ViewVC logotype

Contents of /code/trunk/doc/pcreapi.3

Parent Directory Parent Directory | Revision Log Revision Log

Revision 1459 - (show annotations)
Tue Mar 4 10:45:15 2014 UTC (19 months ago) by ph10
File size: 129199 byte(s)
Error occurred while calculating annotation data.
Preparations for next release.
1 .TH PCREAPI 3 "09 February 2014" "PCRE 8.35"
3 PCRE - Perl-compatible regular expressions
4 .sp
5 .B #include <pcre.h>
6 .
7 .
9 .rs
10 .sp
11 .nf
12 .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
13 .B " const char **\fIerrptr\fP, int *\fIerroffset\fP,"
14 .B " const unsigned char *\fItableptr\fP);"
15 .sp
16 .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
17 .B " int *\fIerrorcodeptr\fP,"
18 .B " const char **\fIerrptr\fP, int *\fIerroffset\fP,"
19 .B " const unsigned char *\fItableptr\fP);"
20 .sp
21 .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,
22 .B " const char **\fIerrptr\fP);"
23 .sp
24 .B void pcre_free_study(pcre_extra *\fIextra\fP);
25 .sp
26 .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
27 .B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP,"
28 .B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);"
29 .sp
30 .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
31 .B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP,"
32 .B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,"
33 .B " int *\fIworkspace\fP, int \fIwscount\fP);"
34 .fi
35 .
36 .
38 .rs
39 .sp
40 .nf
41 .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
42 .B " const char *\fIsubject\fP, int *\fIovector\fP,"
43 .B " int \fIstringcount\fP, const char *\fIstringname\fP,"
44 .B " char *\fIbuffer\fP, int \fIbuffersize\fP);"
45 .sp
46 .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
47 .B " int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,"
48 .B " int \fIbuffersize\fP);"
49 .sp
50 .B int pcre_get_named_substring(const pcre *\fIcode\fP,
51 .B " const char *\fIsubject\fP, int *\fIovector\fP,"
52 .B " int \fIstringcount\fP, const char *\fIstringname\fP,"
53 .B " const char **\fIstringptr\fP);"
54 .sp
55 .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
56 .B " const char *\fIname\fP);"
57 .sp
58 .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
59 .B " const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);"
60 .sp
61 .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
62 .B " int \fIstringcount\fP, int \fIstringnumber\fP,"
63 .B " const char **\fIstringptr\fP);"
64 .sp
65 .B int pcre_get_substring_list(const char *\fIsubject\fP,
66 .B " int *\fIovector\fP, int \fIstringcount\fP, const char ***\fIlistptr\fP);"
67 .sp
68 .B void pcre_free_substring(const char *\fIstringptr\fP);
69 .sp
70 .B void pcre_free_substring_list(const char **\fIstringptr\fP);
71 .fi
72 .
73 .
75 .rs
76 .sp
77 .nf
78 .B int pcre_jit_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
79 .B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP,"
80 .B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,"
81 .B " pcre_jit_stack *\fIjstack\fP);"
82 .sp
83 .B pcre_jit_stack *pcre_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP);
84 .sp
85 .B void pcre_jit_stack_free(pcre_jit_stack *\fIstack\fP);
86 .sp
87 .B void pcre_assign_jit_stack(pcre_extra *\fIextra\fP,
88 .B " pcre_jit_callback \fIcallback\fP, void *\fIdata\fP);"
89 .sp
90 .B const unsigned char *pcre_maketables(void);
91 .sp
92 .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
93 .B " int \fIwhat\fP, void *\fIwhere\fP);"
94 .sp
95 .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
96 .sp
97 .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
98 .sp
99 .B const char *pcre_version(void);
100 .sp
101 .B int pcre_pattern_to_host_byte_order(pcre *\fIcode\fP,
102 .B " pcre_extra *\fIextra\fP, const unsigned char *\fItables\fP);"
103 .fi
104 .
105 .
107 .rs
108 .sp
109 .nf
110 .B void *(*pcre_malloc)(size_t);
111 .sp
112 .B void (*pcre_free)(void *);
113 .sp
114 .B void *(*pcre_stack_malloc)(size_t);
115 .sp
116 .B void (*pcre_stack_free)(void *);
117 .sp
118 .B int (*pcre_callout)(pcre_callout_block *);
119 .sp
120 .B int (*pcre_stack_guard)(void);
121 .fi
122 .
123 .
125 .rs
126 .sp
127 As well as support for 8-bit character strings, PCRE also supports 16-bit
128 strings (from release 8.30) and 32-bit strings (from release 8.32), by means of
129 two additional libraries. They can be built as well as, or instead of, the
130 8-bit library. To avoid too much complication, this document describes the
131 8-bit versions of the functions, with only occasional references to the 16-bit
132 and 32-bit libraries.
133 .P
134 The 16-bit and 32-bit functions operate in the same way as their 8-bit
135 counterparts; they just use different data types for their arguments and
136 results, and their names start with \fBpcre16_\fP or \fBpcre32_\fP instead of
137 \fBpcre_\fP. For every option that has UTF8 in its name (for example,
138 PCRE_UTF8), there are corresponding 16-bit and 32-bit names with UTF8 replaced
139 by UTF16 or UTF32, respectively. This facility is in fact just cosmetic; the
140 16-bit and 32-bit option names define the same bit values.
141 .P
142 References to bytes and UTF-8 in this document should be read as references to
143 16-bit data units and UTF-16 when using the 16-bit library, or 32-bit data
144 units and UTF-32 when using the 32-bit library, unless specified otherwise.
145 More details of the specific differences for the 16-bit and 32-bit libraries
146 are given in the
147 .\" HREF
148 \fBpcre16\fP
149 .\"
150 and
151 .\" HREF
152 \fBpcre32\fP
153 .\"
154 pages.
155 .
156 .
158 .rs
159 .sp
160 PCRE has its own native API, which is described in this document. There are
161 also some wrapper functions (for the 8-bit library only) that correspond to the
162 POSIX regular expression API, but they do not give access to all the
163 functionality. They are described in the
164 .\" HREF
165 \fBpcreposix\fP
166 .\"
167 documentation. Both of these APIs define a set of C function calls. A C++
168 wrapper (again for the 8-bit library only) is also distributed with PCRE. It is
169 documented in the
170 .\" HREF
171 \fBpcrecpp\fP
172 .\"
173 page.
174 .P
175 The native API C function prototypes are defined in the header file
176 \fBpcre.h\fP, and on Unix-like systems the (8-bit) library itself is called
177 \fBlibpcre\fP. It can normally be accessed by adding \fB-lpcre\fP to the
178 command for linking an application that uses PCRE. The header file defines the
179 macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release numbers
180 for the library. Applications can use these to include support for different
181 releases of PCRE.
182 .P
183 In a Windows environment, if you want to statically link an application program
184 against a non-dll \fBpcre.a\fP file, you must define PCRE_STATIC before
185 including \fBpcre.h\fP or \fBpcrecpp.h\fP, because otherwise the
186 \fBpcre_malloc()\fP and \fBpcre_free()\fP exported functions will be declared
187 \fB__declspec(dllimport)\fP, with unwanted results.
188 .P
189 The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,
190 and \fBpcre_exec()\fP are used for compiling and matching regular expressions
191 in a Perl-compatible manner. A sample program that demonstrates the simplest
192 way of using them is provided in the file called \fIpcredemo.c\fP in the PCRE
193 source distribution. A listing of this program is given in the
194 .\" HREF
195 \fBpcredemo\fP
196 .\"
197 documentation, and the
198 .\" HREF
199 \fBpcresample\fP
200 .\"
201 documentation describes how to compile and run it.
202 .P
203 Just-in-time compiler support is an optional feature of PCRE that can be built
204 in appropriate hardware environments. It greatly speeds up the matching
205 performance of many patterns. Simple programs can easily request that it be
206 used if available, by setting an option that is ignored when it is not
207 relevant. More complicated programs might need to make use of the functions
208 \fBpcre_jit_stack_alloc()\fP, \fBpcre_jit_stack_free()\fP, and
209 \fBpcre_assign_jit_stack()\fP in order to control the JIT code's memory usage.
210 .P
211 From release 8.32 there is also a direct interface for JIT execution, which
212 gives improved performance. The JIT-specific functions are discussed in the
213 .\" HREF
214 \fBpcrejit\fP
215 .\"
216 documentation.
217 .P
218 A second matching function, \fBpcre_dfa_exec()\fP, which is not
219 Perl-compatible, is also provided. This uses a different algorithm for the
220 matching. The alternative algorithm finds all possible matches (at a given
221 point in the subject), and scans the subject just once (unless there are
222 lookbehind assertions). However, this algorithm does not return captured
223 substrings. A description of the two matching algorithms and their advantages
224 and disadvantages is given in the
225 .\" HREF
226 \fBpcrematching\fP
227 .\"
228 documentation.
229 .P
230 In addition to the main compiling and matching functions, there are convenience
231 functions for extracting captured substrings from a subject string that is
232 matched by \fBpcre_exec()\fP. They are:
233 .sp
234 \fBpcre_copy_substring()\fP
235 \fBpcre_copy_named_substring()\fP
236 \fBpcre_get_substring()\fP
237 \fBpcre_get_named_substring()\fP
238 \fBpcre_get_substring_list()\fP
239 \fBpcre_get_stringnumber()\fP
240 \fBpcre_get_stringtable_entries()\fP
241 .sp
242 \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also
243 provided, to free the memory used for extracted strings.
244 .P
245 The function \fBpcre_maketables()\fP is used to build a set of character tables
246 in the current locale for passing to \fBpcre_compile()\fP, \fBpcre_exec()\fP,
247 or \fBpcre_dfa_exec()\fP. This is an optional facility that is provided for
248 specialist use. Most commonly, no special tables are passed, in which case
249 internal tables that are generated when PCRE is built are used.
250 .P
251 The function \fBpcre_fullinfo()\fP is used to find out information about a
252 compiled pattern. The function \fBpcre_version()\fP returns a pointer to a
253 string containing the version of PCRE and its date of release.
254 .P
255 The function \fBpcre_refcount()\fP maintains a reference count in a data block
256 containing a compiled pattern. This is provided for the benefit of
257 object-oriented applications.
258 .P
259 The global variables \fBpcre_malloc\fP and \fBpcre_free\fP initially contain
260 the entry points of the standard \fBmalloc()\fP and \fBfree()\fP functions,
261 respectively. PCRE calls the memory management functions via these variables,
262 so a calling program can replace them if it wishes to intercept the calls. This
263 should be done before calling any PCRE functions.
264 .P
265 The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also
266 indirections to memory management functions. These special functions are used
267 only when PCRE is compiled to use the heap for remembering data, instead of
268 recursive function calls, when running the \fBpcre_exec()\fP function. See the
269 .\" HREF
270 \fBpcrebuild\fP
271 .\"
272 documentation for details of how to do this. It is a non-standard way of
273 building PCRE, for use in environments that have limited stacks. Because of the
274 greater use of memory management, it runs more slowly. Separate functions are
275 provided so that special-purpose external code can be used for this case. When
276 used, these functions are always called in a stack-like manner (last obtained,
277 first freed), and always for memory blocks of the same size. There is a
278 discussion about PCRE's stack usage in the
279 .\" HREF
280 \fBpcrestack\fP
281 .\"
282 documentation.
283 .P
284 The global variable \fBpcre_callout\fP initially contains NULL. It can be set
285 by the caller to a "callout" function, which PCRE will then call at specified
286 points during a matching operation. Details are given in the
287 .\" HREF
288 \fBpcrecallout\fP
289 .\"
290 documentation.
291 .P
292 The global variable \fBpcre_stack_guard\fP initially contains NULL. It can be
293 set by the caller to a function that is called by PCRE whenever it starts
294 to compile a parenthesized part of a pattern. When parentheses are nested, PCRE
295 uses recursive function calls, which use up the system stack. This function is
296 provided so that applications with restricted stacks can force a compilation
297 error if the stack runs out. The function should return zero if all is well, or
298 non-zero to force an error.
299 .
300 .
301 .\" HTML <a name="newlines"></a>
303 .rs
304 .sp
305 PCRE supports five different conventions for indicating line breaks in
306 strings: a single CR (carriage return) character, a single LF (linefeed)
307 character, the two-character sequence CRLF, any of the three preceding, or any
308 Unicode newline sequence. The Unicode newline sequences are the three just
309 mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed,
310 U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
311 (paragraph separator, U+2029).
312 .P
313 Each of the first three conventions is used by at least one operating system as
314 its standard newline sequence. When PCRE is built, a default can be specified.
315 The default default is LF, which is the Unix standard. When PCRE is run, the
316 default can be overridden, either when a pattern is compiled, or when it is
317 matched.
318 .P
319 At compile time, the newline convention can be specified by the \fIoptions\fP
320 argument of \fBpcre_compile()\fP, or it can be specified by special text at the
321 start of the pattern itself; this overrides any other settings. See the
322 .\" HREF
323 \fBpcrepattern\fP
324 .\"
325 page for details of the special character sequences.
326 .P
327 In the PCRE documentation the word "newline" is used to mean "the character or
328 pair of characters that indicate a line break". The choice of newline
329 convention affects the handling of the dot, circumflex, and dollar
330 metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
331 recognized line ending sequence, the match position advancement for a
332 non-anchored pattern. There is more detail about this in the
333 .\" HTML <a href="#execoptions">
334 .\" </a>
335 section on \fBpcre_exec()\fP options
336 .\"
337 below.
338 .P
339 The choice of newline convention does not affect the interpretation of
340 the \en or \er escape sequences, nor does it affect what \eR matches, which is
341 controlled in a similar way, but by separate options.
342 .
343 .
345 .rs
346 .sp
347 The PCRE functions can be used in multi-threading applications, with the
348 proviso that the memory management functions pointed to by \fBpcre_malloc\fP,
349 \fBpcre_free\fP, \fBpcre_stack_malloc\fP, and \fBpcre_stack_free\fP, and the
350 callout and stack-checking functions pointed to by \fBpcre_callout\fP and
351 \fBpcre_stack_guard\fP, are shared by all threads.
352 .P
353 The compiled form of a regular expression is not altered during matching, so
354 the same compiled pattern can safely be used by several threads at once.
355 .P
356 If the just-in-time optimization feature is being used, it needs separate
357 memory stack areas for each thread. See the
358 .\" HREF
359 \fBpcrejit\fP
360 .\"
361 documentation for more details.
362 .
363 .
365 .rs
366 .sp
367 The compiled form of a regular expression can be saved and re-used at a later
368 time, possibly by a different program, and even on a host other than the one on
369 which it was compiled. Details are given in the
370 .\" HREF
371 \fBpcreprecompile\fP
372 .\"
373 documentation, which includes a description of the
374 \fBpcre_pattern_to_host_byte_order()\fP function. However, compiling a regular
375 expression with one version of PCRE for use with a different version is not
376 guaranteed to work and may cause crashes.
377 .
378 .
380 .rs
381 .sp
382 .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
383 .PP
384 The function \fBpcre_config()\fP makes it possible for a PCRE client to
385 discover which optional features have been compiled into the PCRE library. The
386 .\" HREF
387 \fBpcrebuild\fP
388 .\"
389 documentation has more details about these optional features.
390 .P
391 The first argument for \fBpcre_config()\fP is an integer, specifying which
392 information is required; the second argument is a pointer to a variable into
393 which the information is placed. The returned value is zero on success, or the
394 negative error code PCRE_ERROR_BADOPTION if the value in the first argument is
395 not recognized. The following information is available:
396 .sp
398 .sp
399 The output is an integer that is set to one if UTF-8 support is available;
400 otherwise it is set to zero. This value should normally be given to the 8-bit
401 version of this function, \fBpcre_config()\fP. If it is given to the 16-bit
402 or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
403 .sp
405 .sp
406 The output is an integer that is set to one if UTF-16 support is available;
407 otherwise it is set to zero. This value should normally be given to the 16-bit
408 version of this function, \fBpcre16_config()\fP. If it is given to the 8-bit
409 or 32-bit version of this function, the result is PCRE_ERROR_BADOPTION.
410 .sp
412 .sp
413 The output is an integer that is set to one if UTF-32 support is available;
414 otherwise it is set to zero. This value should normally be given to the 32-bit
415 version of this function, \fBpcre32_config()\fP. If it is given to the 8-bit
416 or 16-bit version of this function, the result is PCRE_ERROR_BADOPTION.
417 .sp
419 .sp
420 The output is an integer that is set to one if support for Unicode character
421 properties is available; otherwise it is set to zero.
422 .sp
424 .sp
425 The output is an integer that is set to one if support for just-in-time
426 compiling is available; otherwise it is set to zero.
427 .sp
429 .sp
430 The output is a pointer to a zero-terminated "const char *" string. If JIT
431 support is available, the string contains the name of the architecture for
432 which the JIT compiler is configured, for example "x86 32bit (little endian +
433 unaligned)". If JIT support is not available, the result is NULL.
434 .sp
436 .sp
437 The output is an integer whose value specifies the default character sequence
438 that is recognized as meaning "newline". The values that are supported in
439 ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for
440 ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the
441 same values. However, the value for LF is normally 21, though some EBCDIC
442 environments use 37. The corresponding values for CRLF are 3349 and 3365. The
443 default should normally correspond to the standard sequence for your operating
444 system.
445 .sp
447 .sp
448 The output is an integer whose value indicates what character sequences the \eR
449 escape sequence matches by default. A value of 0 means that \eR matches any
450 Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
451 or CRLF. The default can be overridden when a pattern is compiled or matched.
452 .sp
454 .sp
455 The output is an integer that contains the number of bytes used for internal
456 linkage in compiled regular expressions. For the 8-bit library, the value can
457 be 2, 3, or 4. For the 16-bit library, the value is either 2 or 4 and is still
458 a number of bytes. For the 32-bit library, the value is either 2 or 4 and is
459 still a number of bytes. The default value of 2 is sufficient for all but the
460 most massive patterns, since it allows the compiled pattern to be up to 64K in
461 size. Larger values allow larger regular expressions to be compiled, at the
462 expense of slower matching.
463 .sp
465 .sp
466 The output is an integer that contains the threshold above which the POSIX
467 interface uses \fBmalloc()\fP for output vectors. Further details are given in
468 the
469 .\" HREF
470 \fBpcreposix\fP
471 .\"
472 documentation.
473 .sp
475 .sp
476 The output is a long integer that gives the maximum depth of nesting of
477 parentheses (of any kind) in a pattern. This limit is imposed to cap the amount
478 of system stack used when a pattern is compiled. It is specified when PCRE is
479 built; the default is 250. This limit does not take into account the stack that
480 may already be used by the calling application. For finer control over
481 compilation stack usage, you can set a pointer to an external checking function
482 in \fBpcre_stack_guard\fP.
483 .sp
485 .sp
486 The output is a long integer that gives the default limit for the number of
487 internal matching function calls in a \fBpcre_exec()\fP execution. Further
488 details are given with \fBpcre_exec()\fP below.
489 .sp
491 .sp
492 The output is a long integer that gives the default limit for the depth of
493 recursion when calling the internal matching function in a \fBpcre_exec()\fP
494 execution. Further details are given with \fBpcre_exec()\fP below.
495 .sp
497 .sp
498 The output is an integer that is set to one if internal recursion when running
499 \fBpcre_exec()\fP is implemented by recursive function calls that use the stack
500 to remember their state. This is the usual way that PCRE is compiled. The
501 output is zero if PCRE was compiled to use blocks of data on the heap instead
502 of recursive function calls. In this case, \fBpcre_stack_malloc\fP and
503 \fBpcre_stack_free\fP are called to manage memory blocks on the heap, thus
504 avoiding the use of the stack.
505 .
506 .
508 .rs
509 .sp
510 .nf
511 .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
512 .B " const char **\fIerrptr\fP, int *\fIerroffset\fP,"
513 .B " const unsigned char *\fItableptr\fP);"
514 .sp
515 .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
516 .B " int *\fIerrorcodeptr\fP,"
517 .B " const char **\fIerrptr\fP, int *\fIerroffset\fP,"
518 .B " const unsigned char *\fItableptr\fP);"
519 .fi
520 .P
521 Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be
522 called to compile a pattern into an internal form. The only difference between
523 the two interfaces is that \fBpcre_compile2()\fP has an additional argument,
524 \fIerrorcodeptr\fP, via which a numerical error code can be returned. To avoid
525 too much repetition, we refer just to \fBpcre_compile()\fP below, but the
526 information applies equally to \fBpcre_compile2()\fP.
527 .P
528 The pattern is a C string terminated by a binary zero, and is passed in the
529 \fIpattern\fP argument. A pointer to a single block of memory that is obtained
530 via \fBpcre_malloc\fP is returned. This contains the compiled code and related
531 data. The \fBpcre\fP type is defined for the returned block; this is a typedef
532 for a structure whose contents are not externally defined. It is up to the
533 caller to free the memory (via \fBpcre_free\fP) when it is no longer required.
534 .P
535 Although the compiled code of a PCRE regex is relocatable, that is, it does not
536 depend on memory location, the complete \fBpcre\fP data block is not
537 fully relocatable, because it may contain a copy of the \fItableptr\fP
538 argument, which is an address (see below).
539 .P
540 The \fIoptions\fP argument contains various bit settings that affect the
541 compilation. It should be zero if no options are required. The available
542 options are described below. Some of them (in particular, those that are
543 compatible with Perl, but some others as well) can also be set and unset from
544 within the pattern (see the detailed description in the
545 .\" HREF
546 \fBpcrepattern\fP
547 .\"
548 documentation). For those options that can be different in different parts of
549 the pattern, the contents of the \fIoptions\fP argument specifies their
550 settings at the start of compilation and execution. The PCRE_ANCHORED,
552 PCRE_NO_START_OPTIMIZE options can be set at the time of matching as well as at
553 compile time.
554 .P
555 If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
556 Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
557 NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual
558 error message. This is a static string that is part of the library. You must
559 not try to free it. Normally, the offset from the start of the pattern to the
560 data unit that was being processed when the error was discovered is placed in
561 the variable pointed to by \fIerroffset\fP, which must not be NULL (if it is,
562 an immediate error is given). However, for an invalid UTF-8 or UTF-16 string,
563 the offset is that of the first data unit of the failing character.
564 .P
565 Some errors are not detected until the whole pattern has been scanned; in these
566 cases, the offset passed back is the length of the pattern. Note that the
567 offset is in data units, not characters, even in a UTF mode. It may sometimes
568 point into the middle of a UTF-8 or UTF-16 character.
569 .P
570 If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the
571 \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is
572 returned via this argument in the event of an error. This is in addition to the
573 textual error message. Error codes and messages are listed below.
574 .P
575 If the final argument, \fItableptr\fP, is NULL, PCRE uses a default set of
576 character tables that are built when PCRE is compiled, using the default C
577 locale. Otherwise, \fItableptr\fP must be an address that is the result of a
578 call to \fBpcre_maketables()\fP. This value is stored with the compiled
579 pattern, and used again by \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP when the
580 pattern is matched. For more discussion, see the section on locale support
581 below.
582 .P
583 This code fragment shows a typical straightforward call to \fBpcre_compile()\fP:
584 .sp
585 pcre *re;
586 const char *error;
587 int erroffset;
588 re = pcre_compile(
589 "^A.*Z", /* the pattern */
590 0, /* default options */
591 &error, /* for error message */
592 &erroffset, /* for error offset */
593 NULL); /* use default character tables */
594 .sp
595 The following names for option bits are defined in the \fBpcre.h\fP header
596 file:
597 .sp
599 .sp
600 If this bit is set, the pattern is forced to be "anchored", that is, it is
601 constrained to match only at the first matching point in the string that is
602 being searched (the "subject string"). This effect can also be achieved by
603 appropriate constructs in the pattern itself, which is the only way to do it in
604 Perl.
605 .sp
607 .sp
608 If this bit is set, \fBpcre_compile()\fP automatically inserts callout items,
609 all with number 255, before each pattern item. For discussion of the callout
610 facility, see the
611 .\" HREF
612 \fBpcrecallout\fP
613 .\"
614 documentation.
615 .sp
618 .sp
619 These options (which are mutually exclusive) control what the \eR escape
620 sequence matches. The choice is either to match only CR, LF, or CRLF, or to
621 match any Unicode newline sequence. The default is specified when PCRE is
622 built. It can be overridden from within the pattern, or by setting an option
623 when a compiled pattern is matched.
624 .sp
626 .sp
627 If this bit is set, letters in the pattern match both upper and lower case
628 letters. It is equivalent to Perl's /i option, and it can be changed within a
629 pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the
630 concept of case for characters whose values are less than 128, so caseless
631 matching is always possible. For characters with higher values, the concept of
632 case is supported if PCRE is compiled with Unicode property support, but not
633 otherwise. If you want to use caseless matching for characters 128 and above,
634 you must ensure that PCRE is compiled with Unicode property support as well as
635 with UTF-8 support.
636 .sp
638 .sp
639 If this bit is set, a dollar metacharacter in the pattern matches only at the
640 end of the subject string. Without this option, a dollar also matches
641 immediately before a newline at the end of the string (but not before any other
642 newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set.
643 There is no equivalent to this option in Perl, and no way to set it within a
644 pattern.
645 .sp
647 .sp
648 If this bit is set, a dot metacharacter in the pattern matches a character of
649 any value, including one that indicates a newline. However, it only ever
650 matches one character, even if newlines are coded as CRLF. Without this option,
651 a dot does not match when the current position is at a newline. This option is
652 equivalent to Perl's /s option, and it can be changed within a pattern by a
653 (?s) option setting. A negative class such as [^a] always matches newline
654 characters, independent of the setting of this option.
655 .sp
657 .sp
658 If this bit is set, names used to identify capturing subpatterns need not be
659 unique. This can be helpful for certain types of pattern when it is known that
660 only one instance of the named subpattern can ever be matched. There are more
661 details of named subpatterns below; see also the
662 .\" HREF
663 \fBpcrepattern\fP
664 .\"
665 documentation.
666 .sp
668 .sp
669 If this bit is set, most white space characters in the pattern are totally
670 ignored except when escaped or inside a character class. However, white space
671 is not allowed within sequences such as (?> that introduce various
672 parenthesized subpatterns, nor within a numerical quantifier such as {1,3}.
673 However, ignorable white space is permitted between an item and a following
674 quantifier and between a quantifier and a following + that indicates
675 possessiveness.
676 .P
677 White space did not used to include the VT character (code 11), because Perl
678 did not treat this character as white space. However, Perl changed at release
679 5.18, so PCRE followed at release 8.34, and VT is now treated as white space.
680 .P
681 PCRE_EXTENDED also causes characters between an unescaped # outside a character
682 class and the next newline, inclusive, to be ignored. PCRE_EXTENDED is
683 equivalent to Perl's /x option, and it can be changed within a pattern by a
684 (?x) option setting.
685 .P
686 Which characters are interpreted as newlines is controlled by the options
687 passed to \fBpcre_compile()\fP or by a special sequence at the start of the
688 pattern, as described in the section entitled
689 .\" HTML <a href="pcrepattern.html#newlines">
690 .\" </a>
691 "Newline conventions"
692 .\"
693 in the \fBpcrepattern\fP documentation. Note that the end of this type of
694 comment is a literal newline sequence in the pattern; escape sequences that
695 happen to represent a newline do not count.
696 .P
697 This option makes it possible to include comments inside complicated patterns.
698 Note, however, that this applies only to data characters. White space characters
699 may never appear within special character sequences in a pattern, for example
700 within the sequence (?( that introduces a conditional subpattern.
701 .sp
703 .sp
704 This option was invented in order to turn on additional functionality of PCRE
705 that is incompatible with Perl, but it is currently of very little use. When
706 set, any backslash in a pattern that is followed by a letter that has no
707 special meaning causes an error, thus reserving these combinations for future
708 expansion. By default, as in Perl, a backslash followed by a letter with no
709 special meaning is treated as a literal. (Perl can, however, be persuaded to
710 give an error for this, by running it with the -w option.) There are at present
711 no other features controlled by this option. It can also be set by a (?X)
712 option setting within a pattern.
713 .sp
715 .sp
716 If this option is set, an unanchored pattern is required to match before or at
717 the first newline in the subject string, though the matched text may continue
718 over the newline.
719 .sp
721 .sp
722 If this option is set, PCRE's behaviour is changed in some ways so that it is
723 compatible with JavaScript rather than Perl. The changes are as follows:
724 .P
725 (1) A lone closing square bracket in a pattern causes a compile-time error,
726 because this is illegal in JavaScript (by default it is treated as a data
727 character). Thus, the pattern AB]CD becomes illegal when this option is set.
728 .P
729 (2) At run time, a back reference to an unset subpattern group matches an empty
730 string (by default this causes the current matching alternative to fail). A
731 pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
732 an "a" in the subject), whereas it fails by default, for Perl compatibility.
733 .P
734 (3) \eU matches an upper case "U" character; by default \eU causes a compile
735 time error (Perl uses \eU to upper case subsequent characters).
736 .P
737 (4) \eu matches a lower case "u" character unless it is followed by four
738 hexadecimal digits, in which case the hexadecimal number defines the code point
739 to match. By default, \eu causes a compile time error (Perl uses it to upper
740 case the following character).
741 .P
742 (5) \ex matches a lower case "x" character unless it is followed by two
743 hexadecimal digits, in which case the hexadecimal number defines the code point
744 to match. By default, as in Perl, a hexadecimal number is always expected after
745 \ex, but it may have zero, one, or two digits (so, for example, \exz matches a
746 binary zero character followed by z).
747 .sp
749 .sp
750 By default, for the purposes of matching "start of line" and "end of line",
751 PCRE treats the subject string as consisting of a single line of characters,
752 even if it actually contains newlines. The "start of line" metacharacter (^)
753 matches only at the start of the string, and the "end of line" metacharacter
754 ($) matches only at the end of the string, or before a terminating newline
755 (except when PCRE_DOLLAR_ENDONLY is set). Note, however, that unless
756 PCRE_DOTALL is set, the "any character" metacharacter (.) does not match at a
757 newline. This behaviour (for ^, $, and dot) is the same as Perl.
758 .P
759 When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
760 match immediately following or immediately before internal newlines in the
761 subject string, respectively, as well as at the very start and end. This is
762 equivalent to Perl's /m option, and it can be changed within a pattern by a
763 (?m) option setting. If there are no newlines in a subject string, or no
764 occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
765 .sp
767 .sp
768 This option locks out interpretation of the pattern as UTF-8 (or UTF-16 or
769 UTF-32 in the 16-bit and 32-bit libraries). In particular, it prevents the
770 creator of the pattern from switching to UTF interpretation by starting the
771 pattern with (*UTF). This may be useful in applications that process patterns
772 from external sources. The combination of PCRE_UTF8 and PCRE_NEVER_UTF also
773 causes an error.
774 .sp
780 .sp
781 These options override the default newline definition that was chosen when PCRE
782 was built. Setting the first or the second specifies that a newline is
783 indicated by a single character (CR or LF, respectively). Setting
784 PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
785 CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
786 preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
787 that any Unicode newline sequence should be recognized.
788 .P
789 In an ASCII/Unicode environment, the Unicode newline sequences are the three
790 just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form
791 feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
792 (paragraph separator, U+2029). For the 8-bit library, the last two are
793 recognized only in UTF-8 mode.
794 .P
795 When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for
796 CR is 0x0d, the same as ASCII. However, the character code for LF is normally
797 0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is
798 not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all
799 less than 256. For more details, see the
800 .\" HREF
801 \fBpcrebuild\fP
802 .\"
803 documentation.
804 .P
805 The newline setting in the options word uses three bits that are treated
806 as a number, giving eight possibilities. Currently only six are used (default
807 plus the five values above). This means that if you set more than one newline
808 option, the combination may or may not be sensible. For example,
810 other combinations may yield unused numbers and cause an error.
811 .P
812 The only time that a line break in a pattern is specially recognized when
813 compiling is when PCRE_EXTENDED is set. CR and LF are white space characters,
814 and so are ignored in this mode. Also, an unescaped # outside a character class
815 indicates a comment that lasts until after the next line break sequence. In
816 other circumstances, line break sequences in patterns are treated as literal
817 data.
818 .P
819 The newline option that is set at compile time becomes the default that is used
820 for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
821 .sp
823 .sp
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 .sp
831 .sp
832 If this option is set, it disables "auto-possessification". This is an
833 optimization that, for example, turns a+b into a++b in order to avoid
834 backtracks into a+ that can never be successful. However, if callouts are in
835 use, auto-possessification means that some of them are never taken. You can set
836 this option if you want the matching functions to do a full unoptimized search
837 and run all the callouts, but it is mainly provided for testing purposes.
838 .sp
840 .sp
841 This is an option that acts at matching time; that is, it is really an option
842 for \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. If it is set at compile time,
843 it is remembered with the compiled pattern and assumed at matching time. This
844 is necessary if you want to use JIT execution, because the JIT compiler needs
845 to know whether or not this option is set. For details see the discussion of
847 .\" HTML <a href="#execoptions">
848 .\" </a>
849 below.
850 .\"
851 .sp
853 .sp
854 This option changes the way PCRE processes \eB, \eb, \eD, \ed, \eS, \es, \eW,
855 \ew, and some of the POSIX character classes. By default, only ASCII characters
856 are recognized, but if PCRE_UCP is set, Unicode properties are used instead to
857 classify characters. More details are given in the section on
858 .\" HTML <a href="pcre.html#genericchartypes">
859 .\" </a>
860 generic character types
861 .\"
862 in the
863 .\" HREF
864 \fBpcrepattern\fP
865 .\"
866 page. If you set PCRE_UCP, matching one of the items it affects takes much
867 longer. The option is available only if PCRE has been compiled with Unicode
868 property support.
869 .sp
871 .sp
872 This option inverts the "greediness" of the quantifiers so that they are not
873 greedy by default, but become greedy if followed by "?". It is not compatible
874 with Perl. It can also be set by a (?U) option setting within the pattern.
875 .sp
877 .sp
878 This option causes PCRE to regard both the pattern and the subject as strings
879 of UTF-8 characters instead of single-byte strings. However, it is available
880 only when PCRE is built to include UTF support. If not, the use of this option
881 provokes an error. Details of how this option changes the behaviour of PCRE are
882 given in the
883 .\" HREF
884 \fBpcreunicode\fP
885 .\"
886 page.
887 .sp
889 .sp
890 When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
891 automatically checked. There is a discussion about the
892 .\" HTML <a href="pcreunicode.html#utf8strings">
893 .\" </a>
894 validity of UTF-8 strings
895 .\"
896 in the
897 .\" HREF
898 \fBpcreunicode\fP
899 .\"
900 page. If an invalid UTF-8 sequence is found, \fBpcre_compile()\fP returns an
901 error. If you already know that your pattern is valid, and you want to skip
902 this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option.
903 When it is set, the effect of passing an invalid UTF-8 string as a pattern is
904 undefined. It may cause your program to crash or loop. Note that this option
905 can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
906 the validity checking of subject strings only. If the same string is being
907 matched many times, the option can be safely set for the second and subsequent
908 matchings to improve performance.
909 .
910 .
912 .rs
913 .sp
914 The following table lists the error codes than may be returned by
915 \fBpcre_compile2()\fP, along with the error messages that may be returned by
916 both compiling functions. Note that error messages are always 8-bit ASCII
917 strings, even in 16-bit or 32-bit mode. As PCRE has developed, some error codes
918 have fallen out of use. To avoid confusion, they have not been re-used.
919 .sp
920 0 no error
921 1 \e at end of pattern
922 2 \ec at end of pattern
923 3 unrecognized character follows \e
924 4 numbers out of order in {} quantifier
925 5 number too big in {} quantifier
926 6 missing terminating ] for character class
927 7 invalid escape sequence in character class
928 8 range out of order in character class
929 9 nothing to repeat
930 10 [this code is not in use]
931 11 internal error: unexpected repeat
932 12 unrecognized character after (? or (?-
933 13 POSIX named classes are supported only within a class
934 14 missing )
935 15 reference to non-existent subpattern
936 16 erroffset passed as NULL
937 17 unknown option bit(s) set
938 18 missing ) after comment
939 19 [this code is not in use]
940 20 regular expression is too large
941 21 failed to get memory
942 22 unmatched parentheses
943 23 internal error: code overflow
944 24 unrecognized character after (?<
945 25 lookbehind assertion is not fixed length
946 26 malformed number or name after (?(
947 27 conditional group contains more than two branches
948 28 assertion expected after (?(
949 29 (?R or (?[+-]digits must be followed by )
950 30 unknown POSIX class name
951 31 POSIX collating elements are not supported
952 32 this version of PCRE is compiled without UTF support
953 33 [this code is not in use]
954 34 character value in \ex{} or \eo{} is too large
955 35 invalid condition (?(0)
956 36 \eC not allowed in lookbehind assertion
957 37 PCRE does not support \eL, \el, \eN{name}, \eU, or \eu
958 38 number after (?C is > 255
959 39 closing ) for (?C expected
960 40 recursive call could loop indefinitely
961 41 unrecognized character after (?P
962 42 syntax error in subpattern name (missing terminator)
963 43 two named subpatterns have the same name
964 44 invalid UTF-8 string (specifically UTF-8)
965 45 support for \eP, \ep, and \eX has not been compiled
966 46 malformed \eP or \ep sequence
967 47 unknown property name after \eP or \ep
968 48 subpattern name is too long (maximum 32 characters)
969 49 too many named subpatterns (maximum 10000)
970 50 [this code is not in use]
971 51 octal value is greater than \e377 in 8-bit non-UTF-8 mode
972 52 internal error: overran compiling workspace
973 53 internal error: previously-checked referenced subpattern
974 not found
975 54 DEFINE group contains more than one branch
976 55 repeating a DEFINE group is not allowed
977 56 inconsistent NEWLINE options
978 57 \eg is not followed by a braced, angle-bracketed, or quoted
979 name/number or by a plain number
980 58 a numbered reference must not be zero
981 59 an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
982 60 (*VERB) not recognized or malformed
983 61 number is too big
984 62 subpattern name expected
985 63 digit expected after (?+
986 64 ] is an invalid data character in JavaScript compatibility mode
987 65 different names for subpatterns of the same number are
988 not allowed
989 66 (*MARK) must have an argument
990 67 this version of PCRE is not compiled with Unicode property
991 support
992 68 \ec must be followed by an ASCII character
993 69 \ek is not followed by a braced, angle-bracketed, or quoted name
994 70 internal error: unknown opcode in find_fixedlength()
995 71 \eN is not supported in a class
996 72 too many forward references
997 73 disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
998 74 invalid UTF-16 string (specifically UTF-16)
999 75 name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
1000 76 character value in \eu.... sequence is too large
1001 77 invalid UTF-32 string (specifically UTF-32)
1002 78 setting UTF is disabled by the application
1003 79 non-hex character in \ex{} (closing brace missing?)
1004 80 non-octal character in \eo{} (closing brace missing?)
1005 81 missing opening brace after \eo
1006 82 parentheses are too deeply nested
1007 83 invalid range in character class
1008 84 group name must start with a non-digit
1009 85 parentheses are too deeply nested (stack check)
1010 .sp
1011 The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
1012 be used if the limits were changed when PCRE was built.
1013 .
1014 .
1015 .\" HTML <a name="studyingapattern"></a>
1017 .rs
1018 .sp
1019 .nf
1020 .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,
1021 .B " const char **\fIerrptr\fP);"
1022 .fi
1023 .PP
1024 If a compiled pattern is going to be used several times, it is worth spending
1025 more time analyzing it in order to speed up the time taken for matching. The
1026 function \fBpcre_study()\fP takes a pointer to a compiled pattern as its first
1027 argument. If studying the pattern produces additional information that will
1028 help speed up matching, \fBpcre_study()\fP returns a pointer to a
1029 \fBpcre_extra\fP block, in which the \fIstudy_data\fP field points to the
1030 results of the study.
1031 .P
1032 The returned value from \fBpcre_study()\fP can be passed directly to
1033 \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. However, a \fBpcre_extra\fP block
1034 also contains other fields that can be set by the caller before the block is
1035 passed; these are described
1036 .\" HTML <a href="#extradata">
1037 .\" </a>
1038 below
1039 .\"
1040 in the section on matching a pattern.
1041 .P
1042 If studying the pattern does not produce any useful information,
1043 \fBpcre_study()\fP returns NULL by default. In that circumstance, if the
1044 calling program wants to pass any of the other fields to \fBpcre_exec()\fP or
1045 \fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block. However,
1046 if \fBpcre_study()\fP is called with the PCRE_STUDY_EXTRA_NEEDED option, it
1047 returns a \fBpcre_extra\fP block even if studying did not find any additional
1048 information. It may still return NULL, however, if an error occurs in
1049 \fBpcre_study()\fP.
1050 .P
1051 The second argument of \fBpcre_study()\fP contains option bits. There are three
1052 further options in addition to PCRE_STUDY_EXTRA_NEEDED:
1053 .sp
1057 .sp
1058 If any of these are set, and the just-in-time compiler is available, the
1059 pattern is further compiled into machine code that executes much faster than
1060 the \fBpcre_exec()\fP interpretive matching function. If the just-in-time
1061 compiler is not available, these options are ignored. All undefined bits in the
1062 \fIoptions\fP argument must be zero.
1063 .P
1064 JIT compilation is a heavyweight optimization. It can take some time for
1065 patterns to be analyzed, and for one-off matches and simple patterns the
1066 benefit of faster execution might be offset by a much slower study time.
1067 Not all patterns can be optimized by the JIT compiler. For those that cannot be
1068 handled, matching automatically falls back to the \fBpcre_exec()\fP
1069 interpreter. For more details, see the
1070 .\" HREF
1071 \fBpcrejit\fP
1072 .\"
1073 documentation.
1074 .P
1075 The third argument for \fBpcre_study()\fP is a pointer for an error message. If
1076 studying succeeds (even if no data is returned), the variable it points to is
1077 set to NULL. Otherwise it is set to point to a textual error message. This is a
1078 static string that is part of the library. You must not try to free it. You
1079 should test the error pointer for NULL after calling \fBpcre_study()\fP, to be
1080 sure that it has run successfully.
1081 .P
1082 When you are finished with a pattern, you can free the memory used for the
1083 study data by calling \fBpcre_free_study()\fP. This function was added to the
1084 API for release 8.20. For earlier versions, the memory could be freed with
1085 \fBpcre_free()\fP, just like the pattern itself. This will still work in cases
1086 where JIT optimization is not used, but it is advisable to change to the new
1087 function when convenient.
1088 .P
1089 This is a typical way in which \fBpcre_study\fP() is used (except that in a
1090 real application there should be tests for errors):
1091 .sp
1092 int rc;
1093 pcre *re;
1094 pcre_extra *sd;
1095 re = pcre_compile("pattern", 0, &error, &erroroffset, NULL);
1096 sd = pcre_study(
1097 re, /* result of pcre_compile() */
1098 0, /* no options */
1099 &error); /* set to NULL or points to a message */
1100 rc = pcre_exec( /* see below for details of pcre_exec() options */
1101 re, sd, "subject", 7, 0, 0, ovector, 30);
1102 ...
1103 pcre_free_study(sd);
1104 pcre_free(re);
1105 .sp
1106 Studying a pattern does two things: first, a lower bound for the length of
1107 subject string that is needed to match the pattern is computed. This does not
1108 mean that there are any strings of that length that match, but it does
1109 guarantee that no shorter strings match. The value is used to avoid wasting
1110 time by trying to match strings that are shorter than the lower bound. You can
1111 find out the value in a calling program via the \fBpcre_fullinfo()\fP function.
1112 .P
1113 Studying a pattern is also useful for non-anchored patterns that do not have a
1114 single fixed starting character. A bitmap of possible starting bytes is
1115 created. This speeds up finding a position in the subject at which to start
1116 matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.
1117 In 32-bit mode, the bitmap is used for 32-bit values less than 256.)
1118 .P
1119 These two optimizations apply to both \fBpcre_exec()\fP and
1120 \fBpcre_dfa_exec()\fP, and the information is also used by the JIT compiler.
1121 The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option.
1122 You might want to do this if your pattern contains callouts or (*MARK) and you
1123 want to make use of these facilities in cases where matching fails.
1124 .P
1125 PCRE_NO_START_OPTIMIZE can be specified at either compile time or execution
1126 time. However, if PCRE_NO_START_OPTIMIZE is passed to \fBpcre_exec()\fP, (that
1127 is, after any JIT compilation has happened) JIT execution is disabled. For JIT
1128 execution to work with PCRE_NO_START_OPTIMIZE, the option must be set at
1129 compile time.
1130 .P
1131 There is a longer discussion of PCRE_NO_START_OPTIMIZE
1132 .\" HTML <a href="#execoptions">
1133 .\" </a>
1134 below.
1135 .\"
1136 .
1137 .
1138 .\" HTML <a name="localesupport"></a>
1140 .rs
1141 .sp
1142 PCRE handles caseless matching, and determines whether characters are letters,
1143 digits, or whatever, by reference to a set of tables, indexed by character
1144 code point. When running in UTF-8 mode, or in the 16- or 32-bit libraries, this
1145 applies only to characters with code points less than 256. By default,
1146 higher-valued code points never match escapes such as \ew or \ed. However, if
1147 PCRE is built with Unicode property support, all characters can be tested with
1148 \ep and \eP, or, alternatively, the PCRE_UCP option can be set when a pattern
1149 is compiled; this causes \ew and friends to use Unicode property support
1150 instead of the built-in tables.
1151 .P
1152 The use of locales with Unicode is discouraged. If you are handling characters
1153 with code points greater than 128, you should either use Unicode support, or
1154 use locales, but not try to mix the two.
1155 .P
1156 PCRE contains an internal set of tables that are used when the final argument
1157 of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
1158 Normally, the internal tables recognize only ASCII characters. However, when
1159 PCRE is built, it is possible to cause the internal tables to be rebuilt in the
1160 default "C" locale of the local system, which may cause them to be different.
1161 .P
1162 The internal tables can always be overridden by tables supplied by the
1163 application that calls PCRE. These may be created in a different locale from
1164 the default. As more and more applications change to using Unicode, the need
1165 for this locale support is expected to die away.
1166 .P
1167 External tables are built by calling the \fBpcre_maketables()\fP function,
1168 which has no arguments, in the relevant locale. The result can then be passed
1169 to \fBpcre_compile()\fP as often as necessary. For example, to build and use
1170 tables that are appropriate for the French locale (where accented characters
1171 with values greater than 128 are treated as letters), the following code could
1172 be used:
1173 .sp
1174 setlocale(LC_CTYPE, "fr_FR");
1175 tables = pcre_maketables();
1176 re = pcre_compile(..., tables);
1177 .sp
1178 The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
1179 are using Windows, the name for the French locale is "french".
1180 .P
1181 When \fBpcre_maketables()\fP runs, the tables are built in memory that is
1182 obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure
1183 that the memory containing the tables remains available for as long as it is
1184 needed.
1185 .P
1186 The pointer that is passed to \fBpcre_compile()\fP is saved with the compiled
1187 pattern, and the same tables are used via this pointer by \fBpcre_study()\fP
1188 and also by \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP. Thus, for any single
1189 pattern, compilation, studying and matching all happen in the same locale, but
1190 different patterns can be processed in different locales.
1191 .P
1192 It is possible to pass a table pointer or NULL (indicating the use of the
1193 internal tables) to \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP (see the
1194 discussion below in the section on matching a pattern). This facility is
1195 provided for use with pre-compiled patterns that have been saved and reloaded.
1196 Character tables are not saved with patterns, so if a non-standard table was
1197 used at compile time, it must be provided again when the reloaded pattern is
1198 matched. Attempting to use this facility to match a pattern in a different
1199 locale from the one in which it was compiled is likely to lead to anomalous
1200 (usually incorrect) results.
1201 .
1202 .
1203 .\" HTML <a name="infoaboutpattern"></a>
1205 .rs
1206 .sp
1207 .nf
1208 .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
1209 .B " int \fIwhat\fP, void *\fIwhere\fP);"
1210 .fi
1211 .PP
1212 The \fBpcre_fullinfo()\fP function returns information about a compiled
1213 pattern. It replaces the \fBpcre_info()\fP function, which was removed from the
1214 library at version 8.30, after more than 10 years of obsolescence.
1215 .P
1216 The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled
1217 pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if
1218 the pattern was not studied. The third argument specifies which piece of
1219 information is required, and the fourth argument is a pointer to a variable
1220 to receive the data. The yield of the function is zero for success, or one of
1221 the following negative numbers:
1222 .sp
1223 PCRE_ERROR_NULL the argument \fIcode\fP was NULL
1224 the argument \fIwhere\fP was NULL
1225 PCRE_ERROR_BADMAGIC the "magic number" was not found
1226 PCRE_ERROR_BADENDIANNESS the pattern was compiled with different
1227 endianness
1228 PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid
1229 PCRE_ERROR_UNSET the requested field is not set
1230 .sp
1231 The "magic number" is placed at the start of each compiled pattern as an simple
1232 check against passing an arbitrary memory pointer. The endianness error can
1233 occur if a compiled pattern is saved and reloaded on a different host. Here is
1234 a typical call of \fBpcre_fullinfo()\fP, to obtain the length of the compiled
1235 pattern:
1236 .sp
1237 int rc;
1238 size_t length;
1239 rc = pcre_fullinfo(
1240 re, /* result of pcre_compile() */
1241 sd, /* result of pcre_study(), or NULL */
1242 PCRE_INFO_SIZE, /* what is required */
1243 &length); /* where to put the data */
1244 .sp
1245 The possible values for the third argument are defined in \fBpcre.h\fP, and are
1246 as follows:
1247 .sp
1249 .sp
1250 Return the number of the highest back reference in the pattern. The fourth
1251 argument should point to an \fBint\fP variable. Zero is returned if there are
1252 no back references.
1253 .sp
1255 .sp
1256 Return the number of capturing subpatterns in the pattern. The fourth argument
1257 should point to an \fBint\fP variable.
1258 .sp
1260 .sp
1261 Return a pointer to the internal default character tables within PCRE. The
1262 fourth argument should point to an \fBunsigned char *\fP variable. This
1263 information call is provided for internal use by the \fBpcre_study()\fP
1264 function. External callers can cause PCRE to use its internal tables by passing
1265 a NULL table pointer.
1266 .sp
1267 PCRE_INFO_FIRSTBYTE (deprecated)
1268 .sp
1269 Return information about the first data unit of any matched string, for a
1270 non-anchored pattern. The name of this option refers to the 8-bit library,
1271 where data units are bytes. The fourth argument should point to an \fBint\fP
1272 variable. Negative values are used for special cases. However, this means that
1273 when the 32-bit library is in non-UTF-32 mode, the full 32-bit range of
1274 characters cannot be returned. For this reason, this value is deprecated; use
1276 .P
1277 If there is a fixed first value, for example, the letter "c" from a pattern
1278 such as (cat|cow|coyote), its value is returned. In the 8-bit library, the
1279 value is always less than 256. In the 16-bit library the value can be up to
1280 0xffff. In the 32-bit library the value can be up to 0x10ffff.
1281 .P
1282 If there is no fixed first value, and if either
1283 .sp
1284 (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
1285 starts with "^", or
1286 .sp
1287 (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
1288 (if it were set, the pattern would be anchored),
1289 .sp
1290 -1 is returned, indicating that the pattern matches only at the start of a
1291 subject string or after any newline within the string. Otherwise -2 is
1292 returned. For anchored patterns, -2 is returned.
1293 .sp
1295 .sp
1296 Return the value of the first data unit (non-UTF character) of any matched
1297 string in the situation where PCRE_INFO_FIRSTCHARACTERFLAGS returns 1;
1298 otherwise return 0. The fourth argument should point to an \fBuint_t\fP
1299 variable.
1300 .P
1301 In the 8-bit library, the value is always less than 256. In the 16-bit library
1302 the value can be up to 0xffff. In the 32-bit library in UTF-32 mode the value
1303 can be up to 0x10ffff, and up to 0xffffffff when not using UTF-32 mode.
1304 .sp
1306 .sp
1307 Return information about the first data unit of any matched string, for a
1308 non-anchored pattern. The fourth argument should point to an \fBint\fP
1309 variable.
1310 .P
1311 If there is a fixed first value, for example, the letter "c" from a pattern
1312 such as (cat|cow|coyote), 1 is returned, and the character value can be
1313 retrieved using PCRE_INFO_FIRSTCHARACTER. If there is no fixed first value, and
1314 if either
1315 .sp
1316 (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
1317 starts with "^", or
1318 .sp
1319 (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
1320 (if it were set, the pattern would be anchored),
1321 .sp
1322 2 is returned, indicating that the pattern matches only at the start of a
1323 subject string or after any newline within the string. Otherwise 0 is
1324 returned. For anchored patterns, 0 is returned.
1325 .sp
1327 .sp
1328 If the pattern was studied, and this resulted in the construction of a 256-bit
1329 table indicating a fixed set of values for the first data unit in any matching
1330 string, a pointer to the table is returned. Otherwise NULL is returned. The
1331 fourth argument should point to an \fBunsigned char *\fP variable.
1332 .sp
1334 .sp
1335 Return 1 if the pattern contains any explicit matches for CR or LF characters,
1336 otherwise 0. The fourth argument should point to an \fBint\fP variable. An
1337 explicit match is either a literal CR or LF character, or \er or \en.
1338 .sp
1340 .sp
1341 Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
1342 0. The fourth argument should point to an \fBint\fP variable. (?J) and
1343 (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
1344 .sp
1346 .sp
1347 Return 1 if the pattern was studied with one of the JIT options, and
1348 just-in-time compiling was successful. The fourth argument should point to an
1349 \fBint\fP variable. A return value of 0 means that JIT support is not available
1350 in this version of PCRE, or that the pattern was not studied with a JIT option,
1351 or that the JIT compiler could not handle this particular pattern. See the
1352 .\" HREF
1353 \fBpcrejit\fP
1354 .\"
1355 documentation for details of what can and cannot be handled.
1356 .sp
1358 .sp
1359 If the pattern was successfully studied with a JIT option, return the size of
1360 the JIT compiled code, otherwise return zero. The fourth argument should point
1361 to a \fBsize_t\fP variable.
1362 .sp
1364 .sp
1365 Return the value of the rightmost literal data unit that must exist in any
1366 matched string, other than at its start, if such a value has been recorded. The
1367 fourth argument should point to an \fBint\fP variable. If there is no such
1368 value, -1 is returned. For anchored patterns, a last literal value is recorded
1369 only if it follows something of variable length. For example, for the pattern
1370 /^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value
1371 is -1.
1372 .P
1373 Since for the 32-bit library using the non-UTF-32 mode, this function is unable
1374 to return the full 32-bit range of characters, this value is deprecated;
1376 be used.
1377 .sp
1379 .sp
1380 Return 1 if the pattern can match an empty string, otherwise 0. The fourth
1381 argument should point to an \fBint\fP variable.
1382 .sp
1384 .sp
1385 If the pattern set a match limit by including an item of the form
1386 (*LIMIT_MATCH=nnnn) at the start, the value is returned. The fourth argument
1387 should point to an unsigned 32-bit integer. If no such value has been set, the
1388 call to \fBpcre_fullinfo()\fP returns the error PCRE_ERROR_UNSET.
1389 .sp
1391 .sp
1392 Return the number of characters (NB not data units) in the longest lookbehind
1393 assertion in the pattern. This information is useful when doing multi-segment
1394 matching using the partial matching facilities. Note that the simple assertions
1395 \eb and \eB require a one-character lookbehind. \eA also registers a
1396 one-character lookbehind, though it does not actually inspect the previous
1397 character. This is to ensure that at least one character from the old segment
1398 is retained when a new segment is processed. Otherwise, if there are no
1399 lookbehinds in the pattern, \eA might match incorrectly at the start of a new
1400 segment.
1401 .sp
1403 .sp
1404 If the pattern was studied and a minimum length for matching subject strings
1405 was computed, its value is returned. Otherwise the returned value is -1. The
1406 value is a number of characters, which in UTF mode may be different from the
1407 number of data units. The fourth argument should point to an \fBint\fP
1408 variable. A non-negative value is a lower bound to the length of any matching
1409 string. There may not be any strings of that length that do actually match, but
1410 every string that does match is at least that long.
1411 .sp
1415 .sp
1416 PCRE supports the use of named as well as numbered capturing parentheses. The
1417 names are just an additional way of identifying the parentheses, which still
1418 acquire numbers. Several convenience functions such as
1419 \fBpcre_get_named_substring()\fP are provided for extracting captured
1420 substrings by name. It is also possible to extract the data directly, by first
1421 converting the name to a number in order to access the correct pointers in the
1422 output vector (described with \fBpcre_exec()\fP below). To do the conversion,
1423 you need to use the name-to-number map, which is described by these three
1424 values.
1425 .P
1426 The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives
1427 the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
1428 entry; both of these return an \fBint\fP value. The entry size depends on the
1429 length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
1430 entry of the table. This is a pointer to \fBchar\fP in the 8-bit library, where
1431 the first two bytes of each entry are the number of the capturing parenthesis,
1432 most significant byte first. In the 16-bit library, the pointer points to
1433 16-bit data units, the first of which contains the parenthesis number. In the
1434 32-bit library, the pointer points to 32-bit data units, the first of which
1435 contains the parenthesis number. The rest of the entry is the corresponding
1436 name, zero terminated.
1437 .P
1438 The names are in alphabetical order. If (?| is used to create multiple groups
1439 with the same number, as described in the
1440 .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
1441 .\" </a>
1442 section on duplicate subpattern numbers
1443 .\"
1444 in the
1445 .\" HREF
1446 \fBpcrepattern\fP
1447 .\"
1448 page, the groups may be given the same name, but there is only one entry in the
1449 table. Different names for groups of the same number are not permitted.
1450 Duplicate names for subpatterns with different numbers are permitted,
1451 but only if PCRE_DUPNAMES is set. They appear in the table in the order in
1452 which they were found in the pattern. In the absence of (?| this is the order
1453 of increasing number; when (?| is used this is not necessarily the case because
1454 later subpatterns may have lower numbers.
1455 .P
1456 As a simple example of the name/number table, consider the following pattern
1457 after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white
1458 space - including newlines - is ignored):
1459 .sp
1460 .\" JOIN
1461 (?<date> (?<year>(\ed\ed)?\ed\ed) -
1462 (?<month>\ed\ed) - (?<day>\ed\ed) )
1463 .sp
1464 There are four named subpatterns, so the table has four entries, and each entry
1465 in the table is eight bytes long. The table is as follows, with non-printing
1466 bytes shows in hexadecimal, and undefined bytes shown as ??:
1467 .sp
1468 00 01 d a t e 00 ??
1469 00 05 d a y 00 ?? ??
1470 00 04 m o n t h 00
1471 00 02 y e a r 00 ??
1472 .sp
1473 When writing code to extract data from named subpatterns using the
1474 name-to-number map, remember that the length of the entries is likely to be
1475 different for each compiled pattern.
1476 .sp
1478 .sp
1479 Return 1 if the pattern can be used for partial matching with
1480 \fBpcre_exec()\fP, otherwise 0. The fourth argument should point to an
1481 \fBint\fP variable. From release 8.00, this always returns 1, because the
1482 restrictions that previously applied to partial matching have been lifted. The
1483 .\" HREF
1484 \fBpcrepartial\fP
1485 .\"
1486 documentation gives details of partial matching.
1487 .sp
1489 .sp
1490 Return a copy of the options with which the pattern was compiled. The fourth
1491 argument should point to an \fBunsigned long int\fP variable. These option bits
1492 are those specified in the call to \fBpcre_compile()\fP, modified by any
1493 top-level option settings at the start of the pattern itself. In other words,
1494 they are the options that will be in force when matching starts. For example,
1495 if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1497 .P
1498 A pattern is automatically anchored by PCRE if all of its top-level
1499 alternatives begin with one of the following:
1500 .sp
1501 ^ unless PCRE_MULTILINE is set
1502 \eA always
1503 \eG always
1504 .\" JOIN
1505 .* if PCRE_DOTALL is set and there are no back
1506 references to the subpattern in which .* appears
1507 .sp
1508 For such patterns, the PCRE_ANCHORED bit is set in the options returned by
1509 \fBpcre_fullinfo()\fP.
1510 .sp
1512 .sp
1513 If the pattern set a recursion limit by including an item of the form
1514 (*LIMIT_RECURSION=nnnn) at the start, the value is returned. The fourth
1515 argument should point to an unsigned 32-bit integer. If no such value has been
1516 set, the call to \fBpcre_fullinfo()\fP returns the error PCRE_ERROR_UNSET.
1517 .sp
1519 .sp
1520 Return the size of the compiled pattern in bytes (for all three libraries). The
1521 fourth argument should point to a \fBsize_t\fP variable. This value does not
1522 include the size of the \fBpcre\fP structure that is returned by
1523 \fBpcre_compile()\fP. The value that is passed as the argument to
1524 \fBpcre_malloc()\fP when \fBpcre_compile()\fP is getting memory in which to
1525 place the compiled data is the value returned by this option plus the size of
1526 the \fBpcre\fP structure. Studying a compiled pattern, with or without JIT,
1527 does not alter the value returned by this option.
1528 .sp
1530 .sp
1531 Return the size in bytes (for all three libraries) of the data block pointed to
1532 by the \fIstudy_data\fP field in a \fBpcre_extra\fP block. If \fBpcre_extra\fP
1533 is NULL, or there is no study data, zero is returned. The fourth argument
1534 should point to a \fBsize_t\fP variable. The \fIstudy_data\fP field is set by
1535 \fBpcre_study()\fP to record information that will speed up matching (see the
1536 section entitled
1537 .\" HTML <a href="#studyingapattern">
1538 .\" </a>
1539 "Studying a pattern"
1540 .\"
1541 above). The format of the \fIstudy_data\fP block is private, but its length
1542 is made available via this option so that it can be saved and restored (see the
1543 .\" HREF
1544 \fBpcreprecompile\fP
1545 .\"
1546 documentation for details).
1547 .sp
1549 .sp
1550 Returns 1 if there is a rightmost literal data unit that must exist in any
1551 matched string, other than at its start. The fourth argument should point to
1552 an \fBint\fP variable. If there is no such value, 0 is returned. If returning
1553 1, the character value itself can be retrieved using PCRE_INFO_REQUIREDCHAR.
1554 .P
1555 For anchored patterns, a last literal value is recorded only if it follows
1556 something of variable length. For example, for the pattern /^a\ed+z\ed+/ the
1557 returned value 1 (with "z" returned from PCRE_INFO_REQUIREDCHAR), but for
1558 /^a\edz\ed/ the returned value is 0.
1559 .sp
1561 .sp
1562 Return the value of the rightmost literal data unit that must exist in any
1563 matched string, other than at its start, if such a value has been recorded. The
1564 fourth argument should point to an \fBuint32_t\fP variable. If there is no such
1565 value, 0 is returned.
1566 .
1567 .
1569 .rs
1570 .sp
1571 .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
1572 .PP
1573 The \fBpcre_refcount()\fP function is used to maintain a reference count in the
1574 data block that contains a compiled pattern. It is provided for the benefit of
1575 applications that operate in an object-oriented manner, where different parts
1576 of the application may be using the same compiled pattern, but you want to free
1577 the block when they are all done.
1578 .P
1579 When a pattern is compiled, the reference count field is initialized to zero.
1580 It is changed only by calling this function, whose action is to add the
1581 \fIadjust\fP value (which may be positive or negative) to it. The yield of the
1582 function is the new value. However, the value of the count is constrained to
1583 lie between 0 and 65535, inclusive. If the new value is outside these limits,
1584 it is forced to the appropriate limit value.
1585 .P
1586 Except when it is zero, the reference count is not correctly preserved if a
1587 pattern is compiled on one host and then transferred to a host whose byte-order
1588 is different. (This seems a highly unlikely scenario.)
1589 .
1590 .
1592 .rs
1593 .sp
1594 .nf
1595 .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
1596 .B " const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
1597 .B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);"
1598 .fi
1599 .P
1600 The function \fBpcre_exec()\fP is called to match a subject string against a
1601 compiled pattern, which is passed in the \fIcode\fP argument. If the
1602 pattern was studied, the result of the study should be passed in the
1603 \fIextra\fP argument. You can call \fBpcre_exec()\fP with the same \fIcode\fP
1604 and \fIextra\fP arguments as many times as you like, in order to match
1605 different subject strings with the same pattern.
1606 .P
1607 This function is the main matching facility of the library, and it operates in
1608 a Perl-like manner. For specialist use there is also an alternative matching
1609 function, which is described
1610 .\" HTML <a href="#dfamatch">
1611 .\" </a>
1612 below
1613 .\"
1614 in the section about the \fBpcre_dfa_exec()\fP function.
1615 .P
1616 In most applications, the pattern will have been compiled (and optionally
1617 studied) in the same process that calls \fBpcre_exec()\fP. However, it is
1618 possible to save compiled patterns and study data, and then use them later
1619 in different processes, possibly even on different hosts. For a discussion
1620 about this, see the
1621 .\" HREF
1622 \fBpcreprecompile\fP
1623 .\"
1624 documentation.
1625 .P
1626 Here is an example of a simple call to \fBpcre_exec()\fP:
1627 .sp
1628 int rc;
1629 int ovector[30];
1630 rc = pcre_exec(
1631 re, /* result of pcre_compile() */
1632 NULL, /* we didn't study the pattern */
1633 "some string", /* the subject string */
1634 11, /* the length of the subject string */
1635 0, /* start at offset 0 in the subject */
1636 0, /* default options */
1637 ovector, /* vector of integers for substring information */
1638 30); /* number of elements (NOT size in bytes) */
1639 .
1640 .
1641 .\" HTML <a name="extradata"></a>
1642 .SS "Extra data for \fBpcre_exec()\fR"
1643 .rs
1644 .sp
1645 If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP
1646 data block. The \fBpcre_study()\fP function returns such a block (when it
1647 doesn't return NULL), but you can also create one for yourself, and pass
1648 additional information in it. The \fBpcre_extra\fP block contains the following
1649 fields (not necessarily in this order):
1650 .sp
1651 unsigned long int \fIflags\fP;
1652 void *\fIstudy_data\fP;
1653 void *\fIexecutable_jit\fP;
1654 unsigned long int \fImatch_limit\fP;
1655 unsigned long int \fImatch_limit_recursion\fP;
1656 void *\fIcallout_data\fP;
1657 const unsigned char *\fItables\fP;
1658 unsigned char **\fImark\fP;
1659 .sp
1660 In the 16-bit version of this structure, the \fImark\fP field has type
1661 "PCRE_UCHAR16 **".
1662 .sp
1663 In the 32-bit version of this structure, the \fImark\fP field has type
1664 "PCRE_UCHAR32 **".
1665 .P
1666 The \fIflags\fP field is used to specify which of the other fields are set. The
1667 flag bits are:
1668 .sp
1676 .sp
1677 Other flag bits should be set to zero. The \fIstudy_data\fP field and sometimes
1678 the \fIexecutable_jit\fP field are set in the \fBpcre_extra\fP block that is
1679 returned by \fBpcre_study()\fP, together with the appropriate flag bits. You
1680 should not set these yourself, but you may add to the block by setting other
1681 fields and their corresponding flag bits.
1682 .P
1683 The \fImatch_limit\fP field provides a means of preventing PCRE from using up a
1684 vast amount of resources when running patterns that are not going to match,
1685 but which have a very large number of possibilities in their search trees. The
1686 classic example is a pattern that uses nested unlimited repeats.
1687 .P
1688 Internally, \fBpcre_exec()\fP uses a function called \fBmatch()\fP, which it
1689 calls repeatedly (sometimes recursively). The limit set by \fImatch_limit\fP is
1690 imposed on the number of times this function is called during a match, which
1691 has the effect of limiting the amount of backtracking that can take place. For
1692 patterns that are not anchored, the count restarts from zero for each position
1693 in the subject string.
1694 .P
1695 When \fBpcre_exec()\fP is called with a pattern that was successfully studied
1696 with a JIT option, the way that the matching is executed is entirely different.
1697 However, there is still the possibility of runaway matching that goes on for a
1698 very long time, and so the \fImatch_limit\fP value is also used in this case
1699 (but in a different way) to limit how long the matching can continue.
1700 .P
1701 The default value for the limit can be set when PCRE is built; the default
1702 default is 10 million, which handles all but the most extreme cases. You can
1703 override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP
1704 block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in
1705 the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns
1707 .P
1708 A value for the match limit may also be supplied by an item at the start of a
1709 pattern of the form
1710 .sp
1711 (*LIMIT_MATCH=d)
1712 .sp
1713 where d is a decimal number. However, such a setting is ignored unless d is
1714 less than the limit set by the caller of \fBpcre_exec()\fP or, if no such limit
1715 is set, less than the default.
1716 .P
1717 The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but
1718 instead of limiting the total number of times that \fBmatch()\fP is called, it
1719 limits the depth of recursion. The recursion depth is a smaller number than the
1720 total number of calls, because not all calls to \fBmatch()\fP are recursive.
1721 This limit is of use only if it is set smaller than \fImatch_limit\fP.
1722 .P
1723 Limiting the recursion depth limits the amount of machine stack that can be
1724 used, or, when PCRE has been compiled to use memory on the heap instead of the
1725 stack, the amount of heap memory that can be used. This limit is not relevant,
1726 and is ignored, when matching is done using JIT compiled code.
1727 .P
1728 The default value for \fImatch_limit_recursion\fP can be set when PCRE is
1729 built; the default default is the same value as the default for
1730 \fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP
1731 with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and
1732 PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
1733 is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1734 .P
1735 A value for the recursion limit may also be supplied by an item at the start of
1736 a pattern of the form
1737 .sp
1739 .sp
1740 where d is a decimal number. However, such a setting is ignored unless d is
1741 less than the limit set by the caller of \fBpcre_exec()\fP or, if no such limit
1742 is set, less than the default.
1743 .P
1744 The \fIcallout_data\fP field is used in conjunction with the "callout" feature,
1745 and is described in the
1746 .\" HREF
1747 \fBpcrecallout\fP
1748 .\"
1749 documentation.
1750 .P
1751 The \fItables\fP field is provided for use with patterns that have been
1752 pre-compiled using custom character tables, saved to disc or elsewhere, and
1753 then reloaded, because the tables that were used to compile a pattern are not
1754 saved with it. See the
1755 .\" HREF
1756 \fBpcreprecompile\fP
1757 .\"
1758 documentation for a discussion of saving compiled patterns for later use. If
1759 NULL is passed using this mechanism, it forces PCRE's internal tables to be
1760 used.
1761 .P
1762 \fBWarning:\fP The tables that \fBpcre_exec()\fP uses must be the same as those
1763 that were used when the pattern was compiled. If this is not the case, the
1764 behaviour of \fBpcre_exec()\fP is undefined. Therefore, when a pattern is
1765 compiled and matched in the same process, this field should never be set. In
1766 this (the most common) case, the correct table pointer is automatically passed
1767 with the compiled pattern from \fBpcre_compile()\fP to \fBpcre_exec()\fP.
1768 .P
1769 If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must
1770 be set to point to a suitable variable. If the pattern contains any
1771 backtracking control verbs such as (*MARK:NAME), and the execution ends up with
1772 a name to pass back, a pointer to the name string (zero terminated) is placed
1773 in the variable pointed to by the \fImark\fP field. The names are within the
1774 compiled pattern; if you wish to retain such a name you must copy it before
1775 freeing the memory of a compiled pattern. If there is no name to pass back, the
1776 variable pointed to by the \fImark\fP field is set to NULL. For details of the
1777 backtracking control verbs, see the section entitled
1778 .\" HTML <a href="pcrepattern#backtrackcontrol">
1779 .\" </a>
1780 "Backtracking control"
1781 .\"
1782 in the
1783 .\" HREF
1784 \fBpcrepattern\fP
1785 .\"
1786 documentation.
1787 .
1788 .
1789 .\" HTML <a name="execoptions"></a>
1790 .SS "Option bits for \fBpcre_exec()\fP"
1791 .rs
1792 .sp
1793 The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be
1794 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1798 .P
1799 If the pattern was successfully studied with one of the just-in-time (JIT)
1800 compile options, the only supported options for JIT execution are
1803 unsupported option is used, JIT execution is disabled and the normal
1804 interpretive code in \fBpcre_exec()\fP is run.
1805 .sp
1807 .sp
1808 The PCRE_ANCHORED option limits \fBpcre_exec()\fP to matching at the first
1809 matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out
1810 to be anchored by virtue of its contents, it cannot be made unachored at
1811 matching time.
1812 .sp
1815 .sp
1816 These options (which are mutually exclusive) control what the \eR escape
1817 sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1818 match any Unicode newline sequence. These options override the choice that was
1819 made or defaulted when the pattern was compiled.
1820 .sp
1826 .sp
1827 These options override the newline definition that was chosen or defaulted when
1828 the pattern was compiled. For details, see the description of
1829 \fBpcre_compile()\fP above. During matching, the newline choice affects the
1830 behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1831 the way the match position is advanced after a match failure for an unanchored
1832 pattern.
1833 .P
1835 match attempt for an unanchored pattern fails when the current position is at a
1836 CRLF sequence, and the pattern contains no explicit matches for CR or LF
1837 characters, the match position is advanced by two characters instead of one, in
1838 other words, to after the CRLF.
1839 .P
1840 The above rule is a compromise that makes the most common cases work as
1841 expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1842 set), it does not match the string "\er\enA" because, after failing at the
1843 start, it skips both the CR and the LF before retrying. However, the pattern
1844 [\er\en]A does match that string, because it contains an explicit CR or LF
1845 reference, and so advances only by one character after the first failure.
1846 .P
1847 An explicit match for CR of LF is either a literal appearance of one of those
1848 characters, or one of the \er or \en escape sequences. Implicit matches such as
1849 [^X] do not count, nor does \es (which includes CR and LF in the characters
1850 that it matches).
1851 .P
1852 Notwithstanding the above, anomalous effects may still occur when CRLF is a
1853 valid newline sequence and explicit \er or \en escapes appear in the pattern.
1854 .sp
1856 .sp
1857 This option specifies that first character of the subject string is not the
1858 beginning of a line, so the circumflex metacharacter should not match before
1859 it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex
1860 never to match. This option affects only the behaviour of the circumflex
1861 metacharacter. It does not affect \eA.
1862 .sp
1864 .sp
1865 This option specifies that the end of the subject string is not the end of a
1866 line, so the dollar metacharacter should not match it nor (except in multiline
1867 mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at
1868 compile time) causes dollar never to match. This option affects only the
1869 behaviour of the dollar metacharacter. It does not affect \eZ or \ez.
1870 .sp
1872 .sp
1873 An empty string is not considered to be a valid match if this option is set. If
1874 there are alternatives in the pattern, they are tried. If all the alternatives
1875 match the empty string, the entire match fails. For example, if the pattern
1876 .sp
1877 a?b?
1878 .sp
1879 is applied to a string not beginning with "a" or "b", it matches an empty
1880 string at the start of the subject. With PCRE_NOTEMPTY set, this match is not
1881 valid, so PCRE searches further into the string for occurrences of "a" or "b".
1882 .sp
1884 .sp
1885 This is like PCRE_NOTEMPTY, except that an empty string match that is not at
1886 the start of the subject is permitted. If the pattern is anchored, such a match
1887 can occur only if the pattern contains \eK.
1888 .P
1889 Perl has no direct equivalent of PCRE_NOTEMPTY or PCRE_NOTEMPTY_ATSTART, but it
1890 does make a special case of a pattern match of the empty string within its
1891 \fBsplit()\fP function, and when using the /g modifier. It is possible to
1892 emulate Perl's behaviour after matching a null string by first trying the match
1893 again at the same offset with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then
1894 if that fails, by advancing the starting offset (see below) and trying an
1895 ordinary match again. There is some code that demonstrates how to do this in
1896 the
1897 .\" HREF
1898 \fBpcredemo\fP
1899 .\"
1900 sample program. In the most general case, you have to check to see if the
1901 newline convention recognizes CRLF as a newline, and if so, and the current
1902 character is CR followed by LF, advance the starting offset by two characters
1903 instead of one.
1904 .sp
1906 .sp
1907 There are a number of optimizations that \fBpcre_exec()\fP uses at the start of
1908 a match, in order to speed up the process. For example, if it is known that an
1909 unanchored match must start with a specific character, it searches the subject
1910 for that character, and fails immediately if it cannot find it, without
1911 actually running the main matching function. This means that a special item
1912 such as (*COMMIT) at the start of a pattern is not considered until after a
1913 suitable starting point for the match has been found. Also, when callouts or
1914 (*MARK) items are in use, these "start-up" optimizations can cause them to be
1915 skipped if the pattern is never actually used. The start-up optimizations are
1916 in effect a pre-scan of the subject that takes place before the pattern is run.
1917 .P
1918 The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly
1919 causing performance to suffer, but ensuring that in cases where the result is
1920 "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)
1921 are considered at every possible starting position in the subject string. If
1922 PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching
1923 time. The use of PCRE_NO_START_OPTIMIZE at matching time (that is, passing it
1924 to \fBpcre_exec()\fP) disables JIT execution; in this situation, matching is
1925 always done using interpretively.
1926 .P
1927 Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.
1928 Consider the pattern
1929 .sp
1931 .sp
1932 When this is compiled, PCRE records the fact that a match must start with the
1933 character "A". Suppose the subject string is "DEFABC". The start-up
1934 optimization scans along the subject, finds "A" and runs the first match
1935 attempt from there. The (*COMMIT) item means that the pattern must match the
1936 current starting position, which in this case, it does. However, if the same
1937 match is run with PCRE_NO_START_OPTIMIZE set, the initial scan along the
1938 subject string does not happen. The first match attempt is run starting from
1939 "D" and when this fails, (*COMMIT) prevents any further matches being tried, so
1940 the overall result is "no match". If the pattern is studied, more start-up
1941 optimizations may be used. For example, a minimum length for the subject may be
1942 recorded. Consider the pattern
1943 .sp
1944 (*MARK:A)(X|Y)
1945 .sp
1946 The minimum length for a match is one character. If the subject is "ABC", there
1947 will be attempts to match "ABC", "BC", "C", and then finally an empty string.
1948 If the pattern is studied, the final attempt does not take place, because PCRE
1949 knows that the subject is too short, and so the (*MARK) is never encountered.
1950 In this case, studying the pattern does not affect the overall match result,
1951 which is still "no match", but it does affect the auxiliary information that is
1952 returned.
1953 .sp
1955 .sp
1956 When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
1957 string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1958 The entire string is checked before any other processing takes place. The value
1959 of \fIstartoffset\fP is also checked to ensure that it points to the start of a
1960 UTF-8 character. There is a discussion about the
1961 .\" HTML <a href="pcreunicode.html#utf8strings">
1962 .\" </a>
1963 validity of UTF-8 strings
1964 .\"
1965 in the
1966 .\" HREF
1967 \fBpcreunicode\fP
1968 .\"
1969 page. If an invalid sequence of bytes is found, \fBpcre_exec()\fP returns the
1970 error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a
1971 truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both
1972 cases, information about the precise nature of the error may also be returned
1973 (see the descriptions of these errors in the section entitled \fIError return
1974 values from\fP \fBpcre_exec()\fP
1975 .\" HTML <a href="#errorlist">
1976 .\" </a>
1977 below).
1978 .\"
1979 If \fIstartoffset\fP contains a value that does not point to the start of a
1980 UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is
1981 returned.
1982 .P
1983 If you already know that your subject is valid, and you want to skip these
1984 checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
1985 calling \fBpcre_exec()\fP. You might want to do this for the second and
1986 subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find
1987 all the matches in a single subject string. However, you should be sure that
1988 the value of \fIstartoffset\fP points to the start of a character (or the end
1989 of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an
1990 invalid string as a subject or an invalid value of \fIstartoffset\fP is
1991 undefined. Your program may crash or loop.
1992 .sp
1995 .sp
1996 These options turn on the partial matching feature. For backwards
1997 compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match
1998 occurs if the end of the subject string is reached successfully, but there are
1999 not enough subject characters to complete the match. If this happens when
2000 PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, matching continues by
2001 testing any remaining alternatives. Only if no complete match can be found is
2002 PCRE_ERROR_PARTIAL returned instead of PCRE_ERROR_NOMATCH. In other words,
2003 PCRE_PARTIAL_SOFT says that the caller is prepared to handle a partial match,
2004 but only if no complete match can be found.
2005 .P
2006 If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a
2007 partial match is found, \fBpcre_exec()\fP immediately returns
2008 PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words,
2009 when PCRE_PARTIAL_HARD is set, a partial match is considered to be more
2010 important that an alternative complete match.
2011 .P
2012 In both cases, the portion of the string that was inspected when the partial
2013 match was found is set as the first matching string. There is a more detailed
2014 discussion of partial and multi-segment matching, with examples, in the
2015 .\" HREF
2016 \fBpcrepartial\fP
2017 .\"
2018 documentation.
2019 .
2020 .
2021 .SS "The string to be matched by \fBpcre_exec()\fP"
2022 .rs
2023 .sp
2024 The subject string is passed to \fBpcre_exec()\fP as a pointer in
2025 \fIsubject\fP, a length in \fIlength\fP, and a starting offset in
2026 \fIstartoffset\fP. The units for \fIlength\fP and \fIstartoffset\fP are bytes
2027 for the 8-bit library, 16-bit data items for the 16-bit library, and 32-bit
2028 data items for the 32-bit library.
2029 .P
2030 If \fIstartoffset\fP is negative or greater than the length of the subject,
2031 \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting offset is
2032 zero, the search for a match starts at the beginning of the subject, and this
2033 is by far the most common case. In UTF-8 or UTF-16 mode, the offset must point
2034 to the start of a character, or the end of the subject (in UTF-32 mode, one
2035 data unit equals one character, so all offsets are valid). Unlike the pattern
2036 string, the subject may contain binary zeroes.
2037 .P
2038 A non-zero starting offset is useful when searching for another match in the
2039 same subject by calling \fBpcre_exec()\fP again after a previous success.
2040 Setting \fIstartoffset\fP differs from just passing over a shortened string and
2041 setting PCRE_NOTBOL in the case of a pattern that begins with any kind of
2042 lookbehind. For example, consider the pattern
2043 .sp
2044 \eBiss\eB
2045 .sp
2046 which finds occurrences of "iss" in the middle of words. (\eB matches only if
2047 the current position in the subject is not a word boundary.) When applied to
2048 the string "Mississipi" the first call to \fBpcre_exec()\fP finds the first
2049 occurrence. If \fBpcre_exec()\fP is called again with just the remainder of the
2050 subject, namely "issipi", it does not match, because \eB is always false at the
2051 start of the subject, which is deemed to be a word boundary. However, if
2052 \fBpcre_exec()\fP is passed the entire string again, but with \fIstartoffset\fP
2053 set to 4, it finds the second occurrence of "iss" because it is able to look
2054 behind the starting point to discover that it is preceded by a letter.
2055 .P
2056 Finding all the matches in a subject is tricky when the pattern can match an
2057 empty string. It is possible to emulate Perl's /g behaviour by first trying the
2058 match again at the same offset, with the PCRE_NOTEMPTY_ATSTART and
2059 PCRE_ANCHORED options, and then if that fails, advancing the starting offset
2060 and trying an ordinary match again. There is some code that demonstrates how to
2061 do this in the
2062 .\" HREF
2063 \fBpcredemo\fP
2064 .\"
2065 sample program. In the most general case, you have to check to see if the
2066 newline convention recognizes CRLF as a newline, and if so, and the current
2067 character is CR followed by LF, advance the starting offset by two characters
2068 instead of one.
2069 .P
2070 If a non-zero starting offset is passed when the pattern is anchored, one
2071 attempt to match at the given offset is made. This can only succeed if the
2072 pattern does not require the match to be at the start of the subject.
2073 .
2074 .
2075 .SS "How \fBpcre_exec()\fP returns captured substrings"
2076 .rs
2077 .sp
2078 In general, a pattern matches a certain portion of the subject, and in
2079 addition, further substrings from the subject may be picked out by parts of the
2080 pattern. Following the usage in Jeffrey Friedl's book, this is called
2081 "capturing" in what follows, and the phrase "capturing subpattern" is used for
2082 a fragment of a pattern that picks out a substring. PCRE supports several other
2083 kinds of parenthesized subpattern that do not cause substrings to be captured.
2084 .P
2085 Captured substrings are returned to the caller via a vector of integers whose
2086 address is passed in \fIovector\fP. The number of elements in the vector is
2087 passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP: this
2088 argument is NOT the size of \fIovector\fP in bytes.
2089 .P
2090 The first two-thirds of the vector is used to pass back captured substrings,
2091 each substring using a pair of integers. The remaining third of the vector is
2092 used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
2093 and is not available for passing back information. The number passed in
2094 \fIovecsize\fP should always be a multiple of three. If it is not, it is
2095 rounded down.
2096 .P
2097 When a match is successful, information about captured substrings is returned
2098 in pairs of integers, starting at the beginning of \fIovector\fP, and
2099 continuing up to two-thirds of its length at the most. The first element of
2100 each pair is set to the offset of the first character in a substring, and the
2101 second is set to the offset of the first character after the end of a
2102 substring. These values are always data unit offsets, even in UTF mode. They
2103 are byte offsets in the 8-bit library, 16-bit data item offsets in the 16-bit
2104 library, and 32-bit data item offsets in the 32-bit library. \fBNote\fP: they
2105 are not character counts.
2106 .P
2107 The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the
2108 portion of the subject string matched by the entire pattern. The next pair is
2109 used for the first capturing subpattern, and so on. The value returned by
2110 \fBpcre_exec()\fP is one more than the highest numbered pair that has been set.
2111 For example, if two substrings have been captured, the returned value is 3. If
2112 there are no capturing subpatterns, the return value from a successful match is
2113 1, indicating that just the first pair of offsets has been set.
2114 .P
2115 If a capturing subpattern is matched repeatedly, it is the last portion of the
2116 string that it matched that is returned.
2117 .P
2118 If the vector is too small to hold all the captured substring offsets, it is
2119 used as far as possible (up to two-thirds of its length), and the function
2120 returns a value of zero. If neither the actual string matched nor any captured
2121 substrings are of interest, \fBpcre_exec()\fP may be called with \fIovector\fP
2122 passed as NULL and \fIovecsize\fP as zero. However, if the pattern contains
2123 back references and the \fIovector\fP is not big enough to remember the related
2124 substrings, PCRE has to get additional memory for use during matching. Thus it
2125 is usually advisable to supply an \fIovector\fP of reasonable size.
2126 .P
2127 There are some cases where zero is returned (indicating vector overflow) when
2128 in fact the vector is exactly the right size for the final match. For example,
2129 consider the pattern
2130 .sp
2131 (a)(?:(b)c|bd)
2132 .sp
2133 If a vector of 6 elements (allowing for only 1 captured substring) is given
2134 with subject string "abd", \fBpcre_exec()\fP will try to set the second
2135 captured string, thereby recording a vector overflow, before failing to match
2136 "c" and backing up to try the second alternative. The zero return, however,
2137 does correctly indicate that the maximum number of slots (namely 2) have been
2138 filled. In similar cases where there is temporary overflow, but the final
2139 number of used slots is actually less than the maximum, a non-zero value is
2140 returned.
2141 .P
2142 The \fBpcre_fullinfo()\fP function can be used to find out how many capturing
2143 subpatterns there are in a compiled pattern. The smallest size for
2144 \fIovector\fP that will allow for \fIn\fP captured substrings, in addition to
2145 the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3.
2146 .P
2147 It is possible for capturing subpattern number \fIn+1\fP to match some part of
2148 the subject when subpattern \fIn\fP has not been used at all. For example, if
2149 the string "abc" is matched against the pattern (a|(z))(bc) the return from the
2150 function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
2151 happens, both values in the offset pairs corresponding to unused subpatterns
2152 are set to -1.
2153 .P
2154 Offset values that correspond to unused subpatterns at the end of the
2155 expression are also set to -1. For example, if the string "abc" is matched
2156 against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
2157 return from the function is 2, because the highest used capturing subpattern
2158 number is 1, and the offsets for for the second and third capturing subpatterns
2159 (assuming the vector is large enough, of course) are set to -1.
2160 .P
2161 \fBNote\fP: Elements in the first two-thirds of \fIovector\fP that do not
2162 correspond to capturing parentheses in the pattern are never changed. That is,
2163 if a pattern contains \fIn\fP capturing parentheses, no more than
2164 \fIovector[0]\fP to \fIovector[2n+1]\fP are set by \fBpcre_exec()\fP. The other
2165 elements (in the first two-thirds) retain whatever values they previously had.
2166 .P
2167 Some convenience functions are provided for extracting the captured substrings
2168 as separate strings. These are described below.
2169 .
2170 .
2171 .\" HTML <a name="errorlist"></a>
2172 .SS "Error return values from \fBpcre_exec()\fP"
2173 .rs
2174 .sp
2175 If \fBpcre_exec()\fP fails, it returns a negative number. The following are
2176 defined in the header file:
2177 .sp
2179 .sp
2180 The subject string did not match the pattern.
2181 .sp
2183 .sp
2184 Either \fIcode\fP or \fIsubject\fP was passed as NULL, or \fIovector\fP was
2185 NULL and \fIovecsize\fP was not zero.
2186 .sp
2188 .sp
2189 An unrecognized bit was set in the \fIoptions\fP argument.
2190 .sp
2192 .sp
2193 PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch
2194 the case when it is passed a junk pointer and to detect when a pattern that was
2195 compiled in an environment of one endianness is run in an environment with the
2196 other endianness. This is the error that PCRE gives when the magic number is
2197 not present.
2198 .sp
2200 .sp
2201 While running the pattern match, an unknown item was encountered in the
2202 compiled pattern. This error could be caused by a bug in PCRE or by overwriting
2203 of the compiled pattern.
2204 .sp
2206 .sp
2207 If a pattern contains back references, but the \fIovector\fP that is passed to
2208 \fBpcre_exec()\fP is not big enough to remember the referenced substrings, PCRE
2209 gets a block of memory at the start of matching to use for this purpose. If the
2210 call via \fBpcre_malloc()\fP fails, this error is given. The memory is
2211 automatically freed at the end of matching.
2212 .P
2213 This error is also given if \fBpcre_stack_malloc()\fP fails in
2214 \fBpcre_exec()\fP. This can happen only when PCRE has been compiled with
2215 \fB--disable-stack-for-recursion\fP.
2216 .sp
2218 .sp
2219 This error is used by the \fBpcre_copy_substring()\fP,
2220 \fBpcre_get_substring()\fP, and \fBpcre_get_substring_list()\fP functions (see
2221 below). It is never returned by \fBpcre_exec()\fP.
2222 .sp
2224 .sp
2225 The backtracking limit, as specified by the \fImatch_limit\fP field in a
2226 \fBpcre_extra\fP structure (or defaulted) was reached. See the description
2227 above.
2228 .sp
2230 .sp
2231 This error is never generated by \fBpcre_exec()\fP itself. It is provided for
2232 use by callout functions that want to yield a distinctive error code. See the
2233 .\" HREF
2234 \fBpcrecallout\fP
2235 .\"
2236 documentation for details.
2237 .sp
2239 .sp
2240 A string that contains an invalid UTF-8 byte sequence was passed as a subject,
2241 and the PCRE_NO_UTF8_CHECK option was not set. If the size of the output vector
2242 (\fIovecsize\fP) is at least 2, the byte offset to the start of the the invalid
2243 UTF-8 character is placed in the first element, and a reason code is placed in
2244 the second element. The reason codes are listed in the
2245 .\" HTML <a href="#badutf8reasons">
2246 .\" </a>
2247 following section.
2248 .\"
2249 For backward compatibility, if PCRE_PARTIAL_HARD is set and the problem is a
2250 truncated UTF-8 character at the end of the subject (reason codes 1 to 5),
2251 PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8.
2252 .sp
2254 .sp
2255 The UTF-8 byte sequence that was passed as a subject was checked and found to
2256 be valid (the PCRE_NO_UTF8_CHECK option was not set), but the value of
2257 \fIstartoffset\fP did not point to the beginning of a UTF-8 character or the
2258 end of the subject.
2259 .sp
2261 .sp
2262 The subject string did not match, but it did match partially. See the
2263 .\" HREF
2264 \fBpcrepartial\fP
2265 .\"
2266 documentation for details of partial matching.
2267 .sp
2269 .sp
2270 This code is no longer in use. It was formerly returned when the PCRE_PARTIAL
2271 option was used with a compiled pattern containing items that were not
2272 supported for partial matching. From release 8.00 onwards, there are no
2273 restrictions on partial matching.
2274 .sp
2276 .sp
2277 An unexpected internal error has occurred. This error could be caused by a bug
2278 in PCRE or by overwriting of the compiled pattern.
2279 .sp
2281 .sp
2282 This error is given if the value of the \fIovecsize\fP argument is negative.
2283 .sp
2285 .sp
2286 The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
2287 field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
2288 description above.
2289 .sp
2291 .sp
2292 An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
2293 .sp
2295 .sp
2296 The value of \fIstartoffset\fP was negative or greater than the length of the
2297 subject, that is, the value in \fIlength\fP.
2298 .sp
2300 .sp
2301 This error is returned instead of PCRE_ERROR_BADUTF8 when the subject string
2302 ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD option is set.
2303 Information about the failure is returned as for PCRE_ERROR_BADUTF8. It is in
2304 fact sufficient to detect this case, but this special error code for
2305 PCRE_PARTIAL_HARD precedes the implementation of returned information; it is
2306 retained for backwards compatibility.
2307 .sp
2309 .sp
2310 This error is returned when \fBpcre_exec()\fP detects a recursion loop within
2311 the pattern. Specifically, it means that either the whole pattern or a
2312 subpattern has been called recursively for the second time at the same position
2313 in the subject string. Some simple patterns that might do this are detected and
2314 faulted at compile time, but more complicated cases, in particular mutual
2315 recursions between two different subpatterns, cannot be detected until run
2316 time.
2317 .sp
2319 .sp
2320 This error is returned when a pattern that was successfully studied using a
2321 JIT compile option is being matched, but the memory available for the
2322 just-in-time processing stack is not large enough. See the
2323 .\" HREF
2324 \fBpcrejit\fP
2325 .\"
2326 documentation for more details.
2327 .sp
2329 .sp
2330 This error is given if a pattern that was compiled by the 8-bit library is
2331 passed to a 16-bit or 32-bit library function, or vice versa.
2332 .sp
2334 .sp
2335 This error is given if a pattern that was compiled and saved is reloaded on a
2336 host with different endianness. The utility function
2337 \fBpcre_pattern_to_host_byte_order()\fP can be used to convert such a pattern
2338 so that it runs on the new host.
2339 .sp
2341 .sp
2342 This error is returned when a pattern that was successfully studied using a JIT
2343 compile option is being matched, but the matching mode (partial or complete
2344 match) does not correspond to any JIT compilation mode. When the JIT fast path
2345 function is used, this error may be also given for invalid options. See the
2346 .\" HREF
2347 \fBpcrejit\fP
2348 .\"
2349 documentation for more details.
2350 .sp
2352 .sp
2353 This error is given if \fBpcre_exec()\fP is called with a negative value for
2354 the \fIlength\fP argument.
2355 .P
2356 Error numbers -16 to -20, -22, and 30 are not used by \fBpcre_exec()\fP.
2357 .
2358 .
2359 .\" HTML <a name="badutf8reasons"></a>
2360 .SS "Reason codes for invalid UTF-8 strings"
2361 .rs
2362 .sp
2363 This section applies only to the 8-bit library. The corresponding information
2364 for the 16-bit and 32-bit libraries is given in the
2365 .\" HREF
2366 \fBpcre16\fP
2367 .\"
2368 and
2369 .\" HREF
2370 \fBpcre32\fP
2371 .\"
2372 pages.
2373 .P
2374 When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or
2375 PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at
2376 least 2, the offset of the start of the invalid UTF-8 character is placed in
2377 the first output vector element (\fIovector[0]\fP) and a reason code is placed
2378 in the second element (\fIovector[1]\fP). The reason codes are given names in
2379 the \fBpcre.h\fP header file:
2380 .sp
2386 .sp
2387 The string ends with a truncated UTF-8 character; the code specifies how many
2388 bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be
2389 no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279)
2390 allows for up to 6 bytes, and this is checked first; hence the possibility of
2391 4 or 5 missing bytes.
2392 .sp
2397 PCRE_UTF8_ERR10
2398 .sp
2399 The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the
2400 character do not have the binary value 0b10 (that is, either the most
2401 significant bit is 0, or the next bit is 1).
2402 .sp
2403 PCRE_UTF8_ERR11
2404 PCRE_UTF8_ERR12
2405 .sp
2406 A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long;
2407 these code points are excluded by RFC 3629.
2408 .sp
2409 PCRE_UTF8_ERR13
2410 .sp
2411 A 4-byte character has a value greater than 0x10fff; these code points are
2412 excluded by RFC 3629.
2413 .sp
2414 PCRE_UTF8_ERR14
2415 .sp
2416 A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of
2417 code points are reserved by RFC 3629 for use with UTF-16, and so are excluded
2418 from UTF-8.
2419 .sp
2420 PCRE_UTF8_ERR15
2421 PCRE_UTF8_ERR16
2422 PCRE_UTF8_ERR17
2423 PCRE_UTF8_ERR18
2424 PCRE_UTF8_ERR19
2425 .sp
2426 A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a
2427 value that can be represented by fewer bytes, which is invalid. For example,
2428 the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just
2429 one byte.
2430 .sp
2431 PCRE_UTF8_ERR20
2432 .sp
2433 The two most significant bits of the first byte of a character have the binary
2434 value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a
2435 byte can only validly occur as the second or subsequent byte of a multi-byte
2436 character.
2437 .sp
2438 PCRE_UTF8_ERR21
2439 .sp
2440 The first byte of a character has the value 0xfe or 0xff. These values can
2441 never occur in a valid UTF-8 string.
2442 .sp
2443 PCRE_UTF8_ERR22
2444 .sp
2445 This error code was formerly used when the presence of a so-called
2446 "non-character" caused an error. Unicode corrigendum #9 makes it clear that
2447 such characters should not cause a string to be rejected, and so this code is
2448 no longer in use and is never returned.
2449 .
2450 .
2452 .rs
2453 .sp
2454 .nf
2455 .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
2456 .B " int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,"
2457 .B " int \fIbuffersize\fP);"
2458 .sp
2459 .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
2460 .B " int \fIstringcount\fP, int \fIstringnumber\fP,"
2461 .B " const char **\fIstringptr\fP);"
2462 .sp
2463 .B int pcre_get_substring_list(const char *\fIsubject\fP,
2464 .B " int *\fIovector\fP, int \fIstringcount\fP, const char ***\fIlistptr\fP);"
2465 .fi
2466 .PP
2467 Captured substrings can be accessed directly by using the offsets returned by
2468 \fBpcre_exec()\fP in \fIovector\fP. For convenience, the functions
2469 \fBpcre_copy_substring()\fP, \fBpcre_get_substring()\fP, and
2470 \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
2471 as new, separate, zero-terminated strings. These functions identify substrings
2472 by number. The next section describes functions for extracting named
2473 substrings.
2474 .P
2475 A substring that contains a binary zero is correctly extracted and has a
2476 further zero added on the end, but the result is not, of course, a C string.
2477 However, you can process such a string by referring to the length that is
2478 returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
2479 Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
2480 for handling strings containing binary zeros, because the end of the final
2481 string is not independently indicated.
2482 .P
2483 The first three arguments are the same for all three of these functions:
2484 \fIsubject\fP is the subject string that has just been successfully matched,
2485 \fIovector\fP is a pointer to the vector of integer offsets that was passed to
2486 \fBpcre_exec()\fP, and \fIstringcount\fP is the number of substrings that were
2487 captured by the match, including the substring that matched the entire regular
2488 expression. This is the value returned by \fBpcre_exec()\fP if it is greater
2489 than zero. If \fBpcre_exec()\fP returned zero, indicating that it ran out of
2490 space in \fIovector\fP, the value passed as \fIstringcount\fP should be the
2491 number of elements in the vector divided by three.
2492 .P
2493 The functions \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP
2494 extract a single substring, whose number is given as \fIstringnumber\fP. A
2495 value of zero extracts the substring that matched the entire pattern, whereas
2496 higher values extract the captured substrings. For \fBpcre_copy_substring()\fP,
2497 the string is placed in \fIbuffer\fP, whose length is given by
2498 \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is
2499 obtained via \fBpcre_malloc\fP, and its address is returned via
2500 \fIstringptr\fP. The yield of the function is the length of the string, not
2501 including the terminating zero, or one of these error codes:
2502 .sp
2504 .sp
2505 The buffer was too small for \fBpcre_copy_substring()\fP, or the attempt to get
2506 memory failed for \fBpcre_get_substring()\fP.
2507 .sp
2509 .sp
2510 There is no substring whose number is \fIstringnumber\fP.
2511 .P
2512 The \fBpcre_get_substring_list()\fP function extracts all available substrings
2513 and builds a list of pointers to them. All this is done in a single block of
2514 memory that is obtained via \fBpcre_malloc\fP. The address of the memory block
2515 is returned via \fIlistptr\fP, which is also the start of the list of string
2516 pointers. The end of the list is marked by a NULL pointer. The yield of the
2517 function is zero if all went well, or the error code
2518 .sp
2520 .sp
2521 if the attempt to get the memory block failed.
2522 .P
2523 When any of these functions encounter a substring that is unset, which can
2524 happen when capturing subpattern number \fIn+1\fP matches some part of the
2525 subject, but subpattern \fIn\fP has not been used at all, they return an empty
2526 string. This can be distinguished from a genuine zero-length substring by
2527 inspecting the appropriate offset in \fIovector\fP, which is negative for unset
2528 substrings.
2529 .P
2530 The two convenience functions \fBpcre_free_substring()\fP and
2531 \fBpcre_free_substring_list()\fP can be used to free the memory returned by
2532 a previous call of \fBpcre_get_substring()\fP or
2533 \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
2534 the function pointed to by \fBpcre_free\fP, which of course could be called
2535 directly from a C program. However, PCRE is used in some situations where it is
2536 linked via a special interface to another programming language that cannot use
2537 \fBpcre_free\fP directly; it is for these cases that the functions are
2538 provided.
2539 .
2540 .
2542 .rs
2543 .sp
2544 .nf
2545 .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
2546 .B " const char *\fIname\fP);"
2547 .sp
2548 .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
2549 .B " const char *\fIsubject\fP, int *\fIovector\fP,"
2550 .B " int \fIstringcount\fP, const char *\fIstringname\fP,"
2551 .B " char *\fIbuffer\fP, int \fIbuffersize\fP);"
2552 .sp
2553 .B int pcre_get_named_substring(const pcre *\fIcode\fP,
2554 .B " const char *\fIsubject\fP, int *\fIovector\fP,"
2555 .B " int \fIstringcount\fP, const char *\fIstringname\fP,"
2556 .B " const char **\fIstringptr\fP);"
2557 .fi
2558 .PP
2559 To extract a substring by name, you first have to find associated number.
2560 For example, for this pattern
2561 .sp
2562 (a+)b(?<xxx>\ed+)...
2563 .sp
2564 the number of the subpattern called "xxx" is 2. If the name is known to be
2565 unique (PCRE_DUPNAMES was not set), you can find the number from the name by
2566 calling \fBpcre_get_stringnumber()\fP. The first argument is the compiled
2567 pattern, and the second is the name. The yield of the function is the
2568 subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of
2569 that name.
2570 .P
2571 Given the number, you can extract the substring directly, or use one of the
2572 functions described in the previous section. For convenience, there are also
2573 two functions that do the whole job.
2574 .P
2575 Most of the arguments of \fBpcre_copy_named_substring()\fP and
2576 \fBpcre_get_named_substring()\fP are the same as those for the similarly named
2577 functions that extract by number. As these are described in the previous
2578 section, they are not re-described here. There are just two differences:
2579 .P
2580 First, instead of a substring number, a substring name is given. Second, there
2581 is an extra argument, given at the start, which is a pointer to the compiled
2582 pattern. This is needed in order to gain access to the name-to-number
2583 translation table.
2584 .P
2585 These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
2586 then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
2587 appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
2588 the behaviour may not be what you want (see the next section).
2589 .P
2590 \fBWarning:\fP If the pattern uses the (?| feature to set up multiple
2591 subpatterns with the same number, as described in the
2592 .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
2593 .\" </a>
2594 section on duplicate subpattern numbers
2595 .\"
2596 in the
2597 .\" HREF
2598 \fBpcrepattern\fP
2599 .\"
2600 page, you cannot use names to distinguish the different subpatterns, because
2601 names are not included in the compiled code. The matching process uses only
2602 numbers. For this reason, the use of different names for subpatterns of the
2603 same number causes an error at compile time.
2604 .
2605 .
2607 .rs
2608 .sp
2609 .nf
2610 .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
2611 .B " const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);"
2612 .fi
2613 .PP
2614 When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
2615 are not required to be unique. (Duplicate names are always allowed for
2616 subpatterns with the same number, created by using the (?| feature. Indeed, if
2617 such subpatterns are named, they are required to use the same names.)
2618 .P
2619 Normally, patterns with duplicate names are such that in any one match, only
2620 one of the named subpatterns participates. An example is shown in the
2621 .\" HREF
2622 \fBpcrepattern\fP
2623 .\"
2624 documentation.
2625 .P
2626 When duplicates are present, \fBpcre_copy_named_substring()\fP and
2627 \fBpcre_get_named_substring()\fP return the first substring corresponding to
2628 the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
2629 returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
2630 returns one of the numbers that are associated with the name, but it is not
2631 defined which it is.
2632 .P
2633 If you want to get full details of all captured substrings for a given name,
2634 you must use the \fBpcre_get_stringtable_entries()\fP function. The first
2635 argument is the compiled pattern, and the second is the name. The third and
2636 fourth are pointers to variables which are updated by the function. After it
2637 has run, they point to the first and last entries in the name-to-number table
2638 for the given name. The function itself returns the length of each entry, or
2639 PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
2640 described above in the section entitled \fIInformation about a pattern\fP
2641 .\" HTML <a href="#infoaboutpattern">
2642 .\" </a>
2643 above.
2644 .\"
2645 Given all the relevant entries for the name, you can extract each of their
2646 numbers, and hence the captured data, if any.
2647 .
2648 .
2650 .rs
2651 .sp
2652 The traditional matching function uses a similar algorithm to Perl, which stops
2653 when it finds the first match, starting at a given point in the subject. If you
2654 want to find all possible matches, or the longest possible match, consider
2655 using the alternative matching function (see below) instead. If you cannot use
2656 the alternative function, but still need to find all possible matches, you
2657 can kludge it up by making use of the callout facility, which is described in
2658 the
2659 .\" HREF
2660 \fBpcrecallout\fP
2661 .\"
2662 documentation.
2663 .P
2664 What you have to do is to insert a callout right at the end of the pattern.
2665 When your callout function is called, extract and save the current matched
2666 substring. Then return 1, which forces \fBpcre_exec()\fP to backtrack and try
2667 other alternatives. Ultimately, when it runs out of matches, \fBpcre_exec()\fP
2668 will yield PCRE_ERROR_NOMATCH.
2669 .
2670 .
2672 .rs
2673 .sp
2674 Matching certain patterns using \fBpcre_exec()\fP can use a lot of process
2675 stack, which in certain environments can be rather limited in size. Some users
2676 find it helpful to have an estimate of the amount of stack that is used by
2677 \fBpcre_exec()\fP, to help them set recursion limits, as described in the
2678 .\" HREF
2679 \fBpcrestack\fP
2680 .\"
2681 documentation. The estimate that is output by \fBpcretest\fP when called with
2682 the \fB-m\fP and \fB-C\fP options is obtained by calling \fBpcre_exec\fP with
2683 the values NULL, NULL, NULL, -999, and -999 for its first five arguments.
2684 .P
2685 Normally, if its first argument is NULL, \fBpcre_exec()\fP immediately returns
2686 the negative error code PCRE_ERROR_NULL, but with this special combination of
2687 arguments, it returns instead a negative number whose absolute value is the
2688 approximate stack frame size in bytes. (A negative number is used so that it is
2689 clear that no match has happened.) The value is approximate because in some
2690 cases, recursive calls to \fBpcre_exec()\fP occur when there are one or two
2691 additional variables on the stack.
2692 .P
2693 If PCRE has been compiled to use the heap instead of the stack for recursion,
2694 the value returned is the size of each block that is obtained from the heap.
2695 .
2696 .
2697 .\" HTML <a name="dfamatch"></a>
2699 .rs
2700 .sp
2701 .nf
2702 .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
2703 .B " const char *\fIsubject\fP, int \fIlength\fP, int \fIstartoffset\fP,"
2704 .B " int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,"
2705 .B " int *\fIworkspace\fP, int \fIwscount\fP);"
2706 .fi
2707 .P
2708 The function \fBpcre_dfa_exec()\fP is called to match a subject string against
2709 a compiled pattern, using a matching algorithm that scans the subject string
2710 just once, and does not backtrack. This has different characteristics to the
2711 normal algorithm, and is not compatible with Perl. Some of the features of PCRE
2712 patterns are not supported. Nevertheless, there are times when this kind of
2713 matching can be useful. For a discussion of the two matching algorithms, and a
2714 list of features that \fBpcre_dfa_exec()\fP does not support, see the
2715 .\" HREF
2716 \fBpcrematching\fP
2717 .\"
2718 documentation.
2719 .P
2720 The arguments for the \fBpcre_dfa_exec()\fP function are the same as for
2721 \fBpcre_exec()\fP, plus two extras. The \fIovector\fP argument is used in a
2722 different way, and this is described below. The other common arguments are used
2723 in the same way as for \fBpcre_exec()\fP, so their description is not repeated
2724 here.
2725 .P
2726 The two additional arguments provide workspace for the function. The workspace
2727 vector should contain at least 20 elements. It is used for keeping track of
2728 multiple paths through the pattern tree. More workspace will be needed for
2729 patterns and subjects where there are a lot of potential matches.
2730 .P
2731 Here is an example of a simple call to \fBpcre_dfa_exec()\fP:
2732 .sp
2733 int rc;
2734 int ovector[10];
2735 int wspace[20];
2736 rc = pcre_dfa_exec(
2737 re, /* result of pcre_compile() */
2738 NULL, /* we didn't study the pattern */
2739 "some string", /* the subject string */
2740 11, /* the length of the subject string */
2741 0, /* start at offset 0 in the subject */
2742 0, /* default options */
2743 ovector, /* vector of integers for substring information */
2744 10, /* number of elements (NOT size in bytes) */
2745 wspace, /* working space vector */
2746 20); /* number of elements (NOT size in bytes) */
2747 .
2748 .SS "Option bits for \fBpcre_dfa_exec()\fP"
2749 .rs
2750 .sp
2751 The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be
2752 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
2756 All but the last four of these are exactly the same as for \fBpcre_exec()\fP,
2757 so their description is not repeated here.
2758 .sp
2761 .sp
2762 These have the same general effect as they do for \fBpcre_exec()\fP, but the
2763 details are slightly different. When PCRE_PARTIAL_HARD is set for
2764 \fBpcre_dfa_exec()\fP, it returns PCRE_ERROR_PARTIAL if the end of the subject
2765 is reached and there is still at least one matching possibility that requires
2766 additional characters. This happens even if some complete matches have also
2767 been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH
2768 is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached,
2769 there have been no complete matches, but there is still at least one matching
2770 possibility. The portion of the string that was inspected when the longest
2771 partial match was found is set as the first matching string in both cases.
2772 There is a more detailed discussion of partial and multi-segment matching, with
2773 examples, in the
2774 .\" HREF
2775 \fBpcrepartial\fP
2776 .\"
2777 documentation.
2778 .sp
2780 .sp
2781 Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
2782 soon as it has found one match. Because of the way the alternative algorithm
2783 works, this is necessarily the shortest possible match at the first possible
2784 matching point in the subject string.
2785 .sp
2787 .sp
2788 When \fBpcre_dfa_exec()\fP returns a partial match, it is possible to call it
2789 again, with additional subject characters, and have it continue with the same
2790 match. The PCRE_DFA_RESTART option requests this action; when it is set, the
2791 \fIworkspace\fP and \fIwscount\fP options must reference the same vector as
2792 before because data about the match so far is left in them after a partial
2793 match. There is more discussion of this facility in the
2794 .\" HREF
2795 \fBpcrepartial\fP
2796 .\"
2797 documentation.
2798 .
2799 .
2800 .SS "Successful returns from \fBpcre_dfa_exec()\fP"
2801 .rs
2802 .sp
2803 When \fBpcre_dfa_exec()\fP succeeds, it may have matched more than one
2804 substring in the subject. Note, however, that all the matches from one run of
2805 the function start at the same point in the subject. The shorter matches are
2806 all initial substrings of the longer matches. For example, if the pattern
2807 .sp
2808 <.*>
2809 .sp
2810 is matched against the string
2811 .sp
2812 This is <something> <something else> <something further> no more
2813 .sp
2814 the three matched strings are
2815 .sp
2816 <something>
2817 <something> <something else>
2818 <something> <something else> <something further>
2819 .sp
2820 On success, the yield of the function is a number greater than zero, which is
2821 the number of matched substrings. The substrings themselves are returned in
2822 \fIovector\fP. Each string uses two elements; the first is the offset to the
2823 start, and the second is the offset to the end. In fact, all the strings have
2824 the same start offset. (Space could have been saved by giving this only once,
2825 but it was decided to retain some compatibility with the way \fBpcre_exec()\fP
2826 returns data, even though the meaning of the strings is different.)
2827 .P
2828 The strings are returned in reverse order of length; that is, the longest
2829 matching string is given first. If there were too many matches to fit into
2830 \fIovector\fP, the yield of the function is zero, and the vector is filled with
2831 the longest matches. Unlike \fBpcre_exec()\fP, \fBpcre_dfa_exec()\fP can use
2832 the entire \fIovector\fP for returning matched strings.
2833 .P
2834 NOTE: PCRE's "auto-possessification" optimization usually applies to character
2835 repeats at the end of a pattern (as well as internally). For example, the
2836 pattern "a\ed+" is compiled as if it were "a\ed++" because there is no point
2837 even considering the possibility of backtracking into the repeated digits. For
2838 DFA matching, this means that only one possible match is found. If you really
2839 do want multiple matches in such cases, either use an ungreedy repeat
2840 ("a\ed+?") or set the PCRE_NO_AUTO_POSSESS option when compiling.
2841 .
2842 .
2843 .SS "Error returns from \fBpcre_dfa_exec()\fP"
2844 .rs
2845 .sp
2846 The \fBpcre_dfa_exec()\fP function returns a negative number when it fails.
2847 Many of the errors are the same as for \fBpcre_exec()\fP, and these are
2848 described
2849 .\" HTML <a href="#errorlist">
2850 .\" </a>
2851 above.
2852 .\"
2853 There are in addition the following errors that are specific to
2854 \fBpcre_dfa_exec()\fP:
2855 .sp
2857 .sp
2858 This return is given if \fBpcre_dfa_exec()\fP encounters an item in the pattern
2859 that it does not support, for instance, the use of \eC or a back reference.
2860 .sp
2862 .sp
2863 This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that
2864 uses a back reference for the condition, or a test for recursion in a specific
2865 group. These are not supported.
2866 .sp
2868 .sp
2869 This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP
2870 block that contains a setting of the \fImatch_limit\fP or
2871 \fImatch_limit_recursion\fP fields. This is not supported (these fields are
2872 meaningless for DFA matching).
2873 .sp
2875 .sp
2876 This return is given if \fBpcre_dfa_exec()\fP runs out of space in the
2877 \fIworkspace\fP vector.
2878 .sp
2880 .sp
2881 When a recursive subpattern is processed, the matching function calls itself
2882 recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
2883 error is given if the output vector is not large enough. This should be
2884 extremely rare, as a vector of size 1000 is used.
2885 .sp
2887 .sp
2888 When \fBpcre_dfa_exec()\fP is called with the \fBPCRE_DFA_RESTART\fP option,
2889 some plausibility checks are made on the contents of the workspace, which
2890 should contain data about the previous partial match. If any of these checks
2891 fail, this error is given.
2892 .
2893 .
2894 .SH "SEE ALSO"
2895 .rs
2896 .sp
2897 \fBpcre16\fP(3), \fBpcre32\fP(3), \fBpcrebuild\fP(3), \fBpcrecallout\fP(3),
2898 \fBpcrecpp(3)\fP(3), \fBpcrematching\fP(3), \fBpcrepartial\fP(3),
2899 \fBpcreposix\fP(3), \fBpcreprecompile\fP(3), \fBpcresample\fP(3),
2900 \fBpcrestack\fP(3).
2901 .
2902 .
2904 .rs
2905 .sp
2906 .nf
2907 Philip Hazel
2908 University Computing Service
2909 Cambridge CB2 3QH, England.
2910 .fi
2911 .
2912 .
2914 .rs
2915 .sp
2916 .nf
2917 Last updated: 09 February 2014
2918 Copyright (c) 1997-2014 University of Cambridge.
2919 .fi


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

  ViewVC Help
Powered by ViewVC 1.1.5