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

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

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

revision 77 by nigel, Sat Feb 24 21:40:45 2007 UTC revision 429 by ph10, Tue Sep 1 16:10:16 2009 UTC
# Line 1  Line 1 
1  .TH PCRE 3  .TH PCREAPI 3
2  .SH NAME  .SH NAME
3  PCRE - Perl-compatible regular expressions  PCRE - Perl-compatible regular expressions
4  .SH "PCRE NATIVE API"  .SH "PCRE NATIVE API"
# Line 7  PCRE - Perl-compatible regular expressio Line 7  PCRE - Perl-compatible regular expressio
7  .B #include <pcre.h>  .B #include <pcre.h>
8  .PP  .PP
9  .SM  .SM
 .br  
10  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
11  .ti +5n  .ti +5n
12  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
13  .ti +5n  .ti +5n
14  .B const unsigned char *\fItableptr\fP);  .B const unsigned char *\fItableptr\fP);
15  .PP  .PP
 .br  
16  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
17  .ti +5n  .ti +5n
18  .B int *\fIerrorcodeptr\fP,  .B int *\fIerrorcodeptr\fP,
# Line 23  PCRE - Perl-compatible regular expressio Line 21  PCRE - Perl-compatible regular expressio
21  .ti +5n  .ti +5n
22  .B const unsigned char *\fItableptr\fP);  .B const unsigned char *\fItableptr\fP);
23  .PP  .PP
 .br  
24  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,
25  .ti +5n  .ti +5n
26  .B const char **\fIerrptr\fP);  .B const char **\fIerrptr\fP);
27  .PP  .PP
 .br  
28  .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
29  .ti +5n  .ti +5n
30  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
31  .ti +5n  .ti +5n
32  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
33  .PP  .PP
 .br  
34  .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
35  .ti +5n  .ti +5n
36  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
# Line 44  PCRE - Perl-compatible regular expressio Line 39  PCRE - Perl-compatible regular expressio
39  .ti +5n  .ti +5n
40  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
41  .PP  .PP
 .br  
42  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
43  .ti +5n  .ti +5n
44  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 53  PCRE - Perl-compatible regular expressio Line 47  PCRE - Perl-compatible regular expressio
47  .ti +5n  .ti +5n
48  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
49  .PP  .PP
 .br  
50  .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
51  .ti +5n  .ti +5n
52  .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
53  .ti +5n  .ti +5n
54  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
55  .PP  .PP
 .br  
56  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
57  .ti +5n  .ti +5n
58  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 69  PCRE - Perl-compatible regular expressio Line 61  PCRE - Perl-compatible regular expressio
61  .ti +5n  .ti +5n
62  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
63  .PP  .PP
 .br  
64  .B int pcre_get_stringnumber(const pcre *\fIcode\fP,  .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
65  .ti +5n  .ti +5n
66  .B const char *\fIname\fP);  .B const char *\fIname\fP);
67  .PP  .PP
68  .br  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
69    .ti +5n
70    .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
71    .PP
72  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
73  .ti +5n  .ti +5n
74  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
75  .ti +5n  .ti +5n
76  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
77  .PP  .PP
 .br  
78  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
79  .ti +5n  .ti +5n
80  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
81  .PP  .PP
 .br  
82  .B void pcre_free_substring(const char *\fIstringptr\fP);  .B void pcre_free_substring(const char *\fIstringptr\fP);
83  .PP  .PP
 .br  
84  .B void pcre_free_substring_list(const char **\fIstringptr\fP);  .B void pcre_free_substring_list(const char **\fIstringptr\fP);
85  .PP  .PP
 .br  
86  .B const unsigned char *pcre_maketables(void);  .B const unsigned char *pcre_maketables(void);
87  .PP  .PP
 .br  
88  .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
89  .ti +5n  .ti +5n
90  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
91  .PP  .PP
 .br  
92  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
93  .B *\fIfirstcharptr\fP);  .B *\fIfirstcharptr\fP);
94  .PP  .PP
 .br  
95  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
96  .PP  .PP
 .br  
97  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
98  .PP  .PP
 .br  
99  .B char *pcre_version(void);  .B char *pcre_version(void);
100  .PP  .PP
 .br  
101  .B void *(*pcre_malloc)(size_t);  .B void *(*pcre_malloc)(size_t);
102  .PP  .PP
 .br  
103  .B void (*pcre_free)(void *);  .B void (*pcre_free)(void *);
104  .PP  .PP
 .br  
105  .B void *(*pcre_stack_malloc)(size_t);  .B void *(*pcre_stack_malloc)(size_t);
106  .PP  .PP
 .br  
107  .B void (*pcre_stack_free)(void *);  .B void (*pcre_stack_free)(void *);
108  .PP  .PP
 .br  
109  .B int (*pcre_callout)(pcre_callout_block *);  .B int (*pcre_callout)(pcre_callout_block *);
110  .  .
111  .  .
112  .SH "PCRE API OVERVIEW"  .SH "PCRE API OVERVIEW"
113  .rs  .rs
114  .sp  .sp
115  PCRE has its own native API, which is described in this document. There is  PCRE has its own native API, which is described in this document. There are
116  also a set of wrapper functions that correspond to the POSIX regular expression  also some wrapper functions that correspond to the POSIX regular expression
117  API. These are described in the  API. These are described in the
118  .\" HREF  .\" HREF
119  \fBpcreposix\fP  \fBpcreposix\fP
# Line 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. However, this algorithm
153  substrings. A description of the two matching algorithms and their advantages  does not return captured substrings. A description of the two matching
154  and disadvantages is given in the  algorithms and their advantages and disadvantages is given in the
155  .\" HREF  .\" HREF
156  \fBpcrematching\fP  \fBpcrematching\fP
157  .\"  .\"
# Line 183  matched by \fBpcre_exec()\fP. They are: Line 167  matched by \fBpcre_exec()\fP. They are:
167    \fBpcre_get_named_substring()\fP    \fBpcre_get_named_substring()\fP
168    \fBpcre_get_substring_list()\fP    \fBpcre_get_substring_list()\fP
169    \fBpcre_get_stringnumber()\fP    \fBpcre_get_stringnumber()\fP
170      \fBpcre_get_stringtable_entries()\fP
171  .sp  .sp
172  \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also  \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also
173  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 197  should be done before calling any PCRE f
197  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
198  indirections to memory management functions. These special functions are used  indirections to memory management functions. These special functions are used
199  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
200  recursive function calls, when running the \fBpcre_exec()\fP function. This is  recursive function calls, when running the \fBpcre_exec()\fP function. See the
201  a non-standard way of building PCRE, for use in environments that have limited  .\" HREF
202  stacks. Because of the greater use of memory management, it runs more slowly.  \fBpcrebuild\fP
203  Separate functions are provided so that special-purpose external code can be  .\"
204  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
205  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
206  the same size.  greater use of memory management, it runs more slowly. Separate functions are
207    provided so that special-purpose external code can be used for this case. When
208    used, these functions are always called in a stack-like manner (last obtained,
209    first freed), and always for memory blocks of the same size. There is a
210    discussion about PCRE's stack usage in the
211    .\" HREF
212    \fBpcrestack\fP
213    .\"
214    documentation.
215  .P  .P
216  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
217  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 222  points during a matching operation. Deta
222  documentation.  documentation.
223  .  .
224  .  .
225    .\" HTML <a name="newlines"></a>
226    .SH NEWLINES
227    .rs
228    .sp
229    PCRE supports five different conventions for indicating line breaks in
230    strings: a single CR (carriage return) character, a single LF (linefeed)
231    character, the two-character sequence CRLF, any of the three preceding, or any
232    Unicode newline sequence. The Unicode newline sequences are the three just
233    mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
234    U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
235    (paragraph separator, U+2029).
236    .P
237    Each of the first three conventions is used by at least one operating system as
238    its standard newline sequence. When PCRE is built, a default can be specified.
239    The default default is LF, which is the Unix standard. When PCRE is run, the
240    default can be overridden, either when a pattern is compiled, or when it is
241    matched.
242    .P
243    At compile time, the newline convention can be specified by the \fIoptions\fP
244    argument of \fBpcre_compile()\fP, or it can be specified by special text at the
245    start of the pattern itself; this overrides any other settings. See the
246    .\" HREF
247    \fBpcrepattern\fP
248    .\"
249    page for details of the special character sequences.
250    .P
251    In the PCRE documentation the word "newline" is used to mean "the character or
252    pair of characters that indicate a line break". The choice of newline
253    convention affects the handling of the dot, circumflex, and dollar
254    metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
255    recognized line ending sequence, the match position advancement for a
256    non-anchored pattern. There is more detail about this in the
257    .\" HTML <a href="#execoptions">
258    .\" </a>
259    section on \fBpcre_exec()\fP options
260    .\"
261    below.
262    .P
263    The choice of newline convention does not affect the interpretation of
264    the \en or \er escape sequences, nor does it affect what \eR matches, which is
265    controlled in a similar way, but by separate options.
266    .
267    .
268  .SH MULTITHREADING  .SH MULTITHREADING
269  .rs  .rs
270  .sp  .sp
# Line 250  which it was compiled. Details are given Line 286  which it was compiled. Details are given
286  .\" HREF  .\" HREF
287  \fBpcreprecompile\fP  \fBpcreprecompile\fP
288  .\"  .\"
289  documentation.  documentation. However, compiling a regular expression with one version of PCRE
290    for use with a different version is not guaranteed to work and may cause
291    crashes.
292  .  .
293  .  .
294  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 281  properties is available; otherwise it is Line 319  properties is available; otherwise it is
319  .sp  .sp
320    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
321  .sp  .sp
322  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
323  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
324  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.
325    Though they are derived from ASCII, the same values are returned in EBCDIC
326    environments. The default should normally correspond to the standard sequence
327    for your operating system.
328    .sp
329      PCRE_CONFIG_BSR
330    .sp
331    The output is an integer whose value indicates what character sequences the \eR
332    escape sequence matches by default. A value of 0 means that \eR matches any
333    Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
334    or CRLF. The default can be overridden when a pattern is compiled or matched.
335  .sp  .sp
336    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
337  .sp  .sp
# Line 305  documentation. Line 353  documentation.
353  .sp  .sp
354    PCRE_CONFIG_MATCH_LIMIT    PCRE_CONFIG_MATCH_LIMIT
355  .sp  .sp
356  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
357  internal matching function calls in a \fBpcre_exec()\fP execution. Further  internal matching function calls in a \fBpcre_exec()\fP execution. Further
358  details are given with \fBpcre_exec()\fP below.  details are given with \fBpcre_exec()\fP below.
359  .sp  .sp
360      PCRE_CONFIG_MATCH_LIMIT_RECURSION
361    .sp
362    The output is a long integer that gives the default limit for the depth of
363    recursion when calling the internal matching function in a \fBpcre_exec()\fP
364    execution. Further details are given with \fBpcre_exec()\fP below.
365    .sp
366    PCRE_CONFIG_STACKRECURSE    PCRE_CONFIG_STACKRECURSE
367  .sp  .sp
368  The output is an integer that is set to one if internal recursion when running  The output is an integer that is set to one if internal recursion when running
# Line 347  The pattern is a C string terminated by Line 401  The pattern is a C string terminated by
401  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
402  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
403  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
404  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.
405  .P  .P
406  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
407  depend on memory location, the complete \fBpcre\fP data block is not  depend on memory location, the complete \fBpcre\fP data block is not
408  fully relocatable, because it may contain a copy of the \fItableptr\fP  fully relocatable, because it may contain a copy of the \fItableptr\fP
409  argument, which is an address (see below).  argument, which is an address (see below).
410  .P  .P
411  The \fIoptions\fP argument contains independent bits that affect the  The \fIoptions\fP argument contains various bit settings that affect the
412  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
413  options are described below. Some of them, in particular, those that are  options are described below. Some of them (in particular, those that are
414  compatible with Perl, can also be set and unset from within the pattern (see  compatible with Perl, but also some others) can also be set and unset from
415  the detailed description in the  within the pattern (see the detailed description in the
416  .\" HREF  .\" HREF
417  \fBpcrepattern\fP  \fBpcrepattern\fP
418  .\"  .\"
419  documentation). For these options, the contents of the \fIoptions\fP argument  documentation). For those options that can be different in different parts of
420  specifies their initial settings at the start of compilation and execution. The  the pattern, the contents of the \fIoptions\fP argument specifies their initial
421  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 and
422  time.  PCRE_NEWLINE_\fIxxx\fP options can be set at the time of matching as well as at
423    compile time.
424  .P  .P
425  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
426  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
427  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
428  error message. The offset from the start of the pattern to the character where  error message. This is a static string that is part of the library. You must
429  the error was discovered is placed in the variable pointed to by  not try to free it. The offset from the start of the pattern to the character
430    where the error was discovered is placed in the variable pointed to by
431  \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.  \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.
432  .P  .P
433  If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the  If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the
# Line 419  facility, see the Line 475  facility, see the
475  .\"  .\"
476  documentation.  documentation.
477  .sp  .sp
478      PCRE_BSR_ANYCRLF
479      PCRE_BSR_UNICODE
480    .sp
481    These options (which are mutually exclusive) control what the \eR escape
482    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
483    match any Unicode newline sequence. The default is specified when PCRE is
484    built. It can be overridden from within the pattern, or by setting an option
485    when a compiled pattern is matched.
486    .sp
487    PCRE_CASELESS    PCRE_CASELESS
488  .sp  .sp
489  If this bit is set, letters in the pattern match both upper and lower case  If this bit is set, letters in the pattern match both upper and lower case
# Line 435  with UTF-8 support. Line 500  with UTF-8 support.
500  .sp  .sp
501  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
502  end of the subject string. Without this option, a dollar also matches  end of the subject string. Without this option, a dollar also matches
503  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
504  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.
505  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
506  a pattern.  pattern.
507  .sp  .sp
508    PCRE_DOTALL    PCRE_DOTALL
509  .sp  .sp
510  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,
511  including newlines. Without it, newlines are excluded. This option is  including those that indicate newline. Without it, a dot does not match when
512  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
513  (?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
514  character, independent of the setting of this option.  negative class such as [^a] always matches newline characters, independent of
515    the setting of this option.
516    .sp
517      PCRE_DUPNAMES
518    .sp
519    If this bit is set, names used to identify capturing subpatterns need not be
520    unique. This can be helpful for certain types of pattern when it is known that
521    only one instance of the named subpattern can ever be matched. There are more
522    details of named subpatterns below; see also the
523    .\" HREF
524    \fBpcrepattern\fP
525    .\"
526    documentation.
527  .sp  .sp
528    PCRE_EXTENDED    PCRE_EXTENDED
529  .sp  .sp
530  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
531  ignored except when escaped or inside a character class. Whitespace does not  ignored except when escaped or inside a character class. Whitespace does not
532  include the VT character (code 11). In addition, characters between an  include the VT character (code 11). In addition, characters between an
533  unescaped # outside a character class and the next newline character,  unescaped # outside a character class and the next newline, inclusive, are also
534  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
535  be changed within a pattern by a (?x) option setting.  pattern by a (?x) option setting.
536  .P  .P
537  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
538  Note, however, that this applies only to data characters. Whitespace characters  Note, however, that this applies only to data characters. Whitespace characters
# Line 469  that is incompatible with Perl, but it i Line 546  that is incompatible with Perl, but it i
546  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
547  special meaning causes an error, thus reserving these combinations for future  special meaning causes an error, thus reserving these combinations for future
548  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
549  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
550  controlled by this option. It can also be set by a (?X) option setting within a  give a warning for this.) There are at present no other features controlled by
551  pattern.  this option. It can also be set by a (?X) option setting within a pattern.
552  .sp  .sp
553    PCRE_FIRSTLINE    PCRE_FIRSTLINE
554  .sp  .sp
555  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
556  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
557  continue over the newline.  over the newline.
558    .sp
559      PCRE_JAVASCRIPT_COMPAT
560    .sp
561    If this option is set, PCRE's behaviour is changed in some ways so that it is
562    compatible with JavaScript rather than Perl. The changes are as follows:
563    .P
564    (1) A lone closing square bracket in a pattern causes a compile-time error,
565    because this is illegal in JavaScript (by default it is treated as a data
566    character). Thus, the pattern AB]CD becomes illegal when this option is set.
567    .P
568    (2) At run time, a back reference to an unset subpattern group matches an empty
569    string (by default this causes the current matching alternative to fail). A
570    pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
571    an "a" in the subject), whereas it fails by default, for Perl compatibility.
572  .sp  .sp
573    PCRE_MULTILINE    PCRE_MULTILINE
574  .sp  .sp
# Line 489  terminating newline (unless PCRE_DOLLAR_ Line 580  terminating newline (unless PCRE_DOLLAR_
580  Perl.  Perl.
581  .P  .P
582  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
583  match immediately following or immediately before any newline in the subject  match immediately following or immediately before internal newlines in the
584  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
585  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
586  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
587  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
588  .sp  .sp
589      PCRE_NEWLINE_CR
590      PCRE_NEWLINE_LF
591      PCRE_NEWLINE_CRLF
592      PCRE_NEWLINE_ANYCRLF
593      PCRE_NEWLINE_ANY
594    .sp
595    These options override the default newline definition that was chosen when PCRE
596    was built. Setting the first or the second specifies that a newline is
597    indicated by a single character (CR or LF, respectively). Setting
598    PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
599    CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
600    preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
601    that any Unicode newline sequence should be recognized. The Unicode newline
602    sequences are the three just mentioned, plus the single characters VT (vertical
603    tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
604    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
605    recognized only in UTF-8 mode.
606    .P
607    The newline setting in the options word uses three bits that are treated
608    as a number, giving eight possibilities. Currently only six are used (default
609    plus the five values above). This means that if you set more than one newline
610    option, the combination may or may not be sensible. For example,
611    PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
612    other combinations may yield unused numbers and cause an error.
613    .P
614    The only time that a line break is specially recognized when compiling a
615    pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
616    class is encountered. This indicates a comment that lasts until after the next
617    line break sequence. In other circumstances, line break sequences are treated
618    as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
619    as whitespace characters and are therefore ignored.
620    .P
621    The newline option that is set at compile time becomes the default that is used
622    for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
623    .sp
624    PCRE_NO_AUTO_CAPTURE    PCRE_NO_AUTO_CAPTURE
625  .sp  .sp
626  If this option is set, it disables the use of numbered capturing parentheses in  If this option is set, it disables the use of numbered capturing parentheses in
# Line 529  page. Line 655  page.
655    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
656  .sp  .sp
657  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
658  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
659  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
660  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
661  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
662  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
663  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
664  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
665  strings.  \fBpcre\fP
666    .\"
667    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
668    returns an error. If you already know that your pattern is valid, and you want
669    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
670    option. When it is set, the effect of passing an invalid UTF-8 string as a
671    pattern is undefined. It may cause your program to crash. Note that this option
672    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
673    the UTF-8 validity checking of subject strings.
674  .  .
675  .  .
676  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 544  strings. Line 678  strings.
678  .sp  .sp
679  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
680  \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
681  both compiling functions.  both compiling functions. As PCRE has developed, some error codes have fallen
682    out of use. To avoid confusion, they have not been re-used.
683  .sp  .sp
684     0  no error     0  no error
685     1  \e at end of pattern     1  \e at end of pattern
# Line 556  both compiling functions. Line 691  both compiling functions.
691     7  invalid escape sequence in character class     7  invalid escape sequence in character class
692     8  range out of order in character class     8  range out of order in character class
693     9  nothing to repeat     9  nothing to repeat
694    10  operand of unlimited repeat could match the empty string    10  [this code is not in use]
695    11  internal error: unexpected repeat    11  internal error: unexpected repeat
696    12  unrecognized character after (?    12  unrecognized character after (? or (?-
697    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
698    14  missing )    14  missing )
699    15  reference to non-existent subpattern    15  reference to non-existent subpattern
700    16  erroffset passed as NULL    16  erroffset passed as NULL
701    17  unknown option bit(s) set    17  unknown option bit(s) set
702    18  missing ) after comment    18  missing ) after comment
703    19  parentheses nested too deeply    19  [this code is not in use]
704    20  regular expression too large    20  regular expression is too large
705    21  failed to get memory    21  failed to get memory
706    22  unmatched parentheses    22  unmatched parentheses
707    23  internal error: code overflow    23  internal error: code overflow
708    24  unrecognized character after (?<    24  unrecognized character after (?<
709    25  lookbehind assertion is not fixed length    25  lookbehind assertion is not fixed length
710    26  malformed number after (?(    26  malformed number or name after (?(
711    27  conditional group contains more than two branches    27  conditional group contains more than two branches
712    28  assertion expected after (?(    28  assertion expected after (?(
713    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
714    30  unknown POSIX class name    30  unknown POSIX class name
715    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
716    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
717    33  spare error    33  [this code is not in use]
718    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
719    35  invalid condition (?(0)    35  invalid condition (?(0)
720    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
# Line 588  both compiling functions. Line 723  both compiling functions.
723    39  closing ) for (?C expected    39  closing ) for (?C expected
724    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
725    41  unrecognized character after (?P    41  unrecognized character after (?P
726    42  syntax error after (?P    42  syntax error in subpattern name (missing terminator)
727    43  two named groups have the same name    43  two named subpatterns have the same name
728    44  invalid UTF-8 string    44  invalid UTF-8 string
729    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
730    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
731    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
732      48  subpattern name is too long (maximum 32 characters)
733      49  too many named subpatterns (maximum 10000)
734      50  [this code is not in use]
735      51  octal value is greater than \e377 (not in UTF-8 mode)
736      52  internal error: overran compiling workspace
737      53  internal error: previously-checked referenced subpattern not found
738      54  DEFINE group contains more than one branch
739      55  repeating a DEFINE group is not allowed
740      56  inconsistent NEWLINE options
741      57  \eg is not followed by a braced, angle-bracketed, or quoted
742            name/number or by a plain number
743      58  a numbered reference must not be zero
744      59  (*VERB) with an argument is not supported
745      60  (*VERB) not recognized
746      61  number is too big
747      62  subpattern name expected
748      63  digit expected after (?+
749      64  ] is an invalid data character in JavaScript compatibility mode
750    .sp
751    The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
752    be used if the limits were changed when PCRE was built.
753  .  .
754  .  .
755  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 631  options are defined, and this argument s Line 787  options are defined, and this argument s
787  .P  .P
788  The third argument for \fBpcre_study()\fP is a pointer for an error message. If  The third argument for \fBpcre_study()\fP is a pointer for an error message. If
789  studying succeeds (even if no data is returned), the variable it points to is  studying succeeds (even if no data is returned), the variable it points to is
790  set to NULL. Otherwise it points to a textual error message. You should  set to NULL. Otherwise it is set to point to a textual error message. This is a
791  therefore test the error pointer for NULL after calling \fBpcre_study()\fP, to  static string that is part of the library. You must not try to free it. You
792  be sure that it has run successfully.  should test the error pointer for NULL after calling \fBpcre_study()\fP, to be
793    sure that it has run successfully.
794  .P  .P
795  This is a typical call to \fBpcre_study\fP():  This is a typical call to \fBpcre_study\fP():
796  .sp  .sp
# Line 652  bytes is created. Line 809  bytes is created.
809  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
810  .rs  .rs
811  .sp  .sp
812  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
813  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
814  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
815  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
816  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
817  support.  support. The use of locales with Unicode is discouraged. If you are handling
818  .P  characters with codes greater than 128, you should either use UTF-8 and
819  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.
820  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
821  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
822  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.
823  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
824  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
825    default "C" locale of the local system, which may cause them to be different.
826    .P
827    The internal tables can always be overridden by tables supplied by the
828    application that calls PCRE. These may be created in a different locale from
829    the default. As more and more applications change to using Unicode, the need
830    for this locale support is expected to die away.
831  .P  .P
832  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
833  which has no arguments, in the relevant locale. The result can then be passed  which has no arguments, in the relevant locale. The result can then be passed
# Line 677  the following code could be used: Line 840  the following code could be used:
840    tables = pcre_maketables();    tables = pcre_maketables();
841    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
842  .sp  .sp
843    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
844    are using Windows, the name for the French locale is "french".
845    .P
846  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
847  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
848  that the memory containing the tables remains available for as long as it is  that the memory containing the tables remains available for as long as it is
# Line 723  check against passing an arbitrary memor Line 889  check against passing an arbitrary memor
889  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
890  .sp  .sp
891    int rc;    int rc;
892    unsigned long int length;    size_t length;
893    rc = pcre_fullinfo(    rc = pcre_fullinfo(
894      re,               /* result of pcre_compile() */      re,               /* result of pcre_compile() */
895      pe,               /* result of pcre_study(), or NULL */      pe,               /* result of pcre_study(), or NULL */
# Line 755  a NULL table pointer. Line 921  a NULL table pointer.
921    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
922  .sp  .sp
923  Return information about the first byte of any matched string, for a  Return information about the first byte of any matched string, for a
924  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
925  old name is still recognized for backwards compatibility.)  variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
926    still recognized for backwards compatibility.)
927  .P  .P
928  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
929  (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  
930  .sp  .sp
931  (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
932  starts with "^", or  starts with "^", or
# Line 779  table indicating a fixed set of bytes fo Line 945  table indicating a fixed set of bytes fo
945  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
946  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
947  .sp  .sp
948      PCRE_INFO_HASCRORLF
949    .sp
950    Return 1 if the pattern contains any explicit matches for CR or LF characters,
951    otherwise 0. The fourth argument should point to an \fBint\fP variable. An
952    explicit match is either a literal CR or LF character, or \er or \en.
953    .sp
954      PCRE_INFO_JCHANGED
955    .sp
956    Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
957    0. The fourth argument should point to an \fBint\fP variable. (?J) and
958    (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
959    .sp
960    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
961  .sp  .sp
962  Return the value of the rightmost literal byte that must exist in any matched  Return the value of the rightmost literal byte that must exist in any matched
# Line 795  is -1. Line 973  is -1.
973  .sp  .sp
974  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
975  names are just an additional way of identifying the parentheses, which still  names are just an additional way of identifying the parentheses, which still
976  acquire numbers. A convenience function called \fBpcre_get_named_substring()\fP  acquire numbers. Several convenience functions such as
977  is provided for extracting an individual captured substring by name. It is also  \fBpcre_get_named_substring()\fP are provided for extracting captured
978  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
979  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
980  \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,
981  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
982    values.
983  .P  .P
984  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
985  the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each  the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
# Line 809  length of the longest name. PCRE_INFO_NA Line 988  length of the longest name. PCRE_INFO_NA
988  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
989  are the number of the capturing parenthesis, most significant byte first. The  are the number of the capturing parenthesis, most significant byte first. The
990  rest of the entry is the corresponding name, zero terminated. The names are in  rest of the entry is the corresponding name, zero terminated. The names are in
991  alphabetical order. For example, consider the following pattern (assume  alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of
992    their parentheses numbers. For example, consider the following pattern (assume
993  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  PCRE_EXTENDED is set, so white space - including newlines - is ignored):
994  .sp  .sp
995  .\" JOIN  .\" JOIN
996    (?P<date> (?P<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
997    (?P<month>\ed\ed) - (?P<day>\ed\ed) )    (?<month>\ed\ed) - (?<day>\ed\ed) )
998  .sp  .sp
999  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
1000  in the table is eight bytes long. The table is as follows, with non-printing  in the table is eight bytes long. The table is as follows, with non-printing
# Line 826  bytes shows in hexadecimal, and undefine Line 1006  bytes shows in hexadecimal, and undefine
1006    00 02 y  e  a  r  00 ??    00 02 y  e  a  r  00 ??
1007  .sp  .sp
1008  When writing code to extract data from named subpatterns using the  When writing code to extract data from named subpatterns using the
1009  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
1010  different for each compiled pattern.  different for each compiled pattern.
1011  .sp  .sp
1012      PCRE_INFO_OKPARTIAL
1013    .sp
1014    Return 1 if the pattern can be used for partial matching, otherwise 0. The
1015    fourth argument should point to an \fBint\fP variable. From release 8.00, this
1016    always returns 1, because the restrictions that previously applied to partial
1017    matching have been lifted. The
1018    .\" HREF
1019    \fBpcrepartial\fP
1020    .\"
1021    documentation gives details of partial matching.
1022    .sp
1023    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
1024  .sp  .sp
1025  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
1026  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
1027  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
1028  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
1029    they are the options that will be in force when matching starts. For example,
1030    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1031    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
1032  .P  .P
1033  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
1034  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 964  Here is an example of a simple call to \ Line 1158  Here is an example of a simple call to \
1158  If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP  If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP
1159  data block. The \fBpcre_study()\fP function returns such a block (when it  data block. The \fBpcre_study()\fP function returns such a block (when it
1160  doesn't return NULL), but you can also create one for yourself, and pass  doesn't return NULL), but you can also create one for yourself, and pass
1161  additional information in it. The fields in a \fBpcre_extra\fP block are as  additional information in it. The \fBpcre_extra\fP block contains the following
1162  follows:  fields (not necessarily in this order):
1163  .sp  .sp
1164    unsigned long int \fIflags\fP;    unsigned long int \fIflags\fP;
1165    void *\fIstudy_data\fP;    void *\fIstudy_data\fP;
1166    unsigned long int \fImatch_limit\fP;    unsigned long int \fImatch_limit\fP;
1167      unsigned long int \fImatch_limit_recursion\fP;
1168    void *\fIcallout_data\fP;    void *\fIcallout_data\fP;
1169    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1170  .sp  .sp
# Line 978  are set. The flag bits are: Line 1173  are set. The flag bits are:
1173  .sp  .sp
1174    PCRE_EXTRA_STUDY_DATA    PCRE_EXTRA_STUDY_DATA
1175    PCRE_EXTRA_MATCH_LIMIT    PCRE_EXTRA_MATCH_LIMIT
1176      PCRE_EXTRA_MATCH_LIMIT_RECURSION
1177    PCRE_EXTRA_CALLOUT_DATA    PCRE_EXTRA_CALLOUT_DATA
1178    PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
1179  .sp  .sp
# Line 992  but which have a very large number of po Line 1188  but which have a very large number of po
1188  classic example is the use of nested unlimited repeats.  classic example is the use of nested unlimited repeats.
1189  .P  .P
1190  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly
1191  (sometimes recursively). The limit is imposed on the number of times this  (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the
1192  function is called during a match, which has the effect of limiting the amount  number of times this function is called during a match, which has the effect of
1193  of recursion and backtracking that can take place. For patterns that are not  limiting the amount of backtracking that can take place. For patterns that are
1194  anchored, the count starts from zero for each position in the subject string.  not anchored, the count restarts from zero for each position in the subject
1195    string.
1196  .P  .P
1197  The default limit for the library can be set when PCRE is built; the default  The default value for the limit can be set when PCRE is built; the default
1198  default is 10 million, which handles all but the most extreme cases. You can  default is 10 million, which handles all but the most extreme cases. You can
1199  reduce the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP block  override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP
1200  in which \fImatch_limit\fP is set to a smaller value, and  block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in
1201  PCRE_EXTRA_MATCH_LIMIT is set in the \fIflags\fP field. If the limit is  the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns
1202  exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_MATCHLIMIT.  PCRE_ERROR_MATCHLIMIT.
1203    .P
1204    The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but
1205    instead of limiting the total number of times that \fBmatch()\fP is called, it
1206    limits the depth of recursion. The recursion depth is a smaller number than the
1207    total number of calls, because not all calls to \fBmatch()\fP are recursive.
1208    This limit is of use only if it is set smaller than \fImatch_limit\fP.
1209    .P
1210    Limiting the recursion depth limits the amount of stack that can be used, or,
1211    when PCRE has been compiled to use memory on the heap instead of the stack, the
1212    amount of heap memory that can be used.
1213    .P
1214    The default value for \fImatch_limit_recursion\fP can be set when PCRE is
1215    built; the default default is the same value as the default for
1216    \fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP
1217    with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and
1218    PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
1219    is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1220  .P  .P
1221  The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,  The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,
1222  which is described in the  which is described in the
# Line 1025  called. See the Line 1239  called. See the
1239  .\"  .\"
1240  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1241  .  .
1242    .\" HTML <a name="execoptions"></a>
1243  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1244  .rs  .rs
1245  .sp  .sp
1246  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
1247  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,
1248  PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_START_OPTIMIZE,
1249    PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and PCRE_PARTIAL_HARD.
1250  .sp  .sp
1251    PCRE_ANCHORED    PCRE_ANCHORED
1252  .sp  .sp
# Line 1039  matching position. If a pattern was comp Line 1255  matching position. If a pattern was comp
1255  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
1256  matching time.  matching time.
1257  .sp  .sp
1258      PCRE_BSR_ANYCRLF
1259      PCRE_BSR_UNICODE
1260    .sp
1261    These options (which are mutually exclusive) control what the \eR escape
1262    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1263    match any Unicode newline sequence. These options override the choice that was
1264    made or defaulted when the pattern was compiled.
1265    .sp
1266      PCRE_NEWLINE_CR
1267      PCRE_NEWLINE_LF
1268      PCRE_NEWLINE_CRLF
1269      PCRE_NEWLINE_ANYCRLF
1270      PCRE_NEWLINE_ANY
1271    .sp
1272    These options override the newline definition that was chosen or defaulted when
1273    the pattern was compiled. For details, see the description of
1274    \fBpcre_compile()\fP above. During matching, the newline choice affects the
1275    behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1276    the way the match position is advanced after a match failure for an unanchored
1277    pattern.
1278    .P
1279    When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
1280    match attempt for an unanchored pattern fails when the current position is at a
1281    CRLF sequence, and the pattern contains no explicit matches for CR or LF
1282    characters, the match position is advanced by two characters instead of one, in
1283    other words, to after the CRLF.
1284    .P
1285    The above rule is a compromise that makes the most common cases work as
1286    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1287    set), it does not match the string "\er\enA" because, after failing at the
1288    start, it skips both the CR and the LF before retrying. However, the pattern
1289    [\er\en]A does match that string, because it contains an explicit CR or LF
1290    reference, and so advances only by one character after the first failure.
1291    .P
1292    An explicit match for CR of LF is either a literal appearance of one of those
1293    characters, or one of the \er or \en escape sequences. Implicit matches such as
1294    [^X] do not count, nor does \es (which includes CR and LF in the characters
1295    that it matches).
1296    .P
1297    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1298    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1299    .sp
1300    PCRE_NOTBOL    PCRE_NOTBOL
1301  .sp  .sp
1302  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 1073  when using the /g modifier. It is possib Line 1331  when using the /g modifier. It is possib
1331  matching a null string by first trying the match again at the same offset with  matching a null string by first trying the match again at the same offset with
1332  PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the  PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the
1333  starting offset (see below) and trying an ordinary match again. There is some  starting offset (see below) and trying an ordinary match again. There is some
1334  code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.  code that demonstrates how to do this in the
1335    .\" HREF
1336    \fBpcredemo\fP
1337    .\"
1338    sample program.
1339    .sp
1340      PCRE_NO_START_OPTIMIZE
1341    .sp
1342    There are a number of optimizations that \fBpcre_exec()\fP uses at the start of
1343    a match, in order to speed up the process. For example, if it is known that a
1344    match must start with a specific character, it searches the subject for that
1345    character, and fails immediately if it cannot find it, without actually running
1346    the main matching function. When callouts are in use, these optimizations can
1347    cause them to be skipped. This option disables the "start-up" optimizations,
1348    causing performance to suffer, but ensuring that the callouts do occur.
1349  .sp  .sp
1350    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
1351  .sp  .sp
1352  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
1353  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1354  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
1355  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
1356  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1357  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1358    .\" </a>
1359    section on UTF-8 support
1360    .\"
1361    in the main
1362    .\" HREF
1363    \fBpcre\fP
1364    .\"
1365    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1366    the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1367    PCRE_ERROR_BADUTF8_OFFSET is returned.
1368  .P  .P
1369  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
1370  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 1094  PCRE_NO_UTF8_CHECK is set, the effect of Line 1376  PCRE_NO_UTF8_CHECK is set, the effect of
1376  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
1377  UTF-8 character, is undefined. Your program may crash.  UTF-8 character, is undefined. Your program may crash.
1378  .sp  .sp
1379    PCRE_PARTIAL    PCRE_PARTIAL_HARD
1380      PCRE_PARTIAL_SOFT
1381  .sp  .sp
1382  This option turns on the partial matching feature. If the subject string fails  These options turn on the partial matching feature. For backwards
1383  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
1384  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
1385  the failure to match occurred only because there were not enough subject  not enough subject characters to complete the match. If this happens when
1386  characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of  PCRE_PARTIAL_HARD is set, \fBpcre_exec()\fP immediately returns
1387  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
1388  may appear in the pattern. These are discussed in the  by testing any other alternatives. Only if they all fail is PCRE_ERROR_PARTIAL
1389    returned (instead of PCRE_ERROR_NOMATCH). The portion of the string that
1390    provided the partial match is set as the first matching string. There is a more
1391    detailed discussion in the
1392  .\" HREF  .\" HREF
1393  \fBpcrepartial\fP  \fBpcrepartial\fP
1394  .\"  .\"
# Line 1112  documentation. Line 1398  documentation.
1398  .rs  .rs
1399  .sp  .sp
1400  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
1401  \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
1402  \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
1403  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
1404  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
1405  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.
1406  .P  .P
1407  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
1408  same subject by calling \fBpcre_exec()\fP again after a previous success.  same subject by calling \fBpcre_exec()\fP again after a previous success.
# Line 1150  pattern. Following the usage in Jeffrey Line 1436  pattern. Following the usage in Jeffrey
1436  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
1437  kinds of parenthesized subpattern that do not cause substrings to be captured.  kinds of parenthesized subpattern that do not cause substrings to be captured.
1438  .P  .P
1439  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
1440  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
1441  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
1442  this argument is NOT the size of \fIovector\fP in bytes.  argument is NOT the size of \fIovector\fP in bytes.
1443  .P  .P
1444  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,
1445  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
1446  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1447  and is not available for passing back information. The length passed in  and is not available for passing back information. The number passed in
1448  \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
1449  rounded down.  rounded down.
1450  .P  .P
1451  When a match is successful, information about captured substrings is returned  When a match is successful, information about captured substrings is returned
1452  in pairs of integers, starting at the beginning of \fIovector\fP, and  in pairs of integers, starting at the beginning of \fIovector\fP, and
1453  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
1454  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
1455  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
1456  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
1457  subject string matched by the entire pattern. The next pair is used for the  mode. They are not character counts.
1458  first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP  .P
1459  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
1460  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
1461  just the first pair of offsets has been set.  used for the first capturing subpattern, and so on. The value returned by
1462  .P  \fBpcre_exec()\fP is one more than the highest numbered pair that has been set.
1463  Some convenience functions are provided for extracting the captured substrings  For example, if two substrings have been captured, the returned value is 3. If
1464  as separate strings. These are described in the following section.  there are no capturing subpatterns, the return value from a successful match is
1465  .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.  
1466  .P  .P
1467  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
1468  string that it matched that is returned.  string that it matched that is returned.
1469  .P  .P
1470  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
1471  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
1472  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,
1473  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
1474  \fIovecsize\fP as zero. However, if the pattern contains back references and  \fIovecsize\fP as zero. However, if the pattern contains back references and
1475  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
1476  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
1477  advisable to supply an \fIovector\fP.  advisable to supply an \fIovector\fP.
1478  .P  .P
1479  Note that \fBpcre_info()\fP can be used to find out how many capturing  The \fBpcre_info()\fP function can be used to find out how many capturing
1480  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
1481  \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
1482  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.
1483    .P
1484    It is possible for capturing subpattern number \fIn+1\fP to match some part of
1485    the subject when subpattern \fIn\fP has not been used at all. For example, if
1486    the string "abc" is matched against the pattern (a|(z))(bc) the return from the
1487    function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
1488    happens, both values in the offset pairs corresponding to unused subpatterns
1489    are set to -1.
1490    .P
1491    Offset values that correspond to unused subpatterns at the end of the
1492    expression are also set to -1. For example, if the string "abc" is matched
1493    against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1494    return from the function is 2, because the highest used capturing subpattern
1495    number is 1. However, you can refer to the offsets for the second and third
1496    capturing subpatterns if you wish (assuming the vector is large enough, of
1497    course).
1498    .P
1499    Some convenience functions are provided for extracting the captured substrings
1500    as separate strings. These are described below.
1501  .  .
1502  .\" HTML <a name="errorlist"></a>  .\" HTML <a name="errorlist"></a>
1503  .SS "Return values from \fBpcre_exec()\fP"  .SS "Error return values from \fBpcre_exec()\fP"
1504  .rs  .rs
1505  .sp  .sp
1506  If \fBpcre_exec()\fP fails, it returns a negative number. The following are  If \fBpcre_exec()\fP fails, it returns a negative number. The following are
# Line 1228  compiled in an environment of one endian Line 1527  compiled in an environment of one endian
1527  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
1528  not present.  not present.
1529  .sp  .sp
1530    PCRE_ERROR_UNKNOWN_NODE   (-5)    PCRE_ERROR_UNKNOWN_OPCODE (-5)
1531  .sp  .sp
1532  While running the pattern match, an unknown item was encountered in the  While running the pattern match, an unknown item was encountered in the
1533  compiled pattern. This error could be caused by a bug in PCRE or by overwriting  compiled pattern. This error could be caused by a bug in PCRE or by overwriting
# Line 1250  below). It is never returned by \fBpcre_ Line 1549  below). It is never returned by \fBpcre_
1549  .sp  .sp
1550    PCRE_ERROR_MATCHLIMIT     (-8)    PCRE_ERROR_MATCHLIMIT     (-8)
1551  .sp  .sp
1552  The recursion and backtracking limit, as specified by the \fImatch_limit\fP  The backtracking limit, as specified by the \fImatch_limit\fP field in a
1553  field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the  \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1554  description above.  above.
1555  .sp  .sp
1556    PCRE_ERROR_CALLOUT        (-9)    PCRE_ERROR_CALLOUT        (-9)
1557  .sp  .sp
# Line 1282  documentation for details of partial mat Line 1581  documentation for details of partial mat
1581  .sp  .sp
1582    PCRE_ERROR_BADPARTIAL     (-13)    PCRE_ERROR_BADPARTIAL     (-13)
1583  .sp  .sp
1584  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
1585  are not supported for partial matching. See the  option was used with a compiled pattern containing items that were not
1586  .\" HREF  supported for partial matching. From release 8.00 onwards, there are no
1587  \fBpcrepartial\fP  restrictions on partial matching.
 .\"  
 documentation for details of partial matching.  
1588  .sp  .sp
1589    PCRE_ERROR_INTERNAL       (-14)    PCRE_ERROR_INTERNAL       (-14)
1590  .sp  .sp
# Line 1297  in PCRE or by overwriting of the compile Line 1594  in PCRE or by overwriting of the compile
1594    PCRE_ERROR_BADCOUNT       (-15)    PCRE_ERROR_BADCOUNT       (-15)
1595  .sp  .sp
1596  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.
1597    .sp
1598      PCRE_ERROR_RECURSIONLIMIT (-21)
1599    .sp
1600    The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1601    field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1602    description above.
1603    .sp
1604      PCRE_ERROR_BADNEWLINE     (-23)
1605    .sp
1606    An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1607    .P
1608    Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1609  .  .
1610  .  .
1611  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1308  This error is given if the value of the Line 1617  This error is given if the value of the
1617  .ti +5n  .ti +5n
1618  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1619  .PP  .PP
 .br  
1620  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1621  .ti +5n  .ti +5n
1622  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1623  .ti +5n  .ti +5n
1624  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1625  .PP  .PP
 .br  
1626  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1627  .ti +5n  .ti +5n
1628  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
# Line 1326  Captured substrings can be accessed dire Line 1633  Captured substrings can be accessed dire
1633  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
1634  as new, separate, zero-terminated strings. These functions identify substrings  as new, separate, zero-terminated strings. These functions identify substrings
1635  by number. The next section describes functions for extracting named  by number. The next section describes functions for extracting named
1636  substrings. A substring that contains a binary zero is correctly extracted and  substrings.
1637  has a further zero added on the end, but the result is not, of course,  .P
1638  a C string.  A substring that contains a binary zero is correctly extracted and has a
1639    further zero added on the end, but the result is not, of course, a C string.
1640    However, you can process such a string by referring to the length that is
1641    returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
1642    Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
1643    for handling strings containing binary zeros, because the end of the final
1644    string is not independently indicated.
1645  .P  .P
1646  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:
1647  \fIsubject\fP is the subject string that has just been successfully matched,  \fIsubject\fP is the subject string that has just been successfully matched,
# Line 1348  the string is placed in \fIbuffer\fP, wh Line 1661  the string is placed in \fIbuffer\fP, wh
1661  \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
1662  obtained via \fBpcre_malloc\fP, and its address is returned via  obtained via \fBpcre_malloc\fP, and its address is returned via
1663  \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
1664  including the terminating zero, or one of  including the terminating zero, or one of these error codes:
1665  .sp  .sp
1666    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1667  .sp  .sp
# Line 1364  and builds a list of pointers to them. A Line 1677  and builds a list of pointers to them. A
1677  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
1678  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
1679  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
1680  function is zero if all went well, or  function is zero if all went well, or the error code
1681  .sp  .sp
1682    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1683  .sp  .sp
# Line 1383  a previous call of \fBpcre_get_substring Line 1696  a previous call of \fBpcre_get_substring
1696  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
1697  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
1698  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
1699  linked via a special interface to another programming language which cannot use  linked via a special interface to another programming language that cannot use
1700  \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
1701  provided.  provided.
1702  .  .
# Line 1395  provided. Line 1708  provided.
1708  .ti +5n  .ti +5n
1709  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1710  .PP  .PP
 .br  
1711  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1712  .ti +5n  .ti +5n
1713  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1404  provided. Line 1716  provided.
1716  .ti +5n  .ti +5n
1717  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1718  .PP  .PP
 .br  
1719  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1720  .ti +5n  .ti +5n
1721  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1418  For example, for this pattern Line 1729  For example, for this pattern
1729  .sp  .sp
1730    (a+)b(?<xxx>\ed+)...    (a+)b(?<xxx>\ed+)...
1731  .sp  .sp
1732  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
1733  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
1734  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
1735    pattern, and the second is the name. The yield of the function is the
1736  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
1737  that name.  that name.
1738  .P  .P
# Line 1428  Given the number, you can extract the su Line 1740  Given the number, you can extract the su
1740  functions described in the previous section. For convenience, there are also  functions described in the previous section. For convenience, there are also
1741  two functions that do the whole job.  two functions that do the whole job.
1742  .P  .P
1743  Most of the arguments of \fIpcre_copy_named_substring()\fP and  Most of the arguments of \fBpcre_copy_named_substring()\fP and
1744  \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
1745  functions that extract by number. As these are described in the previous  functions that extract by number. As these are described in the previous
1746  section, they are not re-described here. There are just two differences:  section, they are not re-described here. There are just two differences:
1747  .P  .P
# Line 1439  pattern. This is needed in order to gain Line 1751  pattern. This is needed in order to gain
1751  translation table.  translation table.
1752  .P  .P
1753  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1754  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1755  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1756    the behaviour may not be what you want (see the next section).
1757    .P
1758    \fBWarning:\fP If the pattern uses the "(?|" feature to set up multiple
1759    subpatterns with the same number, you cannot use names to distinguish them,
1760    because names are not included in the compiled code. The matching process uses
1761    only numbers.
1762    .
1763    .SH "DUPLICATE SUBPATTERN NAMES"
1764    .rs
1765    .sp
1766    .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
1767    .ti +5n
1768    .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
1769    .PP
1770    When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
1771    are not required to be unique. Normally, patterns with duplicate names are such
1772    that in any one match, only one of the named subpatterns participates. An
1773    example is shown in the
1774    .\" HREF
1775    \fBpcrepattern\fP
1776    .\"
1777    documentation.
1778    .P
1779    When duplicates are present, \fBpcre_copy_named_substring()\fP and
1780    \fBpcre_get_named_substring()\fP return the first substring corresponding to
1781    the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
1782    returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1783    returns one of the numbers that are associated with the name, but it is not
1784    defined which it is.
1785    .P
1786    If you want to get full details of all captured substrings for a given name,
1787    you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1788    argument is the compiled pattern, and the second is the name. The third and
1789    fourth are pointers to variables which are updated by the function. After it
1790    has run, they point to the first and last entries in the name-to-number table
1791    for the given name. The function itself returns the length of each entry, or
1792    PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1793    described above in the section entitled \fIInformation about a pattern\fP.
1794    Given all the relevant entries for the name, you can extract each of their
1795    numbers, and hence the captured data, if any.
1796  .  .
1797  .  .
1798  .SH "FINDING ALL POSSIBLE MATCHES"  .SH "FINDING ALL POSSIBLE MATCHES"
# Line 1478  will yield PCRE_ERROR_NOMATCH. Line 1830  will yield PCRE_ERROR_NOMATCH.
1830  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
1831  .P  .P
1832  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
1833  a compiled pattern, using a "DFA" matching algorithm. This has different  a compiled pattern, using a matching algorithm that scans the subject string
1834  characteristics to the normal algorithm, and is not compatible with Perl. Some  just once, and does not backtrack. This has different characteristics to the
1835  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
1836  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
1837  matching algorithms, see the  matching can be useful. For a discussion of the two matching algorithms, see
1838    the
1839  .\" HREF  .\" HREF
1840  \fBpcrematching\fP  \fBpcrematching\fP
1841  .\"  .\"
# Line 1497  here. Line 1850  here.
1850  The two additional arguments provide workspace for the function. The workspace  The two additional arguments provide workspace for the function. The workspace
1851  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
1852  multiple paths through the pattern tree. More workspace will be needed for  multiple paths through the pattern tree. More workspace will be needed for
1853  patterns and subjects where there are a lot of possible matches.  patterns and subjects where there are a lot of potential matches.
1854  .P  .P
1855  Here is an example of a simple call to \fBpcre_exec()\fP:  Here is an example of a simple call to \fBpcre_dfa_exec()\fP:
1856  .sp  .sp
1857    int rc;    int rc;
1858    int ovector[10];    int ovector[10];
1859    int wspace[20];    int wspace[20];
1860    rc = pcre_exec(    rc = pcre_dfa_exec(
1861      re,             /* result of pcre_compile() */      re,             /* result of pcre_compile() */
1862      NULL,           /* we didn't study the pattern */      NULL,           /* we didn't study the pattern */
1863      "some string",  /* the subject string */      "some string",  /* the subject string */
# Line 1520  Here is an example of a simple call to \ Line 1873  Here is an example of a simple call to \
1873  .rs  .rs
1874  .sp  .sp
1875  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
1876  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,
1877  PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD,
1878  PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are  PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last
1879  the same as for \fBpcre_exec()\fP, so their description is not repeated here.  four of these are exactly the same as for \fBpcre_exec()\fP, so their
1880  .sp  description is not repeated here.
1881    PCRE_PARTIAL  .sp
1882  .sp    PCRE_PARTIAL_HARD
1883  This has the same general effect as it does for \fBpcre_exec()\fP, but the    PCRE_PARTIAL_SOFT
1884  details are slightly different. When PCRE_PARTIAL is set for  .sp
1885  \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
1886  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
1887  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
1888  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
1889  matching string.  additional characters. This happens even if some complete matches have also
1890    been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH
1891    is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached,
1892    there have been no complete matches, but there is still at least one matching
1893    possibility. The portion of the string that provided the longest partial match
1894    is set as the first matching string in both cases.
1895  .sp  .sp
1896    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
1897  .sp  .sp
1898  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
1899  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
1900  this is necessarily the shortest possible match at the first possible matching  works, this is necessarily the shortest possible match at the first possible
1901  point in the subject string.  matching point in the subject string.
1902  .sp  .sp
1903    PCRE_DFA_RESTART    PCRE_DFA_RESTART
1904  .sp  .sp
1905  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
1906  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
1907  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
1908  option requests this action; when it is set, the \fIworkspace\fP and  \fIworkspace\fP and \fIwscount\fP options must reference the same vector as
1909  \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
1910  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  
1911  .\" HREF  .\" HREF
1912  \fBpcrepartial\fP  \fBpcrepartial\fP
1913  .\"  .\"
# Line 1579  the three matched strings are Line 1936  the three matched strings are
1936  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
1937  the number of matched substrings. The substrings themselves are returned in  the number of matched substrings. The substrings themselves are returned in
1938  \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
1939  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
1940  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,
1941  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
1942  data, even though the meaning of the strings is different.)  returns data, even though the meaning of the strings is different.)
1943  .P  .P
1944  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
1945  matching string is given first. If there were too many matches to fit into  matching string is given first. If there were too many matches to fit into
# Line 1609  that it does not support, for instance, Line 1966  that it does not support, for instance,
1966  .sp  .sp
1967    PCRE_ERROR_DFA_UCOND      (-17)    PCRE_ERROR_DFA_UCOND      (-17)
1968  .sp  .sp
1969  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
1970  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
1971    group. These are not supported.
1972  .sp  .sp
1973    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
1974  .sp  .sp
# Line 1629  When a recursive subpattern is processed Line 1987  When a recursive subpattern is processed
1987  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1988  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
1989  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
1990  .P  .
1991  .in 0  .
1992  Last updated: 16 May 2005  .SH "SEE ALSO"
1993  .br  .rs
1994  Copyright (c) 1997-2005 University of Cambridge.  .sp
1995    \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1996    \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1997    \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1998    .
1999    .
2000    .SH AUTHOR
2001    .rs
2002    .sp
2003    .nf
2004    Philip Hazel
2005    University Computing Service
2006    Cambridge CB2 3QH, England.
2007    .fi
2008    .
2009    .
2010    .SH REVISION
2011    .rs
2012    .sp
2013    .nf
2014    Last updated: 01 September 2009
2015    Copyright (c) 1997-2009 University of Cambridge.
2016    .fi

Legend:
Removed from v.77  
changed lines
  Added in v.429

webmaster@exim.org
ViewVC Help
Powered by ViewVC 1.1.12