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

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

Parent Directory Parent Directory | Revision Log Revision Log


Revision 149 - (show annotations) (download)
Mon Apr 16 15:28:08 2007 UTC (7 years, 6 months ago) by ph10
File size: 79832 byte(s)
Add PCRE_NEWLINE_ANYCRLF.

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 .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
11 .ti +5n
12 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
13 .ti +5n
14 .B const unsigned char *\fItableptr\fP);
15 .PP
16 .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
17 .ti +5n
18 .B int *\fIerrorcodeptr\fP,
19 .ti +5n
20 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
21 .ti +5n
22 .B const unsigned char *\fItableptr\fP);
23 .PP
24 .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,
25 .ti +5n
26 .B const char **\fIerrptr\fP);
27 .PP
28 .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
29 .ti +5n
30 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
31 .ti +5n
32 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
33 .PP
34 .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
35 .ti +5n
36 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
37 .ti +5n
38 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
39 .ti +5n
40 .B int *\fIworkspace\fP, int \fIwscount\fP);
41 .PP
42 .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
43 .ti +5n
44 .B const char *\fIsubject\fP, int *\fIovector\fP,
45 .ti +5n
46 .B int \fIstringcount\fP, const char *\fIstringname\fP,
47 .ti +5n
48 .B char *\fIbuffer\fP, int \fIbuffersize\fP);
49 .PP
50 .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
51 .ti +5n
52 .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
53 .ti +5n
54 .B int \fIbuffersize\fP);
55 .PP
56 .B int pcre_get_named_substring(const pcre *\fIcode\fP,
57 .ti +5n
58 .B const char *\fIsubject\fP, int *\fIovector\fP,
59 .ti +5n
60 .B int \fIstringcount\fP, const char *\fIstringname\fP,
61 .ti +5n
62 .B const char **\fIstringptr\fP);
63 .PP
64 .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
65 .ti +5n
66 .B const char *\fIname\fP);
67 .PP
68 .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
69 .ti +5n
70 .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
71 .PP
72 .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
73 .ti +5n
74 .B int \fIstringcount\fP, int \fIstringnumber\fP,
75 .ti +5n
76 .B const char **\fIstringptr\fP);
77 .PP
78 .B int pcre_get_substring_list(const char *\fIsubject\fP,
79 .ti +5n
80 .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
81 .PP
82 .B void pcre_free_substring(const char *\fIstringptr\fP);
83 .PP
84 .B void pcre_free_substring_list(const char **\fIstringptr\fP);
85 .PP
86 .B const unsigned char *pcre_maketables(void);
87 .PP
88 .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
89 .ti +5n
90 .B int \fIwhat\fP, void *\fIwhere\fP);
91 .PP
92 .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
93 .B *\fIfirstcharptr\fP);
94 .PP
95 .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
96 .PP
97 .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
98 .PP
99 .B char *pcre_version(void);
100 .PP
101 .B void *(*pcre_malloc)(size_t);
102 .PP
103 .B void (*pcre_free)(void *);
104 .PP
105 .B void *(*pcre_stack_malloc)(size_t);
106 .PP
107 .B void (*pcre_stack_free)(void *);
108 .PP
109 .B int (*pcre_callout)(pcre_callout_block *);
110 .
111 .
112 .SH "PCRE API OVERVIEW"
113 .rs
114 .sp
115 PCRE has its own native API, which is described in this document. There are
116 also some wrapper functions that correspond to the POSIX regular expression
117 API. These are described in the
118 .\" HREF
119 \fBpcreposix\fP
120 .\"
121 documentation. Both of these APIs define a set of C function calls. A C++
122 wrapper is distributed with PCRE. It is documented in the
123 .\" HREF
124 \fBpcrecpp\fP
125 .\"
126 page.
127 .P
128 The native API C function prototypes are defined in the header file
129 \fBpcre.h\fP, and on Unix systems the library itself is called \fBlibpcre\fP.
130 It can normally be accessed by adding \fB-lpcre\fP to the command for linking
131 an application that uses PCRE. The header file defines the macros PCRE_MAJOR
132 and PCRE_MINOR to contain the major and minor release numbers for the library.
133 Applications can use these to include support for different releases of PCRE.
134 .P
135 The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,
136 and \fBpcre_exec()\fP are used for compiling and matching regular expressions
137 in a Perl-compatible manner. A sample program that demonstrates the simplest
138 way of using them is provided in the file called \fIpcredemo.c\fP in the source
139 distribution. The
140 .\" HREF
141 \fBpcresample\fP
142 .\"
143 documentation describes how to run it.
144 .P
145 A second matching function, \fBpcre_dfa_exec()\fP, which is not
146 Perl-compatible, is also provided. This uses a different algorithm for the
147 matching. The alternative algorithm finds all possible matches (at a given
148 point in the subject), and scans the subject just once. However, this algorithm
149 does not return captured substrings. A description of the two matching
150 algorithms and their advantages and disadvantages is given in the
151 .\" HREF
152 \fBpcrematching\fP
153 .\"
154 documentation.
155 .P
156 In addition to the main compiling and matching functions, there are convenience
157 functions for extracting captured substrings from a subject string that is
158 matched by \fBpcre_exec()\fP. They are:
159 .sp
160 \fBpcre_copy_substring()\fP
161 \fBpcre_copy_named_substring()\fP
162 \fBpcre_get_substring()\fP
163 \fBpcre_get_named_substring()\fP
164 \fBpcre_get_substring_list()\fP
165 \fBpcre_get_stringnumber()\fP
166 \fBpcre_get_stringtable_entries()\fP
167 .sp
168 \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also
169 provided, to free the memory used for extracted strings.
170 .P
171 The function \fBpcre_maketables()\fP is used to build a set of character tables
172 in the current locale for passing to \fBpcre_compile()\fP, \fBpcre_exec()\fP,
173 or \fBpcre_dfa_exec()\fP. This is an optional facility that is provided for
174 specialist use. Most commonly, no special tables are passed, in which case
175 internal tables that are generated when PCRE is built are used.
176 .P
177 The function \fBpcre_fullinfo()\fP is used to find out information about a
178 compiled pattern; \fBpcre_info()\fP is an obsolete version that returns only
179 some of the available information, but is retained for backwards compatibility.
180 The function \fBpcre_version()\fP returns a pointer to a string containing the
181 version of PCRE and its date of release.
182 .P
183 The function \fBpcre_refcount()\fP maintains a reference count in a data block
184 containing a compiled pattern. This is provided for the benefit of
185 object-oriented applications.
186 .P
187 The global variables \fBpcre_malloc\fP and \fBpcre_free\fP initially contain
188 the entry points of the standard \fBmalloc()\fP and \fBfree()\fP functions,
189 respectively. PCRE calls the memory management functions via these variables,
190 so a calling program can replace them if it wishes to intercept the calls. This
191 should be done before calling any PCRE functions.
192 .P
193 The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also
194 indirections to memory management functions. These special functions are used
195 only when PCRE is compiled to use the heap for remembering data, instead of
196 recursive function calls, when running the \fBpcre_exec()\fP function. See the
197 .\" HREF
198 \fBpcrebuild\fP
199 .\"
200 documentation for details of how to do this. It is a non-standard way of
201 building PCRE, for use in environments that have limited stacks. Because of the
202 greater use of memory management, it runs more slowly. Separate functions are
203 provided so that special-purpose external code can be used for this case. When
204 used, these functions are always called in a stack-like manner (last obtained,
205 first freed), and always for memory blocks of the same size. There is a
206 discussion about PCRE's stack usage in the
207 .\" HREF
208 \fBpcrestack\fP
209 .\"
210 documentation.
211 .P
212 The global variable \fBpcre_callout\fP initially contains NULL. It can be set
213 by the caller to a "callout" function, which PCRE will then call at specified
214 points during a matching operation. Details are given in the
215 .\" HREF
216 \fBpcrecallout\fP
217 .\"
218 documentation.
219 .
220 .
221 .SH NEWLINES
222 .rs
223 .sp
224 PCRE supports five different conventions for indicating line breaks in
225 strings: a single CR (carriage return) character, a single LF (linefeed)
226 character, the two-character sequence CRLF, any of the three preceding, or any
227 Unicode newline sequence. The Unicode newline sequences are the three just
228 mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
229 U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
230 (paragraph separator, U+2029).
231 .P
232 Each of the first three conventions is used by at least one operating system as
233 its standard newline sequence. When PCRE is built, a default can be specified.
234 The default default is LF, which is the Unix standard. When PCRE is run, the
235 default can be overridden, either when a pattern is compiled, or when it is
236 matched.
237 .P
238 In the PCRE documentation the word "newline" is used to mean "the character or
239 pair of characters that indicate a line break". The choice of newline
240 convention affects the handling of the dot, circumflex, and dollar
241 metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
242 recognized line ending sequence, the match position advancement for a
243 non-anchored pattern. The choice of newline convention does not affect the
244 interpretation of the \en or \er escape sequences.
245 .
246 .
247 .SH MULTITHREADING
248 .rs
249 .sp
250 The PCRE functions can be used in multi-threading applications, with the
251 proviso that the memory management functions pointed to by \fBpcre_malloc\fP,
252 \fBpcre_free\fP, \fBpcre_stack_malloc\fP, and \fBpcre_stack_free\fP, and the
253 callout function pointed to by \fBpcre_callout\fP, are shared by all threads.
254 .P
255 The compiled form of a regular expression is not altered during matching, so
256 the same compiled pattern can safely be used by several threads at once.
257 .
258 .
259 .SH "SAVING PRECOMPILED PATTERNS FOR LATER USE"
260 .rs
261 .sp
262 The compiled form of a regular expression can be saved and re-used at a later
263 time, possibly by a different program, and even on a host other than the one on
264 which it was compiled. Details are given in the
265 .\" HREF
266 \fBpcreprecompile\fP
267 .\"
268 documentation.
269 .
270 .
271 .SH "CHECKING BUILD-TIME OPTIONS"
272 .rs
273 .sp
274 .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
275 .PP
276 The function \fBpcre_config()\fP makes it possible for a PCRE client to
277 discover which optional features have been compiled into the PCRE library. The
278 .\" HREF
279 \fBpcrebuild\fP
280 .\"
281 documentation has more details about these optional features.
282 .P
283 The first argument for \fBpcre_config()\fP is an integer, specifying which
284 information is required; the second argument is a pointer to a variable into
285 which the information is placed. The following information is available:
286 .sp
287 PCRE_CONFIG_UTF8
288 .sp
289 The output is an integer that is set to one if UTF-8 support is available;
290 otherwise it is set to zero.
291 .sp
292 PCRE_CONFIG_UNICODE_PROPERTIES
293 .sp
294 The output is an integer that is set to one if support for Unicode character
295 properties is available; otherwise it is set to zero.
296 .sp
297 PCRE_CONFIG_NEWLINE
298 .sp
299 The output is an integer whose value specifies the default character sequence
300 that is recognized as meaning "newline". The four values that are supported
301 are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. The
302 default should normally be the standard sequence for your operating system.
303 .sp
304 PCRE_CONFIG_LINK_SIZE
305 .sp
306 The output is an integer that contains the number of bytes used for internal
307 linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values
308 allow larger regular expressions to be compiled, at the expense of slower
309 matching. The default value of 2 is sufficient for all but the most massive
310 patterns, since it allows the compiled pattern to be up to 64K in size.
311 .sp
312 PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
313 .sp
314 The output is an integer that contains the threshold above which the POSIX
315 interface uses \fBmalloc()\fP for output vectors. Further details are given in
316 the
317 .\" HREF
318 \fBpcreposix\fP
319 .\"
320 documentation.
321 .sp
322 PCRE_CONFIG_MATCH_LIMIT
323 .sp
324 The output is an integer that gives the default limit for the number of
325 internal matching function calls in a \fBpcre_exec()\fP execution. Further
326 details are given with \fBpcre_exec()\fP below.
327 .sp
328 PCRE_CONFIG_MATCH_LIMIT_RECURSION
329 .sp
330 The output is an integer that gives the default limit for the depth of
331 recursion when calling the internal matching function in a \fBpcre_exec()\fP
332 execution. Further details are given with \fBpcre_exec()\fP below.
333 .sp
334 PCRE_CONFIG_STACKRECURSE
335 .sp
336 The output is an integer that is set to one if internal recursion when running
337 \fBpcre_exec()\fP is implemented by recursive function calls that use the stack
338 to remember their state. This is the usual way that PCRE is compiled. The
339 output is zero if PCRE was compiled to use blocks of data on the heap instead
340 of recursive function calls. In this case, \fBpcre_stack_malloc\fP and
341 \fBpcre_stack_free\fP are called to manage memory blocks on the heap, thus
342 avoiding the use of the stack.
343 .
344 .
345 .SH "COMPILING A PATTERN"
346 .rs
347 .sp
348 .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
349 .ti +5n
350 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
351 .ti +5n
352 .B const unsigned char *\fItableptr\fP);
353 .sp
354 .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
355 .ti +5n
356 .B int *\fIerrorcodeptr\fP,
357 .ti +5n
358 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
359 .ti +5n
360 .B const unsigned char *\fItableptr\fP);
361 .P
362 Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be
363 called to compile a pattern into an internal form. The only difference between
364 the two interfaces is that \fBpcre_compile2()\fP has an additional argument,
365 \fIerrorcodeptr\fP, via which a numerical error code can be returned.
366 .P
367 The pattern is a C string terminated by a binary zero, and is passed in the
368 \fIpattern\fP argument. A pointer to a single block of memory that is obtained
369 via \fBpcre_malloc\fP is returned. This contains the compiled code and related
370 data. The \fBpcre\fP type is defined for the returned block; this is a typedef
371 for a structure whose contents are not externally defined. It is up to the
372 caller to free the memory (via \fBpcre_free\fP) when it is no longer required.
373 .P
374 Although the compiled code of a PCRE regex is relocatable, that is, it does not
375 depend on memory location, the complete \fBpcre\fP data block is not
376 fully relocatable, because it may contain a copy of the \fItableptr\fP
377 argument, which is an address (see below).
378 .P
379 The \fIoptions\fP argument contains various bit settings that affect the
380 compilation. It should be zero if no options are required. The available
381 options are described below. Some of them, in particular, those that are
382 compatible with Perl, can also be set and unset from within the pattern (see
383 the detailed description in the
384 .\" HREF
385 \fBpcrepattern\fP
386 .\"
387 documentation). For these options, the contents of the \fIoptions\fP argument
388 specifies their initial settings at the start of compilation and execution. The
389 PCRE_ANCHORED and PCRE_NEWLINE_\fIxxx\fP options can be set at the time of
390 matching as well as at compile time.
391 .P
392 If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
393 Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
394 NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual
395 error message. This is a static string that is part of the library. You must
396 not try to free it. The offset from the start of the pattern to the character
397 where the error was discovered is placed in the variable pointed to by
398 \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.
399 .P
400 If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the
401 \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is
402 returned via this argument in the event of an error. This is in addition to the
403 textual error message. Error codes and messages are listed below.
404 .P
405 If the final argument, \fItableptr\fP, is NULL, PCRE uses a default set of
406 character tables that are built when PCRE is compiled, using the default C
407 locale. Otherwise, \fItableptr\fP must be an address that is the result of a
408 call to \fBpcre_maketables()\fP. This value is stored with the compiled
409 pattern, and used again by \fBpcre_exec()\fP, unless another table pointer is
410 passed to it. For more discussion, see the section on locale support below.
411 .P
412 This code fragment shows a typical straightforward call to \fBpcre_compile()\fP:
413 .sp
414 pcre *re;
415 const char *error;
416 int erroffset;
417 re = pcre_compile(
418 "^A.*Z", /* the pattern */
419 0, /* default options */
420 &error, /* for error message */
421 &erroffset, /* for error offset */
422 NULL); /* use default character tables */
423 .sp
424 The following names for option bits are defined in the \fBpcre.h\fP header
425 file:
426 .sp
427 PCRE_ANCHORED
428 .sp
429 If this bit is set, the pattern is forced to be "anchored", that is, it is
430 constrained to match only at the first matching point in the string that is
431 being searched (the "subject string"). This effect can also be achieved by
432 appropriate constructs in the pattern itself, which is the only way to do it in
433 Perl.
434 .sp
435 PCRE_AUTO_CALLOUT
436 .sp
437 If this bit is set, \fBpcre_compile()\fP automatically inserts callout items,
438 all with number 255, before each pattern item. For discussion of the callout
439 facility, see the
440 .\" HREF
441 \fBpcrecallout\fP
442 .\"
443 documentation.
444 .sp
445 PCRE_CASELESS
446 .sp
447 If this bit is set, letters in the pattern match both upper and lower case
448 letters. It is equivalent to Perl's /i option, and it can be changed within a
449 pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the
450 concept of case for characters whose values are less than 128, so caseless
451 matching is always possible. For characters with higher values, the concept of
452 case is supported if PCRE is compiled with Unicode property support, but not
453 otherwise. If you want to use caseless matching for characters 128 and above,
454 you must ensure that PCRE is compiled with Unicode property support as well as
455 with UTF-8 support.
456 .sp
457 PCRE_DOLLAR_ENDONLY
458 .sp
459 If this bit is set, a dollar metacharacter in the pattern matches only at the
460 end of the subject string. Without this option, a dollar also matches
461 immediately before a newline at the end of the string (but not before any other
462 newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set.
463 There is no equivalent to this option in Perl, and no way to set it within a
464 pattern.
465 .sp
466 PCRE_DOTALL
467 .sp
468 If this bit is set, a dot metacharater in the pattern matches all characters,
469 including those that indicate newline. Without it, a dot does not match when
470 the current position is at a newline. This option is equivalent to Perl's /s
471 option, and it can be changed within a pattern by a (?s) option setting. A
472 negative class such as [^a] always matches newline characters, independent of
473 the setting of this option.
474 .sp
475 PCRE_DUPNAMES
476 .sp
477 If this bit is set, names used to identify capturing subpatterns need not be
478 unique. This can be helpful for certain types of pattern when it is known that
479 only one instance of the named subpattern can ever be matched. There are more
480 details of named subpatterns below; see also the
481 .\" HREF
482 \fBpcrepattern\fP
483 .\"
484 documentation.
485 .sp
486 PCRE_EXTENDED
487 .sp
488 If this bit is set, whitespace data characters in the pattern are totally
489 ignored except when escaped or inside a character class. Whitespace does not
490 include the VT character (code 11). In addition, characters between an
491 unescaped # outside a character class and the next newline, inclusive, are also
492 ignored. This is equivalent to Perl's /x option, and it can be changed within a
493 pattern by a (?x) option setting.
494 .P
495 This option makes it possible to include comments inside complicated patterns.
496 Note, however, that this applies only to data characters. Whitespace characters
497 may never appear within special character sequences in a pattern, for example
498 within the sequence (?( which introduces a conditional subpattern.
499 .sp
500 PCRE_EXTRA
501 .sp
502 This option was invented in order to turn on additional functionality of PCRE
503 that is incompatible with Perl, but it is currently of very little use. When
504 set, any backslash in a pattern that is followed by a letter that has no
505 special meaning causes an error, thus reserving these combinations for future
506 expansion. By default, as in Perl, a backslash followed by a letter with no
507 special meaning is treated as a literal. (Perl can, however, be persuaded to
508 give a warning for this.) There are at present no other features controlled by
509 this option. It can also be set by a (?X) option setting within a pattern.
510 .sp
511 PCRE_FIRSTLINE
512 .sp
513 If this option is set, an unanchored pattern is required to match before or at
514 the first newline in the subject string, though the matched text may continue
515 over the newline.
516 .sp
517 PCRE_MULTILINE
518 .sp
519 By default, PCRE treats the subject string as consisting of a single line of
520 characters (even if it actually contains newlines). The "start of line"
521 metacharacter (^) matches only at the start of the string, while the "end of
522 line" metacharacter ($) matches only at the end of the string, or before a
523 terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as
524 Perl.
525 .P
526 When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
527 match immediately following or immediately before internal newlines in the
528 subject string, respectively, as well as at the very start and end. This is
529 equivalent to Perl's /m option, and it can be changed within a pattern by a
530 (?m) option setting. If there are no newlines in a subject string, or no
531 occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
532 .sp
533 PCRE_NEWLINE_CR
534 PCRE_NEWLINE_LF
535 PCRE_NEWLINE_CRLF
536 PCRE_NEWLINE_ANYCRLF
537 PCRE_NEWLINE_ANY
538 .sp
539 These options override the default newline definition that was chosen when PCRE
540 was built. Setting the first or the second specifies that a newline is
541 indicated by a single character (CR or LF, respectively). Setting
542 PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
543 CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
544 preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
545 that any Unicode newline sequence should be recognized. The Unicode newline
546 sequences are the three just mentioned, plus the single characters VT (vertical
547 tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
548 separator, U+2028), and PS (paragraph separator, U+2029). The last two are
549 recognized only in UTF-8 mode.
550 .P
551 The newline setting in the options word uses three bits that are treated
552 as a number, giving eight possibilities. Currently only six are used (default
553 plus the five values above). This means that if you set more than one newline
554 option, the combination may or may not be sensible. For example,
555 PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
556 other combinations may yield unused numbers and cause an error.
557 .P
558 The only time that a line break is specially recognized when compiling a
559 pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
560 class is encountered. This indicates a comment that lasts until after the next
561 line break sequence. In other circumstances, line break sequences are treated
562 as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
563 as whitespace characters and are therefore ignored.
564 .P
565 The newline option that is set at compile time becomes the default that is used
566 for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
567 .sp
568 PCRE_NO_AUTO_CAPTURE
569 .sp
570 If this option is set, it disables the use of numbered capturing parentheses in
571 the pattern. Any opening parenthesis that is not followed by ? behaves as if it
572 were followed by ?: but named parentheses can still be used for capturing (and
573 they acquire numbers in the usual way). There is no equivalent of this option
574 in Perl.
575 .sp
576 PCRE_UNGREEDY
577 .sp
578 This option inverts the "greediness" of the quantifiers so that they are not
579 greedy by default, but become greedy if followed by "?". It is not compatible
580 with Perl. It can also be set by a (?U) option setting within the pattern.
581 .sp
582 PCRE_UTF8
583 .sp
584 This option causes PCRE to regard both the pattern and the subject as strings
585 of UTF-8 characters instead of single-byte character strings. However, it is
586 available only when PCRE is built to include UTF-8 support. If not, the use
587 of this option provokes an error. Details of how this option changes the
588 behaviour of PCRE are given in the
589 .\" HTML <a href="pcre.html#utf8support">
590 .\" </a>
591 section on UTF-8 support
592 .\"
593 in the main
594 .\" HREF
595 \fBpcre\fP
596 .\"
597 page.
598 .sp
599 PCRE_NO_UTF8_CHECK
600 .sp
601 When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
602 automatically checked. If an invalid UTF-8 sequence of bytes is found,
603 \fBpcre_compile()\fP returns an error. If you already know that your pattern is
604 valid, and you want to skip this check for performance reasons, you can set the
605 PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid
606 UTF-8 string as a pattern is undefined. It may cause your program to crash.
607 Note that this option can also be passed to \fBpcre_exec()\fP and
608 \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject
609 strings.
610 .
611 .
612 .SH "COMPILATION ERROR CODES"
613 .rs
614 .sp
615 The following table lists the error codes than may be returned by
616 \fBpcre_compile2()\fP, along with the error messages that may be returned by
617 both compiling functions. As PCRE has developed, some error codes have fallen
618 out of use. To avoid confusion, they have not been re-used.
619 .sp
620 0 no error
621 1 \e at end of pattern
622 2 \ec at end of pattern
623 3 unrecognized character follows \e
624 4 numbers out of order in {} quantifier
625 5 number too big in {} quantifier
626 6 missing terminating ] for character class
627 7 invalid escape sequence in character class
628 8 range out of order in character class
629 9 nothing to repeat
630 10 [this code is not in use]
631 11 internal error: unexpected repeat
632 12 unrecognized character after (?
633 13 POSIX named classes are supported only within a class
634 14 missing )
635 15 reference to non-existent subpattern
636 16 erroffset passed as NULL
637 17 unknown option bit(s) set
638 18 missing ) after comment
639 19 [this code is not in use]
640 20 regular expression too large
641 21 failed to get memory
642 22 unmatched parentheses
643 23 internal error: code overflow
644 24 unrecognized character after (?<
645 25 lookbehind assertion is not fixed length
646 26 malformed number or name after (?(
647 27 conditional group contains more than two branches
648 28 assertion expected after (?(
649 29 (?R or (?digits must be followed by )
650 30 unknown POSIX class name
651 31 POSIX collating elements are not supported
652 32 this version of PCRE is not compiled with PCRE_UTF8 support
653 33 [this code is not in use]
654 34 character value in \ex{...} sequence is too large
655 35 invalid condition (?(0)
656 36 \eC not allowed in lookbehind assertion
657 37 PCRE does not support \eL, \el, \eN, \eU, or \eu
658 38 number after (?C is > 255
659 39 closing ) for (?C expected
660 40 recursive call could loop indefinitely
661 41 unrecognized character after (?P
662 42 syntax error in subpattern name (missing terminator)
663 43 two named subpatterns have the same name
664 44 invalid UTF-8 string
665 45 support for \eP, \ep, and \eX has not been compiled
666 46 malformed \eP or \ep sequence
667 47 unknown property name after \eP or \ep
668 48 subpattern name is too long (maximum 32 characters)
669 49 too many named subpatterns (maximum 10,000)
670 50 repeated subpattern is too long
671 51 octal value is greater than \e377 (not in UTF-8 mode)
672 52 internal error: overran compiling workspace
673 53 internal error: previously-checked referenced subpattern not found
674 54 DEFINE group contains more than one branch
675 55 repeating a DEFINE group is not allowed
676 56 inconsistent NEWLINE options"
677 .
678 .
679 .SH "STUDYING A PATTERN"
680 .rs
681 .sp
682 .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP
683 .ti +5n
684 .B const char **\fIerrptr\fP);
685 .PP
686 If a compiled pattern is going to be used several times, it is worth spending
687 more time analyzing it in order to speed up the time taken for matching. The
688 function \fBpcre_study()\fP takes a pointer to a compiled pattern as its first
689 argument. If studying the pattern produces additional information that will
690 help speed up matching, \fBpcre_study()\fP returns a pointer to a
691 \fBpcre_extra\fP block, in which the \fIstudy_data\fP field points to the
692 results of the study.
693 .P
694 The returned value from \fBpcre_study()\fP can be passed directly to
695 \fBpcre_exec()\fP. However, a \fBpcre_extra\fP block also contains other
696 fields that can be set by the caller before the block is passed; these are
697 described
698 .\" HTML <a href="#extradata">
699 .\" </a>
700 below
701 .\"
702 in the section on matching a pattern.
703 .P
704 If studying the pattern does not produce any additional information
705 \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program
706 wants to pass any of the other fields to \fBpcre_exec()\fP, it must set up its
707 own \fBpcre_extra\fP block.
708 .P
709 The second argument of \fBpcre_study()\fP contains option bits. At present, no
710 options are defined, and this argument should always be zero.
711 .P
712 The third argument for \fBpcre_study()\fP is a pointer for an error message. If
713 studying succeeds (even if no data is returned), the variable it points to is
714 set to NULL. Otherwise it is set to point to a textual error message. This is a
715 static string that is part of the library. You must not try to free it. You
716 should test the error pointer for NULL after calling \fBpcre_study()\fP, to be
717 sure that it has run successfully.
718 .P
719 This is a typical call to \fBpcre_study\fP():
720 .sp
721 pcre_extra *pe;
722 pe = pcre_study(
723 re, /* result of pcre_compile() */
724 0, /* no options exist */
725 &error); /* set to NULL or points to a message */
726 .sp
727 At present, studying a pattern is useful only for non-anchored patterns that do
728 not have a single fixed starting character. A bitmap of possible starting
729 bytes is created.
730 .
731 .
732 .\" HTML <a name="localesupport"></a>
733 .SH "LOCALE SUPPORT"
734 .rs
735 .sp
736 PCRE handles caseless matching, and determines whether characters are letters,
737 digits, or whatever, by reference to a set of tables, indexed by character
738 value. When running in UTF-8 mode, this applies only to characters with codes
739 less than 128. Higher-valued codes never match escapes such as \ew or \ed, but
740 can be tested with \ep if PCRE is built with Unicode character property
741 support. The use of locales with Unicode is discouraged. If you are handling
742 characters with codes greater than 128, you should either use UTF-8 and
743 Unicode, or use locales, but not try to mix the two.
744 .P
745 PCRE contains an internal set of tables that are used when the final argument
746 of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
747 Normally, the internal tables recognize only ASCII characters. However, when
748 PCRE is built, it is possible to cause the internal tables to be rebuilt in the
749 default "C" locale of the local system, which may cause them to be different.
750 .P
751 The internal tables can always be overridden by tables supplied by the
752 application that calls PCRE. These may be created in a different locale from
753 the default. As more and more applications change to using Unicode, the need
754 for this locale support is expected to die away.
755 .P
756 External tables are built by calling the \fBpcre_maketables()\fP function,
757 which has no arguments, in the relevant locale. The result can then be passed
758 to \fBpcre_compile()\fP or \fBpcre_exec()\fP as often as necessary. For
759 example, to build and use tables that are appropriate for the French locale
760 (where accented characters with values greater than 128 are treated as letters),
761 the following code could be used:
762 .sp
763 setlocale(LC_CTYPE, "fr_FR");
764 tables = pcre_maketables();
765 re = pcre_compile(..., tables);
766 .sp
767 The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
768 are using Windows, the name for the French locale is "french".
769 .P
770 When \fBpcre_maketables()\fP runs, the tables are built in memory that is
771 obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure
772 that the memory containing the tables remains available for as long as it is
773 needed.
774 .P
775 The pointer that is passed to \fBpcre_compile()\fP is saved with the compiled
776 pattern, and the same tables are used via this pointer by \fBpcre_study()\fP
777 and normally also by \fBpcre_exec()\fP. Thus, by default, for any single
778 pattern, compilation, studying and matching all happen in the same locale, but
779 different patterns can be compiled in different locales.
780 .P
781 It is possible to pass a table pointer or NULL (indicating the use of the
782 internal tables) to \fBpcre_exec()\fP. Although not intended for this purpose,
783 this facility could be used to match a pattern in a different locale from the
784 one in which it was compiled. Passing table pointers at run time is discussed
785 below in the section on matching a pattern.
786 .
787 .
788 .SH "INFORMATION ABOUT A PATTERN"
789 .rs
790 .sp
791 .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
792 .ti +5n
793 .B int \fIwhat\fP, void *\fIwhere\fP);
794 .PP
795 The \fBpcre_fullinfo()\fP function returns information about a compiled
796 pattern. It replaces the obsolete \fBpcre_info()\fP function, which is
797 nevertheless retained for backwards compability (and is documented below).
798 .P
799 The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled
800 pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if
801 the pattern was not studied. The third argument specifies which piece of
802 information is required, and the fourth argument is a pointer to a variable
803 to receive the data. The yield of the function is zero for success, or one of
804 the following negative numbers:
805 .sp
806 PCRE_ERROR_NULL the argument \fIcode\fP was NULL
807 the argument \fIwhere\fP was NULL
808 PCRE_ERROR_BADMAGIC the "magic number" was not found
809 PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid
810 .sp
811 The "magic number" is placed at the start of each compiled pattern as an simple
812 check against passing an arbitrary memory pointer. Here is a typical call of
813 \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
814 .sp
815 int rc;
816 size_t length;
817 rc = pcre_fullinfo(
818 re, /* result of pcre_compile() */
819 pe, /* result of pcre_study(), or NULL */
820 PCRE_INFO_SIZE, /* what is required */
821 &length); /* where to put the data */
822 .sp
823 The possible values for the third argument are defined in \fBpcre.h\fP, and are
824 as follows:
825 .sp
826 PCRE_INFO_BACKREFMAX
827 .sp
828 Return the number of the highest back reference in the pattern. The fourth
829 argument should point to an \fBint\fP variable. Zero is returned if there are
830 no back references.
831 .sp
832 PCRE_INFO_CAPTURECOUNT
833 .sp
834 Return the number of capturing subpatterns in the pattern. The fourth argument
835 should point to an \fBint\fP variable.
836 .sp
837 PCRE_INFO_DEFAULT_TABLES
838 .sp
839 Return a pointer to the internal default character tables within PCRE. The
840 fourth argument should point to an \fBunsigned char *\fP variable. This
841 information call is provided for internal use by the \fBpcre_study()\fP
842 function. External callers can cause PCRE to use its internal tables by passing
843 a NULL table pointer.
844 .sp
845 PCRE_INFO_FIRSTBYTE
846 .sp
847 Return information about the first byte of any matched string, for a
848 non-anchored pattern. The fourth argument should point to an \fBint\fP
849 variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
850 still recognized for backwards compatibility.)
851 .P
852 If there is a fixed first byte, for example, from a pattern such as
853 (cat|cow|coyote), its value is returned. Otherwise, if either
854 .sp
855 (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
856 starts with "^", or
857 .sp
858 (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
859 (if it were set, the pattern would be anchored),
860 .sp
861 -1 is returned, indicating that the pattern matches only at the start of a
862 subject string or after any newline within the string. Otherwise -2 is
863 returned. For anchored patterns, -2 is returned.
864 .sp
865 PCRE_INFO_FIRSTTABLE
866 .sp
867 If the pattern was studied, and this resulted in the construction of a 256-bit
868 table indicating a fixed set of bytes for the first byte in any matching
869 string, a pointer to the table is returned. Otherwise NULL is returned. The
870 fourth argument should point to an \fBunsigned char *\fP variable.
871 .sp
872 PCRE_INFO_LASTLITERAL
873 .sp
874 Return the value of the rightmost literal byte that must exist in any matched
875 string, other than at its start, if such a byte has been recorded. The fourth
876 argument should point to an \fBint\fP variable. If there is no such byte, -1 is
877 returned. For anchored patterns, a last literal byte is recorded only if it
878 follows something of variable length. For example, for the pattern
879 /^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value
880 is -1.
881 .sp
882 PCRE_INFO_NAMECOUNT
883 PCRE_INFO_NAMEENTRYSIZE
884 PCRE_INFO_NAMETABLE
885 .sp
886 PCRE supports the use of named as well as numbered capturing parentheses. The
887 names are just an additional way of identifying the parentheses, which still
888 acquire numbers. Several convenience functions such as
889 \fBpcre_get_named_substring()\fP are provided for extracting captured
890 substrings by name. It is also possible to extract the data directly, by first
891 converting the name to a number in order to access the correct pointers in the
892 output vector (described with \fBpcre_exec()\fP below). To do the conversion,
893 you need to use the name-to-number map, which is described by these three
894 values.
895 .P
896 The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives
897 the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
898 entry; both of these return an \fBint\fP value. The entry size depends on the
899 length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
900 entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry
901 are the number of the capturing parenthesis, most significant byte first. The
902 rest of the entry is the corresponding name, zero terminated. The names are in
903 alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of
904 their parentheses numbers. For example, consider the following pattern (assume
905 PCRE_EXTENDED is set, so white space - including newlines - is ignored):
906 .sp
907 .\" JOIN
908 (?<date> (?<year>(\ed\ed)?\ed\ed) -
909 (?<month>\ed\ed) - (?<day>\ed\ed) )
910 .sp
911 There are four named subpatterns, so the table has four entries, and each entry
912 in the table is eight bytes long. The table is as follows, with non-printing
913 bytes shows in hexadecimal, and undefined bytes shown as ??:
914 .sp
915 00 01 d a t e 00 ??
916 00 05 d a y 00 ?? ??
917 00 04 m o n t h 00
918 00 02 y e a r 00 ??
919 .sp
920 When writing code to extract data from named subpatterns using the
921 name-to-number map, remember that the length of the entries is likely to be
922 different for each compiled pattern.
923 .sp
924 PCRE_INFO_OPTIONS
925 .sp
926 Return a copy of the options with which the pattern was compiled. The fourth
927 argument should point to an \fBunsigned long int\fP variable. These option bits
928 are those specified in the call to \fBpcre_compile()\fP, modified by any
929 top-level option settings within the pattern itself.
930 .P
931 A pattern is automatically anchored by PCRE if all of its top-level
932 alternatives begin with one of the following:
933 .sp
934 ^ unless PCRE_MULTILINE is set
935 \eA always
936 \eG always
937 .\" JOIN
938 .* if PCRE_DOTALL is set and there are no back
939 references to the subpattern in which .* appears
940 .sp
941 For such patterns, the PCRE_ANCHORED bit is set in the options returned by
942 \fBpcre_fullinfo()\fP.
943 .sp
944 PCRE_INFO_SIZE
945 .sp
946 Return the size of the compiled pattern, that is, the value that was passed as
947 the argument to \fBpcre_malloc()\fP when PCRE was getting memory in which to
948 place the compiled data. The fourth argument should point to a \fBsize_t\fP
949 variable.
950 .sp
951 PCRE_INFO_STUDYSIZE
952 .sp
953 Return the size of the data block pointed to by the \fIstudy_data\fP field in
954 a \fBpcre_extra\fP block. That is, it is the value that was passed to
955 \fBpcre_malloc()\fP when PCRE was getting memory into which to place the data
956 created by \fBpcre_study()\fP. The fourth argument should point to a
957 \fBsize_t\fP variable.
958 .
959 .
960 .SH "OBSOLETE INFO FUNCTION"
961 .rs
962 .sp
963 .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
964 .B *\fIfirstcharptr\fP);
965 .PP
966 The \fBpcre_info()\fP function is now obsolete because its interface is too
967 restrictive to return all the available data about a compiled pattern. New
968 programs should use \fBpcre_fullinfo()\fP instead. The yield of
969 \fBpcre_info()\fP is the number of capturing subpatterns, or one of the
970 following negative numbers:
971 .sp
972 PCRE_ERROR_NULL the argument \fIcode\fP was NULL
973 PCRE_ERROR_BADMAGIC the "magic number" was not found
974 .sp
975 If the \fIoptptr\fP argument is not NULL, a copy of the options with which the
976 pattern was compiled is placed in the integer it points to (see
977 PCRE_INFO_OPTIONS above).
978 .P
979 If the pattern is not anchored and the \fIfirstcharptr\fP argument is not NULL,
980 it is used to pass back information about the first character of any matched
981 string (see PCRE_INFO_FIRSTBYTE above).
982 .
983 .
984 .SH "REFERENCE COUNTS"
985 .rs
986 .sp
987 .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
988 .PP
989 The \fBpcre_refcount()\fP function is used to maintain a reference count in the
990 data block that contains a compiled pattern. It is provided for the benefit of
991 applications that operate in an object-oriented manner, where different parts
992 of the application may be using the same compiled pattern, but you want to free
993 the block when they are all done.
994 .P
995 When a pattern is compiled, the reference count field is initialized to zero.
996 It is changed only by calling this function, whose action is to add the
997 \fIadjust\fP value (which may be positive or negative) to it. The yield of the
998 function is the new value. However, the value of the count is constrained to
999 lie between 0 and 65535, inclusive. If the new value is outside these limits,
1000 it is forced to the appropriate limit value.
1001 .P
1002 Except when it is zero, the reference count is not correctly preserved if a
1003 pattern is compiled on one host and then transferred to a host whose byte-order
1004 is different. (This seems a highly unlikely scenario.)
1005 .
1006 .
1007 .SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION"
1008 .rs
1009 .sp
1010 .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
1011 .ti +5n
1012 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
1013 .ti +5n
1014 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
1015 .P
1016 The function \fBpcre_exec()\fP is called to match a subject string against a
1017 compiled pattern, which is passed in the \fIcode\fP argument. If the
1018 pattern has been studied, the result of the study should be passed in the
1019 \fIextra\fP argument. This function is the main matching facility of the
1020 library, and it operates in a Perl-like manner. For specialist use there is
1021 also an alternative matching function, which is described
1022 .\" HTML <a href="#dfamatch">
1023 .\" </a>
1024 below
1025 .\"
1026 in the section about the \fBpcre_dfa_exec()\fP function.
1027 .P
1028 In most applications, the pattern will have been compiled (and optionally
1029 studied) in the same process that calls \fBpcre_exec()\fP. However, it is
1030 possible to save compiled patterns and study data, and then use them later
1031 in different processes, possibly even on different hosts. For a discussion
1032 about this, see the
1033 .\" HREF
1034 \fBpcreprecompile\fP
1035 .\"
1036 documentation.
1037 .P
1038 Here is an example of a simple call to \fBpcre_exec()\fP:
1039 .sp
1040 int rc;
1041 int ovector[30];
1042 rc = pcre_exec(
1043 re, /* result of pcre_compile() */
1044 NULL, /* we didn't study the pattern */
1045 "some string", /* the subject string */
1046 11, /* the length of the subject string */
1047 0, /* start at offset 0 in the subject */
1048 0, /* default options */
1049 ovector, /* vector of integers for substring information */
1050 30); /* number of elements (NOT size in bytes) */
1051 .
1052 .\" HTML <a name="extradata"></a>
1053 .SS "Extra data for \fBpcre_exec()\fR"
1054 .rs
1055 .sp
1056 If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP
1057 data block. The \fBpcre_study()\fP function returns such a block (when it
1058 doesn't return NULL), but you can also create one for yourself, and pass
1059 additional information in it. The \fBpcre_extra\fP block contains the following
1060 fields (not necessarily in this order):
1061 .sp
1062 unsigned long int \fIflags\fP;
1063 void *\fIstudy_data\fP;
1064 unsigned long int \fImatch_limit\fP;
1065 unsigned long int \fImatch_limit_recursion\fP;
1066 void *\fIcallout_data\fP;
1067 const unsigned char *\fItables\fP;
1068 .sp
1069 The \fIflags\fP field is a bitmap that specifies which of the other fields
1070 are set. The flag bits are:
1071 .sp
1072 PCRE_EXTRA_STUDY_DATA
1073 PCRE_EXTRA_MATCH_LIMIT
1074 PCRE_EXTRA_MATCH_LIMIT_RECURSION
1075 PCRE_EXTRA_CALLOUT_DATA
1076 PCRE_EXTRA_TABLES
1077 .sp
1078 Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the
1079 \fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with
1080 the appropriate flag bit. You should not set this yourself, but you may add to
1081 the block by setting the other fields and their corresponding flag bits.
1082 .P
1083 The \fImatch_limit\fP field provides a means of preventing PCRE from using up a
1084 vast amount of resources when running patterns that are not going to match,
1085 but which have a very large number of possibilities in their search trees. The
1086 classic example is the use of nested unlimited repeats.
1087 .P
1088 Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly
1089 (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the
1090 number of times this function is called during a match, which has the effect of
1091 limiting the amount of backtracking that can take place. For patterns that are
1092 not anchored, the count restarts from zero for each position in the subject
1093 string.
1094 .P
1095 The default value for the limit can be set when PCRE is built; the default
1096 default is 10 million, which handles all but the most extreme cases. You can
1097 override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP
1098 block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in
1099 the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns
1100 PCRE_ERROR_MATCHLIMIT.
1101 .P
1102 The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but
1103 instead of limiting the total number of times that \fBmatch()\fP is called, it
1104 limits the depth of recursion. The recursion depth is a smaller number than the
1105 total number of calls, because not all calls to \fBmatch()\fP are recursive.
1106 This limit is of use only if it is set smaller than \fImatch_limit\fP.
1107 .P
1108 Limiting the recursion depth limits the amount of stack that can be used, or,
1109 when PCRE has been compiled to use memory on the heap instead of the stack, the
1110 amount of heap memory that can be used.
1111 .P
1112 The default value for \fImatch_limit_recursion\fP can be set when PCRE is
1113 built; the default default is the same value as the default for
1114 \fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP
1115 with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and
1116 PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
1117 is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1118 .P
1119 The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,
1120 which is described in the
1121 .\" HREF
1122 \fBpcrecallout\fP
1123 .\"
1124 documentation.
1125 .P
1126 The \fItables\fP field is used to pass a character tables pointer to
1127 \fBpcre_exec()\fP; this overrides the value that is stored with the compiled
1128 pattern. A non-NULL value is stored with the compiled pattern only if custom
1129 tables were supplied to \fBpcre_compile()\fP via its \fItableptr\fP argument.
1130 If NULL is passed to \fBpcre_exec()\fP using this mechanism, it forces PCRE's
1131 internal tables to be used. This facility is helpful when re-using patterns
1132 that have been saved after compiling with an external set of tables, because
1133 the external tables might be at a different address when \fBpcre_exec()\fP is
1134 called. See the
1135 .\" HREF
1136 \fBpcreprecompile\fP
1137 .\"
1138 documentation for a discussion of saving compiled patterns for later use.
1139 .
1140 .SS "Option bits for \fBpcre_exec()\fP"
1141 .rs
1142 .sp
1143 The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be
1144 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1145 PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
1146 .sp
1147 PCRE_ANCHORED
1148 .sp
1149 The PCRE_ANCHORED option limits \fBpcre_exec()\fP to matching at the first
1150 matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out
1151 to be anchored by virtue of its contents, it cannot be made unachored at
1152 matching time.
1153 .sp
1154 PCRE_NEWLINE_CR
1155 PCRE_NEWLINE_LF
1156 PCRE_NEWLINE_CRLF
1157 PCRE_NEWLINE_ANYCRLF
1158 PCRE_NEWLINE_ANY
1159 .sp
1160 These options override the newline definition that was chosen or defaulted when
1161 the pattern was compiled. For details, see the description of
1162 \fBpcre_compile()\fP above. During matching, the newline choice affects the
1163 behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1164 the way the match position is advanced after a match failure for an unanchored
1165 pattern. When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is
1166 set, and a match attempt fails when the current position is at a CRLF sequence,
1167 the match position is advanced by two characters instead of one, in other
1168 words, to after the CRLF.
1169 .sp
1170 PCRE_NOTBOL
1171 .sp
1172 This option specifies that first character of the subject string is not the
1173 beginning of a line, so the circumflex metacharacter should not match before
1174 it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex
1175 never to match. This option affects only the behaviour of the circumflex
1176 metacharacter. It does not affect \eA.
1177 .sp
1178 PCRE_NOTEOL
1179 .sp
1180 This option specifies that the end of the subject string is not the end of a
1181 line, so the dollar metacharacter should not match it nor (except in multiline
1182 mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at
1183 compile time) causes dollar never to match. This option affects only the
1184 behaviour of the dollar metacharacter. It does not affect \eZ or \ez.
1185 .sp
1186 PCRE_NOTEMPTY
1187 .sp
1188 An empty string is not considered to be a valid match if this option is set. If
1189 there are alternatives in the pattern, they are tried. If all the alternatives
1190 match the empty string, the entire match fails. For example, if the pattern
1191 .sp
1192 a?b?
1193 .sp
1194 is applied to a string not beginning with "a" or "b", it matches the empty
1195 string at the start of the subject. With PCRE_NOTEMPTY set, this match is not
1196 valid, so PCRE searches further into the string for occurrences of "a" or "b".
1197 .P
1198 Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case
1199 of a pattern match of the empty string within its \fBsplit()\fP function, and
1200 when using the /g modifier. It is possible to emulate Perl's behaviour after
1201 matching a null string by first trying the match again at the same offset with
1202 PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the
1203 starting offset (see below) and trying an ordinary match again. There is some
1204 code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.
1205 .sp
1206 PCRE_NO_UTF8_CHECK
1207 .sp
1208 When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
1209 string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1210 The value of \fIstartoffset\fP is also checked to ensure that it points to the
1211 start of a UTF-8 character. If an invalid UTF-8 sequence of bytes is found,
1212 \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP
1213 contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.
1214 .P
1215 If you already know that your subject is valid, and you want to skip these
1216 checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
1217 calling \fBpcre_exec()\fP. You might want to do this for the second and
1218 subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find
1219 all the matches in a single subject string. However, you should be sure that
1220 the value of \fIstartoffset\fP points to the start of a UTF-8 character. When
1221 PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a
1222 subject, or a value of \fIstartoffset\fP that does not point to the start of a
1223 UTF-8 character, is undefined. Your program may crash.
1224 .sp
1225 PCRE_PARTIAL
1226 .sp
1227 This option turns on the partial matching feature. If the subject string fails
1228 to match the pattern, but at some point during the matching process the end of
1229 the subject was reached (that is, the subject partially matches the pattern and
1230 the failure to match occurred only because there were not enough subject
1231 characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of
1232 PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what
1233 may appear in the pattern. These are discussed in the
1234 .\" HREF
1235 \fBpcrepartial\fP
1236 .\"
1237 documentation.
1238 .
1239 .SS "The string to be matched by \fBpcre_exec()\fP"
1240 .rs
1241 .sp
1242 The subject string is passed to \fBpcre_exec()\fP as a pointer in
1243 \fIsubject\fP, a length in \fIlength\fP, and a starting byte offset in
1244 \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a
1245 UTF-8 character. Unlike the pattern string, the subject may contain binary zero
1246 bytes. When the starting offset is zero, the search for a match starts at the
1247 beginning of the subject, and this is by far the most common case.
1248 .P
1249 A non-zero starting offset is useful when searching for another match in the
1250 same subject by calling \fBpcre_exec()\fP again after a previous success.
1251 Setting \fIstartoffset\fP differs from just passing over a shortened string and
1252 setting PCRE_NOTBOL in the case of a pattern that begins with any kind of
1253 lookbehind. For example, consider the pattern
1254 .sp
1255 \eBiss\eB
1256 .sp
1257 which finds occurrences of "iss" in the middle of words. (\eB matches only if
1258 the current position in the subject is not a word boundary.) When applied to
1259 the string "Mississipi" the first call to \fBpcre_exec()\fP finds the first
1260 occurrence. If \fBpcre_exec()\fP is called again with just the remainder of the
1261 subject, namely "issipi", it does not match, because \eB is always false at the
1262 start of the subject, which is deemed to be a word boundary. However, if
1263 \fBpcre_exec()\fP is passed the entire string again, but with \fIstartoffset\fP
1264 set to 4, it finds the second occurrence of "iss" because it is able to look
1265 behind the starting point to discover that it is preceded by a letter.
1266 .P
1267 If a non-zero starting offset is passed when the pattern is anchored, one
1268 attempt to match at the given offset is made. This can only succeed if the
1269 pattern does not require the match to be at the start of the subject.
1270 .
1271 .SS "How \fBpcre_exec()\fP returns captured substrings"
1272 .rs
1273 .sp
1274 In general, a pattern matches a certain portion of the subject, and in
1275 addition, further substrings from the subject may be picked out by parts of the
1276 pattern. Following the usage in Jeffrey Friedl's book, this is called
1277 "capturing" in what follows, and the phrase "capturing subpattern" is used for
1278 a fragment of a pattern that picks out a substring. PCRE supports several other
1279 kinds of parenthesized subpattern that do not cause substrings to be captured.
1280 .P
1281 Captured substrings are returned to the caller via a vector of integer offsets
1282 whose address is passed in \fIovector\fP. The number of elements in the vector
1283 is passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP:
1284 this argument is NOT the size of \fIovector\fP in bytes.
1285 .P
1286 The first two-thirds of the vector is used to pass back captured substrings,
1287 each substring using a pair of integers. The remaining third of the vector is
1288 used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1289 and is not available for passing back information. The length passed in
1290 \fIovecsize\fP should always be a multiple of three. If it is not, it is
1291 rounded down.
1292 .P
1293 When a match is successful, information about captured substrings is returned
1294 in pairs of integers, starting at the beginning of \fIovector\fP, and
1295 continuing up to two-thirds of its length at the most. The first element of a
1296 pair is set to the offset of the first character in a substring, and the second
1297 is set to the offset of the first character after the end of a substring. The
1298 first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the
1299 subject string matched by the entire pattern. The next pair is used for the
1300 first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP
1301 is one more than the highest numbered pair that has been set. For example, if
1302 two substrings have been captured, the returned value is 3. If there are no
1303 capturing subpatterns, the return value from a successful match is 1,
1304 indicating that just the first pair of offsets has been set.
1305 .P
1306 If a capturing subpattern is matched repeatedly, it is the last portion of the
1307 string that it matched that is returned.
1308 .P
1309 If the vector is too small to hold all the captured substring offsets, it is
1310 used as far as possible (up to two-thirds of its length), and the function
1311 returns a value of zero. In particular, if the substring offsets are not of
1312 interest, \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and
1313 \fIovecsize\fP as zero. However, if the pattern contains back references and
1314 the \fIovector\fP is not big enough to remember the related substrings, PCRE
1315 has to get additional memory for use during matching. Thus it is usually
1316 advisable to supply an \fIovector\fP.
1317 .P
1318 The \fBpcre_info()\fP function can be used to find out how many capturing
1319 subpatterns there are in a compiled pattern. The smallest size for
1320 \fIovector\fP that will allow for \fIn\fP captured substrings, in addition to
1321 the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3.
1322 .P
1323 It is possible for capturing subpattern number \fIn+1\fP to match some part of
1324 the subject when subpattern \fIn\fP has not been used at all. For example, if
1325 the string "abc" is matched against the pattern (a|(z))(bc) the return from the
1326 function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
1327 happens, both values in the offset pairs corresponding to unused subpatterns
1328 are set to -1.
1329 .P
1330 Offset values that correspond to unused subpatterns at the end of the
1331 expression are also set to -1. For example, if the string "abc" is matched
1332 against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1333 return from the function is 2, because the highest used capturing subpattern
1334 number is 1. However, you can refer to the offsets for the second and third
1335 capturing subpatterns if you wish (assuming the vector is large enough, of
1336 course).
1337 .P
1338 Some convenience functions are provided for extracting the captured substrings
1339 as separate strings. These are described below.
1340 .
1341 .\" HTML <a name="errorlist"></a>
1342 .SS "Error return values from \fBpcre_exec()\fP"
1343 .rs
1344 .sp
1345 If \fBpcre_exec()\fP fails, it returns a negative number. The following are
1346 defined in the header file:
1347 .sp
1348 PCRE_ERROR_NOMATCH (-1)
1349 .sp
1350 The subject string did not match the pattern.
1351 .sp
1352 PCRE_ERROR_NULL (-2)
1353 .sp
1354 Either \fIcode\fP or \fIsubject\fP was passed as NULL, or \fIovector\fP was
1355 NULL and \fIovecsize\fP was not zero.
1356 .sp
1357 PCRE_ERROR_BADOPTION (-3)
1358 .sp
1359 An unrecognized bit was set in the \fIoptions\fP argument.
1360 .sp
1361 PCRE_ERROR_BADMAGIC (-4)
1362 .sp
1363 PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch
1364 the case when it is passed a junk pointer and to detect when a pattern that was
1365 compiled in an environment of one endianness is run in an environment with the
1366 other endianness. This is the error that PCRE gives when the magic number is
1367 not present.
1368 .sp
1369 PCRE_ERROR_UNKNOWN_OPCODE (-5)
1370 .sp
1371 While running the pattern match, an unknown item was encountered in the
1372 compiled pattern. This error could be caused by a bug in PCRE or by overwriting
1373 of the compiled pattern.
1374 .sp
1375 PCRE_ERROR_NOMEMORY (-6)
1376 .sp
1377 If a pattern contains back references, but the \fIovector\fP that is passed to
1378 \fBpcre_exec()\fP is not big enough to remember the referenced substrings, PCRE
1379 gets a block of memory at the start of matching to use for this purpose. If the
1380 call via \fBpcre_malloc()\fP fails, this error is given. The memory is
1381 automatically freed at the end of matching.
1382 .sp
1383 PCRE_ERROR_NOSUBSTRING (-7)
1384 .sp
1385 This error is used by the \fBpcre_copy_substring()\fP,
1386 \fBpcre_get_substring()\fP, and \fBpcre_get_substring_list()\fP functions (see
1387 below). It is never returned by \fBpcre_exec()\fP.
1388 .sp
1389 PCRE_ERROR_MATCHLIMIT (-8)
1390 .sp
1391 The backtracking limit, as specified by the \fImatch_limit\fP field in a
1392 \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1393 above.
1394 .sp
1395 PCRE_ERROR_CALLOUT (-9)
1396 .sp
1397 This error is never generated by \fBpcre_exec()\fP itself. It is provided for
1398 use by callout functions that want to yield a distinctive error code. See the
1399 .\" HREF
1400 \fBpcrecallout\fP
1401 .\"
1402 documentation for details.
1403 .sp
1404 PCRE_ERROR_BADUTF8 (-10)
1405 .sp
1406 A string that contains an invalid UTF-8 byte sequence was passed as a subject.
1407 .sp
1408 PCRE_ERROR_BADUTF8_OFFSET (-11)
1409 .sp
1410 The UTF-8 byte sequence that was passed as a subject was valid, but the value
1411 of \fIstartoffset\fP did not point to the beginning of a UTF-8 character.
1412 .sp
1413 PCRE_ERROR_PARTIAL (-12)
1414 .sp
1415 The subject string did not match, but it did match partially. See the
1416 .\" HREF
1417 \fBpcrepartial\fP
1418 .\"
1419 documentation for details of partial matching.
1420 .sp
1421 PCRE_ERROR_BADPARTIAL (-13)
1422 .sp
1423 The PCRE_PARTIAL option was used with a compiled pattern containing items that
1424 are not supported for partial matching. See the
1425 .\" HREF
1426 \fBpcrepartial\fP
1427 .\"
1428 documentation for details of partial matching.
1429 .sp
1430 PCRE_ERROR_INTERNAL (-14)
1431 .sp
1432 An unexpected internal error has occurred. This error could be caused by a bug
1433 in PCRE or by overwriting of the compiled pattern.
1434 .sp
1435 PCRE_ERROR_BADCOUNT (-15)
1436 .sp
1437 This error is given if the value of the \fIovecsize\fP argument is negative.
1438 .sp
1439 PCRE_ERROR_RECURSIONLIMIT (-21)
1440 .sp
1441 The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1442 field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1443 description above.
1444 .sp
1445 PCRE_ERROR_NULLWSLIMIT (-22)
1446 .sp
1447 When a group that can match an empty substring is repeated with an unbounded
1448 upper limit, the subject position at the start of the group must be remembered,
1449 so that a test for an empty string can be made when the end of the group is
1450 reached. Some workspace is required for this; if it runs out, this error is
1451 given.
1452 .sp
1453 PCRE_ERROR_BADNEWLINE (-23)
1454 .sp
1455 An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1456 .P
1457 Error numbers -16 to -20 are not used by \fBpcre_exec()\fP.
1458 .
1459 .
1460 .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
1461 .rs
1462 .sp
1463 .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1464 .ti +5n
1465 .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
1466 .ti +5n
1467 .B int \fIbuffersize\fP);
1468 .PP
1469 .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1470 .ti +5n
1471 .B int \fIstringcount\fP, int \fIstringnumber\fP,
1472 .ti +5n
1473 .B const char **\fIstringptr\fP);
1474 .PP
1475 .B int pcre_get_substring_list(const char *\fIsubject\fP,
1476 .ti +5n
1477 .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
1478 .PP
1479 Captured substrings can be accessed directly by using the offsets returned by
1480 \fBpcre_exec()\fP in \fIovector\fP. For convenience, the functions
1481 \fBpcre_copy_substring()\fP, \fBpcre_get_substring()\fP, and
1482 \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
1483 as new, separate, zero-terminated strings. These functions identify substrings
1484 by number. The next section describes functions for extracting named
1485 substrings.
1486 .P
1487 A substring that contains a binary zero is correctly extracted and has a
1488 further zero added on the end, but the result is not, of course, a C string.
1489 However, you can process such a string by referring to the length that is
1490 returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
1491 Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
1492 for handling strings containing binary zeros, because the end of the final
1493 string is not independently indicated.
1494 .P
1495 The first three arguments are the same for all three of these functions:
1496 \fIsubject\fP is the subject string that has just been successfully matched,
1497 \fIovector\fP is a pointer to the vector of integer offsets that was passed to
1498 \fBpcre_exec()\fP, and \fIstringcount\fP is the number of substrings that were
1499 captured by the match, including the substring that matched the entire regular
1500 expression. This is the value returned by \fBpcre_exec()\fP if it is greater
1501 than zero. If \fBpcre_exec()\fP returned zero, indicating that it ran out of
1502 space in \fIovector\fP, the value passed as \fIstringcount\fP should be the
1503 number of elements in the vector divided by three.
1504 .P
1505 The functions \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP
1506 extract a single substring, whose number is given as \fIstringnumber\fP. A
1507 value of zero extracts the substring that matched the entire pattern, whereas
1508 higher values extract the captured substrings. For \fBpcre_copy_substring()\fP,
1509 the string is placed in \fIbuffer\fP, whose length is given by
1510 \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is
1511 obtained via \fBpcre_malloc\fP, and its address is returned via
1512 \fIstringptr\fP. The yield of the function is the length of the string, not
1513 including the terminating zero, or one of these error codes:
1514 .sp
1515 PCRE_ERROR_NOMEMORY (-6)
1516 .sp
1517 The buffer was too small for \fBpcre_copy_substring()\fP, or the attempt to get
1518 memory failed for \fBpcre_get_substring()\fP.
1519 .sp
1520 PCRE_ERROR_NOSUBSTRING (-7)
1521 .sp
1522 There is no substring whose number is \fIstringnumber\fP.
1523 .P
1524 The \fBpcre_get_substring_list()\fP function extracts all available substrings
1525 and builds a list of pointers to them. All this is done in a single block of
1526 memory that is obtained via \fBpcre_malloc\fP. The address of the memory block
1527 is returned via \fIlistptr\fP, which is also the start of the list of string
1528 pointers. The end of the list is marked by a NULL pointer. The yield of the
1529 function is zero if all went well, or the error code
1530 .sp
1531 PCRE_ERROR_NOMEMORY (-6)
1532 .sp
1533 if the attempt to get the memory block failed.
1534 .P
1535 When any of these functions encounter a substring that is unset, which can
1536 happen when capturing subpattern number \fIn+1\fP matches some part of the
1537 subject, but subpattern \fIn\fP has not been used at all, they return an empty
1538 string. This can be distinguished from a genuine zero-length substring by
1539 inspecting the appropriate offset in \fIovector\fP, which is negative for unset
1540 substrings.
1541 .P
1542 The two convenience functions \fBpcre_free_substring()\fP and
1543 \fBpcre_free_substring_list()\fP can be used to free the memory returned by
1544 a previous call of \fBpcre_get_substring()\fP or
1545 \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
1546 the function pointed to by \fBpcre_free\fP, which of course could be called
1547 directly from a C program. However, PCRE is used in some situations where it is
1548 linked via a special interface to another programming language that cannot use
1549 \fBpcre_free\fP directly; it is for these cases that the functions are
1550 provided.
1551 .
1552 .
1553 .SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME"
1554 .rs
1555 .sp
1556 .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
1557 .ti +5n
1558 .B const char *\fIname\fP);
1559 .PP
1560 .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1561 .ti +5n
1562 .B const char *\fIsubject\fP, int *\fIovector\fP,
1563 .ti +5n
1564 .B int \fIstringcount\fP, const char *\fIstringname\fP,
1565 .ti +5n
1566 .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1567 .PP
1568 .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1569 .ti +5n
1570 .B const char *\fIsubject\fP, int *\fIovector\fP,
1571 .ti +5n
1572 .B int \fIstringcount\fP, const char *\fIstringname\fP,
1573 .ti +5n
1574 .B const char **\fIstringptr\fP);
1575 .PP
1576 To extract a substring by name, you first have to find associated number.
1577 For example, for this pattern
1578 .sp
1579 (a+)b(?<xxx>\ed+)...
1580 .sp
1581 the number of the subpattern called "xxx" is 2. If the name is known to be
1582 unique (PCRE_DUPNAMES was not set), you can find the number from the name by
1583 calling \fBpcre_get_stringnumber()\fP. The first argument is the compiled
1584 pattern, and the second is the name. The yield of the function is the
1585 subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of
1586 that name.
1587 .P
1588 Given the number, you can extract the substring directly, or use one of the
1589 functions described in the previous section. For convenience, there are also
1590 two functions that do the whole job.
1591 .P
1592 Most of the arguments of \fBpcre_copy_named_substring()\fP and
1593 \fBpcre_get_named_substring()\fP are the same as those for the similarly named
1594 functions that extract by number. As these are described in the previous
1595 section, they are not re-described here. There are just two differences:
1596 .P
1597 First, instead of a substring number, a substring name is given. Second, there
1598 is an extra argument, given at the start, which is a pointer to the compiled
1599 pattern. This is needed in order to gain access to the name-to-number
1600 translation table.
1601 .P
1602 These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1603 then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1604 appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1605 the behaviour may not be what you want (see the next section).
1606 .
1607 .
1608 .SH "DUPLICATE SUBPATTERN NAMES"
1609 .rs
1610 .sp
1611 .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
1612 .ti +5n
1613 .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
1614 .PP
1615 When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
1616 are not required to be unique. Normally, patterns with duplicate names are such
1617 that in any one match, only one of the named subpatterns participates. An
1618 example is shown in the
1619 .\" HREF
1620 \fBpcrepattern\fP
1621 .\"
1622 documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP
1623 and \fBpcre_get_named_substring()\fP return the first substring corresponding
1624 to the given name that is set. If none are set, an empty string is returned.
1625 The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are
1626 associated with the name, but it is not defined which it is.
1627 .sp
1628 If you want to get full details of all captured substrings for a given name,
1629 you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1630 argument is the compiled pattern, and the second is the name. The third and
1631 fourth are pointers to variables which are updated by the function. After it
1632 has run, they point to the first and last entries in the name-to-number table
1633 for the given name. The function itself returns the length of each entry, or
1634 PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1635 described above in the section entitled \fIInformation about a pattern\fP.
1636 Given all the relevant entries for the name, you can extract each of their
1637 numbers, and hence the captured data, if any.
1638 .
1639 .
1640 .SH "FINDING ALL POSSIBLE MATCHES"
1641 .rs
1642 .sp
1643 The traditional matching function uses a similar algorithm to Perl, which stops
1644 when it finds the first match, starting at a given point in the subject. If you
1645 want to find all possible matches, or the longest possible match, consider
1646 using the alternative matching function (see below) instead. If you cannot use
1647 the alternative function, but still need to find all possible matches, you
1648 can kludge it up by making use of the callout facility, which is described in
1649 the
1650 .\" HREF
1651 \fBpcrecallout\fP
1652 .\"
1653 documentation.
1654 .P
1655 What you have to do is to insert a callout right at the end of the pattern.
1656 When your callout function is called, extract and save the current matched
1657 substring. Then return 1, which forces \fBpcre_exec()\fP to backtrack and try
1658 other alternatives. Ultimately, when it runs out of matches, \fBpcre_exec()\fP
1659 will yield PCRE_ERROR_NOMATCH.
1660 .
1661 .
1662 .\" HTML <a name="dfamatch"></a>
1663 .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
1664 .rs
1665 .sp
1666 .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
1667 .ti +5n
1668 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
1669 .ti +5n
1670 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
1671 .ti +5n
1672 .B int *\fIworkspace\fP, int \fIwscount\fP);
1673 .P
1674 The function \fBpcre_dfa_exec()\fP is called to match a subject string against
1675 a compiled pattern, using a matching algorithm that scans the subject string
1676 just once, and does not backtrack. This has different characteristics to the
1677 normal algorithm, and is not compatible with Perl. Some of the features of PCRE
1678 patterns are not supported. Nevertheless, there are times when this kind of
1679 matching can be useful. For a discussion of the two matching algorithms, see
1680 the
1681 .\" HREF
1682 \fBpcrematching\fP
1683 .\"
1684 documentation.
1685 .P
1686 The arguments for the \fBpcre_dfa_exec()\fP function are the same as for
1687 \fBpcre_exec()\fP, plus two extras. The \fIovector\fP argument is used in a
1688 different way, and this is described below. The other common arguments are used
1689 in the same way as for \fBpcre_exec()\fP, so their description is not repeated
1690 here.
1691 .P
1692 The two additional arguments provide workspace for the function. The workspace
1693 vector should contain at least 20 elements. It is used for keeping track of
1694 multiple paths through the pattern tree. More workspace will be needed for
1695 patterns and subjects where there are a lot of potential matches.
1696 .P
1697 Here is an example of a simple call to \fBpcre_dfa_exec()\fP:
1698 .sp
1699 int rc;
1700 int ovector[10];
1701 int wspace[20];
1702 rc = pcre_dfa_exec(
1703 re, /* result of pcre_compile() */
1704 NULL, /* we didn't study the pattern */
1705 "some string", /* the subject string */
1706 11, /* the length of the subject string */
1707 0, /* start at offset 0 in the subject */
1708 0, /* default options */
1709 ovector, /* vector of integers for substring information */
1710 10, /* number of elements (NOT size in bytes) */
1711 wspace, /* working space vector */
1712 20); /* number of elements (NOT size in bytes) */
1713 .
1714 .SS "Option bits for \fBpcre_dfa_exec()\fP"
1715 .rs
1716 .sp
1717 The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be
1718 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1719 PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,
1720 PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are
1721 the same as for \fBpcre_exec()\fP, so their description is not repeated here.
1722 .sp
1723 PCRE_PARTIAL
1724 .sp
1725 This has the same general effect as it does for \fBpcre_exec()\fP, but the
1726 details are slightly different. When PCRE_PARTIAL is set for
1727 \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into
1728 PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no
1729 complete matches, but there is still at least one matching possibility. The
1730 portion of the string that provided the partial match is set as the first
1731 matching string.
1732 .sp
1733 PCRE_DFA_SHORTEST
1734 .sp
1735 Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
1736 soon as it has found one match. Because of the way the alternative algorithm
1737 works, this is necessarily the shortest possible match at the first possible
1738 matching point in the subject string.
1739 .sp
1740 PCRE_DFA_RESTART
1741 .sp
1742 When \fBpcre_dfa_exec()\fP is called with the PCRE_PARTIAL option, and returns
1743 a partial match, it is possible to call it again, with additional subject
1744 characters, and have it continue with the same match. The PCRE_DFA_RESTART
1745 option requests this action; when it is set, the \fIworkspace\fP and
1746 \fIwscount\fP options must reference the same vector as before because data
1747 about the match so far is left in them after a partial match. There is more
1748 discussion of this facility in the
1749 .\" HREF
1750 \fBpcrepartial\fP
1751 .\"
1752 documentation.
1753 .
1754 .SS "Successful returns from \fBpcre_dfa_exec()\fP"
1755 .rs
1756 .sp
1757 When \fBpcre_dfa_exec()\fP succeeds, it may have matched more than one
1758 substring in the subject. Note, however, that all the matches from one run of
1759 the function start at the same point in the subject. The shorter matches are
1760 all initial substrings of the longer matches. For example, if the pattern
1761 .sp
1762 <.*>
1763 .sp
1764 is matched against the string
1765 .sp
1766 This is <something> <something else> <something further> no more
1767 .sp
1768 the three matched strings are
1769 .sp
1770 <something>
1771 <something> <something else>
1772 <something> <something else> <something further>
1773 .sp
1774 On success, the yield of the function is a number greater than zero, which is
1775 the number of matched substrings. The substrings themselves are returned in
1776 \fIovector\fP. Each string uses two elements; the first is the offset to the
1777 start, and the second is the offset to the end. In fact, all the strings have
1778 the same start offset. (Space could have been saved by giving this only once,
1779 but it was decided to retain some compatibility with the way \fBpcre_exec()\fP
1780 returns data, even though the meaning of the strings is different.)
1781 .P
1782 The strings are returned in reverse order of length; that is, the longest
1783 matching string is given first. If there were too many matches to fit into
1784 \fIovector\fP, the yield of the function is zero, and the vector is filled with
1785 the longest matches.
1786 .
1787 .SS "Error returns from \fBpcre_dfa_exec()\fP"
1788 .rs
1789 .sp
1790 The \fBpcre_dfa_exec()\fP function returns a negative number when it fails.
1791 Many of the errors are the same as for \fBpcre_exec()\fP, and these are
1792 described
1793 .\" HTML <a href="#errorlist">
1794 .\" </a>
1795 above.
1796 .\"
1797 There are in addition the following errors that are specific to
1798 \fBpcre_dfa_exec()\fP:
1799 .sp
1800 PCRE_ERROR_DFA_UITEM (-16)
1801 .sp
1802 This return is given if \fBpcre_dfa_exec()\fP encounters an item in the pattern
1803 that it does not support, for instance, the use of \eC or a back reference.
1804 .sp
1805 PCRE_ERROR_DFA_UCOND (-17)
1806 .sp
1807 This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that
1808 uses a back reference for the condition, or a test for recursion in a specific
1809 group. These are not supported.
1810 .sp
1811 PCRE_ERROR_DFA_UMLIMIT (-18)
1812 .sp
1813 This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP
1814 block that contains a setting of the \fImatch_limit\fP field. This is not
1815 supported (it is meaningless).
1816 .sp
1817 PCRE_ERROR_DFA_WSSIZE (-19)
1818 .sp
1819 This return is given if \fBpcre_dfa_exec()\fP runs out of space in the
1820 \fIworkspace\fP vector.
1821 .sp
1822 PCRE_ERROR_DFA_RECURSE (-20)
1823 .sp
1824 When a recursive subpattern is processed, the matching function calls itself
1825 recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1826 error is given if the output vector is not large enough. This should be
1827 extremely rare, as a vector of size 1000 is used.
1828 .
1829 .
1830 .SH "SEE ALSO"
1831 .rs
1832 .sp
1833 \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1834 \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1835 \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1836 .
1837 .
1838 .SH AUTHOR
1839 .rs
1840 .sp
1841 .nf
1842 Philip Hazel
1843 University Computing Service
1844 Cambridge CB2 3QH, England.
1845 .fi
1846 .
1847 .
1848 .SH REVISION
1849 .rs
1850 .sp
1851 .nf
1852 Last updated: 16 April 2007
1853 Copyright (c) 1997-2007 University of Cambridge.
1854 .fi

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