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

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

Parent Directory Parent Directory | Revision Log Revision Log | View Patch Patch

revision 77 by nigel, Sat Feb 24 21:40:45 2007 UTC revision 389 by ph10, Sun Mar 15 18:24:05 2009 UTC
# Line 1  Line 1 
1  .TH PCRE 3  .TH PCREAPI 3
2  .SH NAME  .SH NAME
3  PCRE - Perl-compatible regular expressions  PCRE - Perl-compatible regular expressions
4  .SH "PCRE NATIVE API"  .SH "PCRE NATIVE API"
# Line 7  PCRE - Perl-compatible regular expressio Line 7  PCRE - Perl-compatible regular expressio
7  .B #include <pcre.h>  .B #include <pcre.h>
8  .PP  .PP
9  .SM  .SM
 .br  
10  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
11  .ti +5n  .ti +5n
12  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
13  .ti +5n  .ti +5n
14  .B const unsigned char *\fItableptr\fP);  .B const unsigned char *\fItableptr\fP);
15  .PP  .PP
 .br  
16  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
17  .ti +5n  .ti +5n
18  .B int *\fIerrorcodeptr\fP,  .B int *\fIerrorcodeptr\fP,
# Line 23  PCRE - Perl-compatible regular expressio Line 21  PCRE - Perl-compatible regular expressio
21  .ti +5n  .ti +5n
22  .B const unsigned char *\fItableptr\fP);  .B const unsigned char *\fItableptr\fP);
23  .PP  .PP
 .br  
24  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,
25  .ti +5n  .ti +5n
26  .B const char **\fIerrptr\fP);  .B const char **\fIerrptr\fP);
27  .PP  .PP
 .br  
28  .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
29  .ti +5n  .ti +5n
30  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
31  .ti +5n  .ti +5n
32  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
33  .PP  .PP
 .br  
34  .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
35  .ti +5n  .ti +5n
36  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
# Line 44  PCRE - Perl-compatible regular expressio Line 39  PCRE - Perl-compatible regular expressio
39  .ti +5n  .ti +5n
40  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
41  .PP  .PP
 .br  
42  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
43  .ti +5n  .ti +5n
44  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 53  PCRE - Perl-compatible regular expressio Line 47  PCRE - Perl-compatible regular expressio
47  .ti +5n  .ti +5n
48  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
49  .PP  .PP
 .br  
50  .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
51  .ti +5n  .ti +5n
52  .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
53  .ti +5n  .ti +5n
54  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
55  .PP  .PP
 .br  
56  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
57  .ti +5n  .ti +5n
58  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 69  PCRE - Perl-compatible regular expressio Line 61  PCRE - Perl-compatible regular expressio
61  .ti +5n  .ti +5n
62  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
63  .PP  .PP
 .br  
64  .B int pcre_get_stringnumber(const pcre *\fIcode\fP,  .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
65  .ti +5n  .ti +5n
66  .B const char *\fIname\fP);  .B const char *\fIname\fP);
67  .PP  .PP
68  .br  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
69    .ti +5n
70    .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
71    .PP
72  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
73  .ti +5n  .ti +5n
74  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
75  .ti +5n  .ti +5n
76  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
77  .PP  .PP
 .br  
78  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
79  .ti +5n  .ti +5n
80  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
81  .PP  .PP
 .br  
82  .B void pcre_free_substring(const char *\fIstringptr\fP);  .B void pcre_free_substring(const char *\fIstringptr\fP);
83  .PP  .PP
 .br  
84  .B void pcre_free_substring_list(const char **\fIstringptr\fP);  .B void pcre_free_substring_list(const char **\fIstringptr\fP);
85  .PP  .PP
 .br  
86  .B const unsigned char *pcre_maketables(void);  .B const unsigned char *pcre_maketables(void);
87  .PP  .PP
 .br  
88  .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
89  .ti +5n  .ti +5n
90  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
91  .PP  .PP
 .br  
92  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
93  .B *\fIfirstcharptr\fP);  .B *\fIfirstcharptr\fP);
94  .PP  .PP
 .br  
95  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
96  .PP  .PP
 .br  
97  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
98  .PP  .PP
 .br  
99  .B char *pcre_version(void);  .B char *pcre_version(void);
100  .PP  .PP
 .br  
101  .B void *(*pcre_malloc)(size_t);  .B void *(*pcre_malloc)(size_t);
102  .PP  .PP
 .br  
103  .B void (*pcre_free)(void *);  .B void (*pcre_free)(void *);
104  .PP  .PP
 .br  
105  .B void *(*pcre_stack_malloc)(size_t);  .B void *(*pcre_stack_malloc)(size_t);
106  .PP  .PP
 .br  
107  .B void (*pcre_stack_free)(void *);  .B void (*pcre_stack_free)(void *);
108  .PP  .PP
 .br  
109  .B int (*pcre_callout)(pcre_callout_block *);  .B int (*pcre_callout)(pcre_callout_block *);
110  .  .
111  .  .
112  .SH "PCRE API OVERVIEW"  .SH "PCRE API OVERVIEW"
113  .rs  .rs
114  .sp  .sp
115  PCRE has its own native API, which is described in this document. There is  PCRE has its own native API, which is described in this document. There are
116  also a set of wrapper functions that correspond to the POSIX regular expression  also some wrapper functions that correspond to the POSIX regular expression
117  API. These are described in the  API. These are described in the
118  .\" HREF  .\" HREF
119  \fBpcreposix\fP  \fBpcreposix\fP
# Line 160  distribution. The Line 140  distribution. The
140  .\" HREF  .\" HREF
141  \fBpcresample\fP  \fBpcresample\fP
142  .\"  .\"
143  documentation describes how to run it.  documentation describes how to compile and run it.
144  .P  .P
145  A second matching function, \fBpcre_dfa_exec()\fP, which is not  A second matching function, \fBpcre_dfa_exec()\fP, which is not
146  Perl-compatible, is also provided. This uses a different algorithm for the  Perl-compatible, is also provided. This uses a different algorithm for the
147  matching. This allows it to find all possible matches (at a given point in the  matching. The alternative algorithm finds all possible matches (at a given
148  subject), not just one. However, this algorithm does not return captured  point in the subject), and scans the subject just once. However, this algorithm
149  substrings. A description of the two matching algorithms and their advantages  does not return captured substrings. A description of the two matching
150  and disadvantages is given in the  algorithms and their advantages and disadvantages is given in the
151  .\" HREF  .\" HREF
152  \fBpcrematching\fP  \fBpcrematching\fP
153  .\"  .\"
# Line 183  matched by \fBpcre_exec()\fP. They are: Line 163  matched by \fBpcre_exec()\fP. They are:
163    \fBpcre_get_named_substring()\fP    \fBpcre_get_named_substring()\fP
164    \fBpcre_get_substring_list()\fP    \fBpcre_get_substring_list()\fP
165    \fBpcre_get_stringnumber()\fP    \fBpcre_get_stringnumber()\fP
166      \fBpcre_get_stringtable_entries()\fP
167  .sp  .sp
168  \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also  \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also
169  provided, to free the memory used for extracted strings.  provided, to free the memory used for extracted strings.
# Line 212  should be done before calling any PCRE f Line 193  should be done before calling any PCRE f
193  The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also  The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also
194  indirections to memory management functions. These special functions are used  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  only when PCRE is compiled to use the heap for remembering data, instead of
196  recursive function calls, when running the \fBpcre_exec()\fP function. This is  recursive function calls, when running the \fBpcre_exec()\fP function. See the
197  a non-standard way of building PCRE, for use in environments that have limited  .\" HREF
198  stacks. Because of the greater use of memory management, it runs more slowly.  \fBpcrebuild\fP
199  Separate functions are provided so that special-purpose external code can be  .\"
200  used for this case. When used, these functions are always called in a  documentation for details of how to do this. It is a non-standard way of
201  stack-like manner (last obtained, first freed), and always for memory blocks of  building PCRE, for use in environments that have limited stacks. Because of the
202  the same size.  greater use of memory management, it runs more slowly. Separate functions are
203    provided so that special-purpose external code can be used for this case. When
204    used, these functions are always called in a stack-like manner (last obtained,
205    first freed), and always for memory blocks of the same size. There is a
206    discussion about PCRE's stack usage in the
207    .\" HREF
208    \fBpcrestack\fP
209    .\"
210    documentation.
211  .P  .P
212  The global variable \fBpcre_callout\fP initially contains NULL. It can be set  The global variable \fBpcre_callout\fP initially contains NULL. It can be set
213  by the caller to a "callout" function, which PCRE will then call at specified  by the caller to a "callout" function, which PCRE will then call at specified
# Line 229  points during a matching operation. Deta Line 218  points during a matching operation. Deta
218  documentation.  documentation.
219  .  .
220  .  .
221    .\" HTML <a name="newlines"></a>
222    .SH NEWLINES
223    .rs
224    .sp
225    PCRE supports five different conventions for indicating line breaks in
226    strings: a single CR (carriage return) character, a single LF (linefeed)
227    character, the two-character sequence CRLF, any of the three preceding, or any
228    Unicode newline sequence. The Unicode newline sequences are the three just
229    mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
230    U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
231    (paragraph separator, U+2029).
232    .P
233    Each of the first three conventions is used by at least one operating system as
234    its standard newline sequence. When PCRE is built, a default can be specified.
235    The default default is LF, which is the Unix standard. When PCRE is run, the
236    default can be overridden, either when a pattern is compiled, or when it is
237    matched.
238    .P
239    At compile time, the newline convention can be specified by the \fIoptions\fP
240    argument of \fBpcre_compile()\fP, or it can be specified by special text at the
241    start of the pattern itself; this overrides any other settings. See the
242    .\" HREF
243    \fBpcrepattern\fP
244    .\"
245    page for details of the special character sequences.
246    .P
247    In the PCRE documentation the word "newline" is used to mean "the character or
248    pair of characters that indicate a line break". The choice of newline
249    convention affects the handling of the dot, circumflex, and dollar
250    metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
251    recognized line ending sequence, the match position advancement for a
252    non-anchored pattern. There is more detail about this in the
253    .\" HTML <a href="#execoptions">
254    .\" </a>
255    section on \fBpcre_exec()\fP options
256    .\"
257    below.
258    .P
259    The choice of newline convention does not affect the interpretation of
260    the \en or \er escape sequences, nor does it affect what \eR matches, which is
261    controlled in a similar way, but by separate options.
262    .
263    .
264  .SH MULTITHREADING  .SH MULTITHREADING
265  .rs  .rs
266  .sp  .sp
# Line 250  which it was compiled. Details are given Line 282  which it was compiled. Details are given
282  .\" HREF  .\" HREF
283  \fBpcreprecompile\fP  \fBpcreprecompile\fP
284  .\"  .\"
285  documentation.  documentation. However, compiling a regular expression with one version of PCRE
286    for use with a different version is not guaranteed to work and may cause
287    crashes.
288  .  .
289  .  .
290  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 281  properties is available; otherwise it is Line 315  properties is available; otherwise it is
315  .sp  .sp
316    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
317  .sp  .sp
318  The output is an integer that is set to the value of the code that is used for  The output is an integer whose value specifies the default character sequence
319  the newline character. It is either linefeed (10) or carriage return (13), and  that is recognized as meaning "newline". The four values that are supported
320  should normally be the standard character for your operating system.  are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. The
321    default should normally be the standard sequence for your operating system.
322    .sp
323      PCRE_CONFIG_BSR
324    .sp
325    The output is an integer whose value indicates what character sequences the \eR
326    escape sequence matches by default. A value of 0 means that \eR matches any
327    Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
328    or CRLF. The default can be overridden when a pattern is compiled or matched.
329  .sp  .sp
330    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
331  .sp  .sp
# Line 305  documentation. Line 347  documentation.
347  .sp  .sp
348    PCRE_CONFIG_MATCH_LIMIT    PCRE_CONFIG_MATCH_LIMIT
349  .sp  .sp
350  The output is an integer that gives the default limit for the number of  The output is a long integer that gives the default limit for the number of
351  internal matching function calls in a \fBpcre_exec()\fP execution. Further  internal matching function calls in a \fBpcre_exec()\fP execution. Further
352  details are given with \fBpcre_exec()\fP below.  details are given with \fBpcre_exec()\fP below.
353  .sp  .sp
354      PCRE_CONFIG_MATCH_LIMIT_RECURSION
355    .sp
356    The output is a long integer that gives the default limit for the depth of
357    recursion when calling the internal matching function in a \fBpcre_exec()\fP
358    execution. Further details are given with \fBpcre_exec()\fP below.
359    .sp
360    PCRE_CONFIG_STACKRECURSE    PCRE_CONFIG_STACKRECURSE
361  .sp  .sp
362  The output is an integer that is set to one if internal recursion when running  The output is an integer that is set to one if internal recursion when running
# Line 347  The pattern is a C string terminated by Line 395  The pattern is a C string terminated by
395  via \fBpcre_malloc\fP is returned. This contains the compiled code and related  via \fBpcre_malloc\fP is returned. This contains the compiled code and related
396  data. The \fBpcre\fP type is defined for the returned block; this is a typedef  data. The \fBpcre\fP type is defined for the returned block; this is a typedef
397  for a structure whose contents are not externally defined. It is up to the  for a structure whose contents are not externally defined. It is up to the
398  caller to free the memory when it is no longer required.  caller to free the memory (via \fBpcre_free\fP) when it is no longer required.
399  .P  .P
400  Although the compiled code of a PCRE regex is relocatable, that is, it does not  Although the compiled code of a PCRE regex is relocatable, that is, it does not
401  depend on memory location, the complete \fBpcre\fP data block is not  depend on memory location, the complete \fBpcre\fP data block is not
402  fully relocatable, because it may contain a copy of the \fItableptr\fP  fully relocatable, because it may contain a copy of the \fItableptr\fP
403  argument, which is an address (see below).  argument, which is an address (see below).
404  .P  .P
405  The \fIoptions\fP argument contains independent bits that affect the  The \fIoptions\fP argument contains various bit settings that affect the
406  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
407  options are described below. Some of them, in particular, those that are  options are described below. Some of them, in particular, those that are
408  compatible with Perl, can also be set and unset from within the pattern (see  compatible with Perl, can also be set and unset from within the pattern (see
# Line 364  the detailed description in the Line 412  the detailed description in the
412  .\"  .\"
413  documentation). For these options, the contents of the \fIoptions\fP argument  documentation). For these options, the contents of the \fIoptions\fP argument
414  specifies their initial settings at the start of compilation and execution. The  specifies their initial settings at the start of compilation and execution. The
415  PCRE_ANCHORED option can be set at the time of matching as well as at compile  PCRE_ANCHORED and PCRE_NEWLINE_\fIxxx\fP options can be set at the time of
416  time.  matching as well as at compile time.
417  .P  .P
418  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
419  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
420  NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual  NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual
421  error message. The offset from the start of the pattern to the character where  error message. This is a static string that is part of the library. You must
422  the error was discovered is placed in the variable pointed to by  not try to free it. The offset from the start of the pattern to the character
423    where the error was discovered is placed in the variable pointed to by
424  \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.  \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.
425  .P  .P
426  If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the  If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the
# Line 419  facility, see the Line 468  facility, see the
468  .\"  .\"
469  documentation.  documentation.
470  .sp  .sp
471      PCRE_BSR_ANYCRLF
472      PCRE_BSR_UNICODE
473    .sp
474    These options (which are mutually exclusive) control what the \eR escape
475    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
476    match any Unicode newline sequence. The default is specified when PCRE is
477    built. It can be overridden from within the pattern, or by setting an option
478    when a compiled pattern is matched.
479    .sp
480    PCRE_CASELESS    PCRE_CASELESS
481  .sp  .sp
482  If this bit is set, letters in the pattern match both upper and lower case  If this bit is set, letters in the pattern match both upper and lower case
# Line 435  with UTF-8 support. Line 493  with UTF-8 support.
493  .sp  .sp
494  If this bit is set, a dollar metacharacter in the pattern matches only at the  If this bit is set, a dollar metacharacter in the pattern matches only at the
495  end of the subject string. Without this option, a dollar also matches  end of the subject string. Without this option, a dollar also matches
496  immediately before the final character if it is a newline (but not before any  immediately before a newline at the end of the string (but not before any other
497  other newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is  newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set.
498  set. There is no equivalent to this option in Perl, and no way to set it within  There is no equivalent to this option in Perl, and no way to set it within a
499  a pattern.  pattern.
500  .sp  .sp
501    PCRE_DOTALL    PCRE_DOTALL
502  .sp  .sp
503  If this bit is set, a dot metacharater in the pattern matches all characters,  If this bit is set, a dot metacharater in the pattern matches all characters,
504  including newlines. Without it, newlines are excluded. This option is  including those that indicate newline. Without it, a dot does not match when
505  equivalent to Perl's /s option, and it can be changed within a pattern by a  the current position is at a newline. This option is equivalent to Perl's /s
506  (?s) option setting. A negative class such as [^a] always matches a newline  option, and it can be changed within a pattern by a (?s) option setting. A
507  character, independent of the setting of this option.  negative class such as [^a] always matches newline characters, independent of
508    the setting of this option.
509    .sp
510      PCRE_DUPNAMES
511    .sp
512    If this bit is set, names used to identify capturing subpatterns need not be
513    unique. This can be helpful for certain types of pattern when it is known that
514    only one instance of the named subpattern can ever be matched. There are more
515    details of named subpatterns below; see also the
516    .\" HREF
517    \fBpcrepattern\fP
518    .\"
519    documentation.
520  .sp  .sp
521    PCRE_EXTENDED    PCRE_EXTENDED
522  .sp  .sp
523  If this bit is set, whitespace data characters in the pattern are totally  If this bit is set, whitespace data characters in the pattern are totally
524  ignored except when escaped or inside a character class. Whitespace does not  ignored except when escaped or inside a character class. Whitespace does not
525  include the VT character (code 11). In addition, characters between an  include the VT character (code 11). In addition, characters between an
526  unescaped # outside a character class and the next newline character,  unescaped # outside a character class and the next newline, inclusive, are also
527  inclusive, are also ignored. This is equivalent to Perl's /x option, and it can  ignored. This is equivalent to Perl's /x option, and it can be changed within a
528  be changed within a pattern by a (?x) option setting.  pattern by a (?x) option setting.
529  .P  .P
530  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
531  Note, however, that this applies only to data characters. Whitespace characters  Note, however, that this applies only to data characters. Whitespace characters
# Line 469  that is incompatible with Perl, but it i Line 539  that is incompatible with Perl, but it i
539  set, any backslash in a pattern that is followed by a letter that has no  set, any backslash in a pattern that is followed by a letter that has no
540  special meaning causes an error, thus reserving these combinations for future  special meaning causes an error, thus reserving these combinations for future
541  expansion. By default, as in Perl, a backslash followed by a letter with no  expansion. By default, as in Perl, a backslash followed by a letter with no
542  special meaning is treated as a literal. There are at present no other features  special meaning is treated as a literal. (Perl can, however, be persuaded to
543  controlled by this option. It can also be set by a (?X) option setting within a  give a warning for this.) There are at present no other features controlled by
544  pattern.  this option. It can also be set by a (?X) option setting within a pattern.
545  .sp  .sp
546    PCRE_FIRSTLINE    PCRE_FIRSTLINE
547  .sp  .sp
548  If this option is set, an unanchored pattern is required to match before or at  If this option is set, an unanchored pattern is required to match before or at
549  the first newline character in the subject string, though the matched text may  the first newline in the subject string, though the matched text may continue
550  continue over the newline.  over the newline.
551    .sp
552      PCRE_JAVASCRIPT_COMPAT
553    .sp
554    If this option is set, PCRE's behaviour is changed in some ways so that it is
555    compatible with JavaScript rather than Perl. The changes are as follows:
556    .P
557    (1) A lone closing square bracket in a pattern causes a compile-time error,
558    because this is illegal in JavaScript (by default it is treated as a data
559    character). Thus, the pattern AB]CD becomes illegal when this option is set.
560    .P
561    (2) At run time, a back reference to an unset subpattern group matches an empty
562    string (by default this causes the current matching alternative to fail). A
563    pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
564    an "a" in the subject), whereas it fails by default, for Perl compatibility.
565  .sp  .sp
566    PCRE_MULTILINE    PCRE_MULTILINE
567  .sp  .sp
# Line 489  terminating newline (unless PCRE_DOLLAR_ Line 573  terminating newline (unless PCRE_DOLLAR_
573  Perl.  Perl.
574  .P  .P
575  When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs  When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
576  match immediately following or immediately before any newline in the subject  match immediately following or immediately before internal newlines in the
577  string, respectively, as well as at the very start and end. This is equivalent  subject string, respectively, as well as at the very start and end. This is
578  to Perl's /m option, and it can be changed within a pattern by a (?m) option  equivalent to Perl's /m option, and it can be changed within a pattern by a
579  setting. If there are no "\en" characters in a subject string, or no  (?m) option setting. If there are no newlines in a subject string, or no
580  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
581  .sp  .sp
582      PCRE_NEWLINE_CR
583      PCRE_NEWLINE_LF
584      PCRE_NEWLINE_CRLF
585      PCRE_NEWLINE_ANYCRLF
586      PCRE_NEWLINE_ANY
587    .sp
588    These options override the default newline definition that was chosen when PCRE
589    was built. Setting the first or the second specifies that a newline is
590    indicated by a single character (CR or LF, respectively). Setting
591    PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
592    CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
593    preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
594    that any Unicode newline sequence should be recognized. The Unicode newline
595    sequences are the three just mentioned, plus the single characters VT (vertical
596    tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
597    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
598    recognized only in UTF-8 mode.
599    .P
600    The newline setting in the options word uses three bits that are treated
601    as a number, giving eight possibilities. Currently only six are used (default
602    plus the five values above). This means that if you set more than one newline
603    option, the combination may or may not be sensible. For example,
604    PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
605    other combinations may yield unused numbers and cause an error.
606    .P
607    The only time that a line break is specially recognized when compiling a
608    pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
609    class is encountered. This indicates a comment that lasts until after the next
610    line break sequence. In other circumstances, line break sequences are treated
611    as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
612    as whitespace characters and are therefore ignored.
613    .P
614    The newline option that is set at compile time becomes the default that is used
615    for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
616    .sp
617    PCRE_NO_AUTO_CAPTURE    PCRE_NO_AUTO_CAPTURE
618  .sp  .sp
619  If this option is set, it disables the use of numbered capturing parentheses in  If this option is set, it disables the use of numbered capturing parentheses in
# Line 529  page. Line 648  page.
648    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
649  .sp  .sp
650  When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is  When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
651  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
652  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
653  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
654  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
655  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
656  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
657  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
658  strings.  \fBpcre\fP
659    .\"
660    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
661    returns an error. If you already know that your pattern is valid, and you want
662    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
663    option. When it is set, the effect of passing an invalid UTF-8 string as a
664    pattern is undefined. It may cause your program to crash. Note that this option
665    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
666    the UTF-8 validity checking of subject strings.
667  .  .
668  .  .
669  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 544  strings. Line 671  strings.
671  .sp  .sp
672  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
673  \fBpcre_compile2()\fP, along with the error messages that may be returned by  \fBpcre_compile2()\fP, along with the error messages that may be returned by
674  both compiling functions.  both compiling functions. As PCRE has developed, some error codes have fallen
675    out of use. To avoid confusion, they have not been re-used.
676  .sp  .sp
677     0  no error     0  no error
678     1  \e at end of pattern     1  \e at end of pattern
# Line 556  both compiling functions. Line 684  both compiling functions.
684     7  invalid escape sequence in character class     7  invalid escape sequence in character class
685     8  range out of order in character class     8  range out of order in character class
686     9  nothing to repeat     9  nothing to repeat
687    10  operand of unlimited repeat could match the empty string    10  [this code is not in use]
688    11  internal error: unexpected repeat    11  internal error: unexpected repeat
689    12  unrecognized character after (?    12  unrecognized character after (? or (?-
690    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
691    14  missing )    14  missing )
692    15  reference to non-existent subpattern    15  reference to non-existent subpattern
693    16  erroffset passed as NULL    16  erroffset passed as NULL
694    17  unknown option bit(s) set    17  unknown option bit(s) set
695    18  missing ) after comment    18  missing ) after comment
696    19  parentheses nested too deeply    19  [this code is not in use]
697    20  regular expression too large    20  regular expression is too large
698    21  failed to get memory    21  failed to get memory
699    22  unmatched parentheses    22  unmatched parentheses
700    23  internal error: code overflow    23  internal error: code overflow
701    24  unrecognized character after (?<    24  unrecognized character after (?<
702    25  lookbehind assertion is not fixed length    25  lookbehind assertion is not fixed length
703    26  malformed number after (?(    26  malformed number or name after (?(
704    27  conditional group contains more than two branches    27  conditional group contains more than two branches
705    28  assertion expected after (?(    28  assertion expected after (?(
706    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
707    30  unknown POSIX class name    30  unknown POSIX class name
708    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
709    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
710    33  spare error    33  [this code is not in use]
711    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
712    35  invalid condition (?(0)    35  invalid condition (?(0)
713    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
# Line 588  both compiling functions. Line 716  both compiling functions.
716    39  closing ) for (?C expected    39  closing ) for (?C expected
717    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
718    41  unrecognized character after (?P    41  unrecognized character after (?P
719    42  syntax error after (?P    42  syntax error in subpattern name (missing terminator)
720    43  two named groups have the same name    43  two named subpatterns have the same name
721    44  invalid UTF-8 string    44  invalid UTF-8 string
722    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
723    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
724    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
725      48  subpattern name is too long (maximum 32 characters)
726      49  too many named subpatterns (maximum 10000)
727      50  [this code is not in use]
728      51  octal value is greater than \e377 (not in UTF-8 mode)
729      52  internal error: overran compiling workspace
730      53  internal error: previously-checked referenced subpattern not found
731      54  DEFINE group contains more than one branch
732      55  repeating a DEFINE group is not allowed
733      56  inconsistent NEWLINE options
734      57  \eg is not followed by a braced, angle-bracketed, or quoted
735            name/number or by a plain number
736      58  a numbered reference must not be zero
737      59  (*VERB) with an argument is not supported
738      60  (*VERB) not recognized
739      61  number is too big
740      62  subpattern name expected
741      63  digit expected after (?+
742      64  ] is an invalid data character in JavaScript compatibility mode
743    .sp
744    The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
745    be used if the limits were changed when PCRE was built.
746  .  .
747  .  .
748  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 631  options are defined, and this argument s Line 780  options are defined, and this argument s
780  .P  .P
781  The third argument for \fBpcre_study()\fP is a pointer for an error message. If  The third argument for \fBpcre_study()\fP is a pointer for an error message. If
782  studying succeeds (even if no data is returned), the variable it points to is  studying succeeds (even if no data is returned), the variable it points to is
783  set to NULL. Otherwise it points to a textual error message. You should  set to NULL. Otherwise it is set to point to a textual error message. This is a
784  therefore test the error pointer for NULL after calling \fBpcre_study()\fP, to  static string that is part of the library. You must not try to free it. You
785  be sure that it has run successfully.  should test the error pointer for NULL after calling \fBpcre_study()\fP, to be
786    sure that it has run successfully.
787  .P  .P
788  This is a typical call to \fBpcre_study\fP():  This is a typical call to \fBpcre_study\fP():
789  .sp  .sp
# Line 652  bytes is created. Line 802  bytes is created.
802  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
803  .rs  .rs
804  .sp  .sp
805  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
806  digits, or whatever, by reference to a set of tables, indexed by character  digits, or whatever, by reference to a set of tables, indexed by character
807  value. When running in UTF-8 mode, this applies only to characters with codes  value. When running in UTF-8 mode, this applies only to characters with codes
808  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but
809  can be tested with \ep if PCRE is built with Unicode character property  can be tested with \ep if PCRE is built with Unicode character property
810  support.  support. The use of locales with Unicode is discouraged. If you are handling
811  .P  characters with codes greater than 128, you should either use UTF-8 and
812  An internal set of tables is created in the default C locale when PCRE is  Unicode, or use locales, but not try to mix the two.
813  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
814  and is sufficient for many applications. An alternative set of tables can,  PCRE contains an internal set of tables that are used when the final argument
815  however, be supplied. These may be created in a different locale from the  of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
816  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
817  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
818    default "C" locale of the local system, which may cause them to be different.
819    .P
820    The internal tables can always be overridden by tables supplied by the
821    application that calls PCRE. These may be created in a different locale from
822    the default. As more and more applications change to using Unicode, the need
823    for this locale support is expected to die away.
824  .P  .P
825  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
826  which has no arguments, in the relevant locale. The result can then be passed  which has no arguments, in the relevant locale. The result can then be passed
# Line 677  the following code could be used: Line 833  the following code could be used:
833    tables = pcre_maketables();    tables = pcre_maketables();
834    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
835  .sp  .sp
836    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
837    are using Windows, the name for the French locale is "french".
838    .P
839  When \fBpcre_maketables()\fP runs, the tables are built in memory that is  When \fBpcre_maketables()\fP runs, the tables are built in memory that is
840  obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure  obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure
841  that the memory containing the tables remains available for as long as it is  that the memory containing the tables remains available for as long as it is
# Line 723  check against passing an arbitrary memor Line 882  check against passing an arbitrary memor
882  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
883  .sp  .sp
884    int rc;    int rc;
885    unsigned long int length;    size_t length;
886    rc = pcre_fullinfo(    rc = pcre_fullinfo(
887      re,               /* result of pcre_compile() */      re,               /* result of pcre_compile() */
888      pe,               /* result of pcre_study(), or NULL */      pe,               /* result of pcre_study(), or NULL */
# Line 755  a NULL table pointer. Line 914  a NULL table pointer.
914    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
915  .sp  .sp
916  Return information about the first byte of any matched string, for a  Return information about the first byte of any matched string, for a
917  non-anchored pattern. (This option used to be called PCRE_INFO_FIRSTCHAR; the  non-anchored pattern. The fourth argument should point to an \fBint\fP
918  old name is still recognized for backwards compatibility.)  variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
919    still recognized for backwards compatibility.)
920  .P  .P
921  If there is a fixed first byte, for example, from a pattern such as  If there is a fixed first byte, for example, from a pattern such as
922  (cat|cow|coyote), it is returned in the integer pointed to by \fIwhere\fP.  (cat|cow|coyote), its value is returned. Otherwise, if either
 Otherwise, if either  
923  .sp  .sp
924  (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch  (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
925  starts with "^", or  starts with "^", or
# Line 779  table indicating a fixed set of bytes fo Line 938  table indicating a fixed set of bytes fo
938  string, a pointer to the table is returned. Otherwise NULL is returned. The  string, a pointer to the table is returned. Otherwise NULL is returned. The
939  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
940  .sp  .sp
941      PCRE_INFO_HASCRORLF
942    .sp
943    Return 1 if the pattern contains any explicit matches for CR or LF characters,
944    otherwise 0. The fourth argument should point to an \fBint\fP variable. An
945    explicit match is either a literal CR or LF character, or \er or \en.
946    .sp
947      PCRE_INFO_JCHANGED
948    .sp
949    Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
950    0. The fourth argument should point to an \fBint\fP variable. (?J) and
951    (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
952    .sp
953    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
954  .sp  .sp
955  Return the value of the rightmost literal byte that must exist in any matched  Return the value of the rightmost literal byte that must exist in any matched
# Line 795  is -1. Line 966  is -1.
966  .sp  .sp
967  PCRE supports the use of named as well as numbered capturing parentheses. The  PCRE supports the use of named as well as numbered capturing parentheses. The
968  names are just an additional way of identifying the parentheses, which still  names are just an additional way of identifying the parentheses, which still
969  acquire numbers. A convenience function called \fBpcre_get_named_substring()\fP  acquire numbers. Several convenience functions such as
970  is provided for extracting an individual captured substring by name. It is also  \fBpcre_get_named_substring()\fP are provided for extracting captured
971  possible to extract the data directly, by first converting the name to a number  substrings by name. It is also possible to extract the data directly, by first
972  in order to access the correct pointers in the output vector (described with  converting the name to a number in order to access the correct pointers in the
973  \fBpcre_exec()\fP below). To do the conversion, you need to use the  output vector (described with \fBpcre_exec()\fP below). To do the conversion,
974  name-to-number map, which is described by these three values.  you need to use the name-to-number map, which is described by these three
975    values.
976  .P  .P
977  The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives  The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives
978  the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each  the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
# Line 809  length of the longest name. PCRE_INFO_NA Line 981  length of the longest name. PCRE_INFO_NA
981  entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry  entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry
982  are the number of the capturing parenthesis, most significant byte first. The  are the number of the capturing parenthesis, most significant byte first. The
983  rest of the entry is the corresponding name, zero terminated. The names are in  rest of the entry is the corresponding name, zero terminated. The names are in
984  alphabetical order. For example, consider the following pattern (assume  alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of
985    their parentheses numbers. For example, consider the following pattern (assume
986  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  PCRE_EXTENDED is set, so white space - including newlines - is ignored):
987  .sp  .sp
988  .\" JOIN  .\" JOIN
989    (?P<date> (?P<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
990    (?P<month>\ed\ed) - (?P<day>\ed\ed) )    (?<month>\ed\ed) - (?<day>\ed\ed) )
991  .sp  .sp
992  There are four named subpatterns, so the table has four entries, and each entry  There are four named subpatterns, so the table has four entries, and each entry
993  in the table is eight bytes long. The table is as follows, with non-printing  in the table is eight bytes long. The table is as follows, with non-printing
# Line 826  bytes shows in hexadecimal, and undefine Line 999  bytes shows in hexadecimal, and undefine
999    00 02 y  e  a  r  00 ??    00 02 y  e  a  r  00 ??
1000  .sp  .sp
1001  When writing code to extract data from named subpatterns using the  When writing code to extract data from named subpatterns using the
1002  name-to-number map, remember that the length of each entry is likely to be  name-to-number map, remember that the length of the entries is likely to be
1003  different for each compiled pattern.  different for each compiled pattern.
1004  .sp  .sp
1005      PCRE_INFO_OKPARTIAL
1006    .sp
1007    Return 1 if the pattern can be used for partial matching, otherwise 0. The
1008    fourth argument should point to an \fBint\fP variable. The
1009    .\" HREF
1010    \fBpcrepartial\fP
1011    .\"
1012    documentation lists the restrictions that apply to patterns when partial
1013    matching is used.
1014    .sp
1015    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
1016  .sp  .sp
1017  Return a copy of the options with which the pattern was compiled. The fourth  Return a copy of the options with which the pattern was compiled. The fourth
1018  argument should point to an \fBunsigned long int\fP variable. These option bits  argument should point to an \fBunsigned long int\fP variable. These option bits
1019  are those specified in the call to \fBpcre_compile()\fP, modified by any  are those specified in the call to \fBpcre_compile()\fP, modified by any
1020  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
1021    they are the options that will be in force when matching starts. For example,
1022    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1023    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
1024  .P  .P
1025  A pattern is automatically anchored by PCRE if all of its top-level  A pattern is automatically anchored by PCRE if all of its top-level
1026  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 964  Here is an example of a simple call to \ Line 1150  Here is an example of a simple call to \
1150  If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP  If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP
1151  data block. The \fBpcre_study()\fP function returns such a block (when it  data block. The \fBpcre_study()\fP function returns such a block (when it
1152  doesn't return NULL), but you can also create one for yourself, and pass  doesn't return NULL), but you can also create one for yourself, and pass
1153  additional information in it. The fields in a \fBpcre_extra\fP block are as  additional information in it. The \fBpcre_extra\fP block contains the following
1154  follows:  fields (not necessarily in this order):
1155  .sp  .sp
1156    unsigned long int \fIflags\fP;    unsigned long int \fIflags\fP;
1157    void *\fIstudy_data\fP;    void *\fIstudy_data\fP;
1158    unsigned long int \fImatch_limit\fP;    unsigned long int \fImatch_limit\fP;
1159      unsigned long int \fImatch_limit_recursion\fP;
1160    void *\fIcallout_data\fP;    void *\fIcallout_data\fP;
1161    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1162  .sp  .sp
# Line 978  are set. The flag bits are: Line 1165  are set. The flag bits are:
1165  .sp  .sp
1166    PCRE_EXTRA_STUDY_DATA    PCRE_EXTRA_STUDY_DATA
1167    PCRE_EXTRA_MATCH_LIMIT    PCRE_EXTRA_MATCH_LIMIT
1168      PCRE_EXTRA_MATCH_LIMIT_RECURSION
1169    PCRE_EXTRA_CALLOUT_DATA    PCRE_EXTRA_CALLOUT_DATA
1170    PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
1171  .sp  .sp
# Line 992  but which have a very large number of po Line 1180  but which have a very large number of po
1180  classic example is the use of nested unlimited repeats.  classic example is the use of nested unlimited repeats.
1181  .P  .P
1182  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly
1183  (sometimes recursively). The limit is imposed on the number of times this  (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the
1184  function is called during a match, which has the effect of limiting the amount  number of times this function is called during a match, which has the effect of
1185  of recursion and backtracking that can take place. For patterns that are not  limiting the amount of backtracking that can take place. For patterns that are
1186  anchored, the count starts from zero for each position in the subject string.  not anchored, the count restarts from zero for each position in the subject
1187    string.
1188  .P  .P
1189  The default limit for the library can be set when PCRE is built; the default  The default value for the limit can be set when PCRE is built; the default
1190  default is 10 million, which handles all but the most extreme cases. You can  default is 10 million, which handles all but the most extreme cases. You can
1191  reduce the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP block  override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP
1192  in which \fImatch_limit\fP is set to a smaller value, and  block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in
1193  PCRE_EXTRA_MATCH_LIMIT is set in the \fIflags\fP field. If the limit is  the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns
1194  exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_MATCHLIMIT.  PCRE_ERROR_MATCHLIMIT.
1195    .P
1196    The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but
1197    instead of limiting the total number of times that \fBmatch()\fP is called, it
1198    limits the depth of recursion. The recursion depth is a smaller number than the
1199    total number of calls, because not all calls to \fBmatch()\fP are recursive.
1200    This limit is of use only if it is set smaller than \fImatch_limit\fP.
1201    .P
1202    Limiting the recursion depth limits the amount of stack that can be used, or,
1203    when PCRE has been compiled to use memory on the heap instead of the stack, the
1204    amount of heap memory that can be used.
1205    .P
1206    The default value for \fImatch_limit_recursion\fP can be set when PCRE is
1207    built; the default default is the same value as the default for
1208    \fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP
1209    with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and
1210    PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
1211    is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1212  .P  .P
1213  The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,  The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,
1214  which is described in the  which is described in the
# Line 1025  called. See the Line 1231  called. See the
1231  .\"  .\"
1232  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1233  .  .
1234    .\" HTML <a name="execoptions"></a>
1235  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1236  .rs  .rs
1237  .sp  .sp
1238  The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be  The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be
1239  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NOTBOL,  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1240  PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_START_OPTIMIZE,
1241    PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
1242  .sp  .sp
1243    PCRE_ANCHORED    PCRE_ANCHORED
1244  .sp  .sp
# Line 1039  matching position. If a pattern was comp Line 1247  matching position. If a pattern was comp
1247  to be anchored by virtue of its contents, it cannot be made unachored at  to be anchored by virtue of its contents, it cannot be made unachored at
1248  matching time.  matching time.
1249  .sp  .sp
1250      PCRE_BSR_ANYCRLF
1251      PCRE_BSR_UNICODE
1252    .sp
1253    These options (which are mutually exclusive) control what the \eR escape
1254    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1255    match any Unicode newline sequence. These options override the choice that was
1256    made or defaulted when the pattern was compiled.
1257    .sp
1258      PCRE_NEWLINE_CR
1259      PCRE_NEWLINE_LF
1260      PCRE_NEWLINE_CRLF
1261      PCRE_NEWLINE_ANYCRLF
1262      PCRE_NEWLINE_ANY
1263    .sp
1264    These options override the newline definition that was chosen or defaulted when
1265    the pattern was compiled. For details, see the description of
1266    \fBpcre_compile()\fP above. During matching, the newline choice affects the
1267    behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1268    the way the match position is advanced after a match failure for an unanchored
1269    pattern.
1270    .P
1271    When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
1272    match attempt for an unanchored pattern fails when the current position is at a
1273    CRLF sequence, and the pattern contains no explicit matches for CR or LF
1274    characters, the match position is advanced by two characters instead of one, in
1275    other words, to after the CRLF.
1276    .P
1277    The above rule is a compromise that makes the most common cases work as
1278    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1279    set), it does not match the string "\er\enA" because, after failing at the
1280    start, it skips both the CR and the LF before retrying. However, the pattern
1281    [\er\en]A does match that string, because it contains an explicit CR or LF
1282    reference, and so advances only by one character after the first failure.
1283    .P
1284    An explicit match for CR of LF is either a literal appearance of one of those
1285    characters, or one of the \er or \en escape sequences. Implicit matches such as
1286    [^X] do not count, nor does \es (which includes CR and LF in the characters
1287    that it matches).
1288    .P
1289    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1290    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1291    .sp
1292    PCRE_NOTBOL    PCRE_NOTBOL
1293  .sp  .sp
1294  This option specifies that first character of the subject string is not the  This option specifies that first character of the subject string is not the
# Line 1075  PCRE_NOTEMPTY and PCRE_ANCHORED, and the Line 1325  PCRE_NOTEMPTY and PCRE_ANCHORED, and the
1325  starting offset (see below) and trying an ordinary match again. There is some  starting offset (see below) and trying an ordinary match again. There is some
1326  code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.  code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.
1327  .sp  .sp
1328      PCRE_NO_START_OPTIMIZE
1329    .sp
1330    There are a number of optimizations that \fBpcre_exec()\fP uses at the start of
1331    a match, in order to speed up the process. For example, if it is known that a
1332    match must start with a specific character, it searches the subject for that
1333    character, and fails immediately if it cannot find it, without actually running
1334    the main matching function. When callouts are in use, these optimizations can
1335    cause them to be skipped. This option disables the "start-up" optimizations,
1336    causing performance to suffer, but ensuring that the callouts do occur.
1337    .sp
1338    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
1339  .sp  .sp
1340  When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8  When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
1341  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1342  The value of \fIstartoffset\fP is also checked to ensure that it points to the  The value of \fIstartoffset\fP is also checked to ensure that it points to the
1343  start of a UTF-8 character. If an invalid UTF-8 sequence of bytes is found,  start of a UTF-8 character. There is a discussion about the validity of UTF-8
1344  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1345  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1346    .\" </a>
1347    section on UTF-8 support
1348    .\"
1349    in the main
1350    .\" HREF
1351    \fBpcre\fP
1352    .\"
1353    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1354    the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1355    PCRE_ERROR_BADUTF8_OFFSET is returned.
1356  .P  .P
1357  If you already know that your subject is valid, and you want to skip these  If you already know that your subject is valid, and you want to skip these
1358  checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when  checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
# Line 1112  documentation. Line 1382  documentation.
1382  .rs  .rs
1383  .sp  .sp
1384  The subject string is passed to \fBpcre_exec()\fP as a pointer in  The subject string is passed to \fBpcre_exec()\fP as a pointer in
1385  \fIsubject\fP, a length in \fIlength\fP, and a starting byte offset in  \fIsubject\fP, a length (in bytes) in \fIlength\fP, and a starting byte offset
1386  \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a  in \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of
1387  UTF-8 character. Unlike the pattern string, the subject may contain binary zero  a UTF-8 character. Unlike the pattern string, the subject may contain binary
1388  bytes. When the starting offset is zero, the search for a match starts at the  zero bytes. When the starting offset is zero, the search for a match starts at
1389  beginning of the subject, and this is by far the most common case.  the beginning of the subject, and this is by far the most common case.
1390  .P  .P
1391  A non-zero starting offset is useful when searching for another match in the  A non-zero starting offset is useful when searching for another match in the
1392  same subject by calling \fBpcre_exec()\fP again after a previous success.  same subject by calling \fBpcre_exec()\fP again after a previous success.
# Line 1150  pattern. Following the usage in Jeffrey Line 1420  pattern. Following the usage in Jeffrey
1420  a fragment of a pattern that picks out a substring. PCRE supports several other  a fragment of a pattern that picks out a substring. PCRE supports several other
1421  kinds of parenthesized subpattern that do not cause substrings to be captured.  kinds of parenthesized subpattern that do not cause substrings to be captured.
1422  .P  .P
1423  Captured substrings are returned to the caller via a vector of integer offsets  Captured substrings are returned to the caller via a vector of integers whose
1424  whose address is passed in \fIovector\fP. The number of elements in the vector  address is passed in \fIovector\fP. The number of elements in the vector is
1425  is passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP:  passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP: this
1426  this argument is NOT the size of \fIovector\fP in bytes.  argument is NOT the size of \fIovector\fP in bytes.
1427  .P  .P
1428  The first two-thirds of the vector is used to pass back captured substrings,  The first two-thirds of the vector is used to pass back captured substrings,
1429  each substring using a pair of integers. The remaining third of the vector is  each substring using a pair of integers. The remaining third of the vector is
1430  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1431  and is not available for passing back information. The length passed in  and is not available for passing back information. The number passed in
1432  \fIovecsize\fP should always be a multiple of three. If it is not, it is  \fIovecsize\fP should always be a multiple of three. If it is not, it is
1433  rounded down.  rounded down.
1434  .P  .P
1435  When a match is successful, information about captured substrings is returned  When a match is successful, information about captured substrings is returned
1436  in pairs of integers, starting at the beginning of \fIovector\fP, and  in pairs of integers, starting at the beginning of \fIovector\fP, and
1437  continuing up to two-thirds of its length at the most. The first element of a  continuing up to two-thirds of its length at the most. The first element of
1438  pair is set to the offset of the first character in a substring, and the second  each pair is set to the byte offset of the first character in a substring, and
1439  is set to the offset of the first character after the end of a substring. The  the second is set to the byte offset of the first character after the end of a
1440  first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the  substring. \fBNote\fP: these values are always byte offsets, even in UTF-8
1441  subject string matched by the entire pattern. The next pair is used for the  mode. They are not character counts.
1442  first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP  .P
1443  is the number of pairs that have been set. If there are no capturing  The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the
1444  subpatterns, the return value from a successful match is 1, indicating that  portion of the subject string matched by the entire pattern. The next pair is
1445  just the first pair of offsets has been set.  used for the first capturing subpattern, and so on. The value returned by
1446  .P  \fBpcre_exec()\fP is one more than the highest numbered pair that has been set.
1447  Some convenience functions are provided for extracting the captured substrings  For example, if two substrings have been captured, the returned value is 3. If
1448  as separate strings. These are described in the following section.  there are no capturing subpatterns, the return value from a successful match is
1449  .P  1, indicating that just the first pair of offsets has been set.
 It is possible for an capturing subpattern number \fIn+1\fP to match some  
 part of the subject when subpattern \fIn\fP has not been used at all. For  
 example, if the string "abc" is matched against the pattern (a|(z))(bc)  
 subpatterns 1 and 3 are matched, but 2 is not. When this happens, both offset  
 values corresponding to the unused subpattern are set to -1.  
1450  .P  .P
1451  If a capturing subpattern is matched repeatedly, it is the last portion of the  If a capturing subpattern is matched repeatedly, it is the last portion of the
1452  string that it matched that is returned.  string that it matched that is returned.
1453  .P  .P
1454  If the vector is too small to hold all the captured substring offsets, it is  If the vector is too small to hold all the captured substring offsets, it is
1455  used as far as possible (up to two-thirds of its length), and the function  used as far as possible (up to two-thirds of its length), and the function
1456  returns a value of zero. In particular, if the substring offsets are not of  returns a value of zero. If the substring offsets are not of interest,
1457  interest, \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and  \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and
1458  \fIovecsize\fP as zero. However, if the pattern contains back references and  \fIovecsize\fP as zero. However, if the pattern contains back references and
1459  the \fIovector\fP is not big enough to remember the related substrings, PCRE  the \fIovector\fP is not big enough to remember the related substrings, PCRE
1460  has to get additional memory for use during matching. Thus it is usually  has to get additional memory for use during matching. Thus it is usually
1461  advisable to supply an \fIovector\fP.  advisable to supply an \fIovector\fP.
1462  .P  .P
1463  Note that \fBpcre_info()\fP can be used to find out how many capturing  The \fBpcre_info()\fP function can be used to find out how many capturing
1464  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
1465  \fIovector\fP that will allow for \fIn\fP captured substrings, in addition to  \fIovector\fP that will allow for \fIn\fP captured substrings, in addition to
1466  the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3.  the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3.
1467    .P
1468    It is possible for capturing subpattern number \fIn+1\fP to match some part of
1469    the subject when subpattern \fIn\fP has not been used at all. For example, if
1470    the string "abc" is matched against the pattern (a|(z))(bc) the return from the
1471    function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
1472    happens, both values in the offset pairs corresponding to unused subpatterns
1473    are set to -1.
1474    .P
1475    Offset values that correspond to unused subpatterns at the end of the
1476    expression are also set to -1. For example, if the string "abc" is matched
1477    against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1478    return from the function is 2, because the highest used capturing subpattern
1479    number is 1. However, you can refer to the offsets for the second and third
1480    capturing subpatterns if you wish (assuming the vector is large enough, of
1481    course).
1482    .P
1483    Some convenience functions are provided for extracting the captured substrings
1484    as separate strings. These are described below.
1485  .  .
1486  .\" HTML <a name="errorlist"></a>  .\" HTML <a name="errorlist"></a>
1487  .SS "Return values from \fBpcre_exec()\fP"  .SS "Error return values from \fBpcre_exec()\fP"
1488  .rs  .rs
1489  .sp  .sp
1490  If \fBpcre_exec()\fP fails, it returns a negative number. The following are  If \fBpcre_exec()\fP fails, it returns a negative number. The following are
# Line 1228  compiled in an environment of one endian Line 1511  compiled in an environment of one endian
1511  other endianness. This is the error that PCRE gives when the magic number is  other endianness. This is the error that PCRE gives when the magic number is
1512  not present.  not present.
1513  .sp  .sp
1514    PCRE_ERROR_UNKNOWN_NODE   (-5)    PCRE_ERROR_UNKNOWN_OPCODE (-5)
1515  .sp  .sp
1516  While running the pattern match, an unknown item was encountered in the  While running the pattern match, an unknown item was encountered in the
1517  compiled pattern. This error could be caused by a bug in PCRE or by overwriting  compiled pattern. This error could be caused by a bug in PCRE or by overwriting
# Line 1250  below). It is never returned by \fBpcre_ Line 1533  below). It is never returned by \fBpcre_
1533  .sp  .sp
1534    PCRE_ERROR_MATCHLIMIT     (-8)    PCRE_ERROR_MATCHLIMIT     (-8)
1535  .sp  .sp
1536  The recursion and backtracking limit, as specified by the \fImatch_limit\fP  The backtracking limit, as specified by the \fImatch_limit\fP field in a
1537  field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the  \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1538  description above.  above.
1539  .sp  .sp
1540    PCRE_ERROR_CALLOUT        (-9)    PCRE_ERROR_CALLOUT        (-9)
1541  .sp  .sp
# Line 1297  in PCRE or by overwriting of the compile Line 1580  in PCRE or by overwriting of the compile
1580    PCRE_ERROR_BADCOUNT       (-15)    PCRE_ERROR_BADCOUNT       (-15)
1581  .sp  .sp
1582  This error is given if the value of the \fIovecsize\fP argument is negative.  This error is given if the value of the \fIovecsize\fP argument is negative.
1583    .sp
1584      PCRE_ERROR_RECURSIONLIMIT (-21)
1585    .sp
1586    The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1587    field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1588    description above.
1589    .sp
1590      PCRE_ERROR_BADNEWLINE     (-23)
1591    .sp
1592    An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1593    .P
1594    Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1595  .  .
1596  .  .
1597  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1308  This error is given if the value of the Line 1603  This error is given if the value of the
1603  .ti +5n  .ti +5n
1604  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1605  .PP  .PP
 .br  
1606  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1607  .ti +5n  .ti +5n
1608  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1609  .ti +5n  .ti +5n
1610  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1611  .PP  .PP
 .br  
1612  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1613  .ti +5n  .ti +5n
1614  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
# Line 1326  Captured substrings can be accessed dire Line 1619  Captured substrings can be accessed dire
1619  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
1620  as new, separate, zero-terminated strings. These functions identify substrings  as new, separate, zero-terminated strings. These functions identify substrings
1621  by number. The next section describes functions for extracting named  by number. The next section describes functions for extracting named
1622  substrings. A substring that contains a binary zero is correctly extracted and  substrings.
1623  has a further zero added on the end, but the result is not, of course,  .P
1624  a C string.  A substring that contains a binary zero is correctly extracted and has a
1625    further zero added on the end, but the result is not, of course, a C string.
1626    However, you can process such a string by referring to the length that is
1627    returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
1628    Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
1629    for handling strings containing binary zeros, because the end of the final
1630    string is not independently indicated.
1631  .P  .P
1632  The first three arguments are the same for all three of these functions:  The first three arguments are the same for all three of these functions:
1633  \fIsubject\fP is the subject string that has just been successfully matched,  \fIsubject\fP is the subject string that has just been successfully matched,
# Line 1348  the string is placed in \fIbuffer\fP, wh Line 1647  the string is placed in \fIbuffer\fP, wh
1647  \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is  \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is
1648  obtained via \fBpcre_malloc\fP, and its address is returned via  obtained via \fBpcre_malloc\fP, and its address is returned via
1649  \fIstringptr\fP. The yield of the function is the length of the string, not  \fIstringptr\fP. The yield of the function is the length of the string, not
1650  including the terminating zero, or one of  including the terminating zero, or one of these error codes:
1651  .sp  .sp
1652    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1653  .sp  .sp
# Line 1364  and builds a list of pointers to them. A Line 1663  and builds a list of pointers to them. A
1663  memory that is obtained via \fBpcre_malloc\fP. The address of the memory block  memory that is obtained via \fBpcre_malloc\fP. The address of the memory block
1664  is returned via \fIlistptr\fP, which is also the start of the list of string  is returned via \fIlistptr\fP, which is also the start of the list of string
1665  pointers. The end of the list is marked by a NULL pointer. The yield of the  pointers. The end of the list is marked by a NULL pointer. The yield of the
1666  function is zero if all went well, or  function is zero if all went well, or the error code
1667  .sp  .sp
1668    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1669  .sp  .sp
# Line 1383  a previous call of \fBpcre_get_substring Line 1682  a previous call of \fBpcre_get_substring
1682  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
1683  the function pointed to by \fBpcre_free\fP, which of course could be called  the function pointed to by \fBpcre_free\fP, which of course could be called
1684  directly from a C program. However, PCRE is used in some situations where it is  directly from a C program. However, PCRE is used in some situations where it is
1685  linked via a special interface to another programming language which cannot use  linked via a special interface to another programming language that cannot use
1686  \fBpcre_free\fP directly; it is for these cases that the functions are  \fBpcre_free\fP directly; it is for these cases that the functions are
1687  provided.  provided.
1688  .  .
# Line 1395  provided. Line 1694  provided.
1694  .ti +5n  .ti +5n
1695  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1696  .PP  .PP
 .br  
1697  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1698  .ti +5n  .ti +5n
1699  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1404  provided. Line 1702  provided.
1702  .ti +5n  .ti +5n
1703  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1704  .PP  .PP
 .br  
1705  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1706  .ti +5n  .ti +5n
1707  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1418  For example, for this pattern Line 1715  For example, for this pattern
1715  .sp  .sp
1716    (a+)b(?<xxx>\ed+)...    (a+)b(?<xxx>\ed+)...
1717  .sp  .sp
1718  the number of the subpattern called "xxx" is 2. You can find the number from  the number of the subpattern called "xxx" is 2. If the name is known to be
1719  the name by calling \fBpcre_get_stringnumber()\fP. The first argument is the  unique (PCRE_DUPNAMES was not set), you can find the number from the name by
1720  compiled pattern, and the second is the name. The yield of the function is the  calling \fBpcre_get_stringnumber()\fP. The first argument is the compiled
1721    pattern, and the second is the name. The yield of the function is the
1722  subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of  subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of
1723  that name.  that name.
1724  .P  .P
# Line 1428  Given the number, you can extract the su Line 1726  Given the number, you can extract the su
1726  functions described in the previous section. For convenience, there are also  functions described in the previous section. For convenience, there are also
1727  two functions that do the whole job.  two functions that do the whole job.
1728  .P  .P
1729  Most of the arguments of \fIpcre_copy_named_substring()\fP and  Most of the arguments of \fBpcre_copy_named_substring()\fP and
1730  \fIpcre_get_named_substring()\fP are the same as those for the similarly named  \fBpcre_get_named_substring()\fP are the same as those for the similarly named
1731  functions that extract by number. As these are described in the previous  functions that extract by number. As these are described in the previous
1732  section, they are not re-described here. There are just two differences:  section, they are not re-described here. There are just two differences:
1733  .P  .P
# Line 1439  pattern. This is needed in order to gain Line 1737  pattern. This is needed in order to gain
1737  translation table.  translation table.
1738  .P  .P
1739  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1740  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1741  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1742    the behaviour may not be what you want (see the next section).
1743    .P
1744    \fBWarning:\fP If the pattern uses the "(?|" feature to set up multiple
1745    subpatterns with the same number, you cannot use names to distinguish them,
1746    because names are not included in the compiled code. The matching process uses
1747    only numbers.
1748    .
1749    .SH "DUPLICATE SUBPATTERN NAMES"
1750    .rs
1751    .sp
1752    .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
1753    .ti +5n
1754    .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
1755    .PP
1756    When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
1757    are not required to be unique. Normally, patterns with duplicate names are such
1758    that in any one match, only one of the named subpatterns participates. An
1759    example is shown in the
1760    .\" HREF
1761    \fBpcrepattern\fP
1762    .\"
1763    documentation.
1764    .P
1765    When duplicates are present, \fBpcre_copy_named_substring()\fP and
1766    \fBpcre_get_named_substring()\fP return the first substring corresponding to
1767    the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
1768    returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1769    returns one of the numbers that are associated with the name, but it is not
1770    defined which it is.
1771    .P
1772    If you want to get full details of all captured substrings for a given name,
1773    you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1774    argument is the compiled pattern, and the second is the name. The third and
1775    fourth are pointers to variables which are updated by the function. After it
1776    has run, they point to the first and last entries in the name-to-number table
1777    for the given name. The function itself returns the length of each entry, or
1778    PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1779    described above in the section entitled \fIInformation about a pattern\fP.
1780    Given all the relevant entries for the name, you can extract each of their
1781    numbers, and hence the captured data, if any.
1782  .  .
1783  .  .
1784  .SH "FINDING ALL POSSIBLE MATCHES"  .SH "FINDING ALL POSSIBLE MATCHES"
# Line 1478  will yield PCRE_ERROR_NOMATCH. Line 1816  will yield PCRE_ERROR_NOMATCH.
1816  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
1817  .P  .P
1818  The function \fBpcre_dfa_exec()\fP is called to match a subject string against  The function \fBpcre_dfa_exec()\fP is called to match a subject string against
1819  a compiled pattern, using a "DFA" matching algorithm. This has different  a compiled pattern, using a matching algorithm that scans the subject string
1820  characteristics to the normal algorithm, and is not compatible with Perl. Some  just once, and does not backtrack. This has different characteristics to the
1821  of the features of PCRE patterns are not supported. Nevertheless, there are  normal algorithm, and is not compatible with Perl. Some of the features of PCRE
1822  times when this kind of matching can be useful. For a discussion of the two  patterns are not supported. Nevertheless, there are times when this kind of
1823  matching algorithms, see the  matching can be useful. For a discussion of the two matching algorithms, see
1824    the
1825  .\" HREF  .\" HREF
1826  \fBpcrematching\fP  \fBpcrematching\fP
1827  .\"  .\"
# Line 1497  here. Line 1836  here.
1836  The two additional arguments provide workspace for the function. The workspace  The two additional arguments provide workspace for the function. The workspace
1837  vector should contain at least 20 elements. It is used for keeping track of  vector should contain at least 20 elements. It is used for keeping track of
1838  multiple paths through the pattern tree. More workspace will be needed for  multiple paths through the pattern tree. More workspace will be needed for
1839  patterns and subjects where there are a lot of possible matches.  patterns and subjects where there are a lot of potential matches.
1840  .P  .P
1841  Here is an example of a simple call to \fBpcre_exec()\fP:  Here is an example of a simple call to \fBpcre_dfa_exec()\fP:
1842  .sp  .sp
1843    int rc;    int rc;
1844    int ovector[10];    int ovector[10];
1845    int wspace[20];    int wspace[20];
1846    rc = pcre_exec(    rc = pcre_dfa_exec(
1847      re,             /* result of pcre_compile() */      re,             /* result of pcre_compile() */
1848      NULL,           /* we didn't study the pattern */      NULL,           /* we didn't study the pattern */
1849      "some string",  /* the subject string */      "some string",  /* the subject string */
# Line 1520  Here is an example of a simple call to \ Line 1859  Here is an example of a simple call to \
1859  .rs  .rs
1860  .sp  .sp
1861  The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be  The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be
1862  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NOTBOL,  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1863  PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,
1864  PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are  PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are
1865  the same as for \fBpcre_exec()\fP, so their description is not repeated here.  the same as for \fBpcre_exec()\fP, so their description is not repeated here.
1866  .sp  .sp
# Line 1538  matching string. Line 1877  matching string.
1877    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
1878  .sp  .sp
1879  Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as  Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
1880  soon as it has found one match. Because of the way the DFA algorithm works,  soon as it has found one match. Because of the way the alternative algorithm
1881  this is necessarily the shortest possible match at the first possible matching  works, this is necessarily the shortest possible match at the first possible
1882  point in the subject string.  matching point in the subject string.
1883  .sp  .sp
1884    PCRE_DFA_RESTART    PCRE_DFA_RESTART
1885  .sp  .sp
# Line 1579  the three matched strings are Line 1918  the three matched strings are
1918  On success, the yield of the function is a number greater than zero, which is  On success, the yield of the function is a number greater than zero, which is
1919  the number of matched substrings. The substrings themselves are returned in  the number of matched substrings. The substrings themselves are returned in
1920  \fIovector\fP. Each string uses two elements; the first is the offset to the  \fIovector\fP. Each string uses two elements; the first is the offset to the
1921  start, and the second is the offset to the end. All the strings have the same  start, and the second is the offset to the end. In fact, all the strings have
1922  start offset. (Space could have been saved by giving this only once, but it was  the same start offset. (Space could have been saved by giving this only once,
1923  decided to retain some compatibility with the way \fBpcre_exec()\fP returns  but it was decided to retain some compatibility with the way \fBpcre_exec()\fP
1924  data, even though the meaning of the strings is different.)  returns data, even though the meaning of the strings is different.)
1925  .P  .P
1926  The strings are returned in reverse order of length; that is, the longest  The strings are returned in reverse order of length; that is, the longest
1927  matching string is given first. If there were too many matches to fit into  matching string is given first. If there were too many matches to fit into
# Line 1609  that it does not support, for instance, Line 1948  that it does not support, for instance,
1948  .sp  .sp
1949    PCRE_ERROR_DFA_UCOND      (-17)    PCRE_ERROR_DFA_UCOND      (-17)
1950  .sp  .sp
1951  This return is given if \fBpcre_dfa_exec()\fP encounters a condition item in a  This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that
1952  pattern that uses a back reference for the condition. This is not supported.  uses a back reference for the condition, or a test for recursion in a specific
1953    group. These are not supported.
1954  .sp  .sp
1955    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
1956  .sp  .sp
# Line 1629  When a recursive subpattern is processed Line 1969  When a recursive subpattern is processed
1969  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1970  error is given if the output vector is not large enough. This should be  error is given if the output vector is not large enough. This should be
1971  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
1972  .P  .
1973  .in 0  .
1974  Last updated: 16 May 2005  .SH "SEE ALSO"
1975  .br  .rs
1976  Copyright (c) 1997-2005 University of Cambridge.  .sp
1977    \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1978    \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1979    \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1980    .
1981    .
1982    .SH AUTHOR
1983    .rs
1984    .sp
1985    .nf
1986    Philip Hazel
1987    University Computing Service
1988    Cambridge CB2 3QH, England.
1989    .fi
1990    .
1991    .
1992    .SH REVISION
1993    .rs
1994    .sp
1995    .nf
1996    Last updated: 15 March 2009
1997    Copyright (c) 1997-2009 University of Cambridge.
1998    .fi

Legend:
Removed from v.77  
changed lines
  Added in v.389

  ViewVC Help
Powered by ViewVC 1.1.5