/[pcre]/code/trunk/doc/pcreapi.3
ViewVC logotype

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

Parent Directory Parent Directory | Revision Log Revision Log


Revision 96 - (show annotations) (download)
Fri Mar 2 13:10:43 2007 UTC (7 years, 9 months ago) by nigel
File size: 78945 byte(s)
 r6896@hex:  nm | 2007-03-02 13:09:14 +0000
 Added EOL and keywork properties throughout

1 .TH PCREAPI 3
2 .SH NAME
3 PCRE - Perl-compatible regular expressions
4 .SH "PCRE NATIVE API"
5 .rs
6 .sp
7 .B #include <pcre.h>
8 .PP
9 .SM
10 .br
11 .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
12 .ti +5n
13 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
14 .ti +5n
15 .B const unsigned char *\fItableptr\fP);
16 .PP
17 .br
18 .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
19 .ti +5n
20 .B int *\fIerrorcodeptr\fP,
21 .ti +5n
22 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
23 .ti +5n
24 .B const unsigned char *\fItableptr\fP);
25 .PP
26 .br
27 .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,
28 .ti +5n
29 .B const char **\fIerrptr\fP);
30 .PP
31 .br
32 .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
33 .ti +5n
34 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
35 .ti +5n
36 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
37 .PP
38 .br
39 .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
40 .ti +5n
41 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
42 .ti +5n
43 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
44 .ti +5n
45 .B int *\fIworkspace\fP, int \fIwscount\fP);
46 .PP
47 .br
48 .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
49 .ti +5n
50 .B const char *\fIsubject\fP, int *\fIovector\fP,
51 .ti +5n
52 .B int \fIstringcount\fP, const char *\fIstringname\fP,
53 .ti +5n
54 .B char *\fIbuffer\fP, int \fIbuffersize\fP);
55 .PP
56 .br
57 .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
58 .ti +5n
59 .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
60 .ti +5n
61 .B int \fIbuffersize\fP);
62 .PP
63 .br
64 .B int pcre_get_named_substring(const pcre *\fIcode\fP,
65 .ti +5n
66 .B const char *\fIsubject\fP, int *\fIovector\fP,
67 .ti +5n
68 .B int \fIstringcount\fP, const char *\fIstringname\fP,
69 .ti +5n
70 .B const char **\fIstringptr\fP);
71 .PP
72 .br
73 .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
74 .ti +5n
75 .B const char *\fIname\fP);
76 .PP
77 .br
78 .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
79 .ti +5n
80 .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
81 .PP
82 .br
83 .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
84 .ti +5n
85 .B int \fIstringcount\fP, int \fIstringnumber\fP,
86 .ti +5n
87 .B const char **\fIstringptr\fP);
88 .PP
89 .br
90 .B int pcre_get_substring_list(const char *\fIsubject\fP,
91 .ti +5n
92 .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
93 .PP
94 .br
95 .B void pcre_free_substring(const char *\fIstringptr\fP);
96 .PP
97 .br
98 .B void pcre_free_substring_list(const char **\fIstringptr\fP);
99 .PP
100 .br
101 .B const unsigned char *pcre_maketables(void);
102 .PP
103 .br
104 .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
105 .ti +5n
106 .B int \fIwhat\fP, void *\fIwhere\fP);
107 .PP
108 .br
109 .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
110 .B *\fIfirstcharptr\fP);
111 .PP
112 .br
113 .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
114 .PP
115 .br
116 .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
117 .PP
118 .br
119 .B char *pcre_version(void);
120 .PP
121 .br
122 .B void *(*pcre_malloc)(size_t);
123 .PP
124 .br
125 .B void (*pcre_free)(void *);
126 .PP
127 .br
128 .B void *(*pcre_stack_malloc)(size_t);
129 .PP
130 .br
131 .B void (*pcre_stack_free)(void *);
132 .PP
133 .br
134 .B int (*pcre_callout)(pcre_callout_block *);
135 .
136 .
137 .SH "PCRE API OVERVIEW"
138 .rs
139 .sp
140 PCRE has its own native API, which is described in this document. There are
141 also some wrapper functions that correspond to the POSIX regular expression
142 API. These are described in the
143 .\" HREF
144 \fBpcreposix\fP
145 .\"
146 documentation. Both of these APIs define a set of C function calls. A C++
147 wrapper is distributed with PCRE. It is documented in the
148 .\" HREF
149 \fBpcrecpp\fP
150 .\"
151 page.
152 .P
153 The native API C function prototypes are defined in the header file
154 \fBpcre.h\fP, and on Unix systems the library itself is called \fBlibpcre\fP.
155 It can normally be accessed by adding \fB-lpcre\fP to the command for linking
156 an application that uses PCRE. The header file defines the macros PCRE_MAJOR
157 and PCRE_MINOR to contain the major and minor release numbers for the library.
158 Applications can use these to include support for different releases of PCRE.
159 .P
160 The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,
161 and \fBpcre_exec()\fP are used for compiling and matching regular expressions
162 in a Perl-compatible manner. A sample program that demonstrates the simplest
163 way of using them is provided in the file called \fIpcredemo.c\fP in the source
164 distribution. The
165 .\" HREF
166 \fBpcresample\fP
167 .\"
168 documentation describes how to run it.
169 .P
170 A second matching function, \fBpcre_dfa_exec()\fP, which is not
171 Perl-compatible, is also provided. This uses a different algorithm for the
172 matching. The alternative algorithm finds all possible matches (at a given
173 point in the subject), and scans the subject just once. However, this algorithm
174 does not return captured substrings. A description of the two matching
175 algorithms and their advantages and disadvantages is given in the
176 .\" HREF
177 \fBpcrematching\fP
178 .\"
179 documentation.
180 .P
181 In addition to the main compiling and matching functions, there are convenience
182 functions for extracting captured substrings from a subject string that is
183 matched by \fBpcre_exec()\fP. They are:
184 .sp
185 \fBpcre_copy_substring()\fP
186 \fBpcre_copy_named_substring()\fP
187 \fBpcre_get_substring()\fP
188 \fBpcre_get_named_substring()\fP
189 \fBpcre_get_substring_list()\fP
190 \fBpcre_get_stringnumber()\fP
191 \fBpcre_get_stringtable_entries()\fP
192 .sp
193 \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also
194 provided, to free the memory used for extracted strings.
195 .P
196 The function \fBpcre_maketables()\fP is used to build a set of character tables
197 in the current locale for passing to \fBpcre_compile()\fP, \fBpcre_exec()\fP,
198 or \fBpcre_dfa_exec()\fP. This is an optional facility that is provided for
199 specialist use. Most commonly, no special tables are passed, in which case
200 internal tables that are generated when PCRE is built are used.
201 .P
202 The function \fBpcre_fullinfo()\fP is used to find out information about a
203 compiled pattern; \fBpcre_info()\fP is an obsolete version that returns only
204 some of the available information, but is retained for backwards compatibility.
205 The function \fBpcre_version()\fP returns a pointer to a string containing the
206 version of PCRE and its date of release.
207 .P
208 The function \fBpcre_refcount()\fP maintains a reference count in a data block
209 containing a compiled pattern. This is provided for the benefit of
210 object-oriented applications.
211 .P
212 The global variables \fBpcre_malloc\fP and \fBpcre_free\fP initially contain
213 the entry points of the standard \fBmalloc()\fP and \fBfree()\fP functions,
214 respectively. PCRE calls the memory management functions via these variables,
215 so a calling program can replace them if it wishes to intercept the calls. This
216 should be done before calling any PCRE functions.
217 .P
218 The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also
219 indirections to memory management functions. These special functions are used
220 only when PCRE is compiled to use the heap for remembering data, instead of
221 recursive function calls, when running the \fBpcre_exec()\fP function. See the
222 .\" HREF
223 \fBpcrebuild\fP
224 .\"
225 documentation for details of how to do this. It is a non-standard way of
226 building PCRE, for use in environments that have limited stacks. Because of the
227 greater use of memory management, it runs more slowly. Separate functions are
228 provided so that special-purpose external code can be used for this case. When
229 used, these functions are always called in a stack-like manner (last obtained,
230 first freed), and always for memory blocks of the same size. There is a
231 discussion about PCRE's stack usage in the
232 .\" HREF
233 \fBpcrestack\fP
234 .\"
235 documentation.
236 .P
237 The global variable \fBpcre_callout\fP initially contains NULL. It can be set
238 by the caller to a "callout" function, which PCRE will then call at specified
239 points during a matching operation. Details are given in the
240 .\" HREF
241 \fBpcrecallout\fP
242 .\"
243 documentation.
244 .
245 .
246 .SH NEWLINES
247 .rs
248 .sp
249 PCRE supports four different conventions for indicating line breaks in
250 strings: a single CR (carriage return) character, a single LF (linefeed)
251 character, the two-character sequence CRLF, or any Unicode newline sequence.
252 The Unicode newline sequences are the three just mentioned, plus the single
253 characters VT (vertical tab, U+000B), FF (formfeed, U+000C), NEL (next line,
254 U+0085), LS (line separator, U+2028), and PS (paragraph separator, U+2029).
255 .P
256 Each of the first three conventions is used by at least one operating system as
257 its standard newline sequence. When PCRE is built, a default can be specified.
258 The default default is LF, which is the Unix standard. When PCRE is run, the
259 default can be overridden, either when a pattern is compiled, or when it is
260 matched.
261 .P
262 In the PCRE documentation the word "newline" is used to mean "the character or
263 pair of characters that indicate a line break". The choice of newline
264 convention affects the handling of the dot, circumflex, and dollar
265 metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
266 recognized line ending sequence, the match position advancement for a
267 non-anchored pattern. The choice of newline convention does not affect the
268 interpretation of the \en or \er escape sequences.
269 .
270 .
271 .SH MULTITHREADING
272 .rs
273 .sp
274 The PCRE functions can be used in multi-threading applications, with the
275 proviso that the memory management functions pointed to by \fBpcre_malloc\fP,
276 \fBpcre_free\fP, \fBpcre_stack_malloc\fP, and \fBpcre_stack_free\fP, and the
277 callout function pointed to by \fBpcre_callout\fP, are shared by all threads.
278 .P
279 The compiled form of a regular expression is not altered during matching, so
280 the same compiled pattern can safely be used by several threads at once.
281 .
282 .
283 .SH "SAVING PRECOMPILED PATTERNS FOR LATER USE"
284 .rs
285 .sp
286 The compiled form of a regular expression can be saved and re-used at a later
287 time, possibly by a different program, and even on a host other than the one on
288 which it was compiled. Details are given in the
289 .\" HREF
290 \fBpcreprecompile\fP
291 .\"
292 documentation.
293 .
294 .
295 .SH "CHECKING BUILD-TIME OPTIONS"
296 .rs
297 .sp
298 .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
299 .PP
300 The function \fBpcre_config()\fP makes it possible for a PCRE client to
301 discover which optional features have been compiled into the PCRE library. The
302 .\" HREF
303 \fBpcrebuild\fP
304 .\"
305 documentation has more details about these optional features.
306 .P
307 The first argument for \fBpcre_config()\fP is an integer, specifying which
308 information is required; the second argument is a pointer to a variable into
309 which the information is placed. The following information is available:
310 .sp
311 PCRE_CONFIG_UTF8
312 .sp
313 The output is an integer that is set to one if UTF-8 support is available;
314 otherwise it is set to zero.
315 .sp
316 PCRE_CONFIG_UNICODE_PROPERTIES
317 .sp
318 The output is an integer that is set to one if support for Unicode character
319 properties is available; otherwise it is set to zero.
320 .sp
321 PCRE_CONFIG_NEWLINE
322 .sp
323 The output is an integer whose value specifies the default character sequence
324 that is recognized as meaning "newline". The four values that are supported
325 are: 10 for LF, 13 for CR, 3338 for CRLF, and -1 for ANY. The default should
326 normally be the standard sequence for your operating system.
327 .sp
328 PCRE_CONFIG_LINK_SIZE
329 .sp
330 The output is an integer that contains the number of bytes used for internal
331 linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values
332 allow larger regular expressions to be compiled, at the expense of slower
333 matching. The default value of 2 is sufficient for all but the most massive
334 patterns, since it allows the compiled pattern to be up to 64K in size.
335 .sp
336 PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
337 .sp
338 The output is an integer that contains the threshold above which the POSIX
339 interface uses \fBmalloc()\fP for output vectors. Further details are given in
340 the
341 .\" HREF
342 \fBpcreposix\fP
343 .\"
344 documentation.
345 .sp
346 PCRE_CONFIG_MATCH_LIMIT
347 .sp
348 The output is an integer that gives the default limit for the number of
349 internal matching function calls in a \fBpcre_exec()\fP execution. Further
350 details are given with \fBpcre_exec()\fP below.
351 .sp
352 PCRE_CONFIG_MATCH_LIMIT_RECURSION
353 .sp
354 The output is an integer that gives the default limit for the depth of
355 recursion when calling the internal matching function in a \fBpcre_exec()\fP
356 execution. Further details are given with \fBpcre_exec()\fP below.
357 .sp
358 PCRE_CONFIG_STACKRECURSE
359 .sp
360 The output is an integer that is set to one if internal recursion when running
361 \fBpcre_exec()\fP is implemented by recursive function calls that use the stack
362 to remember their state. This is the usual way that PCRE is compiled. The
363 output is zero if PCRE was compiled to use blocks of data on the heap instead
364 of recursive function calls. In this case, \fBpcre_stack_malloc\fP and
365 \fBpcre_stack_free\fP are called to manage memory blocks on the heap, thus
366 avoiding the use of the stack.
367 .
368 .
369 .SH "COMPILING A PATTERN"
370 .rs
371 .sp
372 .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
373 .ti +5n
374 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
375 .ti +5n
376 .B const unsigned char *\fItableptr\fP);
377 .sp
378 .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
379 .ti +5n
380 .B int *\fIerrorcodeptr\fP,
381 .ti +5n
382 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
383 .ti +5n
384 .B const unsigned char *\fItableptr\fP);
385 .P
386 Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be
387 called to compile a pattern into an internal form. The only difference between
388 the two interfaces is that \fBpcre_compile2()\fP has an additional argument,
389 \fIerrorcodeptr\fP, via which a numerical error code can be returned.
390 .P
391 The pattern is a C string terminated by a binary zero, and is passed in the
392 \fIpattern\fP argument. A pointer to a single block of memory that is obtained
393 via \fBpcre_malloc\fP is returned. This contains the compiled code and related
394 data. The \fBpcre\fP type is defined for the returned block; this is a typedef
395 for a structure whose contents are not externally defined. It is up to the
396 caller to free the memory (via \fBpcre_free\fP) when it is no longer required.
397 .P
398 Although the compiled code of a PCRE regex is relocatable, that is, it does not
399 depend on memory location, the complete \fBpcre\fP data block is not
400 fully relocatable, because it may contain a copy of the \fItableptr\fP
401 argument, which is an address (see below).
402 .P
403 The \fIoptions\fP argument contains various bit settings that affect the
404 compilation. It should be zero if no options are required. The available
405 options are described below. Some of them, in particular, those that are
406 compatible with Perl, can also be set and unset from within the pattern (see
407 the detailed description in the
408 .\" HREF
409 \fBpcrepattern\fP
410 .\"
411 documentation). For these options, the contents of the \fIoptions\fP argument
412 specifies their initial settings at the start of compilation and execution. The
413 PCRE_ANCHORED and PCRE_NEWLINE_\fIxxx\fP options can be set at the time of
414 matching as well as at compile time.
415 .P
416 If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
417 Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
418 NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual
419 error message. This is a static string that is part of the library. You must
420 not try to free it. The offset from the start of the pattern to the character
421 where the error was discovered is placed in the variable pointed to by
422 \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.
423 .P
424 If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the
425 \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is
426 returned via this argument in the event of an error. This is in addition to the
427 textual error message. Error codes and messages are listed below.
428 .P
429 If the final argument, \fItableptr\fP, is NULL, PCRE uses a default set of
430 character tables that are built when PCRE is compiled, using the default C
431 locale. Otherwise, \fItableptr\fP must be an address that is the result of a
432 call to \fBpcre_maketables()\fP. This value is stored with the compiled
433 pattern, and used again by \fBpcre_exec()\fP, unless another table pointer is
434 passed to it. For more discussion, see the section on locale support below.
435 .P
436 This code fragment shows a typical straightforward call to \fBpcre_compile()\fP:
437 .sp
438 pcre *re;
439 const char *error;
440 int erroffset;
441 re = pcre_compile(
442 "^A.*Z", /* the pattern */
443 0, /* default options */
444 &error, /* for error message */
445 &erroffset, /* for error offset */
446 NULL); /* use default character tables */
447 .sp
448 The following names for option bits are defined in the \fBpcre.h\fP header
449 file:
450 .sp
451 PCRE_ANCHORED
452 .sp
453 If this bit is set, the pattern is forced to be "anchored", that is, it is
454 constrained to match only at the first matching point in the string that is
455 being searched (the "subject string"). This effect can also be achieved by
456 appropriate constructs in the pattern itself, which is the only way to do it in
457 Perl.
458 .sp
459 PCRE_AUTO_CALLOUT
460 .sp
461 If this bit is set, \fBpcre_compile()\fP automatically inserts callout items,
462 all with number 255, before each pattern item. For discussion of the callout
463 facility, see the
464 .\" HREF
465 \fBpcrecallout\fP
466 .\"
467 documentation.
468 .sp
469 PCRE_CASELESS
470 .sp
471 If this bit is set, letters in the pattern match both upper and lower case
472 letters. It is equivalent to Perl's /i option, and it can be changed within a
473 pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the
474 concept of case for characters whose values are less than 128, so caseless
475 matching is always possible. For characters with higher values, the concept of
476 case is supported if PCRE is compiled with Unicode property support, but not
477 otherwise. If you want to use caseless matching for characters 128 and above,
478 you must ensure that PCRE is compiled with Unicode property support as well as
479 with UTF-8 support.
480 .sp
481 PCRE_DOLLAR_ENDONLY
482 .sp
483 If this bit is set, a dollar metacharacter in the pattern matches only at the
484 end of the subject string. Without this option, a dollar also matches
485 immediately before a newline at the end of the string (but not before any other
486 newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set.
487 There is no equivalent to this option in Perl, and no way to set it within a
488 pattern.
489 .sp
490 PCRE_DOTALL
491 .sp
492 If this bit is set, a dot metacharater in the pattern matches all characters,
493 including those that indicate newline. Without it, a dot does not match when
494 the current position is at a newline. This option is equivalent to Perl's /s
495 option, and it can be changed within a pattern by a (?s) option setting. A
496 negative class such as [^a] always matches newline characters, independent of
497 the setting of this option.
498 .sp
499 PCRE_DUPNAMES
500 .sp
501 If this bit is set, names used to identify capturing subpatterns need not be
502 unique. This can be helpful for certain types of pattern when it is known that
503 only one instance of the named subpattern can ever be matched. There are more
504 details of named subpatterns below; see also the
505 .\" HREF
506 \fBpcrepattern\fP
507 .\"
508 documentation.
509 .sp
510 PCRE_EXTENDED
511 .sp
512 If this bit is set, whitespace data characters in the pattern are totally
513 ignored except when escaped or inside a character class. Whitespace does not
514 include the VT character (code 11). In addition, characters between an
515 unescaped # outside a character class and the next newline, inclusive, are also
516 ignored. This is equivalent to Perl's /x option, and it can be changed within a
517 pattern by a (?x) option setting.
518 .P
519 This option makes it possible to include comments inside complicated patterns.
520 Note, however, that this applies only to data characters. Whitespace characters
521 may never appear within special character sequences in a pattern, for example
522 within the sequence (?( which introduces a conditional subpattern.
523 .sp
524 PCRE_EXTRA
525 .sp
526 This option was invented in order to turn on additional functionality of PCRE
527 that is incompatible with Perl, but it is currently of very little use. When
528 set, any backslash in a pattern that is followed by a letter that has no
529 special meaning causes an error, thus reserving these combinations for future
530 expansion. By default, as in Perl, a backslash followed by a letter with no
531 special meaning is treated as a literal. (Perl can, however, be persuaded to
532 give a warning for this.) There are at present no other features controlled by
533 this option. It can also be set by a (?X) option setting within a pattern.
534 .sp
535 PCRE_FIRSTLINE
536 .sp
537 If this option is set, an unanchored pattern is required to match before or at
538 the first newline in the subject string, though the matched text may continue
539 over the newline.
540 .sp
541 PCRE_MULTILINE
542 .sp
543 By default, PCRE treats the subject string as consisting of a single line of
544 characters (even if it actually contains newlines). The "start of line"
545 metacharacter (^) matches only at the start of the string, while the "end of
546 line" metacharacter ($) matches only at the end of the string, or before a
547 terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as
548 Perl.
549 .P
550 When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
551 match immediately following or immediately before internal newlines in the
552 subject string, respectively, as well as at the very start and end. This is
553 equivalent to Perl's /m option, and it can be changed within a pattern by a
554 (?m) option setting. If there are no newlines in a subject string, or no
555 occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
556 .sp
557 PCRE_NEWLINE_CR
558 PCRE_NEWLINE_LF
559 PCRE_NEWLINE_CRLF
560 PCRE_NEWLINE_ANY
561 .sp
562 These options override the default newline definition that was chosen when PCRE
563 was built. Setting the first or the second specifies that a newline is
564 indicated by a single character (CR or LF, respectively). Setting
565 PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
566 CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline
567 sequence should be recognized. The Unicode newline sequences are the three just
568 mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
569 U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
570 (paragraph separator, U+2029). The last two are recognized only in UTF-8 mode.
571 .P
572 The newline setting in the options word uses three bits that are treated
573 as a number, giving eight possibilities. Currently only five are used (default
574 plus the four values above). This means that if you set more than one newline
575 option, the combination may or may not be sensible. For example,
576 PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
577 other combinations yield unused numbers and cause an error.
578 .P
579 The only time that a line break is specially recognized when compiling a
580 pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
581 class is encountered. This indicates a comment that lasts until after the next
582 line break sequence. In other circumstances, line break sequences are treated
583 as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
584 as whitespace characters and are therefore ignored.
585 .P
586 The newline option that is set at compile time becomes the default that is used
587 for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
588 .sp
589 PCRE_NO_AUTO_CAPTURE
590 .sp
591 If this option is set, it disables the use of numbered capturing parentheses in
592 the pattern. Any opening parenthesis that is not followed by ? behaves as if it
593 were followed by ?: but named parentheses can still be used for capturing (and
594 they acquire numbers in the usual way). There is no equivalent of this option
595 in Perl.
596 .sp
597 PCRE_UNGREEDY
598 .sp
599 This option inverts the "greediness" of the quantifiers so that they are not
600 greedy by default, but become greedy if followed by "?". It is not compatible
601 with Perl. It can also be set by a (?U) option setting within the pattern.
602 .sp
603 PCRE_UTF8
604 .sp
605 This option causes PCRE to regard both the pattern and the subject as strings
606 of UTF-8 characters instead of single-byte character strings. However, it is
607 available only when PCRE is built to include UTF-8 support. If not, the use
608 of this option provokes an error. Details of how this option changes the
609 behaviour of PCRE are given in the
610 .\" HTML <a href="pcre.html#utf8support">
611 .\" </a>
612 section on UTF-8 support
613 .\"
614 in the main
615 .\" HREF
616 \fBpcre\fP
617 .\"
618 page.
619 .sp
620 PCRE_NO_UTF8_CHECK
621 .sp
622 When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
623 automatically checked. If an invalid UTF-8 sequence of bytes is found,
624 \fBpcre_compile()\fP returns an error. If you already know that your pattern is
625 valid, and you want to skip this check for performance reasons, you can set the
626 PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid
627 UTF-8 string as a pattern is undefined. It may cause your program to crash.
628 Note that this option can also be passed to \fBpcre_exec()\fP and
629 \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject
630 strings.
631 .
632 .
633 .SH "COMPILATION ERROR CODES"
634 .rs
635 .sp
636 The following table lists the error codes than may be returned by
637 \fBpcre_compile2()\fP, along with the error messages that may be returned by
638 both compiling functions. As PCRE has developed, some error codes have fallen
639 out of use. To avoid confusion, they have not been re-used.
640 .sp
641 0 no error
642 1 \e at end of pattern
643 2 \ec at end of pattern
644 3 unrecognized character follows \e
645 4 numbers out of order in {} quantifier
646 5 number too big in {} quantifier
647 6 missing terminating ] for character class
648 7 invalid escape sequence in character class
649 8 range out of order in character class
650 9 nothing to repeat
651 10 [this code is not in use]
652 11 internal error: unexpected repeat
653 12 unrecognized character after (?
654 13 POSIX named classes are supported only within a class
655 14 missing )
656 15 reference to non-existent subpattern
657 16 erroffset passed as NULL
658 17 unknown option bit(s) set
659 18 missing ) after comment
660 19 [this code is not in use]
661 20 regular expression too large
662 21 failed to get memory
663 22 unmatched parentheses
664 23 internal error: code overflow
665 24 unrecognized character after (?<
666 25 lookbehind assertion is not fixed length
667 26 malformed number or name after (?(
668 27 conditional group contains more than two branches
669 28 assertion expected after (?(
670 29 (?R or (?digits must be followed by )
671 30 unknown POSIX class name
672 31 POSIX collating elements are not supported
673 32 this version of PCRE is not compiled with PCRE_UTF8 support
674 33 [this code is not in use]
675 34 character value in \ex{...} sequence is too large
676 35 invalid condition (?(0)
677 36 \eC not allowed in lookbehind assertion
678 37 PCRE does not support \eL, \el, \eN, \eU, or \eu
679 38 number after (?C is > 255
680 39 closing ) for (?C expected
681 40 recursive call could loop indefinitely
682 41 unrecognized character after (?P
683 42 syntax error in subpattern name (missing terminator)
684 43 two named subpatterns have the same name
685 44 invalid UTF-8 string
686 45 support for \eP, \ep, and \eX has not been compiled
687 46 malformed \eP or \ep sequence
688 47 unknown property name after \eP or \ep
689 48 subpattern name is too long (maximum 32 characters)
690 49 too many named subpatterns (maximum 10,000)
691 50 repeated subpattern is too long
692 51 octal value is greater than \e377 (not in UTF-8 mode)
693 52 internal error: overran compiling workspace
694 53 internal error: previously-checked referenced subpattern not found
695 54 DEFINE group contains more than one branch
696 55 repeating a DEFINE group is not allowed
697 56 inconsistent NEWLINE options"
698 .
699 .
700 .SH "STUDYING A PATTERN"
701 .rs
702 .sp
703 .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP
704 .ti +5n
705 .B const char **\fIerrptr\fP);
706 .PP
707 If a compiled pattern is going to be used several times, it is worth spending
708 more time analyzing it in order to speed up the time taken for matching. The
709 function \fBpcre_study()\fP takes a pointer to a compiled pattern as its first
710 argument. If studying the pattern produces additional information that will
711 help speed up matching, \fBpcre_study()\fP returns a pointer to a
712 \fBpcre_extra\fP block, in which the \fIstudy_data\fP field points to the
713 results of the study.
714 .P
715 The returned value from \fBpcre_study()\fP can be passed directly to
716 \fBpcre_exec()\fP. However, a \fBpcre_extra\fP block also contains other
717 fields that can be set by the caller before the block is passed; these are
718 described
719 .\" HTML <a href="#extradata">
720 .\" </a>
721 below
722 .\"
723 in the section on matching a pattern.
724 .P
725 If studying the pattern does not produce any additional information
726 \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program
727 wants to pass any of the other fields to \fBpcre_exec()\fP, it must set up its
728 own \fBpcre_extra\fP block.
729 .P
730 The second argument of \fBpcre_study()\fP contains option bits. At present, no
731 options are defined, and this argument should always be zero.
732 .P
733 The third argument for \fBpcre_study()\fP is a pointer for an error message. If
734 studying succeeds (even if no data is returned), the variable it points to is
735 set to NULL. Otherwise it is set to point to a textual error message. This is a
736 static string that is part of the library. You must not try to free it. You
737 should test the error pointer for NULL after calling \fBpcre_study()\fP, to be
738 sure that it has run successfully.
739 .P
740 This is a typical call to \fBpcre_study\fP():
741 .sp
742 pcre_extra *pe;
743 pe = pcre_study(
744 re, /* result of pcre_compile() */
745 0, /* no options exist */
746 &error); /* set to NULL or points to a message */
747 .sp
748 At present, studying a pattern is useful only for non-anchored patterns that do
749 not have a single fixed starting character. A bitmap of possible starting
750 bytes is created.
751 .
752 .
753 .\" HTML <a name="localesupport"></a>
754 .SH "LOCALE SUPPORT"
755 .rs
756 .sp
757 PCRE handles caseless matching, and determines whether characters are letters
758 digits, or whatever, by reference to a set of tables, indexed by character
759 value. When running in UTF-8 mode, this applies only to characters with codes
760 less than 128. Higher-valued codes never match escapes such as \ew or \ed, but
761 can be tested with \ep if PCRE is built with Unicode character property
762 support. The use of locales with Unicode is discouraged.
763 .P
764 An internal set of tables is created in the default C locale when PCRE is
765 built. This is used when the final argument of \fBpcre_compile()\fP is NULL,
766 and is sufficient for many applications. An alternative set of tables can,
767 however, be supplied. These may be created in a different locale from the
768 default. As more and more applications change to using Unicode, the need for
769 this locale support is expected to die away.
770 .P
771 External tables are built by calling the \fBpcre_maketables()\fP function,
772 which has no arguments, in the relevant locale. The result can then be passed
773 to \fBpcre_compile()\fP or \fBpcre_exec()\fP as often as necessary. For
774 example, to build and use tables that are appropriate for the French locale
775 (where accented characters with values greater than 128 are treated as letters),
776 the following code could be used:
777 .sp
778 setlocale(LC_CTYPE, "fr_FR");
779 tables = pcre_maketables();
780 re = pcre_compile(..., tables);
781 .sp
782 When \fBpcre_maketables()\fP runs, the tables are built in memory that is
783 obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure
784 that the memory containing the tables remains available for as long as it is
785 needed.
786 .P
787 The pointer that is passed to \fBpcre_compile()\fP is saved with the compiled
788 pattern, and the same tables are used via this pointer by \fBpcre_study()\fP
789 and normally also by \fBpcre_exec()\fP. Thus, by default, for any single
790 pattern, compilation, studying and matching all happen in the same locale, but
791 different patterns can be compiled in different locales.
792 .P
793 It is possible to pass a table pointer or NULL (indicating the use of the
794 internal tables) to \fBpcre_exec()\fP. Although not intended for this purpose,
795 this facility could be used to match a pattern in a different locale from the
796 one in which it was compiled. Passing table pointers at run time is discussed
797 below in the section on matching a pattern.
798 .
799 .
800 .SH "INFORMATION ABOUT A PATTERN"
801 .rs
802 .sp
803 .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
804 .ti +5n
805 .B int \fIwhat\fP, void *\fIwhere\fP);
806 .PP
807 The \fBpcre_fullinfo()\fP function returns information about a compiled
808 pattern. It replaces the obsolete \fBpcre_info()\fP function, which is
809 nevertheless retained for backwards compability (and is documented below).
810 .P
811 The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled
812 pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if
813 the pattern was not studied. The third argument specifies which piece of
814 information is required, and the fourth argument is a pointer to a variable
815 to receive the data. The yield of the function is zero for success, or one of
816 the following negative numbers:
817 .sp
818 PCRE_ERROR_NULL the argument \fIcode\fP was NULL
819 the argument \fIwhere\fP was NULL
820 PCRE_ERROR_BADMAGIC the "magic number" was not found
821 PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid
822 .sp
823 The "magic number" is placed at the start of each compiled pattern as an simple
824 check against passing an arbitrary memory pointer. Here is a typical call of
825 \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
826 .sp
827 int rc;
828 size_t length;
829 rc = pcre_fullinfo(
830 re, /* result of pcre_compile() */
831 pe, /* result of pcre_study(), or NULL */
832 PCRE_INFO_SIZE, /* what is required */
833 &length); /* where to put the data */
834 .sp
835 The possible values for the third argument are defined in \fBpcre.h\fP, and are
836 as follows:
837 .sp
838 PCRE_INFO_BACKREFMAX
839 .sp
840 Return the number of the highest back reference in the pattern. The fourth
841 argument should point to an \fBint\fP variable. Zero is returned if there are
842 no back references.
843 .sp
844 PCRE_INFO_CAPTURECOUNT
845 .sp
846 Return the number of capturing subpatterns in the pattern. The fourth argument
847 should point to an \fBint\fP variable.
848 .sp
849 PCRE_INFO_DEFAULT_TABLES
850 .sp
851 Return a pointer to the internal default character tables within PCRE. The
852 fourth argument should point to an \fBunsigned char *\fP variable. This
853 information call is provided for internal use by the \fBpcre_study()\fP
854 function. External callers can cause PCRE to use its internal tables by passing
855 a NULL table pointer.
856 .sp
857 PCRE_INFO_FIRSTBYTE
858 .sp
859 Return information about the first byte of any matched string, for a
860 non-anchored pattern. The fourth argument should point to an \fBint\fP
861 variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
862 still recognized for backwards compatibility.)
863 .P
864 If there is a fixed first byte, for example, from a pattern such as
865 (cat|cow|coyote), its value is returned. Otherwise, if either
866 .sp
867 (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
868 starts with "^", or
869 .sp
870 (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
871 (if it were set, the pattern would be anchored),
872 .sp
873 -1 is returned, indicating that the pattern matches only at the start of a
874 subject string or after any newline within the string. Otherwise -2 is
875 returned. For anchored patterns, -2 is returned.
876 .sp
877 PCRE_INFO_FIRSTTABLE
878 .sp
879 If the pattern was studied, and this resulted in the construction of a 256-bit
880 table indicating a fixed set of bytes for the first byte in any matching
881 string, a pointer to the table is returned. Otherwise NULL is returned. The
882 fourth argument should point to an \fBunsigned char *\fP variable.
883 .sp
884 PCRE_INFO_LASTLITERAL
885 .sp
886 Return the value of the rightmost literal byte that must exist in any matched
887 string, other than at its start, if such a byte has been recorded. The fourth
888 argument should point to an \fBint\fP variable. If there is no such byte, -1 is
889 returned. For anchored patterns, a last literal byte is recorded only if it
890 follows something of variable length. For example, for the pattern
891 /^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value
892 is -1.
893 .sp
894 PCRE_INFO_NAMECOUNT
895 PCRE_INFO_NAMEENTRYSIZE
896 PCRE_INFO_NAMETABLE
897 .sp
898 PCRE supports the use of named as well as numbered capturing parentheses. The
899 names are just an additional way of identifying the parentheses, which still
900 acquire numbers. Several convenience functions such as
901 \fBpcre_get_named_substring()\fP are provided for extracting captured
902 substrings by name. It is also possible to extract the data directly, by first
903 converting the name to a number in order to access the correct pointers in the
904 output vector (described with \fBpcre_exec()\fP below). To do the conversion,
905 you need to use the name-to-number map, which is described by these three
906 values.
907 .P
908 The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives
909 the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
910 entry; both of these return an \fBint\fP value. The entry size depends on the
911 length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
912 entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry
913 are the number of the capturing parenthesis, most significant byte first. The
914 rest of the entry is the corresponding name, zero terminated. The names are in
915 alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of
916 their parentheses numbers. For example, consider the following pattern (assume
917 PCRE_EXTENDED is set, so white space - including newlines - is ignored):
918 .sp
919 .\" JOIN
920 (?<date> (?<year>(\ed\ed)?\ed\ed) -
921 (?<month>\ed\ed) - (?<day>\ed\ed) )
922 .sp
923 There are four named subpatterns, so the table has four entries, and each entry
924 in the table is eight bytes long. The table is as follows, with non-printing
925 bytes shows in hexadecimal, and undefined bytes shown as ??:
926 .sp
927 00 01 d a t e 00 ??
928 00 05 d a y 00 ?? ??
929 00 04 m o n t h 00
930 00 02 y e a r 00 ??
931 .sp
932 When writing code to extract data from named subpatterns using the
933 name-to-number map, remember that the length of the entries is likely to be
934 different for each compiled pattern.
935 .sp
936 PCRE_INFO_OPTIONS
937 .sp
938 Return a copy of the options with which the pattern was compiled. The fourth
939 argument should point to an \fBunsigned long int\fP variable. These option bits
940 are those specified in the call to \fBpcre_compile()\fP, modified by any
941 top-level option settings within the pattern itself.
942 .P
943 A pattern is automatically anchored by PCRE if all of its top-level
944 alternatives begin with one of the following:
945 .sp
946 ^ unless PCRE_MULTILINE is set
947 \eA always
948 \eG always
949 .\" JOIN
950 .* if PCRE_DOTALL is set and there are no back
951 references to the subpattern in which .* appears
952 .sp
953 For such patterns, the PCRE_ANCHORED bit is set in the options returned by
954 \fBpcre_fullinfo()\fP.
955 .sp
956 PCRE_INFO_SIZE
957 .sp
958 Return the size of the compiled pattern, that is, the value that was passed as
959 the argument to \fBpcre_malloc()\fP when PCRE was getting memory in which to
960 place the compiled data. The fourth argument should point to a \fBsize_t\fP
961 variable.
962 .sp
963 PCRE_INFO_STUDYSIZE
964 .sp
965 Return the size of the data block pointed to by the \fIstudy_data\fP field in
966 a \fBpcre_extra\fP block. That is, it is the value that was passed to
967 \fBpcre_malloc()\fP when PCRE was getting memory into which to place the data
968 created by \fBpcre_study()\fP. The fourth argument should point to a
969 \fBsize_t\fP variable.
970 .
971 .
972 .SH "OBSOLETE INFO FUNCTION"
973 .rs
974 .sp
975 .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
976 .B *\fIfirstcharptr\fP);
977 .PP
978 The \fBpcre_info()\fP function is now obsolete because its interface is too
979 restrictive to return all the available data about a compiled pattern. New
980 programs should use \fBpcre_fullinfo()\fP instead. The yield of
981 \fBpcre_info()\fP is the number of capturing subpatterns, or one of the
982 following negative numbers:
983 .sp
984 PCRE_ERROR_NULL the argument \fIcode\fP was NULL
985 PCRE_ERROR_BADMAGIC the "magic number" was not found
986 .sp
987 If the \fIoptptr\fP argument is not NULL, a copy of the options with which the
988 pattern was compiled is placed in the integer it points to (see
989 PCRE_INFO_OPTIONS above).
990 .P
991 If the pattern is not anchored and the \fIfirstcharptr\fP argument is not NULL,
992 it is used to pass back information about the first character of any matched
993 string (see PCRE_INFO_FIRSTBYTE above).
994 .
995 .
996 .SH "REFERENCE COUNTS"
997 .rs
998 .sp
999 .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
1000 .PP
1001 The \fBpcre_refcount()\fP function is used to maintain a reference count in the
1002 data block that contains a compiled pattern. It is provided for the benefit of
1003 applications that operate in an object-oriented manner, where different parts
1004 of the application may be using the same compiled pattern, but you want to free
1005 the block when they are all done.
1006 .P
1007 When a pattern is compiled, the reference count field is initialized to zero.
1008 It is changed only by calling this function, whose action is to add the
1009 \fIadjust\fP value (which may be positive or negative) to it. The yield of the
1010 function is the new value. However, the value of the count is constrained to
1011 lie between 0 and 65535, inclusive. If the new value is outside these limits,
1012 it is forced to the appropriate limit value.
1013 .P
1014 Except when it is zero, the reference count is not correctly preserved if a
1015 pattern is compiled on one host and then transferred to a host whose byte-order
1016 is different. (This seems a highly unlikely scenario.)
1017 .
1018 .
1019 .SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION"
1020 .rs
1021 .sp
1022 .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
1023 .ti +5n
1024 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
1025 .ti +5n
1026 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
1027 .P
1028 The function \fBpcre_exec()\fP is called to match a subject string against a
1029 compiled pattern, which is passed in the \fIcode\fP argument. If the
1030 pattern has been studied, the result of the study should be passed in the
1031 \fIextra\fP argument. This function is the main matching facility of the
1032 library, and it operates in a Perl-like manner. For specialist use there is
1033 also an alternative matching function, which is described
1034 .\" HTML <a href="#dfamatch">
1035 .\" </a>
1036 below
1037 .\"
1038 in the section about the \fBpcre_dfa_exec()\fP function.
1039 .P
1040 In most applications, the pattern will have been compiled (and optionally
1041 studied) in the same process that calls \fBpcre_exec()\fP. However, it is
1042 possible to save compiled patterns and study data, and then use them later
1043 in different processes, possibly even on different hosts. For a discussion
1044 about this, see the
1045 .\" HREF
1046 \fBpcreprecompile\fP
1047 .\"
1048 documentation.
1049 .P
1050 Here is an example of a simple call to \fBpcre_exec()\fP:
1051 .sp
1052 int rc;
1053 int ovector[30];
1054 rc = pcre_exec(
1055 re, /* result of pcre_compile() */
1056 NULL, /* we didn't study the pattern */
1057 "some string", /* the subject string */
1058 11, /* the length of the subject string */
1059 0, /* start at offset 0 in the subject */
1060 0, /* default options */
1061 ovector, /* vector of integers for substring information */
1062 30); /* number of elements (NOT size in bytes) */
1063 .
1064 .\" HTML <a name="extradata"></a>
1065 .SS "Extra data for \fBpcre_exec()\fR"
1066 .rs
1067 .sp
1068 If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP
1069 data block. The \fBpcre_study()\fP function returns such a block (when it
1070 doesn't return NULL), but you can also create one for yourself, and pass
1071 additional information in it. The \fBpcre_extra\fP block contains the following
1072 fields (not necessarily in this order):
1073 .sp
1074 unsigned long int \fIflags\fP;
1075 void *\fIstudy_data\fP;
1076 unsigned long int \fImatch_limit\fP;
1077 unsigned long int \fImatch_limit_recursion\fP;
1078 void *\fIcallout_data\fP;
1079 const unsigned char *\fItables\fP;
1080 .sp
1081 The \fIflags\fP field is a bitmap that specifies which of the other fields
1082 are set. The flag bits are:
1083 .sp
1084 PCRE_EXTRA_STUDY_DATA
1085 PCRE_EXTRA_MATCH_LIMIT
1086 PCRE_EXTRA_MATCH_LIMIT_RECURSION
1087 PCRE_EXTRA_CALLOUT_DATA
1088 PCRE_EXTRA_TABLES
1089 .sp
1090 Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the
1091 \fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with
1092 the appropriate flag bit. You should not set this yourself, but you may add to
1093 the block by setting the other fields and their corresponding flag bits.
1094 .P
1095 The \fImatch_limit\fP field provides a means of preventing PCRE from using up a
1096 vast amount of resources when running patterns that are not going to match,
1097 but which have a very large number of possibilities in their search trees. The
1098 classic example is the use of nested unlimited repeats.
1099 .P
1100 Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly
1101 (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the
1102 number of times this function is called during a match, which has the effect of
1103 limiting the amount of backtracking that can take place. For patterns that are
1104 not anchored, the count restarts from zero for each position in the subject
1105 string.
1106 .P
1107 The default value for the limit can be set when PCRE is built; the default
1108 default is 10 million, which handles all but the most extreme cases. You can
1109 override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP
1110 block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in
1111 the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns
1112 PCRE_ERROR_MATCHLIMIT.
1113 .P
1114 The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but
1115 instead of limiting the total number of times that \fBmatch()\fP is called, it
1116 limits the depth of recursion. The recursion depth is a smaller number than the
1117 total number of calls, because not all calls to \fBmatch()\fP are recursive.
1118 This limit is of use only if it is set smaller than \fImatch_limit\fP.
1119 .P
1120 Limiting the recursion depth limits the amount of stack that can be used, or,
1121 when PCRE has been compiled to use memory on the heap instead of the stack, the
1122 amount of heap memory that can be used.
1123 .P
1124 The default value for \fImatch_limit_recursion\fP can be set when PCRE is
1125 built; the default default is the same value as the default for
1126 \fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP
1127 with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and
1128 PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
1129 is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1130 .P
1131 The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,
1132 which is described in the
1133 .\" HREF
1134 \fBpcrecallout\fP
1135 .\"
1136 documentation.
1137 .P
1138 The \fItables\fP field is used to pass a character tables pointer to
1139 \fBpcre_exec()\fP; this overrides the value that is stored with the compiled
1140 pattern. A non-NULL value is stored with the compiled pattern only if custom
1141 tables were supplied to \fBpcre_compile()\fP via its \fItableptr\fP argument.
1142 If NULL is passed to \fBpcre_exec()\fP using this mechanism, it forces PCRE's
1143 internal tables to be used. This facility is helpful when re-using patterns
1144 that have been saved after compiling with an external set of tables, because
1145 the external tables might be at a different address when \fBpcre_exec()\fP is
1146 called. See the
1147 .\" HREF
1148 \fBpcreprecompile\fP
1149 .\"
1150 documentation for a discussion of saving compiled patterns for later use.
1151 .
1152 .SS "Option bits for \fBpcre_exec()\fP"
1153 .rs
1154 .sp
1155 The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be
1156 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1157 PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
1158 .sp
1159 PCRE_ANCHORED
1160 .sp
1161 The PCRE_ANCHORED option limits \fBpcre_exec()\fP to matching at the first
1162 matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out
1163 to be anchored by virtue of its contents, it cannot be made unachored at
1164 matching time.
1165 .sp
1166 PCRE_NEWLINE_CR
1167 PCRE_NEWLINE_LF
1168 PCRE_NEWLINE_CRLF
1169 PCRE_NEWLINE_ANY
1170 .sp
1171 These options override the newline definition that was chosen or defaulted when
1172 the pattern was compiled. For details, see the description of
1173 \fBpcre_compile()\fP above. During matching, the newline choice affects the
1174 behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1175 the way the match position is advanced after a match failure for an unanchored
1176 pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt
1177 fails when the current position is at a CRLF sequence, the match position is
1178 advanced by two characters instead of one, in other words, to after the CRLF.
1179 .sp
1180 PCRE_NOTBOL
1181 .sp
1182 This option specifies that first character of the subject string is not the
1183 beginning of a line, so the circumflex metacharacter should not match before
1184 it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex
1185 never to match. This option affects only the behaviour of the circumflex
1186 metacharacter. It does not affect \eA.
1187 .sp
1188 PCRE_NOTEOL
1189 .sp
1190 This option specifies that the end of the subject string is not the end of a
1191 line, so the dollar metacharacter should not match it nor (except in multiline
1192 mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at
1193 compile time) causes dollar never to match. This option affects only the
1194 behaviour of the dollar metacharacter. It does not affect \eZ or \ez.
1195 .sp
1196 PCRE_NOTEMPTY
1197 .sp
1198 An empty string is not considered to be a valid match if this option is set. If
1199 there are alternatives in the pattern, they are tried. If all the alternatives
1200 match the empty string, the entire match fails. For example, if the pattern
1201 .sp
1202 a?b?
1203 .sp
1204 is applied to a string not beginning with "a" or "b", it matches the empty
1205 string at the start of the subject. With PCRE_NOTEMPTY set, this match is not
1206 valid, so PCRE searches further into the string for occurrences of "a" or "b".
1207 .P
1208 Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case
1209 of a pattern match of the empty string within its \fBsplit()\fP function, and
1210 when using the /g modifier. It is possible to emulate Perl's behaviour after
1211 matching a null string by first trying the match again at the same offset with
1212 PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the
1213 starting offset (see below) and trying an ordinary match again. There is some
1214 code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.
1215 .sp
1216 PCRE_NO_UTF8_CHECK
1217 .sp
1218 When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
1219 string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1220 The value of \fIstartoffset\fP is also checked to ensure that it points to the
1221 start of a UTF-8 character. If an invalid UTF-8 sequence of bytes is found,
1222 \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP
1223 contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.
1224 .P
1225 If you already know that your subject is valid, and you want to skip these
1226 checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
1227 calling \fBpcre_exec()\fP. You might want to do this for the second and
1228 subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find
1229 all the matches in a single subject string. However, you should be sure that
1230 the value of \fIstartoffset\fP points to the start of a UTF-8 character. When
1231 PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a
1232 subject, or a value of \fIstartoffset\fP that does not point to the start of a
1233 UTF-8 character, is undefined. Your program may crash.
1234 .sp
1235 PCRE_PARTIAL
1236 .sp
1237 This option turns on the partial matching feature. If the subject string fails
1238 to match the pattern, but at some point during the matching process the end of
1239 the subject was reached (that is, the subject partially matches the pattern and
1240 the failure to match occurred only because there were not enough subject
1241 characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of
1242 PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what
1243 may appear in the pattern. These are discussed in the
1244 .\" HREF
1245 \fBpcrepartial\fP
1246 .\"
1247 documentation.
1248 .
1249 .SS "The string to be matched by \fBpcre_exec()\fP"
1250 .rs
1251 .sp
1252 The subject string is passed to \fBpcre_exec()\fP as a pointer in
1253 \fIsubject\fP, a length in \fIlength\fP, and a starting byte offset in
1254 \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a
1255 UTF-8 character. Unlike the pattern string, the subject may contain binary zero
1256 bytes. When the starting offset is zero, the search for a match starts at the
1257 beginning of the subject, and this is by far the most common case.
1258 .P
1259 A non-zero starting offset is useful when searching for another match in the
1260 same subject by calling \fBpcre_exec()\fP again after a previous success.
1261 Setting \fIstartoffset\fP differs from just passing over a shortened string and
1262 setting PCRE_NOTBOL in the case of a pattern that begins with any kind of
1263 lookbehind. For example, consider the pattern
1264 .sp
1265 \eBiss\eB
1266 .sp
1267 which finds occurrences of "iss" in the middle of words. (\eB matches only if
1268 the current position in the subject is not a word boundary.) When applied to
1269 the string "Mississipi" the first call to \fBpcre_exec()\fP finds the first
1270 occurrence. If \fBpcre_exec()\fP is called again with just the remainder of the
1271 subject, namely "issipi", it does not match, because \eB is always false at the
1272 start of the subject, which is deemed to be a word boundary. However, if
1273 \fBpcre_exec()\fP is passed the entire string again, but with \fIstartoffset\fP
1274 set to 4, it finds the second occurrence of "iss" because it is able to look
1275 behind the starting point to discover that it is preceded by a letter.
1276 .P
1277 If a non-zero starting offset is passed when the pattern is anchored, one
1278 attempt to match at the given offset is made. This can only succeed if the
1279 pattern does not require the match to be at the start of the subject.
1280 .
1281 .SS "How \fBpcre_exec()\fP returns captured substrings"
1282 .rs
1283 .sp
1284 In general, a pattern matches a certain portion of the subject, and in
1285 addition, further substrings from the subject may be picked out by parts of the
1286 pattern. Following the usage in Jeffrey Friedl's book, this is called
1287 "capturing" in what follows, and the phrase "capturing subpattern" is used for
1288 a fragment of a pattern that picks out a substring. PCRE supports several other
1289 kinds of parenthesized subpattern that do not cause substrings to be captured.
1290 .P
1291 Captured substrings are returned to the caller via a vector of integer offsets
1292 whose address is passed in \fIovector\fP. The number of elements in the vector
1293 is passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP:
1294 this argument is NOT the size of \fIovector\fP in bytes.
1295 .P
1296 The first two-thirds of the vector is used to pass back captured substrings,
1297 each substring using a pair of integers. The remaining third of the vector is
1298 used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1299 and is not available for passing back information. The length passed in
1300 \fIovecsize\fP should always be a multiple of three. If it is not, it is
1301 rounded down.
1302 .P
1303 When a match is successful, information about captured substrings is returned
1304 in pairs of integers, starting at the beginning of \fIovector\fP, and
1305 continuing up to two-thirds of its length at the most. The first element of a
1306 pair is set to the offset of the first character in a substring, and the second
1307 is set to the offset of the first character after the end of a substring. The
1308 first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the
1309 subject string matched by the entire pattern. The next pair is used for the
1310 first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP
1311 is one more than the highest numbered pair that has been set. For example, if
1312 two substrings have been captured, the returned value is 3. If there are no
1313 capturing subpatterns, the return value from a successful match is 1,
1314 indicating that just the first pair of offsets has been set.
1315 .P
1316 If a capturing subpattern is matched repeatedly, it is the last portion of the
1317 string that it matched that is returned.
1318 .P
1319 If the vector is too small to hold all the captured substring offsets, it is
1320 used as far as possible (up to two-thirds of its length), and the function
1321 returns a value of zero. In particular, if the substring offsets are not of
1322 interest, \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and
1323 \fIovecsize\fP as zero. However, if the pattern contains back references and
1324 the \fIovector\fP is not big enough to remember the related substrings, PCRE
1325 has to get additional memory for use during matching. Thus it is usually
1326 advisable to supply an \fIovector\fP.
1327 .P
1328 The \fBpcre_info()\fP function can be used to find out how many capturing
1329 subpatterns there are in a compiled pattern. The smallest size for
1330 \fIovector\fP that will allow for \fIn\fP captured substrings, in addition to
1331 the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3.
1332 .P
1333 It is possible for capturing subpattern number \fIn+1\fP to match some part of
1334 the subject when subpattern \fIn\fP has not been used at all. For example, if
1335 the string "abc" is matched against the pattern (a|(z))(bc) the return from the
1336 function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
1337 happens, both values in the offset pairs corresponding to unused subpatterns
1338 are set to -1.
1339 .P
1340 Offset values that correspond to unused subpatterns at the end of the
1341 expression are also set to -1. For example, if the string "abc" is matched
1342 against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1343 return from the function is 2, because the highest used capturing subpattern
1344 number is 1. However, you can refer to the offsets for the second and third
1345 capturing subpatterns if you wish (assuming the vector is large enough, of
1346 course).
1347 .P
1348 Some convenience functions are provided for extracting the captured substrings
1349 as separate strings. These are described below.
1350 .
1351 .\" HTML <a name="errorlist"></a>
1352 .SS "Error return values from \fBpcre_exec()\fP"
1353 .rs
1354 .sp
1355 If \fBpcre_exec()\fP fails, it returns a negative number. The following are
1356 defined in the header file:
1357 .sp
1358 PCRE_ERROR_NOMATCH (-1)
1359 .sp
1360 The subject string did not match the pattern.
1361 .sp
1362 PCRE_ERROR_NULL (-2)
1363 .sp
1364 Either \fIcode\fP or \fIsubject\fP was passed as NULL, or \fIovector\fP was
1365 NULL and \fIovecsize\fP was not zero.
1366 .sp
1367 PCRE_ERROR_BADOPTION (-3)
1368 .sp
1369 An unrecognized bit was set in the \fIoptions\fP argument.
1370 .sp
1371 PCRE_ERROR_BADMAGIC (-4)
1372 .sp
1373 PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch
1374 the case when it is passed a junk pointer and to detect when a pattern that was
1375 compiled in an environment of one endianness is run in an environment with the
1376 other endianness. This is the error that PCRE gives when the magic number is
1377 not present.
1378 .sp
1379 PCRE_ERROR_UNKNOWN_OPCODE (-5)
1380 .sp
1381 While running the pattern match, an unknown item was encountered in the
1382 compiled pattern. This error could be caused by a bug in PCRE or by overwriting
1383 of the compiled pattern.
1384 .sp
1385 PCRE_ERROR_NOMEMORY (-6)
1386 .sp
1387 If a pattern contains back references, but the \fIovector\fP that is passed to
1388 \fBpcre_exec()\fP is not big enough to remember the referenced substrings, PCRE
1389 gets a block of memory at the start of matching to use for this purpose. If the
1390 call via \fBpcre_malloc()\fP fails, this error is given. The memory is
1391 automatically freed at the end of matching.
1392 .sp
1393 PCRE_ERROR_NOSUBSTRING (-7)
1394 .sp
1395 This error is used by the \fBpcre_copy_substring()\fP,
1396 \fBpcre_get_substring()\fP, and \fBpcre_get_substring_list()\fP functions (see
1397 below). It is never returned by \fBpcre_exec()\fP.
1398 .sp
1399 PCRE_ERROR_MATCHLIMIT (-8)
1400 .sp
1401 The backtracking limit, as specified by the \fImatch_limit\fP field in a
1402 \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1403 above.
1404 .sp
1405 PCRE_ERROR_CALLOUT (-9)
1406 .sp
1407 This error is never generated by \fBpcre_exec()\fP itself. It is provided for
1408 use by callout functions that want to yield a distinctive error code. See the
1409 .\" HREF
1410 \fBpcrecallout\fP
1411 .\"
1412 documentation for details.
1413 .sp
1414 PCRE_ERROR_BADUTF8 (-10)
1415 .sp
1416 A string that contains an invalid UTF-8 byte sequence was passed as a subject.
1417 .sp
1418 PCRE_ERROR_BADUTF8_OFFSET (-11)
1419 .sp
1420 The UTF-8 byte sequence that was passed as a subject was valid, but the value
1421 of \fIstartoffset\fP did not point to the beginning of a UTF-8 character.
1422 .sp
1423 PCRE_ERROR_PARTIAL (-12)
1424 .sp
1425 The subject string did not match, but it did match partially. See the
1426 .\" HREF
1427 \fBpcrepartial\fP
1428 .\"
1429 documentation for details of partial matching.
1430 .sp
1431 PCRE_ERROR_BADPARTIAL (-13)
1432 .sp
1433 The PCRE_PARTIAL option was used with a compiled pattern containing items that
1434 are not supported for partial matching. See the
1435 .\" HREF
1436 \fBpcrepartial\fP
1437 .\"
1438 documentation for details of partial matching.
1439 .sp
1440 PCRE_ERROR_INTERNAL (-14)
1441 .sp
1442 An unexpected internal error has occurred. This error could be caused by a bug
1443 in PCRE or by overwriting of the compiled pattern.
1444 .sp
1445 PCRE_ERROR_BADCOUNT (-15)
1446 .sp
1447 This error is given if the value of the \fIovecsize\fP argument is negative.
1448 .sp
1449 PCRE_ERROR_RECURSIONLIMIT (-21)
1450 .sp
1451 The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1452 field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1453 description above.
1454 .sp
1455 PCRE_ERROR_NULLWSLIMIT (-22)
1456 .sp
1457 When a group that can match an empty substring is repeated with an unbounded
1458 upper limit, the subject position at the start of the group must be remembered,
1459 so that a test for an empty string can be made when the end of the group is
1460 reached. Some workspace is required for this; if it runs out, this error is
1461 given.
1462 .sp
1463 PCRE_ERROR_BADNEWLINE (-23)
1464 .sp
1465 An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1466 .P
1467 Error numbers -16 to -20 are not used by \fBpcre_exec()\fP.
1468 .
1469 .
1470 .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
1471 .rs
1472 .sp
1473 .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1474 .ti +5n
1475 .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
1476 .ti +5n
1477 .B int \fIbuffersize\fP);
1478 .PP
1479 .br
1480 .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1481 .ti +5n
1482 .B int \fIstringcount\fP, int \fIstringnumber\fP,
1483 .ti +5n
1484 .B const char **\fIstringptr\fP);
1485 .PP
1486 .br
1487 .B int pcre_get_substring_list(const char *\fIsubject\fP,
1488 .ti +5n
1489 .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
1490 .PP
1491 Captured substrings can be accessed directly by using the offsets returned by
1492 \fBpcre_exec()\fP in \fIovector\fP. For convenience, the functions
1493 \fBpcre_copy_substring()\fP, \fBpcre_get_substring()\fP, and
1494 \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
1495 as new, separate, zero-terminated strings. These functions identify substrings
1496 by number. The next section describes functions for extracting named
1497 substrings.
1498 .P
1499 A substring that contains a binary zero is correctly extracted and has a
1500 further zero added on the end, but the result is not, of course, a C string.
1501 However, you can process such a string by referring to the length that is
1502 returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
1503 Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
1504 for handling strings containing binary zeros, because the end of the final
1505 string is not independently indicated.
1506 .P
1507 The first three arguments are the same for all three of these functions:
1508 \fIsubject\fP is the subject string that has just been successfully matched,
1509 \fIovector\fP is a pointer to the vector of integer offsets that was passed to
1510 \fBpcre_exec()\fP, and \fIstringcount\fP is the number of substrings that were
1511 captured by the match, including the substring that matched the entire regular
1512 expression. This is the value returned by \fBpcre_exec()\fP if it is greater
1513 than zero. If \fBpcre_exec()\fP returned zero, indicating that it ran out of
1514 space in \fIovector\fP, the value passed as \fIstringcount\fP should be the
1515 number of elements in the vector divided by three.
1516 .P
1517 The functions \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP
1518 extract a single substring, whose number is given as \fIstringnumber\fP. A
1519 value of zero extracts the substring that matched the entire pattern, whereas
1520 higher values extract the captured substrings. For \fBpcre_copy_substring()\fP,
1521 the string is placed in \fIbuffer\fP, whose length is given by
1522 \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is
1523 obtained via \fBpcre_malloc\fP, and its address is returned via
1524 \fIstringptr\fP. The yield of the function is the length of the string, not
1525 including the terminating zero, or one of these error codes:
1526 .sp
1527 PCRE_ERROR_NOMEMORY (-6)
1528 .sp
1529 The buffer was too small for \fBpcre_copy_substring()\fP, or the attempt to get
1530 memory failed for \fBpcre_get_substring()\fP.
1531 .sp
1532 PCRE_ERROR_NOSUBSTRING (-7)
1533 .sp
1534 There is no substring whose number is \fIstringnumber\fP.
1535 .P
1536 The \fBpcre_get_substring_list()\fP function extracts all available substrings
1537 and builds a list of pointers to them. All this is done in a single block of
1538 memory that is obtained via \fBpcre_malloc\fP. The address of the memory block
1539 is returned via \fIlistptr\fP, which is also the start of the list of string
1540 pointers. The end of the list is marked by a NULL pointer. The yield of the
1541 function is zero if all went well, or the error code
1542 .sp
1543 PCRE_ERROR_NOMEMORY (-6)
1544 .sp
1545 if the attempt to get the memory block failed.
1546 .P
1547 When any of these functions encounter a substring that is unset, which can
1548 happen when capturing subpattern number \fIn+1\fP matches some part of the
1549 subject, but subpattern \fIn\fP has not been used at all, they return an empty
1550 string. This can be distinguished from a genuine zero-length substring by
1551 inspecting the appropriate offset in \fIovector\fP, which is negative for unset
1552 substrings.
1553 .P
1554 The two convenience functions \fBpcre_free_substring()\fP and
1555 \fBpcre_free_substring_list()\fP can be used to free the memory returned by
1556 a previous call of \fBpcre_get_substring()\fP or
1557 \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
1558 the function pointed to by \fBpcre_free\fP, which of course could be called
1559 directly from a C program. However, PCRE is used in some situations where it is
1560 linked via a special interface to another programming language that cannot use
1561 \fBpcre_free\fP directly; it is for these cases that the functions are
1562 provided.
1563 .
1564 .
1565 .SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME"
1566 .rs
1567 .sp
1568 .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
1569 .ti +5n
1570 .B const char *\fIname\fP);
1571 .PP
1572 .br
1573 .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1574 .ti +5n
1575 .B const char *\fIsubject\fP, int *\fIovector\fP,
1576 .ti +5n
1577 .B int \fIstringcount\fP, const char *\fIstringname\fP,
1578 .ti +5n
1579 .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1580 .PP
1581 .br
1582 .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1583 .ti +5n
1584 .B const char *\fIsubject\fP, int *\fIovector\fP,
1585 .ti +5n
1586 .B int \fIstringcount\fP, const char *\fIstringname\fP,
1587 .ti +5n
1588 .B const char **\fIstringptr\fP);
1589 .PP
1590 To extract a substring by name, you first have to find associated number.
1591 For example, for this pattern
1592 .sp
1593 (a+)b(?<xxx>\ed+)...
1594 .sp
1595 the number of the subpattern called "xxx" is 2. If the name is known to be
1596 unique (PCRE_DUPNAMES was not set), you can find the number from the name by
1597 calling \fBpcre_get_stringnumber()\fP. The first argument is the compiled
1598 pattern, and the second is the name. The yield of the function is the
1599 subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of
1600 that name.
1601 .P
1602 Given the number, you can extract the substring directly, or use one of the
1603 functions described in the previous section. For convenience, there are also
1604 two functions that do the whole job.
1605 .P
1606 Most of the arguments of \fBpcre_copy_named_substring()\fP and
1607 \fBpcre_get_named_substring()\fP are the same as those for the similarly named
1608 functions that extract by number. As these are described in the previous
1609 section, they are not re-described here. There are just two differences:
1610 .P
1611 First, instead of a substring number, a substring name is given. Second, there
1612 is an extra argument, given at the start, which is a pointer to the compiled
1613 pattern. This is needed in order to gain access to the name-to-number
1614 translation table.
1615 .P
1616 These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1617 then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as
1618 appropriate.
1619 .
1620 .
1621 .SH "DUPLICATE SUBPATTERN NAMES"
1622 .rs
1623 .sp
1624 .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
1625 .ti +5n
1626 .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
1627 .PP
1628 When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
1629 are not required to be unique. Normally, patterns with duplicate names are such
1630 that in any one match, only one of the named subpatterns participates. An
1631 example is shown in the
1632 .\" HREF
1633 \fBpcrepattern\fP
1634 .\"
1635 documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP
1636 and \fBpcre_get_named_substring()\fP return the first substring corresponding
1637 to the given name that is set. If none are set, an empty string is returned.
1638 The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are
1639 associated with the name, but it is not defined which it is.
1640 .sp
1641 If you want to get full details of all captured substrings for a given name,
1642 you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1643 argument is the compiled pattern, and the second is the name. The third and
1644 fourth are pointers to variables which are updated by the function. After it
1645 has run, they point to the first and last entries in the name-to-number table
1646 for the given name. The function itself returns the length of each entry, or
1647 PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1648 described above in the section entitled \fIInformation about a pattern\fP.
1649 Given all the relevant entries for the name, you can extract each of their
1650 numbers, and hence the captured data, if any.
1651 .
1652 .
1653 .SH "FINDING ALL POSSIBLE MATCHES"
1654 .rs
1655 .sp
1656 The traditional matching function uses a similar algorithm to Perl, which stops
1657 when it finds the first match, starting at a given point in the subject. If you
1658 want to find all possible matches, or the longest possible match, consider
1659 using the alternative matching function (see below) instead. If you cannot use
1660 the alternative function, but still need to find all possible matches, you
1661 can kludge it up by making use of the callout facility, which is described in
1662 the
1663 .\" HREF
1664 \fBpcrecallout\fP
1665 .\"
1666 documentation.
1667 .P
1668 What you have to do is to insert a callout right at the end of the pattern.
1669 When your callout function is called, extract and save the current matched
1670 substring. Then return 1, which forces \fBpcre_exec()\fP to backtrack and try
1671 other alternatives. Ultimately, when it runs out of matches, \fBpcre_exec()\fP
1672 will yield PCRE_ERROR_NOMATCH.
1673 .
1674 .
1675 .\" HTML <a name="dfamatch"></a>
1676 .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
1677 .rs
1678 .sp
1679 .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
1680 .ti +5n
1681 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
1682 .ti +5n
1683 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
1684 .ti +5n
1685 .B int *\fIworkspace\fP, int \fIwscount\fP);
1686 .P
1687 The function \fBpcre_dfa_exec()\fP is called to match a subject string against
1688 a compiled pattern, using a matching algorithm that scans the subject string
1689 just once, and does not backtrack. This has different characteristics to the
1690 normal algorithm, and is not compatible with Perl. Some of the features of PCRE
1691 patterns are not supported. Nevertheless, there are times when this kind of
1692 matching can be useful. For a discussion of the two matching algorithms, see
1693 the
1694 .\" HREF
1695 \fBpcrematching\fP
1696 .\"
1697 documentation.
1698 .P
1699 The arguments for the \fBpcre_dfa_exec()\fP function are the same as for
1700 \fBpcre_exec()\fP, plus two extras. The \fIovector\fP argument is used in a
1701 different way, and this is described below. The other common arguments are used
1702 in the same way as for \fBpcre_exec()\fP, so their description is not repeated
1703 here.
1704 .P
1705 The two additional arguments provide workspace for the function. The workspace
1706 vector should contain at least 20 elements. It is used for keeping track of
1707 multiple paths through the pattern tree. More workspace will be needed for
1708 patterns and subjects where there are a lot of potential matches.
1709 .P
1710 Here is an example of a simple call to \fBpcre_dfa_exec()\fP:
1711 .sp
1712 int rc;
1713 int ovector[10];
1714 int wspace[20];
1715 rc = pcre_dfa_exec(
1716 re, /* result of pcre_compile() */
1717 NULL, /* we didn't study the pattern */
1718 "some string", /* the subject string */
1719 11, /* the length of the subject string */
1720 0, /* start at offset 0 in the subject */
1721 0, /* default options */
1722 ovector, /* vector of integers for substring information */
1723 10, /* number of elements (NOT size in bytes) */
1724 wspace, /* working space vector */
1725 20); /* number of elements (NOT size in bytes) */
1726 .
1727 .SS "Option bits for \fBpcre_dfa_exec()\fP"
1728 .rs
1729 .sp
1730 The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be
1731 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1732 PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,
1733 PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are
1734 the same as for \fBpcre_exec()\fP, so their description is not repeated here.
1735 .sp
1736 PCRE_PARTIAL
1737 .sp
1738 This has the same general effect as it does for \fBpcre_exec()\fP, but the
1739 details are slightly different. When PCRE_PARTIAL is set for
1740 \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into
1741 PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no
1742 complete matches, but there is still at least one matching possibility. The
1743 portion of the string that provided the partial match is set as the first
1744 matching string.
1745 .sp
1746 PCRE_DFA_SHORTEST
1747 .sp
1748 Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
1749 soon as it has found one match. Because of the way the alternative algorithm
1750 works, this is necessarily the shortest possible match at the first possible
1751 matching point in the subject string.
1752 .sp
1753 PCRE_DFA_RESTART
1754 .sp
1755 When \fBpcre_dfa_exec()\fP is called with the PCRE_PARTIAL option, and returns
1756 a partial match, it is possible to call it again, with additional subject
1757 characters, and have it continue with the same match. The PCRE_DFA_RESTART
1758 option requests this action; when it is set, the \fIworkspace\fP and
1759 \fIwscount\fP options must reference the same vector as before because data
1760 about the match so far is left in them after a partial match. There is more
1761 discussion of this facility in the
1762 .\" HREF
1763 \fBpcrepartial\fP
1764 .\"
1765 documentation.
1766 .
1767 .SS "Successful returns from \fBpcre_dfa_exec()\fP"
1768 .rs
1769 .sp
1770 When \fBpcre_dfa_exec()\fP succeeds, it may have matched more than one
1771 substring in the subject. Note, however, that all the matches from one run of
1772 the function start at the same point in the subject. The shorter matches are
1773 all initial substrings of the longer matches. For example, if the pattern
1774 .sp
1775 <.*>
1776 .sp
1777 is matched against the string
1778 .sp
1779 This is <something> <something else> <something further> no more
1780 .sp
1781 the three matched strings are
1782 .sp
1783 <something>
1784 <something> <something else>
1785 <something> <something else> <something further>
1786 .sp
1787 On success, the yield of the function is a number greater than zero, which is
1788 the number of matched substrings. The substrings themselves are returned in
1789 \fIovector\fP. Each string uses two elements; the first is the offset to the
1790 start, and the second is the offset to the end. In fact, all the strings have
1791 the same start offset. (Space could have been saved by giving this only once,
1792 but it was decided to retain some compatibility with the way \fBpcre_exec()\fP
1793 returns data, even though the meaning of the strings is different.)
1794 .P
1795 The strings are returned in reverse order of length; that is, the longest
1796 matching string is given first. If there were too many matches to fit into
1797 \fIovector\fP, the yield of the function is zero, and the vector is filled with
1798 the longest matches.
1799 .
1800 .SS "Error returns from \fBpcre_dfa_exec()\fP"
1801 .rs
1802 .sp
1803 The \fBpcre_dfa_exec()\fP function returns a negative number when it fails.
1804 Many of the errors are the same as for \fBpcre_exec()\fP, and these are
1805 described
1806 .\" HTML <a href="#errorlist">
1807 .\" </a>
1808 above.
1809 .\"
1810 There are in addition the following errors that are specific to
1811 \fBpcre_dfa_exec()\fP:
1812 .sp
1813 PCRE_ERROR_DFA_UITEM (-16)
1814 .sp
1815 This return is given if \fBpcre_dfa_exec()\fP encounters an item in the pattern
1816 that it does not support, for instance, the use of \eC or a back reference.
1817 .sp
1818 PCRE_ERROR_DFA_UCOND (-17)
1819 .sp
1820 This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that
1821 uses a back reference for the condition, or a test for recursion in a specific
1822 group. These are not supported.
1823 .sp
1824 PCRE_ERROR_DFA_UMLIMIT (-18)
1825 .sp
1826 This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP
1827 block that contains a setting of the \fImatch_limit\fP field. This is not
1828 supported (it is meaningless).
1829 .sp
1830 PCRE_ERROR_DFA_WSSIZE (-19)
1831 .sp
1832 This return is given if \fBpcre_dfa_exec()\fP runs out of space in the
1833 \fIworkspace\fP vector.
1834 .sp
1835 PCRE_ERROR_DFA_RECURSE (-20)
1836 .sp
1837 When a recursive subpattern is processed, the matching function calls itself
1838 recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1839 error is given if the output vector is not large enough. This should be
1840 extremely rare, as a vector of size 1000 is used.
1841 .
1842 .
1843 .SH "SEE ALSO"
1844 .rs
1845 .sp
1846 \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1847 \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1848 \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1849 .P
1850 .in 0
1851 Last updated: 30 November 2006
1852 .br
1853 Copyright (c) 1997-2006 University of Cambridge.

Properties

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

webmaster@exim.org
ViewVC Help
Powered by ViewVC 1.1.12