3 <title>pcreapi specification</title>
5 <body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
6 <h1>pcreapi man page</h1>
8 Return to the <a href="index.html">PCRE index page</a>.
11 This page is part of the PCRE HTML documentation. It was generated automatically
12 from the original man page. If there is any nonsense in it, please consult the
13 man page, in case the conversion went wrong.
16 <li><a name="TOC1" href="#SEC1">PCRE NATIVE API BASIC FUNCTIONS</a>
17 <li><a name="TOC2" href="#SEC2">PCRE NATIVE API STRING EXTRACTION FUNCTIONS</a>
18 <li><a name="TOC3" href="#SEC3">PCRE NATIVE API AUXILIARY FUNCTIONS</a>
19 <li><a name="TOC4" href="#SEC4">PCRE NATIVE API INDIRECTED FUNCTIONS</a>
20 <li><a name="TOC5" href="#SEC5">PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a>
21 <li><a name="TOC6" href="#SEC6">PCRE API OVERVIEW</a>
22 <li><a name="TOC7" href="#SEC7">NEWLINES</a>
23 <li><a name="TOC8" href="#SEC8">MULTITHREADING</a>
24 <li><a name="TOC9" href="#SEC9">SAVING PRECOMPILED PATTERNS FOR LATER USE</a>
25 <li><a name="TOC10" href="#SEC10">CHECKING BUILD-TIME OPTIONS</a>
26 <li><a name="TOC11" href="#SEC11">COMPILING A PATTERN</a>
27 <li><a name="TOC12" href="#SEC12">COMPILATION ERROR CODES</a>
28 <li><a name="TOC13" href="#SEC13">STUDYING A PATTERN</a>
29 <li><a name="TOC14" href="#SEC14">LOCALE SUPPORT</a>
30 <li><a name="TOC15" href="#SEC15">INFORMATION ABOUT A PATTERN</a>
31 <li><a name="TOC16" href="#SEC16">REFERENCE COUNTS</a>
32 <li><a name="TOC17" href="#SEC17">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a>
33 <li><a name="TOC18" href="#SEC18">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a>
34 <li><a name="TOC19" href="#SEC19">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a>
35 <li><a name="TOC20" href="#SEC20">DUPLICATE SUBPATTERN NAMES</a>
36 <li><a name="TOC21" href="#SEC21">FINDING ALL POSSIBLE MATCHES</a>
37 <li><a name="TOC22" href="#SEC22">OBTAINING AN ESTIMATE OF STACK USAGE</a>
38 <li><a name="TOC23" href="#SEC23">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a>
39 <li><a name="TOC24" href="#SEC24">SEE ALSO</a>
40 <li><a name="TOC25" href="#SEC25">AUTHOR</a>
41 <li><a name="TOC26" href="#SEC26">REVISION</a>
44 <b>#include <pcre.h></b>
46 <br><a name="SEC1" href="#TOC1">PCRE NATIVE API BASIC FUNCTIONS</a><br>
48 <b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b>
49 <b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
50 <b> const unsigned char *<i>tableptr</i>);</b>
53 <b>pcre *pcre_compile2(const char *<i>pattern</i>, int <i>options</i>,</b>
54 <b> int *<i>errorcodeptr</i>,</b>
55 <b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
56 <b> const unsigned char *<i>tableptr</i>);</b>
59 <b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b>
60 <b> const char **<i>errptr</i>);</b>
63 <b>void pcre_free_study(pcre_extra *<i>extra</i>);</b>
66 <b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
67 <b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
68 <b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b>
71 <b>int pcre_dfa_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
72 <b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
73 <b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
74 <b> int *<i>workspace</i>, int <i>wscount</i>);</b>
76 <br><a name="SEC2" href="#TOC1">PCRE NATIVE API STRING EXTRACTION FUNCTIONS</a><br>
78 <b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b>
79 <b> const char *<i>subject</i>, int *<i>ovector</i>,</b>
80 <b> int <i>stringcount</i>, const char *<i>stringname</i>,</b>
81 <b> char *<i>buffer</i>, int <i>buffersize</i>);</b>
84 <b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
85 <b> int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b>
86 <b> int <i>buffersize</i>);</b>
89 <b>int pcre_get_named_substring(const pcre *<i>code</i>,</b>
90 <b> const char *<i>subject</i>, int *<i>ovector</i>,</b>
91 <b> int <i>stringcount</i>, const char *<i>stringname</i>,</b>
92 <b> const char **<i>stringptr</i>);</b>
95 <b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b>
96 <b> const char *<i>name</i>);</b>
99 <b>int pcre_get_stringtable_entries(const pcre *<i>code</i>,</b>
100 <b> const char *<i>name</i>, char **<i>first</i>, char **<i>last</i>);</b>
103 <b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
104 <b> int <i>stringcount</i>, int <i>stringnumber</i>,</b>
105 <b> const char **<i>stringptr</i>);</b>
108 <b>int pcre_get_substring_list(const char *<i>subject</i>,</b>
109 <b> int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b>
112 <b>void pcre_free_substring(const char *<i>stringptr</i>);</b>
115 <b>void pcre_free_substring_list(const char **<i>stringptr</i>);</b>
117 <br><a name="SEC3" href="#TOC1">PCRE NATIVE API AUXILIARY FUNCTIONS</a><br>
119 <b>int pcre_jit_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
120 <b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
121 <b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
122 <b> pcre_jit_stack *<i>jstack</i>);</b>
125 <b>pcre_jit_stack *pcre_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b>
128 <b>void pcre_jit_stack_free(pcre_jit_stack *<i>stack</i>);</b>
131 <b>void pcre_assign_jit_stack(pcre_extra *<i>extra</i>,</b>
132 <b> pcre_jit_callback <i>callback</i>, void *<i>data</i>);</b>
135 <b>const unsigned char *pcre_maketables(void);</b>
138 <b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
139 <b> int <i>what</i>, void *<i>where</i>);</b>
142 <b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b>
145 <b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b>
148 <b>const char *pcre_version(void);</b>
151 <b>int pcre_pattern_to_host_byte_order(pcre *<i>code</i>,</b>
152 <b> pcre_extra *<i>extra</i>, const unsigned char *<i>tables</i>);</b>
154 <br><a name="SEC4" href="#TOC1">PCRE NATIVE API INDIRECTED FUNCTIONS</a><br>
156 <b>void *(*pcre_malloc)(size_t);</b>
159 <b>void (*pcre_free)(void *);</b>
162 <b>void *(*pcre_stack_malloc)(size_t);</b>
165 <b>void (*pcre_stack_free)(void *);</b>
168 <b>int (*pcre_callout)(pcre_callout_block *);</b>
171 <b>int (*pcre_stack_guard)(void);</b>
173 <br><a name="SEC5" href="#TOC1">PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a><br>
175 As well as support for 8-bit character strings, PCRE also supports 16-bit
176 strings (from release 8.30) and 32-bit strings (from release 8.32), by means of
177 two additional libraries. They can be built as well as, or instead of, the
178 8-bit library. To avoid too much complication, this document describes the
179 8-bit versions of the functions, with only occasional references to the 16-bit
180 and 32-bit libraries.
183 The 16-bit and 32-bit functions operate in the same way as their 8-bit
184 counterparts; they just use different data types for their arguments and
185 results, and their names start with <b>pcre16_</b> or <b>pcre32_</b> instead of
186 <b>pcre_</b>. For every option that has UTF8 in its name (for example,
187 PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 replaced
188 by UTF16 or UTF32, respectively. This facility is in fact just cosmetic; the
189 16-bit and 32-bit option names define the same bit values.
192 References to bytes and UTF-8 in this document should be read as references to
193 16-bit data units and UTF-16 when using the 16-bit library, or 32-bit data
194 units and UTF-32 when using the 32-bit library, unless specified otherwise.
195 More details of the specific differences for the 16-bit and 32-bit libraries
197 <a href="pcre16.html"><b>pcre16</b></a>
199 <a href="pcre32.html"><b>pcre32</b></a>
202 <br><a name="SEC6" href="#TOC1">PCRE API OVERVIEW</a><br>
204 PCRE has its own native API, which is described in this document. There are
205 also some wrapper functions (for the 8-bit library only) that correspond to the
206 POSIX regular expression API, but they do not give access to all the
207 functionality. They are described in the
208 <a href="pcreposix.html"><b>pcreposix</b></a>
209 documentation. Both of these APIs define a set of C function calls. A C++
210 wrapper (again for the 8-bit library only) is also distributed with PCRE. It is
212 <a href="pcrecpp.html"><b>pcrecpp</b></a>
216 The native API C function prototypes are defined in the header file
217 <b>pcre.h</b>, and on Unix-like systems the (8-bit) library itself is called
218 <b>libpcre</b>. It can normally be accessed by adding <b>-lpcre</b> to the
219 command for linking an application that uses PCRE. The header file defines the
220 macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release numbers
221 for the library. Applications can use these to include support for different
225 In a Windows environment, if you want to statically link an application program
226 against a non-dll <b>pcre.a</b> file, you must define PCRE_STATIC before
227 including <b>pcre.h</b> or <b>pcrecpp.h</b>, because otherwise the
228 <b>pcre_malloc()</b> and <b>pcre_free()</b> exported functions will be declared
229 <b>__declspec(dllimport)</b>, with unwanted results.
232 The functions <b>pcre_compile()</b>, <b>pcre_compile2()</b>, <b>pcre_study()</b>,
233 and <b>pcre_exec()</b> are used for compiling and matching regular expressions
234 in a Perl-compatible manner. A sample program that demonstrates the simplest
235 way of using them is provided in the file called <i>pcredemo.c</i> in the PCRE
236 source distribution. A listing of this program is given in the
237 <a href="pcredemo.html"><b>pcredemo</b></a>
238 documentation, and the
239 <a href="pcresample.html"><b>pcresample</b></a>
240 documentation describes how to compile and run it.
243 Just-in-time compiler support is an optional feature of PCRE that can be built
244 in appropriate hardware environments. It greatly speeds up the matching
245 performance of many patterns. Simple programs can easily request that it be
246 used if available, by setting an option that is ignored when it is not
247 relevant. More complicated programs might need to make use of the functions
248 <b>pcre_jit_stack_alloc()</b>, <b>pcre_jit_stack_free()</b>, and
249 <b>pcre_assign_jit_stack()</b> in order to control the JIT code's memory usage.
252 From release 8.32 there is also a direct interface for JIT execution, which
253 gives improved performance. The JIT-specific functions are discussed in the
254 <a href="pcrejit.html"><b>pcrejit</b></a>
258 A second matching function, <b>pcre_dfa_exec()</b>, which is not
259 Perl-compatible, is also provided. This uses a different algorithm for the
260 matching. The alternative algorithm finds all possible matches (at a given
261 point in the subject), and scans the subject just once (unless there are
262 lookbehind assertions). However, this algorithm does not return captured
263 substrings. A description of the two matching algorithms and their advantages
264 and disadvantages is given in the
265 <a href="pcrematching.html"><b>pcrematching</b></a>
269 In addition to the main compiling and matching functions, there are convenience
270 functions for extracting captured substrings from a subject string that is
271 matched by <b>pcre_exec()</b>. They are:
273 <b>pcre_copy_substring()</b>
274 <b>pcre_copy_named_substring()</b>
275 <b>pcre_get_substring()</b>
276 <b>pcre_get_named_substring()</b>
277 <b>pcre_get_substring_list()</b>
278 <b>pcre_get_stringnumber()</b>
279 <b>pcre_get_stringtable_entries()</b>
281 <b>pcre_free_substring()</b> and <b>pcre_free_substring_list()</b> are also
282 provided, to free the memory used for extracted strings.
285 The function <b>pcre_maketables()</b> is used to build a set of character tables
286 in the current locale for passing to <b>pcre_compile()</b>, <b>pcre_exec()</b>,
287 or <b>pcre_dfa_exec()</b>. This is an optional facility that is provided for
288 specialist use. Most commonly, no special tables are passed, in which case
289 internal tables that are generated when PCRE is built are used.
292 The function <b>pcre_fullinfo()</b> is used to find out information about a
293 compiled pattern. The function <b>pcre_version()</b> returns a pointer to a
294 string containing the version of PCRE and its date of release.
297 The function <b>pcre_refcount()</b> maintains a reference count in a data block
298 containing a compiled pattern. This is provided for the benefit of
299 object-oriented applications.
302 The global variables <b>pcre_malloc</b> and <b>pcre_free</b> initially contain
303 the entry points of the standard <b>malloc()</b> and <b>free()</b> functions,
304 respectively. PCRE calls the memory management functions via these variables,
305 so a calling program can replace them if it wishes to intercept the calls. This
306 should be done before calling any PCRE functions.
309 The global variables <b>pcre_stack_malloc</b> and <b>pcre_stack_free</b> are also
310 indirections to memory management functions. These special functions are used
311 only when PCRE is compiled to use the heap for remembering data, instead of
312 recursive function calls, when running the <b>pcre_exec()</b> function. See the
313 <a href="pcrebuild.html"><b>pcrebuild</b></a>
314 documentation for details of how to do this. It is a non-standard way of
315 building PCRE, for use in environments that have limited stacks. Because of the
316 greater use of memory management, it runs more slowly. Separate functions are
317 provided so that special-purpose external code can be used for this case. When
318 used, these functions are always called in a stack-like manner (last obtained,
319 first freed), and always for memory blocks of the same size. There is a
320 discussion about PCRE's stack usage in the
321 <a href="pcrestack.html"><b>pcrestack</b></a>
325 The global variable <b>pcre_callout</b> initially contains NULL. It can be set
326 by the caller to a "callout" function, which PCRE will then call at specified
327 points during a matching operation. Details are given in the
328 <a href="pcrecallout.html"><b>pcrecallout</b></a>
332 The global variable <b>pcre_stack_guard</b> initially contains NULL. It can be
333 set by the caller to a function that is called by PCRE whenever it starts
334 to compile a parenthesized part of a pattern. When parentheses are nested, PCRE
335 uses recursive function calls, which use up the system stack. This function is
336 provided so that applications with restricted stacks can force a compilation
337 error if the stack runs out. The function should return zero if all is well, or
338 non-zero to force an error.
339 <a name="newlines"></a></P>
340 <br><a name="SEC7" href="#TOC1">NEWLINES</a><br>
342 PCRE supports five different conventions for indicating line breaks in
343 strings: a single CR (carriage return) character, a single LF (linefeed)
344 character, the two-character sequence CRLF, any of the three preceding, or any
345 Unicode newline sequence. The Unicode newline sequences are the three just
346 mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed,
347 U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
348 (paragraph separator, U+2029).
351 Each of the first three conventions is used by at least one operating system as
352 its standard newline sequence. When PCRE is built, a default can be specified.
353 The default default is LF, which is the Unix standard. When PCRE is run, the
354 default can be overridden, either when a pattern is compiled, or when it is
358 At compile time, the newline convention can be specified by the <i>options</i>
359 argument of <b>pcre_compile()</b>, or it can be specified by special text at the
360 start of the pattern itself; this overrides any other settings. See the
361 <a href="pcrepattern.html"><b>pcrepattern</b></a>
362 page for details of the special character sequences.
365 In the PCRE documentation the word "newline" is used to mean "the character or
366 pair of characters that indicate a line break". The choice of newline
367 convention affects the handling of the dot, circumflex, and dollar
368 metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
369 recognized line ending sequence, the match position advancement for a
370 non-anchored pattern. There is more detail about this in the
371 <a href="#execoptions">section on <b>pcre_exec()</b> options</a>
375 The choice of newline convention does not affect the interpretation of
376 the \n or \r escape sequences, nor does it affect what \R matches, which is
377 controlled in a similar way, but by separate options.
379 <br><a name="SEC8" href="#TOC1">MULTITHREADING</a><br>
381 The PCRE functions can be used in multi-threading applications, with the
382 proviso that the memory management functions pointed to by <b>pcre_malloc</b>,
383 <b>pcre_free</b>, <b>pcre_stack_malloc</b>, and <b>pcre_stack_free</b>, and the
384 callout and stack-checking functions pointed to by <b>pcre_callout</b> and
385 <b>pcre_stack_guard</b>, are shared by all threads.
388 The compiled form of a regular expression is not altered during matching, so
389 the same compiled pattern can safely be used by several threads at once.
392 If the just-in-time optimization feature is being used, it needs separate
393 memory stack areas for each thread. See the
394 <a href="pcrejit.html"><b>pcrejit</b></a>
395 documentation for more details.
397 <br><a name="SEC9" href="#TOC1">SAVING PRECOMPILED PATTERNS FOR LATER USE</a><br>
399 The compiled form of a regular expression can be saved and re-used at a later
400 time, possibly by a different program, and even on a host other than the one on
401 which it was compiled. Details are given in the
402 <a href="pcreprecompile.html"><b>pcreprecompile</b></a>
403 documentation, which includes a description of the
404 <b>pcre_pattern_to_host_byte_order()</b> function. However, compiling a regular
405 expression with one version of PCRE for use with a different version is not
406 guaranteed to work and may cause crashes.
408 <br><a name="SEC10" href="#TOC1">CHECKING BUILD-TIME OPTIONS</a><br>
410 <b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b>
413 The function <b>pcre_config()</b> makes it possible for a PCRE client to
414 discover which optional features have been compiled into the PCRE library. The
415 <a href="pcrebuild.html"><b>pcrebuild</b></a>
416 documentation has more details about these optional features.
419 The first argument for <b>pcre_config()</b> is an integer, specifying which
420 information is required; the second argument is a pointer to a variable into
421 which the information is placed. The returned value is zero on success, or the
422 negative error code PCRE_ERROR_BADOPTION if the value in the first argument is
423 not recognized. The following information is available:
427 The output is an integer that is set to one if UTF-8 support is available;
428 otherwise it is set to zero. This value should normally be given to the 8-bit
429 version of this function, <b>pcre_config()</b>. If it is given to the 16-bit
430 or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
434 The output is an integer that is set to one if UTF-16 support is available;
435 otherwise it is set to zero. This value should normally be given to the 16-bit
436 version of this function, <b>pcre16_config()</b>. If it is given to the 8-bit
437 or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
441 The output is an integer that is set to one if UTF-32 support is available;
442 otherwise it is set to zero. This value should normally be given to the 32-bit
443 version of this function, <b>pcre32_config()</b>. If it is given to the 8-bit
444 or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION.
446 PCRE_CONFIG_UNICODE_PROPERTIES
448 The output is an integer that is set to one if support for Unicode character
449 properties is available; otherwise it is set to zero.
453 The output is an integer that is set to one if support for just-in-time
454 compiling is available; otherwise it is set to zero.
456 PCRE_CONFIG_JITTARGET
458 The output is a pointer to a zero-terminated "const char *" string. If JIT
459 support is available, the string contains the name of the architecture for
460 which the JIT compiler is configured, for example "x86 32bit (little endian +
461 unaligned)". If JIT support is not available, the result is NULL.
465 The output is an integer whose value specifies the default character sequence
466 that is recognized as meaning "newline". The values that are supported in
467 ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for
468 ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the
469 same values. However, the value for LF is normally 21, though some EBCDIC
470 environments use 37. The corresponding values for CRLF are 3349 and 3365. The
471 default should normally correspond to the standard sequence for your operating
476 The output is an integer whose value indicates what character sequences the \R
477 escape sequence matches by default. A value of 0 means that \R matches any
478 Unicode line ending sequence; a value of 1 means that \R matches only CR, LF,
479 or CRLF. The default can be overridden when a pattern is compiled or matched.
481 PCRE_CONFIG_LINK_SIZE
483 The output is an integer that contains the number of bytes used for internal
484 linkage in compiled regular expressions. For the 8-bit library, the value can
485 be 2, 3, or 4. For the 16-bit library, the value is either 2 or 4 and is still
486 a number of bytes. For the 32-bit library, the value is either 2 or 4 and is
487 still a number of bytes. The default value of 2 is sufficient for all but the
488 most massive patterns, since it allows the compiled pattern to be up to 64K in
489 size. Larger values allow larger regular expressions to be compiled, at the
490 expense of slower matching.
492 PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
494 The output is an integer that contains the threshold above which the POSIX
495 interface uses <b>malloc()</b> for output vectors. Further details are given in
497 <a href="pcreposix.html"><b>pcreposix</b></a>
500 PCRE_CONFIG_PARENS_LIMIT
502 The output is a long integer that gives the maximum depth of nesting of
503 parentheses (of any kind) in a pattern. This limit is imposed to cap the amount
504 of system stack used when a pattern is compiled. It is specified when PCRE is
505 built; the default is 250. This limit does not take into account the stack that
506 may already be used by the calling application. For finer control over
507 compilation stack usage, you can set a pointer to an external checking function
508 in <b>pcre_stack_guard</b>.
510 PCRE_CONFIG_MATCH_LIMIT
512 The output is a long integer that gives the default limit for the number of
513 internal matching function calls in a <b>pcre_exec()</b> execution. Further
514 details are given with <b>pcre_exec()</b> below.
516 PCRE_CONFIG_MATCH_LIMIT_RECURSION
518 The output is a long integer that gives the default limit for the depth of
519 recursion when calling the internal matching function in a <b>pcre_exec()</b>
520 execution. Further details are given with <b>pcre_exec()</b> below.
522 PCRE_CONFIG_STACKRECURSE
524 The output is an integer that is set to one if internal recursion when running
525 <b>pcre_exec()</b> is implemented by recursive function calls that use the stack
526 to remember their state. This is the usual way that PCRE is compiled. The
527 output is zero if PCRE was compiled to use blocks of data on the heap instead
528 of recursive function calls. In this case, <b>pcre_stack_malloc</b> and
529 <b>pcre_stack_free</b> are called to manage memory blocks on the heap, thus
530 avoiding the use of the stack.
532 <br><a name="SEC11" href="#TOC1">COMPILING A PATTERN</a><br>
534 <b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b>
535 <b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
536 <b> const unsigned char *<i>tableptr</i>);</b>
539 <b>pcre *pcre_compile2(const char *<i>pattern</i>, int <i>options</i>,</b>
540 <b> int *<i>errorcodeptr</i>,</b>
541 <b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
542 <b> const unsigned char *<i>tableptr</i>);</b>
545 Either of the functions <b>pcre_compile()</b> or <b>pcre_compile2()</b> can be
546 called to compile a pattern into an internal form. The only difference between
547 the two interfaces is that <b>pcre_compile2()</b> has an additional argument,
548 <i>errorcodeptr</i>, via which a numerical error code can be returned. To avoid
549 too much repetition, we refer just to <b>pcre_compile()</b> below, but the
550 information applies equally to <b>pcre_compile2()</b>.
553 The pattern is a C string terminated by a binary zero, and is passed in the
554 <i>pattern</i> argument. A pointer to a single block of memory that is obtained
555 via <b>pcre_malloc</b> is returned. This contains the compiled code and related
556 data. The <b>pcre</b> type is defined for the returned block; this is a typedef
557 for a structure whose contents are not externally defined. It is up to the
558 caller to free the memory (via <b>pcre_free</b>) when it is no longer required.
561 Although the compiled code of a PCRE regex is relocatable, that is, it does not
562 depend on memory location, the complete <b>pcre</b> data block is not
563 fully relocatable, because it may contain a copy of the <i>tableptr</i>
564 argument, which is an address (see below).
567 The <i>options</i> argument contains various bit settings that affect the
568 compilation. It should be zero if no options are required. The available
569 options are described below. Some of them (in particular, those that are
570 compatible with Perl, but some others as well) can also be set and unset from
571 within the pattern (see the detailed description in the
572 <a href="pcrepattern.html"><b>pcrepattern</b></a>
573 documentation). For those options that can be different in different parts of
574 the pattern, the contents of the <i>options</i> argument specifies their
575 settings at the start of compilation and execution. The PCRE_ANCHORED,
576 PCRE_BSR_<i>xxx</i>, PCRE_NEWLINE_<i>xxx</i>, PCRE_NO_UTF8_CHECK, and
577 PCRE_NO_START_OPTIMIZE options can be set at the time of matching as well as at
581 If <i>errptr</i> is NULL, <b>pcre_compile()</b> returns NULL immediately.
582 Otherwise, if compilation of a pattern fails, <b>pcre_compile()</b> returns
583 NULL, and sets the variable pointed to by <i>errptr</i> to point to a textual
584 error message. This is a static string that is part of the library. You must
585 not try to free it. Normally, the offset from the start of the pattern to the
586 data unit that was being processed when the error was discovered is placed in
587 the variable pointed to by <i>erroffset</i>, which must not be NULL (if it is,
588 an immediate error is given). However, for an invalid UTF-8 or UTF-16 string,
589 the offset is that of the first data unit of the failing character.
592 Some errors are not detected until the whole pattern has been scanned; in these
593 cases, the offset passed back is the length of the pattern. Note that the
594 offset is in data units, not characters, even in a UTF mode. It may sometimes
595 point into the middle of a UTF-8 or UTF-16 character.
598 If <b>pcre_compile2()</b> is used instead of <b>pcre_compile()</b>, and the
599 <i>errorcodeptr</i> argument is not NULL, a non-zero error code number is
600 returned via this argument in the event of an error. This is in addition to the
601 textual error message. Error codes and messages are listed below.
604 If the final argument, <i>tableptr</i>, is NULL, PCRE uses a default set of
605 character tables that are built when PCRE is compiled, using the default C
606 locale. Otherwise, <i>tableptr</i> must be an address that is the result of a
607 call to <b>pcre_maketables()</b>. This value is stored with the compiled
608 pattern, and used again by <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b> when the
609 pattern is matched. For more discussion, see the section on locale support
613 This code fragment shows a typical straightforward call to <b>pcre_compile()</b>:
619 "^A.*Z", /* the pattern */
620 0, /* default options */
621 &error, /* for error message */
622 &erroffset, /* for error offset */
623 NULL); /* use default character tables */
625 The following names for option bits are defined in the <b>pcre.h</b> header
630 If this bit is set, the pattern is forced to be "anchored", that is, it is
631 constrained to match only at the first matching point in the string that is
632 being searched (the "subject string"). This effect can also be achieved by
633 appropriate constructs in the pattern itself, which is the only way to do it in
638 If this bit is set, <b>pcre_compile()</b> automatically inserts callout items,
639 all with number 255, before each pattern item. For discussion of the callout
641 <a href="pcrecallout.html"><b>pcrecallout</b></a>
647 These options (which are mutually exclusive) control what the \R escape
648 sequence matches. The choice is either to match only CR, LF, or CRLF, or to
649 match any Unicode newline sequence. The default is specified when PCRE is
650 built. It can be overridden from within the pattern, or by setting an option
651 when a compiled pattern is matched.
655 If this bit is set, letters in the pattern match both upper and lower case
656 letters. It is equivalent to Perl's /i option, and it can be changed within a
657 pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the
658 concept of case for characters whose values are less than 128, so caseless
659 matching is always possible. For characters with higher values, the concept of
660 case is supported if PCRE is compiled with Unicode property support, but not
661 otherwise. If you want to use caseless matching for characters 128 and above,
662 you must ensure that PCRE is compiled with Unicode property support as well as
667 If this bit is set, a dollar metacharacter in the pattern matches only at the
668 end of the subject string. Without this option, a dollar also matches
669 immediately before a newline at the end of the string (but not before any other
670 newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set.
671 There is no equivalent to this option in Perl, and no way to set it within a
676 If this bit is set, a dot metacharacter in the pattern matches a character of
677 any value, including one that indicates a newline. However, it only ever
678 matches one character, even if newlines are coded as CRLF. Without this option,
679 a dot does not match when the current position is at a newline. This option is
680 equivalent to Perl's /s option, and it can be changed within a pattern by a
681 (?s) option setting. A negative class such as [^a] always matches newline
682 characters, independent of the setting of this option.
686 If this bit is set, names used to identify capturing subpatterns need not be
687 unique. This can be helpful for certain types of pattern when it is known that
688 only one instance of the named subpattern can ever be matched. There are more
689 details of named subpatterns below; see also the
690 <a href="pcrepattern.html"><b>pcrepattern</b></a>
695 If this bit is set, most white space characters in the pattern are totally
696 ignored except when escaped or inside a character class. However, white space
697 is not allowed within sequences such as (?> that introduce various
698 parenthesized subpatterns, nor within a numerical quantifier such as {1,3}.
699 However, ignorable white space is permitted between an item and a following
700 quantifier and between a quantifier and a following + that indicates
704 White space did not used to include the VT character (code 11), because Perl
705 did not treat this character as white space. However, Perl changed at release
706 5.18, so PCRE followed at release 8.34, and VT is now treated as white space.
709 PCRE_EXTENDED also causes characters between an unescaped # outside a character
710 class and the next newline, inclusive, to be ignored. PCRE_EXTENDED is
711 equivalent to Perl's /x option, and it can be changed within a pattern by a
715 Which characters are interpreted as newlines is controlled by the options
716 passed to <b>pcre_compile()</b> or by a special sequence at the start of the
717 pattern, as described in the section entitled
718 <a href="pcrepattern.html#newlines">"Newline conventions"</a>
719 in the <b>pcrepattern</b> documentation. Note that the end of this type of
720 comment is a literal newline sequence in the pattern; escape sequences that
721 happen to represent a newline do not count.
724 This option makes it possible to include comments inside complicated patterns.
725 Note, however, that this applies only to data characters. White space characters
726 may never appear within special character sequences in a pattern, for example
727 within the sequence (?( that introduces a conditional subpattern.
731 This option was invented in order to turn on additional functionality of PCRE
732 that is incompatible with Perl, but it is currently of very little use. When
733 set, any backslash in a pattern that is followed by a letter that has no
734 special meaning causes an error, thus reserving these combinations for future
735 expansion. By default, as in Perl, a backslash followed by a letter with no
736 special meaning is treated as a literal. (Perl can, however, be persuaded to
737 give an error for this, by running it with the -w option.) There are at present
738 no other features controlled by this option. It can also be set by a (?X)
739 option setting within a pattern.
743 If this option is set, an unanchored pattern is required to match before or at
744 the first newline in the subject string, though the matched text may continue
747 PCRE_JAVASCRIPT_COMPAT
749 If this option is set, PCRE's behaviour is changed in some ways so that it is
750 compatible with JavaScript rather than Perl. The changes are as follows:
753 (1) A lone closing square bracket in a pattern causes a compile-time error,
754 because this is illegal in JavaScript (by default it is treated as a data
755 character). Thus, the pattern AB]CD becomes illegal when this option is set.
758 (2) At run time, a back reference to an unset subpattern group matches an empty
759 string (by default this causes the current matching alternative to fail). A
760 pattern such as (\1)(a) succeeds when this option is set (assuming it can find
761 an "a" in the subject), whereas it fails by default, for Perl compatibility.
764 (3) \U matches an upper case "U" character; by default \U causes a compile
765 time error (Perl uses \U to upper case subsequent characters).
768 (4) \u matches a lower case "u" character unless it is followed by four
769 hexadecimal digits, in which case the hexadecimal number defines the code point
770 to match. By default, \u causes a compile time error (Perl uses it to upper
771 case the following character).
774 (5) \x matches a lower case "x" character unless it is followed by two
775 hexadecimal digits, in which case the hexadecimal number defines the code point
776 to match. By default, as in Perl, a hexadecimal number is always expected after
777 \x, but it may have zero, one, or two digits (so, for example, \xz matches a
778 binary zero character followed by z).
782 By default, for the purposes of matching "start of line" and "end of line",
783 PCRE treats the subject string as consisting of a single line of characters,
784 even if it actually contains newlines. The "start of line" metacharacter (^)
785 matches only at the start of the string, and the "end of line" metacharacter
786 ($) matches only at the end of the string, or before a terminating newline
787 (except when PCRE_DOLLAR_ENDONLY is set). Note, however, that unless
788 PCRE_DOTALL is set, the "any character" metacharacter (.) does not match at a
789 newline. This behaviour (for ^, $, and dot) is the same as Perl.
792 When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
793 match immediately following or immediately before internal newlines in the
794 subject string, respectively, as well as at the very start and end. This is
795 equivalent to Perl's /m option, and it can be changed within a pattern by a
796 (?m) option setting. If there are no newlines in a subject string, or no
797 occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
801 This option locks out interpretation of the pattern as UTF-8 (or UTF-16 or
802 UTF-32 in the 16-bit and 32-bit libraries). In particular, it prevents the
803 creator of the pattern from switching to UTF interpretation by starting the
804 pattern with (*UTF). This may be useful in applications that process patterns
805 from external sources. The combination of PCRE_UTF8 and PCRE_NEVER_UTF also
814 These options override the default newline definition that was chosen when PCRE
815 was built. Setting the first or the second specifies that a newline is
816 indicated by a single character (CR or LF, respectively). Setting
817 PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
818 CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
819 preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
820 that any Unicode newline sequence should be recognized.
823 In an ASCII/Unicode environment, the Unicode newline sequences are the three
824 just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form
825 feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
826 (paragraph separator, U+2029). For the 8-bit library, the last two are
827 recognized only in UTF-8 mode.
830 When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for
831 CR is 0x0d, the same as ASCII. However, the character code for LF is normally
832 0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is
833 not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all
834 less than 256. For more details, see the
835 <a href="pcrebuild.html"><b>pcrebuild</b></a>
839 The newline setting in the options word uses three bits that are treated
840 as a number, giving eight possibilities. Currently only six are used (default
841 plus the five values above). This means that if you set more than one newline
842 option, the combination may or may not be sensible. For example,
843 PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
844 other combinations may yield unused numbers and cause an error.
847 The only time that a line break in a pattern is specially recognized when
848 compiling is when PCRE_EXTENDED is set. CR and LF are white space characters,
849 and so are ignored in this mode. Also, an unescaped # outside a character class
850 indicates a comment that lasts until after the next line break sequence. In
851 other circumstances, line break sequences in patterns are treated as literal
855 The newline option that is set at compile time becomes the default that is used
856 for <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, but it can be overridden.
860 If this option is set, it disables the use of numbered capturing parentheses in
861 the pattern. Any opening parenthesis that is not followed by ? behaves as if it
862 were followed by ?: but named parentheses can still be used for capturing (and
863 they acquire numbers in the usual way). There is no equivalent of this option
868 If this option is set, it disables "auto-possessification". This is an
869 optimization that, for example, turns a+b into a++b in order to avoid
870 backtracks into a+ that can never be successful. However, if callouts are in
871 use, auto-possessification means that some of them are never taken. You can set
872 this option if you want the matching functions to do a full unoptimized search
873 and run all the callouts, but it is mainly provided for testing purposes.
875 PCRE_NO_START_OPTIMIZE
877 This is an option that acts at matching time; that is, it is really an option
878 for <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. If it is set at compile time,
879 it is remembered with the compiled pattern and assumed at matching time. This
880 is necessary if you want to use JIT execution, because the JIT compiler needs
881 to know whether or not this option is set. For details see the discussion of
882 PCRE_NO_START_OPTIMIZE
883 <a href="#execoptions">below.</a>
887 This option changes the way PCRE processes \B, \b, \D, \d, \S, \s, \W,
888 \w, and some of the POSIX character classes. By default, only ASCII characters
889 are recognized, but if PCRE_UCP is set, Unicode properties are used instead to
890 classify characters. More details are given in the section on
891 <a href="pcre.html#genericchartypes">generic character types</a>
893 <a href="pcrepattern.html"><b>pcrepattern</b></a>
894 page. If you set PCRE_UCP, matching one of the items it affects takes much
895 longer. The option is available only if PCRE has been compiled with Unicode
900 This option inverts the "greediness" of the quantifiers so that they are not
901 greedy by default, but become greedy if followed by "?". It is not compatible
902 with Perl. It can also be set by a (?U) option setting within the pattern.
906 This option causes PCRE to regard both the pattern and the subject as strings
907 of UTF-8 characters instead of single-byte strings. However, it is available
908 only when PCRE is built to include UTF support. If not, the use of this option
909 provokes an error. Details of how this option changes the behaviour of PCRE are
911 <a href="pcreunicode.html"><b>pcreunicode</b></a>
916 When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
917 automatically checked. There is a discussion about the
918 <a href="pcreunicode.html#utf8strings">validity of UTF-8 strings</a>
920 <a href="pcreunicode.html"><b>pcreunicode</b></a>
921 page. If an invalid UTF-8 sequence is found, <b>pcre_compile()</b> returns an
922 error. If you already know that your pattern is valid, and you want to skip
923 this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option.
924 When it is set, the effect of passing an invalid UTF-8 string as a pattern is
925 undefined. It may cause your program to crash or loop. Note that this option
926 can also be passed to <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, to suppress
927 the validity checking of subject strings only. If the same string is being
928 matched many times, the option can be safely set for the second and subsequent
929 matchings to improve performance.
931 <br><a name="SEC12" href="#TOC1">COMPILATION ERROR CODES</a><br>
933 The following table lists the error codes than may be returned by
934 <b>pcre_compile2()</b>, along with the error messages that may be returned by
935 both compiling functions. Note that error messages are always 8-bit ASCII
936 strings, even in 16-bit or 32-bit mode. As PCRE has developed, some error codes
937 have fallen out of use. To avoid confusion, they have not been re-used.
940 1 \ at end of pattern
941 2 \c at end of pattern
942 3 unrecognized character follows \
943 4 numbers out of order in {} quantifier
944 5 number too big in {} quantifier
945 6 missing terminating ] for character class
946 7 invalid escape sequence in character class
947 8 range out of order in character class
949 10 [this code is not in use]
950 11 internal error: unexpected repeat
951 12 unrecognized character after (? or (?-
952 13 POSIX named classes are supported only within a class
954 15 reference to non-existent subpattern
955 16 erroffset passed as NULL
956 17 unknown option bit(s) set
957 18 missing ) after comment
958 19 [this code is not in use]
959 20 regular expression is too large
960 21 failed to get memory
961 22 unmatched parentheses
962 23 internal error: code overflow
963 24 unrecognized character after (?<
964 25 lookbehind assertion is not fixed length
965 26 malformed number or name after (?(
966 27 conditional group contains more than two branches
967 28 assertion expected after (?(
968 29 (?R or (?[+-]digits must be followed by )
969 30 unknown POSIX class name
970 31 POSIX collating elements are not supported
971 32 this version of PCRE is compiled without UTF support
972 33 [this code is not in use]
973 34 character value in \x{} or \o{} is too large
974 35 invalid condition (?(0)
975 36 \C not allowed in lookbehind assertion
976 37 PCRE does not support \L, \l, \N{name}, \U, or \u
977 38 number after (?C is > 255
978 39 closing ) for (?C expected
979 40 recursive call could loop indefinitely
980 41 unrecognized character after (?P
981 42 syntax error in subpattern name (missing terminator)
982 43 two named subpatterns have the same name
983 44 invalid UTF-8 string (specifically UTF-8)
984 45 support for \P, \p, and \X has not been compiled
985 46 malformed \P or \p sequence
986 47 unknown property name after \P or \p
987 48 subpattern name is too long (maximum 32 characters)
988 49 too many named subpatterns (maximum 10000)
989 50 [this code is not in use]
990 51 octal value is greater than \377 in 8-bit non-UTF-8 mode
991 52 internal error: overran compiling workspace
992 53 internal error: previously-checked referenced subpattern
994 54 DEFINE group contains more than one branch
995 55 repeating a DEFINE group is not allowed
996 56 inconsistent NEWLINE options
997 57 \g is not followed by a braced, angle-bracketed, or quoted
998 name/number or by a plain number
999 58 a numbered reference must not be zero
1000 59 an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
1001 60 (*VERB) not recognized or malformed
1002 61 number is too big
1003 62 subpattern name expected
1004 63 digit expected after (?+
1005 64 ] is an invalid data character in JavaScript compatibility mode
1006 65 different names for subpatterns of the same number are
1008 66 (*MARK) must have an argument
1009 67 this version of PCRE is not compiled with Unicode property
1011 68 \c must be followed by an ASCII character
1012 69 \k is not followed by a braced, angle-bracketed, or quoted name
1013 70 internal error: unknown opcode in find_fixedlength()
1014 71 \N is not supported in a class
1015 72 too many forward references
1016 73 disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
1017 74 invalid UTF-16 string (specifically UTF-16)
1018 75 name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
1019 76 character value in \u.... sequence is too large
1020 77 invalid UTF-32 string (specifically UTF-32)
1021 78 setting UTF is disabled by the application
1022 79 non-hex character in \x{} (closing brace missing?)
1023 80 non-octal character in \o{} (closing brace missing?)
1024 81 missing opening brace after \o
1025 82 parentheses are too deeply nested
1026 83 invalid range in character class
1027 84 group name must start with a non-digit
1028 85 parentheses are too deeply nested (stack check)
1030 The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
1031 be used if the limits were changed when PCRE was built.
1032 <a name="studyingapattern"></a></P>
1033 <br><a name="SEC13" href="#TOC1">STUDYING A PATTERN</a><br>
1035 <b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b>
1036 <b> const char **<i>errptr</i>);</b>
1039 If a compiled pattern is going to be used several times, it is worth spending
1040 more time analyzing it in order to speed up the time taken for matching. The
1041 function <b>pcre_study()</b> takes a pointer to a compiled pattern as its first
1042 argument. If studying the pattern produces additional information that will
1043 help speed up matching, <b>pcre_study()</b> returns a pointer to a
1044 <b>pcre_extra</b> block, in which the <i>study_data</i> field points to the
1045 results of the study.
1048 The returned value from <b>pcre_study()</b> can be passed directly to
1049 <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. However, a <b>pcre_extra</b> block
1050 also contains other fields that can be set by the caller before the block is
1051 passed; these are described
1052 <a href="#extradata">below</a>
1053 in the section on matching a pattern.
1056 If studying the pattern does not produce any useful information,
1057 <b>pcre_study()</b> returns NULL by default. In that circumstance, if the
1058 calling program wants to pass any of the other fields to <b>pcre_exec()</b> or
1059 <b>pcre_dfa_exec()</b>, it must set up its own <b>pcre_extra</b> block. However,
1060 if <b>pcre_study()</b> is called with the PCRE_STUDY_EXTRA_NEEDED option, it
1061 returns a <b>pcre_extra</b> block even if studying did not find any additional
1062 information. It may still return NULL, however, if an error occurs in
1063 <b>pcre_study()</b>.
1066 The second argument of <b>pcre_study()</b> contains option bits. There are three
1067 further options in addition to PCRE_STUDY_EXTRA_NEEDED:
1069 PCRE_STUDY_JIT_COMPILE
1070 PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE
1071 PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE
1073 If any of these are set, and the just-in-time compiler is available, the
1074 pattern is further compiled into machine code that executes much faster than
1075 the <b>pcre_exec()</b> interpretive matching function. If the just-in-time
1076 compiler is not available, these options are ignored. All undefined bits in the
1077 <i>options</i> argument must be zero.
1080 JIT compilation is a heavyweight optimization. It can take some time for
1081 patterns to be analyzed, and for one-off matches and simple patterns the
1082 benefit of faster execution might be offset by a much slower study time.
1083 Not all patterns can be optimized by the JIT compiler. For those that cannot be
1084 handled, matching automatically falls back to the <b>pcre_exec()</b>
1085 interpreter. For more details, see the
1086 <a href="pcrejit.html"><b>pcrejit</b></a>
1090 The third argument for <b>pcre_study()</b> is a pointer for an error message. If
1091 studying succeeds (even if no data is returned), the variable it points to is
1092 set to NULL. Otherwise it is set to point to a textual error message. This is a
1093 static string that is part of the library. You must not try to free it. You
1094 should test the error pointer for NULL after calling <b>pcre_study()</b>, to be
1095 sure that it has run successfully.
1098 When you are finished with a pattern, you can free the memory used for the
1099 study data by calling <b>pcre_free_study()</b>. This function was added to the
1100 API for release 8.20. For earlier versions, the memory could be freed with
1101 <b>pcre_free()</b>, just like the pattern itself. This will still work in cases
1102 where JIT optimization is not used, but it is advisable to change to the new
1103 function when convenient.
1106 This is a typical way in which <b>pcre_study</b>() is used (except that in a
1107 real application there should be tests for errors):
1112 re = pcre_compile("pattern", 0, &error, &erroroffset, NULL);
1114 re, /* result of pcre_compile() */
1116 &error); /* set to NULL or points to a message */
1117 rc = pcre_exec( /* see below for details of pcre_exec() options */
1118 re, sd, "subject", 7, 0, 0, ovector, 30);
1120 pcre_free_study(sd);
1123 Studying a pattern does two things: first, a lower bound for the length of
1124 subject string that is needed to match the pattern is computed. This does not
1125 mean that there are any strings of that length that match, but it does
1126 guarantee that no shorter strings match. The value is used to avoid wasting
1127 time by trying to match strings that are shorter than the lower bound. You can
1128 find out the value in a calling program via the <b>pcre_fullinfo()</b> function.
1131 Studying a pattern is also useful for non-anchored patterns that do not have a
1132 single fixed starting character. A bitmap of possible starting bytes is
1133 created. This speeds up finding a position in the subject at which to start
1134 matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.
1135 In 32-bit mode, the bitmap is used for 32-bit values less than 256.)
1138 These two optimizations apply to both <b>pcre_exec()</b> and
1139 <b>pcre_dfa_exec()</b>, and the information is also used by the JIT compiler.
1140 The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option.
1141 You might want to do this if your pattern contains callouts or (*MARK) and you
1142 want to make use of these facilities in cases where matching fails.
1145 PCRE_NO_START_OPTIMIZE can be specified at either compile time or execution
1146 time. However, if PCRE_NO_START_OPTIMIZE is passed to <b>pcre_exec()</b>, (that
1147 is, after any JIT compilation has happened) JIT execution is disabled. For JIT
1148 execution to work with PCRE_NO_START_OPTIMIZE, the option must be set at
1152 There is a longer discussion of PCRE_NO_START_OPTIMIZE
1153 <a href="#execoptions">below.</a>
1154 <a name="localesupport"></a></P>
1155 <br><a name="SEC14" href="#TOC1">LOCALE SUPPORT</a><br>
1157 PCRE handles caseless matching, and determines whether characters are letters,
1158 digits, or whatever, by reference to a set of tables, indexed by character
1159 code point. When running in UTF-8 mode, or in the 16- or 32-bit libraries, this
1160 applies only to characters with code points less than 256. By default,
1161 higher-valued code points never match escapes such as \w or \d. However, if
1162 PCRE is built with Unicode property support, all characters can be tested with
1163 \p and \P, or, alternatively, the PCRE_UCP option can be set when a pattern
1164 is compiled; this causes \w and friends to use Unicode property support
1165 instead of the built-in tables.
1168 The use of locales with Unicode is discouraged. If you are handling characters
1169 with code points greater than 128, you should either use Unicode support, or
1170 use locales, but not try to mix the two.
1173 PCRE contains an internal set of tables that are used when the final argument
1174 of <b>pcre_compile()</b> is NULL. These are sufficient for many applications.
1175 Normally, the internal tables recognize only ASCII characters. However, when
1176 PCRE is built, it is possible to cause the internal tables to be rebuilt in the
1177 default "C" locale of the local system, which may cause them to be different.
1180 The internal tables can always be overridden by tables supplied by the
1181 application that calls PCRE. These may be created in a different locale from
1182 the default. As more and more applications change to using Unicode, the need
1183 for this locale support is expected to die away.
1186 External tables are built by calling the <b>pcre_maketables()</b> function,
1187 which has no arguments, in the relevant locale. The result can then be passed
1188 to <b>pcre_compile()</b> as often as necessary. For example, to build and use
1189 tables that are appropriate for the French locale (where accented characters
1190 with values greater than 128 are treated as letters), the following code could
1193 setlocale(LC_CTYPE, "fr_FR");
1194 tables = pcre_maketables();
1195 re = pcre_compile(..., tables);
1197 The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
1198 are using Windows, the name for the French locale is "french".
1201 When <b>pcre_maketables()</b> runs, the tables are built in memory that is
1202 obtained via <b>pcre_malloc</b>. It is the caller's responsibility to ensure
1203 that the memory containing the tables remains available for as long as it is
1207 The pointer that is passed to <b>pcre_compile()</b> is saved with the compiled
1208 pattern, and the same tables are used via this pointer by <b>pcre_study()</b>
1209 and also by <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>. Thus, for any single
1210 pattern, compilation, studying and matching all happen in the same locale, but
1211 different patterns can be processed in different locales.
1214 It is possible to pass a table pointer or NULL (indicating the use of the
1215 internal tables) to <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b> (see the
1216 discussion below in the section on matching a pattern). This facility is
1217 provided for use with pre-compiled patterns that have been saved and reloaded.
1218 Character tables are not saved with patterns, so if a non-standard table was
1219 used at compile time, it must be provided again when the reloaded pattern is
1220 matched. Attempting to use this facility to match a pattern in a different
1221 locale from the one in which it was compiled is likely to lead to anomalous
1222 (usually incorrect) results.
1223 <a name="infoaboutpattern"></a></P>
1224 <br><a name="SEC15" href="#TOC1">INFORMATION ABOUT A PATTERN</a><br>
1226 <b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
1227 <b> int <i>what</i>, void *<i>where</i>);</b>
1230 The <b>pcre_fullinfo()</b> function returns information about a compiled
1231 pattern. It replaces the <b>pcre_info()</b> function, which was removed from the
1232 library at version 8.30, after more than 10 years of obsolescence.
1235 The first argument for <b>pcre_fullinfo()</b> is a pointer to the compiled
1236 pattern. The second argument is the result of <b>pcre_study()</b>, or NULL if
1237 the pattern was not studied. The third argument specifies which piece of
1238 information is required, and the fourth argument is a pointer to a variable
1239 to receive the data. The yield of the function is zero for success, or one of
1240 the following negative numbers:
1242 PCRE_ERROR_NULL the argument <i>code</i> was NULL
1243 the argument <i>where</i> was NULL
1244 PCRE_ERROR_BADMAGIC the "magic number" was not found
1245 PCRE_ERROR_BADENDIANNESS the pattern was compiled with different
1247 PCRE_ERROR_BADOPTION the value of <i>what</i> was invalid
1248 PCRE_ERROR_UNSET the requested field is not set
1250 The "magic number" is placed at the start of each compiled pattern as an simple
1251 check against passing an arbitrary memory pointer. The endianness error can
1252 occur if a compiled pattern is saved and reloaded on a different host. Here is
1253 a typical call of <b>pcre_fullinfo()</b>, to obtain the length of the compiled
1259 re, /* result of pcre_compile() */
1260 sd, /* result of pcre_study(), or NULL */
1261 PCRE_INFO_SIZE, /* what is required */
1262 &length); /* where to put the data */
1264 The possible values for the third argument are defined in <b>pcre.h</b>, and are
1267 PCRE_INFO_BACKREFMAX
1269 Return the number of the highest back reference in the pattern. The fourth
1270 argument should point to an <b>int</b> variable. Zero is returned if there are
1273 PCRE_INFO_CAPTURECOUNT
1275 Return the number of capturing subpatterns in the pattern. The fourth argument
1276 should point to an <b>int</b> variable.
1278 PCRE_INFO_DEFAULT_TABLES
1280 Return a pointer to the internal default character tables within PCRE. The
1281 fourth argument should point to an <b>unsigned char *</b> variable. This
1282 information call is provided for internal use by the <b>pcre_study()</b>
1283 function. External callers can cause PCRE to use its internal tables by passing
1284 a NULL table pointer.
1286 PCRE_INFO_FIRSTBYTE (deprecated)
1288 Return information about the first data unit of any matched string, for a
1289 non-anchored pattern. The name of this option refers to the 8-bit library,
1290 where data units are bytes. The fourth argument should point to an <b>int</b>
1291 variable. Negative values are used for special cases. However, this means that
1292 when the 32-bit library is in non-UTF-32 mode, the full 32-bit range of
1293 characters cannot be returned. For this reason, this value is deprecated; use
1294 PCRE_INFO_FIRSTCHARACTERFLAGS and PCRE_INFO_FIRSTCHARACTER instead.
1297 If there is a fixed first value, for example, the letter "c" from a pattern
1298 such as (cat|cow|coyote), its value is returned. In the 8-bit library, the
1299 value is always less than 256. In the 16-bit library the value can be up to
1300 0xffff. In the 32-bit library the value can be up to 0x10ffff.
1303 If there is no fixed first value, and if either
1306 (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
1310 (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
1311 (if it were set, the pattern would be anchored),
1314 -1 is returned, indicating that the pattern matches only at the start of a
1315 subject string or after any newline within the string. Otherwise -2 is
1316 returned. For anchored patterns, -2 is returned.
1318 PCRE_INFO_FIRSTCHARACTER
1320 Return the value of the first data unit (non-UTF character) of any matched
1321 string in the situation where PCRE_INFO_FIRSTCHARACTERFLAGS returns 1;
1322 otherwise return 0. The fourth argument should point to an <b>uint_t</b>
1326 In the 8-bit library, the value is always less than 256. In the 16-bit library
1327 the value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value
1328 can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode.
1330 PCRE_INFO_FIRSTCHARACTERFLAGS
1332 Return information about the first data unit of any matched string, for a
1333 non-anchored pattern. The fourth argument should point to an <b>int</b>
1337 If there is a fixed first value, for example, the letter "c" from a pattern
1338 such as (cat|cow|coyote), 1 is returned, and the character value can be
1339 retrieved using PCRE_INFO_FIRSTCHARACTER. If there is no fixed first value, and
1343 (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
1347 (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
1348 (if it were set, the pattern would be anchored),
1351 2 is returned, indicating that the pattern matches only at the start of a
1352 subject string or after any newline within the string. Otherwise 0 is
1353 returned. For anchored patterns, 0 is returned.
1355 PCRE_INFO_FIRSTTABLE
1357 If the pattern was studied, and this resulted in the construction of a 256-bit
1358 table indicating a fixed set of values for the first data unit in any matching
1359 string, a pointer to the table is returned. Otherwise NULL is returned. The
1360 fourth argument should point to an <b>unsigned char *</b> variable.
1364 Return 1 if the pattern contains any explicit matches for CR or LF characters,
1365 otherwise 0. The fourth argument should point to an <b>int</b> variable. An
1366 explicit match is either a literal CR or LF character, or \r or \n.
1370 Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
1371 0. The fourth argument should point to an <b>int</b> variable. (?J) and
1372 (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
1376 Return 1 if the pattern was studied with one of the JIT options, and
1377 just-in-time compiling was successful. The fourth argument should point to an
1378 <b>int</b> variable. A return value of 0 means that JIT support is not available
1379 in this version of PCRE, or that the pattern was not studied with a JIT option,
1380 or that the JIT compiler could not handle this particular pattern. See the
1381 <a href="pcrejit.html"><b>pcrejit</b></a>
1382 documentation for details of what can and cannot be handled.
1386 If the pattern was successfully studied with a JIT option, return the size of
1387 the JIT compiled code, otherwise return zero. The fourth argument should point
1388 to a <b>size_t</b> variable.
1390 PCRE_INFO_LASTLITERAL
1392 Return the value of the rightmost literal data unit that must exist in any
1393 matched string, other than at its start, if such a value has been recorded. The
1394 fourth argument should point to an <b>int</b> variable. If there is no such
1395 value, -1 is returned. For anchored patterns, a last literal value is recorded
1396 only if it follows something of variable length. For example, for the pattern
1397 /^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value
1401 Since for the 32-bit library using the non-UTF-32 mode, this function is unable
1402 to return the full 32-bit range of characters, this value is deprecated;
1403 instead the PCRE_INFO_REQUIREDCHARFLAGS and PCRE_INFO_REQUIREDCHAR values should
1406 PCRE_INFO_MATCH_EMPTY
1408 Return 1 if the pattern can match an empty string, otherwise 0. The fourth
1409 argument should point to an <b>int</b> variable.
1411 PCRE_INFO_MATCHLIMIT
1413 If the pattern set a match limit by including an item of the form
1414 (*LIMIT_MATCH=nnnn) at the start, the value is returned. The fourth argument
1415 should point to an unsigned 32-bit integer. If no such value has been set, the
1416 call to <b>pcre_fullinfo()</b> returns the error PCRE_ERROR_UNSET.
1418 PCRE_INFO_MAXLOOKBEHIND
1420 Return the number of characters (NB not data units) in the longest lookbehind
1421 assertion in the pattern. This information is useful when doing multi-segment
1422 matching using the partial matching facilities. Note that the simple assertions
1423 \b and \B require a one-character lookbehind. \A also registers a
1424 one-character lookbehind, though it does not actually inspect the previous
1425 character. This is to ensure that at least one character from the old segment
1426 is retained when a new segment is processed. Otherwise, if there are no
1427 lookbehinds in the pattern, \A might match incorrectly at the start of a new
1432 If the pattern was studied and a minimum length for matching subject strings
1433 was computed, its value is returned. Otherwise the returned value is -1. The
1434 value is a number of characters, which in UTF mode may be different from the
1435 number of data units. The fourth argument should point to an <b>int</b>
1436 variable. A non-negative value is a lower bound to the length of any matching
1437 string. There may not be any strings of that length that do actually match, but
1438 every string that does match is at least that long.
1441 PCRE_INFO_NAMEENTRYSIZE
1444 PCRE supports the use of named as well as numbered capturing parentheses. The
1445 names are just an additional way of identifying the parentheses, which still
1446 acquire numbers. Several convenience functions such as
1447 <b>pcre_get_named_substring()</b> are provided for extracting captured
1448 substrings by name. It is also possible to extract the data directly, by first
1449 converting the name to a number in order to access the correct pointers in the
1450 output vector (described with <b>pcre_exec()</b> below). To do the conversion,
1451 you need to use the name-to-number map, which is described by these three
1455 The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives
1456 the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
1457 entry; both of these return an <b>int</b> value. The entry size depends on the
1458 length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
1459 entry of the table. This is a pointer to <b>char</b> in the 8-bit library, where
1460 the first two bytes of each entry are the number of the capturing parenthesis,
1461 most significant byte first. In the 16-bit library, the pointer points to
1462 16-bit data units, the first of which contains the parenthesis number. In the
1463 32-bit library, the pointer points to 32-bit data units, the first of which
1464 contains the parenthesis number. The rest of the entry is the corresponding
1465 name, zero terminated.
1468 The names are in alphabetical order. If (?| is used to create multiple groups
1469 with the same number, as described in the
1470 <a href="pcrepattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a>
1472 <a href="pcrepattern.html"><b>pcrepattern</b></a>
1473 page, the groups may be given the same name, but there is only one entry in the
1474 table. Different names for groups of the same number are not permitted.
1475 Duplicate names for subpatterns with different numbers are permitted,
1476 but only if PCRE_DUPNAMES is set. They appear in the table in the order in
1477 which they were found in the pattern. In the absence of (?| this is the order
1478 of increasing number; when (?| is used this is not necessarily the case because
1479 later subpatterns may have lower numbers.
1482 As a simple example of the name/number table, consider the following pattern
1483 after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white
1484 space - including newlines - is ignored):
1486 (?<date> (?<year>(\d\d)?\d\d) - (?<month>\d\d) - (?<day>\d\d) )
1488 There are four named subpatterns, so the table has four entries, and each entry
1489 in the table is eight bytes long. The table is as follows, with non-printing
1490 bytes shows in hexadecimal, and undefined bytes shown as ??:
1493 00 05 d a y 00 ?? ??
1497 When writing code to extract data from named subpatterns using the
1498 name-to-number map, remember that the length of the entries is likely to be
1499 different for each compiled pattern.
1503 Return 1 if the pattern can be used for partial matching with
1504 <b>pcre_exec()</b>, otherwise 0. The fourth argument should point to an
1505 <b>int</b> variable. From release 8.00, this always returns 1, because the
1506 restrictions that previously applied to partial matching have been lifted. The
1507 <a href="pcrepartial.html"><b>pcrepartial</b></a>
1508 documentation gives details of partial matching.
1512 Return a copy of the options with which the pattern was compiled. The fourth
1513 argument should point to an <b>unsigned long int</b> variable. These option bits
1514 are those specified in the call to <b>pcre_compile()</b>, modified by any
1515 top-level option settings at the start of the pattern itself. In other words,
1516 they are the options that will be in force when matching starts. For example,
1517 if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1518 result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
1521 A pattern is automatically anchored by PCRE if all of its top-level
1522 alternatives begin with one of the following:
1524 ^ unless PCRE_MULTILINE is set
1527 .* if PCRE_DOTALL is set and there are no back references to the subpattern in which .* appears
1529 For such patterns, the PCRE_ANCHORED bit is set in the options returned by
1530 <b>pcre_fullinfo()</b>.
1532 PCRE_INFO_RECURSIONLIMIT
1534 If the pattern set a recursion limit by including an item of the form
1535 (*LIMIT_RECURSION=nnnn) at the start, the value is returned. The fourth
1536 argument should point to an unsigned 32-bit integer. If no such value has been
1537 set, the call to <b>pcre_fullinfo()</b> returns the error PCRE_ERROR_UNSET.
1541 Return the size of the compiled pattern in bytes (for all three libraries). The
1542 fourth argument should point to a <b>size_t</b> variable. This value does not
1543 include the size of the <b>pcre</b> structure that is returned by
1544 <b>pcre_compile()</b>. The value that is passed as the argument to
1545 <b>pcre_malloc()</b> when <b>pcre_compile()</b> is getting memory in which to
1546 place the compiled data is the value returned by this option plus the size of
1547 the <b>pcre</b> structure. Studying a compiled pattern, with or without JIT,
1548 does not alter the value returned by this option.
1552 Return the size in bytes (for all three libraries) of the data block pointed to
1553 by the <i>study_data</i> field in a <b>pcre_extra</b> block. If <b>pcre_extra</b>
1554 is NULL, or there is no study data, zero is returned. The fourth argument
1555 should point to a <b>size_t</b> variable. The <i>study_data</i> field is set by
1556 <b>pcre_study()</b> to record information that will speed up matching (see the
1558 <a href="#studyingapattern">"Studying a pattern"</a>
1559 above). The format of the <i>study_data</i> block is private, but its length
1560 is made available via this option so that it can be saved and restored (see the
1561 <a href="pcreprecompile.html"><b>pcreprecompile</b></a>
1562 documentation for details).
1564 PCRE_INFO_REQUIREDCHARFLAGS
1566 Returns 1 if there is a rightmost literal data unit that must exist in any
1567 matched string, other than at its start. The fourth argument should point to
1568 an <b>int</b> variable. If there is no such value, 0 is returned. If returning
1569 1, the character value itself can be retrieved using PCRE_INFO_REQUIREDCHAR.
1572 For anchored patterns, a last literal value is recorded only if it follows
1573 something of variable length. For example, for the pattern /^a\d+z\d+/ the
1574 returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for
1575 /^a\dz\d/ the returned value is 0.
1577 PCRE_INFO_REQUIREDCHAR
1579 Return the value of the rightmost literal data unit that must exist in any
1580 matched string, other than at its start, if such a value has been recorded. The
1581 fourth argument should point to an <b>uint32_t</b> variable. If there is no such
1582 value, 0 is returned.
1584 <br><a name="SEC16" href="#TOC1">REFERENCE COUNTS</a><br>
1586 <b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b>
1589 The <b>pcre_refcount()</b> function is used to maintain a reference count in the
1590 data block that contains a compiled pattern. It is provided for the benefit of
1591 applications that operate in an object-oriented manner, where different parts
1592 of the application may be using the same compiled pattern, but you want to free
1593 the block when they are all done.
1596 When a pattern is compiled, the reference count field is initialized to zero.
1597 It is changed only by calling this function, whose action is to add the
1598 <i>adjust</i> value (which may be positive or negative) to it. The yield of the
1599 function is the new value. However, the value of the count is constrained to
1600 lie between 0 and 65535, inclusive. If the new value is outside these limits,
1601 it is forced to the appropriate limit value.
1604 Except when it is zero, the reference count is not correctly preserved if a
1605 pattern is compiled on one host and then transferred to a host whose byte-order
1606 is different. (This seems a highly unlikely scenario.)
1608 <br><a name="SEC17" href="#TOC1">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a><br>
1610 <b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
1611 <b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
1612 <b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b>
1615 The function <b>pcre_exec()</b> is called to match a subject string against a
1616 compiled pattern, which is passed in the <i>code</i> argument. If the
1617 pattern was studied, the result of the study should be passed in the
1618 <i>extra</i> argument. You can call <b>pcre_exec()</b> with the same <i>code</i>
1619 and <i>extra</i> arguments as many times as you like, in order to match
1620 different subject strings with the same pattern.
1623 This function is the main matching facility of the library, and it operates in
1624 a Perl-like manner. For specialist use there is also an alternative matching
1625 function, which is described
1626 <a href="#dfamatch">below</a>
1627 in the section about the <b>pcre_dfa_exec()</b> function.
1630 In most applications, the pattern will have been compiled (and optionally
1631 studied) in the same process that calls <b>pcre_exec()</b>. However, it is
1632 possible to save compiled patterns and study data, and then use them later
1633 in different processes, possibly even on different hosts. For a discussion
1635 <a href="pcreprecompile.html"><b>pcreprecompile</b></a>
1639 Here is an example of a simple call to <b>pcre_exec()</b>:
1644 re, /* result of pcre_compile() */
1645 NULL, /* we didn't study the pattern */
1646 "some string", /* the subject string */
1647 11, /* the length of the subject string */
1648 0, /* start at offset 0 in the subject */
1649 0, /* default options */
1650 ovector, /* vector of integers for substring information */
1651 30); /* number of elements (NOT size in bytes) */
1652 <a name="extradata"></a></PRE>
1655 Extra data for <b>pcre_exec()</b>
1658 If the <i>extra</i> argument is not NULL, it must point to a <b>pcre_extra</b>
1659 data block. The <b>pcre_study()</b> function returns such a block (when it
1660 doesn't return NULL), but you can also create one for yourself, and pass
1661 additional information in it. The <b>pcre_extra</b> block contains the following
1662 fields (not necessarily in this order):
1664 unsigned long int <i>flags</i>;
1665 void *<i>study_data</i>;
1666 void *<i>executable_jit</i>;
1667 unsigned long int <i>match_limit</i>;
1668 unsigned long int <i>match_limit_recursion</i>;
1669 void *<i>callout_data</i>;
1670 const unsigned char *<i>tables</i>;
1671 unsigned char **<i>mark</i>;
1673 In the 16-bit version of this structure, the <i>mark</i> field has type
1677 In the 32-bit version of this structure, the <i>mark</i> field has type
1681 The <i>flags</i> field is used to specify which of the other fields are set. The
1684 PCRE_EXTRA_CALLOUT_DATA
1685 PCRE_EXTRA_EXECUTABLE_JIT
1687 PCRE_EXTRA_MATCH_LIMIT
1688 PCRE_EXTRA_MATCH_LIMIT_RECURSION
1689 PCRE_EXTRA_STUDY_DATA
1692 Other flag bits should be set to zero. The <i>study_data</i> field and sometimes
1693 the <i>executable_jit</i> field are set in the <b>pcre_extra</b> block that is
1694 returned by <b>pcre_study()</b>, together with the appropriate flag bits. You
1695 should not set these yourself, but you may add to the block by setting other
1696 fields and their corresponding flag bits.
1699 The <i>match_limit</i> field provides a means of preventing PCRE from using up a
1700 vast amount of resources when running patterns that are not going to match,
1701 but which have a very large number of possibilities in their search trees. The
1702 classic example is a pattern that uses nested unlimited repeats.
1705 Internally, <b>pcre_exec()</b> uses a function called <b>match()</b>, which it
1706 calls repeatedly (sometimes recursively). The limit set by <i>match_limit</i> is
1707 imposed on the number of times this function is called during a match, which
1708 has the effect of limiting the amount of backtracking that can take place. For
1709 patterns that are not anchored, the count restarts from zero for each position
1710 in the subject string.
1713 When <b>pcre_exec()</b> is called with a pattern that was successfully studied
1714 with a JIT option, the way that the matching is executed is entirely different.
1715 However, there is still the possibility of runaway matching that goes on for a
1716 very long time, and so the <i>match_limit</i> value is also used in this case
1717 (but in a different way) to limit how long the matching can continue.
1720 The default value for the limit can be set when PCRE is built; the default
1721 default is 10 million, which handles all but the most extreme cases. You can
1722 override the default by suppling <b>pcre_exec()</b> with a <b>pcre_extra</b>
1723 block in which <i>match_limit</i> is set, and PCRE_EXTRA_MATCH_LIMIT is set in
1724 the <i>flags</i> field. If the limit is exceeded, <b>pcre_exec()</b> returns
1725 PCRE_ERROR_MATCHLIMIT.
1728 A value for the match limit may also be supplied by an item at the start of a
1733 where d is a decimal number. However, such a setting is ignored unless d is
1734 less than the limit set by the caller of <b>pcre_exec()</b> or, if no such limit
1735 is set, less than the default.
1738 The <i>match_limit_recursion</i> field is similar to <i>match_limit</i>, but
1739 instead of limiting the total number of times that <b>match()</b> is called, it
1740 limits the depth of recursion. The recursion depth is a smaller number than the
1741 total number of calls, because not all calls to <b>match()</b> are recursive.
1742 This limit is of use only if it is set smaller than <i>match_limit</i>.
1745 Limiting the recursion depth limits the amount of machine stack that can be
1746 used, or, when PCRE has been compiled to use memory on the heap instead of the
1747 stack, the amount of heap memory that can be used. This limit is not relevant,
1748 and is ignored, when matching is done using JIT compiled code.
1751 The default value for <i>match_limit_recursion</i> can be set when PCRE is
1752 built; the default default is the same value as the default for
1753 <i>match_limit</i>. You can override the default by suppling <b>pcre_exec()</b>
1754 with a <b>pcre_extra</b> block in which <i>match_limit_recursion</i> is set, and
1755 PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the <i>flags</i> field. If the limit
1756 is exceeded, <b>pcre_exec()</b> returns PCRE_ERROR_RECURSIONLIMIT.
1759 A value for the recursion limit may also be supplied by an item at the start of
1760 a pattern of the form
1762 (*LIMIT_RECURSION=d)
1764 where d is a decimal number. However, such a setting is ignored unless d is
1765 less than the limit set by the caller of <b>pcre_exec()</b> or, if no such limit
1766 is set, less than the default.
1769 The <i>callout_data</i> field is used in conjunction with the "callout" feature,
1770 and is described in the
1771 <a href="pcrecallout.html"><b>pcrecallout</b></a>
1775 The <i>tables</i> field is provided for use with patterns that have been
1776 pre-compiled using custom character tables, saved to disc or elsewhere, and
1777 then reloaded, because the tables that were used to compile a pattern are not
1778 saved with it. See the
1779 <a href="pcreprecompile.html"><b>pcreprecompile</b></a>
1780 documentation for a discussion of saving compiled patterns for later use. If
1781 NULL is passed using this mechanism, it forces PCRE's internal tables to be
1785 <b>Warning:</b> The tables that <b>pcre_exec()</b> uses must be the same as those
1786 that were used when the pattern was compiled. If this is not the case, the
1787 behaviour of <b>pcre_exec()</b> is undefined. Therefore, when a pattern is
1788 compiled and matched in the same process, this field should never be set. In
1789 this (the most common) case, the correct table pointer is automatically passed
1790 with the compiled pattern from <b>pcre_compile()</b> to <b>pcre_exec()</b>.
1793 If PCRE_EXTRA_MARK is set in the <i>flags</i> field, the <i>mark</i> field must
1794 be set to point to a suitable variable. If the pattern contains any
1795 backtracking control verbs such as (*MARK:NAME), and the execution ends up with
1796 a name to pass back, a pointer to the name string (zero terminated) is placed
1797 in the variable pointed to by the <i>mark</i> field. The names are within the
1798 compiled pattern; if you wish to retain such a name you must copy it before
1799 freeing the memory of a compiled pattern. If there is no name to pass back, the
1800 variable pointed to by the <i>mark</i> field is set to NULL. For details of the
1801 backtracking control verbs, see the section entitled
1802 <a href="pcrepattern#backtrackcontrol">"Backtracking control"</a>
1804 <a href="pcrepattern.html"><b>pcrepattern</b></a>
1806 <a name="execoptions"></a></P>
1808 Option bits for <b>pcre_exec()</b>
1811 The unused bits of the <i>options</i> argument for <b>pcre_exec()</b> must be
1812 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_<i>xxx</i>,
1813 PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
1814 PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and
1818 If the pattern was successfully studied with one of the just-in-time (JIT)
1819 compile options, the only supported options for JIT execution are
1820 PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY,
1821 PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an
1822 unsupported option is used, JIT execution is disabled and the normal
1823 interpretive code in <b>pcre_exec()</b> is run.
1827 The PCRE_ANCHORED option limits <b>pcre_exec()</b> to matching at the first
1828 matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out
1829 to be anchored by virtue of its contents, it cannot be made unachored at
1835 These options (which are mutually exclusive) control what the \R escape
1836 sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1837 match any Unicode newline sequence. These options override the choice that was
1838 made or defaulted when the pattern was compiled.
1843 PCRE_NEWLINE_ANYCRLF
1846 These options override the newline definition that was chosen or defaulted when
1847 the pattern was compiled. For details, see the description of
1848 <b>pcre_compile()</b> above. During matching, the newline choice affects the
1849 behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1850 the way the match position is advanced after a match failure for an unanchored
1854 When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
1855 match attempt for an unanchored pattern fails when the current position is at a
1856 CRLF sequence, and the pattern contains no explicit matches for CR or LF
1857 characters, the match position is advanced by two characters instead of one, in
1858 other words, to after the CRLF.
1861 The above rule is a compromise that makes the most common cases work as
1862 expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1863 set), it does not match the string "\r\nA" because, after failing at the
1864 start, it skips both the CR and the LF before retrying. However, the pattern
1865 [\r\n]A does match that string, because it contains an explicit CR or LF
1866 reference, and so advances only by one character after the first failure.
1869 An explicit match for CR of LF is either a literal appearance of one of those
1870 characters, or one of the \r or \n escape sequences. Implicit matches such as
1871 [^X] do not count, nor does \s (which includes CR and LF in the characters
1875 Notwithstanding the above, anomalous effects may still occur when CRLF is a
1876 valid newline sequence and explicit \r or \n escapes appear in the pattern.
1880 This option specifies that first character of the subject string is not the
1881 beginning of a line, so the circumflex metacharacter should not match before
1882 it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex
1883 never to match. This option affects only the behaviour of the circumflex
1884 metacharacter. It does not affect \A.
1888 This option specifies that the end of the subject string is not the end of a
1889 line, so the dollar metacharacter should not match it nor (except in multiline
1890 mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at
1891 compile time) causes dollar never to match. This option affects only the
1892 behaviour of the dollar metacharacter. It does not affect \Z or \z.
1896 An empty string is not considered to be a valid match if this option is set. If
1897 there are alternatives in the pattern, they are tried. If all the alternatives
1898 match the empty string, the entire match fails. For example, if the pattern
1902 is applied to a string not beginning with "a" or "b", it matches an empty
1903 string at the start of the subject. With PCRE_NOTEMPTY set, this match is not
1904 valid, so PCRE searches further into the string for occurrences of "a" or "b".
1906 PCRE_NOTEMPTY_ATSTART
1908 This is like PCRE_NOTEMPTY, except that an empty string match that is not at
1909 the start of the subject is permitted. If the pattern is anchored, such a match
1910 can occur only if the pattern contains \K.
1913 Perl has no direct equivalent of PCRE_NOTEMPTY or PCRE_NOTEMPTY_ATSTART, but it
1914 does make a special case of a pattern match of the empty string within its
1915 <b>split()</b> function, and when using the /g modifier. It is possible to
1916 emulate Perl's behaviour after matching a null string by first trying the match
1917 again at the same offset with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then
1918 if that fails, by advancing the starting offset (see below) and trying an
1919 ordinary match again. There is some code that demonstrates how to do this in
1921 <a href="pcredemo.html"><b>pcredemo</b></a>
1922 sample program. In the most general case, you have to check to see if the
1923 newline convention recognizes CRLF as a newline, and if so, and the current
1924 character is CR followed by LF, advance the starting offset by two characters
1927 PCRE_NO_START_OPTIMIZE
1929 There are a number of optimizations that <b>pcre_exec()</b> uses at the start of
1930 a match, in order to speed up the process. For example, if it is known that an
1931 unanchored match must start with a specific character, it searches the subject
1932 for that character, and fails immediately if it cannot find it, without
1933 actually running the main matching function. This means that a special item
1934 such as (*COMMIT) at the start of a pattern is not considered until after a
1935 suitable starting point for the match has been found. Also, when callouts or
1936 (*MARK) items are in use, these "start-up" optimizations can cause them to be
1937 skipped if the pattern is never actually used. The start-up optimizations are
1938 in effect a pre-scan of the subject that takes place before the pattern is run.
1941 The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly
1942 causing performance to suffer, but ensuring that in cases where the result is
1943 "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)
1944 are considered at every possible starting position in the subject string. If
1945 PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching
1946 time. The use of PCRE_NO_START_OPTIMIZE at matching time (that is, passing it
1947 to <b>pcre_exec()</b>) disables JIT execution; in this situation, matching is
1948 always done using interpretively.
1951 Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.
1952 Consider the pattern
1956 When this is compiled, PCRE records the fact that a match must start with the
1957 character "A". Suppose the subject string is "DEFABC". The start-up
1958 optimization scans along the subject, finds "A" and runs the first match
1959 attempt from there. The (*COMMIT) item means that the pattern must match the
1960 current starting position, which in this case, it does. However, if the same
1961 match is run with PCRE_NO_START_OPTIMIZE set, the initial scan along the
1962 subject string does not happen. The first match attempt is run starting from
1963 "D" and when this fails, (*COMMIT) prevents any further matches being tried, so
1964 the overall result is "no match". If the pattern is studied, more start-up
1965 optimizations may be used. For example, a minimum length for the subject may be
1966 recorded. Consider the pattern
1970 The minimum length for a match is one character. If the subject is "ABC", there
1971 will be attempts to match "ABC", "BC", "C", and then finally an empty string.
1972 If the pattern is studied, the final attempt does not take place, because PCRE
1973 knows that the subject is too short, and so the (*MARK) is never encountered.
1974 In this case, studying the pattern does not affect the overall match result,
1975 which is still "no match", but it does affect the auxiliary information that is
1980 When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
1981 string is automatically checked when <b>pcre_exec()</b> is subsequently called.
1982 The entire string is checked before any other processing takes place. The value
1983 of <i>startoffset</i> is also checked to ensure that it points to the start of a
1984 UTF-8 character. There is a discussion about the
1985 <a href="pcreunicode.html#utf8strings">validity of UTF-8 strings</a>
1987 <a href="pcreunicode.html"><b>pcreunicode</b></a>
1988 page. If an invalid sequence of bytes is found, <b>pcre_exec()</b> returns the
1989 error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a
1990 truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both
1991 cases, information about the precise nature of the error may also be returned
1992 (see the descriptions of these errors in the section entitled \fIError return
1993 values from\fP <b>pcre_exec()</b>
1994 <a href="#errorlist">below).</a>
1995 If <i>startoffset</i> contains a value that does not point to the start of a
1996 UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is
2000 If you already know that your subject is valid, and you want to skip these
2001 checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
2002 calling <b>pcre_exec()</b>. You might want to do this for the second and
2003 subsequent calls to <b>pcre_exec()</b> if you are making repeated calls to find
2004 all the matches in a single subject string. However, you should be sure that
2005 the value of <i>startoffset</i> points to the start of a character (or the end
2006 of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an
2007 invalid string as a subject or an invalid value of <i>startoffset</i> is
2008 undefined. Your program may crash or loop.
2013 These options turn on the partial matching feature. For backwards
2014 compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match
2015 occurs if the end of the subject string is reached successfully, but there are
2016 not enough subject characters to complete the match. If this happens when
2017 PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, matching continues by
2018 testing any remaining alternatives. Only if no complete match can be found is
2019 PCRE_ERROR_PARTIAL returned instead of PCRE_ERROR_NOMATCH. In other words,
2020 PCRE_PARTIAL_SOFT says that the caller is prepared to handle a partial match,
2021 but only if no complete match can be found.
2024 If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a
2025 partial match is found, <b>pcre_exec()</b> immediately returns
2026 PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words,
2027 when PCRE_PARTIAL_HARD is set, a partial match is considered to be more
2028 important that an alternative complete match.
2031 In both cases, the portion of the string that was inspected when the partial
2032 match was found is set as the first matching string. There is a more detailed
2033 discussion of partial and multi-segment matching, with examples, in the
2034 <a href="pcrepartial.html"><b>pcrepartial</b></a>
2038 The string to be matched by <b>pcre_exec()</b>
2041 The subject string is passed to <b>pcre_exec()</b> as a pointer in
2042 <i>subject</i>, a length in <i>length</i>, and a starting offset in
2043 <i>startoffset</i>. The units for <i>length</i> and <i>startoffset</i> are bytes
2044 for the 8-bit library, 16-bit data items for the 16-bit library, and 32-bit
2045 data items for the 32-bit library.
2048 If <i>startoffset</i> is negative or greater than the length of the subject,
2049 <b>pcre_exec()</b> returns PCRE_ERROR_BADOFFSET. When the starting offset is
2050 zero, the search for a match starts at the beginning of the subject, and this
2051 is by far the most common case. In UTF-8 or UTF-16 mode, the offset must point
2052 to the start of a character, or the end of the subject (in UTF-32 mode, one
2053 data unit equals one character, so all offsets are valid). Unlike the pattern
2054 string, the subject may contain binary zeroes.
2057 A non-zero starting offset is useful when searching for another match in the
2058 same subject by calling <b>pcre_exec()</b> again after a previous success.
2059 Setting <i>startoffset</i> differs from just passing over a shortened string and
2060 setting PCRE_NOTBOL in the case of a pattern that begins with any kind of
2061 lookbehind. For example, consider the pattern
2065 which finds occurrences of "iss" in the middle of words. (\B matches only if
2066 the current position in the subject is not a word boundary.) When applied to
2067 the string "Mississipi" the first call to <b>pcre_exec()</b> finds the first
2068 occurrence. If <b>pcre_exec()</b> is called again with just the remainder of the
2069 subject, namely "issipi", it does not match, because \B is always false at the
2070 start of the subject, which is deemed to be a word boundary. However, if
2071 <b>pcre_exec()</b> is passed the entire string again, but with <i>startoffset</i>
2072 set to 4, it finds the second occurrence of "iss" because it is able to look
2073 behind the starting point to discover that it is preceded by a letter.
2076 Finding all the matches in a subject is tricky when the pattern can match an
2077 empty string. It is possible to emulate Perl's /g behaviour by first trying the
2078 match again at the same offset, with the PCRE_NOTEMPTY_ATSTART and
2079 PCRE_ANCHORED options, and then if that fails, advancing the starting offset
2080 and trying an ordinary match again. There is some code that demonstrates how to
2082 <a href="pcredemo.html"><b>pcredemo</b></a>
2083 sample program. In the most general case, you have to check to see if the
2084 newline convention recognizes CRLF as a newline, and if so, and the current
2085 character is CR followed by LF, advance the starting offset by two characters
2089 If a non-zero starting offset is passed when the pattern is anchored, one
2090 attempt to match at the given offset is made. This can only succeed if the
2091 pattern does not require the match to be at the start of the subject.
2094 How <b>pcre_exec()</b> returns captured substrings
2097 In general, a pattern matches a certain portion of the subject, and in
2098 addition, further substrings from the subject may be picked out by parts of the
2099 pattern. Following the usage in Jeffrey Friedl's book, this is called
2100 "capturing" in what follows, and the phrase "capturing subpattern" is used for
2101 a fragment of a pattern that picks out a substring. PCRE supports several other
2102 kinds of parenthesized subpattern that do not cause substrings to be captured.
2105 Captured substrings are returned to the caller via a vector of integers whose
2106 address is passed in <i>ovector</i>. The number of elements in the vector is
2107 passed in <i>ovecsize</i>, which must be a non-negative number. <b>Note</b>: this
2108 argument is NOT the size of <i>ovector</i> in bytes.
2111 The first two-thirds of the vector is used to pass back captured substrings,
2112 each substring using a pair of integers. The remaining third of the vector is
2113 used as workspace by <b>pcre_exec()</b> while matching capturing subpatterns,
2114 and is not available for passing back information. The number passed in
2115 <i>ovecsize</i> should always be a multiple of three. If it is not, it is
2119 When a match is successful, information about captured substrings is returned
2120 in pairs of integers, starting at the beginning of <i>ovector</i>, and
2121 continuing up to two-thirds of its length at the most. The first element of
2122 each pair is set to the offset of the first character in a substring, and the
2123 second is set to the offset of the first character after the end of a
2124 substring. These values are always data unit offsets, even in UTF mode. They
2125 are byte offsets in the 8-bit library, 16-bit data item offsets in the 16-bit
2126 library, and 32-bit data item offsets in the 32-bit library. <b>Note</b>: they
2127 are not character counts.
2130 The first pair of integers, <i>ovector[0]</i> and <i>ovector[1]</i>, identify the
2131 portion of the subject string matched by the entire pattern. The next pair is
2132 used for the first capturing subpattern, and so on. The value returned by
2133 <b>pcre_exec()</b> is one more than the highest numbered pair that has been set.
2134 For example, if two substrings have been captured, the returned value is 3. If
2135 there are no capturing subpatterns, the return value from a successful match is
2136 1, indicating that just the first pair of offsets has been set.
2139 If a capturing subpattern is matched repeatedly, it is the last portion of the
2140 string that it matched that is returned.
2143 If the vector is too small to hold all the captured substring offsets, it is
2144 used as far as possible (up to two-thirds of its length), and the function
2145 returns a value of zero. If neither the actual string matched nor any captured
2146 substrings are of interest, <b>pcre_exec()</b> may be called with <i>ovector</i>
2147 passed as NULL and <i>ovecsize</i> as zero. However, if the pattern contains
2148 back references and the <i>ovector</i> is not big enough to remember the related
2149 substrings, PCRE has to get additional memory for use during matching. Thus it
2150 is usually advisable to supply an <i>ovector</i> of reasonable size.
2153 There are some cases where zero is returned (indicating vector overflow) when
2154 in fact the vector is exactly the right size for the final match. For example,
2155 consider the pattern
2159 If a vector of 6 elements (allowing for only 1 captured substring) is given
2160 with subject string "abd", <b>pcre_exec()</b> will try to set the second
2161 captured string, thereby recording a vector overflow, before failing to match
2162 "c" and backing up to try the second alternative. The zero return, however,
2163 does correctly indicate that the maximum number of slots (namely 2) have been
2164 filled. In similar cases where there is temporary overflow, but the final
2165 number of used slots is actually less than the maximum, a non-zero value is
2169 The <b>pcre_fullinfo()</b> function can be used to find out how many capturing
2170 subpatterns there are in a compiled pattern. The smallest size for
2171 <i>ovector</i> that will allow for <i>n</i> captured substrings, in addition to
2172 the offsets of the substring matched by the whole pattern, is (<i>n</i>+1)*3.
2175 It is possible for capturing subpattern number <i>n+1</i> to match some part of
2176 the subject when subpattern <i>n</i> has not been used at all. For example, if
2177 the string "abc" is matched against the pattern (a|(z))(bc) the return from the
2178 function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
2179 happens, both values in the offset pairs corresponding to unused subpatterns
2183 Offset values that correspond to unused subpatterns at the end of the
2184 expression are also set to -1. For example, if the string "abc" is matched
2185 against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
2186 return from the function is 2, because the highest used capturing subpattern
2187 number is 1, and the offsets for for the second and third capturing subpatterns
2188 (assuming the vector is large enough, of course) are set to -1.
2191 <b>Note</b>: Elements in the first two-thirds of <i>ovector</i> that do not
2192 correspond to capturing parentheses in the pattern are never changed. That is,
2193 if a pattern contains <i>n</i> capturing parentheses, no more than
2194 <i>ovector[0]</i> to <i>ovector[2n+1]</i> are set by <b>pcre_exec()</b>. The other
2195 elements (in the first two-thirds) retain whatever values they previously had.
2198 Some convenience functions are provided for extracting the captured substrings
2199 as separate strings. These are described below.
2200 <a name="errorlist"></a></P>
2202 Error return values from <b>pcre_exec()</b>
2205 If <b>pcre_exec()</b> fails, it returns a negative number. The following are
2206 defined in the header file:
2208 PCRE_ERROR_NOMATCH (-1)
2210 The subject string did not match the pattern.
2212 PCRE_ERROR_NULL (-2)
2214 Either <i>code</i> or <i>subject</i> was passed as NULL, or <i>ovector</i> was
2215 NULL and <i>ovecsize</i> was not zero.
2217 PCRE_ERROR_BADOPTION (-3)
2219 An unrecognized bit was set in the <i>options</i> argument.
2221 PCRE_ERROR_BADMAGIC (-4)
2223 PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch
2224 the case when it is passed a junk pointer and to detect when a pattern that was
2225 compiled in an environment of one endianness is run in an environment with the
2226 other endianness. This is the error that PCRE gives when the magic number is
2229 PCRE_ERROR_UNKNOWN_OPCODE (-5)
2231 While running the pattern match, an unknown item was encountered in the
2232 compiled pattern. This error could be caused by a bug in PCRE or by overwriting
2233 of the compiled pattern.
2235 PCRE_ERROR_NOMEMORY (-6)
2237 If a pattern contains back references, but the <i>ovector</i> that is passed to
2238 <b>pcre_exec()</b> is not big enough to remember the referenced substrings, PCRE
2239 gets a block of memory at the start of matching to use for this purpose. If the
2240 call via <b>pcre_malloc()</b> fails, this error is given. The memory is
2241 automatically freed at the end of matching.
2244 This error is also given if <b>pcre_stack_malloc()</b> fails in
2245 <b>pcre_exec()</b>. This can happen only when PCRE has been compiled with
2246 <b>--disable-stack-for-recursion</b>.
2248 PCRE_ERROR_NOSUBSTRING (-7)
2250 This error is used by the <b>pcre_copy_substring()</b>,
2251 <b>pcre_get_substring()</b>, and <b>pcre_get_substring_list()</b> functions (see
2252 below). It is never returned by <b>pcre_exec()</b>.
2254 PCRE_ERROR_MATCHLIMIT (-8)
2256 The backtracking limit, as specified by the <i>match_limit</i> field in a
2257 <b>pcre_extra</b> structure (or defaulted) was reached. See the description
2260 PCRE_ERROR_CALLOUT (-9)
2262 This error is never generated by <b>pcre_exec()</b> itself. It is provided for
2263 use by callout functions that want to yield a distinctive error code. See the
2264 <a href="pcrecallout.html"><b>pcrecallout</b></a>
2265 documentation for details.
2267 PCRE_ERROR_BADUTF8 (-10)
2269 A string that contains an invalid UTF-8 byte sequence was passed as a subject,
2270 and the PCRE_NO_UTF8_CHECK option was not set. If the size of the output vector
2271 (<i>ovecsize</i>) is at least 2, the byte offset to the start of the the invalid
2272 UTF-8 character is placed in the first element, and a reason code is placed in
2273 the second element. The reason codes are listed in the
2274 <a href="#badutf8reasons">following section.</a>
2275 For backward compatibility, if PCRE_PARTIAL_HARD is set and the problem is a
2276 truncated UTF-8 character at the end of the subject (reason codes 1 to 5),
2277 PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8.
2279 PCRE_ERROR_BADUTF8_OFFSET (-11)
2281 The UTF-8 byte sequence that was passed as a subject was checked and found to
2282 be valid (the PCRE_NO_UTF8_CHECK option was not set), but the value of
2283 <i>startoffset</i> did not point to the beginning of a UTF-8 character or the
2286 PCRE_ERROR_PARTIAL (-12)
2288 The subject string did not match, but it did match partially. See the
2289 <a href="pcrepartial.html"><b>pcrepartial</b></a>
2290 documentation for details of partial matching.
2292 PCRE_ERROR_BADPARTIAL (-13)
2294 This code is no longer in use. It was formerly returned when the PCRE_PARTIAL
2295 option was used with a compiled pattern containing items that were not
2296 supported for partial matching. From release 8.00 onwards, there are no
2297 restrictions on partial matching.
2299 PCRE_ERROR_INTERNAL (-14)
2301 An unexpected internal error has occurred. This error could be caused by a bug
2302 in PCRE or by overwriting of the compiled pattern.
2304 PCRE_ERROR_BADCOUNT (-15)
2306 This error is given if the value of the <i>ovecsize</i> argument is negative.
2308 PCRE_ERROR_RECURSIONLIMIT (-21)
2310 The internal recursion limit, as specified by the <i>match_limit_recursion</i>
2311 field in a <b>pcre_extra</b> structure (or defaulted) was reached. See the
2314 PCRE_ERROR_BADNEWLINE (-23)
2316 An invalid combination of PCRE_NEWLINE_<i>xxx</i> options was given.
2318 PCRE_ERROR_BADOFFSET (-24)
2320 The value of <i>startoffset</i> was negative or greater than the length of the
2321 subject, that is, the value in <i>length</i>.
2323 PCRE_ERROR_SHORTUTF8 (-25)
2325 This error is returned instead of PCRE_ERROR_BADUTF8 when the subject string
2326 ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD option is set.
2327 Information about the failure is returned as for PCRE_ERROR_BADUTF8. It is in
2328 fact sufficient to detect this case, but this special error code for
2329 PCRE_PARTIAL_HARD precedes the implementation of returned information; it is
2330 retained for backwards compatibility.
2332 PCRE_ERROR_RECURSELOOP (-26)
2334 This error is returned when <b>pcre_exec()</b> detects a recursion loop within
2335 the pattern. Specifically, it means that either the whole pattern or a
2336 subpattern has been called recursively for the second time at the same position
2337 in the subject string. Some simple patterns that might do this are detected and
2338 faulted at compile time, but more complicated cases, in particular mutual
2339 recursions between two different subpatterns, cannot be detected until run
2342 PCRE_ERROR_JIT_STACKLIMIT (-27)
2344 This error is returned when a pattern that was successfully studied using a
2345 JIT compile option is being matched, but the memory available for the
2346 just-in-time processing stack is not large enough. See the
2347 <a href="pcrejit.html"><b>pcrejit</b></a>
2348 documentation for more details.
2350 PCRE_ERROR_BADMODE (-28)
2352 This error is given if a pattern that was compiled by the 8-bit library is
2353 passed to a 16-bit or 32-bit library function, or vice versa.
2355 PCRE_ERROR_BADENDIANNESS (-29)
2357 This error is given if a pattern that was compiled and saved is reloaded on a
2358 host with different endianness. The utility function
2359 <b>pcre_pattern_to_host_byte_order()</b> can be used to convert such a pattern
2360 so that it runs on the new host.
2362 PCRE_ERROR_JIT_BADOPTION
2364 This error is returned when a pattern that was successfully studied using a JIT
2365 compile option is being matched, but the matching mode (partial or complete
2366 match) does not correspond to any JIT compilation mode. When the JIT fast path
2367 function is used, this error may be also given for invalid options. See the
2368 <a href="pcrejit.html"><b>pcrejit</b></a>
2369 documentation for more details.
2371 PCRE_ERROR_BADLENGTH (-32)
2373 This error is given if <b>pcre_exec()</b> is called with a negative value for
2374 the <i>length</i> argument.
2377 Error numbers -16 to -20, -22, and 30 are not used by <b>pcre_exec()</b>.
2378 <a name="badutf8reasons"></a></P>
2380 Reason codes for invalid UTF-8 strings
2383 This section applies only to the 8-bit library. The corresponding information
2384 for the 16-bit and 32-bit libraries is given in the
2385 <a href="pcre16.html"><b>pcre16</b></a>
2387 <a href="pcre32.html"><b>pcre32</b></a>
2391 When <b>pcre_exec()</b> returns either PCRE_ERROR_BADUTF8 or
2392 PCRE_ERROR_SHORTUTF8, and the size of the output vector (<i>ovecsize</i>) is at
2393 least 2, the offset of the start of the invalid UTF-8 character is placed in
2394 the first output vector element (<i>ovector[0]</i>) and a reason code is placed
2395 in the second element (<i>ovector[1]</i>). The reason codes are given names in
2396 the <b>pcre.h</b> header file:
2404 The string ends with a truncated UTF-8 character; the code specifies how many
2405 bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be
2406 no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279)
2407 allows for up to 6 bytes, and this is checked first; hence the possibility of
2408 4 or 5 missing bytes.
2416 The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the
2417 character do not have the binary value 0b10 (that is, either the most
2418 significant bit is 0, or the next bit is 1).
2423 A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long;
2424 these code points are excluded by RFC 3629.
2428 A 4-byte character has a value greater than 0x10fff; these code points are
2429 excluded by RFC 3629.
2433 A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of
2434 code points are reserved by RFC 3629 for use with UTF-16, and so are excluded
2443 A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a
2444 value that can be represented by fewer bytes, which is invalid. For example,
2445 the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just
2450 The two most significant bits of the first byte of a character have the binary
2451 value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a
2452 byte can only validly occur as the second or subsequent byte of a multi-byte
2457 The first byte of a character has the value 0xfe or 0xff. These values can
2458 never occur in a valid UTF-8 string.
2462 This error code was formerly used when the presence of a so-called
2463 "non-character" caused an error. Unicode corrigendum #9 makes it clear that
2464 such characters should not cause a string to be rejected, and so this code is
2465 no longer in use and is never returned.
2467 <br><a name="SEC18" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a><br>
2469 <b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
2470 <b> int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b>
2471 <b> int <i>buffersize</i>);</b>
2474 <b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
2475 <b> int <i>stringcount</i>, int <i>stringnumber</i>,</b>
2476 <b> const char **<i>stringptr</i>);</b>
2479 <b>int pcre_get_substring_list(const char *<i>subject</i>,</b>
2480 <b> int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b>
2483 Captured substrings can be accessed directly by using the offsets returned by
2484 <b>pcre_exec()</b> in <i>ovector</i>. For convenience, the functions
2485 <b>pcre_copy_substring()</b>, <b>pcre_get_substring()</b>, and
2486 <b>pcre_get_substring_list()</b> are provided for extracting captured substrings
2487 as new, separate, zero-terminated strings. These functions identify substrings
2488 by number. The next section describes functions for extracting named
2492 A substring that contains a binary zero is correctly extracted and has a
2493 further zero added on the end, but the result is not, of course, a C string.
2494 However, you can process such a string by referring to the length that is
2495 returned by <b>pcre_copy_substring()</b> and <b>pcre_get_substring()</b>.
2496 Unfortunately, the interface to <b>pcre_get_substring_list()</b> is not adequate
2497 for handling strings containing binary zeros, because the end of the final
2498 string is not independently indicated.
2501 The first three arguments are the same for all three of these functions:
2502 <i>subject</i> is the subject string that has just been successfully matched,
2503 <i>ovector</i> is a pointer to the vector of integer offsets that was passed to
2504 <b>pcre_exec()</b>, and <i>stringcount</i> is the number of substrings that were
2505 captured by the match, including the substring that matched the entire regular
2506 expression. This is the value returned by <b>pcre_exec()</b> if it is greater
2507 than zero. If <b>pcre_exec()</b> returned zero, indicating that it ran out of
2508 space in <i>ovector</i>, the value passed as <i>stringcount</i> should be the
2509 number of elements in the vector divided by three.
2512 The functions <b>pcre_copy_substring()</b> and <b>pcre_get_substring()</b>
2513 extract a single substring, whose number is given as <i>stringnumber</i>. A
2514 value of zero extracts the substring that matched the entire pattern, whereas
2515 higher values extract the captured substrings. For <b>pcre_copy_substring()</b>,
2516 the string is placed in <i>buffer</i>, whose length is given by
2517 <i>buffersize</i>, while for <b>pcre_get_substring()</b> a new block of memory is
2518 obtained via <b>pcre_malloc</b>, and its address is returned via
2519 <i>stringptr</i>. The yield of the function is the length of the string, not
2520 including the terminating zero, or one of these error codes:
2522 PCRE_ERROR_NOMEMORY (-6)
2524 The buffer was too small for <b>pcre_copy_substring()</b>, or the attempt to get
2525 memory failed for <b>pcre_get_substring()</b>.
2527 PCRE_ERROR_NOSUBSTRING (-7)
2529 There is no substring whose number is <i>stringnumber</i>.
2532 The <b>pcre_get_substring_list()</b> function extracts all available substrings
2533 and builds a list of pointers to them. All this is done in a single block of
2534 memory that is obtained via <b>pcre_malloc</b>. The address of the memory block
2535 is returned via <i>listptr</i>, which is also the start of the list of string
2536 pointers. The end of the list is marked by a NULL pointer. The yield of the
2537 function is zero if all went well, or the error code
2539 PCRE_ERROR_NOMEMORY (-6)
2541 if the attempt to get the memory block failed.
2544 When any of these functions encounter a substring that is unset, which can
2545 happen when capturing subpattern number <i>n+1</i> matches some part of the
2546 subject, but subpattern <i>n</i> has not been used at all, they return an empty
2547 string. This can be distinguished from a genuine zero-length substring by
2548 inspecting the appropriate offset in <i>ovector</i>, which is negative for unset
2552 The two convenience functions <b>pcre_free_substring()</b> and
2553 <b>pcre_free_substring_list()</b> can be used to free the memory returned by
2554 a previous call of <b>pcre_get_substring()</b> or
2555 <b>pcre_get_substring_list()</b>, respectively. They do nothing more than call
2556 the function pointed to by <b>pcre_free</b>, which of course could be called
2557 directly from a C program. However, PCRE is used in some situations where it is
2558 linked via a special interface to another programming language that cannot use
2559 <b>pcre_free</b> directly; it is for these cases that the functions are
2562 <br><a name="SEC19" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a><br>
2564 <b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b>
2565 <b> const char *<i>name</i>);</b>
2568 <b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b>
2569 <b> const char *<i>subject</i>, int *<i>ovector</i>,</b>
2570 <b> int <i>stringcount</i>, const char *<i>stringname</i>,</b>
2571 <b> char *<i>buffer</i>, int <i>buffersize</i>);</b>
2574 <b>int pcre_get_named_substring(const pcre *<i>code</i>,</b>
2575 <b> const char *<i>subject</i>, int *<i>ovector</i>,</b>
2576 <b> int <i>stringcount</i>, const char *<i>stringname</i>,</b>
2577 <b> const char **<i>stringptr</i>);</b>
2580 To extract a substring by name, you first have to find associated number.
2581 For example, for this pattern
2583 (a+)b(?<xxx>\d+)...
2585 the number of the subpattern called "xxx" is 2. If the name is known to be
2586 unique (PCRE_DUPNAMES was not set), you can find the number from the name by
2587 calling <b>pcre_get_stringnumber()</b>. The first argument is the compiled
2588 pattern, and the second is the name. The yield of the function is the
2589 subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of
2593 Given the number, you can extract the substring directly, or use one of the
2594 functions described in the previous section. For convenience, there are also
2595 two functions that do the whole job.
2598 Most of the arguments of <b>pcre_copy_named_substring()</b> and
2599 <b>pcre_get_named_substring()</b> are the same as those for the similarly named
2600 functions that extract by number. As these are described in the previous
2601 section, they are not re-described here. There are just two differences:
2604 First, instead of a substring number, a substring name is given. Second, there
2605 is an extra argument, given at the start, which is a pointer to the compiled
2606 pattern. This is needed in order to gain access to the name-to-number
2610 These functions call <b>pcre_get_stringnumber()</b>, and if it succeeds, they
2611 then call <b>pcre_copy_substring()</b> or <b>pcre_get_substring()</b>, as
2612 appropriate. <b>NOTE:</b> If PCRE_DUPNAMES is set and there are duplicate names,
2613 the behaviour may not be what you want (see the next section).
2616 <b>Warning:</b> If the pattern uses the (?| feature to set up multiple
2617 subpatterns with the same number, as described in the
2618 <a href="pcrepattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a>
2620 <a href="pcrepattern.html"><b>pcrepattern</b></a>
2621 page, you cannot use names to distinguish the different subpatterns, because
2622 names are not included in the compiled code. The matching process uses only
2623 numbers. For this reason, the use of different names for subpatterns of the
2624 same number causes an error at compile time.
2626 <br><a name="SEC20" href="#TOC1">DUPLICATE SUBPATTERN NAMES</a><br>
2628 <b>int pcre_get_stringtable_entries(const pcre *<i>code</i>,</b>
2629 <b> const char *<i>name</i>, char **<i>first</i>, char **<i>last</i>);</b>
2632 When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
2633 are not required to be unique. (Duplicate names are always allowed for
2634 subpatterns with the same number, created by using the (?| feature. Indeed, if
2635 such subpatterns are named, they are required to use the same names.)
2638 Normally, patterns with duplicate names are such that in any one match, only
2639 one of the named subpatterns participates. An example is shown in the
2640 <a href="pcrepattern.html"><b>pcrepattern</b></a>
2644 When duplicates are present, <b>pcre_copy_named_substring()</b> and
2645 <b>pcre_get_named_substring()</b> return the first substring corresponding to
2646 the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
2647 returned; no data is returned. The <b>pcre_get_stringnumber()</b> function
2648 returns one of the numbers that are associated with the name, but it is not
2649 defined which it is.
2652 If you want to get full details of all captured substrings for a given name,
2653 you must use the <b>pcre_get_stringtable_entries()</b> function. The first
2654 argument is the compiled pattern, and the second is the name. The third and
2655 fourth are pointers to variables which are updated by the function. After it
2656 has run, they point to the first and last entries in the name-to-number table
2657 for the given name. The function itself returns the length of each entry, or
2658 PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
2659 described above in the section entitled <i>Information about a pattern</i>
2660 <a href="#infoaboutpattern">above.</a>
2661 Given all the relevant entries for the name, you can extract each of their
2662 numbers, and hence the captured data, if any.
2664 <br><a name="SEC21" href="#TOC1">FINDING ALL POSSIBLE MATCHES</a><br>
2666 The traditional matching function uses a similar algorithm to Perl, which stops
2667 when it finds the first match, starting at a given point in the subject. If you
2668 want to find all possible matches, or the longest possible match, consider
2669 using the alternative matching function (see below) instead. If you cannot use
2670 the alternative function, but still need to find all possible matches, you
2671 can kludge it up by making use of the callout facility, which is described in
2673 <a href="pcrecallout.html"><b>pcrecallout</b></a>
2677 What you have to do is to insert a callout right at the end of the pattern.
2678 When your callout function is called, extract and save the current matched
2679 substring. Then return 1, which forces <b>pcre_exec()</b> to backtrack and try
2680 other alternatives. Ultimately, when it runs out of matches, <b>pcre_exec()</b>
2681 will yield PCRE_ERROR_NOMATCH.
2683 <br><a name="SEC22" href="#TOC1">OBTAINING AN ESTIMATE OF STACK USAGE</a><br>
2685 Matching certain patterns using <b>pcre_exec()</b> can use a lot of process
2686 stack, which in certain environments can be rather limited in size. Some users
2687 find it helpful to have an estimate of the amount of stack that is used by
2688 <b>pcre_exec()</b>, to help them set recursion limits, as described in the
2689 <a href="pcrestack.html"><b>pcrestack</b></a>
2690 documentation. The estimate that is output by <b>pcretest</b> when called with
2691 the <b>-m</b> and <b>-C</b> options is obtained by calling <b>pcre_exec</b> with
2692 the values NULL, NULL, NULL, -999, and -999 for its first five arguments.
2695 Normally, if its first argument is NULL, <b>pcre_exec()</b> immediately returns
2696 the negative error code PCRE_ERROR_NULL, but with this special combination of
2697 arguments, it returns instead a negative number whose absolute value is the
2698 approximate stack frame size in bytes. (A negative number is used so that it is
2699 clear that no match has happened.) The value is approximate because in some
2700 cases, recursive calls to <b>pcre_exec()</b> occur when there are one or two
2701 additional variables on the stack.
2704 If PCRE has been compiled to use the heap instead of the stack for recursion,
2705 the value returned is the size of each block that is obtained from the heap.
2706 <a name="dfamatch"></a></P>
2707 <br><a name="SEC23" href="#TOC1">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a><br>
2709 <b>int pcre_dfa_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
2710 <b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
2711 <b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
2712 <b> int *<i>workspace</i>, int <i>wscount</i>);</b>
2715 The function <b>pcre_dfa_exec()</b> is called to match a subject string against
2716 a compiled pattern, using a matching algorithm that scans the subject string
2717 just once, and does not backtrack. This has different characteristics to the
2718 normal algorithm, and is not compatible with Perl. Some of the features of PCRE
2719 patterns are not supported. Nevertheless, there are times when this kind of
2720 matching can be useful. For a discussion of the two matching algorithms, and a
2721 list of features that <b>pcre_dfa_exec()</b> does not support, see the
2722 <a href="pcrematching.html"><b>pcrematching</b></a>
2726 The arguments for the <b>pcre_dfa_exec()</b> function are the same as for
2727 <b>pcre_exec()</b>, plus two extras. The <i>ovector</i> argument is used in a
2728 different way, and this is described below. The other common arguments are used
2729 in the same way as for <b>pcre_exec()</b>, so their description is not repeated
2733 The two additional arguments provide workspace for the function. The workspace
2734 vector should contain at least 20 elements. It is used for keeping track of
2735 multiple paths through the pattern tree. More workspace will be needed for
2736 patterns and subjects where there are a lot of potential matches.
2739 Here is an example of a simple call to <b>pcre_dfa_exec()</b>:
2745 re, /* result of pcre_compile() */
2746 NULL, /* we didn't study the pattern */
2747 "some string", /* the subject string */
2748 11, /* the length of the subject string */
2749 0, /* start at offset 0 in the subject */
2750 0, /* default options */
2751 ovector, /* vector of integers for substring information */
2752 10, /* number of elements (NOT size in bytes) */
2753 wspace, /* working space vector */
2754 20); /* number of elements (NOT size in bytes) */
2758 Option bits for <b>pcre_dfa_exec()</b>
2761 The unused bits of the <i>options</i> argument for <b>pcre_dfa_exec()</b> must be
2762 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_<i>xxx</i>,
2763 PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
2764 PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE,
2765 PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART.
2766 All but the last four of these are exactly the same as for <b>pcre_exec()</b>,
2767 so their description is not repeated here.
2772 These have the same general effect as they do for <b>pcre_exec()</b>, but the
2773 details are slightly different. When PCRE_PARTIAL_HARD is set for
2774 <b>pcre_dfa_exec()</b>, it returns PCRE_ERROR_PARTIAL if the end of the subject
2775 is reached and there is still at least one matching possibility that requires
2776 additional characters. This happens even if some complete matches have also
2777 been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH
2778 is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached,
2779 there have been no complete matches, but there is still at least one matching
2780 possibility. The portion of the string that was inspected when the longest
2781 partial match was found is set as the first matching string in both cases.
2782 There is a more detailed discussion of partial and multi-segment matching, with
2784 <a href="pcrepartial.html"><b>pcrepartial</b></a>
2789 Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
2790 soon as it has found one match. Because of the way the alternative algorithm
2791 works, this is necessarily the shortest possible match at the first possible
2792 matching point in the subject string.
2796 When <b>pcre_dfa_exec()</b> returns a partial match, it is possible to call it
2797 again, with additional subject characters, and have it continue with the same
2798 match. The PCRE_DFA_RESTART option requests this action; when it is set, the
2799 <i>workspace</i> and <i>wscount</i> options must reference the same vector as
2800 before because data about the match so far is left in them after a partial
2801 match. There is more discussion of this facility in the
2802 <a href="pcrepartial.html"><b>pcrepartial</b></a>
2806 Successful returns from <b>pcre_dfa_exec()</b>
2809 When <b>pcre_dfa_exec()</b> succeeds, it may have matched more than one
2810 substring in the subject. Note, however, that all the matches from one run of
2811 the function start at the same point in the subject. The shorter matches are
2812 all initial substrings of the longer matches. For example, if the pattern
2816 is matched against the string
2818 This is <something> <something else> <something further> no more
2820 the three matched strings are
2823 <something> <something else>
2824 <something> <something else> <something further>
2826 On success, the yield of the function is a number greater than zero, which is
2827 the number of matched substrings. The substrings themselves are returned in
2828 <i>ovector</i>. Each string uses two elements; the first is the offset to the
2829 start, and the second is the offset to the end. In fact, all the strings have
2830 the same start offset. (Space could have been saved by giving this only once,
2831 but it was decided to retain some compatibility with the way <b>pcre_exec()</b>
2832 returns data, even though the meaning of the strings is different.)
2835 The strings are returned in reverse order of length; that is, the longest
2836 matching string is given first. If there were too many matches to fit into
2837 <i>ovector</i>, the yield of the function is zero, and the vector is filled with
2838 the longest matches. Unlike <b>pcre_exec()</b>, <b>pcre_dfa_exec()</b> can use
2839 the entire <i>ovector</i> for returning matched strings.
2842 NOTE: PCRE's "auto-possessification" optimization usually applies to character
2843 repeats at the end of a pattern (as well as internally). For example, the
2844 pattern "a\d+" is compiled as if it were "a\d++" because there is no point
2845 even considering the possibility of backtracking into the repeated digits. For
2846 DFA matching, this means that only one possible match is found. If you really
2847 do want multiple matches in such cases, either use an ungreedy repeat
2848 ("a\d+?") or set the PCRE_NO_AUTO_POSSESS option when compiling.
2851 Error returns from <b>pcre_dfa_exec()</b>
2854 The <b>pcre_dfa_exec()</b> function returns a negative number when it fails.
2855 Many of the errors are the same as for <b>pcre_exec()</b>, and these are
2857 <a href="#errorlist">above.</a>
2858 There are in addition the following errors that are specific to
2859 <b>pcre_dfa_exec()</b>:
2861 PCRE_ERROR_DFA_UITEM (-16)
2863 This return is given if <b>pcre_dfa_exec()</b> encounters an item in the pattern
2864 that it does not support, for instance, the use of \C or a back reference.
2866 PCRE_ERROR_DFA_UCOND (-17)
2868 This return is given if <b>pcre_dfa_exec()</b> encounters a condition item that
2869 uses a back reference for the condition, or a test for recursion in a specific
2870 group. These are not supported.
2872 PCRE_ERROR_DFA_UMLIMIT (-18)
2874 This return is given if <b>pcre_dfa_exec()</b> is called with an <i>extra</i>
2875 block that contains a setting of the <i>match_limit</i> or
2876 <i>match_limit_recursion</i> fields. This is not supported (these fields are
2877 meaningless for DFA matching).
2879 PCRE_ERROR_DFA_WSSIZE (-19)
2881 This return is given if <b>pcre_dfa_exec()</b> runs out of space in the
2882 <i>workspace</i> vector.
2884 PCRE_ERROR_DFA_RECURSE (-20)
2886 When a recursive subpattern is processed, the matching function calls itself
2887 recursively, using private vectors for <i>ovector</i> and <i>workspace</i>. This
2888 error is given if the output vector is not large enough. This should be
2889 extremely rare, as a vector of size 1000 is used.
2891 PCRE_ERROR_DFA_BADRESTART (-30)
2893 When <b>pcre_dfa_exec()</b> is called with the <b>PCRE_DFA_RESTART</b> option,
2894 some plausibility checks are made on the contents of the workspace, which
2895 should contain data about the previous partial match. If any of these checks
2896 fail, this error is given.
2898 <br><a name="SEC24" href="#TOC1">SEE ALSO</a><br>
2900 <b>pcre16</b>(3), <b>pcre32</b>(3), <b>pcrebuild</b>(3), <b>pcrecallout</b>(3),
2901 <b>pcrecpp(3)</b>(3), <b>pcrematching</b>(3), <b>pcrepartial</b>(3),
2902 <b>pcreposix</b>(3), <b>pcreprecompile</b>(3), <b>pcresample</b>(3),
2903 <b>pcrestack</b>(3).
2905 <br><a name="SEC25" href="#TOC1">AUTHOR</a><br>
2909 University Computing Service
2911 Cambridge CB2 3QH, England.
2914 <br><a name="SEC26" href="#TOC1">REVISION</a><br>
2916 Last updated: 09 February 2014
2918 Copyright © 1997-2014 University of Cambridge.
2921 Return to the <a href="index.html">PCRE index page</a>.
~ian / pcre3.git / blob