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

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

Parent Directory Parent Directory | Revision Log Revision Log


Revision 172 - (show annotations) (download)
Tue Jun 5 10:40:13 2007 UTC (7 years, 6 months ago) by ph10
File size: 80495 byte(s)
Drastically reduce workspace used for alternatives in groups; also some 
trailing space removals for a test release.

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