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

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

Parent Directory Parent Directory | Revision Log Revision Log


Revision 209 - (hide annotations) (download)
Tue Aug 7 09:22:06 2007 UTC (7 years ago) by ph10
File size: 80950 byte(s)
Add words about valid UTF-8 vs assigned Unicode code point to the docs.

1 nigel 79 .TH PCREAPI 3
2 nigel 63 .SH NAME
3     PCRE - Perl-compatible regular expressions
4 nigel 75 .SH "PCRE NATIVE API"
5 nigel 63 .rs
6     .sp
7     .B #include <pcre.h>
8     .PP
9     .SM
10 nigel 75 .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
11 nigel 63 .ti +5n
12 nigel 75 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
13 nigel 63 .ti +5n
14 nigel 75 .B const unsigned char *\fItableptr\fP);
15 nigel 63 .PP
16 nigel 77 .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 nigel 75 .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,
25 nigel 63 .ti +5n
26 nigel 75 .B const char **\fIerrptr\fP);
27 nigel 63 .PP
28 nigel 75 .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
29 nigel 63 .ti +5n
30 nigel 75 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
31 nigel 63 .ti +5n
32 nigel 75 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
33 nigel 63 .PP
34 nigel 77 .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 nigel 75 .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
43 nigel 63 .ti +5n
44 nigel 75 .B const char *\fIsubject\fP, int *\fIovector\fP,
45 nigel 63 .ti +5n
46 nigel 75 .B int \fIstringcount\fP, const char *\fIstringname\fP,
47 nigel 63 .ti +5n
48 nigel 75 .B char *\fIbuffer\fP, int \fIbuffersize\fP);
49 nigel 63 .PP
50 nigel 75 .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
51 nigel 63 .ti +5n
52 nigel 75 .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
53 nigel 63 .ti +5n
54 nigel 75 .B int \fIbuffersize\fP);
55 nigel 63 .PP
56 nigel 75 .B int pcre_get_named_substring(const pcre *\fIcode\fP,
57 nigel 63 .ti +5n
58 nigel 75 .B const char *\fIsubject\fP, int *\fIovector\fP,
59 nigel 63 .ti +5n
60 nigel 75 .B int \fIstringcount\fP, const char *\fIstringname\fP,
61 nigel 63 .ti +5n
62 nigel 75 .B const char **\fIstringptr\fP);
63 nigel 63 .PP
64 nigel 75 .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
65 nigel 63 .ti +5n
66 nigel 75 .B const char *\fIname\fP);
67 nigel 63 .PP
68 nigel 91 .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 nigel 75 .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
73 nigel 63 .ti +5n
74 nigel 75 .B int \fIstringcount\fP, int \fIstringnumber\fP,
75 nigel 63 .ti +5n
76 nigel 75 .B const char **\fIstringptr\fP);
77 nigel 63 .PP
78 nigel 75 .B int pcre_get_substring_list(const char *\fIsubject\fP,
79 nigel 63 .ti +5n
80 nigel 75 .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
81 nigel 63 .PP
82 nigel 75 .B void pcre_free_substring(const char *\fIstringptr\fP);
83 nigel 63 .PP
84 nigel 75 .B void pcre_free_substring_list(const char **\fIstringptr\fP);
85 nigel 63 .PP
86     .B const unsigned char *pcre_maketables(void);
87     .PP
88 nigel 75 .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
89 nigel 63 .ti +5n
90 nigel 75 .B int \fIwhat\fP, void *\fIwhere\fP);
91 nigel 63 .PP
92 nigel 75 .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
93     .B *\fIfirstcharptr\fP);
94 nigel 63 .PP
95 nigel 77 .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
96     .PP
97 nigel 75 .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
98 nigel 63 .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 nigel 73 .B void *(*pcre_stack_malloc)(size_t);
106     .PP
107     .B void (*pcre_stack_free)(void *);
108     .PP
109 nigel 63 .B int (*pcre_callout)(pcre_callout_block *);
110 nigel 75 .
111     .
112     .SH "PCRE API OVERVIEW"
113 nigel 63 .rs
114     .sp
115 nigel 93 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 nigel 77 API. These are described in the
118 nigel 75 .\" HREF
119     \fBpcreposix\fP
120     .\"
121 nigel 77 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 nigel 75 .P
128 nigel 77 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 nigel 75 Applications can use these to include support for different releases of PCRE.
134     .P
135 nigel 77 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 nigel 75 .\" HREF
141     \fBpcresample\fP
142     .\"
143     documentation describes how to run it.
144     .P
145 nigel 77 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 nigel 91 matching. The alternative algorithm finds all possible matches (at a given
148 nigel 93 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 nigel 77 .\" HREF
152     \fBpcrematching\fP
153     .\"
154     documentation.
155     .P
156 nigel 75 In addition to the main compiling and matching functions, there are convenience
157 nigel 77 functions for extracting captured substrings from a subject string that is
158     matched by \fBpcre_exec()\fP. They are:
159 nigel 75 .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 nigel 91 \fBpcre_get_stringtable_entries()\fP
167 nigel 75 .sp
168     \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also
169 nigel 63 provided, to free the memory used for extracted strings.
170 nigel 75 .P
171     The function \fBpcre_maketables()\fP is used to build a set of character tables
172 nigel 77 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 nigel 75 .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 nigel 63 some of the available information, but is retained for backwards compatibility.
180 nigel 75 The function \fBpcre_version()\fP returns a pointer to a string containing the
181 nigel 63 version of PCRE and its date of release.
182 nigel 75 .P
183 nigel 77 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 nigel 75 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 nigel 63 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 nigel 75 .P
193     The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also
194 nigel 73 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 nigel 91 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 nigel 75 .P
212     The global variable \fBpcre_callout\fP initially contains NULL. It can be set
213 nigel 63 by the caller to a "callout" function, which PCRE will then call at specified
214 nigel 75 points during a matching operation. Details are given in the
215     .\" HREF
216     \fBpcrecallout\fP
217     .\"
218 nigel 63 documentation.
219 nigel 75 .
220     .
221 nigel 91 .SH NEWLINES
222 nigel 93 .rs
223 nigel 91 .sp
224 ph10 149 PCRE supports five different conventions for indicating line breaks in
225 nigel 93 strings: a single CR (carriage return) character, a single LF (linefeed)
226 ph10 149 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 nigel 93 .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 nigel 91 In the PCRE documentation the word "newline" is used to mean "the character or
239 nigel 93 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 nigel 91 .
246     .
247 nigel 63 .SH MULTITHREADING
248     .rs
249     .sp
250     The PCRE functions can be used in multi-threading applications, with the
251 nigel 75 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 nigel 63 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 nigel 75 .
258     .
259     .SH "SAVING PRECOMPILED PATTERNS FOR LATER USE"
260 nigel 63 .rs
261     .sp
262 nigel 75 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 ph10 155 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 nigel 75 .
272     .
273     .SH "CHECKING BUILD-TIME OPTIONS"
274     .rs
275     .sp
276     .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
277 nigel 63 .PP
278 nigel 75 The function \fBpcre_config()\fP makes it possible for a PCRE client to
279 nigel 63 discover which optional features have been compiled into the PCRE library. The
280     .\" HREF
281 nigel 75 \fBpcrebuild\fP
282 nigel 63 .\"
283     documentation has more details about these optional features.
284 nigel 75 .P
285     The first argument for \fBpcre_config()\fP is an integer, specifying which
286 nigel 63 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 nigel 75 .sp
289 nigel 63 PCRE_CONFIG_UTF8
290 nigel 75 .sp
291 nigel 63 The output is an integer that is set to one if UTF-8 support is available;
292     otherwise it is set to zero.
293 nigel 75 .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 nigel 63 PCRE_CONFIG_NEWLINE
300 nigel 75 .sp
301 nigel 91 The output is an integer whose value specifies the default character sequence
302 nigel 93 that is recognized as meaning "newline". The four values that are supported
303 ph10 149 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 nigel 75 .sp
306 nigel 63 PCRE_CONFIG_LINK_SIZE
307 nigel 75 .sp
308 nigel 63 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 nigel 75 .sp
314 nigel 63 PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
315 nigel 75 .sp
316 nigel 63 The output is an integer that contains the threshold above which the POSIX
317 nigel 75 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 nigel 63 PCRE_CONFIG_MATCH_LIMIT
325 nigel 75 .sp
326 nigel 63 The output is an integer that gives the default limit for the number of
327 nigel 75 internal matching function calls in a \fBpcre_exec()\fP execution. Further
328     details are given with \fBpcre_exec()\fP below.
329     .sp
330 nigel 87 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 nigel 73 PCRE_CONFIG_STACKRECURSE
337 nigel 75 .sp
338 nigel 77 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 nigel 75 .
346     .
347     .SH "COMPILING A PATTERN"
348 nigel 63 .rs
349     .sp
350 nigel 75 .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
351 nigel 63 .ti +5n
352 nigel 75 .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
353 nigel 63 .ti +5n
354 nigel 75 .B const unsigned char *\fItableptr\fP);
355 nigel 77 .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 nigel 75 .P
364 nigel 77 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 nigel 75 .P
369 nigel 77 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 nigel 91 caller to free the memory (via \fBpcre_free\fP) when it is no longer required.
375 nigel 77 .P
376 nigel 63 Although the compiled code of a PCRE regex is relocatable, that is, it does not
377 nigel 75 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 nigel 93 The \fIoptions\fP argument contains various bit settings that affect the
382 nigel 75 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 nigel 91 PCRE_ANCHORED and PCRE_NEWLINE_\fIxxx\fP options can be set at the time of
392     matching as well as at compile time.
393 nigel 75 .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 nigel 87 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 nigel 75 \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.
401     .P
402 nigel 77 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 nigel 75 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 nigel 63 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 nigel 75 .sp
426     The following names for option bits are defined in the \fBpcre.h\fP header
427     file:
428     .sp
429 nigel 63 PCRE_ANCHORED
430 nigel 75 .sp
431 nigel 63 If this bit is set, the pattern is forced to be "anchored", that is, it is
432 nigel 75 constrained to match only at the first matching point in the string that is
433 nigel 63 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 nigel 75 .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 nigel 63 PCRE_CASELESS
448 nigel 75 .sp
449 nigel 63 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 nigel 77 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 nigel 75 .sp
459 nigel 63 PCRE_DOLLAR_ENDONLY
460 nigel 75 .sp
461 nigel 63 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 nigel 91 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 nigel 75 .sp
468 nigel 63 PCRE_DOTALL
469 nigel 75 .sp
470 nigel 63 If this bit is set, a dot metacharater in the pattern matches all characters,
471 nigel 91 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 nigel 93 negative class such as [^a] always matches newline characters, independent of
475     the setting of this option.
476 nigel 75 .sp
477 nigel 91 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 nigel 63 PCRE_EXTENDED
489 nigel 75 .sp
490 nigel 63 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 nigel 91 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 nigel 75 .P
497 nigel 63 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 nigel 75 .sp
502 nigel 63 PCRE_EXTRA
503 nigel 75 .sp
504 nigel 63 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 nigel 91 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 nigel 75 .sp
513 nigel 77 PCRE_FIRSTLINE
514     .sp
515     If this option is set, an unanchored pattern is required to match before or at
516 nigel 91 the first newline in the subject string, though the matched text may continue
517     over the newline.
518 nigel 77 .sp
519 nigel 63 PCRE_MULTILINE
520 nigel 75 .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 nigel 63 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 nigel 75 .P
528 nigel 63 When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
529 nigel 91 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 nigel 63 occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
534 nigel 75 .sp
535 nigel 91 PCRE_NEWLINE_CR
536     PCRE_NEWLINE_LF
537     PCRE_NEWLINE_CRLF
538 ph10 150 PCRE_NEWLINE_ANYCRLF
539 nigel 93 PCRE_NEWLINE_ANY
540 nigel 91 .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 nigel 93 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 ph10 149 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 nigel 91 .P
553 nigel 93 The newline setting in the options word uses three bits that are treated
554 ph10 149 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 nigel 93 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 ph10 149 other combinations may yield unused numbers and cause an error.
559 nigel 93 .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 nigel 91 .sp
570 nigel 63 PCRE_NO_AUTO_CAPTURE
571 nigel 75 .sp
572 nigel 63 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 nigel 75 .sp
578 nigel 63 PCRE_UNGREEDY
579 nigel 75 .sp
580 nigel 63 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 nigel 75 .sp
584 nigel 63 PCRE_UTF8
585 nigel 75 .sp
586 nigel 63 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 nigel 75 available only when PCRE is built to include UTF-8 support. If not, the use
589 nigel 63 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 nigel 75 \fBpcre\fP
598 nigel 63 .\"
599     page.
600 nigel 75 .sp
601 nigel 71 PCRE_NO_UTF8_CHECK
602 nigel 75 .sp
603 nigel 71 When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
604 ph10 209 automatically checked. Note that the check is for a syntactically valid UTF-8
605     byte string, as defined by RFC 2279. It is \fInot\fP a check for a UTF-8 string
606     of assigned or allowable Unicode code points.
607     .P
608     If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP returns an
609     error. If you already know that your pattern is valid, and you want to skip
610     this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option.
611     When it is set, the effect of passing an invalid UTF-8 string as a pattern is
612     undefined. It may cause your program to crash. Note that this option can also
613     be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress the UTF-8
614     validity checking of subject strings.
615 nigel 75 .
616     .
617 nigel 77 .SH "COMPILATION ERROR CODES"
618     .rs
619     .sp
620     The following table lists the error codes than may be returned by
621     \fBpcre_compile2()\fP, along with the error messages that may be returned by
622 nigel 93 both compiling functions. As PCRE has developed, some error codes have fallen
623     out of use. To avoid confusion, they have not been re-used.
624 nigel 77 .sp
625     0 no error
626     1 \e at end of pattern
627     2 \ec at end of pattern
628     3 unrecognized character follows \e
629     4 numbers out of order in {} quantifier
630     5 number too big in {} quantifier
631     6 missing terminating ] for character class
632     7 invalid escape sequence in character class
633     8 range out of order in character class
634     9 nothing to repeat
635 nigel 93 10 [this code is not in use]
636 nigel 77 11 internal error: unexpected repeat
637     12 unrecognized character after (?
638     13 POSIX named classes are supported only within a class
639     14 missing )
640     15 reference to non-existent subpattern
641     16 erroffset passed as NULL
642     17 unknown option bit(s) set
643     18 missing ) after comment
644 nigel 93 19 [this code is not in use]
645 nigel 77 20 regular expression too large
646     21 failed to get memory
647     22 unmatched parentheses
648     23 internal error: code overflow
649     24 unrecognized character after (?<
650     25 lookbehind assertion is not fixed length
651 nigel 91 26 malformed number or name after (?(
652 nigel 77 27 conditional group contains more than two branches
653     28 assertion expected after (?(
654 ph10 181 29 (?R or (?[+-]digits must be followed by )
655 nigel 77 30 unknown POSIX class name
656     31 POSIX collating elements are not supported
657     32 this version of PCRE is not compiled with PCRE_UTF8 support
658 nigel 93 33 [this code is not in use]
659 nigel 77 34 character value in \ex{...} sequence is too large
660     35 invalid condition (?(0)
661     36 \eC not allowed in lookbehind assertion
662     37 PCRE does not support \eL, \el, \eN, \eU, or \eu
663     38 number after (?C is > 255
664     39 closing ) for (?C expected
665     40 recursive call could loop indefinitely
666     41 unrecognized character after (?P
667 nigel 93 42 syntax error in subpattern name (missing terminator)
668 nigel 91 43 two named subpatterns have the same name
669 nigel 77 44 invalid UTF-8 string
670     45 support for \eP, \ep, and \eX has not been compiled
671     46 malformed \eP or \ep sequence
672     47 unknown property name after \eP or \ep
673 nigel 91 48 subpattern name is too long (maximum 32 characters)
674     49 too many named subpatterns (maximum 10,000)
675 ph10 202 50 [this code is not in use]
676 nigel 91 51 octal value is greater than \e377 (not in UTF-8 mode)
677 nigel 93 52 internal error: overran compiling workspace
678     53 internal error: previously-checked referenced subpattern not found
679     54 DEFINE group contains more than one branch
680     55 repeating a DEFINE group is not allowed
681     56 inconsistent NEWLINE options"
682 ph10 182 57 \eg is not followed by a braced name or an optionally braced
683 ph10 181 non-zero number
684     58 (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number
685 nigel 77 .
686     .
687 nigel 75 .SH "STUDYING A PATTERN"
688 nigel 63 .rs
689     .sp
690 nigel 77 .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP
691 nigel 63 .ti +5n
692 nigel 75 .B const char **\fIerrptr\fP);
693 nigel 63 .PP
694 nigel 75 If a compiled pattern is going to be used several times, it is worth spending
695     more time analyzing it in order to speed up the time taken for matching. The
696     function \fBpcre_study()\fP takes a pointer to a compiled pattern as its first
697     argument. If studying the pattern produces additional information that will
698     help speed up matching, \fBpcre_study()\fP returns a pointer to a
699     \fBpcre_extra\fP block, in which the \fIstudy_data\fP field points to the
700     results of the study.
701     .P
702     The returned value from \fBpcre_study()\fP can be passed directly to
703     \fBpcre_exec()\fP. However, a \fBpcre_extra\fP block also contains other
704 nigel 63 fields that can be set by the caller before the block is passed; these are
705 nigel 75 described
706     .\" HTML <a href="#extradata">
707     .\" </a>
708     below
709     .\"
710     in the section on matching a pattern.
711     .P
712 nigel 77 If studying the pattern does not produce any additional information
713 nigel 75 \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program
714     wants to pass any of the other fields to \fBpcre_exec()\fP, it must set up its
715     own \fBpcre_extra\fP block.
716     .P
717     The second argument of \fBpcre_study()\fP contains option bits. At present, no
718     options are defined, and this argument should always be zero.
719     .P
720     The third argument for \fBpcre_study()\fP is a pointer for an error message. If
721 nigel 63 studying succeeds (even if no data is returned), the variable it points to is
722 nigel 87 set to NULL. Otherwise it is set to point to a textual error message. This is a
723     static string that is part of the library. You must not try to free it. You
724     should test the error pointer for NULL after calling \fBpcre_study()\fP, to be
725     sure that it has run successfully.
726 nigel 75 .P
727     This is a typical call to \fBpcre_study\fP():
728     .sp
729 nigel 63 pcre_extra *pe;
730     pe = pcre_study(
731     re, /* result of pcre_compile() */
732     0, /* no options exist */
733     &error); /* set to NULL or points to a message */
734 nigel 75 .sp
735 nigel 63 At present, studying a pattern is useful only for non-anchored patterns that do
736     not have a single fixed starting character. A bitmap of possible starting
737 nigel 75 bytes is created.
738     .
739     .
740 nigel 63 .\" HTML <a name="localesupport"></a>
741 nigel 75 .SH "LOCALE SUPPORT"
742 nigel 63 .rs
743     .sp
744 ph10 139 PCRE handles caseless matching, and determines whether characters are letters,
745 nigel 75 digits, or whatever, by reference to a set of tables, indexed by character
746 nigel 77 value. When running in UTF-8 mode, this applies only to characters with codes
747 nigel 75 less than 128. Higher-valued codes never match escapes such as \ew or \ed, but
748     can be tested with \ep if PCRE is built with Unicode character property
749 ph10 142 support. The use of locales with Unicode is discouraged. If you are handling
750     characters with codes greater than 128, you should either use UTF-8 and
751 ph10 139 Unicode, or use locales, but not try to mix the two.
752 nigel 75 .P
753 ph10 139 PCRE contains an internal set of tables that are used when the final argument
754     of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
755 ph10 142 Normally, the internal tables recognize only ASCII characters. However, when
756 ph10 139 PCRE is built, it is possible to cause the internal tables to be rebuilt in the
757     default "C" locale of the local system, which may cause them to be different.
758 nigel 75 .P
759 ph10 139 The internal tables can always be overridden by tables supplied by the
760     application that calls PCRE. These may be created in a different locale from
761     the default. As more and more applications change to using Unicode, the need
762     for this locale support is expected to die away.
763     .P
764 nigel 75 External tables are built by calling the \fBpcre_maketables()\fP function,
765     which has no arguments, in the relevant locale. The result can then be passed
766     to \fBpcre_compile()\fP or \fBpcre_exec()\fP as often as necessary. For
767     example, to build and use tables that are appropriate for the French locale
768     (where accented characters with values greater than 128 are treated as letters),
769     the following code could be used:
770     .sp
771     setlocale(LC_CTYPE, "fr_FR");
772 nigel 63 tables = pcre_maketables();
773     re = pcre_compile(..., tables);
774 nigel 75 .sp
775 ph10 142 The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
776 ph10 139 are using Windows, the name for the French locale is "french".
777     .P
778 nigel 75 When \fBpcre_maketables()\fP runs, the tables are built in memory that is
779     obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure
780     that the memory containing the tables remains available for as long as it is
781     needed.
782     .P
783     The pointer that is passed to \fBpcre_compile()\fP is saved with the compiled
784     pattern, and the same tables are used via this pointer by \fBpcre_study()\fP
785     and normally also by \fBpcre_exec()\fP. Thus, by default, for any single
786     pattern, compilation, studying and matching all happen in the same locale, but
787     different patterns can be compiled in different locales.
788     .P
789     It is possible to pass a table pointer or NULL (indicating the use of the
790     internal tables) to \fBpcre_exec()\fP. Although not intended for this purpose,
791     this facility could be used to match a pattern in a different locale from the
792     one in which it was compiled. Passing table pointers at run time is discussed
793     below in the section on matching a pattern.
794     .
795     .
796     .SH "INFORMATION ABOUT A PATTERN"
797 nigel 63 .rs
798     .sp
799 nigel 75 .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
800 nigel 63 .ti +5n
801 nigel 75 .B int \fIwhat\fP, void *\fIwhere\fP);
802 nigel 63 .PP
803 nigel 75 The \fBpcre_fullinfo()\fP function returns information about a compiled
804     pattern. It replaces the obsolete \fBpcre_info()\fP function, which is
805 nigel 63 nevertheless retained for backwards compability (and is documented below).
806 nigel 75 .P
807     The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled
808     pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if
809 nigel 63 the pattern was not studied. The third argument specifies which piece of
810     information is required, and the fourth argument is a pointer to a variable
811     to receive the data. The yield of the function is zero for success, or one of
812     the following negative numbers:
813 nigel 75 .sp
814     PCRE_ERROR_NULL the argument \fIcode\fP was NULL
815     the argument \fIwhere\fP was NULL
816 nigel 63 PCRE_ERROR_BADMAGIC the "magic number" was not found
817 nigel 75 PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid
818     .sp
819     The "magic number" is placed at the start of each compiled pattern as an simple
820     check against passing an arbitrary memory pointer. Here is a typical call of
821     \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
822     .sp
823 nigel 63 int rc;
824 nigel 91 size_t length;
825 nigel 63 rc = pcre_fullinfo(
826     re, /* result of pcre_compile() */
827     pe, /* result of pcre_study(), or NULL */
828     PCRE_INFO_SIZE, /* what is required */
829     &length); /* where to put the data */
830 nigel 75 .sp
831     The possible values for the third argument are defined in \fBpcre.h\fP, and are
832 nigel 63 as follows:
833 nigel 75 .sp
834 nigel 63 PCRE_INFO_BACKREFMAX
835 nigel 75 .sp
836 nigel 63 Return the number of the highest back reference in the pattern. The fourth
837 nigel 75 argument should point to an \fBint\fP variable. Zero is returned if there are
838 nigel 63 no back references.
839 nigel 75 .sp
840 nigel 63 PCRE_INFO_CAPTURECOUNT
841 nigel 75 .sp
842 nigel 63 Return the number of capturing subpatterns in the pattern. The fourth argument
843 nigel 75 should point to an \fBint\fP variable.
844     .sp
845 nigel 77 PCRE_INFO_DEFAULT_TABLES
846 nigel 75 .sp
847     Return a pointer to the internal default character tables within PCRE. The
848     fourth argument should point to an \fBunsigned char *\fP variable. This
849     information call is provided for internal use by the \fBpcre_study()\fP
850     function. External callers can cause PCRE to use its internal tables by passing
851     a NULL table pointer.
852     .sp
853 nigel 63 PCRE_INFO_FIRSTBYTE
854 nigel 75 .sp
855 nigel 63 Return information about the first byte of any matched string, for a
856 nigel 91 non-anchored pattern. The fourth argument should point to an \fBint\fP
857     variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
858     still recognized for backwards compatibility.)
859 nigel 75 .P
860     If there is a fixed first byte, for example, from a pattern such as
861 nigel 93 (cat|cow|coyote), its value is returned. Otherwise, if either
862 nigel 75 .sp
863 nigel 63 (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
864     starts with "^", or
865 nigel 75 .sp
866 nigel 63 (b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
867     (if it were set, the pattern would be anchored),
868 nigel 75 .sp
869 nigel 63 -1 is returned, indicating that the pattern matches only at the start of a
870     subject string or after any newline within the string. Otherwise -2 is
871     returned. For anchored patterns, -2 is returned.
872 nigel 75 .sp
873 nigel 63 PCRE_INFO_FIRSTTABLE
874 nigel 75 .sp
875 nigel 63 If the pattern was studied, and this resulted in the construction of a 256-bit
876     table indicating a fixed set of bytes for the first byte in any matching
877     string, a pointer to the table is returned. Otherwise NULL is returned. The
878 nigel 75 fourth argument should point to an \fBunsigned char *\fP variable.
879     .sp
880 ph10 169 PCRE_INFO_JCHANGED
881     .sp
882 ph10 172 Return 1 if the (?J) option setting is used in the pattern, otherwise 0. The
883 ph10 169 fourth argument should point to an \fBint\fP variable. The (?J) internal option
884 ph10 181 setting changes the local PCRE_DUPNAMES option.
885 ph10 169 .sp
886 nigel 63 PCRE_INFO_LASTLITERAL
887 nigel 75 .sp
888 nigel 65 Return the value of the rightmost literal byte that must exist in any matched
889     string, other than at its start, if such a byte has been recorded. The fourth
890 nigel 75 argument should point to an \fBint\fP variable. If there is no such byte, -1 is
891 nigel 65 returned. For anchored patterns, a last literal byte is recorded only if it
892     follows something of variable length. For example, for the pattern
893 nigel 75 /^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value
894 nigel 65 is -1.
895 nigel 75 .sp
896 nigel 63 PCRE_INFO_NAMECOUNT
897     PCRE_INFO_NAMEENTRYSIZE
898     PCRE_INFO_NAMETABLE
899 nigel 75 .sp
900 nigel 63 PCRE supports the use of named as well as numbered capturing parentheses. The
901     names are just an additional way of identifying the parentheses, which still
902 nigel 91 acquire numbers. Several convenience functions such as
903     \fBpcre_get_named_substring()\fP are provided for extracting captured
904     substrings by name. It is also possible to extract the data directly, by first
905     converting the name to a number in order to access the correct pointers in the
906     output vector (described with \fBpcre_exec()\fP below). To do the conversion,
907     you need to use the name-to-number map, which is described by these three
908     values.
909 nigel 75 .P
910 nigel 63 The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives
911     the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
912 nigel 75 entry; both of these return an \fBint\fP value. The entry size depends on the
913 nigel 63 length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
914 nigel 75 entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry
915 nigel 63 are the number of the capturing parenthesis, most significant byte first. The
916     rest of the entry is the corresponding name, zero terminated. The names are in
917 nigel 91 alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of
918     their parentheses numbers. For example, consider the following pattern (assume
919 nigel 63 PCRE_EXTENDED is set, so white space - including newlines - is ignored):
920 nigel 75 .sp
921     .\" JOIN
922 nigel 93 (?<date> (?<year>(\ed\ed)?\ed\ed) -
923     (?<month>\ed\ed) - (?<day>\ed\ed) )
924 nigel 75 .sp
925 nigel 63 There are four named subpatterns, so the table has four entries, and each entry
926     in the table is eight bytes long. The table is as follows, with non-printing
927 nigel 75 bytes shows in hexadecimal, and undefined bytes shown as ??:
928     .sp
929 nigel 63 00 01 d a t e 00 ??
930     00 05 d a y 00 ?? ??
931     00 04 m o n t h 00
932     00 02 y e a r 00 ??
933 nigel 75 .sp
934     When writing code to extract data from named subpatterns using the
935 nigel 91 name-to-number map, remember that the length of the entries is likely to be
936 nigel 75 different for each compiled pattern.
937     .sp
938 ph10 169 PCRE_INFO_OKPARTIAL
939     .sp
940 ph10 172 Return 1 if the pattern can be used for partial matching, otherwise 0. The
941 ph10 169 fourth argument should point to an \fBint\fP variable. The
942     .\" HREF
943     \fBpcrepartial\fP
944     .\"
945     documentation lists the restrictions that apply to patterns when partial
946     matching is used.
947     .sp
948 nigel 63 PCRE_INFO_OPTIONS
949 nigel 75 .sp
950 nigel 63 Return a copy of the options with which the pattern was compiled. The fourth
951 nigel 75 argument should point to an \fBunsigned long int\fP variable. These option bits
952     are those specified in the call to \fBpcre_compile()\fP, modified by any
953 ph10 196 top-level option settings at the start of the pattern itself. In other words,
954     they are the options that will be in force when matching starts. For example,
955     if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
956     result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
957 nigel 75 .P
958 nigel 63 A pattern is automatically anchored by PCRE if all of its top-level
959     alternatives begin with one of the following:
960 nigel 75 .sp
961 nigel 63 ^ unless PCRE_MULTILINE is set
962 nigel 75 \eA always
963     \eG always
964     .\" JOIN
965 nigel 63 .* if PCRE_DOTALL is set and there are no back
966     references to the subpattern in which .* appears
967 nigel 75 .sp
968 nigel 63 For such patterns, the PCRE_ANCHORED bit is set in the options returned by
969 nigel 75 \fBpcre_fullinfo()\fP.
970     .sp
971 nigel 63 PCRE_INFO_SIZE
972 nigel 75 .sp
973 nigel 63 Return the size of the compiled pattern, that is, the value that was passed as
974 nigel 75 the argument to \fBpcre_malloc()\fP when PCRE was getting memory in which to
975     place the compiled data. The fourth argument should point to a \fBsize_t\fP
976 nigel 63 variable.
977 nigel 75 .sp
978 nigel 63 PCRE_INFO_STUDYSIZE
979 nigel 75 .sp
980     Return the size of the data block pointed to by the \fIstudy_data\fP field in
981     a \fBpcre_extra\fP block. That is, it is the value that was passed to
982     \fBpcre_malloc()\fP when PCRE was getting memory into which to place the data
983     created by \fBpcre_study()\fP. The fourth argument should point to a
984     \fBsize_t\fP variable.
985     .
986     .
987     .SH "OBSOLETE INFO FUNCTION"
988 nigel 63 .rs
989     .sp
990 nigel 75 .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
991     .B *\fIfirstcharptr\fP);
992 nigel 63 .PP
993 nigel 75 The \fBpcre_info()\fP function is now obsolete because its interface is too
994 nigel 63 restrictive to return all the available data about a compiled pattern. New
995 nigel 75 programs should use \fBpcre_fullinfo()\fP instead. The yield of
996     \fBpcre_info()\fP is the number of capturing subpatterns, or one of the
997 nigel 63 following negative numbers:
998 nigel 75 .sp
999     PCRE_ERROR_NULL the argument \fIcode\fP was NULL
1000 nigel 63 PCRE_ERROR_BADMAGIC the "magic number" was not found
1001 nigel 75 .sp
1002     If the \fIoptptr\fP argument is not NULL, a copy of the options with which the
1003 nigel 63 pattern was compiled is placed in the integer it points to (see
1004     PCRE_INFO_OPTIONS above).
1005 nigel 75 .P
1006     If the pattern is not anchored and the \fIfirstcharptr\fP argument is not NULL,
1007 nigel 63 it is used to pass back information about the first character of any matched
1008     string (see PCRE_INFO_FIRSTBYTE above).
1009 nigel 75 .
1010     .
1011 nigel 77 .SH "REFERENCE COUNTS"
1012 nigel 63 .rs
1013     .sp
1014 nigel 77 .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
1015     .PP
1016     The \fBpcre_refcount()\fP function is used to maintain a reference count in the
1017     data block that contains a compiled pattern. It is provided for the benefit of
1018     applications that operate in an object-oriented manner, where different parts
1019     of the application may be using the same compiled pattern, but you want to free
1020     the block when they are all done.
1021     .P
1022     When a pattern is compiled, the reference count field is initialized to zero.
1023     It is changed only by calling this function, whose action is to add the
1024     \fIadjust\fP value (which may be positive or negative) to it. The yield of the
1025     function is the new value. However, the value of the count is constrained to
1026     lie between 0 and 65535, inclusive. If the new value is outside these limits,
1027     it is forced to the appropriate limit value.
1028     .P
1029     Except when it is zero, the reference count is not correctly preserved if a
1030     pattern is compiled on one host and then transferred to a host whose byte-order
1031     is different. (This seems a highly unlikely scenario.)
1032     .
1033     .
1034     .SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION"
1035     .rs
1036     .sp
1037 nigel 75 .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
1038 nigel 63 .ti +5n
1039 nigel 75 .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
1040 nigel 63 .ti +5n
1041 nigel 75 .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
1042     .P
1043     The function \fBpcre_exec()\fP is called to match a subject string against a
1044     compiled pattern, which is passed in the \fIcode\fP argument. If the
1045 nigel 63 pattern has been studied, the result of the study should be passed in the
1046 nigel 77 \fIextra\fP argument. This function is the main matching facility of the
1047     library, and it operates in a Perl-like manner. For specialist use there is
1048     also an alternative matching function, which is described
1049     .\" HTML <a href="#dfamatch">
1050     .\" </a>
1051     below
1052     .\"
1053     in the section about the \fBpcre_dfa_exec()\fP function.
1054 nigel 75 .P
1055     In most applications, the pattern will have been compiled (and optionally
1056     studied) in the same process that calls \fBpcre_exec()\fP. However, it is
1057     possible to save compiled patterns and study data, and then use them later
1058     in different processes, possibly even on different hosts. For a discussion
1059     about this, see the
1060     .\" HREF
1061     \fBpcreprecompile\fP
1062     .\"
1063     documentation.
1064     .P
1065     Here is an example of a simple call to \fBpcre_exec()\fP:
1066     .sp
1067 nigel 63 int rc;
1068     int ovector[30];
1069     rc = pcre_exec(
1070     re, /* result of pcre_compile() */
1071     NULL, /* we didn't study the pattern */
1072     "some string", /* the subject string */
1073     11, /* the length of the subject string */
1074     0, /* start at offset 0 in the subject */
1075     0, /* default options */
1076 nigel 75 ovector, /* vector of integers for substring information */
1077 nigel 77 30); /* number of elements (NOT size in bytes) */
1078 nigel 75 .
1079     .\" HTML <a name="extradata"></a>
1080     .SS "Extra data for \fBpcre_exec()\fR"
1081     .rs
1082     .sp
1083     If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP
1084     data block. The \fBpcre_study()\fP function returns such a block (when it
1085 nigel 63 doesn't return NULL), but you can also create one for yourself, and pass
1086 nigel 87 additional information in it. The \fBpcre_extra\fP block contains the following
1087     fields (not necessarily in this order):
1088 nigel 75 .sp
1089     unsigned long int \fIflags\fP;
1090     void *\fIstudy_data\fP;
1091     unsigned long int \fImatch_limit\fP;
1092 nigel 87 unsigned long int \fImatch_limit_recursion\fP;
1093 nigel 75 void *\fIcallout_data\fP;
1094     const unsigned char *\fItables\fP;
1095     .sp
1096     The \fIflags\fP field is a bitmap that specifies which of the other fields
1097 nigel 63 are set. The flag bits are:
1098 nigel 75 .sp
1099 nigel 63 PCRE_EXTRA_STUDY_DATA
1100     PCRE_EXTRA_MATCH_LIMIT
1101 nigel 87 PCRE_EXTRA_MATCH_LIMIT_RECURSION
1102 nigel 63 PCRE_EXTRA_CALLOUT_DATA
1103 nigel 75 PCRE_EXTRA_TABLES
1104     .sp
1105     Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the
1106     \fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with
1107     the appropriate flag bit. You should not set this yourself, but you may add to
1108     the block by setting the other fields and their corresponding flag bits.
1109     .P
1110     The \fImatch_limit\fP field provides a means of preventing PCRE from using up a
1111 nigel 63 vast amount of resources when running patterns that are not going to match,
1112     but which have a very large number of possibilities in their search trees. The
1113 nigel 75 classic example is the use of nested unlimited repeats.
1114     .P
1115     Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly
1116 nigel 87 (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the
1117     number of times this function is called during a match, which has the effect of
1118     limiting the amount of backtracking that can take place. For patterns that are
1119     not anchored, the count restarts from zero for each position in the subject
1120     string.
1121 nigel 75 .P
1122 nigel 87 The default value for the limit can be set when PCRE is built; the default
1123 nigel 63 default is 10 million, which handles all but the most extreme cases. You can
1124 nigel 87 override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP
1125     block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in
1126     the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns
1127     PCRE_ERROR_MATCHLIMIT.
1128 nigel 75 .P
1129 nigel 87 The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but
1130     instead of limiting the total number of times that \fBmatch()\fP is called, it
1131     limits the depth of recursion. The recursion depth is a smaller number than the
1132     total number of calls, because not all calls to \fBmatch()\fP are recursive.
1133     This limit is of use only if it is set smaller than \fImatch_limit\fP.
1134     .P
1135     Limiting the recursion depth limits the amount of stack that can be used, or,
1136     when PCRE has been compiled to use memory on the heap instead of the stack, the
1137     amount of heap memory that can be used.
1138     .P
1139     The default value for \fImatch_limit_recursion\fP can be set when PCRE is
1140     built; the default default is the same value as the default for
1141     \fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP
1142     with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and
1143     PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
1144     is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1145     .P
1146 nigel 75 The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,
1147     which is described in the
1148     .\" HREF
1149     \fBpcrecallout\fP
1150     .\"
1151     documentation.
1152     .P
1153     The \fItables\fP field is used to pass a character tables pointer to
1154     \fBpcre_exec()\fP; this overrides the value that is stored with the compiled
1155     pattern. A non-NULL value is stored with the compiled pattern only if custom
1156     tables were supplied to \fBpcre_compile()\fP via its \fItableptr\fP argument.
1157     If NULL is passed to \fBpcre_exec()\fP using this mechanism, it forces PCRE's
1158     internal tables to be used. This facility is helpful when re-using patterns
1159     that have been saved after compiling with an external set of tables, because
1160     the external tables might be at a different address when \fBpcre_exec()\fP is
1161     called. See the
1162     .\" HREF
1163     \fBpcreprecompile\fP
1164     .\"
1165     documentation for a discussion of saving compiled patterns for later use.
1166     .
1167     .SS "Option bits for \fBpcre_exec()\fP"
1168     .rs
1169     .sp
1170     The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be
1171 nigel 91 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1172     PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
1173 nigel 75 .sp
1174     PCRE_ANCHORED
1175     .sp
1176     The PCRE_ANCHORED option limits \fBpcre_exec()\fP to matching at the first
1177     matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out
1178     to be anchored by virtue of its contents, it cannot be made unachored at
1179     matching time.
1180     .sp
1181 nigel 91 PCRE_NEWLINE_CR
1182     PCRE_NEWLINE_LF
1183     PCRE_NEWLINE_CRLF
1184 ph10 150 PCRE_NEWLINE_ANYCRLF
1185 nigel 93 PCRE_NEWLINE_ANY
1186 nigel 91 .sp
1187     These options override the newline definition that was chosen or defaulted when
1188 nigel 93 the pattern was compiled. For details, see the description of
1189     \fBpcre_compile()\fP above. During matching, the newline choice affects the
1190     behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1191     the way the match position is advanced after a match failure for an unanchored
1192 ph10 149 pattern. When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is
1193     set, and a match attempt fails when the current position is at a CRLF sequence,
1194     the match position is advanced by two characters instead of one, in other
1195     words, to after the CRLF.
1196 nigel 91 .sp
1197 nigel 63 PCRE_NOTBOL
1198 nigel 75 .sp
1199     This option specifies that first character of the subject string is not the
1200     beginning of a line, so the circumflex metacharacter should not match before
1201     it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex
1202     never to match. This option affects only the behaviour of the circumflex
1203     metacharacter. It does not affect \eA.
1204     .sp
1205 nigel 63 PCRE_NOTEOL
1206 nigel 75 .sp
1207     This option specifies that the end of the subject string is not the end of a
1208     line, so the dollar metacharacter should not match it nor (except in multiline
1209     mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at
1210     compile time) causes dollar never to match. This option affects only the
1211     behaviour of the dollar metacharacter. It does not affect \eZ or \ez.
1212     .sp
1213 nigel 63 PCRE_NOTEMPTY
1214 nigel 75 .sp
1215 nigel 63 An empty string is not considered to be a valid match if this option is set. If
1216     there are alternatives in the pattern, they are tried. If all the alternatives
1217     match the empty string, the entire match fails. For example, if the pattern
1218 nigel 75 .sp
1219 nigel 63 a?b?
1220 nigel 75 .sp
1221 nigel 63 is applied to a string not beginning with "a" or "b", it matches the empty
1222     string at the start of the subject. With PCRE_NOTEMPTY set, this match is not
1223     valid, so PCRE searches further into the string for occurrences of "a" or "b".
1224 nigel 75 .P
1225 nigel 63 Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case
1226 nigel 75 of a pattern match of the empty string within its \fBsplit()\fP function, and
1227 nigel 63 when using the /g modifier. It is possible to emulate Perl's behaviour after
1228     matching a null string by first trying the match again at the same offset with
1229 nigel 75 PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the
1230     starting offset (see below) and trying an ordinary match again. There is some
1231     code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.
1232     .sp
1233     PCRE_NO_UTF8_CHECK
1234     .sp
1235     When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
1236     string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1237 ph10 209 Note that the check is for a syntactically valid UTF-8 byte string, as defined
1238     by RFC 2279. It is \fInot\fP a check for a UTF-8 string of assigned or
1239     allowable Unicode code points. The value of \fIstartoffset\fP is also checked
1240     to ensure that it points to the start of a UTF-8 character. If an invalid UTF-8
1241     sequence of bytes is found, \fBpcre_exec()\fP returns the error
1242     PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1243     PCRE_ERROR_BADUTF8_OFFSET is returned.
1244 nigel 75 .P
1245     If you already know that your subject is valid, and you want to skip these
1246     checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
1247     calling \fBpcre_exec()\fP. You might want to do this for the second and
1248     subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find
1249     all the matches in a single subject string. However, you should be sure that
1250     the value of \fIstartoffset\fP points to the start of a UTF-8 character. When
1251     PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a
1252     subject, or a value of \fIstartoffset\fP that does not point to the start of a
1253     UTF-8 character, is undefined. Your program may crash.
1254     .sp
1255     PCRE_PARTIAL
1256     .sp
1257     This option turns on the partial matching feature. If the subject string fails
1258     to match the pattern, but at some point during the matching process the end of
1259     the subject was reached (that is, the subject partially matches the pattern and
1260     the failure to match occurred only because there were not enough subject
1261     characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of
1262     PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what
1263     may appear in the pattern. These are discussed in the
1264     .\" HREF
1265     \fBpcrepartial\fP
1266     .\"
1267     documentation.
1268     .
1269     .SS "The string to be matched by \fBpcre_exec()\fP"
1270     .rs
1271     .sp
1272     The subject string is passed to \fBpcre_exec()\fP as a pointer in
1273     \fIsubject\fP, a length in \fIlength\fP, and a starting byte offset in
1274     \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a
1275     UTF-8 character. Unlike the pattern string, the subject may contain binary zero
1276     bytes. When the starting offset is zero, the search for a match starts at the
1277     beginning of the subject, and this is by far the most common case.
1278     .P
1279 nigel 63 A non-zero starting offset is useful when searching for another match in the
1280 nigel 75 same subject by calling \fBpcre_exec()\fP again after a previous success.
1281     Setting \fIstartoffset\fP differs from just passing over a shortened string and
1282 nigel 63 setting PCRE_NOTBOL in the case of a pattern that begins with any kind of
1283     lookbehind. For example, consider the pattern
1284 nigel 75 .sp
1285     \eBiss\eB
1286     .sp
1287     which finds occurrences of "iss" in the middle of words. (\eB matches only if
1288 nigel 63 the current position in the subject is not a word boundary.) When applied to
1289 nigel 75 the string "Mississipi" the first call to \fBpcre_exec()\fP finds the first
1290     occurrence. If \fBpcre_exec()\fP is called again with just the remainder of the
1291     subject, namely "issipi", it does not match, because \eB is always false at the
1292 nigel 63 start of the subject, which is deemed to be a word boundary. However, if
1293 nigel 75 \fBpcre_exec()\fP is passed the entire string again, but with \fIstartoffset\fP
1294 nigel 63 set to 4, it finds the second occurrence of "iss" because it is able to look
1295     behind the starting point to discover that it is preceded by a letter.
1296 nigel 75 .P
1297 nigel 63 If a non-zero starting offset is passed when the pattern is anchored, one
1298 nigel 75 attempt to match at the given offset is made. This can only succeed if the
1299 nigel 63 pattern does not require the match to be at the start of the subject.
1300 nigel 75 .
1301     .SS "How \fBpcre_exec()\fP returns captured substrings"
1302     .rs
1303     .sp
1304 nigel 63 In general, a pattern matches a certain portion of the subject, and in
1305     addition, further substrings from the subject may be picked out by parts of the
1306     pattern. Following the usage in Jeffrey Friedl's book, this is called
1307     "capturing" in what follows, and the phrase "capturing subpattern" is used for
1308     a fragment of a pattern that picks out a substring. PCRE supports several other
1309     kinds of parenthesized subpattern that do not cause substrings to be captured.
1310 nigel 75 .P
1311 nigel 63 Captured substrings are returned to the caller via a vector of integer offsets
1312 nigel 75 whose address is passed in \fIovector\fP. The number of elements in the vector
1313     is passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP:
1314     this argument is NOT the size of \fIovector\fP in bytes.
1315     .P
1316     The first two-thirds of the vector is used to pass back captured substrings,
1317     each substring using a pair of integers. The remaining third of the vector is
1318     used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1319     and is not available for passing back information. The length passed in
1320     \fIovecsize\fP should always be a multiple of three. If it is not, it is
1321     rounded down.
1322     .P
1323     When a match is successful, information about captured substrings is returned
1324     in pairs of integers, starting at the beginning of \fIovector\fP, and
1325 nigel 63 continuing up to two-thirds of its length at the most. The first element of a
1326     pair is set to the offset of the first character in a substring, and the second
1327     is set to the offset of the first character after the end of a substring. The
1328 nigel 75 first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the
1329 nigel 63 subject string matched by the entire pattern. The next pair is used for the
1330 nigel 75 first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP
1331 nigel 91 is one more than the highest numbered pair that has been set. For example, if
1332     two substrings have been captured, the returned value is 3. If there are no
1333     capturing subpatterns, the return value from a successful match is 1,
1334     indicating that just the first pair of offsets has been set.
1335 nigel 75 .P
1336 nigel 63 If a capturing subpattern is matched repeatedly, it is the last portion of the
1337 nigel 75 string that it matched that is returned.
1338     .P
1339     If the vector is too small to hold all the captured substring offsets, it is
1340     used as far as possible (up to two-thirds of its length), and the function
1341     returns a value of zero. In particular, if the substring offsets are not of
1342     interest, \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and
1343     \fIovecsize\fP as zero. However, if the pattern contains back references and
1344     the \fIovector\fP is not big enough to remember the related substrings, PCRE
1345     has to get additional memory for use during matching. Thus it is usually
1346     advisable to supply an \fIovector\fP.
1347     .P
1348 nigel 91 The \fBpcre_info()\fP function can be used to find out how many capturing
1349 nigel 63 subpatterns there are in a compiled pattern. The smallest size for
1350 nigel 75 \fIovector\fP that will allow for \fIn\fP captured substrings, in addition to
1351     the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3.
1352 nigel 91 .P
1353     It is possible for capturing subpattern number \fIn+1\fP to match some part of
1354     the subject when subpattern \fIn\fP has not been used at all. For example, if
1355     the string "abc" is matched against the pattern (a|(z))(bc) the return from the
1356     function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
1357     happens, both values in the offset pairs corresponding to unused subpatterns
1358     are set to -1.
1359     .P
1360     Offset values that correspond to unused subpatterns at the end of the
1361     expression are also set to -1. For example, if the string "abc" is matched
1362     against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1363     return from the function is 2, because the highest used capturing subpattern
1364     number is 1. However, you can refer to the offsets for the second and third
1365     capturing subpatterns if you wish (assuming the vector is large enough, of
1366     course).
1367     .P
1368     Some convenience functions are provided for extracting the captured substrings
1369     as separate strings. These are described below.
1370 nigel 75 .
1371 nigel 77 .\" HTML <a name="errorlist"></a>
1372 nigel 91 .SS "Error return values from \fBpcre_exec()\fP"
1373 nigel 75 .rs
1374     .sp
1375     If \fBpcre_exec()\fP fails, it returns a negative number. The following are
1376 nigel 63 defined in the header file:
1377 nigel 75 .sp
1378 nigel 63 PCRE_ERROR_NOMATCH (-1)
1379 nigel 75 .sp
1380 nigel 63 The subject string did not match the pattern.
1381 nigel 75 .sp
1382 nigel 63 PCRE_ERROR_NULL (-2)
1383 nigel 75 .sp
1384     Either \fIcode\fP or \fIsubject\fP was passed as NULL, or \fIovector\fP was
1385     NULL and \fIovecsize\fP was not zero.
1386     .sp
1387 nigel 63 PCRE_ERROR_BADOPTION (-3)
1388 nigel 75 .sp
1389     An unrecognized bit was set in the \fIoptions\fP argument.
1390     .sp
1391 nigel 63 PCRE_ERROR_BADMAGIC (-4)
1392 nigel 75 .sp
1393 nigel 63 PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch
1394 nigel 75 the case when it is passed a junk pointer and to detect when a pattern that was
1395     compiled in an environment of one endianness is run in an environment with the
1396     other endianness. This is the error that PCRE gives when the magic number is
1397     not present.
1398     .sp
1399 nigel 93 PCRE_ERROR_UNKNOWN_OPCODE (-5)
1400 nigel 75 .sp
1401 nigel 63 While running the pattern match, an unknown item was encountered in the
1402     compiled pattern. This error could be caused by a bug in PCRE or by overwriting
1403     of the compiled pattern.
1404 nigel 75 .sp
1405 nigel 63 PCRE_ERROR_NOMEMORY (-6)
1406 nigel 75 .sp
1407     If a pattern contains back references, but the \fIovector\fP that is passed to
1408     \fBpcre_exec()\fP is not big enough to remember the referenced substrings, PCRE
1409 nigel 63 gets a block of memory at the start of matching to use for this purpose. If the
1410 nigel 75 call via \fBpcre_malloc()\fP fails, this error is given. The memory is
1411     automatically freed at the end of matching.
1412     .sp
1413 nigel 63 PCRE_ERROR_NOSUBSTRING (-7)
1414 nigel 75 .sp
1415     This error is used by the \fBpcre_copy_substring()\fP,
1416     \fBpcre_get_substring()\fP, and \fBpcre_get_substring_list()\fP functions (see
1417     below). It is never returned by \fBpcre_exec()\fP.
1418     .sp
1419 nigel 63 PCRE_ERROR_MATCHLIMIT (-8)
1420 nigel 75 .sp
1421 nigel 87 The backtracking limit, as specified by the \fImatch_limit\fP field in a
1422     \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1423     above.
1424     .sp
1425 nigel 63 PCRE_ERROR_CALLOUT (-9)
1426 nigel 75 .sp
1427     This error is never generated by \fBpcre_exec()\fP itself. It is provided for
1428 nigel 63 use by callout functions that want to yield a distinctive error code. See the
1429 nigel 75 .\" HREF
1430     \fBpcrecallout\fP
1431     .\"
1432     documentation for details.
1433     .sp
1434 nigel 73 PCRE_ERROR_BADUTF8 (-10)
1435 nigel 75 .sp
1436 nigel 71 A string that contains an invalid UTF-8 byte sequence was passed as a subject.
1437 nigel 75 .sp
1438 nigel 73 PCRE_ERROR_BADUTF8_OFFSET (-11)
1439 nigel 75 .sp
1440 nigel 73 The UTF-8 byte sequence that was passed as a subject was valid, but the value
1441 nigel 75 of \fIstartoffset\fP did not point to the beginning of a UTF-8 character.
1442     .sp
1443 nigel 77 PCRE_ERROR_PARTIAL (-12)
1444 nigel 75 .sp
1445     The subject string did not match, but it did match partially. See the
1446     .\" HREF
1447     \fBpcrepartial\fP
1448     .\"
1449     documentation for details of partial matching.
1450     .sp
1451 nigel 77 PCRE_ERROR_BADPARTIAL (-13)
1452 nigel 75 .sp
1453     The PCRE_PARTIAL option was used with a compiled pattern containing items that
1454     are not supported for partial matching. See the
1455     .\" HREF
1456     \fBpcrepartial\fP
1457     .\"
1458     documentation for details of partial matching.
1459     .sp
1460 nigel 77 PCRE_ERROR_INTERNAL (-14)
1461 nigel 75 .sp
1462     An unexpected internal error has occurred. This error could be caused by a bug
1463     in PCRE or by overwriting of the compiled pattern.
1464     .sp
1465 nigel 77 PCRE_ERROR_BADCOUNT (-15)
1466 nigel 75 .sp
1467     This error is given if the value of the \fIovecsize\fP argument is negative.
1468 nigel 93 .sp
1469     PCRE_ERROR_RECURSIONLIMIT (-21)
1470     .sp
1471     The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1472     field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1473     description above.
1474     .sp
1475     PCRE_ERROR_BADNEWLINE (-23)
1476     .sp
1477     An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1478     .P
1479 ph10 197 Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1480 nigel 75 .
1481     .
1482     .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
1483 nigel 63 .rs
1484     .sp
1485 nigel 75 .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1486 nigel 63 .ti +5n
1487 nigel 75 .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
1488 nigel 63 .ti +5n
1489 nigel 75 .B int \fIbuffersize\fP);
1490 nigel 63 .PP
1491 nigel 75 .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1492 nigel 63 .ti +5n
1493 nigel 75 .B int \fIstringcount\fP, int \fIstringnumber\fP,
1494 nigel 63 .ti +5n
1495 nigel 75 .B const char **\fIstringptr\fP);
1496 nigel 63 .PP
1497 nigel 75 .B int pcre_get_substring_list(const char *\fIsubject\fP,
1498 nigel 63 .ti +5n
1499 nigel 75 .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
1500 nigel 63 .PP
1501     Captured substrings can be accessed directly by using the offsets returned by
1502 nigel 75 \fBpcre_exec()\fP in \fIovector\fP. For convenience, the functions
1503     \fBpcre_copy_substring()\fP, \fBpcre_get_substring()\fP, and
1504     \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
1505 nigel 63 as new, separate, zero-terminated strings. These functions identify substrings
1506     by number. The next section describes functions for extracting named
1507 nigel 91 substrings.
1508 nigel 75 .P
1509 nigel 91 A substring that contains a binary zero is correctly extracted and has a
1510     further zero added on the end, but the result is not, of course, a C string.
1511     However, you can process such a string by referring to the length that is
1512     returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
1513     Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
1514     for handling strings containing binary zeros, because the end of the final
1515     string is not independently indicated.
1516     .P
1517 nigel 63 The first three arguments are the same for all three of these functions:
1518 nigel 75 \fIsubject\fP is the subject string that has just been successfully matched,
1519     \fIovector\fP is a pointer to the vector of integer offsets that was passed to
1520     \fBpcre_exec()\fP, and \fIstringcount\fP is the number of substrings that were
1521 nigel 63 captured by the match, including the substring that matched the entire regular
1522 nigel 75 expression. This is the value returned by \fBpcre_exec()\fP if it is greater
1523     than zero. If \fBpcre_exec()\fP returned zero, indicating that it ran out of
1524     space in \fIovector\fP, the value passed as \fIstringcount\fP should be the
1525     number of elements in the vector divided by three.
1526     .P
1527     The functions \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP
1528     extract a single substring, whose number is given as \fIstringnumber\fP. A
1529     value of zero extracts the substring that matched the entire pattern, whereas
1530     higher values extract the captured substrings. For \fBpcre_copy_substring()\fP,
1531     the string is placed in \fIbuffer\fP, whose length is given by
1532     \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is
1533     obtained via \fBpcre_malloc\fP, and its address is returned via
1534     \fIstringptr\fP. The yield of the function is the length of the string, not
1535 nigel 93 including the terminating zero, or one of these error codes:
1536 nigel 75 .sp
1537 nigel 63 PCRE_ERROR_NOMEMORY (-6)
1538 nigel 75 .sp
1539     The buffer was too small for \fBpcre_copy_substring()\fP, or the attempt to get
1540     memory failed for \fBpcre_get_substring()\fP.
1541     .sp
1542 nigel 63 PCRE_ERROR_NOSUBSTRING (-7)
1543 nigel 75 .sp
1544     There is no substring whose number is \fIstringnumber\fP.
1545     .P
1546     The \fBpcre_get_substring_list()\fP function extracts all available substrings
1547 nigel 63 and builds a list of pointers to them. All this is done in a single block of
1548 nigel 75 memory that is obtained via \fBpcre_malloc\fP. The address of the memory block
1549     is returned via \fIlistptr\fP, which is also the start of the list of string
1550 nigel 63 pointers. The end of the list is marked by a NULL pointer. The yield of the
1551 nigel 93 function is zero if all went well, or the error code
1552 nigel 75 .sp
1553 nigel 63 PCRE_ERROR_NOMEMORY (-6)
1554 nigel 75 .sp
1555 nigel 63 if the attempt to get the memory block failed.
1556 nigel 75 .P
1557 nigel 63 When any of these functions encounter a substring that is unset, which can
1558 nigel 75 happen when capturing subpattern number \fIn+1\fP matches some part of the
1559     subject, but subpattern \fIn\fP has not been used at all, they return an empty
1560 nigel 63 string. This can be distinguished from a genuine zero-length substring by
1561 nigel 75 inspecting the appropriate offset in \fIovector\fP, which is negative for unset
1562 nigel 63 substrings.
1563 nigel 75 .P
1564     The two convenience functions \fBpcre_free_substring()\fP and
1565     \fBpcre_free_substring_list()\fP can be used to free the memory returned by
1566     a previous call of \fBpcre_get_substring()\fP or
1567     \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
1568     the function pointed to by \fBpcre_free\fP, which of course could be called
1569 nigel 63 directly from a C program. However, PCRE is used in some situations where it is
1570 nigel 91 linked via a special interface to another programming language that cannot use
1571 nigel 75 \fBpcre_free\fP directly; it is for these cases that the functions are
1572 nigel 63 provided.
1573 nigel 75 .
1574     .
1575     .SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME"
1576 nigel 63 .rs
1577     .sp
1578 nigel 75 .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
1579 nigel 63 .ti +5n
1580 nigel 75 .B const char *\fIname\fP);
1581 nigel 63 .PP
1582 nigel 75 .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1583 nigel 63 .ti +5n
1584 nigel 75 .B const char *\fIsubject\fP, int *\fIovector\fP,
1585     .ti +5n
1586     .B int \fIstringcount\fP, const char *\fIstringname\fP,
1587     .ti +5n
1588     .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1589 nigel 63 .PP
1590 nigel 75 .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1591 nigel 63 .ti +5n
1592 nigel 75 .B const char *\fIsubject\fP, int *\fIovector\fP,
1593 nigel 63 .ti +5n
1594 nigel 75 .B int \fIstringcount\fP, const char *\fIstringname\fP,
1595 nigel 63 .ti +5n
1596 nigel 75 .B const char **\fIstringptr\fP);
1597 nigel 63 .PP
1598 nigel 75 To extract a substring by name, you first have to find associated number.
1599     For example, for this pattern
1600     .sp
1601 nigel 93 (a+)b(?<xxx>\ed+)...
1602 nigel 75 .sp
1603 nigel 91 the number of the subpattern called "xxx" is 2. If the name is known to be
1604     unique (PCRE_DUPNAMES was not set), you can find the number from the name by
1605     calling \fBpcre_get_stringnumber()\fP. The first argument is the compiled
1606     pattern, and the second is the name. The yield of the function is the
1607 nigel 75 subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of
1608     that name.
1609     .P
1610     Given the number, you can extract the substring directly, or use one of the
1611     functions described in the previous section. For convenience, there are also
1612     two functions that do the whole job.
1613     .P
1614 nigel 91 Most of the arguments of \fBpcre_copy_named_substring()\fP and
1615     \fBpcre_get_named_substring()\fP are the same as those for the similarly named
1616 nigel 75 functions that extract by number. As these are described in the previous
1617     section, they are not re-described here. There are just two differences:
1618     .P
1619 nigel 63 First, instead of a substring number, a substring name is given. Second, there
1620     is an extra argument, given at the start, which is a pointer to the compiled
1621     pattern. This is needed in order to gain access to the name-to-number
1622     translation table.
1623 nigel 75 .P
1624     These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1625 ph10 127 then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1626     appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1627 ph10 128 the behaviour may not be what you want (see the next section).
1628 nigel 77 .
1629     .
1630 nigel 91 .SH "DUPLICATE SUBPATTERN NAMES"
1631     .rs
1632     .sp
1633     .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
1634     .ti +5n
1635     .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
1636     .PP
1637     When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
1638     are not required to be unique. Normally, patterns with duplicate names are such
1639     that in any one match, only one of the named subpatterns participates. An
1640     example is shown in the
1641     .\" HREF
1642     \fBpcrepattern\fP
1643     .\"
1644 ph10 208 documentation.
1645 ph10 203 .P
1646     When duplicates are present, \fBpcre_copy_named_substring()\fP and
1647     \fBpcre_get_named_substring()\fP return the first substring corresponding to
1648     the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
1649     returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1650     returns one of the numbers that are associated with the name, but it is not
1651     defined which it is.
1652     .P
1653 nigel 91 If you want to get full details of all captured substrings for a given name,
1654     you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1655     argument is the compiled pattern, and the second is the name. The third and
1656     fourth are pointers to variables which are updated by the function. After it
1657     has run, they point to the first and last entries in the name-to-number table
1658     for the given name. The function itself returns the length of each entry, or
1659 nigel 93 PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1660     described above in the section entitled \fIInformation about a pattern\fP.
1661     Given all the relevant entries for the name, you can extract each of their
1662     numbers, and hence the captured data, if any.
1663 nigel 91 .
1664     .
1665 nigel 77 .SH "FINDING ALL POSSIBLE MATCHES"
1666     .rs
1667     .sp
1668     The traditional matching function uses a similar algorithm to Perl, which stops
1669     when it finds the first match, starting at a given point in the subject. If you
1670     want to find all possible matches, or the longest possible match, consider
1671     using the alternative matching function (see below) instead. If you cannot use
1672     the alternative function, but still need to find all possible matches, you
1673     can kludge it up by making use of the callout facility, which is described in
1674     the
1675     .\" HREF
1676     \fBpcrecallout\fP
1677     .\"
1678     documentation.
1679 nigel 75 .P
1680 nigel 77 What you have to do is to insert a callout right at the end of the pattern.
1681     When your callout function is called, extract and save the current matched
1682     substring. Then return 1, which forces \fBpcre_exec()\fP to backtrack and try
1683     other alternatives. Ultimately, when it runs out of matches, \fBpcre_exec()\fP
1684     will yield PCRE_ERROR_NOMATCH.
1685     .
1686     .
1687     .\" HTML <a name="dfamatch"></a>
1688     .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
1689     .rs
1690     .sp
1691     .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
1692     .ti +5n
1693     .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
1694     .ti +5n
1695     .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
1696     .ti +5n
1697     .B int *\fIworkspace\fP, int \fIwscount\fP);
1698     .P
1699     The function \fBpcre_dfa_exec()\fP is called to match a subject string against
1700 nigel 93 a compiled pattern, using a matching algorithm that scans the subject string
1701     just once, and does not backtrack. This has different characteristics to the
1702     normal algorithm, and is not compatible with Perl. Some of the features of PCRE
1703     patterns are not supported. Nevertheless, there are times when this kind of
1704     matching can be useful. For a discussion of the two matching algorithms, see
1705     the
1706 nigel 77 .\" HREF
1707     \fBpcrematching\fP
1708     .\"
1709     documentation.
1710     .P
1711     The arguments for the \fBpcre_dfa_exec()\fP function are the same as for
1712     \fBpcre_exec()\fP, plus two extras. The \fIovector\fP argument is used in a
1713     different way, and this is described below. The other common arguments are used
1714     in the same way as for \fBpcre_exec()\fP, so their description is not repeated
1715     here.
1716     .P
1717     The two additional arguments provide workspace for the function. The workspace
1718     vector should contain at least 20 elements. It is used for keeping track of
1719     multiple paths through the pattern tree. More workspace will be needed for
1720 nigel 91 patterns and subjects where there are a lot of potential matches.
1721 nigel 77 .P
1722 nigel 87 Here is an example of a simple call to \fBpcre_dfa_exec()\fP:
1723 nigel 77 .sp
1724     int rc;
1725     int ovector[10];
1726     int wspace[20];
1727 nigel 87 rc = pcre_dfa_exec(
1728 nigel 77 re, /* result of pcre_compile() */
1729     NULL, /* we didn't study the pattern */
1730     "some string", /* the subject string */
1731     11, /* the length of the subject string */
1732     0, /* start at offset 0 in the subject */
1733     0, /* default options */
1734     ovector, /* vector of integers for substring information */
1735     10, /* number of elements (NOT size in bytes) */
1736     wspace, /* working space vector */
1737     20); /* number of elements (NOT size in bytes) */
1738     .
1739     .SS "Option bits for \fBpcre_dfa_exec()\fP"
1740     .rs
1741     .sp
1742     The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be
1743 nigel 91 zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1744     PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,
1745 nigel 77 PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are
1746     the same as for \fBpcre_exec()\fP, so their description is not repeated here.
1747     .sp
1748     PCRE_PARTIAL
1749     .sp
1750     This has the same general effect as it does for \fBpcre_exec()\fP, but the
1751     details are slightly different. When PCRE_PARTIAL is set for
1752     \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into
1753     PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no
1754     complete matches, but there is still at least one matching possibility. The
1755     portion of the string that provided the partial match is set as the first
1756     matching string.
1757     .sp
1758     PCRE_DFA_SHORTEST
1759     .sp
1760     Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
1761 nigel 93 soon as it has found one match. Because of the way the alternative algorithm
1762     works, this is necessarily the shortest possible match at the first possible
1763     matching point in the subject string.
1764 nigel 77 .sp
1765     PCRE_DFA_RESTART
1766     .sp
1767     When \fBpcre_dfa_exec()\fP is called with the PCRE_PARTIAL option, and returns
1768     a partial match, it is possible to call it again, with additional subject
1769     characters, and have it continue with the same match. The PCRE_DFA_RESTART
1770     option requests this action; when it is set, the \fIworkspace\fP and
1771     \fIwscount\fP options must reference the same vector as before because data
1772     about the match so far is left in them after a partial match. There is more
1773     discussion of this facility in the
1774     .\" HREF
1775     \fBpcrepartial\fP
1776     .\"
1777     documentation.
1778     .
1779     .SS "Successful returns from \fBpcre_dfa_exec()\fP"
1780     .rs
1781     .sp
1782     When \fBpcre_dfa_exec()\fP succeeds, it may have matched more than one
1783     substring in the subject. Note, however, that all the matches from one run of
1784     the function start at the same point in the subject. The shorter matches are
1785     all initial substrings of the longer matches. For example, if the pattern
1786     .sp
1787     <.*>
1788     .sp
1789     is matched against the string
1790     .sp
1791     This is <something> <something else> <something further> no more
1792     .sp
1793     the three matched strings are
1794     .sp
1795     <something>
1796     <something> <something else>
1797     <something> <something else> <something further>
1798     .sp
1799     On success, the yield of the function is a number greater than zero, which is
1800     the number of matched substrings. The substrings themselves are returned in
1801     \fIovector\fP. Each string uses two elements; the first is the offset to the
1802 nigel 93 start, and the second is the offset to the end. In fact, all the strings have
1803     the same start offset. (Space could have been saved by giving this only once,
1804     but it was decided to retain some compatibility with the way \fBpcre_exec()\fP
1805     returns data, even though the meaning of the strings is different.)
1806 nigel 77 .P
1807     The strings are returned in reverse order of length; that is, the longest
1808     matching string is given first. If there were too many matches to fit into
1809     \fIovector\fP, the yield of the function is zero, and the vector is filled with
1810     the longest matches.
1811     .
1812     .SS "Error returns from \fBpcre_dfa_exec()\fP"
1813     .rs
1814     .sp
1815     The \fBpcre_dfa_exec()\fP function returns a negative number when it fails.
1816     Many of the errors are the same as for \fBpcre_exec()\fP, and these are
1817     described
1818     .\" HTML <a href="#errorlist">
1819     .\" </a>
1820     above.
1821     .\"
1822     There are in addition the following errors that are specific to
1823     \fBpcre_dfa_exec()\fP:
1824     .sp
1825     PCRE_ERROR_DFA_UITEM (-16)
1826     .sp
1827     This return is given if \fBpcre_dfa_exec()\fP encounters an item in the pattern
1828     that it does not support, for instance, the use of \eC or a back reference.
1829     .sp
1830     PCRE_ERROR_DFA_UCOND (-17)
1831     .sp
1832 nigel 93 This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that
1833     uses a back reference for the condition, or a test for recursion in a specific
1834     group. These are not supported.
1835 nigel 77 .sp
1836     PCRE_ERROR_DFA_UMLIMIT (-18)
1837     .sp
1838     This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP
1839     block that contains a setting of the \fImatch_limit\fP field. This is not
1840     supported (it is meaningless).
1841     .sp
1842     PCRE_ERROR_DFA_WSSIZE (-19)
1843     .sp
1844     This return is given if \fBpcre_dfa_exec()\fP runs out of space in the
1845     \fIworkspace\fP vector.
1846     .sp
1847     PCRE_ERROR_DFA_RECURSE (-20)
1848     .sp
1849     When a recursive subpattern is processed, the matching function calls itself
1850     recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1851     error is given if the output vector is not large enough. This should be
1852     extremely rare, as a vector of size 1000 is used.
1853 nigel 93 .
1854     .
1855     .SH "SEE ALSO"
1856     .rs
1857     .sp
1858     \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1859     \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1860     \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1861 ph10 99 .
1862     .
1863     .SH AUTHOR
1864     .rs
1865     .sp
1866     .nf
1867     Philip Hazel
1868     University Computing Service
1869     Cambridge CB2 3QH, England.
1870     .fi
1871     .
1872     .
1873     .SH REVISION
1874     .rs
1875     .sp
1876     .nf
1877 ph10 209 Last updated: 07 August 2007
1878 ph10 99 Copyright (c) 1997-2007 University of Cambridge.
1879     .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