ViewVC logotype

Contents of /code/trunk/doc/html/pcreapi.html

Parent Directory Parent Directory | Revision Log Revision Log

Revision 1339 - (show annotations)
Fri Jun 14 09:09:28 2013 UTC (6 years, 2 months ago) by ph10
File MIME type: text/html
File size: 131958 byte(s)
Update man pages to avoid the use of .ti (which causes difficulties for some 
translation software).
1 <html>
2 <head>
3 <title>pcreapi specification</title>
4 </head>
5 <body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
6 <h1>pcreapi man page</h1>
7 <p>
8 Return to the <a href="index.html">PCRE index page</a>.
9 </p>
10 <p>
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.
14 <br>
15 <ul>
16 <li><a name="TOC1" href="#SEC1">PCRE NATIVE API BASIC FUNCTIONS</a>
18 <li><a name="TOC3" href="#SEC3">PCRE NATIVE API AUXILIARY 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>
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>
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>
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>
42 </ul>
43 <P>
44 <b>#include &#60;pcre.h&#62;</b>
45 </P>
46 <br><a name="SEC1" href="#TOC1">PCRE NATIVE API BASIC FUNCTIONS</a><br>
47 <P>
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>
51 <br>
52 <br>
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>
57 <br>
58 <br>
59 <b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b>
60 <b> const char **<i>errptr</i>);</b>
61 <br>
62 <br>
63 <b>void pcre_free_study(pcre_extra *<i>extra</i>);</b>
64 <br>
65 <br>
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>
69 <br>
70 <br>
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>
75 </P>
77 <P>
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>
82 <br>
83 <br>
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>
87 <br>
88 <br>
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>
93 <br>
94 <br>
95 <b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b>
96 <b> const char *<i>name</i>);</b>
97 <br>
98 <br>
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>
101 <br>
102 <br>
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>
106 <br>
107 <br>
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>
110 <br>
111 <br>
112 <b>void pcre_free_substring(const char *<i>stringptr</i>);</b>
113 <br>
114 <br>
115 <b>void pcre_free_substring_list(const char **<i>stringptr</i>);</b>
116 </P>
117 <br><a name="SEC3" href="#TOC1">PCRE NATIVE API AUXILIARY FUNCTIONS</a><br>
118 <P>
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>
123 <br>
124 <br>
125 <b>pcre_jit_stack *pcre_jit_stack_alloc(int <i>startsize</i>, int <i>maxsize</i>);</b>
126 <br>
127 <br>
128 <b>void pcre_jit_stack_free(pcre_jit_stack *<i>stack</i>);</b>
129 <br>
130 <br>
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>
133 <br>
134 <br>
135 <b>const unsigned char *pcre_maketables(void);</b>
136 <br>
137 <br>
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>
140 <br>
141 <br>
142 <b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b>
143 <br>
144 <br>
145 <b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b>
146 <br>
147 <br>
148 <b>const char *pcre_version(void);</b>
149 <br>
150 <br>
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>
153 </P>
154 <br><a name="SEC4" href="#TOC1">PCRE NATIVE API INDIRECTED FUNCTIONS</a><br>
155 <P>
156 <b>void *(*pcre_malloc)(size_t);</b>
157 <br>
158 <br>
159 <b>void (*pcre_free)(void *);</b>
160 <br>
161 <br>
162 <b>void *(*pcre_stack_malloc)(size_t);</b>
163 <br>
164 <br>
165 <b>void (*pcre_stack_free)(void *);</b>
166 <br>
167 <br>
168 <b>int (*pcre_callout)(pcre_callout_block *);</b>
169 </P>
170 <br><a name="SEC5" href="#TOC1">PCRE 8-BIT, 16-BIT, AND 32-BIT LIBRARIES</a><br>
171 <P>
172 As well as support for 8-bit character strings, PCRE also supports 16-bit
173 strings (from release 8.30) and 32-bit strings (from release 8.32), by means of
174 two additional libraries. They can be built as well as, or instead of, the
175 8-bit library. To avoid too much complication, this document describes the
176 8-bit versions of the functions, with only occasional references to the 16-bit
177 and 32-bit libraries.
178 </P>
179 <P>
180 The 16-bit and 32-bit functions operate in the same way as their 8-bit
181 counterparts; they just use different data types for their arguments and
182 results, and their names start with <b>pcre16_</b> or <b>pcre32_</b> instead of
183 <b>pcre_</b>. For every option that has UTF8 in its name (for example,
184 PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 replaced
185 by UTF16 or UTF32, respectively. This facility is in fact just cosmetic; the
186 16-bit and 32-bit option names define the same bit values.
187 </P>
188 <P>
189 References to bytes and UTF-8 in this document should be read as references to
190 16-bit data units and UTF-16 when using the 16-bit library, or 32-bit data
191 units and UTF-32 when using the 32-bit library, unless specified otherwise.
192 More details of the specific differences for the 16-bit and 32-bit libraries
193 are given in the
194 <a href="pcre16.html"><b>pcre16</b></a>
195 and
196 <a href="pcre32.html"><b>pcre32</b></a>
197 pages.
198 </P>
199 <br><a name="SEC6" href="#TOC1">PCRE API OVERVIEW</a><br>
200 <P>
201 PCRE has its own native API, which is described in this document. There are
202 also some wrapper functions (for the 8-bit library only) that correspond to the
203 POSIX regular expression API, but they do not give access to all the
204 functionality. They are described in the
205 <a href="pcreposix.html"><b>pcreposix</b></a>
206 documentation. Both of these APIs define a set of C function calls. A C++
207 wrapper (again for the 8-bit library only) is also distributed with PCRE. It is
208 documented in the
209 <a href="pcrecpp.html"><b>pcrecpp</b></a>
210 page.
211 </P>
212 <P>
213 The native API C function prototypes are defined in the header file
214 <b>pcre.h</b>, and on Unix-like systems the (8-bit) library itself is called
215 <b>libpcre</b>. It can normally be accessed by adding <b>-lpcre</b> to the
216 command for linking an application that uses PCRE. The header file defines the
217 macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release numbers
218 for the library. Applications can use these to include support for different
219 releases of PCRE.
220 </P>
221 <P>
222 In a Windows environment, if you want to statically link an application program
223 against a non-dll <b>pcre.a</b> file, you must define PCRE_STATIC before
224 including <b>pcre.h</b> or <b>pcrecpp.h</b>, because otherwise the
225 <b>pcre_malloc()</b> and <b>pcre_free()</b> exported functions will be declared
226 <b>__declspec(dllimport)</b>, with unwanted results.
227 </P>
228 <P>
229 The functions <b>pcre_compile()</b>, <b>pcre_compile2()</b>, <b>pcre_study()</b>,
230 and <b>pcre_exec()</b> are used for compiling and matching regular expressions
231 in a Perl-compatible manner. A sample program that demonstrates the simplest
232 way of using them is provided in the file called <i>pcredemo.c</i> in the PCRE
233 source distribution. A listing of this program is given in the
234 <a href="pcredemo.html"><b>pcredemo</b></a>
235 documentation, and the
236 <a href="pcresample.html"><b>pcresample</b></a>
237 documentation describes how to compile and run it.
238 </P>
239 <P>
240 Just-in-time compiler support is an optional feature of PCRE that can be built
241 in appropriate hardware environments. It greatly speeds up the matching
242 performance of many patterns. Simple programs can easily request that it be
243 used if available, by setting an option that is ignored when it is not
244 relevant. More complicated programs might need to make use of the functions
245 <b>pcre_jit_stack_alloc()</b>, <b>pcre_jit_stack_free()</b>, and
246 <b>pcre_assign_jit_stack()</b> in order to control the JIT code's memory usage.
247 </P>
248 <P>
249 From release 8.32 there is also a direct interface for JIT execution, which
250 gives improved performance. The JIT-specific functions are discussed in the
251 <a href="pcrejit.html"><b>pcrejit</b></a>
252 documentation.
253 </P>
254 <P>
255 A second matching function, <b>pcre_dfa_exec()</b>, which is not
256 Perl-compatible, is also provided. This uses a different algorithm for the
257 matching. The alternative algorithm finds all possible matches (at a given
258 point in the subject), and scans the subject just once (unless there are
259 lookbehind assertions). However, this algorithm does not return captured
260 substrings. A description of the two matching algorithms and their advantages
261 and disadvantages is given in the
262 <a href="pcrematching.html"><b>pcrematching</b></a>
263 documentation.
264 </P>
265 <P>
266 In addition to the main compiling and matching functions, there are convenience
267 functions for extracting captured substrings from a subject string that is
268 matched by <b>pcre_exec()</b>. They are:
269 <pre>
270 <b>pcre_copy_substring()</b>
271 <b>pcre_copy_named_substring()</b>
272 <b>pcre_get_substring()</b>
273 <b>pcre_get_named_substring()</b>
274 <b>pcre_get_substring_list()</b>
275 <b>pcre_get_stringnumber()</b>
276 <b>pcre_get_stringtable_entries()</b>
277 </pre>
278 <b>pcre_free_substring()</b> and <b>pcre_free_substring_list()</b> are also
279 provided, to free the memory used for extracted strings.
280 </P>
281 <P>
282 The function <b>pcre_maketables()</b> is used to build a set of character tables
283 in the current locale for passing to <b>pcre_compile()</b>, <b>pcre_exec()</b>,
284 or <b>pcre_dfa_exec()</b>. This is an optional facility that is provided for
285 specialist use. Most commonly, no special tables are passed, in which case
286 internal tables that are generated when PCRE is built are used.
287 </P>
288 <P>
289 The function <b>pcre_fullinfo()</b> is used to find out information about a
290 compiled pattern. The function <b>pcre_version()</b> returns a pointer to a
291 string containing the version of PCRE and its date of release.
292 </P>
293 <P>
294 The function <b>pcre_refcount()</b> maintains a reference count in a data block
295 containing a compiled pattern. This is provided for the benefit of
296 object-oriented applications.
297 </P>
298 <P>
299 The global variables <b>pcre_malloc</b> and <b>pcre_free</b> initially contain
300 the entry points of the standard <b>malloc()</b> and <b>free()</b> functions,
301 respectively. PCRE calls the memory management functions via these variables,
302 so a calling program can replace them if it wishes to intercept the calls. This
303 should be done before calling any PCRE functions.
304 </P>
305 <P>
306 The global variables <b>pcre_stack_malloc</b> and <b>pcre_stack_free</b> are also
307 indirections to memory management functions. These special functions are used
308 only when PCRE is compiled to use the heap for remembering data, instead of
309 recursive function calls, when running the <b>pcre_exec()</b> function. See the
310 <a href="pcrebuild.html"><b>pcrebuild</b></a>
311 documentation for details of how to do this. It is a non-standard way of
312 building PCRE, for use in environments that have limited stacks. Because of the
313 greater use of memory management, it runs more slowly. Separate functions are
314 provided so that special-purpose external code can be used for this case. When
315 used, these functions are always called in a stack-like manner (last obtained,
316 first freed), and always for memory blocks of the same size. There is a
317 discussion about PCRE's stack usage in the
318 <a href="pcrestack.html"><b>pcrestack</b></a>
319 documentation.
320 </P>
321 <P>
322 The global variable <b>pcre_callout</b> initially contains NULL. It can be set
323 by the caller to a "callout" function, which PCRE will then call at specified
324 points during a matching operation. Details are given in the
325 <a href="pcrecallout.html"><b>pcrecallout</b></a>
326 documentation.
327 <a name="newlines"></a></P>
328 <br><a name="SEC7" href="#TOC1">NEWLINES</a><br>
329 <P>
330 PCRE supports five different conventions for indicating line breaks in
331 strings: a single CR (carriage return) character, a single LF (linefeed)
332 character, the two-character sequence CRLF, any of the three preceding, or any
333 Unicode newline sequence. The Unicode newline sequences are the three just
334 mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed,
335 U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
336 (paragraph separator, U+2029).
337 </P>
338 <P>
339 Each of the first three conventions is used by at least one operating system as
340 its standard newline sequence. When PCRE is built, a default can be specified.
341 The default default is LF, which is the Unix standard. When PCRE is run, the
342 default can be overridden, either when a pattern is compiled, or when it is
343 matched.
344 </P>
345 <P>
346 At compile time, the newline convention can be specified by the <i>options</i>
347 argument of <b>pcre_compile()</b>, or it can be specified by special text at the
348 start of the pattern itself; this overrides any other settings. See the
349 <a href="pcrepattern.html"><b>pcrepattern</b></a>
350 page for details of the special character sequences.
351 </P>
352 <P>
353 In the PCRE documentation the word "newline" is used to mean "the character or
354 pair of characters that indicate a line break". The choice of newline
355 convention affects the handling of the dot, circumflex, and dollar
356 metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
357 recognized line ending sequence, the match position advancement for a
358 non-anchored pattern. There is more detail about this in the
359 <a href="#execoptions">section on <b>pcre_exec()</b> options</a>
360 below.
361 </P>
362 <P>
363 The choice of newline convention does not affect the interpretation of
364 the \n or \r escape sequences, nor does it affect what \R matches, which is
365 controlled in a similar way, but by separate options.
366 </P>
367 <br><a name="SEC8" href="#TOC1">MULTITHREADING</a><br>
368 <P>
369 The PCRE functions can be used in multi-threading applications, with the
370 proviso that the memory management functions pointed to by <b>pcre_malloc</b>,
371 <b>pcre_free</b>, <b>pcre_stack_malloc</b>, and <b>pcre_stack_free</b>, and the
372 callout function pointed to by <b>pcre_callout</b>, are shared by all threads.
373 </P>
374 <P>
375 The compiled form of a regular expression is not altered during matching, so
376 the same compiled pattern can safely be used by several threads at once.
377 </P>
378 <P>
379 If the just-in-time optimization feature is being used, it needs separate
380 memory stack areas for each thread. See the
381 <a href="pcrejit.html"><b>pcrejit</b></a>
382 documentation for more details.
383 </P>
384 <br><a name="SEC9" href="#TOC1">SAVING PRECOMPILED PATTERNS FOR LATER USE</a><br>
385 <P>
386 The compiled form of a regular expression can be saved and re-used at a later
387 time, possibly by a different program, and even on a host other than the one on
388 which it was compiled. Details are given in the
389 <a href="pcreprecompile.html"><b>pcreprecompile</b></a>
390 documentation, which includes a description of the
391 <b>pcre_pattern_to_host_byte_order()</b> function. However, compiling a regular
392 expression with one version of PCRE for use with a different version is not
393 guaranteed to work and may cause crashes.
394 </P>
395 <br><a name="SEC10" href="#TOC1">CHECKING BUILD-TIME OPTIONS</a><br>
396 <P>
397 <b>int pcre_config(int <i>what</i>, void *<i>where</i>);</b>
398 </P>
399 <P>
400 The function <b>pcre_config()</b> makes it possible for a PCRE client to
401 discover which optional features have been compiled into the PCRE library. The
402 <a href="pcrebuild.html"><b>pcrebuild</b></a>
403 documentation has more details about these optional features.
404 </P>
405 <P>
406 The first argument for <b>pcre_config()</b> is an integer, specifying which
407 information is required; the second argument is a pointer to a variable into
408 which the information is placed. The returned value is zero on success, or the
409 negative error code PCRE_ERROR_BADOPTION if the value in the first argument is
410 not recognized. The following information is available:
411 <pre>
413 </pre>
414 The output is an integer that is set to one if UTF-8 support is available;
415 otherwise it is set to zero. This value should normally be given to the 8-bit
416 version of this function, <b>pcre_config()</b>. If it is given to the 16-bit
417 or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
418 <pre>
420 </pre>
421 The output is an integer that is set to one if UTF-16 support is available;
422 otherwise it is set to zero. This value should normally be given to the 16-bit
423 version of this function, <b>pcre16_config()</b>. If it is given to the 8-bit
424 or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
425 <pre>
427 </pre>
428 The output is an integer that is set to one if UTF-32 support is available;
429 otherwise it is set to zero. This value should normally be given to the 32-bit
430 version of this function, <b>pcre32_config()</b>. If it is given to the 8-bit
431 or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION.
432 <pre>
434 </pre>
435 The output is an integer that is set to one if support for Unicode character
436 properties is available; otherwise it is set to zero.
437 <pre>
439 </pre>
440 The output is an integer that is set to one if support for just-in-time
441 compiling is available; otherwise it is set to zero.
442 <pre>
444 </pre>
445 The output is a pointer to a zero-terminated "const char *" string. If JIT
446 support is available, the string contains the name of the architecture for
447 which the JIT compiler is configured, for example "x86 32bit (little endian +
448 unaligned)". If JIT support is not available, the result is NULL.
449 <pre>
451 </pre>
452 The output is an integer whose value specifies the default character sequence
453 that is recognized as meaning "newline". The values that are supported in
454 ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for
455 ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the
456 same values. However, the value for LF is normally 21, though some EBCDIC
457 environments use 37. The corresponding values for CRLF are 3349 and 3365. The
458 default should normally correspond to the standard sequence for your operating
459 system.
460 <pre>
462 </pre>
463 The output is an integer whose value indicates what character sequences the \R
464 escape sequence matches by default. A value of 0 means that \R matches any
465 Unicode line ending sequence; a value of 1 means that \R matches only CR, LF,
466 or CRLF. The default can be overridden when a pattern is compiled or matched.
467 <pre>
469 </pre>
470 The output is an integer that contains the number of bytes used for internal
471 linkage in compiled regular expressions. For the 8-bit library, the value can
472 be 2, 3, or 4. For the 16-bit library, the value is either 2 or 4 and is still
473 a number of bytes. For the 32-bit library, the value is either 2 or 4 and is
474 still a number of bytes. The default value of 2 is sufficient for all but the
475 most massive patterns, since it allows the compiled pattern to be up to 64K in
476 size. Larger values allow larger regular expressions to be compiled, at the
477 expense of slower matching.
478 <pre>
480 </pre>
481 The output is an integer that contains the threshold above which the POSIX
482 interface uses <b>malloc()</b> for output vectors. Further details are given in
483 the
484 <a href="pcreposix.html"><b>pcreposix</b></a>
485 documentation.
486 <pre>
488 </pre>
489 The output is a long integer that gives the default limit for the number of
490 internal matching function calls in a <b>pcre_exec()</b> execution. Further
491 details are given with <b>pcre_exec()</b> below.
492 <pre>
494 </pre>
495 The output is a long integer that gives the default limit for the depth of
496 recursion when calling the internal matching function in a <b>pcre_exec()</b>
497 execution. Further details are given with <b>pcre_exec()</b> below.
498 <pre>
500 </pre>
501 The output is an integer that is set to one if internal recursion when running
502 <b>pcre_exec()</b> is implemented by recursive function calls that use the stack
503 to remember their state. This is the usual way that PCRE is compiled. The
504 output is zero if PCRE was compiled to use blocks of data on the heap instead
505 of recursive function calls. In this case, <b>pcre_stack_malloc</b> and
506 <b>pcre_stack_free</b> are called to manage memory blocks on the heap, thus
507 avoiding the use of the stack.
508 </P>
509 <br><a name="SEC11" href="#TOC1">COMPILING A PATTERN</a><br>
510 <P>
511 <b>pcre *pcre_compile(const char *<i>pattern</i>, int <i>options</i>,</b>
512 <b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
513 <b> const unsigned char *<i>tableptr</i>);</b>
514 <br>
515 <br>
516 <b>pcre *pcre_compile2(const char *<i>pattern</i>, int <i>options</i>,</b>
517 <b> int *<i>errorcodeptr</i>,</b>
518 <b> const char **<i>errptr</i>, int *<i>erroffset</i>,</b>
519 <b> const unsigned char *<i>tableptr</i>);</b>
520 </P>
521 <P>
522 Either of the functions <b>pcre_compile()</b> or <b>pcre_compile2()</b> can be
523 called to compile a pattern into an internal form. The only difference between
524 the two interfaces is that <b>pcre_compile2()</b> has an additional argument,
525 <i>errorcodeptr</i>, via which a numerical error code can be returned. To avoid
526 too much repetition, we refer just to <b>pcre_compile()</b> below, but the
527 information applies equally to <b>pcre_compile2()</b>.
528 </P>
529 <P>
530 The pattern is a C string terminated by a binary zero, and is passed in the
531 <i>pattern</i> argument. A pointer to a single block of memory that is obtained
532 via <b>pcre_malloc</b> is returned. This contains the compiled code and related
533 data. The <b>pcre</b> type is defined for the returned block; this is a typedef
534 for a structure whose contents are not externally defined. It is up to the
535 caller to free the memory (via <b>pcre_free</b>) when it is no longer required.
536 </P>
537 <P>
538 Although the compiled code of a PCRE regex is relocatable, that is, it does not
539 depend on memory location, the complete <b>pcre</b> data block is not
540 fully relocatable, because it may contain a copy of the <i>tableptr</i>
541 argument, which is an address (see below).
542 </P>
543 <P>
544 The <i>options</i> argument contains various bit settings that affect the
545 compilation. It should be zero if no options are required. The available
546 options are described below. Some of them (in particular, those that are
547 compatible with Perl, but some others as well) can also be set and unset from
548 within the pattern (see the detailed description in the
549 <a href="pcrepattern.html"><b>pcrepattern</b></a>
550 documentation). For those options that can be different in different parts of
551 the pattern, the contents of the <i>options</i> argument specifies their
552 settings at the start of compilation and execution. The PCRE_ANCHORED,
553 PCRE_BSR_<i>xxx</i>, PCRE_NEWLINE_<i>xxx</i>, PCRE_NO_UTF8_CHECK, and
554 PCRE_NO_START_OPTIMIZE options can be set at the time of matching as well as at
555 compile time.
556 </P>
557 <P>
558 If <i>errptr</i> is NULL, <b>pcre_compile()</b> returns NULL immediately.
559 Otherwise, if compilation of a pattern fails, <b>pcre_compile()</b> returns
560 NULL, and sets the variable pointed to by <i>errptr</i> to point to a textual
561 error message. This is a static string that is part of the library. You must
562 not try to free it. Normally, the offset from the start of the pattern to the
563 data unit that was being processed when the error was discovered is placed in
564 the variable pointed to by <i>erroffset</i>, which must not be NULL (if it is,
565 an immediate error is given). However, for an invalid UTF-8 or UTF-16 string,
566 the offset is that of the first data unit of the failing character.
567 </P>
568 <P>
569 Some errors are not detected until the whole pattern has been scanned; in these
570 cases, the offset passed back is the length of the pattern. Note that the
571 offset is in data units, not characters, even in a UTF mode. It may sometimes
572 point into the middle of a UTF-8 or UTF-16 character.
573 </P>
574 <P>
575 If <b>pcre_compile2()</b> is used instead of <b>pcre_compile()</b>, and the
576 <i>errorcodeptr</i> argument is not NULL, a non-zero error code number is
577 returned via this argument in the event of an error. This is in addition to the
578 textual error message. Error codes and messages are listed below.
579 </P>
580 <P>
581 If the final argument, <i>tableptr</i>, is NULL, PCRE uses a default set of
582 character tables that are built when PCRE is compiled, using the default C
583 locale. Otherwise, <i>tableptr</i> must be an address that is the result of a
584 call to <b>pcre_maketables()</b>. This value is stored with the compiled
585 pattern, and used again by <b>pcre_exec()</b>, unless another table pointer is
586 passed to it. For more discussion, see the section on locale support below.
587 </P>
588 <P>
589 This code fragment shows a typical straightforward call to <b>pcre_compile()</b>:
590 <pre>
591 pcre *re;
592 const char *error;
593 int erroffset;
594 re = pcre_compile(
595 "^A.*Z", /* the pattern */
596 0, /* default options */
597 &error, /* for error message */
598 &erroffset, /* for error offset */
599 NULL); /* use default character tables */
600 </pre>
601 The following names for option bits are defined in the <b>pcre.h</b> header
602 file:
603 <pre>
605 </pre>
606 If this bit is set, the pattern is forced to be "anchored", that is, it is
607 constrained to match only at the first matching point in the string that is
608 being searched (the "subject string"). This effect can also be achieved by
609 appropriate constructs in the pattern itself, which is the only way to do it in
610 Perl.
611 <pre>
613 </pre>
614 If this bit is set, <b>pcre_compile()</b> automatically inserts callout items,
615 all with number 255, before each pattern item. For discussion of the callout
616 facility, see the
617 <a href="pcrecallout.html"><b>pcrecallout</b></a>
618 documentation.
619 <pre>
622 </pre>
623 These options (which are mutually exclusive) control what the \R escape
624 sequence matches. The choice is either to match only CR, LF, or CRLF, or to
625 match any Unicode newline sequence. The default is specified when PCRE is
626 built. It can be overridden from within the pattern, or by setting an option
627 when a compiled pattern is matched.
628 <pre>
630 </pre>
631 If this bit is set, letters in the pattern match both upper and lower case
632 letters. It is equivalent to Perl's /i option, and it can be changed within a
633 pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the
634 concept of case for characters whose values are less than 128, so caseless
635 matching is always possible. For characters with higher values, the concept of
636 case is supported if PCRE is compiled with Unicode property support, but not
637 otherwise. If you want to use caseless matching for characters 128 and above,
638 you must ensure that PCRE is compiled with Unicode property support as well as
639 with UTF-8 support.
640 <pre>
642 </pre>
643 If this bit is set, a dollar metacharacter in the pattern matches only at the
644 end of the subject string. Without this option, a dollar also matches
645 immediately before a newline at the end of the string (but not before any other
646 newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set.
647 There is no equivalent to this option in Perl, and no way to set it within a
648 pattern.
649 <pre>
651 </pre>
652 If this bit is set, a dot metacharacter in the pattern matches a character of
653 any value, including one that indicates a newline. However, it only ever
654 matches one character, even if newlines are coded as CRLF. Without this option,
655 a dot does not match when the current position is at a newline. This option is
656 equivalent to Perl's /s option, and it can be changed within a pattern by a
657 (?s) option setting. A negative class such as [^a] always matches newline
658 characters, independent of the setting of this option.
659 <pre>
661 </pre>
662 If this bit is set, names used to identify capturing subpatterns need not be
663 unique. This can be helpful for certain types of pattern when it is known that
664 only one instance of the named subpattern can ever be matched. There are more
665 details of named subpatterns below; see also the
666 <a href="pcrepattern.html"><b>pcrepattern</b></a>
667 documentation.
668 <pre>
670 </pre>
671 If this bit is set, white space data characters in the pattern are totally
672 ignored except when escaped or inside a character class. White space does not
673 include the VT character (code 11). In addition, characters between an
674 unescaped # outside a character class and the next newline, inclusive, are also
675 ignored. This is equivalent to Perl's /x option, and it can be changed within a
676 pattern by a (?x) option setting.
677 </P>
678 <P>
679 Which characters are interpreted as newlines is controlled by the options
680 passed to <b>pcre_compile()</b> or by a special sequence at the start of the
681 pattern, as described in the section entitled
682 <a href="pcrepattern.html#newlines">"Newline conventions"</a>
683 in the <b>pcrepattern</b> documentation. Note that the end of this type of
684 comment is a literal newline sequence in the pattern; escape sequences that
685 happen to represent a newline do not count.
686 </P>
687 <P>
688 This option makes it possible to include comments inside complicated patterns.
689 Note, however, that this applies only to data characters. White space characters
690 may never appear within special character sequences in a pattern, for example
691 within the sequence (?( that introduces a conditional subpattern.
692 <pre>
694 </pre>
695 This option was invented in order to turn on additional functionality of PCRE
696 that is incompatible with Perl, but it is currently of very little use. When
697 set, any backslash in a pattern that is followed by a letter that has no
698 special meaning causes an error, thus reserving these combinations for future
699 expansion. By default, as in Perl, a backslash followed by a letter with no
700 special meaning is treated as a literal. (Perl can, however, be persuaded to
701 give an error for this, by running it with the -w option.) There are at present
702 no other features controlled by this option. It can also be set by a (?X)
703 option setting within a pattern.
704 <pre>
706 </pre>
707 If this option is set, an unanchored pattern is required to match before or at
708 the first newline in the subject string, though the matched text may continue
709 over the newline.
710 <pre>
712 </pre>
713 If this option is set, PCRE's behaviour is changed in some ways so that it is
714 compatible with JavaScript rather than Perl. The changes are as follows:
715 </P>
716 <P>
717 (1) A lone closing square bracket in a pattern causes a compile-time error,
718 because this is illegal in JavaScript (by default it is treated as a data
719 character). Thus, the pattern AB]CD becomes illegal when this option is set.
720 </P>
721 <P>
722 (2) At run time, a back reference to an unset subpattern group matches an empty
723 string (by default this causes the current matching alternative to fail). A
724 pattern such as (\1)(a) succeeds when this option is set (assuming it can find
725 an "a" in the subject), whereas it fails by default, for Perl compatibility.
726 </P>
727 <P>
728 (3) \U matches an upper case "U" character; by default \U causes a compile
729 time error (Perl uses \U to upper case subsequent characters).
730 </P>
731 <P>
732 (4) \u matches a lower case "u" character unless it is followed by four
733 hexadecimal digits, in which case the hexadecimal number defines the code point
734 to match. By default, \u causes a compile time error (Perl uses it to upper
735 case the following character).
736 </P>
737 <P>
738 (5) \x matches a lower case "x" character unless it is followed by two
739 hexadecimal digits, in which case the hexadecimal number defines the code point
740 to match. By default, as in Perl, a hexadecimal number is always expected after
741 \x, but it may have zero, one, or two digits (so, for example, \xz matches a
742 binary zero character followed by z).
743 <pre>
745 </pre>
746 By default, for the purposes of matching "start of line" and "end of line",
747 PCRE treats the subject string as consisting of a single line of characters,
748 even if it actually contains newlines. The "start of line" metacharacter (^)
749 matches only at the start of the string, and the "end of line" metacharacter
750 ($) matches only at the end of the string, or before a terminating newline
751 (except when PCRE_DOLLAR_ENDONLY is set). Note, however, that unless
752 PCRE_DOTALL is set, the "any character" metacharacter (.) does not match at a
753 newline. This behaviour (for ^, $, and dot) is the same as Perl.
754 </P>
755 <P>
756 When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
757 match immediately following or immediately before internal newlines in the
758 subject string, respectively, as well as at the very start and end. This is
759 equivalent to Perl's /m option, and it can be changed within a pattern by a
760 (?m) option setting. If there are no newlines in a subject string, or no
761 occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
762 <pre>
764 </pre>
765 This option locks out interpretation of the pattern as UTF-8 (or UTF-16 or
766 UTF-32 in the 16-bit and 32-bit libraries). In particular, it prevents the
767 creator of the pattern from switching to UTF interpretation by starting the
768 pattern with (*UTF). This may be useful in applications that process patterns
769 from external sources. The combination of PCRE_UTF8 and PCRE_NEVER_UTF also
770 causes an error.
771 <pre>
777 </pre>
778 These options override the default newline definition that was chosen when PCRE
779 was built. Setting the first or the second specifies that a newline is
780 indicated by a single character (CR or LF, respectively). Setting
781 PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
782 CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
783 preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
784 that any Unicode newline sequence should be recognized.
785 </P>
786 <P>
787 In an ASCII/Unicode environment, the Unicode newline sequences are the three
788 just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form
789 feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
790 (paragraph separator, U+2029). For the 8-bit library, the last two are
791 recognized only in UTF-8 mode.
792 </P>
793 <P>
794 When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for
795 CR is 0x0d, the same as ASCII. However, the character code for LF is normally
796 0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is
797 not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all
798 less than 256. For more details, see the
799 <a href="pcrebuild.html"><b>pcrebuild</b></a>
800 documentation.
801 </P>
802 <P>
803 The newline setting in the options word uses three bits that are treated
804 as a number, giving eight possibilities. Currently only six are used (default
805 plus the five values above). This means that if you set more than one newline
806 option, the combination may or may not be sensible. For example,
808 other combinations may yield unused numbers and cause an error.
809 </P>
810 <P>
811 The only time that a line break in a pattern is specially recognized when
812 compiling is when PCRE_EXTENDED is set. CR and LF are white space characters,
813 and so are ignored in this mode. Also, an unescaped # outside a character class
814 indicates a comment that lasts until after the next line break sequence. In
815 other circumstances, line break sequences in patterns are treated as literal
816 data.
817 </P>
818 <P>
819 The newline option that is set at compile time becomes the default that is used
820 for <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, but it can be overridden.
821 <pre>
823 </pre>
824 If this option is set, it disables the use of numbered capturing parentheses in
825 the pattern. Any opening parenthesis that is not followed by ? behaves as if it
826 were followed by ?: but named parentheses can still be used for capturing (and
827 they acquire numbers in the usual way). There is no equivalent of this option
828 in Perl.
829 <pre>
831 </pre>
832 This is an option that acts at matching time; that is, it is really an option
833 for <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. If it is set at compile time,
834 it is remembered with the compiled pattern and assumed at matching time. This
835 is necessary if you want to use JIT execution, because the JIT compiler needs
836 to know whether or not this option is set. For details see the discussion of
838 <a href="#execoptions">below.</a>
839 <pre>
841 </pre>
842 This option changes the way PCRE processes \B, \b, \D, \d, \S, \s, \W,
843 \w, and some of the POSIX character classes. By default, only ASCII characters
844 are recognized, but if PCRE_UCP is set, Unicode properties are used instead to
845 classify characters. More details are given in the section on
846 <a href="pcre.html#genericchartypes">generic character types</a>
847 in the
848 <a href="pcrepattern.html"><b>pcrepattern</b></a>
849 page. If you set PCRE_UCP, matching one of the items it affects takes much
850 longer. The option is available only if PCRE has been compiled with Unicode
851 property support.
852 <pre>
854 </pre>
855 This option inverts the "greediness" of the quantifiers so that they are not
856 greedy by default, but become greedy if followed by "?". It is not compatible
857 with Perl. It can also be set by a (?U) option setting within the pattern.
858 <pre>
860 </pre>
861 This option causes PCRE to regard both the pattern and the subject as strings
862 of UTF-8 characters instead of single-byte strings. However, it is available
863 only when PCRE is built to include UTF support. If not, the use of this option
864 provokes an error. Details of how this option changes the behaviour of PCRE are
865 given in the
866 <a href="pcreunicode.html"><b>pcreunicode</b></a>
867 page.
868 <pre>
870 </pre>
871 When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
872 automatically checked. There is a discussion about the
873 <a href="pcreunicode.html#utf8strings">validity of UTF-8 strings</a>
874 in the
875 <a href="pcreunicode.html"><b>pcreunicode</b></a>
876 page. If an invalid UTF-8 sequence is found, <b>pcre_compile()</b> returns an
877 error. If you already know that your pattern is valid, and you want to skip
878 this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option.
879 When it is set, the effect of passing an invalid UTF-8 string as a pattern is
880 undefined. It may cause your program to crash. Note that this option can also
881 be passed to <b>pcre_exec()</b> and <b>pcre_dfa_exec()</b>, to suppress the
882 validity checking of subject strings only. If the same string is being matched
883 many times, the option can be safely set for the second and subsequent
884 matchings to improve performance.
885 </P>
886 <br><a name="SEC12" href="#TOC1">COMPILATION ERROR CODES</a><br>
887 <P>
888 The following table lists the error codes than may be returned by
889 <b>pcre_compile2()</b>, along with the error messages that may be returned by
890 both compiling functions. Note that error messages are always 8-bit ASCII
891 strings, even in 16-bit or 32-bit mode. As PCRE has developed, some error codes
892 have fallen out of use. To avoid confusion, they have not been re-used.
893 <pre>
894 0 no error
895 1 \ at end of pattern
896 2 \c at end of pattern
897 3 unrecognized character follows \
898 4 numbers out of order in {} quantifier
899 5 number too big in {} quantifier
900 6 missing terminating ] for character class
901 7 invalid escape sequence in character class
902 8 range out of order in character class
903 9 nothing to repeat
904 10 [this code is not in use]
905 11 internal error: unexpected repeat
906 12 unrecognized character after (? or (?-
907 13 POSIX named classes are supported only within a class
908 14 missing )
909 15 reference to non-existent subpattern
910 16 erroffset passed as NULL
911 17 unknown option bit(s) set
912 18 missing ) after comment
913 19 [this code is not in use]
914 20 regular expression is too large
915 21 failed to get memory
916 22 unmatched parentheses
917 23 internal error: code overflow
918 24 unrecognized character after (?&#60;
919 25 lookbehind assertion is not fixed length
920 26 malformed number or name after (?(
921 27 conditional group contains more than two branches
922 28 assertion expected after (?(
923 29 (?R or (?[+-]digits must be followed by )
924 30 unknown POSIX class name
925 31 POSIX collating elements are not supported
926 32 this version of PCRE is compiled without UTF support
927 33 [this code is not in use]
928 34 character value in \x{...} sequence is too large
929 35 invalid condition (?(0)
930 36 \C not allowed in lookbehind assertion
931 37 PCRE does not support \L, \l, \N{name}, \U, or \u
932 38 number after (?C is &#62; 255
933 39 closing ) for (?C expected
934 40 recursive call could loop indefinitely
935 41 unrecognized character after (?P
936 42 syntax error in subpattern name (missing terminator)
937 43 two named subpatterns have the same name
938 44 invalid UTF-8 string (specifically UTF-8)
939 45 support for \P, \p, and \X has not been compiled
940 46 malformed \P or \p sequence
941 47 unknown property name after \P or \p
942 48 subpattern name is too long (maximum 32 characters)
943 49 too many named subpatterns (maximum 10000)
944 50 [this code is not in use]
945 51 octal value is greater than \377 in 8-bit non-UTF-8 mode
946 52 internal error: overran compiling workspace
947 53 internal error: previously-checked referenced subpattern
948 not found
949 54 DEFINE group contains more than one branch
950 55 repeating a DEFINE group is not allowed
951 56 inconsistent NEWLINE options
952 57 \g is not followed by a braced, angle-bracketed, or quoted
953 name/number or by a plain number
954 58 a numbered reference must not be zero
955 59 an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
956 60 (*VERB) not recognized or malformed
957 61 number is too big
958 62 subpattern name expected
959 63 digit expected after (?+
960 64 ] is an invalid data character in JavaScript compatibility mode
961 65 different names for subpatterns of the same number are
962 not allowed
963 66 (*MARK) must have an argument
964 67 this version of PCRE is not compiled with Unicode property
965 support
966 68 \c must be followed by an ASCII character
967 69 \k is not followed by a braced, angle-bracketed, or quoted name
968 70 internal error: unknown opcode in find_fixedlength()
969 71 \N is not supported in a class
970 72 too many forward references
971 73 disallowed Unicode code point (&#62;= 0xd800 && &#60;= 0xdfff)
972 74 invalid UTF-16 string (specifically UTF-16)
973 75 name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
974 76 character value in \u.... sequence is too large
975 77 invalid UTF-32 string (specifically UTF-32)
976 </pre>
977 The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
978 be used if the limits were changed when PCRE was built.
979 <a name="studyingapattern"></a></P>
980 <br><a name="SEC13" href="#TOC1">STUDYING A PATTERN</a><br>
981 <P>
982 <b>pcre_extra *pcre_study(const pcre *<i>code</i>, int <i>options</i>,</b>
983 <b> const char **<i>errptr</i>);</b>
984 </P>
985 <P>
986 If a compiled pattern is going to be used several times, it is worth spending
987 more time analyzing it in order to speed up the time taken for matching. The
988 function <b>pcre_study()</b> takes a pointer to a compiled pattern as its first
989 argument. If studying the pattern produces additional information that will
990 help speed up matching, <b>pcre_study()</b> returns a pointer to a
991 <b>pcre_extra</b> block, in which the <i>study_data</i> field points to the
992 results of the study.
993 </P>
994 <P>
995 The returned value from <b>pcre_study()</b> can be passed directly to
996 <b>pcre_exec()</b> or <b>pcre_dfa_exec()</b>. However, a <b>pcre_extra</b> block
997 also contains other fields that can be set by the caller before the block is
998 passed; these are described
999 <a href="#extradata">below</a>
1000 in the section on matching a pattern.
1001 </P>
1002 <P>
1003 If studying the pattern does not produce any useful information,
1004 <b>pcre_study()</b> returns NULL by default. In that circumstance, if the
1005 calling program wants to pass any of the other fields to <b>pcre_exec()</b> or
1006 <b>pcre_dfa_exec()</b>, it must set up its own <b>pcre_extra</b> block. However,
1007 if <b>pcre_study()</b> is called with the PCRE_STUDY_EXTRA_NEEDED option, it
1008 returns a <b>pcre_extra</b> block even if studying did not find any additional
1009 information. It may still return NULL, however, if an error occurs in
1010 <b>pcre_study()</b>.
1011 </P>
1012 <P>
1013 The second argument of <b>pcre_study()</b> contains option bits. There are three
1014 further options in addition to PCRE_STUDY_EXTRA_NEEDED:
1015 <pre>
1019 </pre>
1020 If any of these are set, and the just-in-time compiler is available, the
1021 pattern is further compiled into machine code that executes much faster than
1022 the <b>pcre_exec()</b> interpretive matching function. If the just-in-time
1023 compiler is not available, these options are ignored. All undefined bits in the
1024 <i>options</i> argument must be zero.
1025 </P>
1026 <P>
1027 JIT compilation is a heavyweight optimization. It can take some time for
1028 patterns to be analyzed, and for one-off matches and simple patterns the
1029 benefit of faster execution might be offset by a much slower study time.
1030 Not all patterns can be optimized by the JIT compiler. For those that cannot be
1031 handled, matching automatically falls back to the <b>pcre_exec()</b>
1032 interpreter. For more details, see the
1033 <a href="pcrejit.html"><b>pcrejit</b></a>
1034 documentation.
1035 </P>
1036 <P>
1037 The third argument for <b>pcre_study()</b> is a pointer for an error message. If
1038 studying succeeds (even if no data is returned), the variable it points to is
1039 set to NULL. Otherwise it is set to point to a textual error message. This is a
1040 static string that is part of the library. You must not try to free it. You
1041 should test the error pointer for NULL after calling <b>pcre_study()</b>, to be
1042 sure that it has run successfully.
1043 </P>
1044 <P>
1045 When you are finished with a pattern, you can free the memory used for the
1046 study data by calling <b>pcre_free_study()</b>. This function was added to the
1047 API for release 8.20. For earlier versions, the memory could be freed with
1048 <b>pcre_free()</b>, just like the pattern itself. This will still work in cases
1049 where JIT optimization is not used, but it is advisable to change to the new
1050 function when convenient.
1051 </P>
1052 <P>
1053 This is a typical way in which <b>pcre_study</b>() is used (except that in a
1054 real application there should be tests for errors):
1055 <pre>
1056 int rc;
1057 pcre *re;
1058 pcre_extra *sd;
1059 re = pcre_compile("pattern", 0, &error, &erroroffset, NULL);
1060 sd = pcre_study(
1061 re, /* result of pcre_compile() */
1062 0, /* no options */
1063 &error); /* set to NULL or points to a message */
1064 rc = pcre_exec( /* see below for details of pcre_exec() options */
1065 re, sd, "subject", 7, 0, 0, ovector, 30);
1066 ...
1067 pcre_free_study(sd);
1068 pcre_free(re);
1069 </pre>
1070 Studying a pattern does two things: first, a lower bound for the length of
1071 subject string that is needed to match the pattern is computed. This does not
1072 mean that there are any strings of that length that match, but it does
1073 guarantee that no shorter strings match. The value is used to avoid wasting
1074 time by trying to match strings that are shorter than the lower bound. You can
1075 find out the value in a calling program via the <b>pcre_fullinfo()</b> function.
1076 </P>
1077 <P>
1078 Studying a pattern is also useful for non-anchored patterns that do not have a
1079 single fixed starting character. A bitmap of possible starting bytes is
1080 created. This speeds up finding a position in the subject at which to start
1081 matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.
1082 In 32-bit mode, the bitmap is used for 32-bit values less than 256.)
1083 </P>
1084 <P>
1085 These two optimizations apply to both <b>pcre_exec()</b> and
1086 <b>pcre_dfa_exec()</b>, and the information is also used by the JIT compiler.
1087 The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option.
1088 You might want to do this if your pattern contains callouts or (*MARK) and you
1089 want to make use of these facilities in cases where matching fails.
1090 </P>
1091 <P>
1092 PCRE_NO_START_OPTIMIZE can be specified at either compile time or execution
1093 time. However, if PCRE_NO_START_OPTIMIZE is passed to <b>pcre_exec()</b>, (that
1094 is, after any JIT compilation has happened) JIT execution is disabled. For JIT
1095 execution to work with PCRE_NO_START_OPTIMIZE, the option must be set at
1096 compile time.
1097 </P>
1098 <P>
1099 There is a longer discussion of PCRE_NO_START_OPTIMIZE
1100 <a href="#execoptions">below.</a>
1101 <a name="localesupport"></a></P>
1102 <br><a name="SEC14" href="#TOC1">LOCALE SUPPORT</a><br>
1103 <P>
1104 PCRE handles caseless matching, and determines whether characters are letters,
1105 digits, or whatever, by reference to a set of tables, indexed by character
1106 value. When running in UTF-8 mode, this applies only to characters
1107 with codes less than 128. By default, higher-valued codes never match escapes
1108 such as \w or \d, but they can be tested with \p if PCRE is built with
1109 Unicode character property support. Alternatively, the PCRE_UCP option can be
1110 set at compile time; this causes \w and friends to use Unicode property
1111 support instead of built-in tables. The use of locales with Unicode is
1112 discouraged. If you are handling characters with codes greater than 128, you
1113 should either use UTF-8 and Unicode, or use locales, but not try to mix the
1114 two.
1115 </P>
1116 <P>
1117 PCRE contains an internal set of tables that are used when the final argument
1118 of <b>pcre_compile()</b> is NULL. These are sufficient for many applications.
1119 Normally, the internal tables recognize only ASCII characters. However, when
1120 PCRE is built, it is possible to cause the internal tables to be rebuilt in the
1121 default "C" locale of the local system, which may cause them to be different.
1122 </P>
1123 <P>
1124 The internal tables can always be overridden by tables supplied by the
1125 application that calls PCRE. These may be created in a different locale from
1126 the default. As more and more applications change to using Unicode, the need
1127 for this locale support is expected to die away.
1128 </P>
1129 <P>
1130 External tables are built by calling the <b>pcre_maketables()</b> function,
1131 which has no arguments, in the relevant locale. The result can then be passed
1132 to <b>pcre_compile()</b> or <b>pcre_exec()</b> as often as necessary. For
1133 example, to build and use tables that are appropriate for the French locale
1134 (where accented characters with values greater than 128 are treated as letters),
1135 the following code could be used:
1136 <pre>
1137 setlocale(LC_CTYPE, "fr_FR");
1138 tables = pcre_maketables();
1139 re = pcre_compile(..., tables);
1140 </pre>
1141 The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
1142 are using Windows, the name for the French locale is "french".
1143 </P>
1144 <P>
1145 When <b>pcre_maketables()</b> runs, the tables are built in memory that is
1146 obtained via <b>pcre_malloc</b>. It is the caller's responsibility to ensure
1147 that the memory containing the tables remains available for as long as it is
1148 needed.
1149 </P>
1150 <P>
1151 The pointer that is passed to <b>pcre_compile()</b> is saved with the compiled
1152 pattern, and the same tables are used via this pointer by <b>pcre_study()</b>
1153 and normally also by <b>pcre_exec()</b>. Thus, by default, for any single
1154 pattern, compilation, studying and matching all happen in the same locale, but
1155 different patterns can be compiled in different locales.
1156 </P>
1157 <P>
1158 It is possible to pass a table pointer or NULL (indicating the use of the
1159 internal tables) to <b>pcre_exec()</b>. Although not intended for this purpose,
1160 this facility could be used to match a pattern in a different locale from the
1161 one in which it was compiled. Passing table pointers at run time is discussed
1162 below in the section on matching a pattern.
1163 <a name="infoaboutpattern"></a></P>
1164 <br><a name="SEC15" href="#TOC1">INFORMATION ABOUT A PATTERN</a><br>
1165 <P>
1166 <b>int pcre_fullinfo(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
1167 <b> int <i>what</i>, void *<i>where</i>);</b>
1168 </P>
1169 <P>
1170 The <b>pcre_fullinfo()</b> function returns information about a compiled
1171 pattern. It replaces the <b>pcre_info()</b> function, which was removed from the
1172 library at version 8.30, after more than 10 years of obsolescence.
1173 </P>
1174 <P>
1175 The first argument for <b>pcre_fullinfo()</b> is a pointer to the compiled
1176 pattern. The second argument is the result of <b>pcre_study()</b>, or NULL if
1177 the pattern was not studied. The third argument specifies which piece of
1178 information is required, and the fourth argument is a pointer to a variable
1179 to receive the data. The yield of the function is zero for success, or one of
1180 the following negative numbers:
1181 <pre>
1182 PCRE_ERROR_NULL the argument <i>code</i> was NULL
1183 the argument <i>where</i> was NULL
1184 PCRE_ERROR_BADMAGIC the "magic number" was not found
1185 PCRE_ERROR_BADENDIANNESS the pattern was compiled with different
1186 endianness
1187 PCRE_ERROR_BADOPTION the value of <i>what</i> was invalid
1188 PCRE_ERROR_UNSET the requested field is not set
1189 </pre>
1190 The "magic number" is placed at the start of each compiled pattern as an simple
1191 check against passing an arbitrary memory pointer. The endianness error can
1192 occur if a compiled pattern is saved and reloaded on a different host. Here is
1193 a typical call of <b>pcre_fullinfo()</b>, to obtain the length of the compiled
1194 pattern:
1195 <pre>
1196 int rc;
1197 size_t length;
1198 rc = pcre_fullinfo(
1199 re, /* result of pcre_compile() */
1200 sd, /* result of pcre_study(), or NULL */
1201 PCRE_INFO_SIZE, /* what is required */
1202 &length); /* where to put the data */
1203 </pre>
1204 The possible values for the third argument are defined in <b>pcre.h</b>, and are
1205 as follows:
1206 <pre>
1208 </pre>
1209 Return the number of the highest back reference in the pattern. The fourth
1210 argument should point to an <b>int</b> variable. Zero is returned if there are
1211 no back references.
1212 <pre>
1214 </pre>
1215 Return the number of capturing subpatterns in the pattern. The fourth argument
1216 should point to an <b>int</b> variable.
1217 <pre>
1219 </pre>
1220 Return a pointer to the internal default character tables within PCRE. The
1221 fourth argument should point to an <b>unsigned char *</b> variable. This
1222 information call is provided for internal use by the <b>pcre_study()</b>
1223 function. External callers can cause PCRE to use its internal tables by passing
1224 a NULL table pointer.
1225 <pre>
1227 </pre>
1228 Return information about the first data unit of any matched string, for a
1229 non-anchored pattern. (The name of this option refers to the 8-bit library,
1230 where data units are bytes.) The fourth argument should point to an <b>int</b>
1231 variable.
1232 </P>
1233 <P>
1234 If there is a fixed first value, for example, the letter "c" from a pattern
1235 such as (cat|cow|coyote), its value is returned. In the 8-bit library, the
1236 value is always less than 256. In the 16-bit library the value can be up to
1237 0xffff. In the 32-bit library the value can be up to 0x10ffff.
1238 </P>
1239 <P>
1240 If there is no fixed first value, and if either
1241 <br>
1242 <br>
1243 (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
1244 starts with "^", or
1245 <br>
1246 <br>
1247 (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
1248 (if it were set, the pattern would be anchored),
1249 <br>
1250 <br>
1251 -1 is returned, indicating that the pattern matches only at the start of a
1252 subject string or after any newline within the string. Otherwise -2 is
1253 returned. For anchored patterns, -2 is returned.
1254 </P>
1255 <P>
1256 Since for the 32-bit library using the non-UTF-32 mode, this function is unable
1257 to return the full 32-bit range of the character, this value is deprecated;
1259 should be used.
1260 <pre>
1262 </pre>
1263 If the pattern was studied, and this resulted in the construction of a 256-bit
1264 table indicating a fixed set of values for the first data unit in any matching
1265 string, a pointer to the table is returned. Otherwise NULL is returned. The
1266 fourth argument should point to an <b>unsigned char *</b> variable.
1267 <pre>
1269 </pre>
1270 Return 1 if the pattern contains any explicit matches for CR or LF characters,
1271 otherwise 0. The fourth argument should point to an <b>int</b> variable. An
1272 explicit match is either a literal CR or LF character, or \r or \n.
1273 <pre>
1275 </pre>
1276 Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
1277 0. The fourth argument should point to an <b>int</b> variable. (?J) and
1278 (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
1279 <pre>
1281 </pre>
1282 Return 1 if the pattern was studied with one of the JIT options, and
1283 just-in-time compiling was successful. The fourth argument should point to an
1284 <b>int</b> variable. A return value of 0 means that JIT support is not available
1285 in this version of PCRE, or that the pattern was not studied with a JIT option,
1286 or that the JIT compiler could not handle this particular pattern. See the
1287 <a href="pcrejit.html"><b>pcrejit</b></a>
1288 documentation for details of what can and cannot be handled.
1289 <pre>
1291 </pre>
1292 If the pattern was successfully studied with a JIT option, return the size of
1293 the JIT compiled code, otherwise return zero. The fourth argument should point
1294 to a <b>size_t</b> variable.
1295 <pre>
1297 </pre>
1298 Return the value of the rightmost literal data unit that must exist in any
1299 matched string, other than at its start, if such a value has been recorded. The
1300 fourth argument should point to an <b>int</b> variable. If there is no such
1301 value, -1 is returned. For anchored patterns, a last literal value is recorded
1302 only if it follows something of variable length. For example, for the pattern
1303 /^a\d+z\d+/ the returned value is "z", but for /^a\dz\d/ the returned value
1304 is -1.
1305 </P>
1306 <P>
1307 Since for the 32-bit library using the non-UTF-32 mode, this function is unable
1308 to return the full 32-bit range of the character, this value is deprecated;
1310 be used.
1311 <pre>
1313 </pre>
1314 If the pattern set a match limit by including an item of the form
1315 (*LIMIT_MATCH=nnnn) at the start, the value is returned. The fourth argument
1316 should point to an unsigned 32-bit integer. If no such value has been set, the
1317 call to <b>pcre_fullinfo()</b> returns the error PCRE_ERROR_UNSET.
1318 <pre>
1320 </pre>
1321 Return the number of characters (NB not data units) in the longest lookbehind
1322 assertion in the pattern. This information is useful when doing multi-segment
1323 matching using the partial matching facilities. Note that the simple assertions
1324 \b and \B require a one-character lookbehind. \A also registers a
1325 one-character lookbehind, though it does not actually inspect the previous
1326 character. This is to ensure that at least one character from the old segment
1327 is retained when a new segment is processed. Otherwise, if there are no
1328 lookbehinds in the pattern, \A might match incorrectly at the start of a new
1329 segment.
1330 <pre>
1332 </pre>
1333 If the pattern was studied and a minimum length for matching subject strings
1334 was computed, its value is returned. Otherwise the returned value is -1. The
1335 value is a number of characters, which in UTF mode may be different from the
1336 number of data units. The fourth argument should point to an <b>int</b>
1337 variable. A non-negative value is a lower bound to the length of any matching
1338 string. There may not be any strings of that length that do actually match, but
1339 every string that does match is at least that long.
1340 <pre>
1344 </pre>
1345 PCRE supports the use of named as well as numbered capturing parentheses. The
1346 names are just an additional way of identifying the parentheses, which still
1347 acquire numbers. Several convenience functions such as
1348 <b>pcre_get_named_substring()</b> are provided for extracting captured
1349 substrings by name. It is also possible to extract the data directly, by first
1350 converting the name to a number in order to access the correct pointers in the
1351 output vector (described with <b>pcre_exec()</b> below). To do the conversion,
1352 you need to use the name-to-number map, which is described by these three
1353 values.
1354 </P>
1355 <P>
1356 The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives
1357 the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
1358 entry; both of these return an <b>int</b> value. The entry size depends on the
1359 length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
1360 entry of the table. This is a pointer to <b>char</b> in the 8-bit library, where
1361 the first two bytes of each entry are the number of the capturing parenthesis,
1362 most significant byte first. In the 16-bit library, the pointer points to
1363 16-bit data units, the first of which contains the parenthesis number. In the
1364 32-bit library, the pointer points to 32-bit data units, the first of which
1365 contains the parenthesis number. The rest of the entry is the corresponding
1366 name, zero terminated.
1367 </P>
1368 <P>
1369 The names are in alphabetical order. Duplicate names may appear if (?| is used
1370 to create multiple groups with the same number, as described in the
1371 <a href="pcrepattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a>
1372 in the
1373 <a href="pcrepattern.html"><b>pcrepattern</b></a>
1374 page. Duplicate names for subpatterns with different numbers are permitted only
1375 if PCRE_DUPNAMES is set. In all cases of duplicate names, they appear in the
1376 table in the order in which they were found in the pattern. In the absence of
1377 (?| this is the order of increasing number; when (?| is used this is not
1378 necessarily the case because later subpatterns may have lower numbers.
1379 </P>
1380 <P>
1381 As a simple example of the name/number table, consider the following pattern
1382 after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white
1383 space - including newlines - is ignored):
1384 <pre>
1385 (?&#60;date&#62; (?&#60;year&#62;(\d\d)?\d\d) - (?&#60;month&#62;\d\d) - (?&#60;day&#62;\d\d) )
1386 </pre>
1387 There are four named subpatterns, so the table has four entries, and each entry
1388 in the table is eight bytes long. The table is as follows, with non-printing
1389 bytes shows in hexadecimal, and undefined bytes shown as ??:
1390 <pre>
1391 00 01 d a t e 00 ??
1392 00 05 d a y 00 ?? ??
1393 00 04 m o n t h 00
1394 00 02 y e a r 00 ??
1395 </pre>
1396 When writing code to extract data from named subpatterns using the
1397 name-to-number map, remember that the length of the entries is likely to be
1398 different for each compiled pattern.
1399 <pre>
1401 </pre>
1402 Return 1 if the pattern can be used for partial matching with
1403 <b>pcre_exec()</b>, otherwise 0. The fourth argument should point to an
1404 <b>int</b> variable. From release 8.00, this always returns 1, because the
1405 restrictions that previously applied to partial matching have been lifted. The
1406 <a href="pcrepartial.html"><b>pcrepartial</b></a>
1407 documentation gives details of partial matching.
1408 <pre>
1410 </pre>
1411 Return a copy of the options with which the pattern was compiled. The fourth
1412 argument should point to an <b>unsigned long int</b> variable. These option bits
1413 are those specified in the call to <b>pcre_compile()</b>, modified by any
1414 top-level option settings at the start of the pattern itself. In other words,
1415 they are the options that will be in force when matching starts. For example,
1416 if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1418 </P>
1419 <P>
1420 A pattern is automatically anchored by PCRE if all of its top-level
1421 alternatives begin with one of the following:
1422 <pre>
1423 ^ unless PCRE_MULTILINE is set
1424 \A always
1425 \G always
1426 .* if PCRE_DOTALL is set and there are no back references to the subpattern in which .* appears
1427 </pre>
1428 For such patterns, the PCRE_ANCHORED bit is set in the options returned by
1429 <b>pcre_fullinfo()</b>.
1430 <pre>
1432 </pre>
1433 If the pattern set a recursion limit by including an item of the form
1434 (*LIMIT_RECURSION=nnnn) at the start, the value is returned. The fourth
1435 argument should point to an unsigned 32-bit integer. If no such value has been
1436 set, the call to <b>pcre_fullinfo()</b> returns the error PCRE_ERROR_UNSET.
1437 <pre>
1439 </pre>
1440 Return the size of the compiled pattern in bytes (for all three libraries). The
1441 fourth argument should point to a <b>size_t</b> variable. This value does not
1442 include the size of the <b>pcre</b> structure that is returned by
1443 <b>pcre_compile()</b>. The value that is passed as the argument to
1444 <b>pcre_malloc()</b> when <b>pcre_compile()</b> is getting memory in which to
1445 place the compiled data is the value returned by this option plus the size of
1446 the <b>pcre</b> structure. Studying a compiled pattern, with or without JIT,
1447 does not alter the value returned by this option.
1448 <pre>
1450 </pre>
1451 Return the size in bytes (for all three libraries) of the data block pointed to
1452 by the <i>study_data</i> field in a <b>pcre_extra</b> block. If <b>pcre_extra</b>
1453 is NULL, or there is no study data, zero is returned. The fourth argument
1454 should point to a <b>size_t</b> variable. The <i>study_data</i> field is set by
1455 <b>pcre_study()</b> to record information that will speed up matching (see the
1456 section entitled
1457 <a href="#studyingapattern">"Studying a pattern"</a>
1458 above). The format of the <i>study_data</i> block is private, but its length
1459 is made available via this option so that it can be saved and restored (see the
1460 <a href="pcreprecompile.html"><b>pcreprecompile</b></a>
1461 documentation for details).
1462 <pre>
1464 </pre>
1465 Return information about the first data unit of any matched string, for a
1466 non-anchored pattern. The fourth argument should point to an <b>int</b>
1467 variable.
1468 </P>
1469 <P>
1470 If there is a fixed first value, for example, the letter "c" from a pattern
1471 such as (cat|cow|coyote), 1 is returned, and the character value can be
1472 retrieved using PCRE_INFO_FIRSTCHARACTER.
1473 </P>
1474 <P>
1475 If there is no fixed first value, and if either
1476 <br>
1477 <br>
1478 (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
1479 starts with "^", or
1480 <br>
1481 <br>
1482 (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
1483 (if it were set, the pattern would be anchored),
1484 <br>
1485 <br>
1486 2 is returned, indicating that the pattern matches only at the start of a
1487 subject string or after any newline within the string. Otherwise 0 is
1488 returned. For anchored patterns, 0 is returned.
1489 <pre>
1491 </pre>
1492 Return the fixed first character value, if PCRE_INFO_FIRSTCHARACTERFLAGS
1493 returned 1; otherwise returns 0. The fourth argument should point to an
1494 <b>uint_t</b> variable.
1495 </P>
1496 <P>
1497 In the 8-bit library, the value is always less than 256. In the 16-bit library
1498 the value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value
1499 can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode.
1500 </P>
1501 <P>
1502 If there is no fixed first value, and if either
1503 <br>
1504 <br>
1505 (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
1506 starts with "^", or
1507 <br>
1508 <br>
1509 (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
1510 (if it were set, the pattern would be anchored),
1511 <br>
1512 <br>
1513 -1 is returned, indicating that the pattern matches only at the start of a
1514 subject string or after any newline within the string. Otherwise -2 is
1515 returned. For anchored patterns, -2 is returned.
1516 <pre>
1518 </pre>
1519 Returns 1 if there is a rightmost literal data unit that must exist in any
1520 matched string, other than at its start. The fourth argument should point to
1521 an <b>int</b> variable. If there is no such value, 0 is returned. If returning
1522 1, the character value itself can be retrieved using PCRE_INFO_REQUIREDCHAR.
1523 </P>
1524 <P>
1525 For anchored patterns, a last literal value is recorded only if it follows
1526 something of variable length. For example, for the pattern /^a\d+z\d+/ the
1527 returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for
1528 /^a\dz\d/ the returned value is 0.
1529 <pre>
1531 </pre>
1532 Return the value of the rightmost literal data unit that must exist in any
1533 matched string, other than at its start, if such a value has been recorded. The
1534 fourth argument should point to an <b>uint32_t</b> variable. If there is no such
1535 value, 0 is returned.
1536 </P>
1537 <br><a name="SEC16" href="#TOC1">REFERENCE COUNTS</a><br>
1538 <P>
1539 <b>int pcre_refcount(pcre *<i>code</i>, int <i>adjust</i>);</b>
1540 </P>
1541 <P>
1542 The <b>pcre_refcount()</b> function is used to maintain a reference count in the
1543 data block that contains a compiled pattern. It is provided for the benefit of
1544 applications that operate in an object-oriented manner, where different parts
1545 of the application may be using the same compiled pattern, but you want to free
1546 the block when they are all done.
1547 </P>
1548 <P>
1549 When a pattern is compiled, the reference count field is initialized to zero.
1550 It is changed only by calling this function, whose action is to add the
1551 <i>adjust</i> value (which may be positive or negative) to it. The yield of the
1552 function is the new value. However, the value of the count is constrained to
1553 lie between 0 and 65535, inclusive. If the new value is outside these limits,
1554 it is forced to the appropriate limit value.
1555 </P>
1556 <P>
1557 Except when it is zero, the reference count is not correctly preserved if a
1558 pattern is compiled on one host and then transferred to a host whose byte-order
1559 is different. (This seems a highly unlikely scenario.)
1560 </P>
1561 <br><a name="SEC17" href="#TOC1">MATCHING A PATTERN: THE TRADITIONAL FUNCTION</a><br>
1562 <P>
1563 <b>int pcre_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
1564 <b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
1565 <b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>);</b>
1566 </P>
1567 <P>
1568 The function <b>pcre_exec()</b> is called to match a subject string against a
1569 compiled pattern, which is passed in the <i>code</i> argument. If the
1570 pattern was studied, the result of the study should be passed in the
1571 <i>extra</i> argument. You can call <b>pcre_exec()</b> with the same <i>code</i>
1572 and <i>extra</i> arguments as many times as you like, in order to match
1573 different subject strings with the same pattern.
1574 </P>
1575 <P>
1576 This function is the main matching facility of the library, and it operates in
1577 a Perl-like manner. For specialist use there is also an alternative matching
1578 function, which is described
1579 <a href="#dfamatch">below</a>
1580 in the section about the <b>pcre_dfa_exec()</b> function.
1581 </P>
1582 <P>
1583 In most applications, the pattern will have been compiled (and optionally
1584 studied) in the same process that calls <b>pcre_exec()</b>. However, it is
1585 possible to save compiled patterns and study data, and then use them later
1586 in different processes, possibly even on different hosts. For a discussion
1587 about this, see the
1588 <a href="pcreprecompile.html"><b>pcreprecompile</b></a>
1589 documentation.
1590 </P>
1591 <P>
1592 Here is an example of a simple call to <b>pcre_exec()</b>:
1593 <pre>
1594 int rc;
1595 int ovector[30];
1596 rc = pcre_exec(
1597 re, /* result of pcre_compile() */
1598 NULL, /* we didn't study the pattern */
1599 "some string", /* the subject string */
1600 11, /* the length of the subject string */
1601 0, /* start at offset 0 in the subject */
1602 0, /* default options */
1603 ovector, /* vector of integers for substring information */
1604 30); /* number of elements (NOT size in bytes) */
1605 <a name="extradata"></a></PRE>
1606 </P>
1607 <br><b>
1608 Extra data for <b>pcre_exec()</b>
1609 </b><br>
1610 <P>
1611 If the <i>extra</i> argument is not NULL, it must point to a <b>pcre_extra</b>
1612 data block. The <b>pcre_study()</b> function returns such a block (when it
1613 doesn't return NULL), but you can also create one for yourself, and pass
1614 additional information in it. The <b>pcre_extra</b> block contains the following
1615 fields (not necessarily in this order):
1616 <pre>
1617 unsigned long int <i>flags</i>;
1618 void *<i>study_data</i>;
1619 void *<i>executable_jit</i>;
1620 unsigned long int <i>match_limit</i>;
1621 unsigned long int <i>match_limit_recursion</i>;
1622 void *<i>callout_data</i>;
1623 const unsigned char *<i>tables</i>;
1624 unsigned char **<i>mark</i>;
1625 </pre>
1626 In the 16-bit version of this structure, the <i>mark</i> field has type
1627 "PCRE_UCHAR16 **".
1628 <br>
1629 <br>
1630 In the 32-bit version of this structure, the <i>mark</i> field has type
1631 "PCRE_UCHAR32 **".
1632 </P>
1633 <P>
1634 The <i>flags</i> field is used to specify which of the other fields are set. The
1635 flag bits are:
1636 <pre>
1644 </pre>
1645 Other flag bits should be set to zero. The <i>study_data</i> field and sometimes
1646 the <i>executable_jit</i> field are set in the <b>pcre_extra</b> block that is
1647 returned by <b>pcre_study()</b>, together with the appropriate flag bits. You
1648 should not set these yourself, but you may add to the block by setting other
1649 fields and their corresponding flag bits.
1650 </P>
1651 <P>
1652 The <i>match_limit</i> field provides a means of preventing PCRE from using up a
1653 vast amount of resources when running patterns that are not going to match,
1654 but which have a very large number of possibilities in their search trees. The
1655 classic example is a pattern that uses nested unlimited repeats.
1656 </P>
1657 <P>
1658 Internally, <b>pcre_exec()</b> uses a function called <b>match()</b>, which it
1659 calls repeatedly (sometimes recursively). The limit set by <i>match_limit</i> is
1660 imposed on the number of times this function is called during a match, which
1661 has the effect of limiting the amount of backtracking that can take place. For
1662 patterns that are not anchored, the count restarts from zero for each position
1663 in the subject string.
1664 </P>
1665 <P>
1666 When <b>pcre_exec()</b> is called with a pattern that was successfully studied
1667 with a JIT option, the way that the matching is executed is entirely different.
1668 However, there is still the possibility of runaway matching that goes on for a
1669 very long time, and so the <i>match_limit</i> value is also used in this case
1670 (but in a different way) to limit how long the matching can continue.
1671 </P>
1672 <P>
1673 The default value for the limit can be set when PCRE is built; the default
1674 default is 10 million, which handles all but the most extreme cases. You can
1675 override the default by suppling <b>pcre_exec()</b> with a <b>pcre_extra</b>
1676 block in which <i>match_limit</i> is set, and PCRE_EXTRA_MATCH_LIMIT is set in
1677 the <i>flags</i> field. If the limit is exceeded, <b>pcre_exec()</b> returns
1679 </P>
1680 <P>
1681 A value for the match limit may also be supplied by an item at the start of a
1682 pattern of the form
1683 <pre>
1684 (*LIMIT_MATCH=d)
1685 </pre>
1686 where d is a decimal number. However, such a setting is ignored unless d is
1687 less than the limit set by the caller of <b>pcre_exec()</b> or, if no such limit
1688 is set, less than the default.
1689 </P>
1690 <P>
1691 The <i>match_limit_recursion</i> field is similar to <i>match_limit</i>, but
1692 instead of limiting the total number of times that <b>match()</b> is called, it
1693 limits the depth of recursion. The recursion depth is a smaller number than the
1694 total number of calls, because not all calls to <b>match()</b> are recursive.
1695 This limit is of use only if it is set smaller than <i>match_limit</i>.
1696 </P>
1697 <P>
1698 Limiting the recursion depth limits the amount of machine stack that can be
1699 used, or, when PCRE has been compiled to use memory on the heap instead of the
1700 stack, the amount of heap memory that can be used. This limit is not relevant,
1701 and is ignored, when matching is done using JIT compiled code.
1702 </P>
1703 <P>
1704 The default value for <i>match_limit_recursion</i> can be set when PCRE is
1705 built; the default default is the same value as the default for
1706 <i>match_limit</i>. You can override the default by suppling <b>pcre_exec()</b>
1707 with a <b>pcre_extra</b> block in which <i>match_limit_recursion</i> is set, and
1708 PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the <i>flags</i> field. If the limit
1709 is exceeded, <b>pcre_exec()</b> returns PCRE_ERROR_RECURSIONLIMIT.
1710 </P>
1711 <P>
1712 A value for the recursion limit may also be supplied by an item at the start of
1713 a pattern of the form
1714 <pre>
1716 </pre>
1717 where d is a decimal number. However, such a setting is ignored unless d is
1718 less than the limit set by the caller of <b>pcre_exec()</b> or, if no such limit
1719 is set, less than the default.
1720 </P>
1721 <P>
1722 The <i>callout_data</i> field is used in conjunction with the "callout" feature,
1723 and is described in the
1724 <a href="pcrecallout.html"><b>pcrecallout</b></a>
1725 documentation.
1726 </P>
1727 <P>
1728 The <i>tables</i> field is used to pass a character tables pointer to
1729 <b>pcre_exec()</b>; this overrides the value that is stored with the compiled
1730 pattern. A non-NULL value is stored with the compiled pattern only if custom
1731 tables were supplied to <b>pcre_compile()</b> via its <i>tableptr</i> argument.
1732 If NULL is passed to <b>pcre_exec()</b> using this mechanism, it forces PCRE's
1733 internal tables to be used. This facility is helpful when re-using patterns
1734 that have been saved after compiling with an external set of tables, because
1735 the external tables might be at a different address when <b>pcre_exec()</b> is
1736 called. See the
1737 <a href="pcreprecompile.html"><b>pcreprecompile</b></a>
1738 documentation for a discussion of saving compiled patterns for later use.
1739 </P>
1740 <P>
1741 If PCRE_EXTRA_MARK is set in the <i>flags</i> field, the <i>mark</i> field must
1742 be set to point to a suitable variable. If the pattern contains any
1743 backtracking control verbs such as (*MARK:NAME), and the execution ends up with
1744 a name to pass back, a pointer to the name string (zero terminated) is placed
1745 in the variable pointed to by the <i>mark</i> field. The names are within the
1746 compiled pattern; if you wish to retain such a name you must copy it before
1747 freeing the memory of a compiled pattern. If there is no name to pass back, the
1748 variable pointed to by the <i>mark</i> field is set to NULL. For details of the
1749 backtracking control verbs, see the section entitled
1750 <a href="pcrepattern#backtrackcontrol">"Backtracking control"</a>
1751 in the
1752 <a href="pcrepattern.html"><b>pcrepattern</b></a>
1753 documentation.
1754 <a name="execoptions"></a></P>
1755 <br><b>
1756 Option bits for <b>pcre_exec()</b>
1757 </b><br>
1758 <P>
1759 The unused bits of the <i>options</i> argument for <b>pcre_exec()</b> must be
1760 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_<i>xxx</i>,
1764 </P>
1765 <P>
1766 If the pattern was successfully studied with one of the just-in-time (JIT)
1767 compile options, the only supported options for JIT execution are
1770 unsupported option is used, JIT execution is disabled and the normal
1771 interpretive code in <b>pcre_exec()</b> is run.
1772 <pre>
1774 </pre>
1775 The PCRE_ANCHORED option limits <b>pcre_exec()</b> to matching at the first
1776 matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out
1777 to be anchored by virtue of its contents, it cannot be made unachored at
1778 matching time.
1779 <pre>
1782 </pre>
1783 These options (which are mutually exclusive) control what the \R escape
1784 sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1785 match any Unicode newline sequence. These options override the choice that was
1786 made or defaulted when the pattern was compiled.
1787 <pre>
1793 </pre>
1794 These options override the newline definition that was chosen or defaulted when
1795 the pattern was compiled. For details, see the description of
1796 <b>pcre_compile()</b> above. During matching, the newline choice affects the
1797 behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1798 the way the match position is advanced after a match failure for an unanchored
1799 pattern.
1800 </P>
1801 <P>
1803 match attempt for an unanchored pattern fails when the current position is at a
1804 CRLF sequence, and the pattern contains no explicit matches for CR or LF
1805 characters, the match position is advanced by two characters instead of one, in
1806 other words, to after the CRLF.
1807 </P>
1808 <P>
1809 The above rule is a compromise that makes the most common cases work as
1810 expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1811 set), it does not match the string "\r\nA" because, after failing at the
1812 start, it skips both the CR and the LF before retrying. However, the pattern
1813 [\r\n]A does match that string, because it contains an explicit CR or LF
1814 reference, and so advances only by one character after the first failure.
1815 </P>
1816 <P>
1817 An explicit match for CR of LF is either a literal appearance of one of those
1818 characters, or one of the \r or \n escape sequences. Implicit matches such as
1819 [^X] do not count, nor does \s (which includes CR and LF in the characters
1820 that it matches).
1821 </P>
1822 <P>
1823 Notwithstanding the above, anomalous effects may still occur when CRLF is a
1824 valid newline sequence and explicit \r or \n escapes appear in the pattern.
1825 <pre>
1827 </pre>
1828 This option specifies that first character of the subject string is not the
1829 beginning of a line, so the circumflex metacharacter should not match before
1830 it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex
1831 never to match. This option affects only the behaviour of the circumflex
1832 metacharacter. It does not affect \A.
1833 <pre>
1835 </pre>
1836 This option specifies that the end of the subject string is not the end of a
1837 line, so the dollar metacharacter should not match it nor (except in multiline
1838 mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at
1839 compile time) causes dollar never to match. This option affects only the
1840 behaviour of the dollar metacharacter. It does not affect \Z or \z.
1841 <pre>
1843 </pre>
1844 An empty string is not considered to be a valid match if this option is set. If
1845 there are alternatives in the pattern, they are tried. If all the alternatives
1846 match the empty string, the entire match fails. For example, if the pattern
1847 <pre>
1848 a?b?
1849 </pre>
1850 is applied to a string not beginning with "a" or "b", it matches an empty
1851 string at the start of the subject. With PCRE_NOTEMPTY set, this match is not
1852 valid, so PCRE searches further into the string for occurrences of "a" or "b".
1853 <pre>
1855 </pre>
1856 This is like PCRE_NOTEMPTY, except that an empty string match that is not at
1857 the start of the subject is permitted. If the pattern is anchored, such a match
1858 can occur only if the pattern contains \K.
1859 </P>
1860 <P>
1861 Perl has no direct equivalent of PCRE_NOTEMPTY or PCRE_NOTEMPTY_ATSTART, but it
1862 does make a special case of a pattern match of the empty string within its
1863 <b>split()</b> function, and when using the /g modifier. It is possible to
1864 emulate Perl's behaviour after matching a null string by first trying the match
1865 again at the same offset with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then
1866 if that fails, by advancing the starting offset (see below) and trying an
1867 ordinary match again. There is some code that demonstrates how to do this in
1868 the
1869 <a href="pcredemo.html"><b>pcredemo</b></a>
1870 sample program. In the most general case, you have to check to see if the
1871 newline convention recognizes CRLF as a newline, and if so, and the current
1872 character is CR followed by LF, advance the starting offset by two characters
1873 instead of one.
1874 <pre>
1876 </pre>
1877 There are a number of optimizations that <b>pcre_exec()</b> uses at the start of
1878 a match, in order to speed up the process. For example, if it is known that an
1879 unanchored match must start with a specific character, it searches the subject
1880 for that character, and fails immediately if it cannot find it, without
1881 actually running the main matching function. This means that a special item
1882 such as (*COMMIT) at the start of a pattern is not considered until after a
1883 suitable starting point for the match has been found. Also, when callouts or
1884 (*MARK) items are in use, these "start-up" optimizations can cause them to be
1885 skipped if the pattern is never actually used. The start-up optimizations are
1886 in effect a pre-scan of the subject that takes place before the pattern is run.
1887 </P>
1888 <P>
1889 The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly
1890 causing performance to suffer, but ensuring that in cases where the result is
1891 "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)
1892 are considered at every possible starting position in the subject string. If
1893 PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching
1894 time. The use of PCRE_NO_START_OPTIMIZE at matching time (that is, passing it
1895 to <b>pcre_exec()</b>) disables JIT execution; in this situation, matching is
1896 always done using interpretively.
1897 </P>
1898 <P>
1899 Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.
1900 Consider the pattern
1901 <pre>
1903 </pre>
1904 When this is compiled, PCRE records the fact that a match must start with the
1905 character "A". Suppose the subject string is "DEFABC". The start-up
1906 optimization scans along the subject, finds "A" and runs the first match
1907 attempt from there. The (*COMMIT) item means that the pattern must match the
1908 current starting position, which in this case, it does. However, if the same
1909 match is run with PCRE_NO_START_OPTIMIZE set, the initial scan along the
1910 subject string does not happen. The first match attempt is run starting from
1911 "D" and when this fails, (*COMMIT) prevents any further matches being tried, so
1912 the overall result is "no match". If the pattern is studied, more start-up
1913 optimizations may be used. For example, a minimum length for the subject may be
1914 recorded. Consider the pattern
1915 <pre>
1916 (*MARK:A)(X|Y)
1917 </pre>
1918 The minimum length for a match is one character. If the subject is "ABC", there
1919 will be attempts to match "ABC", "BC", "C", and then finally an empty string.
1920 If the pattern is studied, the final attempt does not take place, because PCRE
1921 knows that the subject is too short, and so the (*MARK) is never encountered.
1922 In this case, studying the pattern does not affect the overall match result,
1923 which is still "no match", but it does affect the auxiliary information that is
1924 returned.
1925 <pre>
1927 </pre>
1928 When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
1929 string is automatically checked when <b>pcre_exec()</b> is subsequently called.
1930 The entire string is checked before any other processing takes place. The value
1931 of <i>startoffset</i> is also checked to ensure that it points to the start of a
1932 UTF-8 character. There is a discussion about the
1933 <a href="pcreunicode.html#utf8strings">validity of UTF-8 strings</a>
1934 in the
1935 <a href="pcreunicode.html"><b>pcreunicode</b></a>
1936 page. If an invalid sequence of bytes is found, <b>pcre_exec()</b> returns the
1937 error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a
1938 truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both
1939 cases, information about the precise nature of the error may also be returned
1940 (see the descriptions of these errors in the section entitled \fIError return
1941 values from\fP <b>pcre_exec()</b>
1942 <a href="#errorlist">below).</a>
1943 If <i>startoffset</i> contains a value that does not point to the start of a
1944 UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is
1945 returned.
1946 </P>
1947 <P>
1948 If you already know that your subject is valid, and you want to skip these
1949 checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
1950 calling <b>pcre_exec()</b>. You might want to do this for the second and
1951 subsequent calls to <b>pcre_exec()</b> if you are making repeated calls to find
1952 all the matches in a single subject string. However, you should be sure that
1953 the value of <i>startoffset</i> points to the start of a character (or the end
1954 of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an
1955 invalid string as a subject or an invalid value of <i>startoffset</i> is
1956 undefined. Your program may crash.
1957 <pre>
1960 </pre>
1961 These options turn on the partial matching feature. For backwards
1962 compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match
1963 occurs if the end of the subject string is reached successfully, but there are
1964 not enough subject characters to complete the match. If this happens when
1965 PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, matching continues by
1966 testing any remaining alternatives. Only if no complete match can be found is
1967 PCRE_ERROR_PARTIAL returned instead of PCRE_ERROR_NOMATCH. In other words,
1968 PCRE_PARTIAL_SOFT says that the caller is prepared to handle a partial match,
1969 but only if no complete match can be found.
1970 </P>
1971 <P>
1972 If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a
1973 partial match is found, <b>pcre_exec()</b> immediately returns
1974 PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words,
1975 when PCRE_PARTIAL_HARD is set, a partial match is considered to be more
1976 important that an alternative complete match.
1977 </P>
1978 <P>
1979 In both cases, the portion of the string that was inspected when the partial
1980 match was found is set as the first matching string. There is a more detailed
1981 discussion of partial and multi-segment matching, with examples, in the
1982 <a href="pcrepartial.html"><b>pcrepartial</b></a>
1983 documentation.
1984 </P>
1985 <br><b>
1986 The string to be matched by <b>pcre_exec()</b>
1987 </b><br>
1988 <P>
1989 The subject string is passed to <b>pcre_exec()</b> as a pointer in
1990 <i>subject</i>, a length in <i>length</i>, and a starting offset in
1991 <i>startoffset</i>. The units for <i>length</i> and <i>startoffset</i> are bytes
1992 for the 8-bit library, 16-bit data items for the 16-bit library, and 32-bit
1993 data items for the 32-bit library.
1994 </P>
1995 <P>
1996 If <i>startoffset</i> is negative or greater than the length of the subject,
1997 <b>pcre_exec()</b> returns PCRE_ERROR_BADOFFSET. When the starting offset is
1998 zero, the search for a match starts at the beginning of the subject, and this
1999 is by far the most common case. In UTF-8 or UTF-16 mode, the offset must point
2000 to the start of a character, or the end of the subject (in UTF-32 mode, one
2001 data unit equals one character, so all offsets are valid). Unlike the pattern
2002 string, the subject may contain binary zeroes.
2003 </P>
2004 <P>
2005 A non-zero starting offset is useful when searching for another match in the
2006 same subject by calling <b>pcre_exec()</b> again after a previous success.
2007 Setting <i>startoffset</i> differs from just passing over a shortened string and
2008 setting PCRE_NOTBOL in the case of a pattern that begins with any kind of
2009 lookbehind. For example, consider the pattern
2010 <pre>
2011 \Biss\B
2012 </pre>
2013 which finds occurrences of "iss" in the middle of words. (\B matches only if
2014 the current position in the subject is not a word boundary.) When applied to
2015 the string "Mississipi" the first call to <b>pcre_exec()</b> finds the first
2016 occurrence. If <b>pcre_exec()</b> is called again with just the remainder of the
2017 subject, namely "issipi", it does not match, because \B is always false at the
2018 start of the subject, which is deemed to be a word boundary. However, if
2019 <b>pcre_exec()</b> is passed the entire string again, but with <i>startoffset</i>
2020 set to 4, it finds the second occurrence of "iss" because it is able to look
2021 behind the starting point to discover that it is preceded by a letter.
2022 </P>
2023 <P>
2024 Finding all the matches in a subject is tricky when the pattern can match an
2025 empty string. It is possible to emulate Perl's /g behaviour by first trying the
2026 match again at the same offset, with the PCRE_NOTEMPTY_ATSTART and
2027 PCRE_ANCHORED options, and then if that fails, advancing the starting offset
2028 and trying an ordinary match again. There is some code that demonstrates how to
2029 do this in the
2030 <a href="pcredemo.html"><b>pcredemo</b></a>
2031 sample program. In the most general case, you have to check to see if the
2032 newline convention recognizes CRLF as a newline, and if so, and the current
2033 character is CR followed by LF, advance the starting offset by two characters
2034 instead of one.
2035 </P>
2036 <P>
2037 If a non-zero starting offset is passed when the pattern is anchored, one
2038 attempt to match at the given offset is made. This can only succeed if the
2039 pattern does not require the match to be at the start of the subject.
2040 </P>
2041 <br><b>
2042 How <b>pcre_exec()</b> returns captured substrings
2043 </b><br>
2044 <P>
2045 In general, a pattern matches a certain portion of the subject, and in
2046 addition, further substrings from the subject may be picked out by parts of the
2047 pattern. Following the usage in Jeffrey Friedl's book, this is called
2048 "capturing" in what follows, and the phrase "capturing subpattern" is used for
2049 a fragment of a pattern that picks out a substring. PCRE supports several other
2050 kinds of parenthesized subpattern that do not cause substrings to be captured.
2051 </P>
2052 <P>
2053 Captured substrings are returned to the caller via a vector of integers whose
2054 address is passed in <i>ovector</i>. The number of elements in the vector is
2055 passed in <i>ovecsize</i>, which must be a non-negative number. <b>Note</b>: this
2056 argument is NOT the size of <i>ovector</i> in bytes.
2057 </P>
2058 <P>
2059 The first two-thirds of the vector is used to pass back captured substrings,
2060 each substring using a pair of integers. The remaining third of the vector is
2061 used as workspace by <b>pcre_exec()</b> while matching capturing subpatterns,
2062 and is not available for passing back information. The number passed in
2063 <i>ovecsize</i> should always be a multiple of three. If it is not, it is
2064 rounded down.
2065 </P>
2066 <P>
2067 When a match is successful, information about captured substrings is returned
2068 in pairs of integers, starting at the beginning of <i>ovector</i>, and
2069 continuing up to two-thirds of its length at the most. The first element of
2070 each pair is set to the offset of the first character in a substring, and the
2071 second is set to the offset of the first character after the end of a
2072 substring. These values are always data unit offsets, even in UTF mode. They
2073 are byte offsets in the 8-bit library, 16-bit data item offsets in the 16-bit
2074 library, and 32-bit data item offsets in the 32-bit library. <b>Note</b>: they
2075 are not character counts.
2076 </P>
2077 <P>
2078 The first pair of integers, <i>ovector[0]</i> and <i>ovector[1]</i>, identify the
2079 portion of the subject string matched by the entire pattern. The next pair is
2080 used for the first capturing subpattern, and so on. The value returned by
2081 <b>pcre_exec()</b> is one more than the highest numbered pair that has been set.
2082 For example, if two substrings have been captured, the returned value is 3. If
2083 there are no capturing subpatterns, the return value from a successful match is
2084 1, indicating that just the first pair of offsets has been set.
2085 </P>
2086 <P>
2087 If a capturing subpattern is matched repeatedly, it is the last portion of the
2088 string that it matched that is returned.
2089 </P>
2090 <P>
2091 If the vector is too small to hold all the captured substring offsets, it is
2092 used as far as possible (up to two-thirds of its length), and the function
2093 returns a value of zero. If neither the actual string matched nor any captured
2094 substrings are of interest, <b>pcre_exec()</b> may be called with <i>ovector</i>
2095 passed as NULL and <i>ovecsize</i> as zero. However, if the pattern contains
2096 back references and the <i>ovector</i> is not big enough to remember the related
2097 substrings, PCRE has to get additional memory for use during matching. Thus it
2098 is usually advisable to supply an <i>ovector</i> of reasonable size.
2099 </P>
2100 <P>
2101 There are some cases where zero is returned (indicating vector overflow) when
2102 in fact the vector is exactly the right size for the final match. For example,
2103 consider the pattern
2104 <pre>
2105 (a)(?:(b)c|bd)
2106 </pre>
2107 If a vector of 6 elements (allowing for only 1 captured substring) is given
2108 with subject string "abd", <b>pcre_exec()</b> will try to set the second
2109 captured string, thereby recording a vector overflow, before failing to match
2110 "c" and backing up to try the second alternative. The zero return, however,
2111 does correctly indicate that the maximum number of slots (namely 2) have been
2112 filled. In similar cases where there is temporary overflow, but the final
2113 number of used slots is actually less than the maximum, a non-zero value is
2114 returned.
2115 </P>
2116 <P>
2117 The <b>pcre_fullinfo()</b> function can be used to find out how many capturing
2118 subpatterns there are in a compiled pattern. The smallest size for
2119 <i>ovector</i> that will allow for <i>n</i> captured substrings, in addition to
2120 the offsets of the substring matched by the whole pattern, is (<i>n</i>+1)*3.
2121 </P>
2122 <P>
2123 It is possible for capturing subpattern number <i>n+1</i> to match some part of
2124 the subject when subpattern <i>n</i> has not been used at all. For example, if
2125 the string "abc" is matched against the pattern (a|(z))(bc) the return from the
2126 function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
2127 happens, both values in the offset pairs corresponding to unused subpatterns
2128 are set to -1.
2129 </P>
2130 <P>
2131 Offset values that correspond to unused subpatterns at the end of the
2132 expression are also set to -1. For example, if the string "abc" is matched
2133 against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
2134 return from the function is 2, because the highest used capturing subpattern
2135 number is 1, and the offsets for for the second and third capturing subpatterns
2136 (assuming the vector is large enough, of course) are set to -1.
2137 </P>
2138 <P>
2139 <b>Note</b>: Elements in the first two-thirds of <i>ovector</i> that do not
2140 correspond to capturing parentheses in the pattern are never changed. That is,
2141 if a pattern contains <i>n</i> capturing parentheses, no more than
2142 <i>ovector[0]</i> to <i>ovector[2n+1]</i> are set by <b>pcre_exec()</b>. The other
2143 elements (in the first two-thirds) retain whatever values they previously had.
2144 </P>
2145 <P>
2146 Some convenience functions are provided for extracting the captured substrings
2147 as separate strings. These are described below.
2148 <a name="errorlist"></a></P>
2149 <br><b>
2150 Error return values from <b>pcre_exec()</b>
2151 </b><br>
2152 <P>
2153 If <b>pcre_exec()</b> fails, it returns a negative number. The following are
2154 defined in the header file:
2155 <pre>
2157 </pre>
2158 The subject string did not match the pattern.
2159 <pre>
2161 </pre>
2162 Either <i>code</i> or <i>subject</i> was passed as NULL, or <i>ovector</i> was
2163 NULL and <i>ovecsize</i> was not zero.
2164 <pre>
2166 </pre>
2167 An unrecognized bit was set in the <i>options</i> argument.
2168 <pre>
2170 </pre>
2171 PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch
2172 the case when it is passed a junk pointer and to detect when a pattern that was
2173 compiled in an environment of one endianness is run in an environment with the
2174 other endianness. This is the error that PCRE gives when the magic number is
2175 not present.
2176 <pre>
2178 </pre>
2179 While running the pattern match, an unknown item was encountered in the
2180 compiled pattern. This error could be caused by a bug in PCRE or by overwriting
2181 of the compiled pattern.
2182 <pre>
2184 </pre>
2185 If a pattern contains back references, but the <i>ovector</i> that is passed to
2186 <b>pcre_exec()</b> is not big enough to remember the referenced substrings, PCRE
2187 gets a block of memory at the start of matching to use for this purpose. If the
2188 call via <b>pcre_malloc()</b> fails, this error is given. The memory is
2189 automatically freed at the end of matching.
2190 </P>
2191 <P>
2192 This error is also given if <b>pcre_stack_malloc()</b> fails in
2193 <b>pcre_exec()</b>. This can happen only when PCRE has been compiled with
2194 <b>--disable-stack-for-recursion</b>.
2195 <pre>
2197 </pre>
2198 This error is used by the <b>pcre_copy_substring()</b>,
2199 <b>pcre_get_substring()</b>, and <b>pcre_get_substring_list()</b> functions (see
2200 below). It is never returned by <b>pcre_exec()</b>.
2201 <pre>
2203 </pre>
2204 The backtracking limit, as specified by the <i>match_limit</i> field in a
2205 <b>pcre_extra</b> structure (or defaulted) was reached. See the description
2206 above.
2207 <pre>
2209 </pre>
2210 This error is never generated by <b>pcre_exec()</b> itself. It is provided for
2211 use by callout functions that want to yield a distinctive error code. See the
2212 <a href="pcrecallout.html"><b>pcrecallout</b></a>
2213 documentation for details.
2214 <pre>
2216 </pre>
2217 A string that contains an invalid UTF-8 byte sequence was passed as a subject,
2218 and the PCRE_NO_UTF8_CHECK option was not set. If the size of the output vector
2219 (<i>ovecsize</i>) is at least 2, the byte offset to the start of the the invalid
2220 UTF-8 character is placed in the first element, and a reason code is placed in
2221 the second element. The reason codes are listed in the
2222 <a href="#badutf8reasons">following section.</a>
2223 For backward compatibility, if PCRE_PARTIAL_HARD is set and the problem is a
2224 truncated UTF-8 character at the end of the subject (reason codes 1 to 5),
2225 PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8.
2226 <pre>
2228 </pre>
2229 The UTF-8 byte sequence that was passed as a subject was checked and found to
2230 be valid (the PCRE_NO_UTF8_CHECK option was not set), but the value of
2231 <i>startoffset</i> did not point to the beginning of a UTF-8 character or the
2232 end of the subject.
2233 <pre>
2235 </pre>
2236 The subject string did not match, but it did match partially. See the
2237 <a href="pcrepartial.html"><b>pcrepartial</b></a>
2238 documentation for details of partial matching.
2239 <pre>
2241 </pre>
2242 This code is no longer in use. It was formerly returned when the PCRE_PARTIAL
2243 option was used with a compiled pattern containing items that were not
2244 supported for partial matching. From release 8.00 onwards, there are no
2245 restrictions on partial matching.
2246 <pre>
2248 </pre>
2249 An unexpected internal error has occurred. This error could be caused by a bug
2250 in PCRE or by overwriting of the compiled pattern.
2251 <pre>
2253 </pre>
2254 This error is given if the value of the <i>ovecsize</i> argument is negative.
2255 <pre>
2257 </pre>
2258 The internal recursion limit, as specified by the <i>match_limit_recursion</i>
2259 field in a <b>pcre_extra</b> structure (or defaulted) was reached. See the
2260 description above.
2261 <pre>
2263 </pre>
2264 An invalid combination of PCRE_NEWLINE_<i>xxx</i> options was given.
2265 <pre>
2267 </pre>
2268 The value of <i>startoffset</i> was negative or greater than the length of the
2269 subject, that is, the value in <i>length</i>.
2270 <pre>
2272 </pre>
2273 This error is returned instead of PCRE_ERROR_BADUTF8 when the subject string
2274 ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD option is set.
2275 Information about the failure is returned as for PCRE_ERROR_BADUTF8. It is in
2276 fact sufficient to detect this case, but this special error code for
2277 PCRE_PARTIAL_HARD precedes the implementation of returned information; it is
2278 retained for backwards compatibility.
2279 <pre>
2281 </pre>
2282 This error is returned when <b>pcre_exec()</b> detects a recursion loop within
2283 the pattern. Specifically, it means that either the whole pattern or a
2284 subpattern has been called recursively for the second time at the same position
2285 in the subject string. Some simple patterns that might do this are detected and
2286 faulted at compile time, but more complicated cases, in particular mutual
2287 recursions between two different subpatterns, cannot be detected until run
2288 time.
2289 <pre>
2291 </pre>
2292 This error is returned when a pattern that was successfully studied using a
2293 JIT compile option is being matched, but the memory available for the
2294 just-in-time processing stack is not large enough. See the
2295 <a href="pcrejit.html"><b>pcrejit</b></a>
2296 documentation for more details.
2297 <pre>
2299 </pre>
2300 This error is given if a pattern that was compiled by the 8-bit library is
2301 passed to a 16-bit or 32-bit library function, or vice versa.
2302 <pre>
2304 </pre>
2305 This error is given if a pattern that was compiled and saved is reloaded on a
2306 host with different endianness. The utility function
2307 <b>pcre_pattern_to_host_byte_order()</b> can be used to convert such a pattern
2308 so that it runs on the new host.
2309 <pre>
2311 </pre>
2312 This error is returned when a pattern that was successfully studied using a JIT
2313 compile option is being matched, but the matching mode (partial or complete
2314 match) does not correspond to any JIT compilation mode. When the JIT fast path
2315 function is used, this error may be also given for invalid options. See the
2316 <a href="pcrejit.html"><b>pcrejit</b></a>
2317 documentation for more details.
2318 <pre>
2320 </pre>
2321 This error is given if <b>pcre_exec()</b> is called with a negative value for
2322 the <i>length</i> argument.
2323 </P>
2324 <P>
2325 Error numbers -16 to -20, -22, and 30 are not used by <b>pcre_exec()</b>.
2326 <a name="badutf8reasons"></a></P>
2327 <br><b>
2328 Reason codes for invalid UTF-8 strings
2329 </b><br>
2330 <P>
2331 This section applies only to the 8-bit library. The corresponding information
2332 for the 16-bit and 32-bit libraries is given in the
2333 <a href="pcre16.html"><b>pcre16</b></a>
2334 and
2335 <a href="pcre32.html"><b>pcre32</b></a>
2336 pages.
2337 </P>
2338 <P>
2339 When <b>pcre_exec()</b> returns either PCRE_ERROR_BADUTF8 or
2340 PCRE_ERROR_SHORTUTF8, and the size of the output vector (<i>ovecsize</i>) is at
2341 least 2, the offset of the start of the invalid UTF-8 character is placed in
2342 the first output vector element (<i>ovector[0]</i>) and a reason code is placed
2343 in the second element (<i>ovector[1]</i>). The reason codes are given names in
2344 the <b>pcre.h</b> header file:
2345 <pre>
2351 </pre>
2352 The string ends with a truncated UTF-8 character; the code specifies how many
2353 bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be
2354 no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279)
2355 allows for up to 6 bytes, and this is checked first; hence the possibility of
2356 4 or 5 missing bytes.
2357 <pre>
2362 PCRE_UTF8_ERR10
2363 </pre>
2364 The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the
2365 character do not have the binary value 0b10 (that is, either the most
2366 significant bit is 0, or the next bit is 1).
2367 <pre>
2368 PCRE_UTF8_ERR11
2369 PCRE_UTF8_ERR12
2370 </pre>
2371 A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long;
2372 these code points are excluded by RFC 3629.
2373 <pre>
2374 PCRE_UTF8_ERR13
2375 </pre>
2376 A 4-byte character has a value greater than 0x10fff; these code points are
2377 excluded by RFC 3629.
2378 <pre>
2379 PCRE_UTF8_ERR14
2380 </pre>
2381 A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of
2382 code points are reserved by RFC 3629 for use with UTF-16, and so are excluded
2383 from UTF-8.
2384 <pre>
2385 PCRE_UTF8_ERR15
2386 PCRE_UTF8_ERR16
2387 PCRE_UTF8_ERR17
2388 PCRE_UTF8_ERR18
2389 PCRE_UTF8_ERR19
2390 </pre>
2391 A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a
2392 value that can be represented by fewer bytes, which is invalid. For example,
2393 the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just
2394 one byte.
2395 <pre>
2396 PCRE_UTF8_ERR20
2397 </pre>
2398 The two most significant bits of the first byte of a character have the binary
2399 value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a
2400 byte can only validly occur as the second or subsequent byte of a multi-byte
2401 character.
2402 <pre>
2403 PCRE_UTF8_ERR21
2404 </pre>
2405 The first byte of a character has the value 0xfe or 0xff. These values can
2406 never occur in a valid UTF-8 string.
2407 <pre>
2408 PCRE_UTF8_ERR22
2409 </pre>
2410 This error code was formerly used when the presence of a so-called
2411 "non-character" caused an error. Unicode corrigendum #9 makes it clear that
2412 such characters should not cause a string to be rejected, and so this code is
2413 no longer in use and is never returned.
2414 </P>
2415 <br><a name="SEC18" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NUMBER</a><br>
2416 <P>
2417 <b>int pcre_copy_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
2418 <b> int <i>stringcount</i>, int <i>stringnumber</i>, char *<i>buffer</i>,</b>
2419 <b> int <i>buffersize</i>);</b>
2420 <br>
2421 <br>
2422 <b>int pcre_get_substring(const char *<i>subject</i>, int *<i>ovector</i>,</b>
2423 <b> int <i>stringcount</i>, int <i>stringnumber</i>,</b>
2424 <b> const char **<i>stringptr</i>);</b>
2425 <br>
2426 <br>
2427 <b>int pcre_get_substring_list(const char *<i>subject</i>,</b>
2428 <b> int *<i>ovector</i>, int <i>stringcount</i>, const char ***<i>listptr</i>);</b>
2429 </P>
2430 <P>
2431 Captured substrings can be accessed directly by using the offsets returned by
2432 <b>pcre_exec()</b> in <i>ovector</i>. For convenience, the functions
2433 <b>pcre_copy_substring()</b>, <b>pcre_get_substring()</b>, and
2434 <b>pcre_get_substring_list()</b> are provided for extracting captured substrings
2435 as new, separate, zero-terminated strings. These functions identify substrings
2436 by number. The next section describes functions for extracting named
2437 substrings.
2438 </P>
2439 <P>
2440 A substring that contains a binary zero is correctly extracted and has a
2441 further zero added on the end, but the result is not, of course, a C string.
2442 However, you can process such a string by referring to the length that is
2443 returned by <b>pcre_copy_substring()</b> and <b>pcre_get_substring()</b>.
2444 Unfortunately, the interface to <b>pcre_get_substring_list()</b> is not adequate
2445 for handling strings containing binary zeros, because the end of the final
2446 string is not independently indicated.
2447 </P>
2448 <P>
2449 The first three arguments are the same for all three of these functions:
2450 <i>subject</i> is the subject string that has just been successfully matched,
2451 <i>ovector</i> is a pointer to the vector of integer offsets that was passed to
2452 <b>pcre_exec()</b>, and <i>stringcount</i> is the number of substrings that were
2453 captured by the match, including the substring that matched the entire regular
2454 expression. This is the value returned by <b>pcre_exec()</b> if it is greater
2455 than zero. If <b>pcre_exec()</b> returned zero, indicating that it ran out of
2456 space in <i>ovector</i>, the value passed as <i>stringcount</i> should be the
2457 number of elements in the vector divided by three.
2458 </P>
2459 <P>
2460 The functions <b>pcre_copy_substring()</b> and <b>pcre_get_substring()</b>
2461 extract a single substring, whose number is given as <i>stringnumber</i>. A
2462 value of zero extracts the substring that matched the entire pattern, whereas
2463 higher values extract the captured substrings. For <b>pcre_copy_substring()</b>,
2464 the string is placed in <i>buffer</i>, whose length is given by
2465 <i>buffersize</i>, while for <b>pcre_get_substring()</b> a new block of memory is
2466 obtained via <b>pcre_malloc</b>, and its address is returned via
2467 <i>stringptr</i>. The yield of the function is the length of the string, not
2468 including the terminating zero, or one of these error codes:
2469 <pre>
2471 </pre>
2472 The buffer was too small for <b>pcre_copy_substring()</b>, or the attempt to get
2473 memory failed for <b>pcre_get_substring()</b>.
2474 <pre>
2476 </pre>
2477 There is no substring whose number is <i>stringnumber</i>.
2478 </P>
2479 <P>
2480 The <b>pcre_get_substring_list()</b> function extracts all available substrings
2481 and builds a list of pointers to them. All this is done in a single block of
2482 memory that is obtained via <b>pcre_malloc</b>. The address of the memory block
2483 is returned via <i>listptr</i>, which is also the start of the list of string
2484 pointers. The end of the list is marked by a NULL pointer. The yield of the
2485 function is zero if all went well, or the error code
2486 <pre>
2488 </pre>
2489 if the attempt to get the memory block failed.
2490 </P>
2491 <P>
2492 When any of these functions encounter a substring that is unset, which can
2493 happen when capturing subpattern number <i>n+1</i> matches some part of the
2494 subject, but subpattern <i>n</i> has not been used at all, they return an empty
2495 string. This can be distinguished from a genuine zero-length substring by
2496 inspecting the appropriate offset in <i>ovector</i>, which is negative for unset
2497 substrings.
2498 </P>
2499 <P>
2500 The two convenience functions <b>pcre_free_substring()</b> and
2501 <b>pcre_free_substring_list()</b> can be used to free the memory returned by
2502 a previous call of <b>pcre_get_substring()</b> or
2503 <b>pcre_get_substring_list()</b>, respectively. They do nothing more than call
2504 the function pointed to by <b>pcre_free</b>, which of course could be called
2505 directly from a C program. However, PCRE is used in some situations where it is
2506 linked via a special interface to another programming language that cannot use
2507 <b>pcre_free</b> directly; it is for these cases that the functions are
2508 provided.
2509 </P>
2510 <br><a name="SEC19" href="#TOC1">EXTRACTING CAPTURED SUBSTRINGS BY NAME</a><br>
2511 <P>
2512 <b>int pcre_get_stringnumber(const pcre *<i>code</i>,</b>
2513 <b> const char *<i>name</i>);</b>
2514 <br>
2515 <br>
2516 <b>int pcre_copy_named_substring(const pcre *<i>code</i>,</b>
2517 <b> const char *<i>subject</i>, int *<i>ovector</i>,</b>
2518 <b> int <i>stringcount</i>, const char *<i>stringname</i>,</b>
2519 <b> char *<i>buffer</i>, int <i>buffersize</i>);</b>
2520 <br>
2521 <br>
2522 <b>int pcre_get_named_substring(const pcre *<i>code</i>,</b>
2523 <b> const char *<i>subject</i>, int *<i>ovector</i>,</b>
2524 <b> int <i>stringcount</i>, const char *<i>stringname</i>,</b>
2525 <b> const char **<i>stringptr</i>);</b>
2526 </P>
2527 <P>
2528 To extract a substring by name, you first have to find associated number.
2529 For example, for this pattern
2530 <pre>
2531 (a+)b(?&#60;xxx&#62;\d+)...
2532 </pre>
2533 the number of the subpattern called "xxx" is 2. If the name is known to be
2534 unique (PCRE_DUPNAMES was not set), you can find the number from the name by
2535 calling <b>pcre_get_stringnumber()</b>. The first argument is the compiled
2536 pattern, and the second is the name. The yield of the function is the
2537 subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of
2538 that name.
2539 </P>
2540 <P>
2541 Given the number, you can extract the substring directly, or use one of the
2542 functions described in the previous section. For convenience, there are also
2543 two functions that do the whole job.
2544 </P>
2545 <P>
2546 Most of the arguments of <b>pcre_copy_named_substring()</b> and
2547 <b>pcre_get_named_substring()</b> are the same as those for the similarly named
2548 functions that extract by number. As these are described in the previous
2549 section, they are not re-described here. There are just two differences:
2550 </P>
2551 <P>
2552 First, instead of a substring number, a substring name is given. Second, there
2553 is an extra argument, given at the start, which is a pointer to the compiled
2554 pattern. This is needed in order to gain access to the name-to-number
2555 translation table.
2556 </P>
2557 <P>
2558 These functions call <b>pcre_get_stringnumber()</b>, and if it succeeds, they
2559 then call <b>pcre_copy_substring()</b> or <b>pcre_get_substring()</b>, as
2560 appropriate. <b>NOTE:</b> If PCRE_DUPNAMES is set and there are duplicate names,
2561 the behaviour may not be what you want (see the next section).
2562 </P>
2563 <P>
2564 <b>Warning:</b> If the pattern uses the (?| feature to set up multiple
2565 subpatterns with the same number, as described in the
2566 <a href="pcrepattern.html#dupsubpatternnumber">section on duplicate subpattern numbers</a>
2567 in the
2568 <a href="pcrepattern.html"><b>pcrepattern</b></a>
2569 page, you cannot use names to distinguish the different subpatterns, because
2570 names are not included in the compiled code. The matching process uses only
2571 numbers. For this reason, the use of different names for subpatterns of the
2572 same number causes an error at compile time.
2573 </P>
2574 <br><a name="SEC20" href="#TOC1">DUPLICATE SUBPATTERN NAMES</a><br>
2575 <P>
2576 <b>int pcre_get_stringtable_entries(const pcre *<i>code</i>,</b>
2577 <b> const char *<i>name</i>, char **<i>first</i>, char **<i>last</i>);</b>
2578 </P>
2579 <P>
2580 When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
2581 are not required to be unique. (Duplicate names are always allowed for
2582 subpatterns with the same number, created by using the (?| feature. Indeed, if
2583 such subpatterns are named, they are required to use the same names.)
2584 </P>
2585 <P>
2586 Normally, patterns with duplicate names are such that in any one match, only
2587 one of the named subpatterns participates. An example is shown in the
2588 <a href="pcrepattern.html"><b>pcrepattern</b></a>
2589 documentation.
2590 </P>
2591 <P>
2592 When duplicates are present, <b>pcre_copy_named_substring()</b> and
2593 <b>pcre_get_named_substring()</b> return the first substring corresponding to
2594 the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
2595 returned; no data is returned. The <b>pcre_get_stringnumber()</b> function
2596 returns one of the numbers that are associated with the name, but it is not
2597 defined which it is.
2598 </P>
2599 <P>
2600 If you want to get full details of all captured substrings for a given name,
2601 you must use the <b>pcre_get_stringtable_entries()</b> function. The first
2602 argument is the compiled pattern, and the second is the name. The third and
2603 fourth are pointers to variables which are updated by the function. After it
2604 has run, they point to the first and last entries in the name-to-number table
2605 for the given name. The function itself returns the length of each entry, or
2606 PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
2607 described above in the section entitled <i>Information about a pattern</i>
2608 <a href="#infoaboutpattern">above.</a>
2609 Given all the relevant entries for the name, you can extract each of their
2610 numbers, and hence the captured data, if any.
2611 </P>
2612 <br><a name="SEC21" href="#TOC1">FINDING ALL POSSIBLE MATCHES</a><br>
2613 <P>
2614 The traditional matching function uses a similar algorithm to Perl, which stops
2615 when it finds the first match, starting at a given point in the subject. If you
2616 want to find all possible matches, or the longest possible match, consider
2617 using the alternative matching function (see below) instead. If you cannot use
2618 the alternative function, but still need to find all possible matches, you
2619 can kludge it up by making use of the callout facility, which is described in
2620 the
2621 <a href="pcrecallout.html"><b>pcrecallout</b></a>
2622 documentation.
2623 </P>
2624 <P>
2625 What you have to do is to insert a callout right at the end of the pattern.
2626 When your callout function is called, extract and save the current matched
2627 substring. Then return 1, which forces <b>pcre_exec()</b> to backtrack and try
2628 other alternatives. Ultimately, when it runs out of matches, <b>pcre_exec()</b>
2629 will yield PCRE_ERROR_NOMATCH.
2630 </P>
2631 <br><a name="SEC22" href="#TOC1">OBTAINING AN ESTIMATE OF STACK USAGE</a><br>
2632 <P>
2633 Matching certain patterns using <b>pcre_exec()</b> can use a lot of process
2634 stack, which in certain environments can be rather limited in size. Some users
2635 find it helpful to have an estimate of the amount of stack that is used by
2636 <b>pcre_exec()</b>, to help them set recursion limits, as described in the
2637 <a href="pcrestack.html"><b>pcrestack</b></a>
2638 documentation. The estimate that is output by <b>pcretest</b> when called with
2639 the <b>-m</b> and <b>-C</b> options is obtained by calling <b>pcre_exec</b> with
2640 the values NULL, NULL, NULL, -999, and -999 for its first five arguments.
2641 </P>
2642 <P>
2643 Normally, if its first argument is NULL, <b>pcre_exec()</b> immediately returns
2644 the negative error code PCRE_ERROR_NULL, but with this special combination of
2645 arguments, it returns instead a negative number whose absolute value is the
2646 approximate stack frame size in bytes. (A negative number is used so that it is
2647 clear that no match has happened.) The value is approximate because in some
2648 cases, recursive calls to <b>pcre_exec()</b> occur when there are one or two
2649 additional variables on the stack.
2650 </P>
2651 <P>
2652 If PCRE has been compiled to use the heap instead of the stack for recursion,
2653 the value returned is the size of each block that is obtained from the heap.
2654 <a name="dfamatch"></a></P>
2655 <br><a name="SEC23" href="#TOC1">MATCHING A PATTERN: THE ALTERNATIVE FUNCTION</a><br>
2656 <P>
2657 <b>int pcre_dfa_exec(const pcre *<i>code</i>, const pcre_extra *<i>extra</i>,</b>
2658 <b> const char *<i>subject</i>, int <i>length</i>, int <i>startoffset</i>,</b>
2659 <b> int <i>options</i>, int *<i>ovector</i>, int <i>ovecsize</i>,</b>
2660 <b> int *<i>workspace</i>, int <i>wscount</i>);</b>
2661 </P>
2662 <P>
2663 The function <b>pcre_dfa_exec()</b> is called to match a subject string against
2664 a compiled pattern, using a matching algorithm that scans the subject string
2665 just once, and does not backtrack. This has different characteristics to the
2666 normal algorithm, and is not compatible with Perl. Some of the features of PCRE
2667 patterns are not supported. Nevertheless, there are times when this kind of
2668 matching can be useful. For a discussion of the two matching algorithms, and a
2669 list of features that <b>pcre_dfa_exec()</b> does not support, see the
2670 <a href="pcrematching.html"><b>pcrematching</b></a>
2671 documentation.
2672 </P>
2673 <P>
2674 The arguments for the <b>pcre_dfa_exec()</b> function are the same as for
2675 <b>pcre_exec()</b>, plus two extras. The <i>ovector</i> argument is used in a
2676 different way, and this is described below. The other common arguments are used
2677 in the same way as for <b>pcre_exec()</b>, so their description is not repeated
2678 here.
2679 </P>
2680 <P>
2681 The two additional arguments provide workspace for the function. The workspace
2682 vector should contain at least 20 elements. It is used for keeping track of
2683 multiple paths through the pattern tree. More workspace will be needed for
2684 patterns and subjects where there are a lot of potential matches.
2685 </P>
2686 <P>
2687 Here is an example of a simple call to <b>pcre_dfa_exec()</b>:
2688 <pre>
2689 int rc;
2690 int ovector[10];
2691 int wspace[20];
2692 rc = pcre_dfa_exec(
2693 re, /* result of pcre_compile() */
2694 NULL, /* we didn't study the pattern */
2695 "some string", /* the subject string */
2696 11, /* the length of the subject string */
2697 0, /* start at offset 0 in the subject */
2698 0, /* default options */
2699 ovector, /* vector of integers for substring information */
2700 10, /* number of elements (NOT size in bytes) */
2701 wspace, /* working space vector */
2702 20); /* number of elements (NOT size in bytes) */
2703 </PRE>
2704 </P>
2705 <br><b>
2706 Option bits for <b>pcre_dfa_exec()</b>
2707 </b><br>
2708 <P>
2709 The unused bits of the <i>options</i> argument for <b>pcre_dfa_exec()</b> must be
2710 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_<i>xxx</i>,
2714 All but the last four of these are exactly the same as for <b>pcre_exec()</b>,
2715 so their description is not repeated here.
2716 <pre>
2719 </pre>
2720 These have the same general effect as they do for <b>pcre_exec()</b>, but the
2721 details are slightly different. When PCRE_PARTIAL_HARD is set for
2722 <b>pcre_dfa_exec()</b>, it returns PCRE_ERROR_PARTIAL if the end of the subject
2723 is reached and there is still at least one matching possibility that requires
2724 additional characters. This happens even if some complete matches have also
2725 been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH
2726 is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached,
2727 there have been no complete matches, but there is still at least one matching
2728 possibility. The portion of the string that was inspected when the longest
2729 partial match was found is set as the first matching string in both cases.
2730 There is a more detailed discussion of partial and multi-segment matching, with
2731 examples, in the
2732 <a href="pcrepartial.html"><b>pcrepartial</b></a>
2733 documentation.
2734 <pre>
2736 </pre>
2737 Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
2738 soon as it has found one match. Because of the way the alternative algorithm
2739 works, this is necessarily the shortest possible match at the first possible
2740 matching point in the subject string.
2741 <pre>
2743 </pre>
2744 When <b>pcre_dfa_exec()</b> returns a partial match, it is possible to call it
2745 again, with additional subject characters, and have it continue with the same
2746 match. The PCRE_DFA_RESTART option requests this action; when it is set, the
2747 <i>workspace</i> and <i>wscount</i> options must reference the same vector as
2748 before because data about the match so far is left in them after a partial
2749 match. There is more discussion of this facility in the
2750 <a href="pcrepartial.html"><b>pcrepartial</b></a>
2751 documentation.
2752 </P>
2753 <br><b>
2754 Successful returns from <b>pcre_dfa_exec()</b>
2755 </b><br>
2756 <P>
2757 When <b>pcre_dfa_exec()</b> succeeds, it may have matched more than one
2758 substring in the subject. Note, however, that all the matches from one run of
2759 the function start at the same point in the subject. The shorter matches are
2760 all initial substrings of the longer matches. For example, if the pattern
2761 <pre>
2762 &#60;.*&#62;
2763 </pre>
2764 is matched against the string
2765 <pre>
2766 This is &#60;something&#62; &#60;something else&#62; &#60;something further&#62; no more
2767 </pre>
2768 the three matched strings are
2769 <pre>
2770 &#60;something&#62;
2771 &#60;something&#62; &#60;something else&#62;
2772 &#60;something&#62; &#60;something else&#62; &#60;something further&#62;
2773 </pre>
2774 On success, the yield of the function is a number greater than zero, which is
2775 the number of matched substrings. The substrings themselves are returned in
2776 <i>ovector</i>. Each string uses two elements; the first is the offset to the
2777 start, and the second is the offset to the end. In fact, all the strings have
2778 the same start offset. (Space could have been saved by giving this only once,
2779 but it was decided to retain some compatibility with the way <b>pcre_exec()</b>
2780 returns data, even though the meaning of the strings is different.)
2781 </P>
2782 <P>
2783 The strings are returned in reverse order of length; that is, the longest
2784 matching string is given first. If there were too many matches to fit into
2785 <i>ovector</i>, the yield of the function is zero, and the vector is filled with
2786 the longest matches. Unlike <b>pcre_exec()</b>, <b>pcre_dfa_exec()</b> can use
2787 the entire <i>ovector</i> for returning matched strings.
2788 </P>
2789 <br><b>
2790 Error returns from <b>pcre_dfa_exec()</b>
2791 </b><br>
2792 <P>
2793 The <b>pcre_dfa_exec()</b> function returns a negative number when it fails.
2794 Many of the errors are the same as for <b>pcre_exec()</b>, and these are
2795 described
2796 <a href="#errorlist">above.</a>
2797 There are in addition the following errors that are specific to
2798 <b>pcre_dfa_exec()</b>:
2799 <pre>
2801 </pre>
2802 This return is given if <b>pcre_dfa_exec()</b> encounters an item in the pattern
2803 that it does not support, for instance, the use of \C or a back reference.
2804 <pre>
2806 </pre>
2807 This return is given if <b>pcre_dfa_exec()</b> encounters a condition item that
2808 uses a back reference for the condition, or a test for recursion in a specific
2809 group. These are not supported.
2810 <pre>
2812 </pre>
2813 This return is given if <b>pcre_dfa_exec()</b> is called with an <i>extra</i>
2814 block that contains a setting of the <i>match_limit</i> or
2815 <i>match_limit_recursion</i> fields. This is not supported (these fields are
2816 meaningless for DFA matching).
2817 <pre>
2819 </pre>
2820 This return is given if <b>pcre_dfa_exec()</b> runs out of space in the
2821 <i>workspace</i> vector.
2822 <pre>
2824 </pre>
2825 When a recursive subpattern is processed, the matching function calls itself
2826 recursively, using private vectors for <i>ovector</i> and <i>workspace</i>. This
2827 error is given if the output vector is not large enough. This should be
2828 extremely rare, as a vector of size 1000 is used.
2829 <pre>
2831 </pre>
2832 When <b>pcre_dfa_exec()</b> is called with the <b>PCRE_DFA_RESTART</b> option,
2833 some plausibility checks are made on the contents of the workspace, which
2834 should contain data about the previous partial match. If any of these checks
2835 fail, this error is given.
2836 </P>
2837 <br><a name="SEC24" href="#TOC1">SEE ALSO</a><br>
2838 <P>
2839 <b>pcre16</b>(3), <b>pcre32</b>(3), <b>pcrebuild</b>(3), <b>pcrecallout</b>(3),
2840 <b>pcrecpp(3)</b>(3), <b>pcrematching</b>(3), <b>pcrepartial</b>(3),
2841 <b>pcreposix</b>(3), <b>pcreprecompile</b>(3), <b>pcresample</b>(3),
2842 <b>pcrestack</b>(3).
2843 </P>
2844 <br><a name="SEC25" href="#TOC1">AUTHOR</a><br>
2845 <P>
2846 Philip Hazel
2847 <br>
2848 University Computing Service
2849 <br>
2850 Cambridge CB2 3QH, England.
2851 <br>
2852 </P>
2853 <br><a name="SEC26" href="#TOC1">REVISION</a><br>
2854 <P>
2855 Last updated: 12 June 2013
2856 <br>
2857 Copyright &copy; 1997-2013 University of Cambridge.
2858 <br>
2859 <p>
2860 Return to the <a href="index.html">PCRE index page</a>.
2861 </p>


Name Value
svn:eol-style native
svn:keywords "Author Date Id Revision Url"

  ViewVC Help
Powered by ViewVC 1.1.5