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

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

Parent Directory Parent Directory | Revision Log Revision Log


Revision 230 - (show annotations) (download)
Mon Sep 10 13:23:56 2007 UTC (7 years, 1 month ago) by ph10
File size: 82595 byte(s)
(1) Move internal flags out of the options field, to make room.
(2) \r and \n must be explicit to trigger the special CRLF handline exception.
(3) (?J) at the start now sets JCHANGED as well as DUPNAMES.

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 .\" HTML <a name="newlines"></a>
222 .SH NEWLINES
223 .rs
224 .sp
225 PCRE supports five different conventions for indicating line breaks in
226 strings: a single CR (carriage return) character, a single LF (linefeed)
227 character, the two-character sequence CRLF, any of the three preceding, or any
228 Unicode newline sequence. The Unicode newline sequences are the three just
229 mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
230 U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
231 (paragraph separator, U+2029).
232 .P
233 Each of the first three conventions is used by at least one operating system as
234 its standard newline sequence. When PCRE is built, a default can be specified.
235 The default default is LF, which is the Unix standard. When PCRE is run, the
236 default can be overridden, either when a pattern is compiled, or when it is
237 matched.
238 .P
239 At compile time, the newline convention can be specified by the \fIoptions\fP
240 argument of \fBpcre_compile()\fP, or it can be specified by special text at the
241 start of the pattern itself; this overrides any other settings. See the
242 .\" HREF
243 \fBpcrepattern\fP
244 .\"
245 page for details of the special character sequences.
246 .P
247 In the PCRE documentation the word "newline" is used to mean "the character or
248 pair of characters that indicate a line break". The choice of newline
249 convention affects the handling of the dot, circumflex, and dollar
250 metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
251 recognized line ending sequence, the match position advancement for a
252 non-anchored pattern. There is more detail about this in the
253 .\" HTML <a href="#execoptions">
254 .\" </a>
255 section on \fBpcre_exec()\fP options
256 .\"
257 below. The choice of newline convention does not affect the interpretation of
258 the \en or \er escape sequences.
259 .
260 .
261 .SH MULTITHREADING
262 .rs
263 .sp
264 The PCRE functions can be used in multi-threading applications, with the
265 proviso that the memory management functions pointed to by \fBpcre_malloc\fP,
266 \fBpcre_free\fP, \fBpcre_stack_malloc\fP, and \fBpcre_stack_free\fP, and the
267 callout function pointed to by \fBpcre_callout\fP, are shared by all threads.
268 .P
269 The compiled form of a regular expression is not altered during matching, so
270 the same compiled pattern can safely be used by several threads at once.
271 .
272 .
273 .SH "SAVING PRECOMPILED PATTERNS FOR LATER USE"
274 .rs
275 .sp
276 The compiled form of a regular expression can be saved and re-used at a later
277 time, possibly by a different program, and even on a host other than the one on
278 which it was compiled. Details are given in the
279 .\" HREF
280 \fBpcreprecompile\fP
281 .\"
282 documentation. However, compiling a regular expression with one version of PCRE
283 for use with a different version is not guaranteed to work and may cause
284 crashes.
285 .
286 .
287 .SH "CHECKING BUILD-TIME OPTIONS"
288 .rs
289 .sp
290 .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
291 .PP
292 The function \fBpcre_config()\fP makes it possible for a PCRE client to
293 discover which optional features have been compiled into the PCRE library. The
294 .\" HREF
295 \fBpcrebuild\fP
296 .\"
297 documentation has more details about these optional features.
298 .P
299 The first argument for \fBpcre_config()\fP is an integer, specifying which
300 information is required; the second argument is a pointer to a variable into
301 which the information is placed. The following information is available:
302 .sp
303 PCRE_CONFIG_UTF8
304 .sp
305 The output is an integer that is set to one if UTF-8 support is available;
306 otherwise it is set to zero.
307 .sp
308 PCRE_CONFIG_UNICODE_PROPERTIES
309 .sp
310 The output is an integer that is set to one if support for Unicode character
311 properties is available; otherwise it is set to zero.
312 .sp
313 PCRE_CONFIG_NEWLINE
314 .sp
315 The output is an integer whose value specifies the default character sequence
316 that is recognized as meaning "newline". The four values that are supported
317 are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. The
318 default should normally be the standard sequence for your operating system.
319 .sp
320 PCRE_CONFIG_LINK_SIZE
321 .sp
322 The output is an integer that contains the number of bytes used for internal
323 linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values
324 allow larger regular expressions to be compiled, at the expense of slower
325 matching. The default value of 2 is sufficient for all but the most massive
326 patterns, since it allows the compiled pattern to be up to 64K in size.
327 .sp
328 PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
329 .sp
330 The output is an integer that contains the threshold above which the POSIX
331 interface uses \fBmalloc()\fP for output vectors. Further details are given in
332 the
333 .\" HREF
334 \fBpcreposix\fP
335 .\"
336 documentation.
337 .sp
338 PCRE_CONFIG_MATCH_LIMIT
339 .sp
340 The output is an integer that gives the default limit for the number of
341 internal matching function calls in a \fBpcre_exec()\fP execution. Further
342 details are given with \fBpcre_exec()\fP below.
343 .sp
344 PCRE_CONFIG_MATCH_LIMIT_RECURSION
345 .sp
346 The output is an integer that gives the default limit for the depth of
347 recursion when calling the internal matching function in a \fBpcre_exec()\fP
348 execution. Further details are given with \fBpcre_exec()\fP below.
349 .sp
350 PCRE_CONFIG_STACKRECURSE
351 .sp
352 The output is an integer that is set to one if internal recursion when running
353 \fBpcre_exec()\fP is implemented by recursive function calls that use the stack
354 to remember their state. This is the usual way that PCRE is compiled. The
355 output is zero if PCRE was compiled to use blocks of data on the heap instead
356 of recursive function calls. In this case, \fBpcre_stack_malloc\fP and
357 \fBpcre_stack_free\fP are called to manage memory blocks on the heap, thus
358 avoiding the use of the stack.
359 .
360 .
361 .SH "COMPILING A PATTERN"
362 .rs
363 .sp
364 .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
365 .ti +5n
366 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
367 .ti +5n
368 .B const unsigned char *\fItableptr\fP);
369 .sp
370 .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
371 .ti +5n
372 .B int *\fIerrorcodeptr\fP,
373 .ti +5n
374 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
375 .ti +5n
376 .B const unsigned char *\fItableptr\fP);
377 .P
378 Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be
379 called to compile a pattern into an internal form. The only difference between
380 the two interfaces is that \fBpcre_compile2()\fP has an additional argument,
381 \fIerrorcodeptr\fP, via which a numerical error code can be returned.
382 .P
383 The pattern is a C string terminated by a binary zero, and is passed in the
384 \fIpattern\fP argument. A pointer to a single block of memory that is obtained
385 via \fBpcre_malloc\fP is returned. This contains the compiled code and related
386 data. The \fBpcre\fP type is defined for the returned block; this is a typedef
387 for a structure whose contents are not externally defined. It is up to the
388 caller to free the memory (via \fBpcre_free\fP) when it is no longer required.
389 .P
390 Although the compiled code of a PCRE regex is relocatable, that is, it does not
391 depend on memory location, the complete \fBpcre\fP data block is not
392 fully relocatable, because it may contain a copy of the \fItableptr\fP
393 argument, which is an address (see below).
394 .P
395 The \fIoptions\fP argument contains various bit settings that affect the
396 compilation. It should be zero if no options are required. The available
397 options are described below. Some of them, in particular, those that are
398 compatible with Perl, can also be set and unset from within the pattern (see
399 the detailed description in the
400 .\" HREF
401 \fBpcrepattern\fP
402 .\"
403 documentation). For these options, the contents of the \fIoptions\fP argument
404 specifies their initial settings at the start of compilation and execution. The
405 PCRE_ANCHORED and PCRE_NEWLINE_\fIxxx\fP options can be set at the time of
406 matching as well as at compile time.
407 .P
408 If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
409 Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
410 NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual
411 error message. This is a static string that is part of the library. You must
412 not try to free it. The offset from the start of the pattern to the character
413 where the error was discovered is placed in the variable pointed to by
414 \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.
415 .P
416 If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the
417 \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is
418 returned via this argument in the event of an error. This is in addition to the
419 textual error message. Error codes and messages are listed below.
420 .P
421 If the final argument, \fItableptr\fP, is NULL, PCRE uses a default set of
422 character tables that are built when PCRE is compiled, using the default C
423 locale. Otherwise, \fItableptr\fP must be an address that is the result of a
424 call to \fBpcre_maketables()\fP. This value is stored with the compiled
425 pattern, and used again by \fBpcre_exec()\fP, unless another table pointer is
426 passed to it. For more discussion, see the section on locale support below.
427 .P
428 This code fragment shows a typical straightforward call to \fBpcre_compile()\fP:
429 .sp
430 pcre *re;
431 const char *error;
432 int erroffset;
433 re = pcre_compile(
434 "^A.*Z", /* the pattern */
435 0, /* default options */
436 &error, /* for error message */
437 &erroffset, /* for error offset */
438 NULL); /* use default character tables */
439 .sp
440 The following names for option bits are defined in the \fBpcre.h\fP header
441 file:
442 .sp
443 PCRE_ANCHORED
444 .sp
445 If this bit is set, the pattern is forced to be "anchored", that is, it is
446 constrained to match only at the first matching point in the string that is
447 being searched (the "subject string"). This effect can also be achieved by
448 appropriate constructs in the pattern itself, which is the only way to do it in
449 Perl.
450 .sp
451 PCRE_AUTO_CALLOUT
452 .sp
453 If this bit is set, \fBpcre_compile()\fP automatically inserts callout items,
454 all with number 255, before each pattern item. For discussion of the callout
455 facility, see the
456 .\" HREF
457 \fBpcrecallout\fP
458 .\"
459 documentation.
460 .sp
461 PCRE_CASELESS
462 .sp
463 If this bit is set, letters in the pattern match both upper and lower case
464 letters. It is equivalent to Perl's /i option, and it can be changed within a
465 pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the
466 concept of case for characters whose values are less than 128, so caseless
467 matching is always possible. For characters with higher values, the concept of
468 case is supported if PCRE is compiled with Unicode property support, but not
469 otherwise. If you want to use caseless matching for characters 128 and above,
470 you must ensure that PCRE is compiled with Unicode property support as well as
471 with UTF-8 support.
472 .sp
473 PCRE_DOLLAR_ENDONLY
474 .sp
475 If this bit is set, a dollar metacharacter in the pattern matches only at the
476 end of the subject string. Without this option, a dollar also matches
477 immediately before a newline at the end of the string (but not before any other
478 newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set.
479 There is no equivalent to this option in Perl, and no way to set it within a
480 pattern.
481 .sp
482 PCRE_DOTALL
483 .sp
484 If this bit is set, a dot metacharater in the pattern matches all characters,
485 including those that indicate newline. Without it, a dot does not match when
486 the current position is at a newline. This option is equivalent to Perl's /s
487 option, and it can be changed within a pattern by a (?s) option setting. A
488 negative class such as [^a] always matches newline characters, independent of
489 the setting of this option.
490 .sp
491 PCRE_DUPNAMES
492 .sp
493 If this bit is set, names used to identify capturing subpatterns need not be
494 unique. This can be helpful for certain types of pattern when it is known that
495 only one instance of the named subpattern can ever be matched. There are more
496 details of named subpatterns below; see also the
497 .\" HREF
498 \fBpcrepattern\fP
499 .\"
500 documentation.
501 .sp
502 PCRE_EXTENDED
503 .sp
504 If this bit is set, whitespace data characters in the pattern are totally
505 ignored except when escaped or inside a character class. Whitespace does not
506 include the VT character (code 11). In addition, characters between an
507 unescaped # outside a character class and the next newline, inclusive, are also
508 ignored. This is equivalent to Perl's /x option, and it can be changed within a
509 pattern by a (?x) option setting.
510 .P
511 This option makes it possible to include comments inside complicated patterns.
512 Note, however, that this applies only to data characters. Whitespace characters
513 may never appear within special character sequences in a pattern, for example
514 within the sequence (?( which introduces a conditional subpattern.
515 .sp
516 PCRE_EXTRA
517 .sp
518 This option was invented in order to turn on additional functionality of PCRE
519 that is incompatible with Perl, but it is currently of very little use. When
520 set, any backslash in a pattern that is followed by a letter that has no
521 special meaning causes an error, thus reserving these combinations for future
522 expansion. By default, as in Perl, a backslash followed by a letter with no
523 special meaning is treated as a literal. (Perl can, however, be persuaded to
524 give a warning for this.) There are at present no other features controlled by
525 this option. It can also be set by a (?X) option setting within a pattern.
526 .sp
527 PCRE_FIRSTLINE
528 .sp
529 If this option is set, an unanchored pattern is required to match before or at
530 the first newline in the subject string, though the matched text may continue
531 over the newline.
532 .sp
533 PCRE_MULTILINE
534 .sp
535 By default, PCRE treats the subject string as consisting of a single line of
536 characters (even if it actually contains newlines). The "start of line"
537 metacharacter (^) matches only at the start of the string, while the "end of
538 line" metacharacter ($) matches only at the end of the string, or before a
539 terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as
540 Perl.
541 .P
542 When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
543 match immediately following or immediately before internal newlines in the
544 subject string, respectively, as well as at the very start and end. This is
545 equivalent to Perl's /m option, and it can be changed within a pattern by a
546 (?m) option setting. If there are no newlines in a subject string, or no
547 occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
548 .sp
549 PCRE_NEWLINE_CR
550 PCRE_NEWLINE_LF
551 PCRE_NEWLINE_CRLF
552 PCRE_NEWLINE_ANYCRLF
553 PCRE_NEWLINE_ANY
554 .sp
555 These options override the default newline definition that was chosen when PCRE
556 was built. Setting the first or the second specifies that a newline is
557 indicated by a single character (CR or LF, respectively). Setting
558 PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
559 CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
560 preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
561 that any Unicode newline sequence should be recognized. The Unicode newline
562 sequences are the three just mentioned, plus the single characters VT (vertical
563 tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
564 separator, U+2028), and PS (paragraph separator, U+2029). The last two are
565 recognized only in UTF-8 mode.
566 .P
567 The newline setting in the options word uses three bits that are treated
568 as a number, giving eight possibilities. Currently only six are used (default
569 plus the five values above). This means that if you set more than one newline
570 option, the combination may or may not be sensible. For example,
571 PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
572 other combinations may yield unused numbers and cause an error.
573 .P
574 The only time that a line break is specially recognized when compiling a
575 pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
576 class is encountered. This indicates a comment that lasts until after the next
577 line break sequence. In other circumstances, line break sequences are treated
578 as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
579 as whitespace characters and are therefore ignored.
580 .P
581 The newline option that is set at compile time becomes the default that is used
582 for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
583 .sp
584 PCRE_NO_AUTO_CAPTURE
585 .sp
586 If this option is set, it disables the use of numbered capturing parentheses in
587 the pattern. Any opening parenthesis that is not followed by ? behaves as if it
588 were followed by ?: but named parentheses can still be used for capturing (and
589 they acquire numbers in the usual way). There is no equivalent of this option
590 in Perl.
591 .sp
592 PCRE_UNGREEDY
593 .sp
594 This option inverts the "greediness" of the quantifiers so that they are not
595 greedy by default, but become greedy if followed by "?". It is not compatible
596 with Perl. It can also be set by a (?U) option setting within the pattern.
597 .sp
598 PCRE_UTF8
599 .sp
600 This option causes PCRE to regard both the pattern and the subject as strings
601 of UTF-8 characters instead of single-byte character strings. However, it is
602 available only when PCRE is built to include UTF-8 support. If not, the use
603 of this option provokes an error. Details of how this option changes the
604 behaviour of PCRE are given in the
605 .\" HTML <a href="pcre.html#utf8support">
606 .\" </a>
607 section on UTF-8 support
608 .\"
609 in the main
610 .\" HREF
611 \fBpcre\fP
612 .\"
613 page.
614 .sp
615 PCRE_NO_UTF8_CHECK
616 .sp
617 When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
618 automatically checked. There is a discussion about the
619 .\" HTML <a href="pcre.html#utf8strings">
620 .\" </a>
621 validity of UTF-8 strings
622 .\"
623 in the main
624 .\" HREF
625 \fBpcre\fP
626 .\"
627 page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
628 returns an error. If you already know that your pattern is valid, and you want
629 to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
630 option. When it is set, the effect of passing an invalid UTF-8 string as a
631 pattern is undefined. It may cause your program to crash. Note that this option
632 can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
633 the UTF-8 validity checking of subject strings.
634 .
635 .
636 .SH "COMPILATION ERROR CODES"
637 .rs
638 .sp
639 The following table lists the error codes than may be returned by
640 \fBpcre_compile2()\fP, along with the error messages that may be returned by
641 both compiling functions. As PCRE has developed, some error codes have fallen
642 out of use. To avoid confusion, they have not been re-used.
643 .sp
644 0 no error
645 1 \e at end of pattern
646 2 \ec at end of pattern
647 3 unrecognized character follows \e
648 4 numbers out of order in {} quantifier
649 5 number too big in {} quantifier
650 6 missing terminating ] for character class
651 7 invalid escape sequence in character class
652 8 range out of order in character class
653 9 nothing to repeat
654 10 [this code is not in use]
655 11 internal error: unexpected repeat
656 12 unrecognized character after (?
657 13 POSIX named classes are supported only within a class
658 14 missing )
659 15 reference to non-existent subpattern
660 16 erroffset passed as NULL
661 17 unknown option bit(s) set
662 18 missing ) after comment
663 19 [this code is not in use]
664 20 regular expression too large
665 21 failed to get memory
666 22 unmatched parentheses
667 23 internal error: code overflow
668 24 unrecognized character after (?<
669 25 lookbehind assertion is not fixed length
670 26 malformed number or name after (?(
671 27 conditional group contains more than two branches
672 28 assertion expected after (?(
673 29 (?R or (?[+-]digits must be followed by )
674 30 unknown POSIX class name
675 31 POSIX collating elements are not supported
676 32 this version of PCRE is not compiled with PCRE_UTF8 support
677 33 [this code is not in use]
678 34 character value in \ex{...} sequence is too large
679 35 invalid condition (?(0)
680 36 \eC not allowed in lookbehind assertion
681 37 PCRE does not support \eL, \el, \eN, \eU, or \eu
682 38 number after (?C is > 255
683 39 closing ) for (?C expected
684 40 recursive call could loop indefinitely
685 41 unrecognized character after (?P
686 42 syntax error in subpattern name (missing terminator)
687 43 two named subpatterns have the same name
688 44 invalid UTF-8 string
689 45 support for \eP, \ep, and \eX has not been compiled
690 46 malformed \eP or \ep sequence
691 47 unknown property name after \eP or \ep
692 48 subpattern name is too long (maximum 32 characters)
693 49 too many named subpatterns (maximum 10,000)
694 50 [this code is not in use]
695 51 octal value is greater than \e377 (not in UTF-8 mode)
696 52 internal error: overran compiling workspace
697 53 internal error: previously-checked referenced subpattern not found
698 54 DEFINE group contains more than one branch
699 55 repeating a DEFINE group is not allowed
700 56 inconsistent NEWLINE options"
701 57 \eg is not followed by a braced name or an optionally braced
702 non-zero number
703 58 (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number
704 .
705 .
706 .SH "STUDYING A PATTERN"
707 .rs
708 .sp
709 .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP
710 .ti +5n
711 .B const char **\fIerrptr\fP);
712 .PP
713 If a compiled pattern is going to be used several times, it is worth spending
714 more time analyzing it in order to speed up the time taken for matching. The
715 function \fBpcre_study()\fP takes a pointer to a compiled pattern as its first
716 argument. If studying the pattern produces additional information that will
717 help speed up matching, \fBpcre_study()\fP returns a pointer to a
718 \fBpcre_extra\fP block, in which the \fIstudy_data\fP field points to the
719 results of the study.
720 .P
721 The returned value from \fBpcre_study()\fP can be passed directly to
722 \fBpcre_exec()\fP. However, a \fBpcre_extra\fP block also contains other
723 fields that can be set by the caller before the block is passed; these are
724 described
725 .\" HTML <a href="#extradata">
726 .\" </a>
727 below
728 .\"
729 in the section on matching a pattern.
730 .P
731 If studying the pattern does not produce any additional information
732 \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program
733 wants to pass any of the other fields to \fBpcre_exec()\fP, it must set up its
734 own \fBpcre_extra\fP block.
735 .P
736 The second argument of \fBpcre_study()\fP contains option bits. At present, no
737 options are defined, and this argument should always be zero.
738 .P
739 The third argument for \fBpcre_study()\fP is a pointer for an error message. If
740 studying succeeds (even if no data is returned), the variable it points to is
741 set to NULL. Otherwise it is set to point to a textual error message. This is a
742 static string that is part of the library. You must not try to free it. You
743 should test the error pointer for NULL after calling \fBpcre_study()\fP, to be
744 sure that it has run successfully.
745 .P
746 This is a typical call to \fBpcre_study\fP():
747 .sp
748 pcre_extra *pe;
749 pe = pcre_study(
750 re, /* result of pcre_compile() */
751 0, /* no options exist */
752 &error); /* set to NULL or points to a message */
753 .sp
754 At present, studying a pattern is useful only for non-anchored patterns that do
755 not have a single fixed starting character. A bitmap of possible starting
756 bytes is created.
757 .
758 .
759 .\" HTML <a name="localesupport"></a>
760 .SH "LOCALE SUPPORT"
761 .rs
762 .sp
763 PCRE handles caseless matching, and determines whether characters are letters,
764 digits, or whatever, by reference to a set of tables, indexed by character
765 value. When running in UTF-8 mode, this applies only to characters with codes
766 less than 128. Higher-valued codes never match escapes such as \ew or \ed, but
767 can be tested with \ep if PCRE is built with Unicode character property
768 support. The use of locales with Unicode is discouraged. If you are handling
769 characters with codes greater than 128, you should either use UTF-8 and
770 Unicode, or use locales, but not try to mix the two.
771 .P
772 PCRE contains an internal set of tables that are used when the final argument
773 of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
774 Normally, the internal tables recognize only ASCII characters. However, when
775 PCRE is built, it is possible to cause the internal tables to be rebuilt in the
776 default "C" locale of the local system, which may cause them to be different.
777 .P
778 The internal tables can always be overridden by tables supplied by the
779 application that calls PCRE. These may be created in a different locale from
780 the default. As more and more applications change to using Unicode, the need
781 for this locale support is expected to die away.
782 .P
783 External tables are built by calling the \fBpcre_maketables()\fP function,
784 which has no arguments, in the relevant locale. The result can then be passed
785 to \fBpcre_compile()\fP or \fBpcre_exec()\fP as often as necessary. For
786 example, to build and use tables that are appropriate for the French locale
787 (where accented characters with values greater than 128 are treated as letters),
788 the following code could be used:
789 .sp
790 setlocale(LC_CTYPE, "fr_FR");
791 tables = pcre_maketables();
792 re = pcre_compile(..., tables);
793 .sp
794 The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
795 are using Windows, the name for the French locale is "french".
796 .P
797 When \fBpcre_maketables()\fP runs, the tables are built in memory that is
798 obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure
799 that the memory containing the tables remains available for as long as it is
800 needed.
801 .P
802 The pointer that is passed to \fBpcre_compile()\fP is saved with the compiled
803 pattern, and the same tables are used via this pointer by \fBpcre_study()\fP
804 and normally also by \fBpcre_exec()\fP. Thus, by default, for any single
805 pattern, compilation, studying and matching all happen in the same locale, but
806 different patterns can be compiled in different locales.
807 .P
808 It is possible to pass a table pointer or NULL (indicating the use of the
809 internal tables) to \fBpcre_exec()\fP. Although not intended for this purpose,
810 this facility could be used to match a pattern in a different locale from the
811 one in which it was compiled. Passing table pointers at run time is discussed
812 below in the section on matching a pattern.
813 .
814 .
815 .SH "INFORMATION ABOUT A PATTERN"
816 .rs
817 .sp
818 .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
819 .ti +5n
820 .B int \fIwhat\fP, void *\fIwhere\fP);
821 .PP
822 The \fBpcre_fullinfo()\fP function returns information about a compiled
823 pattern. It replaces the obsolete \fBpcre_info()\fP function, which is
824 nevertheless retained for backwards compability (and is documented below).
825 .P
826 The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled
827 pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if
828 the pattern was not studied. The third argument specifies which piece of
829 information is required, and the fourth argument is a pointer to a variable
830 to receive the data. The yield of the function is zero for success, or one of
831 the following negative numbers:
832 .sp
833 PCRE_ERROR_NULL the argument \fIcode\fP was NULL
834 the argument \fIwhere\fP was NULL
835 PCRE_ERROR_BADMAGIC the "magic number" was not found
836 PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid
837 .sp
838 The "magic number" is placed at the start of each compiled pattern as an simple
839 check against passing an arbitrary memory pointer. Here is a typical call of
840 \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
841 .sp
842 int rc;
843 size_t length;
844 rc = pcre_fullinfo(
845 re, /* result of pcre_compile() */
846 pe, /* result of pcre_study(), or NULL */
847 PCRE_INFO_SIZE, /* what is required */
848 &length); /* where to put the data */
849 .sp
850 The possible values for the third argument are defined in \fBpcre.h\fP, and are
851 as follows:
852 .sp
853 PCRE_INFO_BACKREFMAX
854 .sp
855 Return the number of the highest back reference in the pattern. The fourth
856 argument should point to an \fBint\fP variable. Zero is returned if there are
857 no back references.
858 .sp
859 PCRE_INFO_CAPTURECOUNT
860 .sp
861 Return the number of capturing subpatterns in the pattern. The fourth argument
862 should point to an \fBint\fP variable.
863 .sp
864 PCRE_INFO_DEFAULT_TABLES
865 .sp
866 Return a pointer to the internal default character tables within PCRE. The
867 fourth argument should point to an \fBunsigned char *\fP variable. This
868 information call is provided for internal use by the \fBpcre_study()\fP
869 function. External callers can cause PCRE to use its internal tables by passing
870 a NULL table pointer.
871 .sp
872 PCRE_INFO_FIRSTBYTE
873 .sp
874 Return information about the first byte of any matched string, for a
875 non-anchored pattern. The fourth argument should point to an \fBint\fP
876 variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
877 still recognized for backwards compatibility.)
878 .P
879 If there is a fixed first byte, for example, from a pattern such as
880 (cat|cow|coyote), its value is returned. Otherwise, if either
881 .sp
882 (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
883 starts with "^", or
884 .sp
885 (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
886 (if it were set, the pattern would be anchored),
887 .sp
888 -1 is returned, indicating that the pattern matches only at the start of a
889 subject string or after any newline within the string. Otherwise -2 is
890 returned. For anchored patterns, -2 is returned.
891 .sp
892 PCRE_INFO_FIRSTTABLE
893 .sp
894 If the pattern was studied, and this resulted in the construction of a 256-bit
895 table indicating a fixed set of bytes for the first byte in any matching
896 string, a pointer to the table is returned. Otherwise NULL is returned. The
897 fourth argument should point to an \fBunsigned char *\fP variable.
898 .sp
899 PCRE_INFO_HASCRORLF
900 .sp
901 Return 1 if the pattern contains any explicit matches for CR or LF characters,
902 otherwise 0. The fourth argument should point to an \fBint\fP variable.
903 .sp
904 PCRE_INFO_JCHANGED
905 .sp
906 Return 1 if the (?J) option setting is used in the pattern, otherwise 0. The
907 fourth argument should point to an \fBint\fP variable. The (?J) internal option
908 setting changes the local PCRE_DUPNAMES option.
909 .sp
910 PCRE_INFO_LASTLITERAL
911 .sp
912 Return the value of the rightmost literal byte that must exist in any matched
913 string, other than at its start, if such a byte has been recorded. The fourth
914 argument should point to an \fBint\fP variable. If there is no such byte, -1 is
915 returned. For anchored patterns, a last literal byte is recorded only if it
916 follows something of variable length. For example, for the pattern
917 /^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value
918 is -1.
919 .sp
920 PCRE_INFO_NAMECOUNT
921 PCRE_INFO_NAMEENTRYSIZE
922 PCRE_INFO_NAMETABLE
923 .sp
924 PCRE supports the use of named as well as numbered capturing parentheses. The
925 names are just an additional way of identifying the parentheses, which still
926 acquire numbers. Several convenience functions such as
927 \fBpcre_get_named_substring()\fP are provided for extracting captured
928 substrings by name. It is also possible to extract the data directly, by first
929 converting the name to a number in order to access the correct pointers in the
930 output vector (described with \fBpcre_exec()\fP below). To do the conversion,
931 you need to use the name-to-number map, which is described by these three
932 values.
933 .P
934 The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives
935 the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
936 entry; both of these return an \fBint\fP value. The entry size depends on the
937 length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
938 entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry
939 are the number of the capturing parenthesis, most significant byte first. The
940 rest of the entry is the corresponding name, zero terminated. The names are in
941 alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of
942 their parentheses numbers. For example, consider the following pattern (assume
943 PCRE_EXTENDED is set, so white space - including newlines - is ignored):
944 .sp
945 .\" JOIN
946 (?<date> (?<year>(\ed\ed)?\ed\ed) -
947 (?<month>\ed\ed) - (?<day>\ed\ed) )
948 .sp
949 There are four named subpatterns, so the table has four entries, and each entry
950 in the table is eight bytes long. The table is as follows, with non-printing
951 bytes shows in hexadecimal, and undefined bytes shown as ??:
952 .sp
953 00 01 d a t e 00 ??
954 00 05 d a y 00 ?? ??
955 00 04 m o n t h 00
956 00 02 y e a r 00 ??
957 .sp
958 When writing code to extract data from named subpatterns using the
959 name-to-number map, remember that the length of the entries is likely to be
960 different for each compiled pattern.
961 .sp
962 PCRE_INFO_OKPARTIAL
963 .sp
964 Return 1 if the pattern can be used for partial matching, otherwise 0. The
965 fourth argument should point to an \fBint\fP variable. The
966 .\" HREF
967 \fBpcrepartial\fP
968 .\"
969 documentation lists the restrictions that apply to patterns when partial
970 matching is used.
971 .sp
972 PCRE_INFO_OPTIONS
973 .sp
974 Return a copy of the options with which the pattern was compiled. The fourth
975 argument should point to an \fBunsigned long int\fP variable. These option bits
976 are those specified in the call to \fBpcre_compile()\fP, modified by any
977 top-level option settings at the start of the pattern itself. In other words,
978 they are the options that will be in force when matching starts. For example,
979 if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
980 result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
981 .P
982 A pattern is automatically anchored by PCRE if all of its top-level
983 alternatives begin with one of the following:
984 .sp
985 ^ unless PCRE_MULTILINE is set
986 \eA always
987 \eG always
988 .\" JOIN
989 .* if PCRE_DOTALL is set and there are no back
990 references to the subpattern in which .* appears
991 .sp
992 For such patterns, the PCRE_ANCHORED bit is set in the options returned by
993 \fBpcre_fullinfo()\fP.
994 .sp
995 PCRE_INFO_SIZE
996 .sp
997 Return the size of the compiled pattern, that is, the value that was passed as
998 the argument to \fBpcre_malloc()\fP when PCRE was getting memory in which to
999 place the compiled data. The fourth argument should point to a \fBsize_t\fP
1000 variable.
1001 .sp
1002 PCRE_INFO_STUDYSIZE
1003 .sp
1004 Return the size of the data block pointed to by the \fIstudy_data\fP field in
1005 a \fBpcre_extra\fP block. That is, it is the value that was passed to
1006 \fBpcre_malloc()\fP when PCRE was getting memory into which to place the data
1007 created by \fBpcre_study()\fP. The fourth argument should point to a
1008 \fBsize_t\fP variable.
1009 .
1010 .
1011 .SH "OBSOLETE INFO FUNCTION"
1012 .rs
1013 .sp
1014 .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
1015 .B *\fIfirstcharptr\fP);
1016 .PP
1017 The \fBpcre_info()\fP function is now obsolete because its interface is too
1018 restrictive to return all the available data about a compiled pattern. New
1019 programs should use \fBpcre_fullinfo()\fP instead. The yield of
1020 \fBpcre_info()\fP is the number of capturing subpatterns, or one of the
1021 following negative numbers:
1022 .sp
1023 PCRE_ERROR_NULL the argument \fIcode\fP was NULL
1024 PCRE_ERROR_BADMAGIC the "magic number" was not found
1025 .sp
1026 If the \fIoptptr\fP argument is not NULL, a copy of the options with which the
1027 pattern was compiled is placed in the integer it points to (see
1028 PCRE_INFO_OPTIONS above).
1029 .P
1030 If the pattern is not anchored and the \fIfirstcharptr\fP argument is not NULL,
1031 it is used to pass back information about the first character of any matched
1032 string (see PCRE_INFO_FIRSTBYTE above).
1033 .
1034 .
1035 .SH "REFERENCE COUNTS"
1036 .rs
1037 .sp
1038 .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
1039 .PP
1040 The \fBpcre_refcount()\fP function is used to maintain a reference count in the
1041 data block that contains a compiled pattern. It is provided for the benefit of
1042 applications that operate in an object-oriented manner, where different parts
1043 of the application may be using the same compiled pattern, but you want to free
1044 the block when they are all done.
1045 .P
1046 When a pattern is compiled, the reference count field is initialized to zero.
1047 It is changed only by calling this function, whose action is to add the
1048 \fIadjust\fP value (which may be positive or negative) to it. The yield of the
1049 function is the new value. However, the value of the count is constrained to
1050 lie between 0 and 65535, inclusive. If the new value is outside these limits,
1051 it is forced to the appropriate limit value.
1052 .P
1053 Except when it is zero, the reference count is not correctly preserved if a
1054 pattern is compiled on one host and then transferred to a host whose byte-order
1055 is different. (This seems a highly unlikely scenario.)
1056 .
1057 .
1058 .SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION"
1059 .rs
1060 .sp
1061 .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
1062 .ti +5n
1063 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
1064 .ti +5n
1065 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
1066 .P
1067 The function \fBpcre_exec()\fP is called to match a subject string against a
1068 compiled pattern, which is passed in the \fIcode\fP argument. If the
1069 pattern has been studied, the result of the study should be passed in the
1070 \fIextra\fP argument. This function is the main matching facility of the
1071 library, and it operates in a Perl-like manner. For specialist use there is
1072 also an alternative matching function, which is described
1073 .\" HTML <a href="#dfamatch">
1074 .\" </a>
1075 below
1076 .\"
1077 in the section about the \fBpcre_dfa_exec()\fP function.
1078 .P
1079 In most applications, the pattern will have been compiled (and optionally
1080 studied) in the same process that calls \fBpcre_exec()\fP. However, it is
1081 possible to save compiled patterns and study data, and then use them later
1082 in different processes, possibly even on different hosts. For a discussion
1083 about this, see the
1084 .\" HREF
1085 \fBpcreprecompile\fP
1086 .\"
1087 documentation.
1088 .P
1089 Here is an example of a simple call to \fBpcre_exec()\fP:
1090 .sp
1091 int rc;
1092 int ovector[30];
1093 rc = pcre_exec(
1094 re, /* result of pcre_compile() */
1095 NULL, /* we didn't study the pattern */
1096 "some string", /* the subject string */
1097 11, /* the length of the subject string */
1098 0, /* start at offset 0 in the subject */
1099 0, /* default options */
1100 ovector, /* vector of integers for substring information */
1101 30); /* number of elements (NOT size in bytes) */
1102 .
1103 .\" HTML <a name="extradata"></a>
1104 .SS "Extra data for \fBpcre_exec()\fR"
1105 .rs
1106 .sp
1107 If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP
1108 data block. The \fBpcre_study()\fP function returns such a block (when it
1109 doesn't return NULL), but you can also create one for yourself, and pass
1110 additional information in it. The \fBpcre_extra\fP block contains the following
1111 fields (not necessarily in this order):
1112 .sp
1113 unsigned long int \fIflags\fP;
1114 void *\fIstudy_data\fP;
1115 unsigned long int \fImatch_limit\fP;
1116 unsigned long int \fImatch_limit_recursion\fP;
1117 void *\fIcallout_data\fP;
1118 const unsigned char *\fItables\fP;
1119 .sp
1120 The \fIflags\fP field is a bitmap that specifies which of the other fields
1121 are set. The flag bits are:
1122 .sp
1123 PCRE_EXTRA_STUDY_DATA
1124 PCRE_EXTRA_MATCH_LIMIT
1125 PCRE_EXTRA_MATCH_LIMIT_RECURSION
1126 PCRE_EXTRA_CALLOUT_DATA
1127 PCRE_EXTRA_TABLES
1128 .sp
1129 Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the
1130 \fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with
1131 the appropriate flag bit. You should not set this yourself, but you may add to
1132 the block by setting the other fields and their corresponding flag bits.
1133 .P
1134 The \fImatch_limit\fP field provides a means of preventing PCRE from using up a
1135 vast amount of resources when running patterns that are not going to match,
1136 but which have a very large number of possibilities in their search trees. The
1137 classic example is the use of nested unlimited repeats.
1138 .P
1139 Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly
1140 (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the
1141 number of times this function is called during a match, which has the effect of
1142 limiting the amount of backtracking that can take place. For patterns that are
1143 not anchored, the count restarts from zero for each position in the subject
1144 string.
1145 .P
1146 The default value for the limit can be set when PCRE is built; the default
1147 default is 10 million, which handles all but the most extreme cases. You can
1148 override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP
1149 block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in
1150 the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns
1151 PCRE_ERROR_MATCHLIMIT.
1152 .P
1153 The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but
1154 instead of limiting the total number of times that \fBmatch()\fP is called, it
1155 limits the depth of recursion. The recursion depth is a smaller number than the
1156 total number of calls, because not all calls to \fBmatch()\fP are recursive.
1157 This limit is of use only if it is set smaller than \fImatch_limit\fP.
1158 .P
1159 Limiting the recursion depth limits the amount of stack that can be used, or,
1160 when PCRE has been compiled to use memory on the heap instead of the stack, the
1161 amount of heap memory that can be used.
1162 .P
1163 The default value for \fImatch_limit_recursion\fP can be set when PCRE is
1164 built; the default default is the same value as the default for
1165 \fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP
1166 with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and
1167 PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
1168 is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1169 .P
1170 The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,
1171 which is described in the
1172 .\" HREF
1173 \fBpcrecallout\fP
1174 .\"
1175 documentation.
1176 .P
1177 The \fItables\fP field is used to pass a character tables pointer to
1178 \fBpcre_exec()\fP; this overrides the value that is stored with the compiled
1179 pattern. A non-NULL value is stored with the compiled pattern only if custom
1180 tables were supplied to \fBpcre_compile()\fP via its \fItableptr\fP argument.
1181 If NULL is passed to \fBpcre_exec()\fP using this mechanism, it forces PCRE's
1182 internal tables to be used. This facility is helpful when re-using patterns
1183 that have been saved after compiling with an external set of tables, because
1184 the external tables might be at a different address when \fBpcre_exec()\fP is
1185 called. See the
1186 .\" HREF
1187 \fBpcreprecompile\fP
1188 .\"
1189 documentation for a discussion of saving compiled patterns for later use.
1190 .
1191 .\" HTML <a name="execoptions"></a>
1192 .SS "Option bits for \fBpcre_exec()\fP"
1193 .rs
1194 .sp
1195 The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be
1196 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1197 PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
1198 .sp
1199 PCRE_ANCHORED
1200 .sp
1201 The PCRE_ANCHORED option limits \fBpcre_exec()\fP to matching at the first
1202 matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out
1203 to be anchored by virtue of its contents, it cannot be made unachored at
1204 matching time.
1205 .sp
1206 PCRE_NEWLINE_CR
1207 PCRE_NEWLINE_LF
1208 PCRE_NEWLINE_CRLF
1209 PCRE_NEWLINE_ANYCRLF
1210 PCRE_NEWLINE_ANY
1211 .sp
1212 These options override the newline definition that was chosen or defaulted when
1213 the pattern was compiled. For details, see the description of
1214 \fBpcre_compile()\fP above. During matching, the newline choice affects the
1215 behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1216 the way the match position is advanced after a match failure for an unanchored
1217 pattern.
1218 .P
1219 When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
1220 match attempt for an unanchored pattern fails when the current position is at a
1221 CRLF sequence, and the pattern contains no explicit matches for CR or LF
1222 characters, the match position is advanced by two characters instead of one, in
1223 other words, to after the CRLF.
1224 .P
1225 The above rule is a compromise that makes the most common cases work as
1226 expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1227 set), it does not match the string "\er\enA" because, after failing at the
1228 start, it skips both the CR and the LF before retrying. However, the pattern
1229 [\er\en]A does match that string, because it contains an explicit CR or LF
1230 reference, and so advances only by one character after the first failure.
1231 .P
1232 An explicit match for CR of LF is either a literal appearance of one of those
1233 characters, or one of the \er or \en escape sequences. Implicit matches such as
1234 [^X] do not count, nor does \es (which includes CR and LF in the characters
1235 that it matches).
1236 .P
1237 Notwithstanding the above, anomalous effects may still occur when CRLF is a
1238 valid newline sequence and explicit \er or \en escapes appear in the pattern.
1239 .sp
1240 PCRE_NOTBOL
1241 .sp
1242 This option specifies that first character of the subject string is not the
1243 beginning of a line, so the circumflex metacharacter should not match before
1244 it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex
1245 never to match. This option affects only the behaviour of the circumflex
1246 metacharacter. It does not affect \eA.
1247 .sp
1248 PCRE_NOTEOL
1249 .sp
1250 This option specifies that the end of the subject string is not the end of a
1251 line, so the dollar metacharacter should not match it nor (except in multiline
1252 mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at
1253 compile time) causes dollar never to match. This option affects only the
1254 behaviour of the dollar metacharacter. It does not affect \eZ or \ez.
1255 .sp
1256 PCRE_NOTEMPTY
1257 .sp
1258 An empty string is not considered to be a valid match if this option is set. If
1259 there are alternatives in the pattern, they are tried. If all the alternatives
1260 match the empty string, the entire match fails. For example, if the pattern
1261 .sp
1262 a?b?
1263 .sp
1264 is applied to a string not beginning with "a" or "b", it matches the empty
1265 string at the start of the subject. With PCRE_NOTEMPTY set, this match is not
1266 valid, so PCRE searches further into the string for occurrences of "a" or "b".
1267 .P
1268 Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case
1269 of a pattern match of the empty string within its \fBsplit()\fP function, and
1270 when using the /g modifier. It is possible to emulate Perl's behaviour after
1271 matching a null string by first trying the match again at the same offset with
1272 PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the
1273 starting offset (see below) and trying an ordinary match again. There is some
1274 code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.
1275 .sp
1276 PCRE_NO_UTF8_CHECK
1277 .sp
1278 When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
1279 string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1280 The value of \fIstartoffset\fP is also checked to ensure that it points to the
1281 start of a UTF-8 character. There is a discussion about the validity of UTF-8
1282 strings in the
1283 .\" HTML <a href="pcre.html#utf8strings">
1284 .\" </a>
1285 section on UTF-8 support
1286 .\"
1287 in the main
1288 .\" HREF
1289 \fBpcre\fP
1290 .\"
1291 page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1292 the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1293 PCRE_ERROR_BADUTF8_OFFSET is returned.
1294 .P
1295 If you already know that your subject is valid, and you want to skip these
1296 checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
1297 calling \fBpcre_exec()\fP. You might want to do this for the second and
1298 subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find
1299 all the matches in a single subject string. However, you should be sure that
1300 the value of \fIstartoffset\fP points to the start of a UTF-8 character. When
1301 PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a
1302 subject, or a value of \fIstartoffset\fP that does not point to the start of a
1303 UTF-8 character, is undefined. Your program may crash.
1304 .sp
1305 PCRE_PARTIAL
1306 .sp
1307 This option turns on the partial matching feature. If the subject string fails
1308 to match the pattern, but at some point during the matching process the end of
1309 the subject was reached (that is, the subject partially matches the pattern and
1310 the failure to match occurred only because there were not enough subject
1311 characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of
1312 PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what
1313 may appear in the pattern. These are discussed in the
1314 .\" HREF
1315 \fBpcrepartial\fP
1316 .\"
1317 documentation.
1318 .
1319 .SS "The string to be matched by \fBpcre_exec()\fP"
1320 .rs
1321 .sp
1322 The subject string is passed to \fBpcre_exec()\fP as a pointer in
1323 \fIsubject\fP, a length in \fIlength\fP, and a starting byte offset in
1324 \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a
1325 UTF-8 character. Unlike the pattern string, the subject may contain binary zero
1326 bytes. When the starting offset is zero, the search for a match starts at the
1327 beginning of the subject, and this is by far the most common case.
1328 .P
1329 A non-zero starting offset is useful when searching for another match in the
1330 same subject by calling \fBpcre_exec()\fP again after a previous success.
1331 Setting \fIstartoffset\fP differs from just passing over a shortened string and
1332 setting PCRE_NOTBOL in the case of a pattern that begins with any kind of
1333 lookbehind. For example, consider the pattern
1334 .sp
1335 \eBiss\eB
1336 .sp
1337 which finds occurrences of "iss" in the middle of words. (\eB matches only if
1338 the current position in the subject is not a word boundary.) When applied to
1339 the string "Mississipi" the first call to \fBpcre_exec()\fP finds the first
1340 occurrence. If \fBpcre_exec()\fP is called again with just the remainder of the
1341 subject, namely "issipi", it does not match, because \eB is always false at the
1342 start of the subject, which is deemed to be a word boundary. However, if
1343 \fBpcre_exec()\fP is passed the entire string again, but with \fIstartoffset\fP
1344 set to 4, it finds the second occurrence of "iss" because it is able to look
1345 behind the starting point to discover that it is preceded by a letter.
1346 .P
1347 If a non-zero starting offset is passed when the pattern is anchored, one
1348 attempt to match at the given offset is made. This can only succeed if the
1349 pattern does not require the match to be at the start of the subject.
1350 .
1351 .SS "How \fBpcre_exec()\fP returns captured substrings"
1352 .rs
1353 .sp
1354 In general, a pattern matches a certain portion of the subject, and in
1355 addition, further substrings from the subject may be picked out by parts of the
1356 pattern. Following the usage in Jeffrey Friedl's book, this is called
1357 "capturing" in what follows, and the phrase "capturing subpattern" is used for
1358 a fragment of a pattern that picks out a substring. PCRE supports several other
1359 kinds of parenthesized subpattern that do not cause substrings to be captured.
1360 .P
1361 Captured substrings are returned to the caller via a vector of integer offsets
1362 whose address is passed in \fIovector\fP. The number of elements in the vector
1363 is passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP:
1364 this argument is NOT the size of \fIovector\fP in bytes.
1365 .P
1366 The first two-thirds of the vector is used to pass back captured substrings,
1367 each substring using a pair of integers. The remaining third of the vector is
1368 used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1369 and is not available for passing back information. The length passed in
1370 \fIovecsize\fP should always be a multiple of three. If it is not, it is
1371 rounded down.
1372 .P
1373 When a match is successful, information about captured substrings is returned
1374 in pairs of integers, starting at the beginning of \fIovector\fP, and
1375 continuing up to two-thirds of its length at the most. The first element of a
1376 pair is set to the offset of the first character in a substring, and the second
1377 is set to the offset of the first character after the end of a substring. The
1378 first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the
1379 subject string matched by the entire pattern. The next pair is used for the
1380 first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP
1381 is one more than the highest numbered pair that has been set. For example, if
1382 two substrings have been captured, the returned value is 3. If there are no
1383 capturing subpatterns, the return value from a successful match is 1,
1384 indicating that just the first pair of offsets has been set.
1385 .P
1386 If a capturing subpattern is matched repeatedly, it is the last portion of the
1387 string that it matched that is returned.
1388 .P
1389 If the vector is too small to hold all the captured substring offsets, it is
1390 used as far as possible (up to two-thirds of its length), and the function
1391 returns a value of zero. In particular, if the substring offsets are not of
1392 interest, \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and
1393 \fIovecsize\fP as zero. However, if the pattern contains back references and
1394 the \fIovector\fP is not big enough to remember the related substrings, PCRE
1395 has to get additional memory for use during matching. Thus it is usually
1396 advisable to supply an \fIovector\fP.
1397 .P
1398 The \fBpcre_info()\fP function can be used to find out how many capturing
1399 subpatterns there are in a compiled pattern. The smallest size for
1400 \fIovector\fP that will allow for \fIn\fP captured substrings, in addition to
1401 the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3.
1402 .P
1403 It is possible for capturing subpattern number \fIn+1\fP to match some part of
1404 the subject when subpattern \fIn\fP has not been used at all. For example, if
1405 the string "abc" is matched against the pattern (a|(z))(bc) the return from the
1406 function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
1407 happens, both values in the offset pairs corresponding to unused subpatterns
1408 are set to -1.
1409 .P
1410 Offset values that correspond to unused subpatterns at the end of the
1411 expression are also set to -1. For example, if the string "abc" is matched
1412 against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1413 return from the function is 2, because the highest used capturing subpattern
1414 number is 1. However, you can refer to the offsets for the second and third
1415 capturing subpatterns if you wish (assuming the vector is large enough, of
1416 course).
1417 .P
1418 Some convenience functions are provided for extracting the captured substrings
1419 as separate strings. These are described below.
1420 .
1421 .\" HTML <a name="errorlist"></a>
1422 .SS "Error return values from \fBpcre_exec()\fP"
1423 .rs
1424 .sp
1425 If \fBpcre_exec()\fP fails, it returns a negative number. The following are
1426 defined in the header file:
1427 .sp
1428 PCRE_ERROR_NOMATCH (-1)
1429 .sp
1430 The subject string did not match the pattern.
1431 .sp
1432 PCRE_ERROR_NULL (-2)
1433 .sp
1434 Either \fIcode\fP or \fIsubject\fP was passed as NULL, or \fIovector\fP was
1435 NULL and \fIovecsize\fP was not zero.
1436 .sp
1437 PCRE_ERROR_BADOPTION (-3)
1438 .sp
1439 An unrecognized bit was set in the \fIoptions\fP argument.
1440 .sp
1441 PCRE_ERROR_BADMAGIC (-4)
1442 .sp
1443 PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch
1444 the case when it is passed a junk pointer and to detect when a pattern that was
1445 compiled in an environment of one endianness is run in an environment with the
1446 other endianness. This is the error that PCRE gives when the magic number is
1447 not present.
1448 .sp
1449 PCRE_ERROR_UNKNOWN_OPCODE (-5)
1450 .sp
1451 While running the pattern match, an unknown item was encountered in the
1452 compiled pattern. This error could be caused by a bug in PCRE or by overwriting
1453 of the compiled pattern.
1454 .sp
1455 PCRE_ERROR_NOMEMORY (-6)
1456 .sp
1457 If a pattern contains back references, but the \fIovector\fP that is passed to
1458 \fBpcre_exec()\fP is not big enough to remember the referenced substrings, PCRE
1459 gets a block of memory at the start of matching to use for this purpose. If the
1460 call via \fBpcre_malloc()\fP fails, this error is given. The memory is
1461 automatically freed at the end of matching.
1462 .sp
1463 PCRE_ERROR_NOSUBSTRING (-7)
1464 .sp
1465 This error is used by the \fBpcre_copy_substring()\fP,
1466 \fBpcre_get_substring()\fP, and \fBpcre_get_substring_list()\fP functions (see
1467 below). It is never returned by \fBpcre_exec()\fP.
1468 .sp
1469 PCRE_ERROR_MATCHLIMIT (-8)
1470 .sp
1471 The backtracking limit, as specified by the \fImatch_limit\fP field in a
1472 \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1473 above.
1474 .sp
1475 PCRE_ERROR_CALLOUT (-9)
1476 .sp
1477 This error is never generated by \fBpcre_exec()\fP itself. It is provided for
1478 use by callout functions that want to yield a distinctive error code. See the
1479 .\" HREF
1480 \fBpcrecallout\fP
1481 .\"
1482 documentation for details.
1483 .sp
1484 PCRE_ERROR_BADUTF8 (-10)
1485 .sp
1486 A string that contains an invalid UTF-8 byte sequence was passed as a subject.
1487 .sp
1488 PCRE_ERROR_BADUTF8_OFFSET (-11)
1489 .sp
1490 The UTF-8 byte sequence that was passed as a subject was valid, but the value
1491 of \fIstartoffset\fP did not point to the beginning of a UTF-8 character.
1492 .sp
1493 PCRE_ERROR_PARTIAL (-12)
1494 .sp
1495 The subject string did not match, but it did match partially. See the
1496 .\" HREF
1497 \fBpcrepartial\fP
1498 .\"
1499 documentation for details of partial matching.
1500 .sp
1501 PCRE_ERROR_BADPARTIAL (-13)
1502 .sp
1503 The PCRE_PARTIAL option was used with a compiled pattern containing items that
1504 are not supported for partial matching. See the
1505 .\" HREF
1506 \fBpcrepartial\fP
1507 .\"
1508 documentation for details of partial matching.
1509 .sp
1510 PCRE_ERROR_INTERNAL (-14)
1511 .sp
1512 An unexpected internal error has occurred. This error could be caused by a bug
1513 in PCRE or by overwriting of the compiled pattern.
1514 .sp
1515 PCRE_ERROR_BADCOUNT (-15)
1516 .sp
1517 This error is given if the value of the \fIovecsize\fP argument is negative.
1518 .sp
1519 PCRE_ERROR_RECURSIONLIMIT (-21)
1520 .sp
1521 The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1522 field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1523 description above.
1524 .sp
1525 PCRE_ERROR_BADNEWLINE (-23)
1526 .sp
1527 An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1528 .P
1529 Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1530 .
1531 .
1532 .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
1533 .rs
1534 .sp
1535 .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1536 .ti +5n
1537 .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
1538 .ti +5n
1539 .B int \fIbuffersize\fP);
1540 .PP
1541 .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1542 .ti +5n
1543 .B int \fIstringcount\fP, int \fIstringnumber\fP,
1544 .ti +5n
1545 .B const char **\fIstringptr\fP);
1546 .PP
1547 .B int pcre_get_substring_list(const char *\fIsubject\fP,
1548 .ti +5n
1549 .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
1550 .PP
1551 Captured substrings can be accessed directly by using the offsets returned by
1552 \fBpcre_exec()\fP in \fIovector\fP. For convenience, the functions
1553 \fBpcre_copy_substring()\fP, \fBpcre_get_substring()\fP, and
1554 \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
1555 as new, separate, zero-terminated strings. These functions identify substrings
1556 by number. The next section describes functions for extracting named
1557 substrings.
1558 .P
1559 A substring that contains a binary zero is correctly extracted and has a
1560 further zero added on the end, but the result is not, of course, a C string.
1561 However, you can process such a string by referring to the length that is
1562 returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
1563 Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
1564 for handling strings containing binary zeros, because the end of the final
1565 string is not independently indicated.
1566 .P
1567 The first three arguments are the same for all three of these functions:
1568 \fIsubject\fP is the subject string that has just been successfully matched,
1569 \fIovector\fP is a pointer to the vector of integer offsets that was passed to
1570 \fBpcre_exec()\fP, and \fIstringcount\fP is the number of substrings that were
1571 captured by the match, including the substring that matched the entire regular
1572 expression. This is the value returned by \fBpcre_exec()\fP if it is greater
1573 than zero. If \fBpcre_exec()\fP returned zero, indicating that it ran out of
1574 space in \fIovector\fP, the value passed as \fIstringcount\fP should be the
1575 number of elements in the vector divided by three.
1576 .P
1577 The functions \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP
1578 extract a single substring, whose number is given as \fIstringnumber\fP. A
1579 value of zero extracts the substring that matched the entire pattern, whereas
1580 higher values extract the captured substrings. For \fBpcre_copy_substring()\fP,
1581 the string is placed in \fIbuffer\fP, whose length is given by
1582 \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is
1583 obtained via \fBpcre_malloc\fP, and its address is returned via
1584 \fIstringptr\fP. The yield of the function is the length of the string, not
1585 including the terminating zero, or one of these error codes:
1586 .sp
1587 PCRE_ERROR_NOMEMORY (-6)
1588 .sp
1589 The buffer was too small for \fBpcre_copy_substring()\fP, or the attempt to get
1590 memory failed for \fBpcre_get_substring()\fP.
1591 .sp
1592 PCRE_ERROR_NOSUBSTRING (-7)
1593 .sp
1594 There is no substring whose number is \fIstringnumber\fP.
1595 .P
1596 The \fBpcre_get_substring_list()\fP function extracts all available substrings
1597 and builds a list of pointers to them. All this is done in a single block of
1598 memory that is obtained via \fBpcre_malloc\fP. The address of the memory block
1599 is returned via \fIlistptr\fP, which is also the start of the list of string
1600 pointers. The end of the list is marked by a NULL pointer. The yield of the
1601 function is zero if all went well, or the error code
1602 .sp
1603 PCRE_ERROR_NOMEMORY (-6)
1604 .sp
1605 if the attempt to get the memory block failed.
1606 .P
1607 When any of these functions encounter a substring that is unset, which can
1608 happen when capturing subpattern number \fIn+1\fP matches some part of the
1609 subject, but subpattern \fIn\fP has not been used at all, they return an empty
1610 string. This can be distinguished from a genuine zero-length substring by
1611 inspecting the appropriate offset in \fIovector\fP, which is negative for unset
1612 substrings.
1613 .P
1614 The two convenience functions \fBpcre_free_substring()\fP and
1615 \fBpcre_free_substring_list()\fP can be used to free the memory returned by
1616 a previous call of \fBpcre_get_substring()\fP or
1617 \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
1618 the function pointed to by \fBpcre_free\fP, which of course could be called
1619 directly from a C program. However, PCRE is used in some situations where it is
1620 linked via a special interface to another programming language that cannot use
1621 \fBpcre_free\fP directly; it is for these cases that the functions are
1622 provided.
1623 .
1624 .
1625 .SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME"
1626 .rs
1627 .sp
1628 .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
1629 .ti +5n
1630 .B const char *\fIname\fP);
1631 .PP
1632 .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1633 .ti +5n
1634 .B const char *\fIsubject\fP, int *\fIovector\fP,
1635 .ti +5n
1636 .B int \fIstringcount\fP, const char *\fIstringname\fP,
1637 .ti +5n
1638 .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1639 .PP
1640 .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1641 .ti +5n
1642 .B const char *\fIsubject\fP, int *\fIovector\fP,
1643 .ti +5n
1644 .B int \fIstringcount\fP, const char *\fIstringname\fP,
1645 .ti +5n
1646 .B const char **\fIstringptr\fP);
1647 .PP
1648 To extract a substring by name, you first have to find associated number.
1649 For example, for this pattern
1650 .sp
1651 (a+)b(?<xxx>\ed+)...
1652 .sp
1653 the number of the subpattern called "xxx" is 2. If the name is known to be
1654 unique (PCRE_DUPNAMES was not set), you can find the number from the name by
1655 calling \fBpcre_get_stringnumber()\fP. The first argument is the compiled
1656 pattern, and the second is the name. The yield of the function is the
1657 subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of
1658 that name.
1659 .P
1660 Given the number, you can extract the substring directly, or use one of the
1661 functions described in the previous section. For convenience, there are also
1662 two functions that do the whole job.
1663 .P
1664 Most of the arguments of \fBpcre_copy_named_substring()\fP and
1665 \fBpcre_get_named_substring()\fP are the same as those for the similarly named
1666 functions that extract by number. As these are described in the previous
1667 section, they are not re-described here. There are just two differences:
1668 .P
1669 First, instead of a substring number, a substring name is given. Second, there
1670 is an extra argument, given at the start, which is a pointer to the compiled
1671 pattern. This is needed in order to gain access to the name-to-number
1672 translation table.
1673 .P
1674 These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1675 then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1676 appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1677 the behaviour may not be what you want (see the next section).
1678 .
1679 .
1680 .SH "DUPLICATE SUBPATTERN NAMES"
1681 .rs
1682 .sp
1683 .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
1684 .ti +5n
1685 .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
1686 .PP
1687 When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
1688 are not required to be unique. Normally, patterns with duplicate names are such
1689 that in any one match, only one of the named subpatterns participates. An
1690 example is shown in the
1691 .\" HREF
1692 \fBpcrepattern\fP
1693 .\"
1694 documentation.
1695 .P
1696 When duplicates are present, \fBpcre_copy_named_substring()\fP and
1697 \fBpcre_get_named_substring()\fP return the first substring corresponding to
1698 the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
1699 returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1700 returns one of the numbers that are associated with the name, but it is not
1701 defined which it is.
1702 .P
1703 If you want to get full details of all captured substrings for a given name,
1704 you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1705 argument is the compiled pattern, and the second is the name. The third and
1706 fourth are pointers to variables which are updated by the function. After it
1707 has run, they point to the first and last entries in the name-to-number table
1708 for the given name. The function itself returns the length of each entry, or
1709 PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1710 described above in the section entitled \fIInformation about a pattern\fP.
1711 Given all the relevant entries for the name, you can extract each of their
1712 numbers, and hence the captured data, if any.
1713 .
1714 .
1715 .SH "FINDING ALL POSSIBLE MATCHES"
1716 .rs
1717 .sp
1718 The traditional matching function uses a similar algorithm to Perl, which stops
1719 when it finds the first match, starting at a given point in the subject. If you
1720 want to find all possible matches, or the longest possible match, consider
1721 using the alternative matching function (see below) instead. If you cannot use
1722 the alternative function, but still need to find all possible matches, you
1723 can kludge it up by making use of the callout facility, which is described in
1724 the
1725 .\" HREF
1726 \fBpcrecallout\fP
1727 .\"
1728 documentation.
1729 .P
1730 What you have to do is to insert a callout right at the end of the pattern.
1731 When your callout function is called, extract and save the current matched
1732 substring. Then return 1, which forces \fBpcre_exec()\fP to backtrack and try
1733 other alternatives. Ultimately, when it runs out of matches, \fBpcre_exec()\fP
1734 will yield PCRE_ERROR_NOMATCH.
1735 .
1736 .
1737 .\" HTML <a name="dfamatch"></a>
1738 .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
1739 .rs
1740 .sp
1741 .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
1742 .ti +5n
1743 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
1744 .ti +5n
1745 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
1746 .ti +5n
1747 .B int *\fIworkspace\fP, int \fIwscount\fP);
1748 .P
1749 The function \fBpcre_dfa_exec()\fP is called to match a subject string against
1750 a compiled pattern, using a matching algorithm that scans the subject string
1751 just once, and does not backtrack. This has different characteristics to the
1752 normal algorithm, and is not compatible with Perl. Some of the features of PCRE
1753 patterns are not supported. Nevertheless, there are times when this kind of
1754 matching can be useful. For a discussion of the two matching algorithms, see
1755 the
1756 .\" HREF
1757 \fBpcrematching\fP
1758 .\"
1759 documentation.
1760 .P
1761 The arguments for the \fBpcre_dfa_exec()\fP function are the same as for
1762 \fBpcre_exec()\fP, plus two extras. The \fIovector\fP argument is used in a
1763 different way, and this is described below. The other common arguments are used
1764 in the same way as for \fBpcre_exec()\fP, so their description is not repeated
1765 here.
1766 .P
1767 The two additional arguments provide workspace for the function. The workspace
1768 vector should contain at least 20 elements. It is used for keeping track of
1769 multiple paths through the pattern tree. More workspace will be needed for
1770 patterns and subjects where there are a lot of potential matches.
1771 .P
1772 Here is an example of a simple call to \fBpcre_dfa_exec()\fP:
1773 .sp
1774 int rc;
1775 int ovector[10];
1776 int wspace[20];
1777 rc = pcre_dfa_exec(
1778 re, /* result of pcre_compile() */
1779 NULL, /* we didn't study the pattern */
1780 "some string", /* the subject string */
1781 11, /* the length of the subject string */
1782 0, /* start at offset 0 in the subject */
1783 0, /* default options */
1784 ovector, /* vector of integers for substring information */
1785 10, /* number of elements (NOT size in bytes) */
1786 wspace, /* working space vector */
1787 20); /* number of elements (NOT size in bytes) */
1788 .
1789 .SS "Option bits for \fBpcre_dfa_exec()\fP"
1790 .rs
1791 .sp
1792 The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be
1793 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1794 PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,
1795 PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are
1796 the same as for \fBpcre_exec()\fP, so their description is not repeated here.
1797 .sp
1798 PCRE_PARTIAL
1799 .sp
1800 This has the same general effect as it does for \fBpcre_exec()\fP, but the
1801 details are slightly different. When PCRE_PARTIAL is set for
1802 \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into
1803 PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no
1804 complete matches, but there is still at least one matching possibility. The
1805 portion of the string that provided the partial match is set as the first
1806 matching string.
1807 .sp
1808 PCRE_DFA_SHORTEST
1809 .sp
1810 Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
1811 soon as it has found one match. Because of the way the alternative algorithm
1812 works, this is necessarily the shortest possible match at the first possible
1813 matching point in the subject string.
1814 .sp
1815 PCRE_DFA_RESTART
1816 .sp
1817 When \fBpcre_dfa_exec()\fP is called with the PCRE_PARTIAL option, and returns
1818 a partial match, it is possible to call it again, with additional subject
1819 characters, and have it continue with the same match. The PCRE_DFA_RESTART
1820 option requests this action; when it is set, the \fIworkspace\fP and
1821 \fIwscount\fP options must reference the same vector as before because data
1822 about the match so far is left in them after a partial match. There is more
1823 discussion of this facility in the
1824 .\" HREF
1825 \fBpcrepartial\fP
1826 .\"
1827 documentation.
1828 .
1829 .SS "Successful returns from \fBpcre_dfa_exec()\fP"
1830 .rs
1831 .sp
1832 When \fBpcre_dfa_exec()\fP succeeds, it may have matched more than one
1833 substring in the subject. Note, however, that all the matches from one run of
1834 the function start at the same point in the subject. The shorter matches are
1835 all initial substrings of the longer matches. For example, if the pattern
1836 .sp
1837 <.*>
1838 .sp
1839 is matched against the string
1840 .sp
1841 This is <something> <something else> <something further> no more
1842 .sp
1843 the three matched strings are
1844 .sp
1845 <something>
1846 <something> <something else>
1847 <something> <something else> <something further>
1848 .sp
1849 On success, the yield of the function is a number greater than zero, which is
1850 the number of matched substrings. The substrings themselves are returned in
1851 \fIovector\fP. Each string uses two elements; the first is the offset to the
1852 start, and the second is the offset to the end. In fact, all the strings have
1853 the same start offset. (Space could have been saved by giving this only once,
1854 but it was decided to retain some compatibility with the way \fBpcre_exec()\fP
1855 returns data, even though the meaning of the strings is different.)
1856 .P
1857 The strings are returned in reverse order of length; that is, the longest
1858 matching string is given first. If there were too many matches to fit into
1859 \fIovector\fP, the yield of the function is zero, and the vector is filled with
1860 the longest matches.
1861 .
1862 .SS "Error returns from \fBpcre_dfa_exec()\fP"
1863 .rs
1864 .sp
1865 The \fBpcre_dfa_exec()\fP function returns a negative number when it fails.
1866 Many of the errors are the same as for \fBpcre_exec()\fP, and these are
1867 described
1868 .\" HTML <a href="#errorlist">
1869 .\" </a>
1870 above.
1871 .\"
1872 There are in addition the following errors that are specific to
1873 \fBpcre_dfa_exec()\fP:
1874 .sp
1875 PCRE_ERROR_DFA_UITEM (-16)
1876 .sp
1877 This return is given if \fBpcre_dfa_exec()\fP encounters an item in the pattern
1878 that it does not support, for instance, the use of \eC or a back reference.
1879 .sp
1880 PCRE_ERROR_DFA_UCOND (-17)
1881 .sp
1882 This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that
1883 uses a back reference for the condition, or a test for recursion in a specific
1884 group. These are not supported.
1885 .sp
1886 PCRE_ERROR_DFA_UMLIMIT (-18)
1887 .sp
1888 This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP
1889 block that contains a setting of the \fImatch_limit\fP field. This is not
1890 supported (it is meaningless).
1891 .sp
1892 PCRE_ERROR_DFA_WSSIZE (-19)
1893 .sp
1894 This return is given if \fBpcre_dfa_exec()\fP runs out of space in the
1895 \fIworkspace\fP vector.
1896 .sp
1897 PCRE_ERROR_DFA_RECURSE (-20)
1898 .sp
1899 When a recursive subpattern is processed, the matching function calls itself
1900 recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1901 error is given if the output vector is not large enough. This should be
1902 extremely rare, as a vector of size 1000 is used.
1903 .
1904 .
1905 .SH "SEE ALSO"
1906 .rs
1907 .sp
1908 \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1909 \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1910 \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1911 .
1912 .
1913 .SH AUTHOR
1914 .rs
1915 .sp
1916 .nf
1917 Philip Hazel
1918 University Computing Service
1919 Cambridge CB2 3QH, England.
1920 .fi
1921 .
1922 .
1923 .SH REVISION
1924 .rs
1925 .sp
1926 .nf
1927 Last updated: 10 September 2007
1928 Copyright (c) 1997-2007 University of Cambridge.
1929 .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