From 582b500cd996c96054615870fd13d6ab0ea77428 Mon Sep 17 00:00:00 2001
From: Jay Berkenbilt
+#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 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:
+
+
+
+
+
SYNOPSIS OF PCRE API
+
PCRE API
+
+ 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. +
++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. +
++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. +
++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(). +
++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. +
++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. +
++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. +
++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). +
++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. +
++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. +
++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.
--
cgit v1.2.3-54-g00ecf