 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Named capturing subpatterns: - Tes 1 - Test 2 -No options -No first char -No need char - -/(?P<Test>)(?P<Tes>)/D ------------------------------------------------------------------- - 0 15 Bra 0 - 3 3 Bra 1 - 6 3 Ket - 9 3 Bra 2 - 12 3 Ket - 15 15 Ket - 18 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Named capturing subpatterns: - Tes 2 - Test 1 -No options -No first char -No need char - -/(?P<Z>zz)(?P<A>aa)/ -Capturing subpattern count = 2 -Named capturing subpatterns: - A 2 - Z 1 -No options -First char = 'z' -Need char = 'a' - zzaa\CZ - 0: zzaa - 1: zz - 2: aa - 1C zz (2) - zzaa\CA - 0: zzaa - 1: zz - 2: aa - 2C aa (2) - -/(?P<x>eks)(?P<x>eccs)/ -Failed: two named groups have the same name at offset 16 - -/(?P<abc>abc(?P<def>def)(?P<abc>xyz))/ -Failed: two named groups have the same name at offset 31 - -"\[((?P<elem>\d+)(,(?P>elem))*)\]" -Capturing subpattern count = 3 -Named capturing subpatterns: - elem 2 -No options -First char = '[' -Need char = ']' - [10,20,30,5,5,4,4,2,43,23,4234] - 0: [10,20,30,5,5,4,4,2,43,23,4234] - 1: 10,20,30,5,5,4,4,2,43,23,4234 - 2: 10 - 3: ,4234 - *** Failers -No match - [] -No match - -"\[((?P<elem>\d+)(,(?P>elem))*)?\]" -Capturing subpattern count = 3 -Named capturing subpatterns: - elem 2 -No options -First char = '[' -Need char = ']' - [10,20,30,5,5,4,4,2,43,23,4234] - 0: [10,20,30,5,5,4,4,2,43,23,4234] - 1: 10,20,30,5,5,4,4,2,43,23,4234 - 2: 10 - 3: ,4234 - [] - 0: [] - -/(a(b(?2)c))?/D ------------------------------------------------------------------- - 0 28 Bra 0 - 3 Brazero - 4 21 Bra 1 - 7 1 a - 10 12 Bra 2 - 13 1 b - 16 10 Recurse - 19 1 c - 22 12 Ket - 25 21 Ket - 28 28 Ket - 31 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -No options -No first char -No need char - -/(a(b(?2)c))*/D ------------------------------------------------------------------- - 0 28 Bra 0 - 3 Brazero - 4 21 Bra 1 - 7 1 a - 10 12 Bra 2 - 13 1 b - 16 10 Recurse - 19 1 c - 22 12 Ket - 25 21 KetRmax - 28 28 Ket - 31 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -No options -No first char -No need char - -/(a(b(?2)c)){0,2}/D ------------------------------------------------------------------- - 0 59 Bra 0 - 3 Brazero - 4 52 Bra 0 - 7 21 Bra 1 - 10 1 a - 13 12 Bra 2 - 16 1 b - 19 13 Recurse - 22 1 c - 25 12 Ket - 28 21 Ket - 31 Brazero - 32 21 Bra 1 - 35 1 a - 38 12 Bra 2 - 41 1 b - 44 13 Recurse - 47 1 c - 50 12 Ket - 53 21 Ket - 56 52 Ket - 59 59 Ket - 62 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -No options -No first char -No need char - -/[ab]{1}+/D ------------------------------------------------------------------- - 0 47 Bra 0 - 3 41 Once - 6 [a-b]{1,1} - 44 41 Ket - 47 47 Ket - 50 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/i -Capturing subpattern count = 3 -Options: caseless -No first char -Need char = 'g' (caseless) - Baby Bjorn Active Carrier - With free SHIPPING!! - 0: Baby Bjorn Active Carrier - With free SHIPPING!! - 1: Baby Bjorn Active Carrier - With free SHIPPING!! - -/((w\/|-|with)*(free|immediate)*.*?shipping\s*[!.-]*)/iS -Capturing subpattern count = 3 -Options: caseless -No first char -Need char = 'g' (caseless) -Study returned NULL - Baby Bjorn Active Carrier - With free SHIPPING!! - 0: Baby Bjorn Active Carrier - With free SHIPPING!! - 1: Baby Bjorn Active Carrier - With free SHIPPING!! - -/a*.*b/SD ------------------------------------------------------------------- - 0 10 Bra 0 - 3 a* - 5 Any* - 7 1 b - 10 10 Ket - 13 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -Need char = 'b' -Study returned NULL - -/(a|b)*.?c/SD ------------------------------------------------------------------- - 0 24 Bra 0 - 3 Brazero - 4 6 Bra 1 - 7 1 a - 10 6 Alt - 13 1 b - 16 12 KetRmax - 19 Any? - 21 1 c - 24 24 Ket - 27 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -No options -No first char -Need char = 'c' -Study returned NULL - -/ End of testinput2 / -Capturing subpattern count = 0 -No options -First char = ' ' -Need char = ' ' diff --git a/external-libs/pcre/testdata/testoutput3 b/external-libs/pcre/testdata/testoutput3 deleted file mode 100644 index 7d1d6fc6..00000000 --- a/external-libs/pcre/testdata/testoutput3 +++ /dev/null @@ -1,115 +0,0 @@ -PCRE version 4.5 01-December-2003 - -/^[\w]+/ - *** Failers -No match - cole -No match - -/^[\w]+/Lfr_FR - cole - 0: cole - -/^[\w]+/ - *** Failers -No match - cole -No match - -/^[\W]+/ - cole - 0: \xc9 - -/^[\W]+/Lfr_FR - *** Failers - 0: *** - cole -No match - -/[\b]/ - \b - 0: \x08 - *** Failers -No match - a -No match - -/[\b]/Lfr_FR - \b - 0: \x08 - *** Failers -No match - a -No match - -/^\w+/ - *** Failers -No match - cole -No match - -/^\w+/Lfr_FR - cole - 0: cole - -/(.+)\b(.+)/ - cole - 0: \xc9cole - 1: \xc9 - 2: cole - -/(.+)\b(.+)/Lfr_FR - *** Failers - 0: *** Failers - 1: *** - 2: Failers - cole -No match - -/cole/i - cole - 0: \xc9cole - *** Failers -No match - cole -No match - -/cole/iLfr_FR - cole - 0: cole - cole - 0: cole - -/\w/IS -Capturing subpattern count = 0 -No options -No first char -No need char -Starting character set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P - Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z - -/\w/ISLfr_FR -Capturing subpattern count = 0 -No options -No first char -No need char -Starting character set: 0 1 2 3 4 5 6 7 8 9 A B C D E F G H I J K L M N O P - Q R S T U V W X Y Z _ a b c d e f g h i j k l m n o p q r s t u v w x y z - - - -/^[\xc8-\xc9]/iLfr_FR - cole - 0: - cole - 0: - -/^[\xc8-\xc9]/Lfr_FR - cole - 0: - *** Failers -No match - cole -No match - -/ End of testinput3 / diff --git a/external-libs/pcre/testdata/testoutput4 b/external-libs/pcre/testdata/testoutput4 deleted file mode 100644 index a0f6c24a..00000000 --- a/external-libs/pcre/testdata/testoutput4 +++ /dev/null @@ -1,909 +0,0 @@ -PCRE version 4.5 01-December-2003 - -/-- Do not use the \x{} construct except with patterns that have the --/ -/-- /8 option set, because PCRE doesn't recognize them as UTF-8 unless --/ -No match -/-- that option is set. However, the latest Perls recognize them always. --/ -No match - -/a.b/8 - acb - 0: acb - a\x7fb - 0: a\x{7f}b - a\x{100}b - 0: a\x{100}b - *** Failers -No match - a\nb -No match - -/a(.{3})b/8 - a\x{4000}xyb - 0: a\x{4000}xyb - 1: \x{4000}xy - a\x{4000}\x7fyb - 0: a\x{4000}\x{7f}yb - 1: \x{4000}\x{7f}y - a\x{4000}\x{100}yb - 0: a\x{4000}\x{100}yb - 1: \x{4000}\x{100}y - *** Failers -No match - a\x{4000}b -No match - ac\ncb -No match - -/a(.*?)(.)/ - a\xc0\x88b - 0: a\xc0 - 1: - 2: \xc0 - -/a(.*?)(.)/8 - a\x{100}b - 0: a\x{100} - 1: - 2: \x{100} - -/a(.*)(.)/ - a\xc0\x88b - 0: a\xc0\x88b - 1: \xc0\x88 - 2: b - -/a(.*)(.)/8 - a\x{100}b - 0: a\x{100}b - 1: \x{100} - 2: b - -/a(.)(.)/ - a\xc0\x92bcd - 0: a\xc0\x92 - 1: \xc0 - 2: \x92 - -/a(.)(.)/8 - a\x{240}bcd - 0: a\x{240}b - 1: \x{240} - 2: b - -/a(.?)(.)/ - a\xc0\x92bcd - 0: a\xc0\x92 - 1: \xc0 - 2: \x92 - -/a(.?)(.)/8 - a\x{240}bcd - 0: a\x{240}b - 1: \x{240} - 2: b - -/a(.??)(.)/ - a\xc0\x92bcd - 0: a\xc0 - 1: - 2: \xc0 - -/a(.??)(.)/8 - a\x{240}bcd - 0: a\x{240} - 1: - 2: \x{240} - -/a(.{3})b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - 1: \x{1234}xy - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - 1: \x{1234}\x{4321}y - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - 1: \x{1234}\x{4321}\x{3412} - *** Failers -No match - a\x{1234}b -No match - ac\ncb -No match - -/a(.{3,})b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - 1: \x{1234}xy - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - 1: \x{1234}\x{4321}y - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - 1: \x{1234}\x{4321}\x{3412} - axxxxbcdefghijb - 0: axxxxbcdefghijb - 1: xxxxbcdefghij - a\x{1234}\x{4321}\x{3412}\x{3421}b - 0: a\x{1234}\x{4321}\x{3412}\x{3421}b - 1: \x{1234}\x{4321}\x{3412}\x{3421} - *** Failers -No match - a\x{1234}b -No match - -/a(.{3,}?)b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - 1: \x{1234}xy - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - 1: \x{1234}\x{4321}y - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - 1: \x{1234}\x{4321}\x{3412} - axxxxbcdefghijb - 0: axxxxb - 1: xxxx - a\x{1234}\x{4321}\x{3412}\x{3421}b - 0: a\x{1234}\x{4321}\x{3412}\x{3421}b - 1: \x{1234}\x{4321}\x{3412}\x{3421} - *** Failers -No match - a\x{1234}b -No match - -/a(.{3,5})b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - 1: \x{1234}xy - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - 1: \x{1234}\x{4321}y - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - 1: \x{1234}\x{4321}\x{3412} - axxxxbcdefghijb - 0: axxxxb - 1: xxxx - a\x{1234}\x{4321}\x{3412}\x{3421}b - 0: a\x{1234}\x{4321}\x{3412}\x{3421}b - 1: \x{1234}\x{4321}\x{3412}\x{3421} - axbxxbcdefghijb - 0: axbxxb - 1: xbxx - axxxxxbcdefghijb - 0: axxxxxb - 1: xxxxx - *** Failers -No match - a\x{1234}b -No match - axxxxxxbcdefghijb -No match - -/a(.{3,5}?)b/8 - a\x{1234}xyb - 0: a\x{1234}xyb - 1: \x{1234}xy - a\x{1234}\x{4321}yb - 0: a\x{1234}\x{4321}yb - 1: \x{1234}\x{4321}y - a\x{1234}\x{4321}\x{3412}b - 0: a\x{1234}\x{4321}\x{3412}b - 1: \x{1234}\x{4321}\x{3412} - axxxxbcdefghijb - 0: axxxxb - 1: xxxx - a\x{1234}\x{4321}\x{3412}\x{3421}b - 0: a\x{1234}\x{4321}\x{3412}\x{3421}b - 1: \x{1234}\x{4321}\x{3412}\x{3421} - axbxxbcdefghijb - 0: axbxxb - 1: xbxx - axxxxxbcdefghijb - 0: axxxxxb - 1: xxxxx - *** Failers -No match - a\x{1234}b -No match - axxxxxxbcdefghijb -No match - -/^[a\x{c0}]/8 - *** Failers -No match - \x{100} -No match - -/(?<=aXb)cd/8 - aXbcd - 0: cd - -/(?<=a\x{100}b)cd/8 - a\x{100}bcd - 0: cd - -/(?<=a\x{100000}b)cd/8 - a\x{100000}bcd - 0: cd - -/(?:\x{100}){3}b/8 - \x{100}\x{100}\x{100}b - 0: \x{100}\x{100}\x{100}b - *** Failers -No match - \x{100}\x{100}b -No match - -/\x{ab}/8 - \x{ab} - 0: \x{ab} - \xc2\xab - 0: \x{ab} - *** Failers -No match - \x00{ab} -No match - -/(?<=(.))X/8 - WXYZ - 0: X - 1: W - \x{256}XYZ - 0: X - 1: \x{256} - *** Failers -No match - XYZ -No match - -/X(\C{3})/8 - X\x{1234} - 0: X\x{1234} - 1: \x{1234} - -/X(\C{4})/8 - X\x{1234}YZ - 0: X\x{1234}Y - 1: \x{1234}Y - -/X\C*/8 - XYZabcdce - 0: XYZabcdce - -/X\C*?/8 - XYZabcde - 0: X - -/X\C{3,5}/8 - Xabcdefg - 0: Xabcde - X\x{1234} - 0: X\x{1234} - X\x{1234}YZ - 0: X\x{1234}YZ - X\x{1234}\x{512} - 0: X\x{1234}\x{512} - X\x{1234}\x{512}YZ - 0: X\x{1234}\x{512} - -/X\C{3,5}?/8 - Xabcdefg - 0: Xabc - X\x{1234} - 0: X\x{1234} - X\x{1234}YZ - 0: X\x{1234} - X\x{1234}\x{512} - 0: X\x{1234} - -/[^a]+/8g - bcd - 0: bcd - \x{100}aY\x{256}Z - 0: \x{100} - 0: Y\x{256}Z - -/^[^a]{2}/8 - \x{100}bc - 0: \x{100}b - -/^[^a]{2,}/8 - \x{100}bcAa - 0: \x{100}bcA - -/^[^a]{2,}?/8 - \x{100}bca - 0: \x{100}b - -/[^a]+/8ig - bcd - 0: bcd - \x{100}aY\x{256}Z - 0: \x{100} - 0: Y\x{256}Z - -/^[^a]{2}/8i - \x{100}bc - 0: \x{100}b - -/^[^a]{2,}/8i - \x{100}bcAa - 0: \x{100}bc - -/^[^a]{2,}?/8i - \x{100}bca - 0: \x{100}b - -/\x{100}{0,0}/8 - abcd - 0: - -/\x{100}?/8 - abcd - 0: - \x{100}\x{100} - 0: \x{100} - -/\x{100}{0,3}/8 - \x{100}\x{100} - 0: \x{100}\x{100} - \x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100} - -/\x{100}*/8 - abce - 0: - \x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100}\x{100} - -/\x{100}{1,1}/8 - abcd\x{100}\x{100}\x{100}\x{100} - 0: \x{100} - -/\x{100}{1,3}/8 - abcd\x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100} - -/\x{100}+/8 - abcd\x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100}\x{100} - -/\x{100}{3}/8 - abcd\x{100}\x{100}\x{100}XX - 0: \x{100}\x{100}\x{100} - -/\x{100}{3,5}/8 - abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX - 0: \x{100}\x{100}\x{100}\x{100}\x{100} - -/\x{100}{3,}/8 - abcd\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}XX - 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - -/(?<=a\x{100}{2}b)X/8+ - Xyyya\x{100}\x{100}bXzzz - 0: X - 0+ zzz - -/\D*/8 - aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - 0: aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa - -/\D*/8 - \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - 0: \x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100}\x{100} - -/\D/8 - 1X2 - 0: X - 1\x{100}2 - 0: \x{100} - -/>\S/8 - > >X Y - 0: >X - > >\x{100} Y - 0: >\x{100} - -/\W/8 - A.B - 0: . - A\x{100}B - 0: \x{100} - -/\d/8 - \x{100}3 - 0: 3 - -/\s/8 - \x{100} X - 0: - -/\w/8 - \x{100}X - 0: X - -/\D+/8 - 12abcd34 - 0: abcd - *** Failers - 0: *** Failers - 1234 -No match - -/\D{2,3}/8 - 12abcd34 - 0: abc - 12ab34 - 0: ab - *** Failers - 0: *** - 1234 -No match - 12a34 -No match - -/\D{2,3}?/8 - 12abcd34 - 0: ab - 12ab34 - 0: ab - *** Failers - 0: ** - 1234 -No match - 12a34 -No match - -/\d+/8 - 12abcd34 - 0: 12 - *** Failers -No match - -/\d{2,3}/8 - 12abcd34 - 0: 12 - 1234abcd - 0: 123 - *** Failers -No match - 1.4 -No match - -/\d{2,3}?/8 - 12abcd34 - 0: 12 - 1234abcd - 0: 12 - *** Failers -No match - 1.4 -No match - -/\S+/8 - 12abcd34 - 0: 12abcd34 - *** Failers - 0: *** - \ \ -No match - -/\S{2,3}/8 - 12abcd34 - 0: 12a - 1234abcd - 0: 123 - *** Failers - 0: *** - \ \ -No match - -/\S{2,3}?/8 - 12abcd34 - 0: 12 - 1234abcd - 0: 12 - *** Failers - 0: ** - \ \ -No match - -/>\s+</8+ - 12> <34 - 0: > < - 0+ 34 - *** Failers -No match - -/>\s{2,3}</8+ - ab> <cd - 0: > < - 0+ cd - ab> <ce - 0: > < - 0+ ce - *** Failers -No match - ab> <cd -No match - -/>\s{2,3}?</8+ - ab> <cd - 0: > < - 0+ cd - ab> <ce - 0: > < - 0+ ce - *** Failers -No match - ab> <cd -No match - -/\w+/8 - 12 34 - 0: 12 - *** Failers - 0: Failers - +++=*! -No match - -/\w{2,3}/8 - ab cd - 0: ab - abcd ce - 0: abc - *** Failers - 0: Fai - a.b.c -No match - -/\w{2,3}?/8 - ab cd - 0: ab - abcd ce - 0: ab - *** Failers - 0: Fa - a.b.c -No match - -/\W+/8 - 12====34 - 0: ==== - *** Failers - 0: *** - abcd -No match - -/\W{2,3}/8 - ab====cd - 0: === - ab==cd - 0: == - *** Failers - 0: *** - a.b.c -No match - -/\W{2,3}?/8 - ab====cd - 0: == - ab==cd - 0: == - *** Failers - 0: ** - a.b.c -No match - -/[\x{100}]/8 - \x{100} - 0: \x{100} - Z\x{100} - 0: \x{100} - \x{100}Z - 0: \x{100} - *** Failers -No match - -/[Z\x{100}]/8 - Z\x{100} - 0: Z - \x{100} - 0: \x{100} - \x{100}Z - 0: \x{100} - *** Failers -No match - -/[\x{100}\x{200}]/8 - ab\x{100}cd - 0: \x{100} - ab\x{200}cd - 0: \x{200} - *** Failers -No match - -/[\x{100}-\x{200}]/8 - ab\x{100}cd - 0: \x{100} - ab\x{200}cd - 0: \x{200} - ab\x{111}cd - 0: \x{111} - *** Failers -No match - -/[z-\x{200}]/8 - ab\x{100}cd - 0: \x{100} - ab\x{200}cd - 0: \x{200} - ab\x{111}cd - 0: \x{111} - abzcd - 0: z - ab|cd - 0: | - *** Failers -No match - -/[Q\x{100}\x{200}]/8 - ab\x{100}cd - 0: \x{100} - ab\x{200}cd - 0: \x{200} - Q? - 0: Q - *** Failers -No match - -/[Q\x{100}-\x{200}]/8 - ab\x{100}cd - 0: \x{100} - ab\x{200}cd - 0: \x{200} - ab\x{111}cd - 0: \x{111} - Q? - 0: Q - *** Failers -No match - -/[Qz-\x{200}]/8 - ab\x{100}cd - 0: \x{100} - ab\x{200}cd - 0: \x{200} - ab\x{111}cd - 0: \x{111} - abzcd - 0: z - ab|cd - 0: | - Q? - 0: Q - *** Failers -No match - -/[\x{100}\x{200}]{1,3}/8 - ab\x{100}cd - 0: \x{100} - ab\x{200}cd - 0: \x{200} - ab\x{200}\x{100}\x{200}\x{100}cd - 0: \x{200}\x{100}\x{200} - *** Failers -No match - -/[\x{100}\x{200}]{1,3}?/8 - ab\x{100}cd - 0: \x{100} - ab\x{200}cd - 0: \x{200} - ab\x{200}\x{100}\x{200}\x{100}cd - 0: \x{200} - *** Failers -No match - -/[Q\x{100}\x{200}]{1,3}/8 - ab\x{100}cd - 0: \x{100} - ab\x{200}cd - 0: \x{200} - ab\x{200}\x{100}\x{200}\x{100}cd - 0: \x{200}\x{100}\x{200} - *** Failers -No match - -/[Q\x{100}\x{200}]{1,3}?/8 - ab\x{100}cd - 0: \x{100} - ab\x{200}cd - 0: \x{200} - ab\x{200}\x{100}\x{200}\x{100}cd - 0: \x{200} - *** Failers -No match - -/(?<=[\x{100}\x{200}])X/8 - abc\x{200}X - 0: X - abc\x{100}X - 0: X - *** Failers -No match - X -No match - -/(?<=[Q\x{100}\x{200}])X/8 - abc\x{200}X - 0: X - abc\x{100}X - 0: X - abQX - 0: X - *** Failers -No match - X -No match - -/(?<=[\x{100}\x{200}]{3})X/8 - abc\x{100}\x{200}\x{100}X - 0: X - *** Failers -No match - abc\x{200}X -No match - X -No match - -/[^\x{100}\x{200}]X/8 - AX - 0: AX - \x{150}X - 0: \x{150}X - \x{500}X - 0: \x{500}X - *** Failers -No match - \x{100}X -No match - \x{200}X -No match - -/[^Q\x{100}\x{200}]X/8 - AX - 0: AX - \x{150}X - 0: \x{150}X - \x{500}X - 0: \x{500}X - *** Failers -No match - \x{100}X -No match - \x{200}X -No match - QX -No match - -/[^\x{100}-\x{200}]X/8 - AX - 0: AX - \x{500}X - 0: \x{500}X - *** Failers -No match - \x{100}X -No match - \x{150}X -No match - \x{200}X -No match - -/a\Cb/ - aXb - 0: aXb - a\nb - 0: a\x0ab - -/a\Cb/8 - aXb - 0: aXb - a\nb - 0: a\x{0a}b - *** Failers -No match - a\x{100}b -No match - -/[z-\x{100}]/8i - z - 0: z - Z - 0: Z - \x{100} - 0: \x{100} - *** Failers -No match - \x{101} -No match - y -No match - -/[\xFF]/ - >\xff< - 0: \xff - -/[\xff]/8 - >\x{ff}< - 0: \x{ff} - -/[^\xFF]/ - XYZ - 0: X - -/[^\xff]/8 - XYZ - 0: X - \x{123} - 0: \x{123} - -/^[ac]*b/8 - xb -No match - -/^[ac\x{100}]*b/8 - xb -No match - -/^[^x]*b/8i - xb -No match - -/^[^x]*b/8 - xb -No match - -/^\d*b/8 - xb -No match - -/(|a)/g8 - catac - 0: - 1: - 0: - 1: - 0: a - 1: a - 0: - 1: - 0: - 1: - 0: a - 1: a - 0: - 1: - 0: - 1: - a\x{256}a - 0: - 1: - 0: a - 1: a - 0: - 1: - 0: - 1: - 0: a - 1: a - 0: - 1: - -/ End of testinput4 / diff --git a/external-libs/pcre/testdata/testoutput5 b/external-libs/pcre/testdata/testoutput5 deleted file mode 100644 index 1476367e..00000000 --- a/external-libs/pcre/testdata/testoutput5 +++ /dev/null @@ -1,1063 +0,0 @@ -PCRE version 4.5 01-December-2003 - -/\x{100}/8DM -Memory allocation (code space): 11 ------------------------------------------------------------------- - 0 7 Bra 0 - 3 2 \x{100} - 7 7 Ket - 10 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 196 -Need char = 128 - -/\x{1000}/8DM -Memory allocation (code space): 12 ------------------------------------------------------------------- - 0 8 Bra 0 - 3 3 \x{1000} - 8 8 Ket - 11 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 225 -Need char = 128 - -/\x{10000}/8DM -Memory allocation (code space): 13 ------------------------------------------------------------------- - 0 9 Bra 0 - 3 4 \x{10000} - 9 9 Ket - 12 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 240 -Need char = 128 - -/\x{100000}/8DM -Memory allocation (code space): 13 ------------------------------------------------------------------- - 0 9 Bra 0 - 3 4 \x{100000} - 9 9 Ket - 12 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 244 -Need char = 128 - -/\x{1000000}/8DM -Memory allocation (code space): 14 ------------------------------------------------------------------- - 0 10 Bra 0 - 3 5 \x{1000000} - 10 10 Ket - 13 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 249 -Need char = 128 - -/\x{4000000}/8DM -Memory allocation (code space): 15 ------------------------------------------------------------------- - 0 11 Bra 0 - 3 6 \x{4000000} - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 252 -Need char = 128 - -/\x{7fffFFFF}/8DM -Memory allocation (code space): 15 ------------------------------------------------------------------- - 0 11 Bra 0 - 3 6 \x{7fffffff} - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 253 -Need char = 191 - -/[\x{ff}]/8DM -Memory allocation (code space): 40 ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\xff] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/[\x{100}]/8DM -Memory allocation (code space): 47 ------------------------------------------------------------------- - 0 11 Bra 0 - 3 [\x{100}] - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/\x{ffffffff}/8 -Failed: character value in \x{...} sequence is too large at offset 11 - -/\x{100000000}/8 -Failed: character value in \x{...} sequence is too large at offset 12 - -/^\x{100}a\x{1234}/8 - \x{100}a\x{1234}bcd - 0: \x{100}a\x{1234} - -/\x80/8D ------------------------------------------------------------------- - 0 7 Bra 0 - 3 2 \x{80} - 7 7 Ket - 10 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 194 -Need char = 128 - -/\xff/8D ------------------------------------------------------------------- - 0 7 Bra 0 - 3 2 \x{ff} - 7 7 Ket - 10 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 195 -Need char = 191 - -/\x{0041}\x{2262}\x{0391}\x{002e}/D8 ------------------------------------------------------------------- - 0 12 Bra 0 - 3 7 A\x{2262}\x{391}. - 12 12 Ket - 15 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 'A' -Need char = '.' - \x{0041}\x{2262}\x{0391}\x{002e} - 0: A\x{2262}\x{391}. - -/\x{D55c}\x{ad6d}\x{C5B4}/D8 ------------------------------------------------------------------- - 0 14 Bra 0 - 3 9 \x{d55c}\x{ad6d}\x{c5b4} - 14 14 Ket - 17 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 237 -Need char = 180 - \x{D55c}\x{ad6d}\x{C5B4} - 0: \x{d55c}\x{ad6d}\x{c5b4} - -/\x{65e5}\x{672c}\x{8a9e}/D8 ------------------------------------------------------------------- - 0 14 Bra 0 - 3 9 \x{65e5}\x{672c}\x{8a9e} - 14 14 Ket - 17 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 230 -Need char = 158 - \x{65e5}\x{672c}\x{8a9e} - 0: \x{65e5}\x{672c}\x{8a9e} - -/\x{80}/D8 ------------------------------------------------------------------- - 0 7 Bra 0 - 3 2 \x{80} - 7 7 Ket - 10 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 194 -Need char = 128 - -/\x{084}/D8 ------------------------------------------------------------------- - 0 7 Bra 0 - 3 2 \x{84} - 7 7 Ket - 10 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 194 -Need char = 132 - -/\x{104}/D8 ------------------------------------------------------------------- - 0 7 Bra 0 - 3 2 \x{104} - 7 7 Ket - 10 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 196 -Need char = 132 - -/\x{861}/D8 ------------------------------------------------------------------- - 0 8 Bra 0 - 3 3 \x{861} - 8 8 Ket - 11 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 224 -Need char = 161 - -/\x{212ab}/D8 ------------------------------------------------------------------- - 0 9 Bra 0 - 3 4 \x{212ab} - 9 9 Ket - 12 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 240 -Need char = 171 - -/.{3,5}X/D8 ------------------------------------------------------------------- - 0 14 Bra 0 - 3 Any{3} - 7 Any{0,2} - 11 1 X - 14 14 Ket - 17 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -Need char = 'X' - \x{212ab}\x{212ab}\x{212ab}\x{861}X - 0: \x{212ab}\x{212ab}\x{212ab}\x{861}X - - -/.{3,5}?/D8 ------------------------------------------------------------------- - 0 11 Bra 0 - 3 Any{3} - 7 Any{0,2}? - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - \x{212ab}\x{212ab}\x{212ab}\x{861} - 0: \x{212ab}\x{212ab}\x{212ab} - -/-- These tests are here rather than in testinput4 because Perl 5.6 has --/ -/-- some problems with UTF-8 support, in the area of \x{..} where the --/ -No match -/-- value is < 255. It grumbles about invalid UTF-8 strings. --/ -No match - -/^[a\x{c0}]b/8 - \x{c0}b - 0: \x{c0}b - -/^([a\x{c0}]*?)aa/8 - a\x{c0}aaaa/ - 0: a\x{c0}aa - 1: a\x{c0} - -/^([a\x{c0}]*?)aa/8 - a\x{c0}aaaa/ - 0: a\x{c0}aa - 1: a\x{c0} - a\x{c0}a\x{c0}aaa/ - 0: a\x{c0}a\x{c0}aa - 1: a\x{c0}a\x{c0} - -/^([a\x{c0}]*)aa/8 - a\x{c0}aaaa/ - 0: a\x{c0}aaaa - 1: a\x{c0}aa - a\x{c0}a\x{c0}aaa/ - 0: a\x{c0}a\x{c0}aaa - 1: a\x{c0}a\x{c0}a - -/^([a\x{c0}]*)a\x{c0}/8 - a\x{c0}aaaa/ - 0: a\x{c0} - 1: - a\x{c0}a\x{c0}aaa/ - 0: a\x{c0}a\x{c0} - 1: a\x{c0} - -/-- --/ - -/(?<=\C)X/8 -Failed: \C not allowed in lookbehind assertion at offset 6 - -/-- This one is here not because it's different to Perl, but because the --/ -/-- way the captured single-byte is displayed. (In Perl it becomes a --/ -No match -/-- character, and you can't tell the difference.) --/ -No match - -/X(\C)(.*)/8 - X\x{1234} - 0: X\x{1234} - 1: \xe1 - 2: \x88\xb4 - X\nabc - 0: X\x{0a}abc - 1: \x{0a} - 2: abc - -/^[ab]/8D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [a-b] - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored utf8 -No first char -No need char - bar - 0: b - *** Failers -No match - c -No match - \x{ff} -No match - \x{100} -No match - -/^[^ab]/8D ------------------------------------------------------------------- - 0 37 Bra 0 - 3 ^ - 4 [\x00-`c-\xff] (neg) - 37 37 Ket - 40 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: anchored utf8 -No first char -No need char - c - 0: c - \x{ff} - 0: \x{ff} - \x{100} - 0: \x{100} - *** Failers - 0: * - aaa -No match - -/[^ab\xC0-\xF0]/8SD ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x00-`c-\xbf\xf1-\xff] (neg) - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char -Starting character set: \x00 \x01 \x02 \x03 \x04 \x05 \x06 \x07 \x08 \x09 \x0a - \x0b \x0c \x0d \x0e \x0f \x10 \x11 \x12 \x13 \x14 \x15 \x16 \x17 \x18 \x19 - \x1a \x1b \x1c \x1d \x1e \x1f \x20 ! " # $ % & ' ( ) * + , - . / 0 1 2 3 4 - 5 6 7 8 9 : ; < = > ? @ A B C D E F G H I J K L M N O P Q R S T U V W X Y - Z [ \ ] ^ _ ` c d e f g h i j k l m n o p q r s t u v w x y z { | } ~ \x7f - \xc2 \xc3 \xc4 \xc5 \xc6 \xc7 \xc8 \xc9 \xca \xcb \xcc \xcd \xce \xcf \xd0 - \xd1 \xd2 \xd3 \xd4 \xd5 \xd6 \xd7 \xd8 \xd9 \xda \xdb \xdc \xdd \xde \xdf - \xe0 \xe1 \xe2 \xe3 \xe4 \xe5 \xe6 \xe7 \xe8 \xe9 \xea \xeb \xec \xed \xee - \xef \xf0 \xf1 \xf2 \xf3 \xf4 \xf5 \xf6 \xf7 \xf8 \xf9 \xfa \xfb \xfc \xfd - \xfe \xff - \x{f1} - 0: \x{f1} - \x{bf} - 0: \x{bf} - \x{100} - 0: \x{100} - \x{1000} - 0: \x{1000} - *** Failers - 0: * - \x{c0} -No match - \x{f0} -No match - -/Ā{3,4}/8SD ------------------------------------------------------------------- - 0 13 Bra 0 - 3 \x{100}{3} - 8 \x{100}{,1} - 13 13 Ket - 16 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 196 -Need char = 128 -Study returned NULL - \x{100}\x{100}\x{100}\x{100\x{100} - 0: \x{100}\x{100}\x{100} - -/(\x{100}+|x)/8SD ------------------------------------------------------------------- - 0 18 Bra 0 - 3 6 Bra 1 - 6 \x{100}+ - 9 6 Alt - 12 1 x - 15 12 Ket - 18 18 Ket - 21 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: utf8 -No first char -No need char -Starting character set: x \xc4 - -/(\x{100}*a|x)/8SD ------------------------------------------------------------------- - 0 21 Bra 0 - 3 9 Bra 1 - 6 \x{100}* - 9 1 a - 12 6 Alt - 15 1 x - 18 15 Ket - 21 21 Ket - 24 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: utf8 -No first char -No need char -Starting character set: a x \xc4 - -/(\x{100}{0,2}a|x)/8SD ------------------------------------------------------------------- - 0 23 Bra 0 - 3 11 Bra 1 - 6 \x{100}{,2} - 11 1 a - 14 6 Alt - 17 1 x - 20 17 Ket - 23 23 Ket - 26 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: utf8 -No first char -No need char -Starting character set: a x \xc4 - -/(\x{100}{1,2}a|x)/8SD ------------------------------------------------------------------- - 0 27 Bra 0 - 3 15 Bra 1 - 6 2 \x{100} - 10 \x{100}{,1} - 15 1 a - 18 6 Alt - 21 1 x - 24 21 Ket - 27 27 Ket - 30 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: utf8 -No first char -No need char -Starting character set: x \xc4 - -/\x{100}*(\d+|"(?1)")/8 - 1234 - 0: 1234 - 1: 1234 - "1234" - 0: "1234" - 1: "1234" - \x{100}1234 - 0: \x{100}1234 - 1: 1234 - "\x{100}1234" - 0: \x{100}1234 - 1: 1234 - \x{100}\x{100}12ab - 0: \x{100}\x{100}12 - 1: 12 - \x{100}\x{100}"12" - 0: \x{100}\x{100}"12" - 1: "12" - *** Failers -No match - \x{100}\x{100}abcd -No match - -/\x{100}/8D ------------------------------------------------------------------- - 0 7 Bra 0 - 3 2 \x{100} - 7 7 Ket - 10 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 196 -Need char = 128 - -/\x{100}*/8D ------------------------------------------------------------------- - 0 6 Bra 0 - 3 \x{100}* - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/a\x{100}*/8D ------------------------------------------------------------------- - 0 9 Bra 0 - 3 1 a - 6 \x{100}* - 9 9 Ket - 12 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 'a' -No need char - -/ab\x{100}*/8D ------------------------------------------------------------------- - 0 10 Bra 0 - 3 2 ab - 7 \x{100}* - 10 10 Ket - 13 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 'a' -Need char = 'b' - -/a\x{100}\x{101}*/8D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 3 a\x{100} - 8 \x{101}* - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 'a' -Need char = 128 - -/a\x{100}\x{101}+/8D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 3 a\x{100} - 8 \x{101}+ - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -First char = 'a' -Need char = 129 - -/\x{100}*A/8D ------------------------------------------------------------------- - 0 9 Bra 0 - 3 \x{100}* - 6 1 A - 9 9 Ket - 12 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -Need char = 'A' - A - 0: A - -/\x{100}*\d(?R)/8D ------------------------------------------------------------------- - 0 10 Bra 0 - 3 \x{100}* - 6 \d - 7 0 Recurse - 10 10 Ket - 13 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/[^\x{c4}]/D ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x01-35-bd-z|~-\xff] (neg) - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[^\x{c4}]/8D ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x00-\xc3\xc5-\xff] (neg) - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/[\x{100}]/8DM -Memory allocation (code space): 47 ------------------------------------------------------------------- - 0 11 Bra 0 - 3 [\x{100}] - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - \x{100} - 0: \x{100} - Z\x{100} - 0: \x{100} - \x{100}Z - 0: \x{100} - *** Failers -No match - -/[Z\x{100}]/8DM -Memory allocation (code space): 47 ------------------------------------------------------------------- - 0 43 Bra 0 - 3 [Z\x{100}] - 43 43 Ket - 46 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - Z\x{100} - 0: Z - \x{100} - 0: \x{100} - \x{100}Z - 0: \x{100} - *** Failers -No match - -/[\x{200}-\x{100}]/8 -Failed: range out of order in character class at offset 15 - -/[Ā-Ą]/8 - \x{100} - 0: \x{100} - \x{104} - 0: \x{104} - *** Failers -No match - \x{105} -No match - \x{ff} -No match - -/[z-\x{100}]/8D ------------------------------------------------------------------- - 0 12 Bra 0 - 3 [z-\x{100}] - 12 12 Ket - 15 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/[z-\x{100}]/8Di ------------------------------------------------------------------- - 0 45 Bra 0 - 3 [Zz-\xff\x{100}-\x{100}] - 45 45 Ket - 48 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: caseless utf8 -No first char -No need char - -/[z\Qa-d]Ā\E]/8D ------------------------------------------------------------------- - 0 43 Bra 0 - 3 [\-\]adz\x{100}] - 43 43 Ket - 46 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - \x{100} - 0: \x{100} - Ā - 0: \x{100} - -/[\xFF]/D ------------------------------------------------------------------- - 0 6 Bra 0 - 3 1 \xff - 6 6 Ket - 9 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -First char = 255 -No need char - >\xff< - 0: \xff - -/[\xff]/D8 ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\xff] - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - >\x{ff}< - 0: \x{ff} - -/[^\xFF]/D ------------------------------------------------------------------- - 0 5 Bra 0 - 3 [^\xff] - 5 5 Ket - 8 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -No options -No first char -No need char - -/[^\xff]/8D ------------------------------------------------------------------- - 0 36 Bra 0 - 3 [\x00-\xfe] (neg) - 36 36 Ket - 39 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 -No first char -No need char - -/[Ä-Ü]/8 - Ö # Matches without Study - 0: \x{d6} - \x{d6} - 0: \x{d6} - -/[Ä-Ü]/8S - Ö <-- Same with Study - 0: \x{d6} - \x{d6} - 0: \x{d6} - -/[\x{c4}-\x{dc}]/8 - Ö # Matches without Study - 0: \x{d6} - \x{d6} - 0: \x{d6} - -/[\x{c4}-\x{dc}]/8S - Ö <-- Same with Study - 0: \x{d6} - \x{d6} - 0: \x{d6} - -/[]/8 -Failed: invalid UTF-8 string at offset 2 - -//8 -Failed: invalid UTF-8 string at offset 0 - -/xxx/8 -Failed: invalid UTF-8 string at offset 1 - -/xxx/8?D ------------------------------------------------------------------- - 0 11 Bra 0 - 3 6 \x{c3}\x{f8}xx - 11 11 Ket - 14 End ------------------------------------------------------------------- -Capturing subpattern count = 0 -Options: utf8 no_utf8_check -First char = 195 -Need char = 'x' - -/abc/8 - ] -Error -10 - -Error -10 - -Error -10 - \? -No match - -/anything/8 - \xc0\x80 -Error -10 - \xc1\x8f -Error -10 - \xe0\x9f\x80 -Error -10 - \xf0\x8f\x80\x80 -Error -10 - \xf8\x87\x80\x80\x80 -Error -10 - \xfc\x83\x80\x80\x80\x80 -Error -10 - \xfe\x80\x80\x80\x80\x80 -Error -10 - \xff\x80\x80\x80\x80\x80 -Error -10 - \xc3\x8f -No match - \xe0\xaf\x80 -No match - \xe1\x80\x80 -No match - \xf0\x9f\x80\x80 -No match - \xf1\x8f\x80\x80 -No match - \xf8\x88\x80\x80\x80 -No match - \xf9\x87\x80\x80\x80 -No match - \xfc\x84\x80\x80\x80\x80 -No match - \xfd\x83\x80\x80\x80\x80 -No match - -/\x{100}abc(xyz(?1))/8D ------------------------------------------------------------------- - 0 24 Bra 0 - 3 5 \x{100}abc - 10 11 Bra 1 - 13 3 xyz - 18 10 Recurse - 21 11 Ket - 24 24 Ket - 27 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: utf8 -First char = 196 -Need char = 'z' - -/[^\x{100}]abc(xyz(?1))/8D ------------------------------------------------------------------- - 0 30 Bra 0 - 3 [^\x{100}] - 11 3 abc - 16 11 Bra 1 - 19 3 xyz - 24 16 Recurse - 27 11 Ket - 30 30 Ket - 33 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: utf8 -No first char -Need char = 'z' - -/[ab\x{100}]abc(xyz(?1))/8D ------------------------------------------------------------------- - 0 62 Bra 0 - 3 [a-b\x{100}] - 43 3 abc - 48 11 Bra 1 - 51 3 xyz - 56 48 Recurse - 59 11 Ket - 62 62 Ket - 65 End ------------------------------------------------------------------- -Capturing subpattern count = 1 -Options: utf8 -No first char -Need char = 'z' - -/(\x{100}(b(?2)c))?/D8 ------------------------------------------------------------------- - 0 29 Bra 0 - 3 Brazero - 4 22 Bra 1 - 7 2 \x{100} - 11 12 Bra 2 - 14 1 b - 17 11 Recurse - 20 1 c - 23 12 Ket - 26 22 Ket - 29 29 Ket - 32 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Options: utf8 -No first char -No need char - -/(\x{100}(b(?2)c)){0,2}/D8 ------------------------------------------------------------------- - 0 61 Bra 0 - 3 Brazero - 4 54 Bra 0 - 7 22 Bra 1 - 10 2 \x{100} - 14 12 Bra 2 - 17 1 b - 20 14 Recurse - 23 1 c - 26 12 Ket - 29 22 Ket - 32 Brazero - 33 22 Bra 1 - 36 2 \x{100} - 40 12 Bra 2 - 43 1 b - 46 14 Recurse - 49 1 c - 52 12 Ket - 55 22 Ket - 58 54 Ket - 61 61 Ket - 64 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Options: utf8 -No first char -No need char - -/(\x{100}(b(?1)c))?/D8 ------------------------------------------------------------------- - 0 29 Bra 0 - 3 Brazero - 4 22 Bra 1 - 7 2 \x{100} - 11 12 Bra 2 - 14 1 b - 17 4 Recurse - 20 1 c - 23 12 Ket - 26 22 Ket - 29 29 Ket - 32 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Options: utf8 -No first char -No need char - -/(\x{100}(b(?1)c)){0,2}/D8 ------------------------------------------------------------------- - 0 61 Bra 0 - 3 Brazero - 4 54 Bra 0 - 7 22 Bra 1 - 10 2 \x{100} - 14 12 Bra 2 - 17 1 b - 20 7 Recurse - 23 1 c - 26 12 Ket - 29 22 Ket - 32 Brazero - 33 22 Bra 1 - 36 2 \x{100} - 40 12 Bra 2 - 43 1 b - 46 7 Recurse - 49 1 c - 52 12 Ket - 55 22 Ket - 58 54 Ket - 61 61 Ket - 64 End ------------------------------------------------------------------- -Capturing subpattern count = 2 -Options: utf8 -No first char -No need char - -/ End of testinput5 / |