/[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 93 by nigel, Sat Feb 24 21:41:42 2007 UTC revision 572 by ph10, Wed Nov 17 17:55:57 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 157  an application that uses PCRE. The heade Line 132  an application that uses PCRE. The heade
132  and PCRE_MINOR to contain the major and minor release numbers for the library.  and PCRE_MINOR to contain the major and minor release numbers for the library.
133  Applications can use these to include support for different releases of PCRE.  Applications can use these to include support for different releases of PCRE.
134  .P  .P
135    In a Windows environment, if you want to statically link an application program
136    against a non-dll \fBpcre.a\fP file, you must define PCRE_STATIC before
137    including \fBpcre.h\fP or \fBpcrecpp.h\fP, because otherwise the
138    \fBpcre_malloc()\fP and \fBpcre_free()\fP exported functions will be declared
139    \fB__declspec(dllimport)\fP, with unwanted results.
140    .P
141  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,
142  and \fBpcre_exec()\fP are used for compiling and matching regular expressions  and \fBpcre_exec()\fP are used for compiling and matching regular expressions
143  in a Perl-compatible manner. A sample program that demonstrates the simplest  in a Perl-compatible manner. A sample program that demonstrates the simplest
144  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
145  distribution. The  source distribution. A listing of this program is given in the
146    .\" HREF
147    \fBpcredemo\fP
148    .\"
149    documentation, and the
150  .\" HREF  .\" HREF
151  \fBpcresample\fP  \fBpcresample\fP
152  .\"  .\"
153  documentation describes how to run it.  documentation describes how to compile and run it.
154  .P  .P
155  A second matching function, \fBpcre_dfa_exec()\fP, which is not  A second matching function, \fBpcre_dfa_exec()\fP, which is not
156  Perl-compatible, is also provided. This uses a different algorithm for the  Perl-compatible, is also provided. This uses a different algorithm for the
157  matching. The alternative algorithm finds all possible matches (at a given  matching. The alternative algorithm finds all possible matches (at a given
158  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
159  does not return captured substrings. A description of the two matching  lookbehind assertions). However, this algorithm does not return captured
160  algorithms and their advantages and disadvantages is given in the  substrings. A description of the two matching algorithms and their advantages
161    and disadvantages is given in the
162  .\" HREF  .\" HREF
163  \fBpcrematching\fP  \fBpcrematching\fP
164  .\"  .\"
# Line 243  points during a matching operation. Deta Line 229  points during a matching operation. Deta
229  documentation.  documentation.
230  .  .
231  .  .
232    .\" HTML <a name="newlines"></a>
233  .SH NEWLINES  .SH NEWLINES
234  .rs  .rs
235  .sp  .sp
236  PCRE supports four different conventions for indicating line breaks in  PCRE supports five different conventions for indicating line breaks in
237  strings: a single CR (carriage return) character, a single LF (linefeed)  strings: a single CR (carriage return) character, a single LF (linefeed)
238  character, the two-character sequence CRLF, or any Unicode newline sequence.  character, the two-character sequence CRLF, any of the three preceding, or any
239  The Unicode newline sequences are the three just mentioned, plus the single  Unicode newline sequence. The Unicode newline sequences are the three just
240  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,
241  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
242    (paragraph separator, U+2029).
243  .P  .P
244  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
245  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 247  The default default is LF, which is the
247  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
248  matched.  matched.
249  .P  .P
250    At compile time, the newline convention can be specified by the \fIoptions\fP
251    argument of \fBpcre_compile()\fP, or it can be specified by special text at the
252    start of the pattern itself; this overrides any other settings. See the
253    .\" HREF
254    \fBpcrepattern\fP
255    .\"
256    page for details of the special character sequences.
257    .P
258  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
259  pair of characters that indicate a line break". The choice of newline  pair of characters that indicate a line break". The choice of newline
260  convention affects the handling of the dot, circumflex, and dollar  convention affects the handling of the dot, circumflex, and dollar
261  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
262  recognized line ending sequence, the match position advancement for a  recognized line ending sequence, the match position advancement for a
263  non-anchored pattern. The choice of newline convention does not affect the  non-anchored pattern. There is more detail about this in the
264  interpretation of the \en or \er escape sequences.  .\" HTML <a href="#execoptions">
265    .\" </a>
266    section on \fBpcre_exec()\fP options
267    .\"
268    below.
269    .P
270    The choice of newline convention does not affect the interpretation of
271    the \en or \er escape sequences, nor does it affect what \eR matches, which is
272    controlled in a similar way, but by separate options.
273  .  .
274  .  .
275  .SH MULTITHREADING  .SH MULTITHREADING
# Line 289  which it was compiled. Details are given Line 293  which it was compiled. Details are given
293  .\" HREF  .\" HREF
294  \fBpcreprecompile\fP  \fBpcreprecompile\fP
295  .\"  .\"
296  documentation.  documentation. However, compiling a regular expression with one version of PCRE
297    for use with a different version is not guaranteed to work and may cause
298    crashes.
299  .  .
300  .  .
301  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 322  properties is available; otherwise it is Line 328  properties is available; otherwise it is
328  .sp  .sp
329  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
330  that is recognized as meaning "newline". The four values that are supported  that is recognized as meaning "newline". The four values that are supported
331  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.
332  normally be the standard sequence for your operating system.  Though they are derived from ASCII, the same values are returned in EBCDIC
333    environments. The default should normally correspond to the standard sequence
334    for your operating system.
335    .sp
336      PCRE_CONFIG_BSR
337    .sp
338    The output is an integer whose value indicates what character sequences the \eR
339    escape sequence matches by default. A value of 0 means that \eR matches any
340    Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
341    or CRLF. The default can be overridden when a pattern is compiled or matched.
342  .sp  .sp
343    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
344  .sp  .sp
# Line 345  documentation. Line 360  documentation.
360  .sp  .sp
361    PCRE_CONFIG_MATCH_LIMIT    PCRE_CONFIG_MATCH_LIMIT
362  .sp  .sp
363  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
364  internal matching function calls in a \fBpcre_exec()\fP execution. Further  internal matching function calls in a \fBpcre_exec()\fP execution. Further
365  details are given with \fBpcre_exec()\fP below.  details are given with \fBpcre_exec()\fP below.
366  .sp  .sp
367    PCRE_CONFIG_MATCH_LIMIT_RECURSION    PCRE_CONFIG_MATCH_LIMIT_RECURSION
368  .sp  .sp
369  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
370  recursion when calling the internal matching function in a \fBpcre_exec()\fP  recursion when calling the internal matching function in a \fBpcre_exec()\fP
371  execution. Further details are given with \fBpcre_exec()\fP below.  execution. Further details are given with \fBpcre_exec()\fP below.
372  .sp  .sp
# Line 386  avoiding the use of the stack. Line 401  avoiding the use of the stack.
401  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
402  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
403  the two interfaces is that \fBpcre_compile2()\fP has an additional argument,  the two interfaces is that \fBpcre_compile2()\fP has an additional argument,
404  \fIerrorcodeptr\fP, via which a numerical error code can be returned.  \fIerrorcodeptr\fP, via which a numerical error code can be returned. To avoid
405    too much repetition, we refer just to \fBpcre_compile()\fP below, but the
406    information applies equally to \fBpcre_compile2()\fP.
407  .P  .P
408  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
409  \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 419  argument, which is an address (see below
419  .P  .P
420  The \fIoptions\fP argument contains various bit settings that affect the  The \fIoptions\fP argument contains various bit settings that affect the
421  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
422  options are described below. Some of them, in particular, those that are  options are described below. Some of them (in particular, those that are
423  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
424  the detailed description in the  within the pattern (see the detailed description in the
425  .\" HREF  .\" HREF
426  \fBpcrepattern\fP  \fBpcrepattern\fP
427  .\"  .\"
428  documentation). For these options, the contents of the \fIoptions\fP argument  documentation). For those options that can be different in different parts of
429  specifies their initial settings at the start of compilation and execution. The  the pattern, the contents of the \fIoptions\fP argument specifies their
430  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,
431  matching as well as at compile time.  PCRE_BSR_\fIxxx\fP, and PCRE_NEWLINE_\fIxxx\fP options can be set at the time
432    of matching as well as at compile time.
433  .P  .P
434  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
435  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
436  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
437  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
438  not try to free it. The offset from the start of the pattern to the character  not try to free it. The offset from the start of the pattern to the byte that
439  where the error was discovered is placed in the variable pointed to by  was being processed when the error was discovered is placed in the variable
440  \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.  pointed to by \fIerroffset\fP, which must not be NULL. If it is, an immediate
441    error is given. Some errors are not detected until checks are carried out when
442    the whole pattern has been scanned; in this case the offset is set to the end
443    of the pattern.
444    .P
445    Note that the offset is in bytes, not characters, even in UTF-8 mode. It may
446    point into the middle of a UTF-8 character (for example, when
447    PCRE_ERROR_BADUTF8 is returned for an invalid UTF-8 string).
448  .P  .P
449  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
450  \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 491  facility, see the
491  .\"  .\"
492  documentation.  documentation.
493  .sp  .sp
494      PCRE_BSR_ANYCRLF
495      PCRE_BSR_UNICODE
496    .sp
497    These options (which are mutually exclusive) control what the \eR escape
498    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
499    match any Unicode newline sequence. The default is specified when PCRE is
500    built. It can be overridden from within the pattern, or by setting an option
501    when a compiled pattern is matched.
502    .sp
503    PCRE_CASELESS    PCRE_CASELESS
504  .sp  .sp
505  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 489  pattern. Line 523  pattern.
523  .sp  .sp
524    PCRE_DOTALL    PCRE_DOTALL
525  .sp  .sp
526  If this bit is set, a dot metacharater in the pattern matches all characters,  If this bit is set, a dot metacharacter in the pattern matches a character of
527  including those that indicate newline. Without it, a dot does not match when  any value, including one that indicates a newline. However, it only ever
528  the current position is at a newline. This option is equivalent to Perl's /s  matches one character, even if newlines are coded as CRLF. Without this option,
529  option, and it can be changed within a pattern by a (?s) option setting. A  a dot does not match when the current position is at a newline. This option is
530  negative class such as [^a] always matches newline characters, independent of  equivalent to Perl's /s option, and it can be changed within a pattern by a
531  the setting of this option.  (?s) option setting. A negative class such as [^a] always matches newline
532    characters, independent of the setting of this option.
533  .sp  .sp
534    PCRE_DUPNAMES    PCRE_DUPNAMES
535  .sp  .sp
# Line 516  unescaped # outside a character class an Line 551  unescaped # outside a character class an
551  ignored. This is equivalent to Perl's /x option, and it can be changed within a  ignored. This is equivalent to Perl's /x option, and it can be changed within a
552  pattern by a (?x) option setting.  pattern by a (?x) option setting.
553  .P  .P
554    Which characters are interpreted as newlines
555    is controlled by the options passed to \fBpcre_compile()\fP or by a special
556    sequence at the start of the pattern, as described in the section entitled
557    .\" HTML <a href="pcrepattern.html#newlines">
558    .\" </a>
559    "Newline conventions"
560    .\"
561    in the \fBpcrepattern\fP documentation. Note that the end of this type of
562    comment is a literal newline sequence in the pattern; escape sequences that
563    happen to represent a newline do not count.
564    .P
565  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
566  Note, however, that this applies only to data characters. Whitespace characters  Note, however, that this applies only to data characters. Whitespace characters
567  may never appear within special character sequences in a pattern, for example  may never appear within special character sequences in a pattern, for example
568  within the sequence (?( which introduces a conditional subpattern.  within the sequence (?( that introduces a conditional subpattern.
569  .sp  .sp
570    PCRE_EXTRA    PCRE_EXTRA
571  .sp  .sp
# Line 529  set, any backslash in a pattern that is Line 575  set, any backslash in a pattern that is
575  special meaning causes an error, thus reserving these combinations for future  special meaning causes an error, thus reserving these combinations for future
576  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
577  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
578  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
579  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)
580    option setting within a pattern.
581  .sp  .sp
582    PCRE_FIRSTLINE    PCRE_FIRSTLINE
583  .sp  .sp
# Line 538  If this option is set, an unanchored pat Line 585  If this option is set, an unanchored pat
585  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
586  over the newline.  over the newline.
587  .sp  .sp
588      PCRE_JAVASCRIPT_COMPAT
589    .sp
590    If this option is set, PCRE's behaviour is changed in some ways so that it is
591    compatible with JavaScript rather than Perl. The changes are as follows:
592    .P
593    (1) A lone closing square bracket in a pattern causes a compile-time error,
594    because this is illegal in JavaScript (by default it is treated as a data
595    character). Thus, the pattern AB]CD becomes illegal when this option is set.
596    .P
597    (2) At run time, a back reference to an unset subpattern group matches an empty
598    string (by default this causes the current matching alternative to fail). A
599    pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
600    an "a" in the subject), whereas it fails by default, for Perl compatibility.
601    .sp
602    PCRE_MULTILINE    PCRE_MULTILINE
603  .sp  .sp
604  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 618  occurrences of ^ or $ in a pattern, sett
618    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
619    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
620    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
621      PCRE_NEWLINE_ANYCRLF
622    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
623  .sp  .sp
624  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
625  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
626  indicated by a single character (CR or LF, respectively). Setting  indicated by a single character (CR or LF, respectively). Setting
627  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
628  CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
629  sequence should be recognized. The Unicode newline sequences are the three just  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
630  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,  that any Unicode newline sequence should be recognized. The Unicode newline
631  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
632  (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
633    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
634    recognized only in UTF-8 mode.
635  .P  .P
636  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
637  as a number, giving eight possibilities. Currently only five are used (default  as a number, giving eight possibilities. Currently only six are used (default
638  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
639  option, the combination may or may not be sensible. For example,  option, the combination may or may not be sensible. For example,
640  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
641  other combinations yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
642  .P  .P
643  The only time that a line break is specially recognized when compiling a  The only time that a line break in a pattern is specially recognized when
644  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character  compiling is when PCRE_EXTENDED is set. CR and LF are whitespace characters,
645  class is encountered. This indicates a comment that lasts until after the next  and so are ignored in this mode. Also, an unescaped # outside a character class
646  line break sequence. In other circumstances, line break sequences are treated  indicates a comment that lasts until after the next line break sequence. In
647  as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated  other circumstances, line break sequences in patterns are treated as literal
648  as whitespace characters and are therefore ignored.  data.
649  .P  .P
650  The newline option that is set at compile time becomes the default that is used  The newline option that is set at compile time becomes the default that is used
651  for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.  for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
# Line 594  were followed by ?: but named parenthese Line 658  were followed by ?: but named parenthese
658  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
659  in Perl.  in Perl.
660  .sp  .sp
661      PCRE_UCP
662    .sp
663    This option changes the way PCRE processes \eB, \eb, \eD, \ed, \eS, \es, \eW,
664    \ew, and some of the POSIX character classes. By default, only ASCII characters
665    are recognized, but if PCRE_UCP is set, Unicode properties are used instead to
666    classify characters. More details are given in the section on
667    .\" HTML <a href="pcre.html#genericchartypes">
668    .\" </a>
669    generic character types
670    .\"
671    in the
672    .\" HREF
673    \fBpcrepattern\fP
674    .\"
675    page. If you set PCRE_UCP, matching one of the items it affects takes much
676    longer. The option is available only if PCRE has been compiled with Unicode
677    property support.
678    .sp
679    PCRE_UNGREEDY    PCRE_UNGREEDY
680  .sp  .sp
681  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 702  page.
702    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
703  .sp  .sp
704  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
705  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
706  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
707  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
708  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
709  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
710  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
711  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
712  strings.  \fBpcre\fP
713    .\"
714    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
715    returns an error. If you already know that your pattern is valid, and you want
716    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
717    option. When it is set, the effect of passing an invalid UTF-8 string as a
718    pattern is undefined. It may cause your program to crash. Note that this option
719    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
720    the UTF-8 validity checking of subject strings.
721  .  .
722  .  .
723  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 650  out of use. To avoid confusion, they hav Line 740  out of use. To avoid confusion, they hav
740     9  nothing to repeat     9  nothing to repeat
741    10  [this code is not in use]    10  [this code is not in use]
742    11  internal error: unexpected repeat    11  internal error: unexpected repeat
743    12  unrecognized character after (?    12  unrecognized character after (? or (?-
744    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
745    14  missing )    14  missing )
746    15  reference to non-existent subpattern    15  reference to non-existent subpattern
# Line 658  out of use. To avoid confusion, they hav Line 748  out of use. To avoid confusion, they hav
748    17  unknown option bit(s) set    17  unknown option bit(s) set
749    18  missing ) after comment    18  missing ) after comment
750    19  [this code is not in use]    19  [this code is not in use]
751    20  regular expression too large    20  regular expression is too large
752    21  failed to get memory    21  failed to get memory
753    22  unmatched parentheses    22  unmatched parentheses
754    23  internal error: code overflow    23  internal error: code overflow
# Line 667  out of use. To avoid confusion, they hav Line 757  out of use. To avoid confusion, they hav
757    26  malformed number or name after (?(    26  malformed number or name after (?(
758    27  conditional group contains more than two branches    27  conditional group contains more than two branches
759    28  assertion expected after (?(    28  assertion expected after (?(
760    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
761    30  unknown POSIX class name    30  unknown POSIX class name
762    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
763    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 777  out of use. To avoid confusion, they hav
777    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
778    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
779    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
780    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10000)
781    50  repeated subpattern is too long    50  [this code is not in use]
782    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
783    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
784    53  internal error: previously-checked referenced subpattern not found    53  internal error: previously-checked referenced subpattern
785            not found
786    54  DEFINE group contains more than one branch    54  DEFINE group contains more than one branch
787    55  repeating a DEFINE group is not allowed    55  repeating a DEFINE group is not allowed
788    56  inconsistent NEWLINE options"    56  inconsistent NEWLINE options
789      57  \eg is not followed by a braced, angle-bracketed, or quoted
790            name/number or by a plain number
791      58  a numbered reference must not be zero
792      59  an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
793      60  (*VERB) not recognized
794      61  number is too big
795      62  subpattern name expected
796      63  digit expected after (?+
797      64  ] is an invalid data character in JavaScript compatibility mode
798      65  different names for subpatterns of the same number are
799            not allowed
800      66  (*MARK) must have an argument
801      67  this version of PCRE is not compiled with PCRE_UCP support
802    .sp
803    The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
804    be used if the limits were changed when PCRE was built.
805  .  .
806  .  .
807  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 713  help speed up matching, \fBpcre_study()\ Line 820  help speed up matching, \fBpcre_study()\
820  results of the study.  results of the study.
821  .P  .P
822  The returned value from \fBpcre_study()\fP can be passed directly to  The returned value from \fBpcre_study()\fP can be passed directly to
823  \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
824  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
825  described  passed; these are described
826  .\" HTML <a href="#extradata">  .\" HTML <a href="#extradata">
827  .\" </a>  .\" </a>
828  below  below
829  .\"  .\"
830  in the section on matching a pattern.  in the section on matching a pattern.
831  .P  .P
832  If studying the pattern does not produce any additional information  If studying the pattern does not produce any useful information,
833  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program
834  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
835  own \fBpcre_extra\fP block.  \fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block.
836  .P  .P
837  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
838  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 852  This is a typical call to \fBpcre_study\
852      0,              /* no options exist */      0,              /* no options exist */
853      &error);        /* set to NULL or points to a message */      &error);        /* set to NULL or points to a message */
854  .sp  .sp
855  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
856  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
857  bytes is created.  mean that there are any strings of that length that match, but it does
858    guarantee that no shorter strings match. The value is used by
859    \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP to avoid wasting time by trying to
860    match strings that are shorter than the lower bound. You can find out the value
861    in a calling program via the \fBpcre_fullinfo()\fP function.
862    .P
863    Studying a pattern is also useful for non-anchored patterns that do not have a
864    single fixed starting character. A bitmap of possible starting bytes is
865    created. This speeds up finding a position in the subject at which to start
866    matching.
867    .P
868    The two optimizations just described can be disabled by setting the
869    PCRE_NO_START_OPTIMIZE option when calling \fBpcre_exec()\fP or
870    \fBpcre_dfa_exec()\fP. You might want to do this if your pattern contains
871    callouts or (*MARK), and you want to make use of these facilities in cases
872    where matching fails. See the discussion of PCRE_NO_START_OPTIMIZE
873    .\" HTML <a href="#execoptions">
874    .\" </a>
875    below.
876    .\"
877  .  .
878  .  .
879  .\" HTML <a name="localesupport"></a>  .\" HTML <a name="localesupport"></a>
880  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
881  .rs  .rs
882  .sp  .sp
883  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
884  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
885  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
886  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
887  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
888  support. The use of locales with Unicode is discouraged.  property support. Alternatively, the PCRE_UCP option can be set at compile
889  .P  time; this causes \ew and friends to use Unicode property support instead of
890  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
891  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
892  and is sufficient for many applications. An alternative set of tables can,  and Unicode, or use locales, but not try to mix the two.
893  however, be supplied. These may be created in a different locale from the  .P
894  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
895  this locale support is expected to die away.  of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
896    Normally, the internal tables recognize only ASCII characters. However, when
897    PCRE is built, it is possible to cause the internal tables to be rebuilt in the
898    default "C" locale of the local system, which may cause them to be different.
899    .P
900    The internal tables can always be overridden by tables supplied by the
901    application that calls PCRE. These may be created in a different locale from
902    the default. As more and more applications change to using Unicode, the need
903    for this locale support is expected to die away.
904  .P  .P
905  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
906  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 913  the following code could be used:
913    tables = pcre_maketables();    tables = pcre_maketables();
914    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
915  .sp  .sp
916    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
917    are using Windows, the name for the French locale is "french".
918    .P
919  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
920  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
921  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 1018  table indicating a fixed set of bytes fo
1018  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
1019  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
1020  .sp  .sp
1021      PCRE_INFO_HASCRORLF
1022    .sp
1023    Return 1 if the pattern contains any explicit matches for CR or LF characters,
1024    otherwise 0. The fourth argument should point to an \fBint\fP variable. An
1025    explicit match is either a literal CR or LF character, or \er or \en.
1026    .sp
1027      PCRE_INFO_JCHANGED
1028    .sp
1029    Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
1030    0. The fourth argument should point to an \fBint\fP variable. (?J) and
1031    (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
1032    .sp
1033    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
1034  .sp  .sp
1035  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 1040  follows something of variable length. Fo
1040  /^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
1041  is -1.  is -1.
1042  .sp  .sp
1043      PCRE_INFO_MINLENGTH
1044    .sp
1045    If the pattern was studied and a minimum length for matching subject strings
1046    was computed, its value is returned. Otherwise the returned value is -1. The
1047    value is a number of characters, not bytes (this may be relevant in UTF-8
1048    mode). The fourth argument should point to an \fBint\fP variable. A
1049    non-negative value is a lower bound to the length of any matching string. There
1050    may not be any strings of that length that do actually match, but every string
1051    that does match is at least that long.
1052    .sp
1053    PCRE_INFO_NAMECOUNT    PCRE_INFO_NAMECOUNT
1054    PCRE_INFO_NAMEENTRYSIZE    PCRE_INFO_NAMEENTRYSIZE
1055    PCRE_INFO_NAMETABLE    PCRE_INFO_NAMETABLE
# Line 911  entry; both of these return an \fBint\fP Line 1070  entry; both of these return an \fBint\fP
1070  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
1071  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
1072  are the number of the capturing parenthesis, most significant byte first. The  are the number of the capturing parenthesis, most significant byte first. The
1073  rest of the entry is the corresponding name, zero terminated. The names are in  rest of the entry is the corresponding name, zero terminated.
1074  alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of  .P
1075  their parentheses numbers. For example, consider the following pattern (assume  The names are in alphabetical order. Duplicate names may appear if (?| is used
1076  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  to create multiple groups with the same number, as described in the
1077    .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
1078    .\" </a>
1079    section on duplicate subpattern numbers
1080    .\"
1081    in the
1082    .\" HREF
1083    \fBpcrepattern\fP
1084    .\"
1085    page. Duplicate names for subpatterns with different numbers are permitted only
1086    if PCRE_DUPNAMES is set. In all cases of duplicate names, they appear in the
1087    table in the order in which they were found in the pattern. In the absence of
1088    (?| this is the order of increasing number; when (?| is used this is not
1089    necessarily the case because later subpatterns may have lower numbers.
1090    .P
1091    As a simple example of the name/number table, consider the following pattern
1092    (assume PCRE_EXTENDED is set, so white space - including newlines - is
1093    ignored):
1094  .sp  .sp
1095  .\" JOIN  .\" JOIN
1096    (?<date> (?<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
# Line 933  When writing code to extract data from n Line 1109  When writing code to extract data from n
1109  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
1110  different for each compiled pattern.  different for each compiled pattern.
1111  .sp  .sp
1112      PCRE_INFO_OKPARTIAL
1113    .sp
1114    Return 1 if the pattern can be used for partial matching with
1115    \fBpcre_exec()\fP, otherwise 0. The fourth argument should point to an
1116    \fBint\fP variable. From release 8.00, this always returns 1, because the
1117    restrictions that previously applied to partial matching have been lifted. The
1118    .\" HREF
1119    \fBpcrepartial\fP
1120    .\"
1121    documentation gives details of partial matching.
1122    .sp
1123    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
1124  .sp  .sp
1125  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
1126  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
1127  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
1128  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
1129    they are the options that will be in force when matching starts. For example,
1130    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1131    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
1132  .P  .P
1133  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
1134  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 965  variable. Line 1155  variable.
1155  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
1156  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
1157  \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
1158  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
1159    study data, zero is returned. The fourth argument should point to a
1160  \fBsize_t\fP variable.  \fBsize_t\fP variable.
1161  .  .
1162  .  .
# Line 1027  is different. (This seems a highly unlik Line 1218  is different. (This seems a highly unlik
1218  .P  .P
1219  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
1220  compiled pattern, which is passed in the \fIcode\fP argument. If the  compiled pattern, which is passed in the \fIcode\fP argument. If the
1221  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
1222  \fIextra\fP argument. This function is the main matching facility of the  \fIextra\fP argument. This function is the main matching facility of the
1223  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
1224  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 1268  fields (not necessarily in this order):
1268    unsigned long int \fImatch_limit_recursion\fP;    unsigned long int \fImatch_limit_recursion\fP;
1269    void *\fIcallout_data\fP;    void *\fIcallout_data\fP;
1270    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1271      unsigned char **\fImark\fP;
1272  .sp  .sp
1273  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
1274  are set. The flag bits are:  are set. The flag bits are:
# Line 1086  are set. The flag bits are: Line 1278  are set. The flag bits are:
1278    PCRE_EXTRA_MATCH_LIMIT_RECURSION    PCRE_EXTRA_MATCH_LIMIT_RECURSION
1279    PCRE_EXTRA_CALLOUT_DATA    PCRE_EXTRA_CALLOUT_DATA
1280    PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
1281      PCRE_EXTRA_MARK
1282  .sp  .sp
1283  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
1284  \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 1288  the block by setting the other fields an
1288  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
1289  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,
1290  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
1291  classic example is the use of nested unlimited repeats.  classic example is a pattern that uses nested unlimited repeats.
1292  .P  .P
1293  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly
1294  (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 1321  with a \fBpcre_extra\fP block in which \
1321  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
1322  is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.  is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1323  .P  .P
1324  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,
1325  which is described in the  and is described in the
1326  .\" HREF  .\" HREF
1327  \fBpcrecallout\fP  \fBpcrecallout\fP
1328  .\"  .\"
# Line 1148  called. See the Line 1341  called. See the
1341  \fBpcreprecompile\fP  \fBpcreprecompile\fP
1342  .\"  .\"
1343  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1344    .P
1345    If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must
1346    be set to point to a \fBchar *\fP variable. If the pattern contains any
1347    backtracking control verbs such as (*MARK:NAME), and the execution ends up with
1348    a name to pass back, a pointer to the name string (zero terminated) is placed
1349    in the variable pointed to by the \fImark\fP field. The names are within the
1350    compiled pattern; if you wish to retain such a name you must copy it before
1351    freeing the memory of a compiled pattern. If there is no name to pass back, the
1352    variable pointed to by the \fImark\fP field set to NULL. For details of the
1353    backtracking control verbs, see the section entitled
1354    .\" HTML <a href="pcrepattern#backtrackcontrol">
1355    .\" </a>
1356    "Backtracking control"
1357    .\"
1358    in the
1359    .\" HREF
1360    \fBpcrepattern\fP
1361    .\"
1362    documentation.
1363    .
1364  .  .
1365    .\" HTML <a name="execoptions"></a>
1366  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1367  .rs  .rs
1368  .sp  .sp
1369  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
1370  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,
1371  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
1372    PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and
1373    PCRE_PARTIAL_HARD.
1374  .sp  .sp
1375    PCRE_ANCHORED    PCRE_ANCHORED
1376  .sp  .sp
# Line 1163  matching position. If a pattern was comp Line 1379  matching position. If a pattern was comp
1379  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
1380  matching time.  matching time.
1381  .sp  .sp
1382      PCRE_BSR_ANYCRLF
1383      PCRE_BSR_UNICODE
1384    .sp
1385    These options (which are mutually exclusive) control what the \eR escape
1386    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1387    match any Unicode newline sequence. These options override the choice that was
1388    made or defaulted when the pattern was compiled.
1389    .sp
1390    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1391    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1392    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1393      PCRE_NEWLINE_ANYCRLF
1394    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
1395  .sp  .sp
1396  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 1398  the pattern was compiled. For details, s
1398  \fBpcre_compile()\fP above. During matching, the newline choice affects the  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1399  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1400  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
1401  pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt  pattern.
1402  fails when the current position is at a CRLF sequence, the match position is  .P
1403  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
1404    match attempt for an unanchored pattern fails when the current position is at a
1405    CRLF sequence, and the pattern contains no explicit matches for CR or LF
1406    characters, the match position is advanced by two characters instead of one, in
1407    other words, to after the CRLF.
1408    .P
1409    The above rule is a compromise that makes the most common cases work as
1410    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1411    set), it does not match the string "\er\enA" because, after failing at the
1412    start, it skips both the CR and the LF before retrying. However, the pattern
1413    [\er\en]A does match that string, because it contains an explicit CR or LF
1414    reference, and so advances only by one character after the first failure.
1415    .P
1416    An explicit match for CR of LF is either a literal appearance of one of those
1417    characters, or one of the \er or \en escape sequences. Implicit matches such as
1418    [^X] do not count, nor does \es (which includes CR and LF in the characters
1419    that it matches).
1420    .P
1421    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1422    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1423  .sp  .sp
1424    PCRE_NOTBOL    PCRE_NOTBOL
1425  .sp  .sp
# Line 1201  match the empty string, the entire match Line 1445  match the empty string, the entire match
1445  .sp  .sp
1446    a?b?    a?b?
1447  .sp  .sp
1448  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
1449  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
1450  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".
1451  .P  .sp
1452  Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case    PCRE_NOTEMPTY_ATSTART
1453  of a pattern match of the empty string within its \fBsplit()\fP function, and  .sp
1454  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
1455  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
1456  PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the  can occur only if the pattern contains \eK.
1457  starting offset (see below) and trying an ordinary match again. There is some  .P
1458  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
1459    does make a special case of a pattern match of the empty string within its
1460    \fBsplit()\fP function, and when using the /g modifier. It is possible to
1461    emulate Perl's behaviour after matching a null string by first trying the match
1462    again at the same offset with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then
1463    if that fails, by advancing the starting offset (see below) and trying an
1464    ordinary match again. There is some code that demonstrates how to do this in
1465    the
1466    .\" HREF
1467    \fBpcredemo\fP
1468    .\"
1469    sample program. In the most general case, you have to check to see if the
1470    newline convention recognizes CRLF as a newline, and if so, and the current
1471    character is CR followed by LF, advance the starting offset by two characters
1472    instead of one.
1473    .sp
1474      PCRE_NO_START_OPTIMIZE
1475    .sp
1476    There are a number of optimizations that \fBpcre_exec()\fP uses at the start of
1477    a match, in order to speed up the process. For example, if it is known that an
1478    unanchored match must start with a specific character, it searches the subject
1479    for that character, and fails immediately if it cannot find it, without
1480    actually running the main matching function. This means that a special item
1481    such as (*COMMIT) at the start of a pattern is not considered until after a
1482    suitable starting point for the match has been found. When callouts or (*MARK)
1483    items are in use, these "start-up" optimizations can cause them to be skipped
1484    if the pattern is never actually used. The start-up optimizations are in effect
1485    a pre-scan of the subject that takes place before the pattern is run.
1486    .P
1487    The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly
1488    causing performance to suffer, but ensuring that in cases where the result is
1489    "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)
1490    are considered at every possible starting position in the subject string.
1491    Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.
1492    Consider the pattern
1493    .sp
1494      (*COMMIT)ABC
1495    .sp
1496    When this is compiled, PCRE records the fact that a match must start with the
1497    character "A". Suppose the subject string is "DEFABC". The start-up
1498    optimization scans along the subject, finds "A" and runs the first match
1499    attempt from there. The (*COMMIT) item means that the pattern must match the
1500    current starting position, which in this case, it does. However, if the same
1501    match is run with PCRE_NO_START_OPTIMIZE set, the initial scan along the
1502    subject string does not happen. The first match attempt is run starting from
1503    "D" and when this fails, (*COMMIT) prevents any further matches being tried, so
1504    the overall result is "no match". If the pattern is studied, more start-up
1505    optimizations may be used. For example, a minimum length for the subject may be
1506    recorded. Consider the pattern
1507    .sp
1508      (*MARK:A)(X|Y)
1509    .sp
1510    The minimum length for a match is one character. If the subject is "ABC", there
1511    will be attempts to match "ABC", "BC", "C", and then finally an empty string.
1512    If the pattern is studied, the final attempt does not take place, because PCRE
1513    knows that the subject is too short, and so the (*MARK) is never encountered.
1514    In this case, studying the pattern does not affect the overall match result,
1515    which is still "no match", but it does affect the auxiliary information that is
1516    returned.
1517  .sp  .sp
1518    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
1519  .sp  .sp
1520  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
1521  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1522  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
1523  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
1524  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1525  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1526    .\" </a>
1527    section on UTF-8 support
1528    .\"
1529    in the main
1530    .\" HREF
1531    \fBpcre\fP
1532    .\"
1533    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1534    the error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is
1535    a truncated UTF-8 character at the end of the subject, PCRE_ERROR_SHORTUTF8. If
1536    \fIstartoffset\fP contains a value that does not point to the start of a UTF-8
1537    character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is
1538    returned.
1539  .P  .P
1540  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
1541  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
1542  calling \fBpcre_exec()\fP. You might want to do this for the second and  calling \fBpcre_exec()\fP. You might want to do this for the second and
1543  subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find  subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find
1544  all the matches in a single subject string. However, you should be sure that  all the matches in a single subject string. However, you should be sure that
1545  the value of \fIstartoffset\fP points to the start of a UTF-8 character. When  the value of \fIstartoffset\fP points to the start of a UTF-8 character (or the
1546  PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a  end of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an
1547  subject, or a value of \fIstartoffset\fP that does not point to the start of a  invalid UTF-8 string as a subject or an invalid value of \fIstartoffset\fP is
1548  UTF-8 character, is undefined. Your program may crash.  undefined. Your program may crash.
1549  .sp  .sp
1550    PCRE_PARTIAL    PCRE_PARTIAL_HARD
1551  .sp    PCRE_PARTIAL_SOFT
1552  This option turns on the partial matching feature. If the subject string fails  .sp
1553  to match the pattern, but at some point during the matching process the end of  These options turn on the partial matching feature. For backwards
1554  the subject was reached (that is, the subject partially matches the pattern and  compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match
1555  the failure to match occurred only because there were not enough subject  occurs if the end of the subject string is reached successfully, but there are
1556  characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of  not enough subject characters to complete the match. If this happens when
1557  PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what  PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, matching continues by
1558  may appear in the pattern. These are discussed in the  testing any remaining alternatives. Only if no complete match can be found is
1559    PCRE_ERROR_PARTIAL returned instead of PCRE_ERROR_NOMATCH. In other words,
1560    PCRE_PARTIAL_SOFT says that the caller is prepared to handle a partial match,
1561    but only if no complete match can be found.
1562    .P
1563    If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a
1564    partial match is found, \fBpcre_exec()\fP immediately returns
1565    PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words,
1566    when PCRE_PARTIAL_HARD is set, a partial match is considered to be more
1567    important that an alternative complete match.
1568    .P
1569    In both cases, the portion of the string that was inspected when the partial
1570    match was found is set as the first matching string. There is a more detailed
1571    discussion of partial and multi-segment matching, with examples, in the
1572  .\" HREF  .\" HREF
1573  \fBpcrepartial\fP  \fBpcrepartial\fP
1574  .\"  .\"
1575  documentation.  documentation.
1576  .  .
1577    .
1578  .SS "The string to be matched by \fBpcre_exec()\fP"  .SS "The string to be matched by \fBpcre_exec()\fP"
1579  .rs  .rs
1580  .sp  .sp
1581  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
1582  \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
1583  \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a  in \fIstartoffset\fP. If this is negative or greater than the length of the
1584  UTF-8 character. Unlike the pattern string, the subject may contain binary zero  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting
1585  bytes. When the starting offset is zero, the search for a match starts at the  offset is zero, the search for a match starts at the beginning of the subject,
1586  beginning of the subject, and this is by far the most common case.  and this is by far the most common case. In UTF-8 mode, the byte offset must
1587    point to the start of a UTF-8 character (or the end of the subject). Unlike the
1588    pattern string, the subject may contain binary zero bytes.
1589  .P  .P
1590  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
1591  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 1274  start of the subject, which is deemed to Line 1605  start of the subject, which is deemed to
1605  set to 4, it finds the second occurrence of "iss" because it is able to look  set to 4, it finds the second occurrence of "iss" because it is able to look
1606  behind the starting point to discover that it is preceded by a letter.  behind the starting point to discover that it is preceded by a letter.
1607  .P  .P
1608    Finding all the matches in a subject is tricky when the pattern can match an
1609    empty string. It is possible to emulate Perl's /g behaviour by first trying the
1610    match again at the same offset, with the PCRE_NOTEMPTY_ATSTART and
1611    PCRE_ANCHORED options, and then if that fails, advancing the starting offset
1612    and trying an ordinary match again. There is some code that demonstrates how to
1613    do this in the
1614    .\" HREF
1615    \fBpcredemo\fP
1616    .\"
1617    sample program. In the most general case, you have to check to see if the
1618    newline convention recognizes CRLF as a newline, and if so, and the current
1619    character is CR followed by LF, advance the starting offset by two characters
1620    instead of one.
1621    .P
1622  If a non-zero starting offset is passed when the pattern is anchored, one  If a non-zero starting offset is passed when the pattern is anchored, one
1623  attempt to match at the given offset is made. This can only succeed if the  attempt to match at the given offset is made. This can only succeed if the
1624  pattern does not require the match to be at the start of the subject.  pattern does not require the match to be at the start of the subject.
1625  .  .
1626    .
1627  .SS "How \fBpcre_exec()\fP returns captured substrings"  .SS "How \fBpcre_exec()\fP returns captured substrings"
1628  .rs  .rs
1629  .sp  .sp
# Line 1288  pattern. Following the usage in Jeffrey Line 1634  pattern. Following the usage in Jeffrey
1634  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
1635  kinds of parenthesized subpattern that do not cause substrings to be captured.  kinds of parenthesized subpattern that do not cause substrings to be captured.
1636  .P  .P
1637  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
1638  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
1639  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
1640  this argument is NOT the size of \fIovector\fP in bytes.  argument is NOT the size of \fIovector\fP in bytes.
1641  .P  .P
1642  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,
1643  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
1644  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1645  and is not available for passing back information. The length passed in  and is not available for passing back information. The number passed in
1646  \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
1647  rounded down.  rounded down.
1648  .P  .P
1649  When a match is successful, information about captured substrings is returned  When a match is successful, information about captured substrings is returned
1650  in pairs of integers, starting at the beginning of \fIovector\fP, and  in pairs of integers, starting at the beginning of \fIovector\fP, and
1651  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
1652  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
1653  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
1654  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
1655  subject string matched by the entire pattern. The next pair is used for the  mode. They are not character counts.
1656  first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP  .P
1657  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
1658  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
1659  capturing subpatterns, the return value from a successful match is 1,  used for the first capturing subpattern, and so on. The value returned by
1660  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.
1661    For example, if two substrings have been captured, the returned value is 3. If
1662    there are no capturing subpatterns, the return value from a successful match is
1663    1, indicating that just the first pair of offsets has been set.
1664  .P  .P
1665  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
1666  string that it matched that is returned.  string that it matched that is returned.
1667  .P  .P
1668  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
1669  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
1670  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,
1671  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
1672  \fIovecsize\fP as zero. However, if the pattern contains back references and  \fIovecsize\fP as zero. However, if the pattern contains back references and
1673  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
1674  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
1675  advisable to supply an \fIovector\fP.  advisable to supply an \fIovector\fP.
1676  .P  .P
1677  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
1678  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
1679  \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
1680  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 1341  Offset values that correspond to unused Line 1690  Offset values that correspond to unused
1690  expression are also set to -1. For example, if the string "abc" is matched  expression are also set to -1. For example, if the string "abc" is matched
1691  against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The  against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1692  return from the function is 2, because the highest used capturing subpattern  return from the function is 2, because the highest used capturing subpattern
1693  number is 1. However, you can refer to the offsets for the second and third  number is 1, and the offsets for for the second and third capturing subpatterns
1694  capturing subpatterns if you wish (assuming the vector is large enough, of  (assuming the vector is large enough, of course) are set to -1.
1695  course).  .P
1696    \fBNote\fP: Elements of \fIovector\fP that do not correspond to capturing
1697    parentheses in the pattern are never changed. That is, if a pattern contains
1698    \fIn\fP capturing parentheses, no more than \fIovector[0]\fP to
1699    \fIovector[2n+1]\fP are set by \fBpcre_exec()\fP. The other elements retain
1700    whatever values they previously had.
1701  .P  .P
1702  Some convenience functions are provided for extracting the captured substrings  Some convenience functions are provided for extracting the captured substrings
1703  as separate strings. These are described below.  as separate strings. These are described below.
# Line 1389  If a pattern contains back references, b Line 1743  If a pattern contains back references, b
1743  gets a block of memory at the start of matching to use for this purpose. If the  gets a block of memory at the start of matching to use for this purpose. If the
1744  call via \fBpcre_malloc()\fP fails, this error is given. The memory is  call via \fBpcre_malloc()\fP fails, this error is given. The memory is
1745  automatically freed at the end of matching.  automatically freed at the end of matching.
1746    .P
1747    This error is also given if \fBpcre_stack_malloc()\fP fails in
1748    \fBpcre_exec()\fP. This can happen only when PCRE has been compiled with
1749    \fB--disable-stack-for-recursion\fP.
1750  .sp  .sp
1751    PCRE_ERROR_NOSUBSTRING    (-7)    PCRE_ERROR_NOSUBSTRING    (-7)
1752  .sp  .sp
# Line 1414  documentation for details. Line 1772  documentation for details.
1772    PCRE_ERROR_BADUTF8        (-10)    PCRE_ERROR_BADUTF8        (-10)
1773  .sp  .sp
1774  A string that contains an invalid UTF-8 byte sequence was passed as a subject.  A string that contains an invalid UTF-8 byte sequence was passed as a subject.
1775    However, if PCRE_PARTIAL_HARD is set and the problem is a truncated UTF-8
1776    character at the end of the subject, PCRE_ERROR_SHORTUTF8 is used instead.
1777  .sp  .sp
1778    PCRE_ERROR_BADUTF8_OFFSET (-11)    PCRE_ERROR_BADUTF8_OFFSET (-11)
1779  .sp  .sp
1780  The UTF-8 byte sequence that was passed as a subject was valid, but the value  The UTF-8 byte sequence that was passed as a subject was valid, but the value
1781  of \fIstartoffset\fP did not point to the beginning of a UTF-8 character.  of \fIstartoffset\fP did not point to the beginning of a UTF-8 character or the
1782    end of the subject.
1783  .sp  .sp
1784    PCRE_ERROR_PARTIAL        (-12)    PCRE_ERROR_PARTIAL        (-12)
1785  .sp  .sp
# Line 1430  documentation for details of partial mat Line 1791  documentation for details of partial mat
1791  .sp  .sp
1792    PCRE_ERROR_BADPARTIAL     (-13)    PCRE_ERROR_BADPARTIAL     (-13)
1793  .sp  .sp
1794  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
1795  are not supported for partial matching. See the  option was used with a compiled pattern containing items that were not
1796  .\" HREF  supported for partial matching. From release 8.00 onwards, there are no
1797  \fBpcrepartial\fP  restrictions on partial matching.
 .\"  
 documentation for details of partial matching.  
1798  .sp  .sp
1799    PCRE_ERROR_INTERNAL       (-14)    PCRE_ERROR_INTERNAL       (-14)
1800  .sp  .sp
# Line 1452  The internal recursion limit, as specifi Line 1811  The internal recursion limit, as specifi
1811  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
1812  description above.  description above.
1813  .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  
1814    PCRE_ERROR_BADNEWLINE     (-23)    PCRE_ERROR_BADNEWLINE     (-23)
1815  .sp  .sp
1816  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1817    .sp
1818      PCRE_ERROR_BADOFFSET      (-24)
1819    .sp
1820    The value of \fIstartoffset\fP was negative or greater than the length of the
1821    subject, that is, the value in \fIlength\fP.
1822    .sp
1823      PCRE_ERROR_SHORTUTF8      (-25)
1824    .sp
1825    The subject string ended with an incomplete (truncated) UTF-8 character, and
1826    the PCRE_PARTIAL_HARD option was set. Without this option, PCRE_ERROR_BADUTF8
1827    is returned in this situation.
1828  .P  .P
1829  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.
1830  .  .
1831  .  .
1832  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1476  Error numbers -16 to -20 are not used by Line 1838  Error numbers -16 to -20 are not used by
1838  .ti +5n  .ti +5n
1839  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1840  .PP  .PP
 .br  
1841  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1842  .ti +5n  .ti +5n
1843  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1844  .ti +5n  .ti +5n
1845  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1846  .PP  .PP
 .br  
1847  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1848  .ti +5n  .ti +5n
1849  .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 1929  provided.
1929  .ti +5n  .ti +5n
1930  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1931  .PP  .PP
 .br  
1932  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1933  .ti +5n  .ti +5n
1934  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1578  provided. Line 1937  provided.
1937  .ti +5n  .ti +5n
1938  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1939  .PP  .PP
 .br  
1940  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1941  .ti +5n  .ti +5n
1942  .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 1972  pattern. This is needed in order to gain
1972  translation table.  translation table.
1973  .P  .P
1974  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1975  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1976  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1977  .  the behaviour may not be what you want (see the next section).
1978    .P
1979    \fBWarning:\fP If the pattern uses the (?| feature to set up multiple
1980    subpatterns with the same number, as described in the
1981    .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
1982    .\" </a>
1983    section on duplicate subpattern numbers
1984    .\"
1985    in the
1986    .\" HREF
1987    \fBpcrepattern\fP
1988    .\"
1989    page, you cannot use names to distinguish the different subpatterns, because
1990    names are not included in the compiled code. The matching process uses only
1991    numbers. For this reason, the use of different names for subpatterns of the
1992    same number causes an error at compile time.
1993  .  .
1994  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
1995  .rs  .rs
# Line 1626  appropriate. Line 1999  appropriate.
1999  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
2000  .PP  .PP
2001  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
2002  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
2003  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
2004  example is shown in the  such subpatterns are named, they are required to use the same names.)
2005    .P
2006    Normally, patterns with duplicate names are such that in any one match, only
2007    one of the named subpatterns participates. An example is shown in the
2008  .\" HREF  .\" HREF
2009  \fBpcrepattern\fP  \fBpcrepattern\fP
2010  .\"  .\"
2011  documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP  documentation.
2012  and \fBpcre_get_named_substring()\fP return the first substring corresponding  .P
2013  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
2014  The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are  \fBpcre_get_named_substring()\fP return the first substring corresponding to
2015  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
2016  .sp  returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
2017    returns one of the numbers that are associated with the name, but it is not
2018    defined which it is.
2019    .P
2020  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,
2021  you must use the \fBpcre_get_stringtable_entries()\fP function. The first  you must use the \fBpcre_get_stringtable_entries()\fP function. The first
2022  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 2068  a compiled pattern, using a matching alg
2068  just once, and does not backtrack. This has different characteristics to the  just once, and does not backtrack. This has different characteristics to the
2069  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
2070  patterns are not supported. Nevertheless, there are times when this kind of  patterns are not supported. Nevertheless, there are times when this kind of
2071  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
2072  the  list of features that \fBpcre_dfa_exec()\fP does not support, see the
2073  .\" HREF  .\" HREF
2074  \fBpcrematching\fP  \fBpcrematching\fP
2075  .\"  .\"
# Line 1729  Here is an example of a simple call to \ Line 2108  Here is an example of a simple call to \
2108  .sp  .sp
2109  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
2110  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,
2111  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
2112  PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are  PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE,
2113  the same as for \fBpcre_exec()\fP, so their description is not repeated here.  PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART.
2114  .sp  All but the last four of these are exactly the same as for \fBpcre_exec()\fP,
2115    PCRE_PARTIAL  so their description is not repeated here.
2116  .sp  .sp
2117  This has the same general effect as it does for \fBpcre_exec()\fP, but the    PCRE_PARTIAL_HARD
2118  details are slightly different. When PCRE_PARTIAL is set for    PCRE_PARTIAL_SOFT
2119  \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into  .sp
2120  PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no  These have the same general effect as they do for \fBpcre_exec()\fP, but the
2121  complete matches, but there is still at least one matching possibility. The  details are slightly different. When PCRE_PARTIAL_HARD is set for
2122  portion of the string that provided the partial match is set as the first  \fBpcre_dfa_exec()\fP, it returns PCRE_ERROR_PARTIAL if the end of the subject
2123  matching string.  is reached and there is still at least one matching possibility that requires
2124    additional characters. This happens even if some complete matches have also
2125    been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH
2126    is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached,
2127    there have been no complete matches, but there is still at least one matching
2128    possibility. The portion of the string that was inspected when the longest
2129    partial match was found is set as the first matching string in both cases.
2130    There is a more detailed discussion of partial and multi-segment matching, with
2131    examples, in the
2132    .\" HREF
2133    \fBpcrepartial\fP
2134    .\"
2135    documentation.
2136  .sp  .sp
2137    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
2138  .sp  .sp
# Line 1752  matching point in the subject string. Line 2143  matching point in the subject string.
2143  .sp  .sp
2144    PCRE_DFA_RESTART    PCRE_DFA_RESTART
2145  .sp  .sp
2146  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
2147  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
2148  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
2149  option requests this action; when it is set, the \fIworkspace\fP and  \fIworkspace\fP and \fIwscount\fP options must reference the same vector as
2150  \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
2151  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  
2152  .\" HREF  .\" HREF
2153  \fBpcrepartial\fP  \fBpcrepartial\fP
2154  .\"  .\"
# Line 1846  extremely rare, as a vector of size 1000 Line 2236  extremely rare, as a vector of size 1000
2236  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
2237  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
2238  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
2239  .P  .
2240  .in 0  .
2241  Last updated: 30 November 2006  .SH AUTHOR
2242  .br  .rs
2243  Copyright (c) 1997-2006 University of Cambridge.  .sp
2244    .nf
2245    Philip Hazel
2246    University Computing Service
2247    Cambridge CB2 3QH, England.
2248    .fi
2249    .
2250    .
2251    .SH REVISION
2252    .rs
2253    .sp
2254    .nf
2255    Last updated: 13 November 2010
2256    Copyright (c) 1997-2010 University of Cambridge.
2257    .fi

Legend:
Removed from v.93  
changed lines
  Added in v.572

  ViewVC Help
Powered by ViewVC 1.1.5