From 582b500cd996c96054615870fd13d6ab0ea77428 Mon Sep 17 00:00:00 2001 From: Jay Berkenbilt Date: Sat, 10 Oct 2009 15:10:05 +0000 Subject: start integrating windows port git-svn-id: svn+q:///qpdf/trunk@757 71b93d88-0707-0410-a8cf-f5a4172ac649 --- external-libs/pcre/doc/html/index.html | 102 ++ external-libs/pcre/doc/html/pcre.html | 190 +++ external-libs/pcre/doc/html/pcre_compile.html | 71 + external-libs/pcre/doc/html/pcre_config.html | 56 + .../pcre/doc/html/pcre_copy_named_substring.html | 46 + .../pcre/doc/html/pcre_copy_substring.html | 44 + external-libs/pcre/doc/html/pcre_exec.html | 58 + .../pcre/doc/html/pcre_free_substring.html | 29 + .../pcre/doc/html/pcre_free_substring_list.html | 29 + external-libs/pcre/doc/html/pcre_fullinfo.html | 68 + .../pcre/doc/html/pcre_get_named_substring.html | 46 + .../pcre/doc/html/pcre_get_stringnumber.html | 39 + .../pcre/doc/html/pcre_get_substring.html | 44 + .../pcre/doc/html/pcre_get_substring_list.html | 41 + external-libs/pcre/doc/html/pcre_info.html | 28 + external-libs/pcre/doc/html/pcre_maketables.html | 31 + external-libs/pcre/doc/html/pcre_study.html | 45 + external-libs/pcre/doc/html/pcre_version.html | 28 + external-libs/pcre/doc/html/pcreapi.html | 1346 ++++++++++++++++ external-libs/pcre/doc/html/pcrebuild.html | 189 +++ external-libs/pcre/doc/html/pcrecallout.html | 117 ++ external-libs/pcre/doc/html/pcrecompat.html | 136 ++ external-libs/pcre/doc/html/pcregrep.html | 153 ++ external-libs/pcre/doc/html/pcrepattern.html | 1607 ++++++++++++++++++++ external-libs/pcre/doc/html/pcreperform.html | 93 ++ external-libs/pcre/doc/html/pcreposix.html | 237 +++ external-libs/pcre/doc/html/pcresample.html | 79 + external-libs/pcre/doc/html/pcretest.html | 443 ++++++ 28 files changed, 5395 insertions(+) create mode 100644 external-libs/pcre/doc/html/index.html create mode 100644 external-libs/pcre/doc/html/pcre.html create mode 100644 external-libs/pcre/doc/html/pcre_compile.html create mode 100644 external-libs/pcre/doc/html/pcre_config.html create mode 100644 external-libs/pcre/doc/html/pcre_copy_named_substring.html create mode 100644 external-libs/pcre/doc/html/pcre_copy_substring.html create mode 100644 external-libs/pcre/doc/html/pcre_exec.html create mode 100644 external-libs/pcre/doc/html/pcre_free_substring.html create mode 100644 external-libs/pcre/doc/html/pcre_free_substring_list.html create mode 100644 external-libs/pcre/doc/html/pcre_fullinfo.html create mode 100644 external-libs/pcre/doc/html/pcre_get_named_substring.html create mode 100644 external-libs/pcre/doc/html/pcre_get_stringnumber.html create mode 100644 external-libs/pcre/doc/html/pcre_get_substring.html create mode 100644 external-libs/pcre/doc/html/pcre_get_substring_list.html create mode 100644 external-libs/pcre/doc/html/pcre_info.html create mode 100644 external-libs/pcre/doc/html/pcre_maketables.html create mode 100644 external-libs/pcre/doc/html/pcre_study.html create mode 100644 external-libs/pcre/doc/html/pcre_version.html create mode 100644 external-libs/pcre/doc/html/pcreapi.html create mode 100644 external-libs/pcre/doc/html/pcrebuild.html create mode 100644 external-libs/pcre/doc/html/pcrecallout.html create mode 100644 external-libs/pcre/doc/html/pcrecompat.html create mode 100644 external-libs/pcre/doc/html/pcregrep.html create mode 100644 external-libs/pcre/doc/html/pcrepattern.html create mode 100644 external-libs/pcre/doc/html/pcreperform.html create mode 100644 external-libs/pcre/doc/html/pcreposix.html create mode 100644 external-libs/pcre/doc/html/pcresample.html create mode 100644 external-libs/pcre/doc/html/pcretest.html (limited to 'external-libs/pcre/doc/html') diff --git a/external-libs/pcre/doc/html/index.html b/external-libs/pcre/doc/html/index.html new file mode 100644 index 00000000..3751ff0f --- /dev/null +++ b/external-libs/pcre/doc/html/index.html @@ -0,0 +1,102 @@ + + +PCRE specification + + +

Perl-compatible Regular Expressions (PCRE)

+

+The HTML documentation for PCRE comprises the following pages: +

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
pcre  Introductory page
pcreapi  PCRE's native API
pcrebuild  Options for building PCRE
pcrecallout  The callout facility
pcrecompat  Compability with Perl
pcregrep  The pcregrep command
pcrepattern  Regular expressions supported by PCRE
pcreperform  Some comments on performance
pcreposix  The POSIX API to the PCRE library
pcresample  Description of the sample program
pcretest  The pcretest command for testing PCRE
+ +

+There are also individual pages that summarize the interface for each function +in the library: +

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
pcre_compile  Compile a regular expression
pcre_config  Show build-time configuration options
pcre_copy_named_substring  Extract named substring into given buffer
pcre_copy_substring  Extract numbered substring into given buffer
pcre_exec  Match a compiled pattern to a subject string
pcre_free_substring  Free extracted substring
pcre_free_substring_list  Free list of extracted substrings
pcre_fullinfo  Extract information about a pattern
pcre_get_named_substring  Extract named substring into new memory
pcre_get_stringnumber  Convert captured string name to number
pcre_get_substring  Extract numbered substring into new memory
pcre_get_substring_list  Extract all substrings into new memory
pcre_info  Obsolete information extraction function
pcre_maketables  Build character tables in current locale
pcre_study  Study a compiled pattern
pcre_version  Return PCRE version and release date
+ + diff --git a/external-libs/pcre/doc/html/pcre.html b/external-libs/pcre/doc/html/pcre.html new file mode 100644 index 00000000..bb0d3548 --- /dev/null +++ b/external-libs/pcre/doc/html/pcre.html @@ -0,0 +1,190 @@ + + +pcre specification + + +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.
+ +
DESCRIPTION
+

+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 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 +pcrepattern +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 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 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 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. +

+
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 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. +

+
AUTHOR
+

+Philip Hazel <ph10@cam.ac.uk> +
+University Computing Service, +
+Cambridge CB2 3QG, England. +
+Phone: +44 1223 334714 +

+

+Last updated: 20 August 2003 +
+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 new file mode 100644 index 00000000..e1a43793 --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_compile.html @@ -0,0 +1,71 @@ + + +pcre_compile specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+pcre *pcre_compile(const char *pattern, int options, +const char **errptr, int *erroffset, +const unsigned char *tableptr); +

+
+DESCRIPTION +
+

+This function compiles a regular expression into an internal form. Its +arguments are: +

+

+

+  pattern       A zero-terminated string containing the
+                  regular expression to be compiled
+  options       Zero or more option bits
+  errptr        Where to put an error message
+  erroffset     Offset in pattern where error was found
+  tableptr      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 +pcreapi +page. diff --git a/external-libs/pcre/doc/html/pcre_config.html b/external-libs/pcre/doc/html/pcre_config.html new file mode 100644 index 00000000..3328b792 --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_config.html @@ -0,0 +1,56 @@ + + +pcre_config specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_config(int what, void *where); +

+
+DESCRIPTION +
+

+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: +

+

+

+  what     A code specifying what information is required
+  where    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 malloc() 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 +pcreapi +page, and a description of the POSIX API in the +pcreposix +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 new file mode 100644 index 00000000..3b1da364 --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_copy_named_substring.html @@ -0,0 +1,46 @@ + + +pcre_copy_named_substring specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_copy_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +char *buffer, int buffersize); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a captured substring, identified +by name, into a given buffer. The arguments are: +

+

+

+  code          Pattern that was successfully matched
+  subject       Subject that has been successfully matched
+  ovector       Offset vector that pcre_exec() used
+  stringcount   Value returned by pcre_exec()
+  stringname    Name of the required substring
+  buffer        Buffer to receive the string
+  buffersize    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 +pcreapi +page. diff --git a/external-libs/pcre/doc/html/pcre_copy_substring.html b/external-libs/pcre/doc/html/pcre_copy_substring.html new file mode 100644 index 00000000..f5b9b553 --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_copy_substring.html @@ -0,0 +1,44 @@ + + +pcre_copy_substring specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_copy_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, char *buffer, +int buffersize); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a captured substring into a given +buffer. The arguments are: +

+

+

+  subject       Subject that has been successfully matched
+  ovector       Offset vector that pcre_exec() used
+  stringcount   Value returned by pcre_exec()
+  stringnumber  Number of the required substring
+  buffer        Buffer to receive the string
+  buffersize    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 +pcreapi +page. diff --git a/external-libs/pcre/doc/html/pcre_exec.html b/external-libs/pcre/doc/html/pcre_exec.html new file mode 100644 index 00000000..cf86dfda --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_exec.html @@ -0,0 +1,58 @@ + + +pcre_exec specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_exec(const pcre *code, const pcre_extra *extra, +const char *subject, int length, int startoffset, +int options, int *ovector, int ovecsize); +

+
+DESCRIPTION +
+

+This function matches a compiled regular expression against a given subject +string, and returns offsets to capturing subexpressions. Its arguments are: +

+

+

+  code         Points to the compiled pattern
+  extra        Points to an associated pcre_extra structure,
+                 or is NULL
+  subject      Points to the subject string
+  length       Length of the subject string, in bytes
+  startoffset  Offset in bytes in the subject at which to
+                 start matching
+  options      Option bits
+  ovector      Points to a vector of ints for result offsets
+  ovecsize     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 +pcreapi +page. diff --git a/external-libs/pcre/doc/html/pcre_free_substring.html b/external-libs/pcre/doc/html/pcre_free_substring.html new file mode 100644 index 00000000..08b16078 --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_free_substring.html @@ -0,0 +1,29 @@ + + +pcre_free_substring specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+void pcre_free_substring(const char *stringptr); +

+
+DESCRIPTION +
+

+This is a convenience function for freeing the store obtained by a previous +call to pcre_get_substring() or pcre_get_named_substring(). Its +only argument is a pointer to the string. +

+

+There is a complete description of the PCRE API in the +pcreapi +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 new file mode 100644 index 00000000..c130f281 --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_free_substring_list.html @@ -0,0 +1,29 @@ + + +pcre_free_substring_list specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+void pcre_free_substring_list(const char **stringptr); +

+
+DESCRIPTION +
+

+This is a convenience function for freeing the store obtained by a previous +call to pcre_get_substring_list(). Its only argument is a pointer to the +list of string pointers. +

+

+There is a complete description of the PCRE API in the +pcreapi +page. diff --git a/external-libs/pcre/doc/html/pcre_fullinfo.html b/external-libs/pcre/doc/html/pcre_fullinfo.html new file mode 100644 index 00000000..f43fa65f --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_fullinfo.html @@ -0,0 +1,68 @@ + + +pcre_fullinfo specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_fullinfo(const pcre *code, const pcre_extra *extra, +int what, void *where); +

+
+DESCRIPTION +
+

+This function returns information about a compiled pattern. Its arguments are: +

+

+

+  code    Compiled regular expression
+  extra   Result of pcre_study() or NULL
+  what    What information is required
+  where   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 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
+
+

+

+There is a complete description of the PCRE API in the +pcreapi +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 new file mode 100644 index 00000000..89a2beeb --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_get_named_substring.html @@ -0,0 +1,46 @@ + + +pcre_get_named_substring specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_get_named_substring(const pcre *code, +const char *subject, int *ovector, +int stringcount, const char *stringname, +const char **stringptr); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a captured substring by name. The +arguments are: +

+

+

+  code          Compiled pattern
+  subject       Subject that has been successfully matched
+  ovector       Offset vector that pcre_exec() used
+  stringcount   Value returned by pcre_exec()
+  stringname    Name of the required substring
+  stringptr     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 +pcreapi +page. diff --git a/external-libs/pcre/doc/html/pcre_get_stringnumber.html b/external-libs/pcre/doc/html/pcre_get_stringnumber.html new file mode 100644 index 00000000..ee1c0a9c --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_get_stringnumber.html @@ -0,0 +1,39 @@ + + +pcre_get_stringnumber specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_get_stringnumber(const pcre *code, +const char *name); +

+
+DESCRIPTION +
+

+This convenience function finds the number of a named substring capturing +parenthesis in a compiled pattern. Its arguments are: +

+

+

+  code    Compiled regular expression
+  name    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 +pcreapi +page. diff --git a/external-libs/pcre/doc/html/pcre_get_substring.html b/external-libs/pcre/doc/html/pcre_get_substring.html new file mode 100644 index 00000000..2a55c10f --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_get_substring.html @@ -0,0 +1,44 @@ + + +pcre_get_substring specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_get_substring(const char *subject, int *ovector, +int stringcount, int stringnumber, +const char **stringptr); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a captured substring. The +arguments are: +

+

+

+  subject       Subject that has been successfully matched
+  ovector       Offset vector that pcre_exec() used
+  stringcount   Value returned by pcre_exec()
+  stringnumber  Number of the required substring
+  stringptr     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 +pcreapi +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 new file mode 100644 index 00000000..7e91f56b --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_get_substring_list.html @@ -0,0 +1,41 @@ + + +pcre_get_substring_list specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_get_substring_list(const char *subject, +int *ovector, int stringcount, const char ***listptr); +

+
+DESCRIPTION +
+

+This is a convenience function for extracting a list of all the captured +substrings. The arguments are: +

+

+

+  subject       Subject that has been successfully matched
+  ovector       Offset vector that pcre_exec used
+  stringcount   Value returned by pcre_exec
+  listptr       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 +pcreapi +page. diff --git a/external-libs/pcre/doc/html/pcre_info.html b/external-libs/pcre/doc/html/pcre_info.html new file mode 100644 index 00000000..97fc59b4 --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_info.html @@ -0,0 +1,28 @@ + + +pcre_info specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+int pcre_info(const pcre *code, int *optptr, int +*firstcharptr); +

+
+DESCRIPTION +
+

+This function is obsolete. You should be using pcre_fullinfo() instead. +

+

+There is a complete description of the PCRE API in the +pcreapi +page. diff --git a/external-libs/pcre/doc/html/pcre_maketables.html b/external-libs/pcre/doc/html/pcre_maketables.html new file mode 100644 index 00000000..ba3e026b --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_maketables.html @@ -0,0 +1,31 @@ + + +pcre_maketables specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+const unsigned char *pcre_maketables(void); +

+
+DESCRIPTION +
+

+This function builds a set of character tables which can be passed to +pcre_compile() to override PCRE's internal, built-in tables (which were +made by pcre_maketables() 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 +pcreapi +page. diff --git a/external-libs/pcre/doc/html/pcre_study.html b/external-libs/pcre/doc/html/pcre_study.html new file mode 100644 index 00000000..f3727d1f --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_study.html @@ -0,0 +1,45 @@ + + +pcre_study specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+pcre_extra *pcre_study(const pcre *code, int options, +const char **errptr); +

+
+DESCRIPTION +
+

+This function studies a compiled pattern, to see if additional information can +be extracted that might speed up matching. Its arguments are: +

+

+

+  code       A compiled regular expression
+  options    Options for pcre_study()
+  errptr     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 +pcreapi +page. diff --git a/external-libs/pcre/doc/html/pcre_version.html b/external-libs/pcre/doc/html/pcre_version.html new file mode 100644 index 00000000..35c47cd6 --- /dev/null +++ b/external-libs/pcre/doc/html/pcre_version.html @@ -0,0 +1,28 @@ + + +pcre_version specification + + +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.
+
+SYNOPSIS +
+

+#include <pcre.h> +

+

+char *pcre_version(void); +

+
+DESCRIPTION +
+

+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 +pcreapi +page. diff --git a/external-libs/pcre/doc/html/pcreapi.html b/external-libs/pcre/doc/html/pcreapi.html new file mode 100644 index 00000000..8ae6fb1e --- /dev/null +++ b/external-libs/pcre/doc/html/pcreapi.html @@ -0,0 +1,1346 @@ + + +pcreapi specification + + +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.
+

+
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 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 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 +pcredemo.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 compatibility. +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 +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 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 matching, 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 +discover which optional features have been compiled into the PCRE library. The +pcrebuild +documentation has more details about these optional features. +

+

+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 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 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 +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 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 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 +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_compile(): +

+

+

+  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 +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 suppressing 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 matching. The +function pcre_study() takes a pointer to a compiled pattern as its first +argument. If studing the pattern produces additional information 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 additional +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 message. You should +therefore test the error pointer for NULL after calling 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 possible 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 arguments, 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 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 pcre_malloc. The +pointer that is passed to pcre_compile is saved with the compiled +pattern, 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 +pattern. It replaces the obsolete pcre_info() function, which is +nevertheless 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 \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 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 * 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 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 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 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 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 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 +following 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 +pattern 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 +additional 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 \fRpcre_extra\fR 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" feature, +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 character. 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 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 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 success. +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 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 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 substring, and the second +is set to the offset of the first character after the end of a substring. The +first pair, ovector[0] and ovector[1], 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 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 function 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 references and +the ovector 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 ovector. +

+

+Note that pcre_info() can be used to find out how many capturing +subpatterns 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 character. +

+
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_substring_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 functions: +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_substring(), +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 substrings +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 substring by +inspecting the appropriate offset in ovector, which is negative 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 special interface to another programming language which cannot use +pcre_free directly; it is for these cases that the functions are +provided. +

+
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 number. This +can be done by calling pcre_get_stringnumber(). 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 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. 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 pcre_get_stringnumber(), and if it succeeds, they +then call pcre_copy_substring() or pcre_get_substring(), as +appropriate. +

+

+Last updated: 09 December 2003 +
+Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcrebuild.html b/external-libs/pcre/doc/html/pcrebuild.html new file mode 100644 index 00000000..c70f8221 --- /dev/null +++ b/external-libs/pcre/doc/html/pcrebuild.html @@ -0,0 +1,189 @@ + + +pcrebuild specification + + +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.
+

+
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 deselected, 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 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 +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 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 configure command. For completeness there is also a +--enable-newline-is-lf option, which explicitly specifies linefeed as the +newline 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 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 pcre_exec(). The limit can be changed +at run time, as described in the pcreapi documentation. 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 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 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 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 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 © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcrecallout.html b/external-libs/pcre/doc/html/pcrecallout.html new file mode 100644 index 00000000..f4b7104e --- /dev/null +++ b/external-libs/pcre/doc/html/pcrecallout.html @@ -0,0 +1,117 @@ + + +pcrecallout specification + + +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.
+

+
PCRE CALLOUTS
+

+int (*pcre_callout)(pcre_callout_block *); +

+

+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 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)\dabc(?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 compiled +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 captured +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 structure. 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 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. +

+

+Last updated: 21 January 2003 +
+Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcrecompat.html b/external-libs/pcre/doc/html/pcrecompat.html new file mode 100644 index 00000000..1ec22038 --- /dev/null +++ b/external-libs/pcre/doc/html/pcrecompat.html @@ -0,0 +1,136 @@ + + +pcrecompat specification + + +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.
+

+
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 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. +

+

+© 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 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 © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcregrep.html b/external-libs/pcre/doc/html/pcregrep.html new file mode 100644 index 00000000..a76cac21 --- /dev/null +++ b/external-libs/pcre/doc/html/pcregrep.html @@ -0,0 +1,153 @@ + + +pcregrep specification + + +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.
+

+
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 output 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 messages. +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 © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcrepattern.html b/external-libs/pcre/doc/html/pcrepattern.html new file mode 100644 index 00000000..65abcc21 --- /dev/null +++ b/external-libs/pcre/doc/html/pcrepattern.html @@ -0,0 +1,1607 @@ + + +pcrepattern specification + + +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.
+

+
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 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 pcre_compile() 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 +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 alternatives 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 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. +

+
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 # 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 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 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 +"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 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 +startoffset argument of pcre_exec() 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 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 +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. +

+
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 argument 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 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 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 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. +

+
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 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. +

+
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 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. +

+
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 alternatives are within a +subpattern (defined below), "succeeds" means matching the rest of the main +pattern as well as the alternative in the subpattern. +

+
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 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 +pcre_fullinfo() 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. +

+
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 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". +

+
NAMED SUBPATTERNS
+

+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 +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 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". +

+
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 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. +

+
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 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 +"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. +

+
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 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 not 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. +

+
CONDITIONAL SUBPATTERNS
+

+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. +

+
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 newline +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 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 +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 pattern, PCRE +has to obtain extra memory to store data during a recursion, which it does by +using pcre_malloc, freeing it via pcre_free 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. +

+
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 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. +

+
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 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 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)\dabc(?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 +documentation. +

+

+Last updated: 03 February 2003 +
+Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcreperform.html b/external-libs/pcre/doc/html/pcreperform.html new file mode 100644 index 00000000..418ac6d4 --- /dev/null +++ b/external-libs/pcre/doc/html/pcreperform.html @@ -0,0 +1,93 @@ + + +pcreperform specification + + +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.
+

+
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 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. +

+

+Last updated: 03 February 2003 +
+Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcreposix.html b/external-libs/pcre/doc/html/pcreposix.html new file mode 100644 index 00000000..d0a5e127 --- /dev/null +++ b/external-libs/pcre/doc/html/pcreposix.html @@ -0,0 +1,237 @@ + + +pcreposix specification + + +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.
+

+
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 \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 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 +regmatch_t for returning captured substrings. It also defines some +constants 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 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 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 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. +

+
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 substrings, +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 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 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 +function is the size of buffer needed to hold the whole message. +

+
STORAGE
+

+Compiling a regular expression causes memory to be allocated and associated +with the preg structure. The function regfree() frees all such +memory, after which preg may no longer be used as a compiled expression. +

+
AUTHOR
+

+Philip Hazel <ph10@cam.ac.uk> +
+University Computing Service, +
+Cambridge CB2 3QG, England. +

+

+Last updated: 03 February 2003 +
+Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcresample.html b/external-libs/pcre/doc/html/pcresample.html new file mode 100644 index 00000000..fed41f62 --- /dev/null +++ b/external-libs/pcre/doc/html/pcresample.html @@ -0,0 +1,79 @@ + + +pcresample specification + + +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.
+

+
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 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 /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 systems. You +need to add +

+

+

+  -R/usr/local/lib
+
+

+

+to the compile command to get round this problem. +

+

+Last updated: 28 January 2003 +
+Copyright © 1997-2003 University of Cambridge. diff --git a/external-libs/pcre/doc/html/pcretest.html b/external-libs/pcre/doc/html/pcretest.html new file mode 100644 index 00000000..2ba9893d --- /dev/null +++ b/external-libs/pcre/doc/html/pcretest.html @@ -0,0 +1,443 @@ + + +pcretest specification + + +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.
+

+
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 available 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 milliseconds). 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 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. +

+
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 difference 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 handles 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 compiling 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 character, and +so on). It does this by calling pcre_fullinfo() after compiling 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 compiled +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, +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 /? 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 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 pcretest to check +complicated 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 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. +

+
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 "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 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 +different values in the match_limit field of the pcre_extra data +structure, 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 terminates the data input. +

+

+If /P was present on the regex, causing the POSIX wrapper API to be used, +only \B, and \Z have any effect, 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, identified 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 +parentheses 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 newlines 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 © 1997-2003 University of Cambridge. -- cgit v1.2.3-70-g09d2