/[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 87 by nigel, Sat Feb 24 21:41:21 2007 UTC revision 513 by ph10, Mon May 3 11:13:37 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
68  .br  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
69    .ti +5n
70    .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
71    .PP
72  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
73  .ti +5n  .ti +5n
74  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
75  .ti +5n  .ti +5n
76  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
77  .PP  .PP
 .br  
78  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
79  .ti +5n  .ti +5n
80  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
81  .PP  .PP
 .br  
82  .B void pcre_free_substring(const char *\fIstringptr\fP);  .B void pcre_free_substring(const char *\fIstringptr\fP);
83  .PP  .PP
 .br  
84  .B void pcre_free_substring_list(const char **\fIstringptr\fP);  .B void pcre_free_substring_list(const char **\fIstringptr\fP);
85  .PP  .PP
 .br  
86  .B const unsigned char *pcre_maketables(void);  .B const unsigned char *pcre_maketables(void);
87  .PP  .PP
 .br  
88  .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
89  .ti +5n  .ti +5n
90  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
91  .PP  .PP
 .br  
92  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
93  .B *\fIfirstcharptr\fP);  .B *\fIfirstcharptr\fP);
94  .PP  .PP
 .br  
95  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
96  .PP  .PP
 .br  
97  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
98  .PP  .PP
 .br  
99  .B char *pcre_version(void);  .B char *pcre_version(void);
100  .PP  .PP
 .br  
101  .B void *(*pcre_malloc)(size_t);  .B void *(*pcre_malloc)(size_t);
102  .PP  .PP
 .br  
103  .B void (*pcre_free)(void *);  .B void (*pcre_free)(void *);
104  .PP  .PP
 .br  
105  .B void *(*pcre_stack_malloc)(size_t);  .B void *(*pcre_stack_malloc)(size_t);
106  .PP  .PP
 .br  
107  .B void (*pcre_stack_free)(void *);  .B void (*pcre_stack_free)(void *);
108  .PP  .PP
 .br  
109  .B int (*pcre_callout)(pcre_callout_block *);  .B int (*pcre_callout)(pcre_callout_block *);
110  .  .
111  .  .
112  .SH "PCRE API OVERVIEW"  .SH "PCRE API OVERVIEW"
113  .rs  .rs
114  .sp  .sp
115  PCRE has its own native API, which is described in this document. There is  PCRE has its own native API, which is described in this document. There are
116  also a set of wrapper functions that correspond to the POSIX regular expression  also some wrapper functions that correspond to the POSIX regular expression
117  API. These are described in the  API. These are described in the
118  .\" HREF  .\" HREF
119  \fBpcreposix\fP  \fBpcreposix\fP
# Line 155  Applications can use these to include su Line 135  Applications can use these to include su
135  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,
136  and \fBpcre_exec()\fP are used for compiling and matching regular expressions  and \fBpcre_exec()\fP are used for compiling and matching regular expressions
137  in a Perl-compatible manner. A sample program that demonstrates the simplest  in a Perl-compatible manner. A sample program that demonstrates the simplest
138  way of using them is provided in the file called \fIpcredemo.c\fP in the source  way of using them is provided in the file called \fIpcredemo.c\fP in the PCRE
139  distribution. The  source distribution. A listing of this program is given in the
140    .\" HREF
141    \fBpcredemo\fP
142    .\"
143    documentation, and the
144  .\" HREF  .\" HREF
145  \fBpcresample\fP  \fBpcresample\fP
146  .\"  .\"
147  documentation describes how to run it.  documentation describes how to compile and run it.
148  .P  .P
149  A second matching function, \fBpcre_dfa_exec()\fP, which is not  A second matching function, \fBpcre_dfa_exec()\fP, which is not
150  Perl-compatible, is also provided. This uses a different algorithm for the  Perl-compatible, is also provided. This uses a different algorithm for the
151  matching. This allows it to find all possible matches (at a given point in the  matching. The alternative algorithm finds all possible matches (at a given
152  subject), not just one. However, this algorithm does not return captured  point in the subject), and scans the subject just once (unless there are
153    lookbehind assertions). However, this algorithm does not return captured
154  substrings. A description of the two matching algorithms and their advantages  substrings. A description of the two matching algorithms and their advantages
155  and disadvantages is given in the  and disadvantages is given in the
156  .\" HREF  .\" HREF
# Line 183  matched by \fBpcre_exec()\fP. They are: Line 168  matched by \fBpcre_exec()\fP. They are:
168    \fBpcre_get_named_substring()\fP    \fBpcre_get_named_substring()\fP
169    \fBpcre_get_substring_list()\fP    \fBpcre_get_substring_list()\fP
170    \fBpcre_get_stringnumber()\fP    \fBpcre_get_stringnumber()\fP
171      \fBpcre_get_stringtable_entries()\fP
172  .sp  .sp
173  \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also  \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also
174  provided, to free the memory used for extracted strings.  provided, to free the memory used for extracted strings.
# Line 212  should be done before calling any PCRE f Line 198  should be done before calling any PCRE f
198  The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also  The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also
199  indirections to memory management functions. These special functions are used  indirections to memory management functions. These special functions are used
200  only when PCRE is compiled to use the heap for remembering data, instead of  only when PCRE is compiled to use the heap for remembering data, instead of
201  recursive function calls, when running the \fBpcre_exec()\fP function. This is  recursive function calls, when running the \fBpcre_exec()\fP function. See the
202  a non-standard way of building PCRE, for use in environments that have limited  .\" HREF
203  stacks. Because of the greater use of memory management, it runs more slowly.  \fBpcrebuild\fP
204  Separate functions are provided so that special-purpose external code can be  .\"
205  used for this case. When used, these functions are always called in a  documentation for details of how to do this. It is a non-standard way of
206  stack-like manner (last obtained, first freed), and always for memory blocks of  building PCRE, for use in environments that have limited stacks. Because of the
207  the same size.  greater use of memory management, it runs more slowly. Separate functions are
208    provided so that special-purpose external code can be used for this case. When
209    used, these functions are always called in a stack-like manner (last obtained,
210    first freed), and always for memory blocks of the same size. There is a
211    discussion about PCRE's stack usage in the
212    .\" HREF
213    \fBpcrestack\fP
214    .\"
215    documentation.
216  .P  .P
217  The global variable \fBpcre_callout\fP initially contains NULL. It can be set  The global variable \fBpcre_callout\fP initially contains NULL. It can be set
218  by the caller to a "callout" function, which PCRE will then call at specified  by the caller to a "callout" function, which PCRE will then call at specified
# Line 229  points during a matching operation. Deta Line 223  points during a matching operation. Deta
223  documentation.  documentation.
224  .  .
225  .  .
226    .\" HTML <a name="newlines"></a>
227    .SH NEWLINES
228    .rs
229    .sp
230    PCRE supports five different conventions for indicating line breaks in
231    strings: a single CR (carriage return) character, a single LF (linefeed)
232    character, the two-character sequence CRLF, any of the three preceding, or any
233    Unicode newline sequence. The Unicode newline sequences are the three just
234    mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
235    U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
236    (paragraph separator, U+2029).
237    .P
238    Each of the first three conventions is used by at least one operating system as
239    its standard newline sequence. When PCRE is built, a default can be specified.
240    The default default is LF, which is the Unix standard. When PCRE is run, the
241    default can be overridden, either when a pattern is compiled, or when it is
242    matched.
243    .P
244    At compile time, the newline convention can be specified by the \fIoptions\fP
245    argument of \fBpcre_compile()\fP, or it can be specified by special text at the
246    start of the pattern itself; this overrides any other settings. See the
247    .\" HREF
248    \fBpcrepattern\fP
249    .\"
250    page for details of the special character sequences.
251    .P
252    In the PCRE documentation the word "newline" is used to mean "the character or
253    pair of characters that indicate a line break". The choice of newline
254    convention affects the handling of the dot, circumflex, and dollar
255    metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
256    recognized line ending sequence, the match position advancement for a
257    non-anchored pattern. There is more detail about this in the
258    .\" HTML <a href="#execoptions">
259    .\" </a>
260    section on \fBpcre_exec()\fP options
261    .\"
262    below.
263    .P
264    The choice of newline convention does not affect the interpretation of
265    the \en or \er escape sequences, nor does it affect what \eR matches, which is
266    controlled in a similar way, but by separate options.
267    .
268    .
269  .SH MULTITHREADING  .SH MULTITHREADING
270  .rs  .rs
271  .sp  .sp
# Line 250  which it was compiled. Details are given Line 287  which it was compiled. Details are given
287  .\" HREF  .\" HREF
288  \fBpcreprecompile\fP  \fBpcreprecompile\fP
289  .\"  .\"
290  documentation.  documentation. However, compiling a regular expression with one version of PCRE
291    for use with a different version is not guaranteed to work and may cause
292    crashes.
293  .  .
294  .  .
295  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 281  properties is available; otherwise it is Line 320  properties is available; otherwise it is
320  .sp  .sp
321    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
322  .sp  .sp
323  The output is an integer that is set to the value of the code that is used for  The output is an integer whose value specifies the default character sequence
324  the newline character. It is either linefeed (10) or carriage return (13), and  that is recognized as meaning "newline". The four values that are supported
325  should normally be the standard character for your operating system.  are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY.
326    Though they are derived from ASCII, the same values are returned in EBCDIC
327    environments. The default should normally correspond to the standard sequence
328    for your operating system.
329    .sp
330      PCRE_CONFIG_BSR
331    .sp
332    The output is an integer whose value indicates what character sequences the \eR
333    escape sequence matches by default. A value of 0 means that \eR matches any
334    Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
335    or CRLF. The default can be overridden when a pattern is compiled or matched.
336  .sp  .sp
337    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
338  .sp  .sp
# Line 305  documentation. Line 354  documentation.
354  .sp  .sp
355    PCRE_CONFIG_MATCH_LIMIT    PCRE_CONFIG_MATCH_LIMIT
356  .sp  .sp
357  The output is an integer that gives the default limit for the number of  The output is a long integer that gives the default limit for the number of
358  internal matching function calls in a \fBpcre_exec()\fP execution. Further  internal matching function calls in a \fBpcre_exec()\fP execution. Further
359  details are given with \fBpcre_exec()\fP below.  details are given with \fBpcre_exec()\fP below.
360  .sp  .sp
361    PCRE_CONFIG_MATCH_LIMIT_RECURSION    PCRE_CONFIG_MATCH_LIMIT_RECURSION
362  .sp  .sp
363  The output is an integer that gives the default limit for the depth of  The output is a long integer that gives the default limit for the depth of
364  recursion when calling the internal matching function in a \fBpcre_exec()\fP  recursion when calling the internal matching function in a \fBpcre_exec()\fP
365  execution. Further details are given with \fBpcre_exec()\fP below.  execution. Further details are given with \fBpcre_exec()\fP below.
366  .sp  .sp
# Line 346  avoiding the use of the stack. Line 395  avoiding the use of the stack.
395  Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be  Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be
396  called to compile a pattern into an internal form. The only difference between  called to compile a pattern into an internal form. The only difference between
397  the two interfaces is that \fBpcre_compile2()\fP has an additional argument,  the two interfaces is that \fBpcre_compile2()\fP has an additional argument,
398  \fIerrorcodeptr\fP, via which a numerical error code can be returned.  \fIerrorcodeptr\fP, via which a numerical error code can be returned. To avoid
399    too much repetition, we refer just to \fBpcre_compile()\fP below, but the
400    information applies equally to \fBpcre_compile2()\fP.
401  .P  .P
402  The pattern is a C string terminated by a binary zero, and is passed in the  The pattern is a C string terminated by a binary zero, and is passed in the
403  \fIpattern\fP argument. A pointer to a single block of memory that is obtained  \fIpattern\fP argument. A pointer to a single block of memory that is obtained
404  via \fBpcre_malloc\fP is returned. This contains the compiled code and related  via \fBpcre_malloc\fP is returned. This contains the compiled code and related
405  data. The \fBpcre\fP type is defined for the returned block; this is a typedef  data. The \fBpcre\fP type is defined for the returned block; this is a typedef
406  for a structure whose contents are not externally defined. It is up to the  for a structure whose contents are not externally defined. It is up to the
407  caller to free the memory when it is no longer required.  caller to free the memory (via \fBpcre_free\fP) when it is no longer required.
408  .P  .P
409  Although the compiled code of a PCRE regex is relocatable, that is, it does not  Although the compiled code of a PCRE regex is relocatable, that is, it does not
410  depend on memory location, the complete \fBpcre\fP data block is not  depend on memory location, the complete \fBpcre\fP data block is not
411  fully relocatable, because it may contain a copy of the \fItableptr\fP  fully relocatable, because it may contain a copy of the \fItableptr\fP
412  argument, which is an address (see below).  argument, which is an address (see below).
413  .P  .P
414  The \fIoptions\fP argument contains independent bits that affect the  The \fIoptions\fP argument contains various bit settings that affect the
415  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
416  options are described below. Some of them, in particular, those that are  options are described below. Some of them (in particular, those that are
417  compatible with Perl, can also be set and unset from within the pattern (see  compatible with Perl, but some others as well) can also be set and unset from
418  the detailed description in the  within the pattern (see the detailed description in the
419  .\" HREF  .\" HREF
420  \fBpcrepattern\fP  \fBpcrepattern\fP
421  .\"  .\"
422  documentation). For these options, the contents of the \fIoptions\fP argument  documentation). For those options that can be different in different parts of
423  specifies their initial settings at the start of compilation and execution. The  the pattern, the contents of the \fIoptions\fP argument specifies their
424  PCRE_ANCHORED option can be set at the time of matching as well as at compile  settings at the start of compilation and execution. The PCRE_ANCHORED,
425  time.  PCRE_BSR_\fIxxx\fP, and PCRE_NEWLINE_\fIxxx\fP options can be set at the time
426    of matching as well as at compile time.
427  .P  .P
428  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
429  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
430  NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual  NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual
431  error message. This is a static string that is part of the library. You must  error message. This is a static string that is part of the library. You must
432  not try to free it. The offset from the start of the pattern to the character  not try to free it. The byte offset from the start of the pattern to the
433  where the error was discovered is placed in the variable pointed to by  character that was being processed when the error was discovered is placed in
434  \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.  the variable pointed to by \fIerroffset\fP, which must not be NULL. If it is,
435    an immediate error is given. Some errors are not detected until checks are
436    carried out when the whole pattern has been scanned; in this case the offset is
437    set to the end of the pattern.
438  .P  .P
439  If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the  If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the
440  \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is  \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is
# Line 426  facility, see the Line 481  facility, see the
481  .\"  .\"
482  documentation.  documentation.
483  .sp  .sp
484      PCRE_BSR_ANYCRLF
485      PCRE_BSR_UNICODE
486    .sp
487    These options (which are mutually exclusive) control what the \eR escape
488    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
489    match any Unicode newline sequence. The default is specified when PCRE is
490    built. It can be overridden from within the pattern, or by setting an option
491    when a compiled pattern is matched.
492    .sp
493    PCRE_CASELESS    PCRE_CASELESS
494  .sp  .sp
495  If this bit is set, letters in the pattern match both upper and lower case  If this bit is set, letters in the pattern match both upper and lower case
# Line 442  with UTF-8 support. Line 506  with UTF-8 support.
506  .sp  .sp
507  If this bit is set, a dollar metacharacter in the pattern matches only at the  If this bit is set, a dollar metacharacter in the pattern matches only at the
508  end of the subject string. Without this option, a dollar also matches  end of the subject string. Without this option, a dollar also matches
509  immediately before the final character if it is a newline (but not before any  immediately before a newline at the end of the string (but not before any other
510  other newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is  newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set.
511  set. There is no equivalent to this option in Perl, and no way to set it within  There is no equivalent to this option in Perl, and no way to set it within a
512  a pattern.  pattern.
513  .sp  .sp
514    PCRE_DOTALL    PCRE_DOTALL
515  .sp  .sp
516  If this bit is set, a dot metacharater in the pattern matches all characters,  If this bit is set, a dot metacharater in the pattern matches all characters,
517  including newlines. Without it, newlines are excluded. This option is  including those that indicate newline. Without it, a dot does not match when
518  equivalent to Perl's /s option, and it can be changed within a pattern by a  the current position is at a newline. This option is equivalent to Perl's /s
519  (?s) option setting. A negative class such as [^a] always matches a newline  option, and it can be changed within a pattern by a (?s) option setting. A
520  character, independent of the setting of this option.  negative class such as [^a] always matches newline characters, independent of
521    the setting of this option.
522    .sp
523      PCRE_DUPNAMES
524    .sp
525    If this bit is set, names used to identify capturing subpatterns need not be
526    unique. This can be helpful for certain types of pattern when it is known that
527    only one instance of the named subpattern can ever be matched. There are more
528    details of named subpatterns below; see also the
529    .\" HREF
530    \fBpcrepattern\fP
531    .\"
532    documentation.
533  .sp  .sp
534    PCRE_EXTENDED    PCRE_EXTENDED
535  .sp  .sp
536  If this bit is set, whitespace data characters in the pattern are totally  If this bit is set, whitespace data characters in the pattern are totally
537  ignored except when escaped or inside a character class. Whitespace does not  ignored except when escaped or inside a character class. Whitespace does not
538  include the VT character (code 11). In addition, characters between an  include the VT character (code 11). In addition, characters between an
539  unescaped # outside a character class and the next newline character,  unescaped # outside a character class and the next newline, inclusive, are also
540  inclusive, are also ignored. This is equivalent to Perl's /x option, and it can  ignored. This is equivalent to Perl's /x option, and it can be changed within a
541  be changed within a pattern by a (?x) option setting.  pattern by a (?x) option setting.
542  .P  .P
543  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
544  Note, however, that this applies only to data characters. Whitespace characters  Note, however, that this applies only to data characters. Whitespace characters
# Line 476  that is incompatible with Perl, but it i Line 552  that is incompatible with Perl, but it i
552  set, any backslash in a pattern that is followed by a letter that has no  set, any backslash in a pattern that is followed by a letter that has no
553  special meaning causes an error, thus reserving these combinations for future  special meaning causes an error, thus reserving these combinations for future
554  expansion. By default, as in Perl, a backslash followed by a letter with no  expansion. By default, as in Perl, a backslash followed by a letter with no
555  special meaning is treated as a literal. There are at present no other features  special meaning is treated as a literal. (Perl can, however, be persuaded to
556  controlled by this option. It can also be set by a (?X) option setting within a  give an error for this, by running it with the -w option.) There are at present
557  pattern.  no other features controlled by this option. It can also be set by a (?X)
558    option setting within a pattern.
559  .sp  .sp
560    PCRE_FIRSTLINE    PCRE_FIRSTLINE
561  .sp  .sp
562  If this option is set, an unanchored pattern is required to match before or at  If this option is set, an unanchored pattern is required to match before or at
563  the first newline character in the subject string, though the matched text may  the first newline in the subject string, though the matched text may continue
564  continue over the newline.  over the newline.
565    .sp
566      PCRE_JAVASCRIPT_COMPAT
567    .sp
568    If this option is set, PCRE's behaviour is changed in some ways so that it is
569    compatible with JavaScript rather than Perl. The changes are as follows:
570    .P
571    (1) A lone closing square bracket in a pattern causes a compile-time error,
572    because this is illegal in JavaScript (by default it is treated as a data
573    character). Thus, the pattern AB]CD becomes illegal when this option is set.
574    .P
575    (2) At run time, a back reference to an unset subpattern group matches an empty
576    string (by default this causes the current matching alternative to fail). A
577    pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
578    an "a" in the subject), whereas it fails by default, for Perl compatibility.
579  .sp  .sp
580    PCRE_MULTILINE    PCRE_MULTILINE
581  .sp  .sp
# Line 496  terminating newline (unless PCRE_DOLLAR_ Line 587  terminating newline (unless PCRE_DOLLAR_
587  Perl.  Perl.
588  .P  .P
589  When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs  When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
590  match immediately following or immediately before any newline in the subject  match immediately following or immediately before internal newlines in the
591  string, respectively, as well as at the very start and end. This is equivalent  subject string, respectively, as well as at the very start and end. This is
592  to Perl's /m option, and it can be changed within a pattern by a (?m) option  equivalent to Perl's /m option, and it can be changed within a pattern by a
593  setting. If there are no "\en" characters in a subject string, or no  (?m) option setting. If there are no newlines in a subject string, or no
594  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
595  .sp  .sp
596      PCRE_NEWLINE_CR
597      PCRE_NEWLINE_LF
598      PCRE_NEWLINE_CRLF
599      PCRE_NEWLINE_ANYCRLF
600      PCRE_NEWLINE_ANY
601    .sp
602    These options override the default newline definition that was chosen when PCRE
603    was built. Setting the first or the second specifies that a newline is
604    indicated by a single character (CR or LF, respectively). Setting
605    PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
606    CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
607    preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
608    that any Unicode newline sequence should be recognized. The Unicode newline
609    sequences are the three just mentioned, plus the single characters VT (vertical
610    tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
611    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
612    recognized only in UTF-8 mode.
613    .P
614    The newline setting in the options word uses three bits that are treated
615    as a number, giving eight possibilities. Currently only six are used (default
616    plus the five values above). This means that if you set more than one newline
617    option, the combination may or may not be sensible. For example,
618    PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
619    other combinations may yield unused numbers and cause an error.
620    .P
621    The only time that a line break is specially recognized when compiling a
622    pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
623    class is encountered. This indicates a comment that lasts until after the next
624    line break sequence. In other circumstances, line break sequences are treated
625    as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
626    as whitespace characters and are therefore ignored.
627    .P
628    The newline option that is set at compile time becomes the default that is used
629    for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
630    .sp
631    PCRE_NO_AUTO_CAPTURE    PCRE_NO_AUTO_CAPTURE
632  .sp  .sp
633  If this option is set, it disables the use of numbered capturing parentheses in  If this option is set, it disables the use of numbered capturing parentheses in
# Line 536  page. Line 662  page.
662    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
663  .sp  .sp
664  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
665  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
666  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
667  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
668  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
669  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
670  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
671  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
672  strings.  \fBpcre\fP
673    .\"
674    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
675    returns an error. If you already know that your pattern is valid, and you want
676    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
677    option. When it is set, the effect of passing an invalid UTF-8 string as a
678    pattern is undefined. It may cause your program to crash. Note that this option
679    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
680    the UTF-8 validity checking of subject strings.
681  .  .
682  .  .
683  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 551  strings. Line 685  strings.
685  .sp  .sp
686  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
687  \fBpcre_compile2()\fP, along with the error messages that may be returned by  \fBpcre_compile2()\fP, along with the error messages that may be returned by
688  both compiling functions.  both compiling functions. As PCRE has developed, some error codes have fallen
689    out of use. To avoid confusion, they have not been re-used.
690  .sp  .sp
691     0  no error     0  no error
692     1  \e at end of pattern     1  \e at end of pattern
# Line 563  both compiling functions. Line 698  both compiling functions.
698     7  invalid escape sequence in character class     7  invalid escape sequence in character class
699     8  range out of order in character class     8  range out of order in character class
700     9  nothing to repeat     9  nothing to repeat
701    10  operand of unlimited repeat could match the empty string    10  [this code is not in use]
702    11  internal error: unexpected repeat    11  internal error: unexpected repeat
703    12  unrecognized character after (?    12  unrecognized character after (? or (?-
704    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
705    14  missing )    14  missing )
706    15  reference to non-existent subpattern    15  reference to non-existent subpattern
707    16  erroffset passed as NULL    16  erroffset passed as NULL
708    17  unknown option bit(s) set    17  unknown option bit(s) set
709    18  missing ) after comment    18  missing ) after comment
710    19  parentheses nested too deeply    19  [this code is not in use]
711    20  regular expression too large    20  regular expression is too large
712    21  failed to get memory    21  failed to get memory
713    22  unmatched parentheses    22  unmatched parentheses
714    23  internal error: code overflow    23  internal error: code overflow
715    24  unrecognized character after (?<    24  unrecognized character after (?<
716    25  lookbehind assertion is not fixed length    25  lookbehind assertion is not fixed length
717    26  malformed number after (?(    26  malformed number or name after (?(
718    27  conditional group contains more than two branches    27  conditional group contains more than two branches
719    28  assertion expected after (?(    28  assertion expected after (?(
720    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
721    30  unknown POSIX class name    30  unknown POSIX class name
722    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
723    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
724    33  spare error    33  [this code is not in use]
725    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
726    35  invalid condition (?(0)    35  invalid condition (?(0)
727    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
# Line 595  both compiling functions. Line 730  both compiling functions.
730    39  closing ) for (?C expected    39  closing ) for (?C expected
731    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
732    41  unrecognized character after (?P    41  unrecognized character after (?P
733    42  syntax error after (?P    42  syntax error in subpattern name (missing terminator)
734    43  two named groups have the same name    43  two named subpatterns have the same name
735    44  invalid UTF-8 string    44  invalid UTF-8 string
736    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
737    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
738    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
739      48  subpattern name is too long (maximum 32 characters)
740      49  too many named subpatterns (maximum 10000)
741      50  [this code is not in use]
742      51  octal value is greater than \e377 (not in UTF-8 mode)
743      52  internal error: overran compiling workspace
744      53  internal error: previously-checked referenced subpattern not found
745      54  DEFINE group contains more than one branch
746      55  repeating a DEFINE group is not allowed
747      56  inconsistent NEWLINE options
748      57  \eg is not followed by a braced, angle-bracketed, or quoted
749            name/number or by a plain number
750      58  a numbered reference must not be zero
751      59  an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
752      60  (*VERB) not recognized
753      61  number is too big
754      62  subpattern name expected
755      63  digit expected after (?+
756      64  ] is an invalid data character in JavaScript compatibility mode
757      65  different names for subpatterns of the same number are not allowed
758      66  (*MARK) must have an argument
759    .sp
760    The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
761    be used if the limits were changed when PCRE was built.
762  .  .
763  .  .
764  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 619  help speed up matching, \fBpcre_study()\ Line 777  help speed up matching, \fBpcre_study()\
777  results of the study.  results of the study.
778  .P  .P
779  The returned value from \fBpcre_study()\fP can be passed directly to  The returned value from \fBpcre_study()\fP can be passed directly to
780  \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
781  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
782  described  passed; these are described
783  .\" HTML <a href="#extradata">  .\" HTML <a href="#extradata">
784  .\" </a>  .\" </a>
785  below  below
786  .\"  .\"
787  in the section on matching a pattern.  in the section on matching a pattern.
788  .P  .P
789  If studying the pattern does not produce any additional information  If studying the pattern does not produce any useful information,
790  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program
791  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
792  own \fBpcre_extra\fP block.  \fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block.
793  .P  .P
794  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
795  options are defined, and this argument should always be zero.  options are defined, and this argument should always be zero.
# Line 651  This is a typical call to \fBpcre_study\ Line 809  This is a typical call to \fBpcre_study\
809      0,              /* no options exist */      0,              /* no options exist */
810      &error);        /* set to NULL or points to a message */      &error);        /* set to NULL or points to a message */
811  .sp  .sp
812  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
813  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
814  bytes is created.  mean that there are any strings of that length that match, but it does
815    guarantee that no shorter strings match. The value is used by
816    \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP to avoid wasting time by trying to
817    match strings that are shorter than the lower bound. You can find out the value
818    in a calling program via the \fBpcre_fullinfo()\fP function.
819    .P
820    Studying a pattern is also useful for non-anchored patterns that do not have a
821    single fixed starting character. A bitmap of possible starting bytes is
822    created. This speeds up finding a position in the subject at which to start
823    matching.
824  .  .
825  .  .
826  .\" HTML <a name="localesupport"></a>  .\" HTML <a name="localesupport"></a>
827  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
828  .rs  .rs
829  .sp  .sp
830  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
831  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
832  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
833  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but
834  can be tested with \ep if PCRE is built with Unicode character property  can be tested with \ep if PCRE is built with Unicode character property
835  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
836  .P  characters with codes greater than 128, you should either use UTF-8 and
837  An internal set of tables is created in the default C locale when PCRE is  Unicode, or use locales, but not try to mix the two.
838  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
839  and is sufficient for many applications. An alternative set of tables can,  PCRE contains an internal set of tables that are used when the final argument
840  however, be supplied. These may be created in a different locale from the  of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
841  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
842  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
843    default "C" locale of the local system, which may cause them to be different.
844    .P
845    The internal tables can always be overridden by tables supplied by the
846    application that calls PCRE. These may be created in a different locale from
847    the default. As more and more applications change to using Unicode, the need
848    for this locale support is expected to die away.
849  .P  .P
850  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
851  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 685  the following code could be used: Line 858  the following code could be used:
858    tables = pcre_maketables();    tables = pcre_maketables();
859    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
860  .sp  .sp
861    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
862    are using Windows, the name for the French locale is "french".
863    .P
864  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
865  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
866  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 731  check against passing an arbitrary memor Line 907  check against passing an arbitrary memor
907  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
908  .sp  .sp
909    int rc;    int rc;
910    unsigned long int length;    size_t length;
911    rc = pcre_fullinfo(    rc = pcre_fullinfo(
912      re,               /* result of pcre_compile() */      re,               /* result of pcre_compile() */
913      pe,               /* result of pcre_study(), or NULL */      pe,               /* result of pcre_study(), or NULL */
# Line 763  a NULL table pointer. Line 939  a NULL table pointer.
939    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
940  .sp  .sp
941  Return information about the first byte of any matched string, for a  Return information about the first byte of any matched string, for a
942  non-anchored pattern. (This option used to be called PCRE_INFO_FIRSTCHAR; the  non-anchored pattern. The fourth argument should point to an \fBint\fP
943  old name is still recognized for backwards compatibility.)  variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
944    still recognized for backwards compatibility.)
945  .P  .P
946  If there is a fixed first byte, for example, from a pattern such as  If there is a fixed first byte, for example, from a pattern such as
947  (cat|cow|coyote), it is returned in the integer pointed to by \fIwhere\fP.  (cat|cow|coyote), its value is returned. Otherwise, if either
 Otherwise, if either  
948  .sp  .sp
949  (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch  (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
950  starts with "^", or  starts with "^", or
# Line 787  table indicating a fixed set of bytes fo Line 963  table indicating a fixed set of bytes fo
963  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
964  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
965  .sp  .sp
966      PCRE_INFO_HASCRORLF
967    .sp
968    Return 1 if the pattern contains any explicit matches for CR or LF characters,
969    otherwise 0. The fourth argument should point to an \fBint\fP variable. An
970    explicit match is either a literal CR or LF character, or \er or \en.
971    .sp
972      PCRE_INFO_JCHANGED
973    .sp
974    Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
975    0. The fourth argument should point to an \fBint\fP variable. (?J) and
976    (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
977    .sp
978    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
979  .sp  .sp
980  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 797  follows something of variable length. Fo Line 985  follows something of variable length. Fo
985  /^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
986  is -1.  is -1.
987  .sp  .sp
988      PCRE_INFO_MINLENGTH
989    .sp
990    If the pattern was studied and a minimum length for matching subject strings
991    was computed, its value is returned. Otherwise the returned value is -1. The
992    value is a number of characters, not bytes (this may be relevant in UTF-8
993    mode). The fourth argument should point to an \fBint\fP variable. A
994    non-negative value is a lower bound to the length of any matching string. There
995    may not be any strings of that length that do actually match, but every string
996    that does match is at least that long.
997    .sp
998    PCRE_INFO_NAMECOUNT    PCRE_INFO_NAMECOUNT
999    PCRE_INFO_NAMEENTRYSIZE    PCRE_INFO_NAMEENTRYSIZE
1000    PCRE_INFO_NAMETABLE    PCRE_INFO_NAMETABLE
1001  .sp  .sp
1002  PCRE supports the use of named as well as numbered capturing parentheses. The  PCRE supports the use of named as well as numbered capturing parentheses. The
1003  names are just an additional way of identifying the parentheses, which still  names are just an additional way of identifying the parentheses, which still
1004  acquire numbers. A convenience function called \fBpcre_get_named_substring()\fP  acquire numbers. Several convenience functions such as
1005  is provided for extracting an individual captured substring by name. It is also  \fBpcre_get_named_substring()\fP are provided for extracting captured
1006  possible to extract the data directly, by first converting the name to a number  substrings by name. It is also possible to extract the data directly, by first
1007  in order to access the correct pointers in the output vector (described with  converting the name to a number in order to access the correct pointers in the
1008  \fBpcre_exec()\fP below). To do the conversion, you need to use the  output vector (described with \fBpcre_exec()\fP below). To do the conversion,
1009  name-to-number map, which is described by these three values.  you need to use the name-to-number map, which is described by these three
1010    values.
1011  .P  .P
1012  The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives  The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives
1013  the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each  the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
# Line 816  entry; both of these return an \fBint\fP Line 1015  entry; both of these return an \fBint\fP
1015  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
1016  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
1017  are the number of the capturing parenthesis, most significant byte first. The  are the number of the capturing parenthesis, most significant byte first. The
1018  rest of the entry is the corresponding name, zero terminated. The names are in  rest of the entry is the corresponding name, zero terminated.
1019  alphabetical order. For example, consider the following pattern (assume  .P
1020  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  The names are in alphabetical order. Duplicate names may appear if (?| is used
1021    to create multiple groups with the same number, as described in the
1022    .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
1023    .\" </a>
1024    section on duplicate subpattern numbers
1025    .\"
1026    in the
1027    .\" HREF
1028    \fBpcrepattern\fP
1029    .\"
1030    page. Duplicate names for subpatterns with different numbers are permitted only
1031    if PCRE_DUPNAMES is set. In all cases of duplicate names, they appear in the
1032    table in the order in which they were found in the pattern. In the absence of
1033    (?| this is the order of increasing number; when (?| is used this is not
1034    necessarily the case because later subpatterns may have lower numbers.
1035    .P
1036    As a simple example of the name/number table, consider the following pattern
1037    (assume PCRE_EXTENDED is set, so white space - including newlines - is
1038    ignored):
1039  .sp  .sp
1040  .\" JOIN  .\" JOIN
1041    (?P<date> (?P<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
1042    (?P<month>\ed\ed) - (?P<day>\ed\ed) )    (?<month>\ed\ed) - (?<day>\ed\ed) )
1043  .sp  .sp
1044  There are four named subpatterns, so the table has four entries, and each entry  There are four named subpatterns, so the table has four entries, and each entry
1045  in the table is eight bytes long. The table is as follows, with non-printing  in the table is eight bytes long. The table is as follows, with non-printing
# Line 834  bytes shows in hexadecimal, and undefine Line 1051  bytes shows in hexadecimal, and undefine
1051    00 02 y  e  a  r  00 ??    00 02 y  e  a  r  00 ??
1052  .sp  .sp
1053  When writing code to extract data from named subpatterns using the  When writing code to extract data from named subpatterns using the
1054  name-to-number map, remember that the length of each entry is likely to be  name-to-number map, remember that the length of the entries is likely to be
1055  different for each compiled pattern.  different for each compiled pattern.
1056  .sp  .sp
1057      PCRE_INFO_OKPARTIAL
1058    .sp
1059    Return 1 if the pattern can be used for partial matching with
1060    \fBpcre_exec()\fP, otherwise 0. The fourth argument should point to an
1061    \fBint\fP variable. From release 8.00, this always returns 1, because the
1062    restrictions that previously applied to partial matching have been lifted. The
1063    .\" HREF
1064    \fBpcrepartial\fP
1065    .\"
1066    documentation gives details of partial matching.
1067    .sp
1068    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
1069  .sp  .sp
1070  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
1071  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
1072  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
1073  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
1074    they are the options that will be in force when matching starts. For example,
1075    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1076    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
1077  .P  .P
1078  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
1079  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 869  variable. Line 1100  variable.
1100  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
1101  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
1102  \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
1103  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
1104    study data, zero is returned. The fourth argument should point to a
1105  \fBsize_t\fP variable.  \fBsize_t\fP variable.
1106  .  .
1107  .  .
# Line 931  is different. (This seems a highly unlik Line 1163  is different. (This seems a highly unlik
1163  .P  .P
1164  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
1165  compiled pattern, which is passed in the \fIcode\fP argument. If the  compiled pattern, which is passed in the \fIcode\fP argument. If the
1166  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
1167  \fIextra\fP argument. This function is the main matching facility of the  \fIextra\fP argument. This function is the main matching facility of the
1168  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
1169  also an alternative matching function, which is described  also an alternative matching function, which is described
# Line 981  fields (not necessarily in this order): Line 1213  fields (not necessarily in this order):
1213    unsigned long int \fImatch_limit_recursion\fP;    unsigned long int \fImatch_limit_recursion\fP;
1214    void *\fIcallout_data\fP;    void *\fIcallout_data\fP;
1215    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1216      unsigned char **\fImark\fP;
1217  .sp  .sp
1218  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
1219  are set. The flag bits are:  are set. The flag bits are:
# Line 990  are set. The flag bits are: Line 1223  are set. The flag bits are:
1223    PCRE_EXTRA_MATCH_LIMIT_RECURSION    PCRE_EXTRA_MATCH_LIMIT_RECURSION
1224    PCRE_EXTRA_CALLOUT_DATA    PCRE_EXTRA_CALLOUT_DATA
1225    PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
1226      PCRE_EXTRA_MARK
1227  .sp  .sp
1228  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
1229  \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 999  the block by setting the other fields an Line 1233  the block by setting the other fields an
1233  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
1234  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,
1235  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
1236  classic example is the use of nested unlimited repeats.  classic example is a pattern that uses nested unlimited repeats.
1237  .P  .P
1238  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly
1239  (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 1032  with a \fBpcre_extra\fP block in which \ Line 1266  with a \fBpcre_extra\fP block in which \
1266  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
1267  is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.  is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1268  .P  .P
1269  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,
1270  which is described in the  and is described in the
1271  .\" HREF  .\" HREF
1272  \fBpcrecallout\fP  \fBpcrecallout\fP
1273  .\"  .\"
# Line 1052  called. See the Line 1286  called. See the
1286  \fBpcreprecompile\fP  \fBpcreprecompile\fP
1287  .\"  .\"
1288  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1289    .P
1290    If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must
1291    be set to point to a \fBchar *\fP variable. If the pattern contains any
1292    backtracking control verbs such as (*MARK:NAME), and the execution ends up with
1293    a name to pass back, a pointer to the name string (zero terminated) is placed
1294    in the variable pointed to by the \fImark\fP field. The names are within the
1295    compiled pattern; if you wish to retain such a name you must copy it before
1296    freeing the memory of a compiled pattern. If there is no name to pass back, the
1297    variable pointed to by the \fImark\fP field set to NULL. For details of the
1298    backtracking control verbs, see the section entitled
1299    .\" HTML <a href="pcrepattern#backtrackcontrol">
1300    .\" </a>
1301    "Backtracking control"
1302    .\"
1303    in the
1304    .\" HREF
1305    \fBpcrepattern\fP
1306    .\"
1307    documentation.
1308  .  .
1309    .
1310    .\" HTML <a name="execoptions"></a>
1311  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1312  .rs  .rs
1313  .sp  .sp
1314  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
1315  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NOTBOL,  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1316  PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
1317    PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and
1318    PCRE_PARTIAL_HARD.
1319  .sp  .sp
1320    PCRE_ANCHORED    PCRE_ANCHORED
1321  .sp  .sp
# Line 1067  matching position. If a pattern was comp Line 1324  matching position. If a pattern was comp
1324  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
1325  matching time.  matching time.
1326  .sp  .sp
1327      PCRE_BSR_ANYCRLF
1328      PCRE_BSR_UNICODE
1329    .sp
1330    These options (which are mutually exclusive) control what the \eR escape
1331    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1332    match any Unicode newline sequence. These options override the choice that was
1333    made or defaulted when the pattern was compiled.
1334    .sp
1335      PCRE_NEWLINE_CR
1336      PCRE_NEWLINE_LF
1337      PCRE_NEWLINE_CRLF
1338      PCRE_NEWLINE_ANYCRLF
1339      PCRE_NEWLINE_ANY
1340    .sp
1341    These options override the newline definition that was chosen or defaulted when
1342    the pattern was compiled. For details, see the description of
1343    \fBpcre_compile()\fP above. During matching, the newline choice affects the
1344    behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1345    the way the match position is advanced after a match failure for an unanchored
1346    pattern.
1347    .P
1348    When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
1349    match attempt for an unanchored pattern fails when the current position is at a
1350    CRLF sequence, and the pattern contains no explicit matches for CR or LF
1351    characters, the match position is advanced by two characters instead of one, in
1352    other words, to after the CRLF.
1353    .P
1354    The above rule is a compromise that makes the most common cases work as
1355    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1356    set), it does not match the string "\er\enA" because, after failing at the
1357    start, it skips both the CR and the LF before retrying. However, the pattern
1358    [\er\en]A does match that string, because it contains an explicit CR or LF
1359    reference, and so advances only by one character after the first failure.
1360    .P
1361    An explicit match for CR of LF is either a literal appearance of one of those
1362    characters, or one of the \er or \en escape sequences. Implicit matches such as
1363    [^X] do not count, nor does \es (which includes CR and LF in the characters
1364    that it matches).
1365    .P
1366    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1367    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1368    .sp
1369    PCRE_NOTBOL    PCRE_NOTBOL
1370  .sp  .sp
1371  This option specifies that first character of the subject string is not the  This option specifies that first character of the subject string is not the
# Line 1091  match the empty string, the entire match Line 1390  match the empty string, the entire match
1390  .sp  .sp
1391    a?b?    a?b?
1392  .sp  .sp
1393  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
1394  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
1395  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".
1396  .P  .sp
1397  Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case    PCRE_NOTEMPTY_ATSTART
1398  of a pattern match of the empty string within its \fBsplit()\fP function, and  .sp
1399  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
1400  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
1401  PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the  can occur only if the pattern contains \eK.
1402  starting offset (see below) and trying an ordinary match again. There is some  .P
1403  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
1404    does make a special case of a pattern match of the empty string within its
1405    \fBsplit()\fP function, and when using the /g modifier. It is possible to
1406    emulate Perl's behaviour after matching a null string by first trying the match
1407    again at the same offset with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then
1408    if that fails, by advancing the starting offset (see below) and trying an
1409    ordinary match again. There is some code that demonstrates how to do this in
1410    the
1411    .\" HREF
1412    \fBpcredemo\fP
1413    .\"
1414    sample program.
1415    .sp
1416      PCRE_NO_START_OPTIMIZE
1417    .sp
1418    There are a number of optimizations that \fBpcre_exec()\fP uses at the start of
1419    a match, in order to speed up the process. For example, if it is known that a
1420    match must start with a specific character, it searches the subject for that
1421    character, and fails immediately if it cannot find it, without actually running
1422    the main matching function. When callouts are in use, these optimizations can
1423    cause them to be skipped. This option disables the "start-up" optimizations,
1424    causing performance to suffer, but ensuring that the callouts do occur.
1425  .sp  .sp
1426    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
1427  .sp  .sp
1428  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
1429  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1430  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
1431  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
1432  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1433  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1434    .\" </a>
1435    section on UTF-8 support
1436    .\"
1437    in the main
1438    .\" HREF
1439    \fBpcre\fP
1440    .\"
1441    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1442    the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1443    PCRE_ERROR_BADUTF8_OFFSET is returned.
1444  .P  .P
1445  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
1446  checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when  checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
# Line 1122  PCRE_NO_UTF8_CHECK is set, the effect of Line 1452  PCRE_NO_UTF8_CHECK is set, the effect of
1452  subject, or a value of \fIstartoffset\fP that does not point to the start of a  subject, or a value of \fIstartoffset\fP that does not point to the start of a
1453  UTF-8 character, is undefined. Your program may crash.  UTF-8 character, is undefined. Your program may crash.
1454  .sp  .sp
1455    PCRE_PARTIAL    PCRE_PARTIAL_HARD
1456      PCRE_PARTIAL_SOFT
1457  .sp  .sp
1458  This option turns on the partial matching feature. If the subject string fails  These options turn on the partial matching feature. For backwards
1459  to match the pattern, but at some point during the matching process the end of  compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match
1460  the subject was reached (that is, the subject partially matches the pattern and  occurs if the end of the subject string is reached successfully, but there are
1461  the failure to match occurred only because there were not enough subject  not enough subject characters to complete the match. If this happens when
1462  characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of  PCRE_PARTIAL_HARD is set, \fBpcre_exec()\fP immediately returns
1463  PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what  PCRE_ERROR_PARTIAL. Otherwise, if PCRE_PARTIAL_SOFT is set, matching continues
1464  may appear in the pattern. These are discussed in the  by testing any other alternatives. Only if they all fail is PCRE_ERROR_PARTIAL
1465    returned (instead of PCRE_ERROR_NOMATCH). The portion of the string that
1466    was inspected when the partial match was found is set as the first matching
1467    string. There is a more detailed discussion in the
1468  .\" HREF  .\" HREF
1469  \fBpcrepartial\fP  \fBpcrepartial\fP
1470  .\"  .\"
# Line 1140  documentation. Line 1474  documentation.
1474  .rs  .rs
1475  .sp  .sp
1476  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
1477  \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
1478  \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a  in \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of
1479  UTF-8 character. Unlike the pattern string, the subject may contain binary zero  a UTF-8 character. Unlike the pattern string, the subject may contain binary
1480  bytes. When the starting offset is zero, the search for a match starts at the  zero bytes. When the starting offset is zero, the search for a match starts at
1481  beginning of the subject, and this is by far the most common case.  the beginning of the subject, and this is by far the most common case.
1482  .P  .P
1483  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
1484  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 1178  pattern. Following the usage in Jeffrey Line 1512  pattern. Following the usage in Jeffrey
1512  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
1513  kinds of parenthesized subpattern that do not cause substrings to be captured.  kinds of parenthesized subpattern that do not cause substrings to be captured.
1514  .P  .P
1515  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
1516  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
1517  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
1518  this argument is NOT the size of \fIovector\fP in bytes.  argument is NOT the size of \fIovector\fP in bytes.
1519  .P  .P
1520  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,
1521  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
1522  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1523  and is not available for passing back information. The length passed in  and is not available for passing back information. The number passed in
1524  \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
1525  rounded down.  rounded down.
1526  .P  .P
1527  When a match is successful, information about captured substrings is returned  When a match is successful, information about captured substrings is returned
1528  in pairs of integers, starting at the beginning of \fIovector\fP, and  in pairs of integers, starting at the beginning of \fIovector\fP, and
1529  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
1530  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
1531  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
1532  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
1533  subject string matched by the entire pattern. The next pair is used for the  mode. They are not character counts.
1534  first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP  .P
1535  is the number of pairs that have been set. If there are no capturing  The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the
1536  subpatterns, the return value from a successful match is 1, indicating that  portion of the subject string matched by the entire pattern. The next pair is
1537  just the first pair of offsets has been set.  used for the first capturing subpattern, and so on. The value returned by
1538  .P  \fBpcre_exec()\fP is one more than the highest numbered pair that has been set.
1539  Some convenience functions are provided for extracting the captured substrings  For example, if two substrings have been captured, the returned value is 3. If
1540  as separate strings. These are described in the following section.  there are no capturing subpatterns, the return value from a successful match is
1541  .P  1, indicating that just the first pair of offsets has been set.
 It is possible for an capturing subpattern number \fIn+1\fP to match some  
 part of the subject when subpattern \fIn\fP has not been used at all. For  
 example, if the string "abc" is matched against the pattern (a|(z))(bc)  
 subpatterns 1 and 3 are matched, but 2 is not. When this happens, both offset  
 values corresponding to the unused subpattern are set to -1.  
1542  .P  .P
1543  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
1544  string that it matched that is returned.  string that it matched that is returned.
1545  .P  .P
1546  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
1547  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
1548  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,
1549  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
1550  \fIovecsize\fP as zero. However, if the pattern contains back references and  \fIovecsize\fP as zero. However, if the pattern contains back references and
1551  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
1552  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
1553  advisable to supply an \fIovector\fP.  advisable to supply an \fIovector\fP.
1554  .P  .P
1555  Note that \fBpcre_info()\fP can be used to find out how many capturing  The \fBpcre_fullinfo()\fP function can be used to find out how many capturing
1556  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
1557  \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
1558  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.
1559    .P
1560    It is possible for capturing subpattern number \fIn+1\fP to match some part of
1561    the subject when subpattern \fIn\fP has not been used at all. For example, if
1562    the string "abc" is matched against the pattern (a|(z))(bc) the return from the
1563    function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
1564    happens, both values in the offset pairs corresponding to unused subpatterns
1565    are set to -1.
1566    .P
1567    Offset values that correspond to unused subpatterns at the end of the
1568    expression are also set to -1. For example, if the string "abc" is matched
1569    against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1570    return from the function is 2, because the highest used capturing subpattern
1571    number is 1. However, you can refer to the offsets for the second and third
1572    capturing subpatterns if you wish (assuming the vector is large enough, of
1573    course).
1574    .P
1575    Some convenience functions are provided for extracting the captured substrings
1576    as separate strings. These are described below.
1577  .  .
1578  .\" HTML <a name="errorlist"></a>  .\" HTML <a name="errorlist"></a>
1579  .SS "Return values from \fBpcre_exec()\fP"  .SS "Error return values from \fBpcre_exec()\fP"
1580  .rs  .rs
1581  .sp  .sp
1582  If \fBpcre_exec()\fP fails, it returns a negative number. The following are  If \fBpcre_exec()\fP fails, it returns a negative number. The following are
# Line 1256  compiled in an environment of one endian Line 1603  compiled in an environment of one endian
1603  other endianness. This is the error that PCRE gives when the magic number is  other endianness. This is the error that PCRE gives when the magic number is
1604  not present.  not present.
1605  .sp  .sp
1606    PCRE_ERROR_UNKNOWN_NODE   (-5)    PCRE_ERROR_UNKNOWN_OPCODE (-5)
1607  .sp  .sp
1608  While running the pattern match, an unknown item was encountered in the  While running the pattern match, an unknown item was encountered in the
1609  compiled pattern. This error could be caused by a bug in PCRE or by overwriting  compiled pattern. This error could be caused by a bug in PCRE or by overwriting
# Line 1282  The backtracking limit, as specified by Line 1629  The backtracking limit, as specified by
1629  \fBpcre_extra\fP structure (or defaulted) was reached. See the description  \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1630  above.  above.
1631  .sp  .sp
   PCRE_ERROR_RECURSIONLIMIT (-21)  
 .sp  
 The internal recursion limit, as specified by the \fImatch_limit_recursion\fP  
 field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the  
 description above.  
 .sp  
1632    PCRE_ERROR_CALLOUT        (-9)    PCRE_ERROR_CALLOUT        (-9)
1633  .sp  .sp
1634  This error is never generated by \fBpcre_exec()\fP itself. It is provided for  This error is never generated by \fBpcre_exec()\fP itself. It is provided for
# Line 1316  documentation for details of partial mat Line 1657  documentation for details of partial mat
1657  .sp  .sp
1658    PCRE_ERROR_BADPARTIAL     (-13)    PCRE_ERROR_BADPARTIAL     (-13)
1659  .sp  .sp
1660  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
1661  are not supported for partial matching. See the  option was used with a compiled pattern containing items that were not
1662  .\" HREF  supported for partial matching. From release 8.00 onwards, there are no
1663  \fBpcrepartial\fP  restrictions on partial matching.
 .\"  
 documentation for details of partial matching.  
1664  .sp  .sp
1665    PCRE_ERROR_INTERNAL       (-14)    PCRE_ERROR_INTERNAL       (-14)
1666  .sp  .sp
# Line 1331  in PCRE or by overwriting of the compile Line 1670  in PCRE or by overwriting of the compile
1670    PCRE_ERROR_BADCOUNT       (-15)    PCRE_ERROR_BADCOUNT       (-15)
1671  .sp  .sp
1672  This error is given if the value of the \fIovecsize\fP argument is negative.  This error is given if the value of the \fIovecsize\fP argument is negative.
1673    .sp
1674      PCRE_ERROR_RECURSIONLIMIT (-21)
1675    .sp
1676    The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1677    field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1678    description above.
1679    .sp
1680      PCRE_ERROR_BADNEWLINE     (-23)
1681    .sp
1682    An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1683    .P
1684    Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1685  .  .
1686  .  .
1687  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1342  This error is given if the value of the Line 1693  This error is given if the value of the
1693  .ti +5n  .ti +5n
1694  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1695  .PP  .PP
 .br  
1696  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1697  .ti +5n  .ti +5n
1698  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1699  .ti +5n  .ti +5n
1700  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1701  .PP  .PP
 .br  
1702  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1703  .ti +5n  .ti +5n
1704  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
# Line 1360  Captured substrings can be accessed dire Line 1709  Captured substrings can be accessed dire
1709  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
1710  as new, separate, zero-terminated strings. These functions identify substrings  as new, separate, zero-terminated strings. These functions identify substrings
1711  by number. The next section describes functions for extracting named  by number. The next section describes functions for extracting named
1712  substrings. A substring that contains a binary zero is correctly extracted and  substrings.
1713  has a further zero added on the end, but the result is not, of course,  .P
1714  a C string.  A substring that contains a binary zero is correctly extracted and has a
1715    further zero added on the end, but the result is not, of course, a C string.
1716    However, you can process such a string by referring to the length that is
1717    returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
1718    Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
1719    for handling strings containing binary zeros, because the end of the final
1720    string is not independently indicated.
1721  .P  .P
1722  The first three arguments are the same for all three of these functions:  The first three arguments are the same for all three of these functions:
1723  \fIsubject\fP is the subject string that has just been successfully matched,  \fIsubject\fP is the subject string that has just been successfully matched,
# Line 1382  the string is placed in \fIbuffer\fP, wh Line 1737  the string is placed in \fIbuffer\fP, wh
1737  \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is  \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is
1738  obtained via \fBpcre_malloc\fP, and its address is returned via  obtained via \fBpcre_malloc\fP, and its address is returned via
1739  \fIstringptr\fP. The yield of the function is the length of the string, not  \fIstringptr\fP. The yield of the function is the length of the string, not
1740  including the terminating zero, or one of  including the terminating zero, or one of these error codes:
1741  .sp  .sp
1742    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1743  .sp  .sp
# Line 1398  and builds a list of pointers to them. A Line 1753  and builds a list of pointers to them. A
1753  memory that is obtained via \fBpcre_malloc\fP. The address of the memory block  memory that is obtained via \fBpcre_malloc\fP. The address of the memory block
1754  is returned via \fIlistptr\fP, which is also the start of the list of string  is returned via \fIlistptr\fP, which is also the start of the list of string
1755  pointers. The end of the list is marked by a NULL pointer. The yield of the  pointers. The end of the list is marked by a NULL pointer. The yield of the
1756  function is zero if all went well, or  function is zero if all went well, or the error code
1757  .sp  .sp
1758    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1759  .sp  .sp
# Line 1417  a previous call of \fBpcre_get_substring Line 1772  a previous call of \fBpcre_get_substring
1772  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
1773  the function pointed to by \fBpcre_free\fP, which of course could be called  the function pointed to by \fBpcre_free\fP, which of course could be called
1774  directly from a C program. However, PCRE is used in some situations where it is  directly from a C program. However, PCRE is used in some situations where it is
1775  linked via a special interface to another programming language which cannot use  linked via a special interface to another programming language that cannot use
1776  \fBpcre_free\fP directly; it is for these cases that the functions are  \fBpcre_free\fP directly; it is for these cases that the functions are
1777  provided.  provided.
1778  .  .
# Line 1429  provided. Line 1784  provided.
1784  .ti +5n  .ti +5n
1785  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1786  .PP  .PP
 .br  
1787  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1788  .ti +5n  .ti +5n
1789  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1438  provided. Line 1792  provided.
1792  .ti +5n  .ti +5n
1793  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1794  .PP  .PP
 .br  
1795  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1796  .ti +5n  .ti +5n
1797  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1450  provided. Line 1803  provided.
1803  To extract a substring by name, you first have to find associated number.  To extract a substring by name, you first have to find associated number.
1804  For example, for this pattern  For example, for this pattern
1805  .sp  .sp
1806    (a+)b(?P<xxx>\ed+)...    (a+)b(?<xxx>\ed+)...
1807  .sp  .sp
1808  the number of the subpattern called "xxx" is 2. You can find the number from  the number of the subpattern called "xxx" is 2. If the name is known to be
1809  the name by calling \fBpcre_get_stringnumber()\fP. The first argument is the  unique (PCRE_DUPNAMES was not set), you can find the number from the name by
1810  compiled pattern, and the second is the name. The yield of the function is the  calling \fBpcre_get_stringnumber()\fP. The first argument is the compiled
1811    pattern, and the second is the name. The yield of the function is the
1812  subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of  subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of
1813  that name.  that name.
1814  .P  .P
# Line 1462  Given the number, you can extract the su Line 1816  Given the number, you can extract the su
1816  functions described in the previous section. For convenience, there are also  functions described in the previous section. For convenience, there are also
1817  two functions that do the whole job.  two functions that do the whole job.
1818  .P  .P
1819  Most of the arguments of \fIpcre_copy_named_substring()\fP and  Most of the arguments of \fBpcre_copy_named_substring()\fP and
1820  \fIpcre_get_named_substring()\fP are the same as those for the similarly named  \fBpcre_get_named_substring()\fP are the same as those for the similarly named
1821  functions that extract by number. As these are described in the previous  functions that extract by number. As these are described in the previous
1822  section, they are not re-described here. There are just two differences:  section, they are not re-described here. There are just two differences:
1823  .P  .P
# Line 1473  pattern. This is needed in order to gain Line 1827  pattern. This is needed in order to gain
1827  translation table.  translation table.
1828  .P  .P
1829  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1830  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1831  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1832    the behaviour may not be what you want (see the next section).
1833    .P
1834    \fBWarning:\fP If the pattern uses the (?| feature to set up multiple
1835    subpatterns with the same number, as described in the
1836    .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
1837    .\" </a>
1838    section on duplicate subpattern numbers
1839    .\"
1840    in the
1841    .\" HREF
1842    \fBpcrepattern\fP
1843    .\"
1844    page, you cannot use names to distinguish the different subpatterns, because
1845    names are not included in the compiled code. The matching process uses only
1846    numbers. For this reason, the use of different names for subpatterns of the
1847    same number causes an error at compile time.
1848    .
1849    .SH "DUPLICATE SUBPATTERN NAMES"
1850    .rs
1851    .sp
1852    .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
1853    .ti +5n
1854    .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
1855    .PP
1856    When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
1857    are not required to be unique. (Duplicate names are always allowed for
1858    subpatterns with the same number, created by using the (?| feature. Indeed, if
1859    such subpatterns are named, they are required to use the same names.)
1860    .P
1861    Normally, patterns with duplicate names are such that in any one match, only
1862    one of the named subpatterns participates. An example is shown in the
1863    .\" HREF
1864    \fBpcrepattern\fP
1865    .\"
1866    documentation.
1867    .P
1868    When duplicates are present, \fBpcre_copy_named_substring()\fP and
1869    \fBpcre_get_named_substring()\fP return the first substring corresponding to
1870    the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
1871    returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1872    returns one of the numbers that are associated with the name, but it is not
1873    defined which it is.
1874    .P
1875    If you want to get full details of all captured substrings for a given name,
1876    you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1877    argument is the compiled pattern, and the second is the name. The third and
1878    fourth are pointers to variables which are updated by the function. After it
1879    has run, they point to the first and last entries in the name-to-number table
1880    for the given name. The function itself returns the length of each entry, or
1881    PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1882    described above in the section entitled \fIInformation about a pattern\fP.
1883    Given all the relevant entries for the name, you can extract each of their
1884    numbers, and hence the captured data, if any.
1885  .  .
1886  .  .
1887  .SH "FINDING ALL POSSIBLE MATCHES"  .SH "FINDING ALL POSSIBLE MATCHES"
# Line 1512  will yield PCRE_ERROR_NOMATCH. Line 1919  will yield PCRE_ERROR_NOMATCH.
1919  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
1920  .P  .P
1921  The function \fBpcre_dfa_exec()\fP is called to match a subject string against  The function \fBpcre_dfa_exec()\fP is called to match a subject string against
1922  a compiled pattern, using a "DFA" matching algorithm. This has different  a compiled pattern, using a matching algorithm that scans the subject string
1923  characteristics to the normal algorithm, and is not compatible with Perl. Some  just once, and does not backtrack. This has different characteristics to the
1924  of the features of PCRE patterns are not supported. Nevertheless, there are  normal algorithm, and is not compatible with Perl. Some of the features of PCRE
1925  times when this kind of matching can be useful. For a discussion of the two  patterns are not supported. Nevertheless, there are times when this kind of
1926  matching algorithms, see the  matching can be useful. For a discussion of the two matching algorithms, and a
1927    list of features that \fBpcre_dfa_exec()\fP does not support, see the
1928  .\" HREF  .\" HREF
1929  \fBpcrematching\fP  \fBpcrematching\fP
1930  .\"  .\"
# Line 1531  here. Line 1939  here.
1939  The two additional arguments provide workspace for the function. The workspace  The two additional arguments provide workspace for the function. The workspace
1940  vector should contain at least 20 elements. It is used for keeping track of  vector should contain at least 20 elements. It is used for keeping track of
1941  multiple paths through the pattern tree. More workspace will be needed for  multiple paths through the pattern tree. More workspace will be needed for
1942  patterns and subjects where there are a lot of possible matches.  patterns and subjects where there are a lot of potential matches.
1943  .P  .P
1944  Here is an example of a simple call to \fBpcre_dfa_exec()\fP:  Here is an example of a simple call to \fBpcre_dfa_exec()\fP:
1945  .sp  .sp
# Line 1554  Here is an example of a simple call to \ Line 1962  Here is an example of a simple call to \
1962  .rs  .rs
1963  .sp  .sp
1964  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
1965  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NOTBOL,  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1966  PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
1967  PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are  PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST,
1968  the same as for \fBpcre_exec()\fP, so their description is not repeated here.  and PCRE_DFA_RESTART. All but the last four of these are exactly the same as
1969  .sp  for \fBpcre_exec()\fP, so their description is not repeated here.
1970    PCRE_PARTIAL  .sp
1971  .sp    PCRE_PARTIAL_HARD
1972  This has the same general effect as it does for \fBpcre_exec()\fP, but the    PCRE_PARTIAL_SOFT
1973  details are slightly different. When PCRE_PARTIAL is set for  .sp
1974  \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into  These have the same general effect as they do for \fBpcre_exec()\fP, but the
1975  PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no  details are slightly different. When PCRE_PARTIAL_HARD is set for
1976  complete matches, but there is still at least one matching possibility. The  \fBpcre_dfa_exec()\fP, it returns PCRE_ERROR_PARTIAL if the end of the subject
1977  portion of the string that provided the partial match is set as the first  is reached and there is still at least one matching possibility that requires
1978  matching string.  additional characters. This happens even if some complete matches have also
1979    been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH
1980    is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached,
1981    there have been no complete matches, but there is still at least one matching
1982    possibility. The portion of the string that was inspected when the longest
1983    partial match was found is set as the first matching string in both cases.
1984  .sp  .sp
1985    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
1986  .sp  .sp
1987  Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as  Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
1988  soon as it has found one match. Because of the way the DFA algorithm works,  soon as it has found one match. Because of the way the alternative algorithm
1989  this is necessarily the shortest possible match at the first possible matching  works, this is necessarily the shortest possible match at the first possible
1990  point in the subject string.  matching point in the subject string.
1991  .sp  .sp
1992    PCRE_DFA_RESTART    PCRE_DFA_RESTART
1993  .sp  .sp
1994  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
1995  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
1996  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
1997  option requests this action; when it is set, the \fIworkspace\fP and  \fIworkspace\fP and \fIwscount\fP options must reference the same vector as
1998  \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
1999  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  
2000  .\" HREF  .\" HREF
2001  \fBpcrepartial\fP  \fBpcrepartial\fP
2002  .\"  .\"
# Line 1613  the three matched strings are Line 2025  the three matched strings are
2025  On success, the yield of the function is a number greater than zero, which is  On success, the yield of the function is a number greater than zero, which is
2026  the number of matched substrings. The substrings themselves are returned in  the number of matched substrings. The substrings themselves are returned in
2027  \fIovector\fP. Each string uses two elements; the first is the offset to the  \fIovector\fP. Each string uses two elements; the first is the offset to the
2028  start, and the second is the offset to the end. All the strings have the same  start, and the second is the offset to the end. In fact, all the strings have
2029  start offset. (Space could have been saved by giving this only once, but it was  the same start offset. (Space could have been saved by giving this only once,
2030  decided to retain some compatibility with the way \fBpcre_exec()\fP returns  but it was decided to retain some compatibility with the way \fBpcre_exec()\fP
2031  data, even though the meaning of the strings is different.)  returns data, even though the meaning of the strings is different.)
2032  .P  .P
2033  The strings are returned in reverse order of length; that is, the longest  The strings are returned in reverse order of length; that is, the longest
2034  matching string is given first. If there were too many matches to fit into  matching string is given first. If there were too many matches to fit into
# Line 1643  that it does not support, for instance, Line 2055  that it does not support, for instance,
2055  .sp  .sp
2056    PCRE_ERROR_DFA_UCOND      (-17)    PCRE_ERROR_DFA_UCOND      (-17)
2057  .sp  .sp
2058  This return is given if \fBpcre_dfa_exec()\fP encounters a condition item in a  This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that
2059  pattern that uses a back reference for the condition. This is not supported.  uses a back reference for the condition, or a test for recursion in a specific
2060    group. These are not supported.
2061  .sp  .sp
2062    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
2063  .sp  .sp
# Line 1663  When a recursive subpattern is processed Line 2076  When a recursive subpattern is processed
2076  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
2077  error is given if the output vector is not large enough. This should be  error is given if the output vector is not large enough. This should be
2078  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
2079  .P  .
2080  .in 0  .
2081  Last updated: 18 January 2006  .SH "SEE ALSO"
2082  .br  .rs
2083  Copyright (c) 1997-2006 University of Cambridge.  .sp
2084    \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
2085    \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
2086    \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
2087    .
2088    .
2089    .SH AUTHOR
2090    .rs
2091    .sp
2092    .nf
2093    Philip Hazel
2094    University Computing Service
2095    Cambridge CB2 3QH, England.
2096    .fi
2097    .
2098    .
2099    .SH REVISION
2100    .rs
2101    .sp
2102    .nf
2103    Last updated: 03 May 2010
2104    Copyright (c) 1997-2010 University of Cambridge.
2105    .fi

Legend:
Removed from v.87  
changed lines
  Added in v.513

  ViewVC Help
Powered by ViewVC 1.1.5