/[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 96 by nigel, Fri Mar 2 13:10:43 2007 UTC revision 518 by ph10, Tue May 18 15:47:01 2010 UTC
# 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
 .br  
68  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
69  .ti +5n  .ti +5n
70  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
71  .PP  .PP
 .br  
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  .  .
# Line 160  Applications can use these to include su Line 135  Applications can use these to include su
135  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,
136  and \fBpcre_exec()\fP are used for compiling and matching regular expressions  and \fBpcre_exec()\fP are used for compiling and matching regular expressions
137  in a Perl-compatible manner. A sample program that demonstrates the simplest  in a Perl-compatible manner. A sample program that demonstrates the simplest
138  way of using them is provided in the file called \fIpcredemo.c\fP in the source  way of using them is provided in the file called \fIpcredemo.c\fP in the PCRE
139  distribution. The  source distribution. A listing of this program is given in the
140    .\" HREF
141    \fBpcredemo\fP
142    .\"
143    documentation, and the
144  .\" HREF  .\" HREF
145  \fBpcresample\fP  \fBpcresample\fP
146  .\"  .\"
147  documentation describes how to run it.  documentation describes how to compile and run it.
148  .P  .P
149  A second matching function, \fBpcre_dfa_exec()\fP, which is not  A second matching function, \fBpcre_dfa_exec()\fP, which is not
150  Perl-compatible, is also provided. This uses a different algorithm for the  Perl-compatible, is also provided. This uses a different algorithm for the
151  matching. The alternative algorithm finds all possible matches (at a given  matching. The alternative algorithm finds all possible matches (at a given
152  point in the subject), and scans the subject just once. However, this algorithm  point in the subject), and scans the subject just once (unless there are
153  does not return captured substrings. A description of the two matching  lookbehind assertions). However, this algorithm does not return captured
154  algorithms and their advantages and disadvantages is given in the  substrings. A description of the two matching algorithms and their advantages
155    and disadvantages is given in the
156  .\" HREF  .\" HREF
157  \fBpcrematching\fP  \fBpcrematching\fP
158  .\"  .\"
# Line 243  points during a matching operation. Deta Line 223  points during a matching operation. Deta
223  documentation.  documentation.
224  .  .
225  .  .
226    .\" HTML <a name="newlines"></a>
227  .SH NEWLINES  .SH NEWLINES
228  .rs  .rs
229  .sp  .sp
230  PCRE supports four different conventions for indicating line breaks in  PCRE supports five different conventions for indicating line breaks in
231  strings: a single CR (carriage return) character, a single LF (linefeed)  strings: a single CR (carriage return) character, a single LF (linefeed)
232  character, the two-character sequence CRLF, or any Unicode newline sequence.  character, the two-character sequence CRLF, any of the three preceding, or any
233  The Unicode newline sequences are the three just mentioned, plus the single  Unicode newline sequence. The Unicode newline sequences are the three just
234  characters VT (vertical tab, U+000B), FF (formfeed, U+000C), NEL (next line,  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
235  U+0085), LS (line separator, U+2028), and PS (paragraph separator, U+2029).  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
236    (paragraph separator, U+2029).
237  .P  .P
238  Each of the first three conventions is used by at least one operating system as  Each of the first three conventions is used by at least one operating system as
239  its standard newline sequence. When PCRE is built, a default can be specified.  its standard newline sequence. When PCRE is built, a default can be specified.
# Line 259  The default default is LF, which is the Line 241  The default default is LF, which is the
241  default can be overridden, either when a pattern is compiled, or when it is  default can be overridden, either when a pattern is compiled, or when it is
242  matched.  matched.
243  .P  .P
244    At compile time, the newline convention can be specified by the \fIoptions\fP
245    argument of \fBpcre_compile()\fP, or it can be specified by special text at the
246    start of the pattern itself; this overrides any other settings. See the
247    .\" HREF
248    \fBpcrepattern\fP
249    .\"
250    page for details of the special character sequences.
251    .P
252  In the PCRE documentation the word "newline" is used to mean "the character or  In the PCRE documentation the word "newline" is used to mean "the character or
253  pair of characters that indicate a line break". The choice of newline  pair of characters that indicate a line break". The choice of newline
254  convention affects the handling of the dot, circumflex, and dollar  convention affects the handling of the dot, circumflex, and dollar
255  metacharacters, the handling of #-comments in /x mode, and, when CRLF is a  metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
256  recognized line ending sequence, the match position advancement for a  recognized line ending sequence, the match position advancement for a
257  non-anchored pattern. The choice of newline convention does not affect the  non-anchored pattern. There is more detail about this in the
258  interpretation of the \en or \er escape sequences.  .\" HTML <a href="#execoptions">
259    .\" </a>
260    section on \fBpcre_exec()\fP options
261    .\"
262    below.
263    .P
264    The choice of newline convention does not affect the interpretation of
265    the \en or \er escape sequences, nor does it affect what \eR matches, which is
266    controlled in a similar way, but by separate options.
267  .  .
268  .  .
269  .SH MULTITHREADING  .SH MULTITHREADING
# Line 289  which it was compiled. Details are given Line 287  which it was compiled. Details are given
287  .\" HREF  .\" HREF
288  \fBpcreprecompile\fP  \fBpcreprecompile\fP
289  .\"  .\"
290  documentation.  documentation. However, compiling a regular expression with one version of PCRE
291    for use with a different version is not guaranteed to work and may cause
292    crashes.
293  .  .
294  .  .
295  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 322  properties is available; otherwise it is Line 322  properties is available; otherwise it is
322  .sp  .sp
323  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
324  that is recognized as meaning "newline". The four values that are supported  that is recognized as meaning "newline". The four values that are supported
325  are: 10 for LF, 13 for CR, 3338 for CRLF, and -1 for ANY. The default should  are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY.
326  normally be the standard sequence for your operating system.  Though they are derived from ASCII, the same values are returned in EBCDIC
327    environments. The default should normally correspond to the standard sequence
328    for your operating system.
329    .sp
330      PCRE_CONFIG_BSR
331    .sp
332    The output is an integer whose value indicates what character sequences the \eR
333    escape sequence matches by default. A value of 0 means that \eR matches any
334    Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
335    or CRLF. The default can be overridden when a pattern is compiled or matched.
336  .sp  .sp
337    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
338  .sp  .sp
# Line 345  documentation. Line 354  documentation.
354  .sp  .sp
355    PCRE_CONFIG_MATCH_LIMIT    PCRE_CONFIG_MATCH_LIMIT
356  .sp  .sp
357  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
358  internal matching function calls in a \fBpcre_exec()\fP execution. Further  internal matching function calls in a \fBpcre_exec()\fP execution. Further
359  details are given with \fBpcre_exec()\fP below.  details are given with \fBpcre_exec()\fP below.
360  .sp  .sp
361    PCRE_CONFIG_MATCH_LIMIT_RECURSION    PCRE_CONFIG_MATCH_LIMIT_RECURSION
362  .sp  .sp
363  The output is an integer that gives the default limit for the depth of  The output is a long integer that gives the default limit for the depth of
364  recursion when calling the internal matching function in a \fBpcre_exec()\fP  recursion when calling the internal matching function in a \fBpcre_exec()\fP
365  execution. Further details are given with \fBpcre_exec()\fP below.  execution. Further details are given with \fBpcre_exec()\fP below.
366  .sp  .sp
# Line 386  avoiding the use of the stack. Line 395  avoiding the use of the stack.
395  Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be  Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be
396  called to compile a pattern into an internal form. The only difference between  called to compile a pattern into an internal form. The only difference between
397  the two interfaces is that \fBpcre_compile2()\fP has an additional argument,  the two interfaces is that \fBpcre_compile2()\fP has an additional argument,
398  \fIerrorcodeptr\fP, via which a numerical error code can be returned.  \fIerrorcodeptr\fP, via which a numerical error code can be returned. To avoid
399    too much repetition, we refer just to \fBpcre_compile()\fP below, but the
400    information applies equally to \fBpcre_compile2()\fP.
401  .P  .P
402  The pattern is a C string terminated by a binary zero, and is passed in the  The pattern is a C string terminated by a binary zero, and is passed in the
403  \fIpattern\fP argument. A pointer to a single block of memory that is obtained  \fIpattern\fP argument. A pointer to a single block of memory that is obtained
# Line 402  argument, which is an address (see below Line 413  argument, which is an address (see below
413  .P  .P
414  The \fIoptions\fP argument contains various bit settings that affect the  The \fIoptions\fP argument contains various bit settings that affect the
415  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
416  options are described below. Some of them, in particular, those that are  options are described below. Some of them (in particular, those that are
417  compatible with Perl, can also be set and unset from within the pattern (see  compatible with Perl, but some others as well) can also be set and unset from
418  the detailed description in the  within the pattern (see the detailed description in the
419  .\" HREF  .\" HREF
420  \fBpcrepattern\fP  \fBpcrepattern\fP
421  .\"  .\"
422  documentation). For these options, the contents of the \fIoptions\fP argument  documentation). For those options that can be different in different parts of
423  specifies their initial settings at the start of compilation and execution. The  the pattern, the contents of the \fIoptions\fP argument specifies their
424  PCRE_ANCHORED and PCRE_NEWLINE_\fIxxx\fP options can be set at the time of  settings at the start of compilation and execution. The PCRE_ANCHORED,
425  matching as well as at compile time.  PCRE_BSR_\fIxxx\fP, and PCRE_NEWLINE_\fIxxx\fP options can be set at the time
426    of matching as well as at compile time.
427  .P  .P
428  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
429  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
430  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
431  error message. This is a static string that is part of the library. You must  error message. This is a static string that is part of the library. You must
432  not try to free it. The offset from the start of the pattern to the character  not try to free it. The byte offset from the start of the pattern to the
433  where the error was discovered is placed in the variable pointed to by  character that was being processed when the error was discovered is placed in
434  \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.  the variable pointed to by \fIerroffset\fP, which must not be NULL. If it is,
435    an immediate error is given. Some errors are not detected until checks are
436    carried out when the whole pattern has been scanned; in this case the offset is
437    set to the end of the pattern.
438  .P  .P
439  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
440  \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is  \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is
# Line 466  facility, see the Line 481  facility, see the
481  .\"  .\"
482  documentation.  documentation.
483  .sp  .sp
484      PCRE_BSR_ANYCRLF
485      PCRE_BSR_UNICODE
486    .sp
487    These options (which are mutually exclusive) control what the \eR escape
488    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
489    match any Unicode newline sequence. The default is specified when PCRE is
490    built. It can be overridden from within the pattern, or by setting an option
491    when a compiled pattern is matched.
492    .sp
493    PCRE_CASELESS    PCRE_CASELESS
494  .sp  .sp
495  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 529  set, any backslash in a pattern that is Line 553  set, any backslash in a pattern that is
553  special meaning causes an error, thus reserving these combinations for future  special meaning causes an error, thus reserving these combinations for future
554  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
555  special meaning is treated as a literal. (Perl can, however, be persuaded to  special meaning is treated as a literal. (Perl can, however, be persuaded to
556  give a warning for this.) There are at present no other features controlled by  give an error for this, by running it with the -w option.) There are at present
557  this option. It can also be set by a (?X) option setting within a pattern.  no other features controlled by this option. It can also be set by a (?X)
558    option setting within a pattern.
559  .sp  .sp
560    PCRE_FIRSTLINE    PCRE_FIRSTLINE
561  .sp  .sp
# Line 538  If this option is set, an unanchored pat Line 563  If this option is set, an unanchored pat
563  the first newline in the subject string, though the matched text may continue  the first newline in the subject string, though the matched text may continue
564  over the newline.  over the newline.
565  .sp  .sp
566      PCRE_JAVASCRIPT_COMPAT
567    .sp
568    If this option is set, PCRE's behaviour is changed in some ways so that it is
569    compatible with JavaScript rather than Perl. The changes are as follows:
570    .P
571    (1) A lone closing square bracket in a pattern causes a compile-time error,
572    because this is illegal in JavaScript (by default it is treated as a data
573    character). Thus, the pattern AB]CD becomes illegal when this option is set.
574    .P
575    (2) At run time, a back reference to an unset subpattern group matches an empty
576    string (by default this causes the current matching alternative to fail). A
577    pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
578    an "a" in the subject), whereas it fails by default, for Perl compatibility.
579    .sp
580    PCRE_MULTILINE    PCRE_MULTILINE
581  .sp  .sp
582  By default, PCRE treats the subject string as consisting of a single line of  By default, PCRE treats the subject string as consisting of a single line of
# Line 557  occurrences of ^ or $ in a pattern, sett Line 596  occurrences of ^ or $ in a pattern, sett
596    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
597    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
598    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
599      PCRE_NEWLINE_ANYCRLF
600    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
601  .sp  .sp
602  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
603  was built. Setting the first or the second specifies that a newline is  was built. Setting the first or the second specifies that a newline is
604  indicated by a single character (CR or LF, respectively). Setting  indicated by a single character (CR or LF, respectively). Setting
605  PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character  PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
606  CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
607  sequence should be recognized. The Unicode newline sequences are the three just  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
608  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,  that any Unicode newline sequence should be recognized. The Unicode newline
609  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS  sequences are the three just mentioned, plus the single characters VT (vertical
610  (paragraph separator, U+2029). The last two are recognized only in UTF-8 mode.  tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
611    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
612    recognized only in UTF-8 mode.
613  .P  .P
614  The newline setting in the options word uses three bits that are treated  The newline setting in the options word uses three bits that are treated
615  as a number, giving eight possibilities. Currently only five are used (default  as a number, giving eight possibilities. Currently only six are used (default
616  plus the four values above). This means that if you set more than one newline  plus the five values above). This means that if you set more than one newline
617  option, the combination may or may not be sensible. For example,  option, the combination may or may not be sensible. For example,
618  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
619  other combinations yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
620  .P  .P
621  The only time that a line break is specially recognized when compiling a  The only time that a line break is specially recognized when compiling a
622  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
# Line 594  were followed by ?: but named parenthese Line 636  were followed by ?: but named parenthese
636  they acquire numbers in the usual way). There is no equivalent of this option  they acquire numbers in the usual way). There is no equivalent of this option
637  in Perl.  in Perl.
638  .sp  .sp
639      PCRE_UCP
640    .sp
641    This option changes the way PCRE processes \eb, \ed, \es, \ew, and some of the
642    POSIX character classes. By default, only ASCII characters are recognized, but
643    if PCRE_UCP is set, Unicode properties are used instead to classify characters.
644    More details are given in the section on
645    .\" HTML <a href="pcre.html#genericchartypes">
646    .\" </a>
647    generic character types
648    .\"
649    in the
650    .\" HREF
651    \fBpcrepattern\fP
652    .\"
653    page. If you set PCRE_UCP, matching one of the items it affects takes much
654    longer. The option is available only if PCRE has been compiled with Unicode
655    property support.
656    .sp
657    PCRE_UNGREEDY    PCRE_UNGREEDY
658  .sp  .sp
659  This option inverts the "greediness" of the quantifiers so that they are not  This option inverts the "greediness" of the quantifiers so that they are not
# Line 620  page. Line 680  page.
680    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
681  .sp  .sp
682  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
683  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
684  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
685  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
686  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
687  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
688  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
689  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
690  strings.  \fBpcre\fP
691    .\"
692    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
693    returns an error. If you already know that your pattern is valid, and you want
694    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
695    option. When it is set, the effect of passing an invalid UTF-8 string as a
696    pattern is undefined. It may cause your program to crash. Note that this option
697    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
698    the UTF-8 validity checking of subject strings.
699  .  .
700  .  .
701  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 650  out of use. To avoid confusion, they hav Line 718  out of use. To avoid confusion, they hav
718     9  nothing to repeat     9  nothing to repeat
719    10  [this code is not in use]    10  [this code is not in use]
720    11  internal error: unexpected repeat    11  internal error: unexpected repeat
721    12  unrecognized character after (?    12  unrecognized character after (? or (?-
722    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
723    14  missing )    14  missing )
724    15  reference to non-existent subpattern    15  reference to non-existent subpattern
# Line 658  out of use. To avoid confusion, they hav Line 726  out of use. To avoid confusion, they hav
726    17  unknown option bit(s) set    17  unknown option bit(s) set
727    18  missing ) after comment    18  missing ) after comment
728    19  [this code is not in use]    19  [this code is not in use]
729    20  regular expression too large    20  regular expression is too large
730    21  failed to get memory    21  failed to get memory
731    22  unmatched parentheses    22  unmatched parentheses
732    23  internal error: code overflow    23  internal error: code overflow
# Line 667  out of use. To avoid confusion, they hav Line 735  out of use. To avoid confusion, they hav
735    26  malformed number or name after (?(    26  malformed number or name after (?(
736    27  conditional group contains more than two branches    27  conditional group contains more than two branches
737    28  assertion expected after (?(    28  assertion expected after (?(
738    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
739    30  unknown POSIX class name    30  unknown POSIX class name
740    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
741    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
# Line 687  out of use. To avoid confusion, they hav Line 755  out of use. To avoid confusion, they hav
755    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
756    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
757    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
758    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10000)
759    50  repeated subpattern is too long    50  [this code is not in use]
760    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
761    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
762    53  internal error: previously-checked referenced subpattern not found    53  internal error: previously-checked referenced subpattern not found
763    54  DEFINE group contains more than one branch    54  DEFINE group contains more than one branch
764    55  repeating a DEFINE group is not allowed    55  repeating a DEFINE group is not allowed
765    56  inconsistent NEWLINE options"    56  inconsistent NEWLINE options
766      57  \eg is not followed by a braced, angle-bracketed, or quoted
767            name/number or by a plain number
768      58  a numbered reference must not be zero
769      59  an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
770      60  (*VERB) not recognized
771      61  number is too big
772      62  subpattern name expected
773      63  digit expected after (?+
774      64  ] is an invalid data character in JavaScript compatibility mode
775      65  different names for subpatterns of the same number are not allowed
776      66  (*MARK) must have an argument
777      67  this version of PCRE is not compiled with PCRE_UCP support
778    .sp
779    The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
780    be used if the limits were changed when PCRE was built.
781  .  .
782  .  .
783  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 713  help speed up matching, \fBpcre_study()\ Line 796  help speed up matching, \fBpcre_study()\
796  results of the study.  results of the study.
797  .P  .P
798  The returned value from \fBpcre_study()\fP can be passed directly to  The returned value from \fBpcre_study()\fP can be passed directly to
799  \fBpcre_exec()\fP. However, a \fBpcre_extra\fP block also contains other  \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. However, a \fBpcre_extra\fP block
800  fields that can be set by the caller before the block is passed; these are  also contains other fields that can be set by the caller before the block is
801  described  passed; these are described
802  .\" HTML <a href="#extradata">  .\" HTML <a href="#extradata">
803  .\" </a>  .\" </a>
804  below  below
805  .\"  .\"
806  in the section on matching a pattern.  in the section on matching a pattern.
807  .P  .P
808  If studying the pattern does not produce any additional information  If studying the pattern does not produce any useful information,
809  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program
810  wants to pass any of the other fields to \fBpcre_exec()\fP, it must set up its  wants to pass any of the other fields to \fBpcre_exec()\fP or
811  own \fBpcre_extra\fP block.  \fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block.
812  .P  .P
813  The second argument of \fBpcre_study()\fP contains option bits. At present, no  The second argument of \fBpcre_study()\fP contains option bits. At present, no
814  options are defined, and this argument should always be zero.  options are defined, and this argument should always be zero.
# Line 745  This is a typical call to \fBpcre_study\ Line 828  This is a typical call to \fBpcre_study\
828      0,              /* no options exist */      0,              /* no options exist */
829      &error);        /* set to NULL or points to a message */      &error);        /* set to NULL or points to a message */
830  .sp  .sp
831  At present, studying a pattern is useful only for non-anchored patterns that do  Studying a pattern does two things: first, a lower bound for the length of
832  not have a single fixed starting character. A bitmap of possible starting  subject string that is needed to match the pattern is computed. This does not
833  bytes is created.  mean that there are any strings of that length that match, but it does
834    guarantee that no shorter strings match. The value is used by
835    \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP to avoid wasting time by trying to
836    match strings that are shorter than the lower bound. You can find out the value
837    in a calling program via the \fBpcre_fullinfo()\fP function.
838    .P
839    Studying a pattern is also useful for non-anchored patterns that do not have a
840    single fixed starting character. A bitmap of possible starting bytes is
841    created. This speeds up finding a position in the subject at which to start
842    matching.
843  .  .
844  .  .
845  .\" HTML <a name="localesupport"></a>  .\" HTML <a name="localesupport"></a>
846  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
847  .rs  .rs
848  .sp  .sp
849  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
850  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
851  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
852  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but  less than 128. By default, higher-valued codes never match escapes such as \ew
853  can be tested with \ep if PCRE is built with Unicode character property  or \ed, but they can be tested with \ep if PCRE is built with Unicode character
854  support. The use of locales with Unicode is discouraged.  property support. Alternatively, the PCRE_UCP option can be set at compile
855  .P  time; this causes \ew and friends to use Unicode property support instead of
856  An internal set of tables is created in the default C locale when PCRE is  built-in tables. The use of locales with Unicode is discouraged. If you are
857  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  handling characters with codes greater than 128, you should either use UTF-8
858  and is sufficient for many applications. An alternative set of tables can,  and Unicode, or use locales, but not try to mix the two.
859  however, be supplied. These may be created in a different locale from the  .P
860  default. As more and more applications change to using Unicode, the need for  PCRE contains an internal set of tables that are used when the final argument
861  this locale support is expected to die away.  of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
862    Normally, the internal tables recognize only ASCII characters. However, when
863    PCRE is built, it is possible to cause the internal tables to be rebuilt in the
864    default "C" locale of the local system, which may cause them to be different.
865    .P
866    The internal tables can always be overridden by tables supplied by the
867    application that calls PCRE. These may be created in a different locale from
868    the default. As more and more applications change to using Unicode, the need
869    for this locale support is expected to die away.
870  .P  .P
871  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
872  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 779  the following code could be used: Line 879  the following code could be used:
879    tables = pcre_maketables();    tables = pcre_maketables();
880    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
881  .sp  .sp
882    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
883    are using Windows, the name for the French locale is "french".
884    .P
885  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
886  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
887  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 881  table indicating a fixed set of bytes fo Line 984  table indicating a fixed set of bytes fo
984  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
985  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
986  .sp  .sp
987      PCRE_INFO_HASCRORLF
988    .sp
989    Return 1 if the pattern contains any explicit matches for CR or LF characters,
990    otherwise 0. The fourth argument should point to an \fBint\fP variable. An
991    explicit match is either a literal CR or LF character, or \er or \en.
992    .sp
993      PCRE_INFO_JCHANGED
994    .sp
995    Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
996    0. The fourth argument should point to an \fBint\fP variable. (?J) and
997    (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
998    .sp
999    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
1000  .sp  .sp
1001  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 891  follows something of variable length. Fo Line 1006  follows something of variable length. Fo
1006  /^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value  /^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value
1007  is -1.  is -1.
1008  .sp  .sp
1009      PCRE_INFO_MINLENGTH
1010    .sp
1011    If the pattern was studied and a minimum length for matching subject strings
1012    was computed, its value is returned. Otherwise the returned value is -1. The
1013    value is a number of characters, not bytes (this may be relevant in UTF-8
1014    mode). The fourth argument should point to an \fBint\fP variable. A
1015    non-negative value is a lower bound to the length of any matching string. There
1016    may not be any strings of that length that do actually match, but every string
1017    that does match is at least that long.
1018    .sp
1019    PCRE_INFO_NAMECOUNT    PCRE_INFO_NAMECOUNT
1020    PCRE_INFO_NAMEENTRYSIZE    PCRE_INFO_NAMEENTRYSIZE
1021    PCRE_INFO_NAMETABLE    PCRE_INFO_NAMETABLE
# Line 911  entry; both of these return an \fBint\fP Line 1036  entry; both of these return an \fBint\fP
1036  length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first  length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
1037  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
1038  are the number of the capturing parenthesis, most significant byte first. The  are the number of the capturing parenthesis, most significant byte first. The
1039  rest of the entry is the corresponding name, zero terminated. The names are in  rest of the entry is the corresponding name, zero terminated.
1040  alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of  .P
1041  their parentheses numbers. For example, consider the following pattern (assume  The names are in alphabetical order. Duplicate names may appear if (?| is used
1042  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  to create multiple groups with the same number, as described in the
1043    .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
1044    .\" </a>
1045    section on duplicate subpattern numbers
1046    .\"
1047    in the
1048    .\" HREF
1049    \fBpcrepattern\fP
1050    .\"
1051    page. Duplicate names for subpatterns with different numbers are permitted only
1052    if PCRE_DUPNAMES is set. In all cases of duplicate names, they appear in the
1053    table in the order in which they were found in the pattern. In the absence of
1054    (?| this is the order of increasing number; when (?| is used this is not
1055    necessarily the case because later subpatterns may have lower numbers.
1056    .P
1057    As a simple example of the name/number table, consider the following pattern
1058    (assume PCRE_EXTENDED is set, so white space - including newlines - is
1059    ignored):
1060  .sp  .sp
1061  .\" JOIN  .\" JOIN
1062    (?<date> (?<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
# Line 933  When writing code to extract data from n Line 1075  When writing code to extract data from n
1075  name-to-number map, remember that the length of the entries is likely to be  name-to-number map, remember that the length of the entries is likely to be
1076  different for each compiled pattern.  different for each compiled pattern.
1077  .sp  .sp
1078      PCRE_INFO_OKPARTIAL
1079    .sp
1080    Return 1 if the pattern can be used for partial matching with
1081    \fBpcre_exec()\fP, otherwise 0. The fourth argument should point to an
1082    \fBint\fP variable. From release 8.00, this always returns 1, because the
1083    restrictions that previously applied to partial matching have been lifted. The
1084    .\" HREF
1085    \fBpcrepartial\fP
1086    .\"
1087    documentation gives details of partial matching.
1088    .sp
1089    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
1090  .sp  .sp
1091  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
1092  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
1093  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
1094  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
1095    they are the options that will be in force when matching starts. For example,
1096    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1097    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
1098  .P  .P
1099  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
1100  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 965  variable. Line 1121  variable.
1121  Return the size of the data block pointed to by the \fIstudy_data\fP field in  Return the size of the data block pointed to by the \fIstudy_data\fP field in
1122  a \fBpcre_extra\fP block. That is, it is the value that was passed to  a \fBpcre_extra\fP block. That is, it is the value that was passed to
1123  \fBpcre_malloc()\fP when PCRE was getting memory into which to place the data  \fBpcre_malloc()\fP when PCRE was getting memory into which to place the data
1124  created by \fBpcre_study()\fP. The fourth argument should point to a  created by \fBpcre_study()\fP. If \fBpcre_extra\fP is NULL, or there is no
1125    study data, zero is returned. The fourth argument should point to a
1126  \fBsize_t\fP variable.  \fBsize_t\fP variable.
1127  .  .
1128  .  .
# Line 1027  is different. (This seems a highly unlik Line 1184  is different. (This seems a highly unlik
1184  .P  .P
1185  The function \fBpcre_exec()\fP is called to match a subject string against a  The function \fBpcre_exec()\fP is called to match a subject string against a
1186  compiled pattern, which is passed in the \fIcode\fP argument. If the  compiled pattern, which is passed in the \fIcode\fP argument. If the
1187  pattern has been studied, the result of the study should be passed in the  pattern was studied, the result of the study should be passed in the
1188  \fIextra\fP argument. This function is the main matching facility of the  \fIextra\fP argument. This function is the main matching facility of the
1189  library, and it operates in a Perl-like manner. For specialist use there is  library, and it operates in a Perl-like manner. For specialist use there is
1190  also an alternative matching function, which is described  also an alternative matching function, which is described
# Line 1077  fields (not necessarily in this order): Line 1234  fields (not necessarily in this order):
1234    unsigned long int \fImatch_limit_recursion\fP;    unsigned long int \fImatch_limit_recursion\fP;
1235    void *\fIcallout_data\fP;    void *\fIcallout_data\fP;
1236    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1237      unsigned char **\fImark\fP;
1238  .sp  .sp
1239  The \fIflags\fP field is a bitmap that specifies which of the other fields  The \fIflags\fP field is a bitmap that specifies which of the other fields
1240  are set. The flag bits are:  are set. The flag bits are:
# Line 1086  are set. The flag bits are: Line 1244  are set. The flag bits are:
1244    PCRE_EXTRA_MATCH_LIMIT_RECURSION    PCRE_EXTRA_MATCH_LIMIT_RECURSION
1245    PCRE_EXTRA_CALLOUT_DATA    PCRE_EXTRA_CALLOUT_DATA
1246    PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
1247      PCRE_EXTRA_MARK
1248  .sp  .sp
1249  Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the  Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the
1250  \fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with  \fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with
# Line 1095  the block by setting the other fields an Line 1254  the block by setting the other fields an
1254  The \fImatch_limit\fP field provides a means of preventing PCRE from using up a  The \fImatch_limit\fP field provides a means of preventing PCRE from using up a
1255  vast amount of resources when running patterns that are not going to match,  vast amount of resources when running patterns that are not going to match,
1256  but which have a very large number of possibilities in their search trees. The  but which have a very large number of possibilities in their search trees. The
1257  classic example is the use of nested unlimited repeats.  classic example is a pattern that uses nested unlimited repeats.
1258  .P  .P
1259  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly
1260  (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the  (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the
# Line 1128  with a \fBpcre_extra\fP block in which \ Line 1287  with a \fBpcre_extra\fP block in which \
1287  PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit  PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
1288  is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.  is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1289  .P  .P
1290  The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,  The \fIcallout_data\fP field is used in conjunction with the "callout" feature,
1291  which is described in the  and is described in the
1292  .\" HREF  .\" HREF
1293  \fBpcrecallout\fP  \fBpcrecallout\fP
1294  .\"  .\"
# Line 1148  called. See the Line 1307  called. See the
1307  \fBpcreprecompile\fP  \fBpcreprecompile\fP
1308  .\"  .\"
1309  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1310    .P
1311    If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must
1312    be set to point to a \fBchar *\fP variable. If the pattern contains any
1313    backtracking control verbs such as (*MARK:NAME), and the execution ends up with
1314    a name to pass back, a pointer to the name string (zero terminated) is placed
1315    in the variable pointed to by the \fImark\fP field. The names are within the
1316    compiled pattern; if you wish to retain such a name you must copy it before
1317    freeing the memory of a compiled pattern. If there is no name to pass back, the
1318    variable pointed to by the \fImark\fP field set to NULL. For details of the
1319    backtracking control verbs, see the section entitled
1320    .\" HTML <a href="pcrepattern#backtrackcontrol">
1321    .\" </a>
1322    "Backtracking control"
1323    .\"
1324    in the
1325    .\" HREF
1326    \fBpcrepattern\fP
1327    .\"
1328    documentation.
1329    .
1330  .  .
1331    .\" HTML <a name="execoptions"></a>
1332  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1333  .rs  .rs
1334  .sp  .sp
1335  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
1336  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1337  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
1338    PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and
1339    PCRE_PARTIAL_HARD.
1340  .sp  .sp
1341    PCRE_ANCHORED    PCRE_ANCHORED
1342  .sp  .sp
# Line 1163  matching position. If a pattern was comp Line 1345  matching position. If a pattern was comp
1345  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
1346  matching time.  matching time.
1347  .sp  .sp
1348      PCRE_BSR_ANYCRLF
1349      PCRE_BSR_UNICODE
1350    .sp
1351    These options (which are mutually exclusive) control what the \eR escape
1352    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1353    match any Unicode newline sequence. These options override the choice that was
1354    made or defaulted when the pattern was compiled.
1355    .sp
1356    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1357    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1358    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1359      PCRE_NEWLINE_ANYCRLF
1360    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
1361  .sp  .sp
1362  These options override the newline definition that was chosen or defaulted when  These options override the newline definition that was chosen or defaulted when
# Line 1173  the pattern was compiled. For details, s Line 1364  the pattern was compiled. For details, s
1364  \fBpcre_compile()\fP above. During matching, the newline choice affects the  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1365  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1366  the way the match position is advanced after a match failure for an unanchored  the way the match position is advanced after a match failure for an unanchored
1367  pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt  pattern.
1368  fails when the current position is at a CRLF sequence, the match position is  .P
1369  advanced by two characters instead of one, in other words, to after the CRLF.  When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
1370    match attempt for an unanchored pattern fails when the current position is at a
1371    CRLF sequence, and the pattern contains no explicit matches for CR or LF
1372    characters, the match position is advanced by two characters instead of one, in
1373    other words, to after the CRLF.
1374    .P
1375    The above rule is a compromise that makes the most common cases work as
1376    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1377    set), it does not match the string "\er\enA" because, after failing at the
1378    start, it skips both the CR and the LF before retrying. However, the pattern
1379    [\er\en]A does match that string, because it contains an explicit CR or LF
1380    reference, and so advances only by one character after the first failure.
1381    .P
1382    An explicit match for CR of LF is either a literal appearance of one of those
1383    characters, or one of the \er or \en escape sequences. Implicit matches such as
1384    [^X] do not count, nor does \es (which includes CR and LF in the characters
1385    that it matches).
1386    .P
1387    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1388    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1389  .sp  .sp
1390    PCRE_NOTBOL    PCRE_NOTBOL
1391  .sp  .sp
# Line 1201  match the empty string, the entire match Line 1411  match the empty string, the entire match
1411  .sp  .sp
1412    a?b?    a?b?
1413  .sp  .sp
1414  is applied to a string not beginning with "a" or "b", it matches the empty  is applied to a string not beginning with "a" or "b", it matches an empty
1415  string at the start of the subject. With PCRE_NOTEMPTY set, this match is not  string at the start of the subject. With PCRE_NOTEMPTY set, this match is not
1416  valid, so PCRE searches further into the string for occurrences of "a" or "b".  valid, so PCRE searches further into the string for occurrences of "a" or "b".
1417  .P  .sp
1418  Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case    PCRE_NOTEMPTY_ATSTART
1419  of a pattern match of the empty string within its \fBsplit()\fP function, and  .sp
1420  when using the /g modifier. It is possible to emulate Perl's behaviour after  This is like PCRE_NOTEMPTY, except that an empty string match that is not at
1421  matching a null string by first trying the match again at the same offset with  the start of the subject is permitted. If the pattern is anchored, such a match
1422  PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the  can occur only if the pattern contains \eK.
1423  starting offset (see below) and trying an ordinary match again. There is some  .P
1424  code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.  Perl has no direct equivalent of PCRE_NOTEMPTY or PCRE_NOTEMPTY_ATSTART, but it
1425    does make a special case of a pattern match of the empty string within its
1426    \fBsplit()\fP function, and when using the /g modifier. It is possible to
1427    emulate Perl's behaviour after matching a null string by first trying the match
1428    again at the same offset with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then
1429    if that fails, by advancing the starting offset (see below) and trying an
1430    ordinary match again. There is some code that demonstrates how to do this in
1431    the
1432    .\" HREF
1433    \fBpcredemo\fP
1434    .\"
1435    sample program.
1436    .sp
1437      PCRE_NO_START_OPTIMIZE
1438    .sp
1439    There are a number of optimizations that \fBpcre_exec()\fP uses at the start of
1440    a match, in order to speed up the process. For example, if it is known that a
1441    match must start with a specific character, it searches the subject for that
1442    character, and fails immediately if it cannot find it, without actually running
1443    the main matching function. When callouts are in use, these optimizations can
1444    cause them to be skipped. This option disables the "start-up" optimizations,
1445    causing performance to suffer, but ensuring that the callouts do occur.
1446  .sp  .sp
1447    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
1448  .sp  .sp
1449  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
1450  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1451  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
1452  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
1453  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1454  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1455    .\" </a>
1456    section on UTF-8 support
1457    .\"
1458    in the main
1459    .\" HREF
1460    \fBpcre\fP
1461    .\"
1462    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1463    the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1464    PCRE_ERROR_BADUTF8_OFFSET is returned.
1465  .P  .P
1466  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
1467  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 1232  PCRE_NO_UTF8_CHECK is set, the effect of Line 1473  PCRE_NO_UTF8_CHECK is set, the effect of
1473  subject, or a value of \fIstartoffset\fP that does not point to the start of a  subject, or a value of \fIstartoffset\fP that does not point to the start of a
1474  UTF-8 character, is undefined. Your program may crash.  UTF-8 character, is undefined. Your program may crash.
1475  .sp  .sp
1476    PCRE_PARTIAL    PCRE_PARTIAL_HARD
1477      PCRE_PARTIAL_SOFT
1478  .sp  .sp
1479  This option turns on the partial matching feature. If the subject string fails  These options turn on the partial matching feature. For backwards
1480  to match the pattern, but at some point during the matching process the end of  compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match
1481  the subject was reached (that is, the subject partially matches the pattern and  occurs if the end of the subject string is reached successfully, but there are
1482  the failure to match occurred only because there were not enough subject  not enough subject characters to complete the match. If this happens when
1483  characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of  PCRE_PARTIAL_HARD is set, \fBpcre_exec()\fP immediately returns
1484  PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what  PCRE_ERROR_PARTIAL. Otherwise, if PCRE_PARTIAL_SOFT is set, matching continues
1485  may appear in the pattern. These are discussed in the  by testing any other alternatives. Only if they all fail is PCRE_ERROR_PARTIAL
1486    returned (instead of PCRE_ERROR_NOMATCH). The portion of the string that
1487    was inspected when the partial match was found is set as the first matching
1488    string. There is a more detailed discussion in the
1489  .\" HREF  .\" HREF
1490  \fBpcrepartial\fP  \fBpcrepartial\fP
1491  .\"  .\"
# Line 1250  documentation. Line 1495  documentation.
1495  .rs  .rs
1496  .sp  .sp
1497  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
1498  \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
1499  \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
1500  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
1501  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
1502  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.
1503  .P  .P
1504  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
1505  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 1288  pattern. Following the usage in Jeffrey Line 1533  pattern. Following the usage in Jeffrey
1533  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
1534  kinds of parenthesized subpattern that do not cause substrings to be captured.  kinds of parenthesized subpattern that do not cause substrings to be captured.
1535  .P  .P
1536  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
1537  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
1538  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
1539  this argument is NOT the size of \fIovector\fP in bytes.  argument is NOT the size of \fIovector\fP in bytes.
1540  .P  .P
1541  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,
1542  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
1543  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1544  and is not available for passing back information. The length passed in  and is not available for passing back information. The number passed in
1545  \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
1546  rounded down.  rounded down.
1547  .P  .P
1548  When a match is successful, information about captured substrings is returned  When a match is successful, information about captured substrings is returned
1549  in pairs of integers, starting at the beginning of \fIovector\fP, and  in pairs of integers, starting at the beginning of \fIovector\fP, and
1550  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
1551  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
1552  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
1553  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
1554  subject string matched by the entire pattern. The next pair is used for the  mode. They are not character counts.
1555  first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP  .P
1556  is one more than the highest numbered pair that has been set. For example, if  The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the
1557  two substrings have been captured, the returned value is 3. If there are no  portion of the subject string matched by the entire pattern. The next pair is
1558  capturing subpatterns, the return value from a successful match is 1,  used for the first capturing subpattern, and so on. The value returned by
1559  indicating that just the first pair of offsets has been set.  \fBpcre_exec()\fP is one more than the highest numbered pair that has been set.
1560    For example, if two substrings have been captured, the returned value is 3. If
1561    there are no capturing subpatterns, the return value from a successful match is
1562    1, indicating that just the first pair of offsets has been set.
1563  .P  .P
1564  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
1565  string that it matched that is returned.  string that it matched that is returned.
1566  .P  .P
1567  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
1568  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
1569  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,
1570  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
1571  \fIovecsize\fP as zero. However, if the pattern contains back references and  \fIovecsize\fP as zero. However, if the pattern contains back references and
1572  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
1573  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
1574  advisable to supply an \fIovector\fP.  advisable to supply an \fIovector\fP.
1575  .P  .P
1576  The \fBpcre_info()\fP function can be used to find out how many capturing  The \fBpcre_fullinfo()\fP function can be used to find out how many capturing
1577  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
1578  \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
1579  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.
# Line 1430  documentation for details of partial mat Line 1678  documentation for details of partial mat
1678  .sp  .sp
1679    PCRE_ERROR_BADPARTIAL     (-13)    PCRE_ERROR_BADPARTIAL     (-13)
1680  .sp  .sp
1681  The PCRE_PARTIAL option was used with a compiled pattern containing items that  This code is no longer in use. It was formerly returned when the PCRE_PARTIAL
1682  are not supported for partial matching. See the  option was used with a compiled pattern containing items that were not
1683  .\" HREF  supported for partial matching. From release 8.00 onwards, there are no
1684  \fBpcrepartial\fP  restrictions on partial matching.
 .\"  
 documentation for details of partial matching.  
1685  .sp  .sp
1686    PCRE_ERROR_INTERNAL       (-14)    PCRE_ERROR_INTERNAL       (-14)
1687  .sp  .sp
# Line 1452  The internal recursion limit, as specifi Line 1698  The internal recursion limit, as specifi
1698  field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the  field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1699  description above.  description above.
1700  .sp  .sp
   PCRE_ERROR_NULLWSLIMIT    (-22)  
 .sp  
 When a group that can match an empty substring is repeated with an unbounded  
 upper limit, the subject position at the start of the group must be remembered,  
 so that a test for an empty string can be made when the end of the group is  
 reached. Some workspace is required for this; if it runs out, this error is  
 given.  
 .sp  
1701    PCRE_ERROR_BADNEWLINE     (-23)    PCRE_ERROR_BADNEWLINE     (-23)
1702  .sp  .sp
1703  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1704  .P  .P
1705  Error numbers -16 to -20 are not used by \fBpcre_exec()\fP.  Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1706  .  .
1707  .  .
1708  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1476  Error numbers -16 to -20 are not used by Line 1714  Error numbers -16 to -20 are not used by
1714  .ti +5n  .ti +5n
1715  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1716  .PP  .PP
 .br  
1717  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1718  .ti +5n  .ti +5n
1719  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1720  .ti +5n  .ti +5n
1721  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1722  .PP  .PP
 .br  
1723  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1724  .ti +5n  .ti +5n
1725  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
# Line 1569  provided. Line 1805  provided.
1805  .ti +5n  .ti +5n
1806  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1807  .PP  .PP
 .br  
1808  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1809  .ti +5n  .ti +5n
1810  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1578  provided. Line 1813  provided.
1813  .ti +5n  .ti +5n
1814  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1815  .PP  .PP
 .br  
1816  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1817  .ti +5n  .ti +5n
1818  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1614  pattern. This is needed in order to gain Line 1848  pattern. This is needed in order to gain
1848  translation table.  translation table.
1849  .P  .P
1850  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1851  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1852  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1853  .  the behaviour may not be what you want (see the next section).
1854    .P
1855    \fBWarning:\fP If the pattern uses the (?| feature to set up multiple
1856    subpatterns with the same number, as described in the
1857    .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
1858    .\" </a>
1859    section on duplicate subpattern numbers
1860    .\"
1861    in the
1862    .\" HREF
1863    \fBpcrepattern\fP
1864    .\"
1865    page, you cannot use names to distinguish the different subpatterns, because
1866    names are not included in the compiled code. The matching process uses only
1867    numbers. For this reason, the use of different names for subpatterns of the
1868    same number causes an error at compile time.
1869  .  .
1870  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
1871  .rs  .rs
# Line 1626  appropriate. Line 1875  appropriate.
1875  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
1876  .PP  .PP
1877  When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns  When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
1878  are not required to be unique. Normally, patterns with duplicate names are such  are not required to be unique. (Duplicate names are always allowed for
1879  that in any one match, only one of the named subpatterns participates. An  subpatterns with the same number, created by using the (?| feature. Indeed, if
1880  example is shown in the  such subpatterns are named, they are required to use the same names.)
1881    .P
1882    Normally, patterns with duplicate names are such that in any one match, only
1883    one of the named subpatterns participates. An example is shown in the
1884  .\" HREF  .\" HREF
1885  \fBpcrepattern\fP  \fBpcrepattern\fP
1886  .\"  .\"
1887  documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP  documentation.
1888  and \fBpcre_get_named_substring()\fP return the first substring corresponding  .P
1889  to the given name that is set. If none are set, an empty string is returned.  When duplicates are present, \fBpcre_copy_named_substring()\fP and
1890  The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are  \fBpcre_get_named_substring()\fP return the first substring corresponding to
1891  associated with the name, but it is not defined which it is.  the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
1892  .sp  returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1893    returns one of the numbers that are associated with the name, but it is not
1894    defined which it is.
1895    .P
1896  If you want to get full details of all captured substrings for a given name,  If you want to get full details of all captured substrings for a given name,
1897  you must use the \fBpcre_get_stringtable_entries()\fP function. The first  you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1898  argument is the compiled pattern, and the second is the name. The third and  argument is the compiled pattern, and the second is the name. The third and
# Line 1689  a compiled pattern, using a matching alg Line 1944  a compiled pattern, using a matching alg
1944  just once, and does not backtrack. This has different characteristics to the  just once, and does not backtrack. This has different characteristics to the
1945  normal algorithm, and is not compatible with Perl. Some of the features of PCRE  normal algorithm, and is not compatible with Perl. Some of the features of PCRE
1946  patterns are not supported. Nevertheless, there are times when this kind of  patterns are not supported. Nevertheless, there are times when this kind of
1947  matching can be useful. For a discussion of the two matching algorithms, see  matching can be useful. For a discussion of the two matching algorithms, and a
1948  the  list of features that \fBpcre_dfa_exec()\fP does not support, see the
1949  .\" HREF  .\" HREF
1950  \fBpcrematching\fP  \fBpcrematching\fP
1951  .\"  .\"
# Line 1729  Here is an example of a simple call to \ Line 1984  Here is an example of a simple call to \
1984  .sp  .sp
1985  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
1986  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1987  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
1988  PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are  PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST,
1989  the same as for \fBpcre_exec()\fP, so their description is not repeated here.  and PCRE_DFA_RESTART. All but the last four of these are exactly the same as
1990  .sp  for \fBpcre_exec()\fP, so their description is not repeated here.
1991    PCRE_PARTIAL  .sp
1992  .sp    PCRE_PARTIAL_HARD
1993  This has the same general effect as it does for \fBpcre_exec()\fP, but the    PCRE_PARTIAL_SOFT
1994  details are slightly different. When PCRE_PARTIAL is set for  .sp
1995  \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into  These have the same general effect as they do for \fBpcre_exec()\fP, but the
1996  PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no  details are slightly different. When PCRE_PARTIAL_HARD is set for
1997  complete matches, but there is still at least one matching possibility. The  \fBpcre_dfa_exec()\fP, it returns PCRE_ERROR_PARTIAL if the end of the subject
1998  portion of the string that provided the partial match is set as the first  is reached and there is still at least one matching possibility that requires
1999  matching string.  additional characters. This happens even if some complete matches have also
2000    been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH
2001    is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached,
2002    there have been no complete matches, but there is still at least one matching
2003    possibility. The portion of the string that was inspected when the longest
2004    partial match was found is set as the first matching string in both cases.
2005  .sp  .sp
2006    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
2007  .sp  .sp
# Line 1752  matching point in the subject string. Line 2012  matching point in the subject string.
2012  .sp  .sp
2013    PCRE_DFA_RESTART    PCRE_DFA_RESTART
2014  .sp  .sp
2015  When \fBpcre_dfa_exec()\fP is called with the PCRE_PARTIAL option, and returns  When \fBpcre_dfa_exec()\fP returns a partial match, it is possible to call it
2016  a partial match, it is possible to call it again, with additional subject  again, with additional subject characters, and have it continue with the same
2017  characters, and have it continue with the same match. The PCRE_DFA_RESTART  match. The PCRE_DFA_RESTART option requests this action; when it is set, the
2018  option requests this action; when it is set, the \fIworkspace\fP and  \fIworkspace\fP and \fIwscount\fP options must reference the same vector as
2019  \fIwscount\fP options must reference the same vector as before because data  before because data about the match so far is left in them after a partial
2020  about the match so far is left in them after a partial match. There is more  match. There is more discussion of this facility in the
 discussion of this facility in the  
2021  .\" HREF  .\" HREF
2022  \fBpcrepartial\fP  \fBpcrepartial\fP
2023  .\"  .\"
# Line 1846  extremely rare, as a vector of size 1000 Line 2105  extremely rare, as a vector of size 1000
2105  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
2106  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
2107  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
2108  .P  .
2109  .in 0  .
2110  Last updated: 30 November 2006  .SH AUTHOR
2111  .br  .rs
2112  Copyright (c) 1997-2006 University of Cambridge.  .sp
2113    .nf
2114    Philip Hazel
2115    University Computing Service
2116    Cambridge CB2 3QH, England.
2117    .fi
2118    .
2119    .
2120    .SH REVISION
2121    .rs
2122    .sp
2123    .nf
2124    Last updated: 16 May 2010
2125    Copyright (c) 1997-2010 University of Cambridge.
2126    .fi

Legend:
Removed from v.96  
changed lines
  Added in v.518

  ViewVC Help
Powered by ViewVC 1.1.5