#include <pcre.h>
+pcre *pcre_compile(const char *pattern, int options, -const char **errptr, int *erroffset, -const unsigned char *tableptr); -
-
+ const char **errptr, int *erroffset,
+ const unsigned char *tableptr);
+
+
pcre *pcre_compile2(const char *pattern, int options,
-int *errorcodeptr,
-const char **errptr, int *erroffset,
-const unsigned char *tableptr);
-
+ int *errorcodeptr,
+ const char **errptr, int *erroffset,
+ const unsigned char *tableptr);
+
+
pcre_extra *pcre_study(const pcre *code, int options,
-const char **errptr);
-
+ const char **errptr);
+
+
void pcre_free_study(pcre_extra *extra);
-
+
+
int pcre_exec(const pcre *code, const pcre_extra *extra,
-const char *subject, int length, int startoffset,
-int options, int *ovector, int ovecsize);
-
-pcre_jit_stack *pcre_jit_stack_alloc(int startsize, int maxsize); -
--void pcre_jit_stack_free(pcre_jit_stack *stack); -
--void pcre_assign_jit_stack(pcre_extra *extra, -pcre_jit_callback callback, void *data); -
-
+ const char *subject, int length, int startoffset,
+ int options, int *ovector, int ovecsize);
+
+
int pcre_dfa_exec(const pcre *code, const pcre_extra *extra,
-const char *subject, int length, int startoffset,
-int options, int *ovector, int ovecsize,
-int *workspace, int wscount);
+ const char *subject, int length, int startoffset,
+ int options, int *ovector, int ovecsize,
+ int *workspace, int wscount);
int pcre_copy_named_substring(const pcre *code, -const char *subject, int *ovector, -int stringcount, const char *stringname, -char *buffer, int buffersize); -
-
+ 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 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);
-
+ const char *subject, int *ovector,
+ int stringcount, const char *stringname,
+ const char **stringptr);
+
+
int pcre_get_stringnumber(const pcre *code,
-const char *name);
-
+ const char *name);
+
+
int pcre_get_stringtable_entries(const pcre *code,
-const char *name, char **first, char **last);
-
+ const char *name, char **first, char **last);
+
+
int pcre_get_substring(const char *subject, int *ovector,
-int stringcount, int stringnumber,
-const char **stringptr);
-
+ int stringcount, int stringnumber,
+ const char **stringptr);
+
+
int pcre_get_substring_list(const char *subject,
-int *ovector, int stringcount, const char ***listptr);
-
+ int *ovector, int stringcount, const char ***listptr);
+
+
void pcre_free_substring(const char *stringptr);
-
+
+
void pcre_free_substring_list(const char **stringptr);
+int pcre_jit_exec(const pcre *code, const pcre_extra *extra,
+ const char *subject, int length, int startoffset,
+ int options, int *ovector, int ovecsize,
+ pcre_jit_stack *jstack);
+
+
+pcre_jit_stack *pcre_jit_stack_alloc(int startsize, int maxsize);
+
+
+void pcre_jit_stack_free(pcre_jit_stack *stack);
+
+
+void pcre_assign_jit_stack(pcre_extra *extra,
+ pcre_jit_callback callback, void *data);
+
+
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 what, void *where);
+
+
int pcre_refcount(pcre *code, int adjust);
-
+
+
int pcre_config(int what, void *where);
+
+
+const char *pcre_version(void);
+
+
+int pcre_pattern_to_host_byte_order(pcre *code,
+ pcre_extra *extra, const unsigned char *tables);
-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 *);
-void *(*pcre_stack_malloc)(size_t); +As well as support for 8-bit character strings, PCRE also supports 16-bit +strings (from release 8.30) and 32-bit strings (from release 8.32), by means of +two additional libraries. They can be built as well as, or instead of, the +8-bit library. To avoid too much complication, this document describes the +8-bit versions of the functions, with only occasional references to the 16-bit +and 32-bit libraries.
-void (*pcre_stack_free)(void *); +The 16-bit and 32-bit functions operate in the same way as their 8-bit +counterparts; they just use different data types for their arguments and +results, and their names start with pcre16_ or pcre32_ instead of +pcre_. For every option that has UTF8 in its name (for example, +PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 replaced +by UTF16 or UTF32, respectively. This facility is in fact just cosmetic; the +16-bit and 32-bit option names define the same bit values.
-int (*pcre_callout)(pcre_callout_block *); +References to bytes and UTF-8 in this document should be read as references to +16-bit data units and UTF-16 when using the 16-bit library, or 32-bit data +units and UTF-32 when using the 32-bit library, unless specified otherwise. +More details of the specific differences for the 16-bit and 32-bit libraries +are given in the +pcre16 +and +pcre32 +pages.
-PCRE has its own native API, which is described in this document. There are -also some wrapper functions that correspond to the POSIX regular expression -API, but they do not give access to all the functionality. They are described -in the +also some wrapper functions (for the 8-bit library only) that correspond to the +POSIX regular expression API, but they do not give access to all the +functionality. They are described in the pcreposix documentation. Both of these APIs define a set of C function calls. A C++ -wrapper is also distributed with PCRE. It is documented in the +wrapper (again for the 8-bit library only) is also distributed with PCRE. It is +documented in the pcrecpp page.
The native API C function prototypes are defined in the header file -pcre.h, and on Unix systems the library itself is called libpcre. -It can normally be accessed by adding -lpcre to the command for linking -an application that uses PCRE. 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 of PCRE. +pcre.h, and on Unix-like systems the (8-bit) library itself is called +libpcre. It can normally be accessed by adding -lpcre to the +command for linking an application that uses PCRE. 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 of PCRE.
In a Windows environment, if you want to statically link an application program @@ -204,7 +244,10 @@ used if available, by setting an option that is ignore relevant. More complicated programs might need to make use of the functions pcre_jit_stack_alloc(), pcre_jit_stack_free(), and pcre_assign_jit_stack() in order to control the JIT code's memory usage. -These functions are discussed in the +
++From release 8.32 there is also a direct interface for JIT execution, which +gives improved performance. The JIT-specific functions are discussed in the pcrejit documentation.
@@ -244,10 +287,8 @@ internal tables that are generated when PCRE is builtThe function pcre_fullinfo() is used to find out information about a -compiled pattern; pcre_info() is an obsolete version that 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. +compiled pattern. The function pcre_version() returns a pointer to a +string containing the version of PCRE and its date of release.
The function pcre_refcount() maintains a reference count in a data block @@ -284,13 +325,13 @@ points during a matching operation. Details are given pcrecallout documentation.
-PCRE supports five different conventions for indicating line breaks in strings: a single CR (carriage return) character, a single LF (linefeed) character, the two-character sequence CRLF, any of the three preceding, or any Unicode newline sequence. The Unicode newline sequences are the three just -mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed, +mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS (paragraph separator, U+2029).
@@ -323,7 +364,7 @@ The choice of newline convention does not affect the i the \n or \r escape sequences, nor does it affect what \R matches, which is controlled in a similar way, but by separate options. -The PCRE functions can be used in multi-threading applications, with the proviso that the memory management functions pointed to by pcre_malloc, @@ -340,17 +381,18 @@ memory stack areas for each thread. See the pcrejit documentation for more details.
-The compiled form of a regular expression can be saved and re-used at a later time, possibly by a different program, and even on a host other than the one on which it was compiled. Details are given in the pcreprecompile -documentation. However, compiling a regular expression with one version of PCRE -for use with a different version is not guaranteed to work and may cause -crashes. +documentation, which includes a description of the +pcre_pattern_to_host_byte_order() function. However, compiling a regular +expression with one version of PCRE for use with a different version is not +guaranteed to work and may cause crashes.
-int pcre_config(int what, void *where);
@@ -363,13 +405,31 @@ documentation has more details about these optional feThe 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: +which the information is placed. The returned value is zero on success, or the +negative error code PCRE_ERROR_BADOPTION if the value in the first argument is +not recognized. The following information is available:
PCRE_CONFIG_UTF8The output is an integer that is set to one if UTF-8 support is available; -otherwise it is set to zero. +otherwise it is set to zero. This value should normally be given to the 8-bit +version of this function, pcre_config(). If it is given to the 16-bit +or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
+ PCRE_CONFIG_UTF16 ++The output is an integer that is set to one if UTF-16 support is available; +otherwise it is set to zero. This value should normally be given to the 16-bit +version of this function, pcre16_config(). If it is given to the 8-bit +or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION. +
+ PCRE_CONFIG_UTF32 ++The output is an integer that is set to one if UTF-32 support is available; +otherwise it is set to zero. This value should normally be given to the 32-bit +version of this function, pcre32_config(). If it is given to the 8-bit +or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION. +
PCRE_CONFIG_UNICODE_PROPERTIESThe output is an integer that is set to one if support for Unicode character @@ -380,14 +440,23 @@ properties is available; otherwise it is set to zero. The output is an integer that is set to one if support for just-in-time compiling is available; otherwise it is set to zero.
+ PCRE_CONFIG_JITTARGET ++The output is a pointer to a zero-terminated "const char *" string. If JIT +support is available, the string contains the name of the architecture for +which the JIT compiler is configured, for example "x86 32bit (little endian + +unaligned)". If JIT support is not available, the result is NULL. +
PCRE_CONFIG_NEWLINEThe output is an integer whose value specifies the default character sequence -that is recognized as meaning "newline". The four values that are supported -are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. -Though they are derived from ASCII, the same values are returned in EBCDIC -environments. The default should normally correspond to the standard sequence -for your operating system. +that is recognized as meaning "newline". The values that are supported in +ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for +ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the +same values. However, the value for LF is normally 21, though some EBCDIC +environments use 37. The corresponding values for CRLF are 3349 and 3365. The +default should normally correspond to the standard sequence for your operating +system.
PCRE_CONFIG_BSR@@ -399,10 +468,13 @@ or CRLF. The default can be overridden when a pattern 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. +linkage in compiled regular expressions. For the 8-bit library, the value can +be 2, 3, or 4. For the 16-bit library, the value is either 2 or 4 and is still +a number of bytes. For the 32-bit library, the value is either 2 or 4 and is +still a number of bytes. 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. Larger values allow larger regular expressions to be compiled, at the +expense of slower matching.
PCRE_CONFIG_POSIX_MALLOC_THRESHOLD@@ -412,6 +484,13 @@ the pcreposix documentation.
+ PCRE_CONFIG_PARENS_LIMIT ++The output is a long integer that gives the maximum depth of nesting of +parentheses (of any kind) in a pattern. This limit is imposed to cap the amount +of system stack used when a pattern is compiled. It is specified when PCRE is +built; the default is 250. +
PCRE_CONFIG_MATCH_LIMITThe output is a long integer that gives the default limit for the number of @@ -434,15 +513,17 @@ of recursive function calls. In this case, pcre_sta 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);
+ const char **errptr, int *erroffset,
+ const unsigned char *tableptr);
+
+
pcre *pcre_compile2(const char *pattern, int options,
-int *errorcodeptr,
-const char **errptr, int *erroffset,
-const unsigned char *tableptr);
+ int *errorcodeptr,
+ const char **errptr, int *erroffset,
+ const unsigned char *tableptr);
Either of the functions pcre_compile() or pcre_compile2() can be @@ -477,7 +558,7 @@ documentation). For those options that can be differen the pattern, the contents of the options argument specifies their settings at the start of compilation and execution. The PCRE_ANCHORED, PCRE_BSR_xxx, PCRE_NEWLINE_xxx, PCRE_NO_UTF8_CHECK, and -PCRE_NO_START_OPT options can be set at the time of matching as well as at +PCRE_NO_START_OPTIMIZE options can be set at the time of matching as well as at compile time.
@@ -486,16 +567,16 @@ Otherwise, if compilation of a pattern fails, pcre_ NULL, and sets the variable pointed to by errptr to point to a textual error message. This is a static string that is part of the library. You must not try to free it. Normally, the offset from the start of the pattern to the -byte that was being processed when 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). However, for an invalid UTF-8 string, the offset is -that of the first byte of the failing character. Also, some errors are not -detected until checks are carried out when the whole pattern has been scanned; -in these cases the offset passed back is the length of the pattern. +data unit that was being processed when 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). However, for an invalid UTF-8 or UTF-16 string, +the offset is that of the first data unit of the failing character.
-Note that the offset is in bytes, not characters, even in UTF-8 mode. It may -sometimes point into the middle of a UTF-8 character. +Some errors are not detected until the whole pattern has been scanned; in these +cases, the offset passed back is the length of the pattern. Note that the +offset is in data units, not characters, even in a UTF mode. It may sometimes +point into the middle of a UTF-8 or UTF-16 character.
If pcre_compile2() is used instead of pcre_compile(), and the @@ -508,8 +589,9 @@ If the final argument, tableptr, is NULL, PCRE character tables that are built when PCRE is compiled, using the default C locale. Otherwise, tableptr must be an address that is the result of a call to pcre_maketables(). This value is stored with the compiled -pattern, and used again by pcre_exec(), unless another table pointer is -passed to it. For more discussion, see the section on locale support below. +pattern, and used again by pcre_exec() and pcre_dfa_exec() when the +pattern is matched. For more discussion, see the section on locale support +below.
This code fragment shows a typical straightforward call to pcre_compile(): @@ -594,14 +676,26 @@ documentation.
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, 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. +If this bit is set, most white space characters in the pattern are totally +ignored except when escaped or inside a character class. However, white space +is not allowed within sequences such as (?> that introduce various +parenthesized subpatterns, nor within a numerical quantifier such as {1,3}. +However, ignorable white space is permitted between an item and a following +quantifier and between a quantifier and a following + that indicates +possessiveness.
+White space did not used to include the VT character (code 11), because Perl +did not treat this character as white space. However, Perl changed at release +5.18, so PCRE followed at release 8.34, and VT is now treated as white space. +
++PCRE_EXTENDED also causes characters between an unescaped # outside a character +class and the next newline, inclusive, to be ignored. PCRE_EXTENDED is +equivalent to Perl's /x option, and it can be changed within a pattern by a +(?x) option setting. +
+Which characters are interpreted as newlines is controlled by the options passed to pcre_compile() or by a special sequence at the start of the pattern, as described in the section entitled @@ -612,7 +706,7 @@ happen to represent a newline do not count.
This option makes it possible to include comments inside complicated patterns. -Note, however, that this applies only to data characters. Whitespace characters +Note, however, that this applies only to data characters. White space characters may never appear within special character sequences in a pattern, for example within the sequence (?( that introduces a conditional subpattern.
@@ -669,12 +763,14 @@ binary zero character followed by z).PCRE_MULTILINE-By default, PCRE treats the subject string as consisting of a single line of -characters (even if it actually contains newlines). The "start of line" -metacharacter (^) matches only at the start of the string, while the "end of -line" metacharacter ($) matches only at the end of the string, or before a -terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as -Perl. +By default, for the purposes of matching "start of line" and "end of line", +PCRE treats the subject string as consisting of a single line of characters, +even if it actually contains newlines. The "start of line" metacharacter (^) +matches only at the start of the string, and the "end of line" metacharacter +($) matches only at the end of the string, or before a terminating newline +(except when PCRE_DOLLAR_ENDONLY is set). Note, however, that unless +PCRE_DOTALL is set, the "any character" metacharacter (.) does not match at a +newline. This behaviour (for ^, $, and dot) is the same as Perl.When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs @@ -684,6 +780,15 @@ equivalent to Perl's /m option, and it can be changed (?m) option setting. If there are no newlines in a subject string, or no occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
+ PCRE_NEVER_UTF ++This option locks out interpretation of the pattern as UTF-8 (or UTF-16 or +UTF-32 in the 16-bit and 32-bit libraries). In particular, it prevents the +creator of the pattern from switching to UTF interpretation by starting the +pattern with (*UTF). This may be useful in applications that process patterns +from external sources. The combination of PCRE_UTF8 and PCRE_NEVER_UTF also +causes an error. +PCRE_NEWLINE_CR PCRE_NEWLINE_LF PCRE_NEWLINE_CRLF @@ -696,13 +801,25 @@ indicated by a single character (CR or LF, respectivel PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies -that any Unicode newline sequence should be recognized. The Unicode newline -sequences are the three just mentioned, plus the single characters VT (vertical -tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line -separator, U+2028), and PS (paragraph separator, U+2029). The last two are +that any Unicode newline sequence should be recognized. + ++In an ASCII/Unicode environment, the Unicode newline sequences are the three +just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form +feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS +(paragraph separator, U+2029). For the 8-bit library, the last two are recognized only in UTF-8 mode.
+When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for +CR is 0x0d, the same as ASCII. However, the character code for LF is normally +0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is +not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all +less than 256. For more details, see the +pcrebuild +documentation. +
+The newline setting in the options word uses three bits that are treated as a number, giving eight possibilities. Currently only six are used (default plus the five values above). This means that if you set more than one newline @@ -712,7 +829,7 @@ other combinations may yield unused numbers and cause
The only time that a line break in a pattern is specially recognized when -compiling is when PCRE_EXTENDED is set. CR and LF are whitespace characters, +compiling is when PCRE_EXTENDED is set. CR and LF are white space characters, and so are ignored in this mode. Also, an unescaped # outside a character class indicates a comment that lasts until after the next line break sequence. In other circumstances, line break sequences in patterns are treated as literal @@ -730,12 +847,23 @@ were followed by ?: but named parentheses can still be they acquire numbers in the usual way). There is no equivalent of this option in Perl.
- NO_START_OPTIMIZE + PCRE_NO_AUTO_POSSESS+If this option is set, it disables "auto-possessification". This is an +optimization that, for example, turns a+b into a++b in order to avoid +backtracks into a+ that can never be successful. However, if callouts are in +use, auto-possessification means that some of them are never taken. You can set +this option if you want the matching functions to do a full unoptimized search +and run all the callouts, but it is mainly provided for testing purposes. ++ PCRE_NO_START_OPTIMIZE +This is an option that acts at matching time; that is, it is really an option for pcre_exec() or pcre_dfa_exec(). If it is set at compile time, -it is remembered with the compiled pattern and assumed at matching time. For -details see the discussion of PCRE_NO_START_OPTIMIZE +it is remembered with the compiled pattern and assumed at matching time. This +is necessary if you want to use JIT execution, because the JIT compiler needs +to know whether or not this option is set. For details see the discussion of +PCRE_NO_START_OPTIMIZE below.PCRE_UCP @@ -760,10 +888,10 @@ with Perl. It can also be set by a (?U) option setting PCRE_UTF8This 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 when PCRE is 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 +of UTF-8 characters instead of single-byte strings. However, it is available +only when PCRE is built to include UTF 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 pcreunicode page.@@ -771,23 +899,26 @@ page.When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is automatically checked. There is a discussion about the -validity of UTF-8 strings -in the main -pcre -page. 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 this option +validity of UTF-8 strings +in the +pcreunicode +page. If an invalid UTF-8 sequence 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 or loop. Note that this option can also be passed to pcre_exec() and pcre_dfa_exec(), to suppress -the UTF-8 validity checking of subject strings. +the validity checking of subject strings only. If the same string is being +matched many times, the option can be safely set for the second and subsequent +matchings to improve performance. -
COMPILATION ERROR CODES
+
COMPILATION ERROR CODES
The following table lists the error codes than may be returned by pcre_compile2(), along with the error messages that may be returned by -both compiling functions. As PCRE has developed, some error codes have fallen -out of use. To avoid confusion, they have not been re-used. +both compiling functions. Note that error messages are always 8-bit ASCII +strings, even in 16-bit or 32-bit mode. As PCRE has developed, some error codes +have fallen out of use. To avoid confusion, they have not been re-used.
0 no error 1 \ at end of pattern @@ -821,9 +952,9 @@ out of use. To avoid confusion, they have not been re- 29 (?R or (?[+-]digits must be followed by ) 30 unknown POSIX class name 31 POSIX collating elements are not supported - 32 this version of PCRE is not compiled with PCRE_UTF8 support + 32 this version of PCRE is compiled without UTF support 33 [this code is not in use] - 34 character value in \x{...} sequence is too large + 34 character value in \x{} or \o{} is too large 35 invalid condition (?(0) 36 \C not allowed in lookbehind assertion 37 PCRE does not support \L, \l, \N{name}, \U, or \u @@ -833,14 +964,14 @@ out of use. To avoid confusion, they have not been re- 41 unrecognized character after (?P 42 syntax error in subpattern name (missing terminator) 43 two named subpatterns have the same name - 44 invalid UTF-8 string + 44 invalid UTF-8 string (specifically UTF-8) 45 support for \P, \p, and \X has not been compiled 46 malformed \P or \p sequence 47 unknown property name after \P or \p 48 subpattern name is too long (maximum 32 characters) 49 too many named subpatterns (maximum 10000) 50 [this code is not in use] - 51 octal value is greater than \377 (not in UTF-8 mode) + 51 octal value is greater than \377 in 8-bit non-UTF-8 mode 52 internal error: overran compiling workspace 53 internal error: previously-checked referenced subpattern not found @@ -851,7 +982,7 @@ out of use. To avoid confusion, they have not been re- name/number or by a plain number 58 a numbered reference must not be zero 59 an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT) - 60 (*VERB) not recognized + 60 (*VERB) not recognized or malformed 61 number is too big 62 subpattern name expected 63 digit expected after (?+ @@ -859,17 +990,32 @@ out of use. To avoid confusion, they have not been re- 65 different names for subpatterns of the same number are not allowed 66 (*MARK) must have an argument - 67 this version of PCRE is not compiled with PCRE_UCP support + 67 this version of PCRE is not compiled with Unicode property + support 68 \c must be followed by an ASCII character 69 \k is not followed by a braced, angle-bracketed, or quoted name + 70 internal error: unknown opcode in find_fixedlength() + 71 \N is not supported in a class + 72 too many forward references + 73 disallowed Unicode code point (>= 0xd800 && <= 0xdfff) + 74 invalid UTF-16 string (specifically UTF-16) + 75 name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN) + 76 character value in \u.... sequence is too large + 77 invalid UTF-32 string (specifically UTF-32) + 78 setting UTF is disabled by the application + 79 non-hex character in \x{} (closing brace missing?) + 80 non-octal character in \o{} (closing brace missing?) + 81 missing opening brace after \o + 82 parentheses are too deeply nested + 83 invalid range in character classThe numbers 32 and 10000 in errors 48 and 49 are defaults; different values may be used if the limits were changed when PCRE was built. -
STUDYING A PATTERN
+
STUDYING A PATTERN
-pcre_extra *pcre_study(const pcre *code, int options -const char **errptr); +pcre_extra *pcre_study(const pcre *code, int options, + const char **errptr);
If a compiled pattern is going to be used several times, it is worth spending @@ -890,17 +1036,27 @@ in the section on matching a pattern.
If studying the pattern does not produce any useful information, -pcre_study() returns NULL. In that circumstance, if the calling program -wants to pass any of the other fields to pcre_exec() or -pcre_dfa_exec(), it must set up its own pcre_extra block. +pcre_study() returns NULL by default. In that circumstance, if the +calling program wants to pass any of the other fields to pcre_exec() or +pcre_dfa_exec(), it must set up its own pcre_extra block. However, +if pcre_study() is called with the PCRE_STUDY_EXTRA_NEEDED option, it +returns a pcre_extra block even if studying did not find any additional +information. It may still return NULL, however, if an error occurs in +pcre_study().
-The second argument of pcre_study() contains option bits. There is only -one option: PCRE_STUDY_JIT_COMPILE. If this is set, and the just-in-time -compiler is available, the pattern is further compiled into machine code that -executes much faster than the pcre_exec() matching function. If -the just-in-time compiler is not available, this option is ignored. All other -bits in the options argument must be zero. +The second argument of pcre_study() contains option bits. There are three +further options in addition to PCRE_STUDY_EXTRA_NEEDED: +
+ PCRE_STUDY_JIT_COMPILE + PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE + PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE ++If any of these are set, and the just-in-time compiler is available, the +pattern is further compiled into machine code that executes much faster than +the pcre_exec() interpretive matching function. If the just-in-time +compiler is not available, these options are ignored. All undefined bits in the +options argument must be zero.JIT compilation is a heavyweight optimization. It can take some time for @@ -925,8 +1081,8 @@ When you are finished with a pattern, you can free the study data by calling pcre_free_study(). This function was added to the API for release 8.20. For earlier versions, the memory could be freed with pcre_free(), just like the pattern itself. This will still work in cases -where PCRE_STUDY_JIT_COMPILE is not used, but it is advisable to change to the -new function when convenient. +where JIT optimization is not used, but it is advisable to change to the new +function when convenient.
This is a typical way in which pcre_study() is used (except that in a @@ -949,43 +1105,53 @@ real application there should be tests for errors): Studying a pattern does two things: first, a lower bound for the length of subject string that is needed to match the pattern is computed. This does not mean that there are any strings of that length that match, but it does -guarantee that no shorter strings match. The value is used by -pcre_exec() and pcre_dfa_exec() to avoid wasting time by trying to -match strings that are shorter than the lower bound. You can find out the value -in a calling program via the pcre_fullinfo() function. +guarantee that no shorter strings match. The value is used to avoid wasting +time by trying to match strings that are shorter than the lower bound. You can +find out the value in a calling program via the pcre_fullinfo() function.
Studying a pattern is also useful for non-anchored patterns that do not have a single fixed starting character. A bitmap of possible starting bytes is created. This speeds up finding a position in the subject at which to start -matching. +matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256. +In 32-bit mode, the bitmap is used for 32-bit values less than 256.)
These two optimizations apply to both pcre_exec() and -pcre_dfa_exec(). However, they are not used by pcre_exec() if -pcre_study() is called with the PCRE_STUDY_JIT_COMPILE option, and -just-in-time compiling is successful. The optimizations can be disabled by -setting the PCRE_NO_START_OPTIMIZE option when calling pcre_exec() or -pcre_dfa_exec(). You might want to do this if your pattern contains -callouts or (*MARK) (which cannot be handled by the JIT compiler), and you want -to make use of these facilities in cases where matching fails. See the -discussion of PCRE_NO_START_OPTIMIZE +pcre_dfa_exec(), and the information is also used by the JIT compiler. +The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option. +You might want to do this if your pattern contains callouts or (*MARK) and you +want to make use of these facilities in cases where matching fails. +
++PCRE_NO_START_OPTIMIZE can be specified at either compile time or execution +time. However, if PCRE_NO_START_OPTIMIZE is passed to pcre_exec(), (that +is, after any JIT compilation has happened) JIT execution is disabled. For JIT +execution to work with PCRE_NO_START_OPTIMIZE, the option must be set at +compile time. +
++There is a longer discussion of PCRE_NO_START_OPTIMIZE below.
-
LOCALE SUPPORT
+
LOCALE SUPPORT
PCRE handles caseless matching, and determines whether characters are letters, digits, or whatever, by reference to a set of tables, indexed by character -value. When running in UTF-8 mode, this applies only to characters with codes -less than 128. By default, higher-valued codes never match escapes such as \w -or \d, but they can be tested with \p if PCRE is built with Unicode character -property support. Alternatively, the PCRE_UCP option can be set at compile -time; this causes \w and friends to use Unicode property support instead of -built-in tables. The use of locales with Unicode is discouraged. If you are -handling characters with codes greater than 128, you should either use UTF-8 -and Unicode, or use locales, but not try to mix the two. +code point. When running in UTF-8 mode, or in the 16- or 32-bit libraries, this +applies only to characters with code points less than 256. By default, +higher-valued code points never match escapes such as \w or \d. However, if +PCRE is built with Unicode property support, all characters can be tested with +\p and \P, or, alternatively, the PCRE_UCP option can be set when a pattern +is compiled; this causes \w and friends to use Unicode property support +instead of the built-in tables.
+The use of locales with Unicode is discouraged. If you are handling characters +with code points greater than 128, you should either use Unicode support, or +use locales, but not try to mix the two. +
+PCRE contains an internal set of tables that are used when the final argument of pcre_compile() is NULL. These are sufficient for many applications. Normally, the internal tables recognize only ASCII characters. However, when @@ -1001,10 +1167,10 @@ for this locale support is expected to die away.
External 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() or pcre_exec() as often as necessary. For -example, to build and use tables that are appropriate for the French locale -(where accented characters with values greater than 128 are treated as letters), -the following code could be used: +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 values greater than 128 are treated as letters), the following code could +be used:
setlocale(LC_CTYPE, "fr_FR"); tables = pcre_maketables(); @@ -1022,26 +1188,30 @@ needed.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 normally also by pcre_exec(). Thus, by default, for any single +and also by pcre_exec() and pcre_dfa_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. +different patterns can be processed in different locales.
It is possible to pass a table pointer or NULL (indicating the use of the -internal tables) to pcre_exec(). Although not intended for this purpose, -this facility could be used to match a pattern in a different locale from the -one in which it was compiled. Passing table pointers at run time is discussed -below in the section on matching a pattern. +internal tables) to pcre_exec() or pcre_dfa_exec() (see the +discussion below in the section on matching a pattern). This facility is +provided for use with pre-compiled patterns that have been saved and reloaded. +Character tables are not saved with patterns, so if a non-standard table was +used at compile time, it must be provided again when the reloaded pattern is +matched. Attempting to use this facility to match a pattern in a different +locale from the one in which it was compiled is likely to lead to anomalous +(usually incorrect) results.
-
INFORMATION ABOUT A PATTERN
+
INFORMATION ABOUT A PATTERN
int pcre_fullinfo(const pcre *code, const pcre_extra *extra, -int what, void *where); + 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). +pattern. It replaces the pcre_info() function, which was removed from the +library at version 8.30, after more than 10 years of obsolescence.
The first argument for pcre_fullinfo() is a pointer to the compiled @@ -1051,14 +1221,19 @@ information is required, and the fourth argument is a 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 + PCRE_ERROR_NULL the argument code was NULL + the argument where was NULL + PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_ERROR_BADENDIANNESS the pattern was compiled with different + endianness + PCRE_ERROR_BADOPTION the value of what was invalid + PCRE_ERROR_UNSET the requested field is not setThe "magic number" is placed at the start of each compiled pattern as an simple -check against passing an arbitrary memory pointer. Here is a typical call of -pcre_fullinfo(), to obtain the length of the compiled pattern: +check against passing an arbitrary memory pointer. The endianness error can +occur if a compiled pattern is saved and reloaded on a different host. Here is +a typical call of pcre_fullinfo(), to obtain the length of the compiled +pattern:int rc; size_t length; @@ -1092,14 +1267,19 @@ a NULL table pointer.PCRE_INFO_FIRSTBYTE-Return information about the first byte of any matched string, for a -non-anchored pattern. The fourth argument should point to an int -variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is -still recognized for backwards compatibility.) +Return information about the first data unit of any matched string, for a +non-anchored pattern. (The name of this option refers to the 8-bit library, +where data units are bytes.) The fourth argument should point to an int +variable.-If there is a fixed first byte, for example, from a pattern such as -(cat|cow|coyote), its value is returned. Otherwise, if either +If there is a fixed first value, for example, the letter "c" from a pattern +such as (cat|cow|coyote), its value is returned. In the 8-bit library, the +value is always less than 256. In the 16-bit library the value can be up to +0xffff. In the 32-bit library the value can be up to 0x10ffff. +
++If there is no fixed first value, and if either
+
(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch @@ -1113,11 +1293,17 @@ starts with "^", or -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. ++Since for the 32-bit library using the non-UTF-32 mode, this function is unable +to return the full 32-bit range of the character, this value is deprecated; +instead the PCRE_INFO_FIRSTCHARACTERFLAGS and PCRE_INFO_FIRSTCHARACTER values +should be used.
PCRE_INFO_FIRSTTABLEIf 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 +table indicating a fixed set of values for the first data unit 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.@@ -1135,40 +1321,69 @@ Return 1 if the (?J) or (?-J) option setting is used iWhen PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8 string is automatically checked when pcre_exec() is subsequently called. -The value of startoffset is also checked to ensure that it points to the -start of a UTF-8 character. There is a discussion about the validity of UTF-8 -strings in the -section on UTF-8 support -in the main -pcre -page. If an invalid UTF-8 sequence of bytes is found, pcre_exec() returns -the error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is -a truncated UTF-8 character at the end of the subject, PCRE_ERROR_SHORTUTF8. In -both cases, information about the precise nature of the error may also be -returned (see the descriptions of these errors in the section entitled \fIError -return values from\fP pcre_exec() +The entire string is checked before any other processing takes place. The value +of startoffset is also checked to ensure that it points to the start of a +UTF-8 character. There is a discussion about the +validity of UTF-8 strings +in the +pcreunicode +page. If an invalid sequence of bytes is found, pcre_exec() returns the +error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a +truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both +cases, information about the precise nature of the error may also be returned +(see the descriptions of these errors in the section entitled \fIError return +values from\fP pcre_exec() below). If startoffset contains a value that does not point to the start of a UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is @@ -1691,10 +1988,10 @@ checks for performance reasons, you can set the PCRE_N 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 (or the -end of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an -invalid UTF-8 string as a subject or an invalid value of startoffset is -undefined. Your program may crash. +the value of startoffset points to the start of a character (or the end +of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an +invalid string as a subject or an invalid value of startoffset is +undefined. Your program may crash or loop.PCRE_INFO_JIT-Return 1 if the pattern was studied with the PCRE_STUDY_JIT_COMPILE option, and +Return 1 if the pattern was studied with one of the JIT options, and just-in-time compiling was successful. The fourth argument should point to an int variable. A return value of 0 means that JIT support is not available -in this version of PCRE, or that the pattern was not studied with the -PCRE_STUDY_JIT_COMPILE option, or that the JIT compiler could not handle this -particular pattern. See the +in this version of PCRE, or that the pattern was not studied with a JIT option, +or that the JIT compiler could not handle this particular pattern. See the pcrejit documentation for details of what can and cannot be handled.PCRE_INFO_JITSIZE-If the pattern was successfully studied with the PCRE_STUDY_JIT_COMPILE option, -return the size of the JIT compiled code, otherwise return zero. The fourth -argument should point to a size_t variable. +If the pattern was successfully studied with a JIT option, return the size of +the JIT compiled code, otherwise return zero. The fourth argument should point +to a size_t 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 +Return the value of the rightmost literal data unit that must exist in any +matched string, other than at its start, if such a value has been recorded. The +fourth argument should point to an int variable. If there is no such +value, -1 is returned. For anchored patterns, a last literal value 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. + ++Since for the 32-bit library using the non-UTF-32 mode, this function is unable +to return the full 32-bit range of characters, this value is deprecated; +instead the PCRE_INFO_REQUIREDCHARFLAGS and PCRE_INFO_REQUIREDCHAR values should +be used.
+ PCRE_INFO_MATCH_EMPTY ++Return 1 if the pattern can match an empty string, otherwise 0. The fourth +argument should point to an int variable. ++ PCRE_INFO_MATCHLIMIT ++If the pattern set a match limit by including an item of the form +(*LIMIT_MATCH=nnnn) at the start, the value is returned. The fourth argument +should point to an unsigned 32-bit integer. If no such value has been set, the +call to pcre_fullinfo() returns the error PCRE_ERROR_UNSET. ++ PCRE_INFO_MAXLOOKBEHIND ++Return the number of characters (NB not data units) in the longest lookbehind +assertion in the pattern. This information is useful when doing multi-segment +matching using the partial matching facilities. Note that the simple assertions +\b and \B require a one-character lookbehind. \A also registers a +one-character lookbehind, though it does not actually inspect the previous +character. This is to ensure that at least one character from the old segment +is retained when a new segment is processed. Otherwise, if there are no +lookbehinds in the pattern, \A might match incorrectly at the start of a new +segment. +PCRE_INFO_MINLENGTHIf the pattern was studied and a minimum length for matching subject strings was computed, its value is returned. Otherwise the returned value is -1. The -value is a number of characters, not bytes (this may be relevant in UTF-8 -mode). The fourth argument should point to an int variable. A -non-negative value is a lower bound to the length of any matching string. There -may not be any strings of that length that do actually match, but every string -that does match is at least that long. +value is a number of characters, which in UTF mode may be different from the +number of data units. The fourth argument should point to an int +variable. A non-negative value is a lower bound to the length of any matching +string. There may not be any strings of that length that do actually match, but +every string that does match is at least that long.PCRE_INFO_NAMECOUNT PCRE_INFO_NAMEENTRYSIZE @@ -1189,26 +1404,32 @@ The map consists of a number of fixed-size entries. PC 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. +entry of the table. This is a pointer to char in the 8-bit library, where +the first two bytes of each entry are the number of the capturing parenthesis, +most significant byte first. In the 16-bit library, the pointer points to +16-bit data units, the first of which contains the parenthesis number. In the +32-bit library, the pointer points to 32-bit data units, the first of which +contains the parenthesis number. The rest of the entry is the corresponding +name, zero terminated.-The flags field is a bitmap that specifies which of the other fields -are set. The flag bits are: +In the 16-bit version of this structure, the mark field has type +"PCRE_UCHAR16 **". +-The names are in alphabetical order. Duplicate names may appear if (?| is used -to create multiple groups with the same number, as described in the +The names are in alphabetical order. If (?| is used to create multiple groups +with the same number, as described in the section on duplicate subpattern numbers in the pcrepattern -page. Duplicate names for subpatterns with different numbers are permitted only -if PCRE_DUPNAMES is set. In all cases of duplicate names, they appear in the -table in the order in which they were found in the pattern. In the absence of -(?| this is the order of increasing number; when (?| is used this is not -necessarily the case because later subpatterns may have lower numbers. +page, the groups may be given the same name, but there is only one entry in the +table. Different names for groups of the same number are not permitted. +Duplicate names for subpatterns with different numbers are permitted, +but only if PCRE_DUPNAMES is set. They appear in the table in the order in +which they were found in the pattern. In the absence of (?| this is the order +of increasing number; when (?| is used this is not necessarily the case because +later subpatterns may have lower numbers.
As a simple example of the name/number table, consider the following pattern -(assume PCRE_EXTENDED is set, so white space - including newlines - is -ignored): +after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white +space - including newlines - is ignored):
(?<date> (?<year>(\d\d)?\d\d) - (?<month>\d\d) - (?<day>\d\d) )@@ -1256,55 +1477,98 @@ alternatives begin with one of the following: For such patterns, the PCRE_ANCHORED bit is set in the options returned by pcre_fullinfo().+ PCRE_INFO_RECURSIONLIMIT ++If the pattern set a recursion limit by including an item of the form +(*LIMIT_RECURSION=nnnn) at the start, the value is returned. The fourth +argument should point to an unsigned 32-bit integer. If no such value has been +set, the call to pcre_fullinfo() returns the error PCRE_ERROR_UNSET. +PCRE_INFO_SIZE-Return the size of the compiled pattern. The fourth argument should point to a -size_t variable. This value does not include the size of the pcre -structure that is returned by pcre_compile(). The value that is passed as -the argument to pcre_malloc() when pcre_compile() is getting memory -in which to place the compiled data is the value returned by this option plus -the size of the pcre structure. Studying a compiled pattern, with or -without JIT, does not alter the value returned by this option. +Return the size of the compiled pattern in bytes (for all three libraries). The +fourth argument should point to a size_t variable. This value does not +include the size of the pcre structure that is returned by +pcre_compile(). The value that is passed as the argument to +pcre_malloc() when pcre_compile() is getting memory in which to +place the compiled data is the value returned by this option plus the size of +the pcre structure. Studying a compiled pattern, with or without JIT, +does not alter the value returned by this option.PCRE_INFO_STUDYSIZE-Return the size of the data block pointed to by the study_data field in a -pcre_extra block. If pcre_extra is NULL, or there is no study data, -zero is returned. The fourth argument should point to a size_t variable. -The study_data field is set by pcre_study() to record information -that will speed up matching (see the section entitled +Return the size in bytes (for all three libraries) of the data block pointed to +by the study_data field in a pcre_extra block. If pcre_extra +is NULL, or there is no study data, zero is returned. The fourth argument +should point to a size_t variable. The study_data field is set by +pcre_study() to record information that will speed up matching (see the +section entitled "Studying a pattern" above). The format of the study_data block is private, but its length is made available via this option so that it can be saved and restored (see the pcreprecompile documentation for details). ++ PCRE_INFO_FIRSTCHARACTERFLAGS ++Return information about the first data unit of any matched string, for a +non-anchored pattern. The fourth argument should point to an int +variable. -
OBSOLETE INFO FUNCTION
-int pcre_info(const pcre *code, int *optptr, int -*firstcharptr); +If there is a fixed first value, for example, the letter "c" from a pattern +such as (cat|cow|coyote), 1 is returned, and the character value can be +retrieved using PCRE_INFO_FIRSTCHARACTER.
-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: +If there is no fixed first value, and 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), +
+
+2 is returned, indicating that the pattern matches only at the start of a +subject string or after any newline within the string. Otherwise 0 is +returned. For anchored patterns, 0 is returned.- PCRE_ERROR_NULL the argument code was NULL - PCRE_ERROR_BADMAGIC the "magic number" was not found + PCRE_INFO_FIRSTCHARACTER-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). +Return the fixed first character value in the situation where +PCRE_INFO_FIRSTCHARACTERFLAGS returns 1; otherwise return 0. The fourth +argument should point to an uint_t variable.-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). +In the 8-bit library, the value is always less than 256. In the 16-bit library +the value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value +can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode. +
+ PCRE_INFO_REQUIREDCHARFLAGS ++Returns 1 if there is a rightmost literal data unit that must exist in any +matched string, other than at its start. The fourth argument should point to +an int variable. If there is no such value, 0 is returned. If returning +1, the character value itself can be retrieved using PCRE_INFO_REQUIREDCHAR. -
REFERENCE COUNTS
+For anchored patterns, a last literal value is recorded only if it follows +something of variable length. For example, for the pattern /^a\d+z\d+/ the +returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for +/^a\dz\d/ the returned value is 0. +
+ PCRE_INFO_REQUIREDCHAR ++Return the value of the rightmost literal data unit that must exist in any +matched string, other than at its start, if such a value has been recorded. The +fourth argument should point to an uint32_t variable. If there is no such +value, 0 is returned. + +
REFERENCE COUNTS
+int pcre_refcount(pcre *code, int adjust);
@@ -1327,11 +1591,11 @@ Except when it is zero, the reference count is not cor pattern is compiled on one host and then transferred to a host whose byte-order is different. (This seems a highly unlikely scenario.)
-
MATCHING A PATTERN: THE TRADITIONAL FUNCTION
+
MATCHING A PATTERN: THE TRADITIONAL FUNCTION
int pcre_exec(const pcre *code, const pcre_extra *extra, -const char *subject, int length, int startoffset, -int options, int *ovector, int ovecsize); + 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 @@ -1392,22 +1656,30 @@ fields (not necessarily in this order): const unsigned char *tables; unsigned char **mark;
+
+In the 32-bit version of this structure, the mark field has type +"PCRE_UCHAR32 **". + ++The flags field is used to specify which of the other fields are set. The +flag bits are:
- PCRE_EXTRA_STUDY_DATA + PCRE_EXTRA_CALLOUT_DATA PCRE_EXTRA_EXECUTABLE_JIT + PCRE_EXTRA_MARK PCRE_EXTRA_MATCH_LIMIT PCRE_EXTRA_MATCH_LIMIT_RECURSION - PCRE_EXTRA_CALLOUT_DATA + PCRE_EXTRA_STUDY_DATA PCRE_EXTRA_TABLES - PCRE_EXTRA_MARKOther flag bits should be set to zero. The study_data field and sometimes the executable_jit field are set in the pcre_extra block that is returned by pcre_study(), together with the appropriate flag bits. You -should not set these yourself, but you may add to the block by setting the -other fields and their corresponding flag bits. +should not set these yourself, but you may add to the block by setting other +fields and their corresponding flag bits.The match_limit field provides a means of preventing PCRE from using up a @@ -1425,11 +1697,10 @@ in the subject string.
When pcre_exec() is called with a pattern that was successfully studied -with the PCRE_STUDY_JIT_COMPILE option, the way that the matching is executed -is entirely different. However, there is still the possibility of runaway -matching that goes on for a very long time, and so the match_limit value -is also used in this case (but in a different way) to limit how long the -matching can continue. +with a JIT option, the way that the matching is executed is entirely different. +However, there is still the possibility of runaway matching that goes on for a +very long time, and so the match_limit value is also used in this case +(but in a different way) to limit how long the matching can continue.
The default value for the limit can be set when PCRE is built; the default @@ -1440,6 +1711,16 @@ the flags field. If the limit is exceeded, p PCRE_ERROR_MATCHLIMIT.
+A value for the match limit may also be supplied by an item at the start of a +pattern of the form +
+ (*LIMIT_MATCH=d) ++where d is a decimal number. However, such a setting is ignored unless d is +less than the limit set by the caller of pcre_exec() or, if no such limit +is set, less than the default. + +The match_limit_recursion field is similar to match_limit, but instead of limiting the total number of times that match() is called, it limits the depth of recursion. The recursion depth is a smaller number than the @@ -1450,8 +1731,7 @@ This limit is of use only if it is set smaller than
The default value for match_limit_recursion can be set when PCRE is @@ -1462,33 +1742,48 @@ PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the flag is exceeded, pcre_exec() returns PCRE_ERROR_RECURSIONLIMIT.
+A value for the recursion limit may also be supplied by an item at the start of +a pattern of the form +
+ (*LIMIT_RECURSION=d) ++where d is a decimal number. However, such a setting is ignored unless d is +less than the limit set by the caller of pcre_exec() or, if no such limit +is set, less than the default. + +The callout_data field is used in conjunction with the "callout" feature, and is described in the pcrecallout documentation.
-The tables field is used to pass a character tables pointer to -pcre_exec(); this overrides the value that is stored with the compiled -pattern. A non-NULL value is stored with the compiled pattern only if custom -tables were supplied to pcre_compile() via its tableptr argument. -If NULL is passed to pcre_exec() using this mechanism, it forces PCRE's -internal tables to be used. This facility is helpful when re-using patterns -that have been saved after compiling with an external set of tables, because -the external tables might be at a different address when pcre_exec() is -called. See the +The tables field is provided for use with patterns that have been +pre-compiled using custom character tables, saved to disc or elsewhere, and +then reloaded, because the tables that were used to compile a pattern are not +saved with it. See the pcreprecompile -documentation for a discussion of saving compiled patterns for later use. +documentation for a discussion of saving compiled patterns for later use. If +NULL is passed using this mechanism, it forces PCRE's internal tables to be +used.
+Warning: The tables that pcre_exec() uses must be the same as those +that were used when the pattern was compiled. If this is not the case, the +behaviour of pcre_exec() is undefined. Therefore, when a pattern is +compiled and matched in the same process, this field should never be set. In +this (the most common) case, the correct table pointer is automatically passed +with the compiled pattern from pcre_compile() to pcre_exec(). +
+If PCRE_EXTRA_MARK is set in the flags field, the mark field must -be set to point to a char * variable. If the pattern contains any +be set to point to a suitable variable. If the pattern contains any backtracking control verbs such as (*MARK:NAME), and the execution ends up with a name to pass back, a pointer to the name string (zero terminated) is placed in the variable pointed to by the mark field. The names are within the compiled pattern; if you wish to retain such a name you must copy it before freeing the memory of a compiled pattern. If there is no name to pass back, the -variable pointed to by the mark field set to NULL. For details of the +variable pointed to by the mark field is set to NULL. For details of the backtracking control verbs, see the section entitled "Backtracking control" in the @@ -1502,16 +1797,16 @@ Option bits for pcre_exec() The unused bits of the options argument for pcre_exec() must be zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_xxx, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART, -PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and -PCRE_PARTIAL_HARD. +PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and +PCRE_PARTIAL_SOFT.
-If the pattern was successfully studied with the PCRE_STUDY_JIT_COMPILE option, -the only supported options for JIT execution are PCRE_NO_UTF8_CHECK, -PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, and PCRE_NOTEMPTY_ATSTART. Note in -particular that partial matching is not supported. If an unsupported option is -used, JIT execution is disabled and the normal interpretive code in -pcre_exec() is run. +If the pattern was successfully studied with one of the just-in-time (JIT) +compile options, the only supported options for JIT execution are +PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, +PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an +unsupported option is used, JIT execution is disabled and the normal +interpretive code in pcre_exec() is run.
PCRE_ANCHORED@@ -1623,10 +1918,10 @@ unanchored match must start with a specific character, for that character, and fails immediately if it cannot find it, without actually running the main matching function. This means that a special item such as (*COMMIT) at the start of a pattern is not considered until after a -suitable starting point for the match has been found. When callouts or (*MARK) -items are in use, these "start-up" optimizations can cause them to be skipped -if the pattern is never actually used. The start-up optimizations are in effect -a pre-scan of the subject that takes place before the pattern is run. +suitable starting point for the match has been found. Also, when callouts or +(*MARK) items are in use, these "start-up" optimizations can cause them to be +skipped if the pattern is never actually used. The start-up optimizations are +in effect a pre-scan of the subject that takes place before the pattern is run.The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly @@ -1634,7 +1929,9 @@ causing performance to suffer, but ensuring that in ca "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK) are considered at every possible starting position in the subject string. If PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching -time. +time. The use of PCRE_NO_START_OPTIMIZE at matching time (that is, passing it +to pcre_exec()) disables JIT execution; in this situation, matching is +always done using interpretively.
Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation. @@ -1668,18 +1965,18 @@ returned.
PCRE_PARTIAL_HARD PCRE_PARTIAL_SOFT @@ -1728,15 +2025,21 @@ The string to be matched by pcre_exec()The first byte of a character has the value 0xfe or 0xff. These values can never occur in a valid UTF-8 string. +
The subject string is passed to pcre_exec() as a pointer in -subject, a length (in bytes) in length, and a starting byte offset -in startoffset. If this is negative or greater than the length of the -subject, pcre_exec() returns PCRE_ERROR_BADOFFSET. 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. In UTF-8 mode, the byte offset must -point to the start of a UTF-8 character (or the end of the subject). Unlike the -pattern string, the subject may contain binary zero bytes. +subject, a length in length, and a starting offset in +startoffset. The units for length and startoffset are bytes +for the 8-bit library, 16-bit data items for the 16-bit library, and 32-bit +data items for the 32-bit library.
+If startoffset is negative or greater than the length of the subject, +pcre_exec() returns PCRE_ERROR_BADOFFSET. 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. In UTF-8 or UTF-16 mode, the offset must point +to the start of a character, or the end of the subject (in UTF-32 mode, one +data unit equals one character, so all offsets are valid). Unlike the pattern +string, the subject may contain binary zeroes. +
+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 @@ -1802,10 +2105,12 @@ rounded down. When a match is 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 -each pair is set to the byte offset of the first character in a substring, and -the second is set to the byte offset of the first character after the end of a -substring. Note: these values are always byte offsets, even in UTF-8 -mode. They are not character counts. +each 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. These values are always data unit offsets, even in UTF mode. They +are byte offsets in the 8-bit library, 16-bit data item offsets in the 16-bit +library, and 32-bit data item offsets in the 32-bit library. Note: they +are not character counts.
The first pair of integers, ovector[0] and ovector[1], identify the @@ -1823,7 +2128,7 @@ string that it matched that is returned.
If the vector is too small to hold all the captured substring offsets, it is used as far as possible (up to two-thirds of its length), and the function -returns a value of zero. If neither the actual string matched not any captured +returns a value of zero. If neither the actual string matched nor any captured substrings are 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 is not big enough to remember the related @@ -2022,19 +2327,53 @@ time.
PCRE_ERROR_JIT_STACKLIMIT (-27)-This error is returned when a pattern that was successfully studied using the -PCRE_STUDY_JIT_COMPILE option is being matched, but the memory available for -the just-in-time processing stack is not large enough. See the +This error is returned when a pattern that was successfully studied using a +JIT compile option is being matched, but the memory available for the +just-in-time processing stack is not large enough. See the pcrejit documentation for more details. ++ PCRE_ERROR_BADMODE (-28) ++This error is given if a pattern that was compiled by the 8-bit library is +passed to a 16-bit or 32-bit library function, or vice versa. ++ PCRE_ERROR_BADENDIANNESS (-29) ++This error is given if a pattern that was compiled and saved is reloaded on a +host with different endianness. The utility function +pcre_pattern_to_host_byte_order() can be used to convert such a pattern +so that it runs on the new host. ++ PCRE_ERROR_JIT_BADOPTION ++This error is returned when a pattern that was successfully studied using a JIT +compile option is being matched, but the matching mode (partial or complete +match) does not correspond to any JIT compilation mode. When the JIT fast path +function is used, this error may be also given for invalid options. See the +pcrejit +documentation for more details. ++ PCRE_ERROR_BADLENGTH (-32) ++This error is given if pcre_exec() is called with a negative value for +the length argument.-Error numbers -16 to -20 and -22 are not used by pcre_exec(). +Error numbers -16 to -20, -22, and 30 are not used by pcre_exec().
Reason codes for invalid UTF-8 strings
+This section applies only to the 8-bit library. The corresponding information +for the 16-bit and 32-bit libraries is given in the +pcre16 +and +pcre32 +pages. +
+When pcre_exec() returns either PCRE_ERROR_BADUTF8 or PCRE_ERROR_SHORTUTF8, and the size of the output vector (ovecsize) is at least 2, the offset of the start of the invalid UTF-8 character is placed in @@ -2103,21 +2442,28 @@ character.
+ PCRE_UTF8_ERR22 ++This error code was formerly used when the presence of a so-called +"non-character" caused an error. Unicode corrigendum #9 makes it clear that +such characters should not cause a string to be rejected, and so this code is +no longer in use and is never returned. -
EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
+
EXTRACTING CAPTURED SUBSTRINGS BY NUMBER
int pcre_copy_substring(const char *subject, int *ovector, -int stringcount, int stringnumber, char *buffer, -int buffersize); -
-+ 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 stringcount, int stringnumber, + const char **stringptr); +
+
int pcre_get_substring_list(const char *subject, -int *ovector, int stringcount, const char ***listptr); + int *ovector, int stringcount, const char ***listptr);Captured substrings can be accessed directly by using the offsets returned by @@ -2199,22 +2545,22 @@ linked via a special interface to another programming pcre_free directly; it is for these cases that the functions are provided.
-
EXTRACTING CAPTURED SUBSTRINGS BY NAME
+
EXTRACTING CAPTURED SUBSTRINGS BY NAME
int pcre_get_stringnumber(const pcre *code, -const char *name); -
-+ const char *name); +
-
+
int pcre_copy_named_substring(const pcre *code, -const char *subject, int *ovector, -int stringcount, const char *stringname, -char *buffer, int buffersize); -+ const char *subject, int *ovector, + int stringcount, const char *stringname, + 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); + 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. @@ -2263,10 +2609,10 @@ names are not included in the compiled code. The match numbers. For this reason, the use of different names for subpatterns of the same number causes an error at compile time.
-
DUPLICATE SUBPATTERN NAMES
+
DUPLICATE SUBPATTERN NAMES
int pcre_get_stringtable_entries(const pcre *code, -const char *name, char **first, char **last); + const char *name, char **first, char **last);
When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns @@ -2301,7 +2647,7 @@ described above in the section entitled Information Given all the relevant entries for the name, you can extract each of their numbers, and hence the captured data, if any.
-
FINDING ALL POSSIBLE MATCHES
+
FINDING ALL POSSIBLE MATCHES
The traditional matching function uses a similar algorithm to Perl, which stops when it finds the first match, starting at a given point in the subject. If you @@ -2319,13 +2665,37 @@ When your callout function is called, extract and save substring. Then return 1, which forces pcre_exec() to backtrack and try other alternatives. Ultimately, when it runs out of matches, pcre_exec() will yield PCRE_ERROR_NOMATCH. +
+
OBTAINING AN ESTIMATE OF STACK USAGE
++Matching certain patterns using pcre_exec() can use a lot of process +stack, which in certain environments can be rather limited in size. Some users +find it helpful to have an estimate of the amount of stack that is used by +pcre_exec(), to help them set recursion limits, as described in the +pcrestack +documentation. The estimate that is output by pcretest when called with +the -m and -C options is obtained by calling pcre_exec with +the values NULL, NULL, NULL, -999, and -999 for its first five arguments. +
++Normally, if its first argument is NULL, pcre_exec() immediately returns +the negative error code PCRE_ERROR_NULL, but with this special combination of +arguments, it returns instead a negative number whose absolute value is the +approximate stack frame size in bytes. (A negative number is used so that it is +clear that no match has happened.) The value is approximate because in some +cases, recursive calls to pcre_exec() occur when there are one or two +additional variables on the stack. +
++If PCRE has been compiled to use the heap instead of the stack for recursion, +the value returned is the size of each block that is obtained from the heap.
-
MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
+
MATCHING A PATTERN: THE ALTERNATIVE FUNCTION
int pcre_dfa_exec(const pcre *code, const pcre_extra *extra, -const char *subject, int length, int startoffset, -int options, int *ovector, int ovecsize, -int *workspace, int wscount); + const char *subject, int length, int startoffset, + int options, int *ovector, int ovecsize, + int *workspace, int wscount);
The function pcre_dfa_exec() is called to match a subject string against @@ -2454,6 +2824,15 @@ matching string is given first. If there were too many the longest matches. Unlike pcre_exec(), pcre_dfa_exec() can use the entire ovector for returning matched strings.
++NOTE: PCRE's "auto-possessification" optimization usually applies to character +repeats at the end of a pattern (as well as internally). For example, the +pattern "a\d+" is compiled as if it were "a\d++" because there is no point +even considering the possibility of backtracking into the repeated digits. For +DFA matching, this means that only one possible match is found. If you really +do want multiple matches in such cases, either use an ungreedy repeat +("a\d+?") or set the PCRE_NO_AUTO_POSSESS option when compiling. +
Error returns from pcre_dfa_exec()
@@ -2494,14 +2873,22 @@ When a recursive subpattern is processed, the matching recursively, using private vectors for ovector and workspace. This error is given if the output vector is not large enough. This should be extremely rare, as a vector of size 1000 is used. ++ PCRE_ERROR_DFA_BADRESTART (-30) ++When pcre_dfa_exec() is called with the PCRE_DFA_RESTART option, +some plausibility checks are made on the contents of the workspace, which +should contain data about the previous partial match. If any of these checks +fail, this error is given. -
SEE ALSO
+
SEE ALSO
-pcrebuild(3), pcrecallout(3), pcrecpp(3)(3), -pcrematching(3), pcrepartial(3), pcreposix(3), -pcreprecompile(3), pcresample(3), pcrestack(3). +pcre16(3), pcre32(3), pcrebuild(3), pcrecallout(3), +pcrecpp(3)(3), pcrematching(3), pcrepartial(3), +pcreposix(3), pcreprecompile(3), pcresample(3), +pcrestack(3).
-
AUTHOR
+
AUTHOR
Philip Hazel
-
@@ -2510,11 +2897,11 @@ University Computing Service Cambridge CB2 3QH, England.
REVISION
+
REVISION
-Last updated: 02 December 2011 +Last updated: 12 November 2013
-Copyright © 1997-2011 University of Cambridge. +Copyright © 1997-2013 University of Cambridge.
Return to the PCRE index page.