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

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

Parent Directory Parent Directory | Revision Log Revision Log


Revision 128 - (show annotations) (download)
Tue Mar 20 11:46:50 2007 UTC (7 years, 6 months ago) by ph10
File size: 79077 byte(s)
Make the use of dftables optional, and not the default. Further tidies to 
documentation.

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 four 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, or any Unicode newline sequence.
227 The Unicode newline sequences are the three just mentioned, plus the single
228 characters VT (vertical tab, U+000B), FF (formfeed, U+000C), NEL (next line,
229 U+0085), LS (line separator, U+2028), and PS (paragraph separator, U+2029).
230 .P
231 Each of the first three conventions is used by at least one operating system as
232 its standard newline sequence. When PCRE is built, a default can be specified.
233 The default default is LF, which is the Unix standard. When PCRE is run, the
234 default can be overridden, either when a pattern is compiled, or when it is
235 matched.
236 .P
237 In the PCRE documentation the word "newline" is used to mean "the character or
238 pair of characters that indicate a line break". The choice of newline
239 convention affects the handling of the dot, circumflex, and dollar
240 metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
241 recognized line ending sequence, the match position advancement for a
242 non-anchored pattern. The choice of newline convention does not affect the
243 interpretation of the \en or \er escape sequences.
244 .
245 .
246 .SH MULTITHREADING
247 .rs
248 .sp
249 The PCRE functions can be used in multi-threading applications, with the
250 proviso that the memory management functions pointed to by \fBpcre_malloc\fP,
251 \fBpcre_free\fP, \fBpcre_stack_malloc\fP, and \fBpcre_stack_free\fP, and the
252 callout function pointed to by \fBpcre_callout\fP, are shared by all threads.
253 .P
254 The compiled form of a regular expression is not altered during matching, so
255 the same compiled pattern can safely be used by several threads at once.
256 .
257 .
258 .SH "SAVING PRECOMPILED PATTERNS FOR LATER USE"
259 .rs
260 .sp
261 The compiled form of a regular expression can be saved and re-used at a later
262 time, possibly by a different program, and even on a host other than the one on
263 which it was compiled. Details are given in the
264 .\" HREF
265 \fBpcreprecompile\fP
266 .\"
267 documentation.
268 .
269 .
270 .SH "CHECKING BUILD-TIME OPTIONS"
271 .rs
272 .sp
273 .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
274 .PP
275 The function \fBpcre_config()\fP makes it possible for a PCRE client to
276 discover which optional features have been compiled into the PCRE library. The
277 .\" HREF
278 \fBpcrebuild\fP
279 .\"
280 documentation has more details about these optional features.
281 .P
282 The first argument for \fBpcre_config()\fP is an integer, specifying which
283 information is required; the second argument is a pointer to a variable into
284 which the information is placed. The following information is available:
285 .sp
286 PCRE_CONFIG_UTF8
287 .sp
288 The output is an integer that is set to one if UTF-8 support is available;
289 otherwise it is set to zero.
290 .sp
291 PCRE_CONFIG_UNICODE_PROPERTIES
292 .sp
293 The output is an integer that is set to one if support for Unicode character
294 properties is available; otherwise it is set to zero.
295 .sp
296 PCRE_CONFIG_NEWLINE
297 .sp
298 The output is an integer whose value specifies the default character sequence
299 that is recognized as meaning "newline". The four values that are supported
300 are: 10 for LF, 13 for CR, 3338 for CRLF, and -1 for ANY. The default should
301 normally be the standard sequence for your operating system.
302 .sp
303 PCRE_CONFIG_LINK_SIZE
304 .sp
305 The output is an integer that contains the number of bytes used for internal
306 linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values
307 allow larger regular expressions to be compiled, at the expense of slower
308 matching. The default value of 2 is sufficient for all but the most massive
309 patterns, since it allows the compiled pattern to be up to 64K in size.
310 .sp
311 PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
312 .sp
313 The output is an integer that contains the threshold above which the POSIX
314 interface uses \fBmalloc()\fP for output vectors. Further details are given in
315 the
316 .\" HREF
317 \fBpcreposix\fP
318 .\"
319 documentation.
320 .sp
321 PCRE_CONFIG_MATCH_LIMIT
322 .sp
323 The output is an integer that gives the default limit for the number of
324 internal matching function calls in a \fBpcre_exec()\fP execution. Further
325 details are given with \fBpcre_exec()\fP below.
326 .sp
327 PCRE_CONFIG_MATCH_LIMIT_RECURSION
328 .sp
329 The output is an integer that gives the default limit for the depth of
330 recursion when calling the internal matching function in a \fBpcre_exec()\fP
331 execution. Further details are given with \fBpcre_exec()\fP below.
332 .sp
333 PCRE_CONFIG_STACKRECURSE
334 .sp
335 The output is an integer that is set to one if internal recursion when running
336 \fBpcre_exec()\fP is implemented by recursive function calls that use the stack
337 to remember their state. This is the usual way that PCRE is compiled. The
338 output is zero if PCRE was compiled to use blocks of data on the heap instead
339 of recursive function calls. In this case, \fBpcre_stack_malloc\fP and
340 \fBpcre_stack_free\fP are called to manage memory blocks on the heap, thus
341 avoiding the use of the stack.
342 .
343 .
344 .SH "COMPILING A PATTERN"
345 .rs
346 .sp
347 .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
348 .ti +5n
349 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
350 .ti +5n
351 .B const unsigned char *\fItableptr\fP);
352 .sp
353 .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
354 .ti +5n
355 .B int *\fIerrorcodeptr\fP,
356 .ti +5n
357 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
358 .ti +5n
359 .B const unsigned char *\fItableptr\fP);
360 .P
361 Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be
362 called to compile a pattern into an internal form. The only difference between
363 the two interfaces is that \fBpcre_compile2()\fP has an additional argument,
364 \fIerrorcodeptr\fP, via which a numerical error code can be returned.
365 .P
366 The pattern is a C string terminated by a binary zero, and is passed in the
367 \fIpattern\fP argument. A pointer to a single block of memory that is obtained
368 via \fBpcre_malloc\fP is returned. This contains the compiled code and related
369 data. The \fBpcre\fP type is defined for the returned block; this is a typedef
370 for a structure whose contents are not externally defined. It is up to the
371 caller to free the memory (via \fBpcre_free\fP) when it is no longer required.
372 .P
373 Although the compiled code of a PCRE regex is relocatable, that is, it does not
374 depend on memory location, the complete \fBpcre\fP data block is not
375 fully relocatable, because it may contain a copy of the \fItableptr\fP
376 argument, which is an address (see below).
377 .P
378 The \fIoptions\fP argument contains various bit settings that affect the
379 compilation. It should be zero if no options are required. The available
380 options are described below. Some of them, in particular, those that are
381 compatible with Perl, can also be set and unset from within the pattern (see
382 the detailed description in the
383 .\" HREF
384 \fBpcrepattern\fP
385 .\"
386 documentation). For these options, the contents of the \fIoptions\fP argument
387 specifies their initial settings at the start of compilation and execution. The
388 PCRE_ANCHORED and PCRE_NEWLINE_\fIxxx\fP options can be set at the time of
389 matching as well as at compile time.
390 .P
391 If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
392 Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
393 NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual
394 error message. This is a static string that is part of the library. You must
395 not try to free it. The offset from the start of the pattern to the character
396 where the error was discovered is placed in the variable pointed to by
397 \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.
398 .P
399 If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the
400 \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is
401 returned via this argument in the event of an error. This is in addition to the
402 textual error message. Error codes and messages are listed below.
403 .P
404 If the final argument, \fItableptr\fP, is NULL, PCRE uses a default set of
405 character tables that are built when PCRE is compiled, using the default C
406 locale. Otherwise, \fItableptr\fP must be an address that is the result of a
407 call to \fBpcre_maketables()\fP. This value is stored with the compiled
408 pattern, and used again by \fBpcre_exec()\fP, unless another table pointer is
409 passed to it. For more discussion, see the section on locale support below.
410 .P
411 This code fragment shows a typical straightforward call to \fBpcre_compile()\fP:
412 .sp
413 pcre *re;
414 const char *error;
415 int erroffset;
416 re = pcre_compile(
417 "^A.*Z", /* the pattern */
418 0, /* default options */
419 &error, /* for error message */
420 &erroffset, /* for error offset */
421 NULL); /* use default character tables */
422 .sp
423 The following names for option bits are defined in the \fBpcre.h\fP header
424 file:
425 .sp
426 PCRE_ANCHORED
427 .sp
428 If this bit is set, the pattern is forced to be "anchored", that is, it is
429 constrained to match only at the first matching point in the string that is
430 being searched (the "subject string"). This effect can also be achieved by
431 appropriate constructs in the pattern itself, which is the only way to do it in
432 Perl.
433 .sp
434 PCRE_AUTO_CALLOUT
435 .sp
436 If this bit is set, \fBpcre_compile()\fP automatically inserts callout items,
437 all with number 255, before each pattern item. For discussion of the callout
438 facility, see the
439 .\" HREF
440 \fBpcrecallout\fP
441 .\"
442 documentation.
443 .sp
444 PCRE_CASELESS
445 .sp
446 If this bit is set, letters in the pattern match both upper and lower case
447 letters. It is equivalent to Perl's /i option, and it can be changed within a
448 pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the
449 concept of case for characters whose values are less than 128, so caseless
450 matching is always possible. For characters with higher values, the concept of
451 case is supported if PCRE is compiled with Unicode property support, but not
452 otherwise. If you want to use caseless matching for characters 128 and above,
453 you must ensure that PCRE is compiled with Unicode property support as well as
454 with UTF-8 support.
455 .sp
456 PCRE_DOLLAR_ENDONLY
457 .sp
458 If this bit is set, a dollar metacharacter in the pattern matches only at the
459 end of the subject string. Without this option, a dollar also matches
460 immediately before a newline at the end of the string (but not before any other
461 newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set.
462 There is no equivalent to this option in Perl, and no way to set it within a
463 pattern.
464 .sp
465 PCRE_DOTALL
466 .sp
467 If this bit is set, a dot metacharater in the pattern matches all characters,
468 including those that indicate newline. Without it, a dot does not match when
469 the current position is at a newline. This option is equivalent to Perl's /s
470 option, and it can be changed within a pattern by a (?s) option setting. A
471 negative class such as [^a] always matches newline characters, independent of
472 the setting of this option.
473 .sp
474 PCRE_DUPNAMES
475 .sp
476 If this bit is set, names used to identify capturing subpatterns need not be
477 unique. This can be helpful for certain types of pattern when it is known that
478 only one instance of the named subpattern can ever be matched. There are more
479 details of named subpatterns below; see also the
480 .\" HREF
481 \fBpcrepattern\fP
482 .\"
483 documentation.
484 .sp
485 PCRE_EXTENDED
486 .sp
487 If this bit is set, whitespace data characters in the pattern are totally
488 ignored except when escaped or inside a character class. Whitespace does not
489 include the VT character (code 11). In addition, characters between an
490 unescaped # outside a character class and the next newline, inclusive, are also
491 ignored. This is equivalent to Perl's /x option, and it can be changed within a
492 pattern by a (?x) option setting.
493 .P
494 This option makes it possible to include comments inside complicated patterns.
495 Note, however, that this applies only to data characters. Whitespace characters
496 may never appear within special character sequences in a pattern, for example
497 within the sequence (?( which introduces a conditional subpattern.
498 .sp
499 PCRE_EXTRA
500 .sp
501 This option was invented in order to turn on additional functionality of PCRE
502 that is incompatible with Perl, but it is currently of very little use. When
503 set, any backslash in a pattern that is followed by a letter that has no
504 special meaning causes an error, thus reserving these combinations for future
505 expansion. By default, as in Perl, a backslash followed by a letter with no
506 special meaning is treated as a literal. (Perl can, however, be persuaded to
507 give a warning for this.) There are at present no other features controlled by
508 this option. It can also be set by a (?X) option setting within a pattern.
509 .sp
510 PCRE_FIRSTLINE
511 .sp
512 If this option is set, an unanchored pattern is required to match before or at
513 the first newline in the subject string, though the matched text may continue
514 over the newline.
515 .sp
516 PCRE_MULTILINE
517 .sp
518 By default, PCRE treats the subject string as consisting of a single line of
519 characters (even if it actually contains newlines). The "start of line"
520 metacharacter (^) matches only at the start of the string, while the "end of
521 line" metacharacter ($) matches only at the end of the string, or before a
522 terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as
523 Perl.
524 .P
525 When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
526 match immediately following or immediately before internal newlines in the
527 subject string, respectively, as well as at the very start and end. This is
528 equivalent to Perl's /m option, and it can be changed within a pattern by a
529 (?m) option setting. If there are no newlines in a subject string, or no
530 occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
531 .sp
532 PCRE_NEWLINE_CR
533 PCRE_NEWLINE_LF
534 PCRE_NEWLINE_CRLF
535 PCRE_NEWLINE_ANY
536 .sp
537 These options override the default newline definition that was chosen when PCRE
538 was built. Setting the first or the second specifies that a newline is
539 indicated by a single character (CR or LF, respectively). Setting
540 PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
541 CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline
542 sequence should be recognized. The Unicode newline sequences are the three just
543 mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
544 U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
545 (paragraph separator, U+2029). The last two are recognized only in UTF-8 mode.
546 .P
547 The newline setting in the options word uses three bits that are treated
548 as a number, giving eight possibilities. Currently only five are used (default
549 plus the four values above). This means that if you set more than one newline
550 option, the combination may or may not be sensible. For example,
551 PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
552 other combinations yield unused numbers and cause an error.
553 .P
554 The only time that a line break is specially recognized when compiling a
555 pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
556 class is encountered. This indicates a comment that lasts until after the next
557 line break sequence. In other circumstances, line break sequences are treated
558 as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
559 as whitespace characters and are therefore ignored.
560 .P
561 The newline option that is set at compile time becomes the default that is used
562 for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
563 .sp
564 PCRE_NO_AUTO_CAPTURE
565 .sp
566 If this option is set, it disables the use of numbered capturing parentheses in
567 the pattern. Any opening parenthesis that is not followed by ? behaves as if it
568 were followed by ?: but named parentheses can still be used for capturing (and
569 they acquire numbers in the usual way). There is no equivalent of this option
570 in Perl.
571 .sp
572 PCRE_UNGREEDY
573 .sp
574 This option inverts the "greediness" of the quantifiers so that they are not
575 greedy by default, but become greedy if followed by "?". It is not compatible
576 with Perl. It can also be set by a (?U) option setting within the pattern.
577 .sp
578 PCRE_UTF8
579 .sp
580 This option causes PCRE to regard both the pattern and the subject as strings
581 of UTF-8 characters instead of single-byte character strings. However, it is
582 available only when PCRE is built to include UTF-8 support. If not, the use
583 of this option provokes an error. Details of how this option changes the
584 behaviour of PCRE are given in the
585 .\" HTML <a href="pcre.html#utf8support">
586 .\" </a>
587 section on UTF-8 support
588 .\"
589 in the main
590 .\" HREF
591 \fBpcre\fP
592 .\"
593 page.
594 .sp
595 PCRE_NO_UTF8_CHECK
596 .sp
597 When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
598 automatically checked. If an invalid UTF-8 sequence of bytes is found,
599 \fBpcre_compile()\fP returns an error. If you already know that your pattern is
600 valid, and you want to skip this check for performance reasons, you can set the
601 PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid
602 UTF-8 string as a pattern is undefined. It may cause your program to crash.
603 Note that this option can also be passed to \fBpcre_exec()\fP and
604 \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject
605 strings.
606 .
607 .
608 .SH "COMPILATION ERROR CODES"
609 .rs
610 .sp
611 The following table lists the error codes than may be returned by
612 \fBpcre_compile2()\fP, along with the error messages that may be returned by
613 both compiling functions. As PCRE has developed, some error codes have fallen
614 out of use. To avoid confusion, they have not been re-used.
615 .sp
616 0 no error
617 1 \e at end of pattern
618 2 \ec at end of pattern
619 3 unrecognized character follows \e
620 4 numbers out of order in {} quantifier
621 5 number too big in {} quantifier
622 6 missing terminating ] for character class
623 7 invalid escape sequence in character class
624 8 range out of order in character class
625 9 nothing to repeat
626 10 [this code is not in use]
627 11 internal error: unexpected repeat
628 12 unrecognized character after (?
629 13 POSIX named classes are supported only within a class
630 14 missing )
631 15 reference to non-existent subpattern
632 16 erroffset passed as NULL
633 17 unknown option bit(s) set
634 18 missing ) after comment
635 19 [this code is not in use]
636 20 regular expression too large
637 21 failed to get memory
638 22 unmatched parentheses
639 23 internal error: code overflow
640 24 unrecognized character after (?<
641 25 lookbehind assertion is not fixed length
642 26 malformed number or name after (?(
643 27 conditional group contains more than two branches
644 28 assertion expected after (?(
645 29 (?R or (?digits must be followed by )
646 30 unknown POSIX class name
647 31 POSIX collating elements are not supported
648 32 this version of PCRE is not compiled with PCRE_UTF8 support
649 33 [this code is not in use]
650 34 character value in \ex{...} sequence is too large
651 35 invalid condition (?(0)
652 36 \eC not allowed in lookbehind assertion
653 37 PCRE does not support \eL, \el, \eN, \eU, or \eu
654 38 number after (?C is > 255
655 39 closing ) for (?C expected
656 40 recursive call could loop indefinitely
657 41 unrecognized character after (?P
658 42 syntax error in subpattern name (missing terminator)
659 43 two named subpatterns have the same name
660 44 invalid UTF-8 string
661 45 support for \eP, \ep, and \eX has not been compiled
662 46 malformed \eP or \ep sequence
663 47 unknown property name after \eP or \ep
664 48 subpattern name is too long (maximum 32 characters)
665 49 too many named subpatterns (maximum 10,000)
666 50 repeated subpattern is too long
667 51 octal value is greater than \e377 (not in UTF-8 mode)
668 52 internal error: overran compiling workspace
669 53 internal error: previously-checked referenced subpattern not found
670 54 DEFINE group contains more than one branch
671 55 repeating a DEFINE group is not allowed
672 56 inconsistent NEWLINE options"
673 .
674 .
675 .SH "STUDYING A PATTERN"
676 .rs
677 .sp
678 .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP
679 .ti +5n
680 .B const char **\fIerrptr\fP);
681 .PP
682 If a compiled pattern is going to be used several times, it is worth spending
683 more time analyzing it in order to speed up the time taken for matching. The
684 function \fBpcre_study()\fP takes a pointer to a compiled pattern as its first
685 argument. If studying the pattern produces additional information that will
686 help speed up matching, \fBpcre_study()\fP returns a pointer to a
687 \fBpcre_extra\fP block, in which the \fIstudy_data\fP field points to the
688 results of the study.
689 .P
690 The returned value from \fBpcre_study()\fP can be passed directly to
691 \fBpcre_exec()\fP. However, a \fBpcre_extra\fP block also contains other
692 fields that can be set by the caller before the block is passed; these are
693 described
694 .\" HTML <a href="#extradata">
695 .\" </a>
696 below
697 .\"
698 in the section on matching a pattern.
699 .P
700 If studying the pattern does not produce any additional information
701 \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program
702 wants to pass any of the other fields to \fBpcre_exec()\fP, it must set up its
703 own \fBpcre_extra\fP block.
704 .P
705 The second argument of \fBpcre_study()\fP contains option bits. At present, no
706 options are defined, and this argument should always be zero.
707 .P
708 The third argument for \fBpcre_study()\fP is a pointer for an error message. If
709 studying succeeds (even if no data is returned), the variable it points to is
710 set to NULL. Otherwise it is set to point to a textual error message. This is a
711 static string that is part of the library. You must not try to free it. You
712 should test the error pointer for NULL after calling \fBpcre_study()\fP, to be
713 sure that it has run successfully.
714 .P
715 This is a typical call to \fBpcre_study\fP():
716 .sp
717 pcre_extra *pe;
718 pe = pcre_study(
719 re, /* result of pcre_compile() */
720 0, /* no options exist */
721 &error); /* set to NULL or points to a message */
722 .sp
723 At present, studying a pattern is useful only for non-anchored patterns that do
724 not have a single fixed starting character. A bitmap of possible starting
725 bytes is created.
726 .
727 .
728 .\" HTML <a name="localesupport"></a>
729 .SH "LOCALE SUPPORT"
730 .rs
731 .sp
732 PCRE handles caseless matching, and determines whether characters are letters
733 digits, or whatever, by reference to a set of tables, indexed by character
734 value. When running in UTF-8 mode, this applies only to characters with codes
735 less than 128. Higher-valued codes never match escapes such as \ew or \ed, but
736 can be tested with \ep if PCRE is built with Unicode character property
737 support. The use of locales with Unicode is discouraged.
738 .P
739 An internal set of tables is created in the default C locale when PCRE is
740 built. This is used when the final argument of \fBpcre_compile()\fP is NULL,
741 and is sufficient for many applications. An alternative set of tables can,
742 however, be supplied. These may be created in a different locale from the
743 default. As more and more applications change to using Unicode, the need for
744 this locale support is expected to die away.
745 .P
746 External tables are built by calling the \fBpcre_maketables()\fP function,
747 which has no arguments, in the relevant locale. The result can then be passed
748 to \fBpcre_compile()\fP or \fBpcre_exec()\fP as often as necessary. For
749 example, to build and use tables that are appropriate for the French locale
750 (where accented characters with values greater than 128 are treated as letters),
751 the following code could be used:
752 .sp
753 setlocale(LC_CTYPE, "fr_FR");
754 tables = pcre_maketables();
755 re = pcre_compile(..., tables);
756 .sp
757 When \fBpcre_maketables()\fP runs, the tables are built in memory that is
758 obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure
759 that the memory containing the tables remains available for as long as it is
760 needed.
761 .P
762 The pointer that is passed to \fBpcre_compile()\fP is saved with the compiled
763 pattern, and the same tables are used via this pointer by \fBpcre_study()\fP
764 and normally also by \fBpcre_exec()\fP. Thus, by default, for any single
765 pattern, compilation, studying and matching all happen in the same locale, but
766 different patterns can be compiled in different locales.
767 .P
768 It is possible to pass a table pointer or NULL (indicating the use of the
769 internal tables) to \fBpcre_exec()\fP. Although not intended for this purpose,
770 this facility could be used to match a pattern in a different locale from the
771 one in which it was compiled. Passing table pointers at run time is discussed
772 below in the section on matching a pattern.
773 .
774 .
775 .SH "INFORMATION ABOUT A PATTERN"
776 .rs
777 .sp
778 .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
779 .ti +5n
780 .B int \fIwhat\fP, void *\fIwhere\fP);
781 .PP
782 The \fBpcre_fullinfo()\fP function returns information about a compiled
783 pattern. It replaces the obsolete \fBpcre_info()\fP function, which is
784 nevertheless retained for backwards compability (and is documented below).
785 .P
786 The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled
787 pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if
788 the pattern was not studied. The third argument specifies which piece of
789 information is required, and the fourth argument is a pointer to a variable
790 to receive the data. The yield of the function is zero for success, or one of
791 the following negative numbers:
792 .sp
793 PCRE_ERROR_NULL the argument \fIcode\fP was NULL
794 the argument \fIwhere\fP was NULL
795 PCRE_ERROR_BADMAGIC the "magic number" was not found
796 PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid
797 .sp
798 The "magic number" is placed at the start of each compiled pattern as an simple
799 check against passing an arbitrary memory pointer. Here is a typical call of
800 \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
801 .sp
802 int rc;
803 size_t length;
804 rc = pcre_fullinfo(
805 re, /* result of pcre_compile() */
806 pe, /* result of pcre_study(), or NULL */
807 PCRE_INFO_SIZE, /* what is required */
808 &length); /* where to put the data */
809 .sp
810 The possible values for the third argument are defined in \fBpcre.h\fP, and are
811 as follows:
812 .sp
813 PCRE_INFO_BACKREFMAX
814 .sp
815 Return the number of the highest back reference in the pattern. The fourth
816 argument should point to an \fBint\fP variable. Zero is returned if there are
817 no back references.
818 .sp
819 PCRE_INFO_CAPTURECOUNT
820 .sp
821 Return the number of capturing subpatterns in the pattern. The fourth argument
822 should point to an \fBint\fP variable.
823 .sp
824 PCRE_INFO_DEFAULT_TABLES
825 .sp
826 Return a pointer to the internal default character tables within PCRE. The
827 fourth argument should point to an \fBunsigned char *\fP variable. This
828 information call is provided for internal use by the \fBpcre_study()\fP
829 function. External callers can cause PCRE to use its internal tables by passing
830 a NULL table pointer.
831 .sp
832 PCRE_INFO_FIRSTBYTE
833 .sp
834 Return information about the first byte of any matched string, for a
835 non-anchored pattern. The fourth argument should point to an \fBint\fP
836 variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
837 still recognized for backwards compatibility.)
838 .P
839 If there is a fixed first byte, for example, from a pattern such as
840 (cat|cow|coyote), its value is returned. Otherwise, if either
841 .sp
842 (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
843 starts with "^", or
844 .sp
845 (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
846 (if it were set, the pattern would be anchored),
847 .sp
848 -1 is returned, indicating that the pattern matches only at the start of a
849 subject string or after any newline within the string. Otherwise -2 is
850 returned. For anchored patterns, -2 is returned.
851 .sp
852 PCRE_INFO_FIRSTTABLE
853 .sp
854 If the pattern was studied, and this resulted in the construction of a 256-bit
855 table indicating a fixed set of bytes for the first byte in any matching
856 string, a pointer to the table is returned. Otherwise NULL is returned. The
857 fourth argument should point to an \fBunsigned char *\fP variable.
858 .sp
859 PCRE_INFO_LASTLITERAL
860 .sp
861 Return the value of the rightmost literal byte that must exist in any matched
862 string, other than at its start, if such a byte has been recorded. The fourth
863 argument should point to an \fBint\fP variable. If there is no such byte, -1 is
864 returned. For anchored patterns, a last literal byte is recorded only if it
865 follows something of variable length. For example, for the pattern
866 /^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value
867 is -1.
868 .sp
869 PCRE_INFO_NAMECOUNT
870 PCRE_INFO_NAMEENTRYSIZE
871 PCRE_INFO_NAMETABLE
872 .sp
873 PCRE supports the use of named as well as numbered capturing parentheses. The
874 names are just an additional way of identifying the parentheses, which still
875 acquire numbers. Several convenience functions such as
876 \fBpcre_get_named_substring()\fP are provided for extracting captured
877 substrings by name. It is also possible to extract the data directly, by first
878 converting the name to a number in order to access the correct pointers in the
879 output vector (described with \fBpcre_exec()\fP below). To do the conversion,
880 you need to use the name-to-number map, which is described by these three
881 values.
882 .P
883 The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives
884 the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
885 entry; both of these return an \fBint\fP value. The entry size depends on the
886 length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
887 entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry
888 are the number of the capturing parenthesis, most significant byte first. The
889 rest of the entry is the corresponding name, zero terminated. The names are in
890 alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of
891 their parentheses numbers. For example, consider the following pattern (assume
892 PCRE_EXTENDED is set, so white space - including newlines - is ignored):
893 .sp
894 .\" JOIN
895 (?<date> (?<year>(\ed\ed)?\ed\ed) -
896 (?<month>\ed\ed) - (?<day>\ed\ed) )
897 .sp
898 There are four named subpatterns, so the table has four entries, and each entry
899 in the table is eight bytes long. The table is as follows, with non-printing
900 bytes shows in hexadecimal, and undefined bytes shown as ??:
901 .sp
902 00 01 d a t e 00 ??
903 00 05 d a y 00 ?? ??
904 00 04 m o n t h 00
905 00 02 y e a r 00 ??
906 .sp
907 When writing code to extract data from named subpatterns using the
908 name-to-number map, remember that the length of the entries is likely to be
909 different for each compiled pattern.
910 .sp
911 PCRE_INFO_OPTIONS
912 .sp
913 Return a copy of the options with which the pattern was compiled. The fourth
914 argument should point to an \fBunsigned long int\fP variable. These option bits
915 are those specified in the call to \fBpcre_compile()\fP, modified by any
916 top-level option settings within the pattern itself.
917 .P
918 A pattern is automatically anchored by PCRE if all of its top-level
919 alternatives begin with one of the following:
920 .sp
921 ^ unless PCRE_MULTILINE is set
922 \eA always
923 \eG always
924 .\" JOIN
925 .* if PCRE_DOTALL is set and there are no back
926 references to the subpattern in which .* appears
927 .sp
928 For such patterns, the PCRE_ANCHORED bit is set in the options returned by
929 \fBpcre_fullinfo()\fP.
930 .sp
931 PCRE_INFO_SIZE
932 .sp
933 Return the size of the compiled pattern, that is, the value that was passed as
934 the argument to \fBpcre_malloc()\fP when PCRE was getting memory in which to
935 place the compiled data. The fourth argument should point to a \fBsize_t\fP
936 variable.
937 .sp
938 PCRE_INFO_STUDYSIZE
939 .sp
940 Return the size of the data block pointed to by the \fIstudy_data\fP field in
941 a \fBpcre_extra\fP block. That is, it is the value that was passed to
942 \fBpcre_malloc()\fP when PCRE was getting memory into which to place the data
943 created by \fBpcre_study()\fP. The fourth argument should point to a
944 \fBsize_t\fP variable.
945 .
946 .
947 .SH "OBSOLETE INFO FUNCTION"
948 .rs
949 .sp
950 .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
951 .B *\fIfirstcharptr\fP);
952 .PP
953 The \fBpcre_info()\fP function is now obsolete because its interface is too
954 restrictive to return all the available data about a compiled pattern. New
955 programs should use \fBpcre_fullinfo()\fP instead. The yield of
956 \fBpcre_info()\fP is the number of capturing subpatterns, or one of the
957 following negative numbers:
958 .sp
959 PCRE_ERROR_NULL the argument \fIcode\fP was NULL
960 PCRE_ERROR_BADMAGIC the "magic number" was not found
961 .sp
962 If the \fIoptptr\fP argument is not NULL, a copy of the options with which the
963 pattern was compiled is placed in the integer it points to (see
964 PCRE_INFO_OPTIONS above).
965 .P
966 If the pattern is not anchored and the \fIfirstcharptr\fP argument is not NULL,
967 it is used to pass back information about the first character of any matched
968 string (see PCRE_INFO_FIRSTBYTE above).
969 .
970 .
971 .SH "REFERENCE COUNTS"
972 .rs
973 .sp
974 .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
975 .PP
976 The \fBpcre_refcount()\fP function is used to maintain a reference count in the
977 data block that contains a compiled pattern. It is provided for the benefit of
978 applications that operate in an object-oriented manner, where different parts
979 of the application may be using the same compiled pattern, but you want to free
980 the block when they are all done.
981 .P
982 When a pattern is compiled, the reference count field is initialized to zero.
983 It is changed only by calling this function, whose action is to add the
984 \fIadjust\fP value (which may be positive or negative) to it. The yield of the
985 function is the new value. However, the value of the count is constrained to
986 lie between 0 and 65535, inclusive. If the new value is outside these limits,
987 it is forced to the appropriate limit value.
988 .P
989 Except when it is zero, the reference count is not correctly preserved if a
990 pattern is compiled on one host and then transferred to a host whose byte-order
991 is different. (This seems a highly unlikely scenario.)
992 .
993 .
994 .SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION"
995 .rs
996 .sp
997 .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
998 .ti +5n
999 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
1000 .ti +5n
1001 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
1002 .P
1003 The function \fBpcre_exec()\fP is called to match a subject string against a
1004 compiled pattern, which is passed in the \fIcode\fP argument. If the
1005 pattern has been studied, the result of the study should be passed in the
1006 \fIextra\fP argument. This function is the main matching facility of the
1007 library, and it operates in a Perl-like manner. For specialist use there is
1008 also an alternative matching function, which is described
1009 .\" HTML <a href="#dfamatch">
1010 .\" </a>
1011 below
1012 .\"
1013 in the section about the \fBpcre_dfa_exec()\fP function.
1014 .P
1015 In most applications, the pattern will have been compiled (and optionally
1016 studied) in the same process that calls \fBpcre_exec()\fP. However, it is
1017 possible to save compiled patterns and study data, and then use them later
1018 in different processes, possibly even on different hosts. For a discussion
1019 about this, see the
1020 .\" HREF
1021 \fBpcreprecompile\fP
1022 .\"
1023 documentation.
1024 .P
1025 Here is an example of a simple call to \fBpcre_exec()\fP:
1026 .sp
1027 int rc;
1028 int ovector[30];
1029 rc = pcre_exec(
1030 re, /* result of pcre_compile() */
1031 NULL, /* we didn't study the pattern */
1032 "some string", /* the subject string */
1033 11, /* the length of the subject string */
1034 0, /* start at offset 0 in the subject */
1035 0, /* default options */
1036 ovector, /* vector of integers for substring information */
1037 30); /* number of elements (NOT size in bytes) */
1038 .
1039 .\" HTML <a name="extradata"></a>
1040 .SS "Extra data for \fBpcre_exec()\fR"
1041 .rs
1042 .sp
1043 If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP
1044 data block. The \fBpcre_study()\fP function returns such a block (when it
1045 doesn't return NULL), but you can also create one for yourself, and pass
1046 additional information in it. The \fBpcre_extra\fP block contains the following
1047 fields (not necessarily in this order):
1048 .sp
1049 unsigned long int \fIflags\fP;
1050 void *\fIstudy_data\fP;
1051 unsigned long int \fImatch_limit\fP;
1052 unsigned long int \fImatch_limit_recursion\fP;
1053 void *\fIcallout_data\fP;
1054 const unsigned char *\fItables\fP;
1055 .sp
1056 The \fIflags\fP field is a bitmap that specifies which of the other fields
1057 are set. The flag bits are:
1058 .sp
1059 PCRE_EXTRA_STUDY_DATA
1060 PCRE_EXTRA_MATCH_LIMIT
1061 PCRE_EXTRA_MATCH_LIMIT_RECURSION
1062 PCRE_EXTRA_CALLOUT_DATA
1063 PCRE_EXTRA_TABLES
1064 .sp
1065 Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the
1066 \fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with
1067 the appropriate flag bit. You should not set this yourself, but you may add to
1068 the block by setting the other fields and their corresponding flag bits.
1069 .P
1070 The \fImatch_limit\fP field provides a means of preventing PCRE from using up a
1071 vast amount of resources when running patterns that are not going to match,
1072 but which have a very large number of possibilities in their search trees. The
1073 classic example is the use of nested unlimited repeats.
1074 .P
1075 Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly
1076 (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the
1077 number of times this function is called during a match, which has the effect of
1078 limiting the amount of backtracking that can take place. For patterns that are
1079 not anchored, the count restarts from zero for each position in the subject
1080 string.
1081 .P
1082 The default value for the limit can be set when PCRE is built; the default
1083 default is 10 million, which handles all but the most extreme cases. You can
1084 override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP
1085 block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in
1086 the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns
1087 PCRE_ERROR_MATCHLIMIT.
1088 .P
1089 The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but
1090 instead of limiting the total number of times that \fBmatch()\fP is called, it
1091 limits the depth of recursion. The recursion depth is a smaller number than the
1092 total number of calls, because not all calls to \fBmatch()\fP are recursive.
1093 This limit is of use only if it is set smaller than \fImatch_limit\fP.
1094 .P
1095 Limiting the recursion depth limits the amount of stack that can be used, or,
1096 when PCRE has been compiled to use memory on the heap instead of the stack, the
1097 amount of heap memory that can be used.
1098 .P
1099 The default value for \fImatch_limit_recursion\fP can be set when PCRE is
1100 built; the default default is the same value as the default for
1101 \fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP
1102 with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and
1103 PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
1104 is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1105 .P
1106 The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,
1107 which is described in the
1108 .\" HREF
1109 \fBpcrecallout\fP
1110 .\"
1111 documentation.
1112 .P
1113 The \fItables\fP field is used to pass a character tables pointer to
1114 \fBpcre_exec()\fP; this overrides the value that is stored with the compiled
1115 pattern. A non-NULL value is stored with the compiled pattern only if custom
1116 tables were supplied to \fBpcre_compile()\fP via its \fItableptr\fP argument.
1117 If NULL is passed to \fBpcre_exec()\fP using this mechanism, it forces PCRE's
1118 internal tables to be used. This facility is helpful when re-using patterns
1119 that have been saved after compiling with an external set of tables, because
1120 the external tables might be at a different address when \fBpcre_exec()\fP is
1121 called. See the
1122 .\" HREF
1123 \fBpcreprecompile\fP
1124 .\"
1125 documentation for a discussion of saving compiled patterns for later use.
1126 .
1127 .SS "Option bits for \fBpcre_exec()\fP"
1128 .rs
1129 .sp
1130 The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be
1131 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1132 PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
1133 .sp
1134 PCRE_ANCHORED
1135 .sp
1136 The PCRE_ANCHORED option limits \fBpcre_exec()\fP to matching at the first
1137 matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out
1138 to be anchored by virtue of its contents, it cannot be made unachored at
1139 matching time.
1140 .sp
1141 PCRE_NEWLINE_CR
1142 PCRE_NEWLINE_LF
1143 PCRE_NEWLINE_CRLF
1144 PCRE_NEWLINE_ANY
1145 .sp
1146 These options override the newline definition that was chosen or defaulted when
1147 the pattern was compiled. For details, see the description of
1148 \fBpcre_compile()\fP above. During matching, the newline choice affects the
1149 behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1150 the way the match position is advanced after a match failure for an unanchored
1151 pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt
1152 fails when the current position is at a CRLF sequence, the match position is
1153 advanced by two characters instead of one, in other words, to after the CRLF.
1154 .sp
1155 PCRE_NOTBOL
1156 .sp
1157 This option specifies that first character of the subject string is not the
1158 beginning of a line, so the circumflex metacharacter should not match before
1159 it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex
1160 never to match. This option affects only the behaviour of the circumflex
1161 metacharacter. It does not affect \eA.
1162 .sp
1163 PCRE_NOTEOL
1164 .sp
1165 This option specifies that the end of the subject string is not the end of a
1166 line, so the dollar metacharacter should not match it nor (except in multiline
1167 mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at
1168 compile time) causes dollar never to match. This option affects only the
1169 behaviour of the dollar metacharacter. It does not affect \eZ or \ez.
1170 .sp
1171 PCRE_NOTEMPTY
1172 .sp
1173 An empty string is not considered to be a valid match if this option is set. If
1174 there are alternatives in the pattern, they are tried. If all the alternatives
1175 match the empty string, the entire match fails. For example, if the pattern
1176 .sp
1177 a?b?
1178 .sp
1179 is applied to a string not beginning with "a" or "b", it matches the empty
1180 string at the start of the subject. With PCRE_NOTEMPTY set, this match is not
1181 valid, so PCRE searches further into the string for occurrences of "a" or "b".
1182 .P
1183 Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case
1184 of a pattern match of the empty string within its \fBsplit()\fP function, and
1185 when using the /g modifier. It is possible to emulate Perl's behaviour after
1186 matching a null string by first trying the match again at the same offset with
1187 PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the
1188 starting offset (see below) and trying an ordinary match again. There is some
1189 code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.
1190 .sp
1191 PCRE_NO_UTF8_CHECK
1192 .sp
1193 When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
1194 string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1195 The value of \fIstartoffset\fP is also checked to ensure that it points to the
1196 start of a UTF-8 character. If an invalid UTF-8 sequence of bytes is found,
1197 \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP
1198 contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.
1199 .P
1200 If you already know that your subject is valid, and you want to skip these
1201 checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
1202 calling \fBpcre_exec()\fP. You might want to do this for the second and
1203 subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find
1204 all the matches in a single subject string. However, you should be sure that
1205 the value of \fIstartoffset\fP points to the start of a UTF-8 character. When
1206 PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a
1207 subject, or a value of \fIstartoffset\fP that does not point to the start of a
1208 UTF-8 character, is undefined. Your program may crash.
1209 .sp
1210 PCRE_PARTIAL
1211 .sp
1212 This option turns on the partial matching feature. If the subject string fails
1213 to match the pattern, but at some point during the matching process the end of
1214 the subject was reached (that is, the subject partially matches the pattern and
1215 the failure to match occurred only because there were not enough subject
1216 characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of
1217 PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what
1218 may appear in the pattern. These are discussed in the
1219 .\" HREF
1220 \fBpcrepartial\fP
1221 .\"
1222 documentation.
1223 .
1224 .SS "The string to be matched by \fBpcre_exec()\fP"
1225 .rs
1226 .sp
1227 The subject string is passed to \fBpcre_exec()\fP as a pointer in
1228 \fIsubject\fP, a length in \fIlength\fP, and a starting byte offset in
1229 \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a
1230 UTF-8 character. Unlike the pattern string, the subject may contain binary zero
1231 bytes. When the starting offset is zero, the search for a match starts at the
1232 beginning of the subject, and this is by far the most common case.
1233 .P
1234 A non-zero starting offset is useful when searching for another match in the
1235 same subject by calling \fBpcre_exec()\fP again after a previous success.
1236 Setting \fIstartoffset\fP differs from just passing over a shortened string and
1237 setting PCRE_NOTBOL in the case of a pattern that begins with any kind of
1238 lookbehind. For example, consider the pattern
1239 .sp
1240 \eBiss\eB
1241 .sp
1242 which finds occurrences of "iss" in the middle of words. (\eB matches only if
1243 the current position in the subject is not a word boundary.) When applied to
1244 the string "Mississipi" the first call to \fBpcre_exec()\fP finds the first
1245 occurrence. If \fBpcre_exec()\fP is called again with just the remainder of the
1246 subject, namely "issipi", it does not match, because \eB is always false at the
1247 start of the subject, which is deemed to be a word boundary. However, if
1248 \fBpcre_exec()\fP is passed the entire string again, but with \fIstartoffset\fP
1249 set to 4, it finds the second occurrence of "iss" because it is able to look
1250 behind the starting point to discover that it is preceded by a letter.
1251 .P
1252 If a non-zero starting offset is passed when the pattern is anchored, one
1253 attempt to match at the given offset is made. This can only succeed if the
1254 pattern does not require the match to be at the start of the subject.
1255 .
1256 .SS "How \fBpcre_exec()\fP returns captured substrings"
1257 .rs
1258 .sp
1259 In general, a pattern matches a certain portion of the subject, and in
1260 addition, further substrings from the subject may be picked out by parts of the
1261 pattern. Following the usage in Jeffrey Friedl's book, this is called
1262 "capturing" in what follows, and the phrase "capturing subpattern" is used for
1263 a fragment of a pattern that picks out a substring. PCRE supports several other
1264 kinds of parenthesized subpattern that do not cause substrings to be captured.
1265 .P
1266 Captured substrings are returned to the caller via a vector of integer offsets
1267 whose address is passed in \fIovector\fP. The number of elements in the vector
1268 is passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP:
1269 this argument is NOT the size of \fIovector\fP in bytes.
1270 .P
1271 The first two-thirds of the vector is used to pass back captured substrings,
1272 each substring using a pair of integers. The remaining third of the vector is
1273 used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1274 and is not available for passing back information. The length passed in
1275 \fIovecsize\fP should always be a multiple of three. If it is not, it is
1276 rounded down.
1277 .P
1278 When a match is successful, information about captured substrings is returned
1279 in pairs of integers, starting at the beginning of \fIovector\fP, and
1280 continuing up to two-thirds of its length at the most. The first element of a
1281 pair is set to the offset of the first character in a substring, and the second
1282 is set to the offset of the first character after the end of a substring. The
1283 first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the
1284 subject string matched by the entire pattern. The next pair is used for the
1285 first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP
1286 is one more than the highest numbered pair that has been set. For example, if
1287 two substrings have been captured, the returned value is 3. If there are no
1288 capturing subpatterns, the return value from a successful match is 1,
1289 indicating that just the first pair of offsets has been set.
1290 .P
1291 If a capturing subpattern is matched repeatedly, it is the last portion of the
1292 string that it matched that is returned.
1293 .P
1294 If the vector is too small to hold all the captured substring offsets, it is
1295 used as far as possible (up to two-thirds of its length), and the function
1296 returns a value of zero. In particular, if the substring offsets are not of
1297 interest, \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and
1298 \fIovecsize\fP as zero. However, if the pattern contains back references and
1299 the \fIovector\fP is not big enough to remember the related substrings, PCRE
1300 has to get additional memory for use during matching. Thus it is usually
1301 advisable to supply an \fIovector\fP.
1302 .P
1303 The \fBpcre_info()\fP function can be used to find out how many capturing
1304 subpatterns there are in a compiled pattern. The smallest size for
1305 \fIovector\fP that will allow for \fIn\fP captured substrings, in addition to
1306 the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3.
1307 .P
1308 It is possible for capturing subpattern number \fIn+1\fP to match some part of
1309 the subject when subpattern \fIn\fP has not been used at all. For example, if
1310 the string "abc" is matched against the pattern (a|(z))(bc) the return from the
1311 function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
1312 happens, both values in the offset pairs corresponding to unused subpatterns
1313 are set to -1.
1314 .P
1315 Offset values that correspond to unused subpatterns at the end of the
1316 expression are also set to -1. For example, if the string "abc" is matched
1317 against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1318 return from the function is 2, because the highest used capturing subpattern
1319 number is 1. However, you can refer to the offsets for the second and third
1320 capturing subpatterns if you wish (assuming the vector is large enough, of
1321 course).
1322 .P
1323 Some convenience functions are provided for extracting the captured substrings
1324 as separate strings. These are described below.
1325 .
1326 .\" HTML <a name="errorlist"></a>
1327 .SS "Error return values from \fBpcre_exec()\fP"
1328 .rs
1329 .sp
1330 If \fBpcre_exec()\fP fails, it returns a negative number. The following are
1331 defined in the header file:
1332 .sp
1333 PCRE_ERROR_NOMATCH (-1)
1334 .sp
1335 The subject string did not match the pattern.
1336 .sp
1337 PCRE_ERROR_NULL (-2)
1338 .sp
1339 Either \fIcode\fP or \fIsubject\fP was passed as NULL, or \fIovector\fP was
1340 NULL and \fIovecsize\fP was not zero.
1341 .sp
1342 PCRE_ERROR_BADOPTION (-3)
1343 .sp
1344 An unrecognized bit was set in the \fIoptions\fP argument.
1345 .sp
1346 PCRE_ERROR_BADMAGIC (-4)
1347 .sp
1348 PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch
1349 the case when it is passed a junk pointer and to detect when a pattern that was
1350 compiled in an environment of one endianness is run in an environment with the
1351 other endianness. This is the error that PCRE gives when the magic number is
1352 not present.
1353 .sp
1354 PCRE_ERROR_UNKNOWN_OPCODE (-5)
1355 .sp
1356 While running the pattern match, an unknown item was encountered in the
1357 compiled pattern. This error could be caused by a bug in PCRE or by overwriting
1358 of the compiled pattern.
1359 .sp
1360 PCRE_ERROR_NOMEMORY (-6)
1361 .sp
1362 If a pattern contains back references, but the \fIovector\fP that is passed to
1363 \fBpcre_exec()\fP is not big enough to remember the referenced substrings, PCRE
1364 gets a block of memory at the start of matching to use for this purpose. If the
1365 call via \fBpcre_malloc()\fP fails, this error is given. The memory is
1366 automatically freed at the end of matching.
1367 .sp
1368 PCRE_ERROR_NOSUBSTRING (-7)
1369 .sp
1370 This error is used by the \fBpcre_copy_substring()\fP,
1371 \fBpcre_get_substring()\fP, and \fBpcre_get_substring_list()\fP functions (see
1372 below). It is never returned by \fBpcre_exec()\fP.
1373 .sp
1374 PCRE_ERROR_MATCHLIMIT (-8)
1375 .sp
1376 The backtracking limit, as specified by the \fImatch_limit\fP field in a
1377 \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1378 above.
1379 .sp
1380 PCRE_ERROR_CALLOUT (-9)
1381 .sp
1382 This error is never generated by \fBpcre_exec()\fP itself. It is provided for
1383 use by callout functions that want to yield a distinctive error code. See the
1384 .\" HREF
1385 \fBpcrecallout\fP
1386 .\"
1387 documentation for details.
1388 .sp
1389 PCRE_ERROR_BADUTF8 (-10)
1390 .sp
1391 A string that contains an invalid UTF-8 byte sequence was passed as a subject.
1392 .sp
1393 PCRE_ERROR_BADUTF8_OFFSET (-11)
1394 .sp
1395 The UTF-8 byte sequence that was passed as a subject was valid, but the value
1396 of \fIstartoffset\fP did not point to the beginning of a UTF-8 character.
1397 .sp
1398 PCRE_ERROR_PARTIAL (-12)
1399 .sp
1400 The subject string did not match, but it did match partially. See the
1401 .\" HREF
1402 \fBpcrepartial\fP
1403 .\"
1404 documentation for details of partial matching.
1405 .sp
1406 PCRE_ERROR_BADPARTIAL (-13)
1407 .sp
1408 The PCRE_PARTIAL option was used with a compiled pattern containing items that
1409 are not supported for partial matching. See the
1410 .\" HREF
1411 \fBpcrepartial\fP
1412 .\"
1413 documentation for details of partial matching.
1414 .sp
1415 PCRE_ERROR_INTERNAL (-14)
1416 .sp
1417 An unexpected internal error has occurred. This error could be caused by a bug
1418 in PCRE or by overwriting of the compiled pattern.
1419 .sp
1420 PCRE_ERROR_BADCOUNT (-15)
1421 .sp
1422 This error is given if the value of the \fIovecsize\fP argument is negative.
1423 .sp
1424 PCRE_ERROR_RECURSIONLIMIT (-21)
1425 .sp
1426 The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1427 field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1428 description above.
1429 .sp
1430 PCRE_ERROR_NULLWSLIMIT (-22)
1431 .sp
1432 When a group that can match an empty substring is repeated with an unbounded
1433 upper limit, the subject position at the start of the group must be remembered,
1434 so that a test for an empty string can be made when the end of the group is
1435 reached. Some workspace is required for this; if it runs out, this error is
1436 given.
1437 .sp
1438 PCRE_ERROR_BADNEWLINE (-23)
1439 .sp
1440 An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1441 .P
1442 Error numbers -16 to -20 are not used by \fBpcre_exec()\fP.
1443 .
1444 .
1445 .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
1446 .rs
1447 .sp
1448 .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1449 .ti +5n
1450 .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
1451 .ti +5n
1452 .B int \fIbuffersize\fP);
1453 .PP
1454 .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1455 .ti +5n
1456 .B int \fIstringcount\fP, int \fIstringnumber\fP,
1457 .ti +5n
1458 .B const char **\fIstringptr\fP);
1459 .PP
1460 .B int pcre_get_substring_list(const char *\fIsubject\fP,
1461 .ti +5n
1462 .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
1463 .PP
1464 Captured substrings can be accessed directly by using the offsets returned by
1465 \fBpcre_exec()\fP in \fIovector\fP. For convenience, the functions
1466 \fBpcre_copy_substring()\fP, \fBpcre_get_substring()\fP, and
1467 \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
1468 as new, separate, zero-terminated strings. These functions identify substrings
1469 by number. The next section describes functions for extracting named
1470 substrings.
1471 .P
1472 A substring that contains a binary zero is correctly extracted and has a
1473 further zero added on the end, but the result is not, of course, a C string.
1474 However, you can process such a string by referring to the length that is
1475 returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
1476 Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
1477 for handling strings containing binary zeros, because the end of the final
1478 string is not independently indicated.
1479 .P
1480 The first three arguments are the same for all three of these functions:
1481 \fIsubject\fP is the subject string that has just been successfully matched,
1482 \fIovector\fP is a pointer to the vector of integer offsets that was passed to
1483 \fBpcre_exec()\fP, and \fIstringcount\fP is the number of substrings that were
1484 captured by the match, including the substring that matched the entire regular
1485 expression. This is the value returned by \fBpcre_exec()\fP if it is greater
1486 than zero. If \fBpcre_exec()\fP returned zero, indicating that it ran out of
1487 space in \fIovector\fP, the value passed as \fIstringcount\fP should be the
1488 number of elements in the vector divided by three.
1489 .P
1490 The functions \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP
1491 extract a single substring, whose number is given as \fIstringnumber\fP. A
1492 value of zero extracts the substring that matched the entire pattern, whereas
1493 higher values extract the captured substrings. For \fBpcre_copy_substring()\fP,
1494 the string is placed in \fIbuffer\fP, whose length is given by
1495 \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is
1496 obtained via \fBpcre_malloc\fP, and its address is returned via
1497 \fIstringptr\fP. The yield of the function is the length of the string, not
1498 including the terminating zero, or one of these error codes:
1499 .sp
1500 PCRE_ERROR_NOMEMORY (-6)
1501 .sp
1502 The buffer was too small for \fBpcre_copy_substring()\fP, or the attempt to get
1503 memory failed for \fBpcre_get_substring()\fP.
1504 .sp
1505 PCRE_ERROR_NOSUBSTRING (-7)
1506 .sp
1507 There is no substring whose number is \fIstringnumber\fP.
1508 .P
1509 The \fBpcre_get_substring_list()\fP function extracts all available substrings
1510 and builds a list of pointers to them. All this is done in a single block of
1511 memory that is obtained via \fBpcre_malloc\fP. The address of the memory block
1512 is returned via \fIlistptr\fP, which is also the start of the list of string
1513 pointers. The end of the list is marked by a NULL pointer. The yield of the
1514 function is zero if all went well, or the error code
1515 .sp
1516 PCRE_ERROR_NOMEMORY (-6)
1517 .sp
1518 if the attempt to get the memory block failed.
1519 .P
1520 When any of these functions encounter a substring that is unset, which can
1521 happen when capturing subpattern number \fIn+1\fP matches some part of the
1522 subject, but subpattern \fIn\fP has not been used at all, they return an empty
1523 string. This can be distinguished from a genuine zero-length substring by
1524 inspecting the appropriate offset in \fIovector\fP, which is negative for unset
1525 substrings.
1526 .P
1527 The two convenience functions \fBpcre_free_substring()\fP and
1528 \fBpcre_free_substring_list()\fP can be used to free the memory returned by
1529 a previous call of \fBpcre_get_substring()\fP or
1530 \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
1531 the function pointed to by \fBpcre_free\fP, which of course could be called
1532 directly from a C program. However, PCRE is used in some situations where it is
1533 linked via a special interface to another programming language that cannot use
1534 \fBpcre_free\fP directly; it is for these cases that the functions are
1535 provided.
1536 .
1537 .
1538 .SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME"
1539 .rs
1540 .sp
1541 .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
1542 .ti +5n
1543 .B const char *\fIname\fP);
1544 .PP
1545 .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1546 .ti +5n
1547 .B const char *\fIsubject\fP, int *\fIovector\fP,
1548 .ti +5n
1549 .B int \fIstringcount\fP, const char *\fIstringname\fP,
1550 .ti +5n
1551 .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1552 .PP
1553 .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1554 .ti +5n
1555 .B const char *\fIsubject\fP, int *\fIovector\fP,
1556 .ti +5n
1557 .B int \fIstringcount\fP, const char *\fIstringname\fP,
1558 .ti +5n
1559 .B const char **\fIstringptr\fP);
1560 .PP
1561 To extract a substring by name, you first have to find associated number.
1562 For example, for this pattern
1563 .sp
1564 (a+)b(?<xxx>\ed+)...
1565 .sp
1566 the number of the subpattern called "xxx" is 2. If the name is known to be
1567 unique (PCRE_DUPNAMES was not set), you can find the number from the name by
1568 calling \fBpcre_get_stringnumber()\fP. The first argument is the compiled
1569 pattern, and the second is the name. The yield of the function is the
1570 subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of
1571 that name.
1572 .P
1573 Given the number, you can extract the substring directly, or use one of the
1574 functions described in the previous section. For convenience, there are also
1575 two functions that do the whole job.
1576 .P
1577 Most of the arguments of \fBpcre_copy_named_substring()\fP and
1578 \fBpcre_get_named_substring()\fP are the same as those for the similarly named
1579 functions that extract by number. As these are described in the previous
1580 section, they are not re-described here. There are just two differences:
1581 .P
1582 First, instead of a substring number, a substring name is given. Second, there
1583 is an extra argument, given at the start, which is a pointer to the compiled
1584 pattern. This is needed in order to gain access to the name-to-number
1585 translation table.
1586 .P
1587 These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1588 then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1589 appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1590 the behaviour may not be what you want (see the next section).
1591 .
1592 .
1593 .SH "DUPLICATE SUBPATTERN NAMES"
1594 .rs
1595 .sp
1596 .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
1597 .ti +5n
1598 .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
1599 .PP
1600 When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
1601 are not required to be unique. Normally, patterns with duplicate names are such
1602 that in any one match, only one of the named subpatterns participates. An
1603 example is shown in the
1604 .\" HREF
1605 \fBpcrepattern\fP
1606 .\"
1607 documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP
1608 and \fBpcre_get_named_substring()\fP return the first substring corresponding
1609 to the given name that is set. If none are set, an empty string is returned.
1610 The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are
1611 associated with the name, but it is not defined which it is.
1612 .sp
1613 If you want to get full details of all captured substrings for a given name,
1614 you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1615 argument is the compiled pattern, and the second is the name. The third and
1616 fourth are pointers to variables which are updated by the function. After it
1617 has run, they point to the first and last entries in the name-to-number table
1618 for the given name. The function itself returns the length of each entry, or
1619 PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1620 described above in the section entitled \fIInformation about a pattern\fP.
1621 Given all the relevant entries for the name, you can extract each of their
1622 numbers, and hence the captured data, if any.
1623 .
1624 .
1625 .SH "FINDING ALL POSSIBLE MATCHES"
1626 .rs
1627 .sp
1628 The traditional matching function uses a similar algorithm to Perl, which stops
1629 when it finds the first match, starting at a given point in the subject. If you
1630 want to find all possible matches, or the longest possible match, consider
1631 using the alternative matching function (see below) instead. If you cannot use
1632 the alternative function, but still need to find all possible matches, you
1633 can kludge it up by making use of the callout facility, which is described in
1634 the
1635 .\" HREF
1636 \fBpcrecallout\fP
1637 .\"
1638 documentation.
1639 .P
1640 What you have to do is to insert a callout right at the end of the pattern.
1641 When your callout function is called, extract and save the current matched
1642 substring. Then return 1, which forces \fBpcre_exec()\fP to backtrack and try
1643 other alternatives. Ultimately, when it runs out of matches, \fBpcre_exec()\fP
1644 will yield PCRE_ERROR_NOMATCH.
1645 .
1646 .
1647 .\" HTML <a name="dfamatch"></a>
1648 .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
1649 .rs
1650 .sp
1651 .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
1652 .ti +5n
1653 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
1654 .ti +5n
1655 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
1656 .ti +5n
1657 .B int *\fIworkspace\fP, int \fIwscount\fP);
1658 .P
1659 The function \fBpcre_dfa_exec()\fP is called to match a subject string against
1660 a compiled pattern, using a matching algorithm that scans the subject string
1661 just once, and does not backtrack. This has different characteristics to the
1662 normal algorithm, and is not compatible with Perl. Some of the features of PCRE
1663 patterns are not supported. Nevertheless, there are times when this kind of
1664 matching can be useful. For a discussion of the two matching algorithms, see
1665 the
1666 .\" HREF
1667 \fBpcrematching\fP
1668 .\"
1669 documentation.
1670 .P
1671 The arguments for the \fBpcre_dfa_exec()\fP function are the same as for
1672 \fBpcre_exec()\fP, plus two extras. The \fIovector\fP argument is used in a
1673 different way, and this is described below. The other common arguments are used
1674 in the same way as for \fBpcre_exec()\fP, so their description is not repeated
1675 here.
1676 .P
1677 The two additional arguments provide workspace for the function. The workspace
1678 vector should contain at least 20 elements. It is used for keeping track of
1679 multiple paths through the pattern tree. More workspace will be needed for
1680 patterns and subjects where there are a lot of potential matches.
1681 .P
1682 Here is an example of a simple call to \fBpcre_dfa_exec()\fP:
1683 .sp
1684 int rc;
1685 int ovector[10];
1686 int wspace[20];
1687 rc = pcre_dfa_exec(
1688 re, /* result of pcre_compile() */
1689 NULL, /* we didn't study the pattern */
1690 "some string", /* the subject string */
1691 11, /* the length of the subject string */
1692 0, /* start at offset 0 in the subject */
1693 0, /* default options */
1694 ovector, /* vector of integers for substring information */
1695 10, /* number of elements (NOT size in bytes) */
1696 wspace, /* working space vector */
1697 20); /* number of elements (NOT size in bytes) */
1698 .
1699 .SS "Option bits for \fBpcre_dfa_exec()\fP"
1700 .rs
1701 .sp
1702 The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be
1703 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1704 PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,
1705 PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are
1706 the same as for \fBpcre_exec()\fP, so their description is not repeated here.
1707 .sp
1708 PCRE_PARTIAL
1709 .sp
1710 This has the same general effect as it does for \fBpcre_exec()\fP, but the
1711 details are slightly different. When PCRE_PARTIAL is set for
1712 \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into
1713 PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no
1714 complete matches, but there is still at least one matching possibility. The
1715 portion of the string that provided the partial match is set as the first
1716 matching string.
1717 .sp
1718 PCRE_DFA_SHORTEST
1719 .sp
1720 Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
1721 soon as it has found one match. Because of the way the alternative algorithm
1722 works, this is necessarily the shortest possible match at the first possible
1723 matching point in the subject string.
1724 .sp
1725 PCRE_DFA_RESTART
1726 .sp
1727 When \fBpcre_dfa_exec()\fP is called with the PCRE_PARTIAL option, and returns
1728 a partial match, it is possible to call it again, with additional subject
1729 characters, and have it continue with the same match. The PCRE_DFA_RESTART
1730 option requests this action; when it is set, the \fIworkspace\fP and
1731 \fIwscount\fP options must reference the same vector as before because data
1732 about the match so far is left in them after a partial match. There is more
1733 discussion of this facility in the
1734 .\" HREF
1735 \fBpcrepartial\fP
1736 .\"
1737 documentation.
1738 .
1739 .SS "Successful returns from \fBpcre_dfa_exec()\fP"
1740 .rs
1741 .sp
1742 When \fBpcre_dfa_exec()\fP succeeds, it may have matched more than one
1743 substring in the subject. Note, however, that all the matches from one run of
1744 the function start at the same point in the subject. The shorter matches are
1745 all initial substrings of the longer matches. For example, if the pattern
1746 .sp
1747 <.*>
1748 .sp
1749 is matched against the string
1750 .sp
1751 This is <something> <something else> <something further> no more
1752 .sp
1753 the three matched strings are
1754 .sp
1755 <something>
1756 <something> <something else>
1757 <something> <something else> <something further>
1758 .sp
1759 On success, the yield of the function is a number greater than zero, which is
1760 the number of matched substrings. The substrings themselves are returned in
1761 \fIovector\fP. Each string uses two elements; the first is the offset to the
1762 start, and the second is the offset to the end. In fact, all the strings have
1763 the same start offset. (Space could have been saved by giving this only once,
1764 but it was decided to retain some compatibility with the way \fBpcre_exec()\fP
1765 returns data, even though the meaning of the strings is different.)
1766 .P
1767 The strings are returned in reverse order of length; that is, the longest
1768 matching string is given first. If there were too many matches to fit into
1769 \fIovector\fP, the yield of the function is zero, and the vector is filled with
1770 the longest matches.
1771 .
1772 .SS "Error returns from \fBpcre_dfa_exec()\fP"
1773 .rs
1774 .sp
1775 The \fBpcre_dfa_exec()\fP function returns a negative number when it fails.
1776 Many of the errors are the same as for \fBpcre_exec()\fP, and these are
1777 described
1778 .\" HTML <a href="#errorlist">
1779 .\" </a>
1780 above.
1781 .\"
1782 There are in addition the following errors that are specific to
1783 \fBpcre_dfa_exec()\fP:
1784 .sp
1785 PCRE_ERROR_DFA_UITEM (-16)
1786 .sp
1787 This return is given if \fBpcre_dfa_exec()\fP encounters an item in the pattern
1788 that it does not support, for instance, the use of \eC or a back reference.
1789 .sp
1790 PCRE_ERROR_DFA_UCOND (-17)
1791 .sp
1792 This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that
1793 uses a back reference for the condition, or a test for recursion in a specific
1794 group. These are not supported.
1795 .sp
1796 PCRE_ERROR_DFA_UMLIMIT (-18)
1797 .sp
1798 This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP
1799 block that contains a setting of the \fImatch_limit\fP field. This is not
1800 supported (it is meaningless).
1801 .sp
1802 PCRE_ERROR_DFA_WSSIZE (-19)
1803 .sp
1804 This return is given if \fBpcre_dfa_exec()\fP runs out of space in the
1805 \fIworkspace\fP vector.
1806 .sp
1807 PCRE_ERROR_DFA_RECURSE (-20)
1808 .sp
1809 When a recursive subpattern is processed, the matching function calls itself
1810 recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1811 error is given if the output vector is not large enough. This should be
1812 extremely rare, as a vector of size 1000 is used.
1813 .
1814 .
1815 .SH "SEE ALSO"
1816 .rs
1817 .sp
1818 \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1819 \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1820 \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1821 .
1822 .
1823 .SH AUTHOR
1824 .rs
1825 .sp
1826 .nf
1827 Philip Hazel
1828 University Computing Service
1829 Cambridge CB2 3QH, England.
1830 .fi
1831 .
1832 .
1833 .SH REVISION
1834 .rs
1835 .sp
1836 .nf
1837 Last updated: 06 March 2007
1838 Copyright (c) 1997-2007 University of Cambridge.
1839 .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