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

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

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

revision 87 by nigel, Sat Feb 24 21:41:21 2007 UTC revision 426 by ph10, Wed Aug 26 15:38:32 2009 UTC
# Line 7  PCRE - Perl-compatible regular expressio Line 7  PCRE - Perl-compatible regular expressio
7  .B #include <pcre.h>  .B #include <pcre.h>
8  .PP  .PP
9  .SM  .SM
 .br  
10  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
11  .ti +5n  .ti +5n
12  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
13  .ti +5n  .ti +5n
14  .B const unsigned char *\fItableptr\fP);  .B const unsigned char *\fItableptr\fP);
15  .PP  .PP
 .br  
16  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
17  .ti +5n  .ti +5n
18  .B int *\fIerrorcodeptr\fP,  .B int *\fIerrorcodeptr\fP,
# Line 23  PCRE - Perl-compatible regular expressio Line 21  PCRE - Perl-compatible regular expressio
21  .ti +5n  .ti +5n
22  .B const unsigned char *\fItableptr\fP);  .B const unsigned char *\fItableptr\fP);
23  .PP  .PP
 .br  
24  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,
25  .ti +5n  .ti +5n
26  .B const char **\fIerrptr\fP);  .B const char **\fIerrptr\fP);
27  .PP  .PP
 .br  
28  .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
29  .ti +5n  .ti +5n
30  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
31  .ti +5n  .ti +5n
32  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
33  .PP  .PP
 .br  
34  .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
35  .ti +5n  .ti +5n
36  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
# Line 44  PCRE - Perl-compatible regular expressio Line 39  PCRE - Perl-compatible regular expressio
39  .ti +5n  .ti +5n
40  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
41  .PP  .PP
 .br  
42  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
43  .ti +5n  .ti +5n
44  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 53  PCRE - Perl-compatible regular expressio Line 47  PCRE - Perl-compatible regular expressio
47  .ti +5n  .ti +5n
48  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
49  .PP  .PP
 .br  
50  .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
51  .ti +5n  .ti +5n
52  .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
53  .ti +5n  .ti +5n
54  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
55  .PP  .PP
 .br  
56  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
57  .ti +5n  .ti +5n
58  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 69  PCRE - Perl-compatible regular expressio Line 61  PCRE - Perl-compatible regular expressio
61  .ti +5n  .ti +5n
62  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
63  .PP  .PP
 .br  
64  .B int pcre_get_stringnumber(const pcre *\fIcode\fP,  .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
65  .ti +5n  .ti +5n
66  .B const char *\fIname\fP);  .B const char *\fIname\fP);
67  .PP  .PP
68  .br  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
69    .ti +5n
70    .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
71    .PP
72  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
73  .ti +5n  .ti +5n
74  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
75  .ti +5n  .ti +5n
76  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
77  .PP  .PP
 .br  
78  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
79  .ti +5n  .ti +5n
80  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
81  .PP  .PP
 .br  
82  .B void pcre_free_substring(const char *\fIstringptr\fP);  .B void pcre_free_substring(const char *\fIstringptr\fP);
83  .PP  .PP
 .br  
84  .B void pcre_free_substring_list(const char **\fIstringptr\fP);  .B void pcre_free_substring_list(const char **\fIstringptr\fP);
85  .PP  .PP
 .br  
86  .B const unsigned char *pcre_maketables(void);  .B const unsigned char *pcre_maketables(void);
87  .PP  .PP
 .br  
88  .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"  .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
89  .ti +5n  .ti +5n
90  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
91  .PP  .PP
 .br  
92  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
93  .B *\fIfirstcharptr\fP);  .B *\fIfirstcharptr\fP);
94  .PP  .PP
 .br  
95  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
96  .PP  .PP
 .br  
97  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
98  .PP  .PP
 .br  
99  .B char *pcre_version(void);  .B char *pcre_version(void);
100  .PP  .PP
 .br  
101  .B void *(*pcre_malloc)(size_t);  .B void *(*pcre_malloc)(size_t);
102  .PP  .PP
 .br  
103  .B void (*pcre_free)(void *);  .B void (*pcre_free)(void *);
104  .PP  .PP
 .br  
105  .B void *(*pcre_stack_malloc)(size_t);  .B void *(*pcre_stack_malloc)(size_t);
106  .PP  .PP
 .br  
107  .B void (*pcre_stack_free)(void *);  .B void (*pcre_stack_free)(void *);
108  .PP  .PP
 .br  
109  .B int (*pcre_callout)(pcre_callout_block *);  .B int (*pcre_callout)(pcre_callout_block *);
110  .  .
111  .  .
112  .SH "PCRE API OVERVIEW"  .SH "PCRE API OVERVIEW"
113  .rs  .rs
114  .sp  .sp
115  PCRE has its own native API, which is described in this document. There is  PCRE has its own native API, which is described in this document. There are
116  also a set of wrapper functions that correspond to the POSIX regular expression  also some wrapper functions that correspond to the POSIX regular expression
117  API. These are described in the  API. These are described in the
118  .\" HREF  .\" HREF
119  \fBpcreposix\fP  \fBpcreposix\fP
# Line 160  distribution. The Line 140  distribution. The
140  .\" HREF  .\" HREF
141  \fBpcresample\fP  \fBpcresample\fP
142  .\"  .\"
143  documentation describes how to run it.  documentation describes how to compile and run it.
144  .P  .P
145  A second matching function, \fBpcre_dfa_exec()\fP, which is not  A second matching function, \fBpcre_dfa_exec()\fP, which is not
146  Perl-compatible, is also provided. This uses a different algorithm for the  Perl-compatible, is also provided. This uses a different algorithm for the
147  matching. This allows it to find all possible matches (at a given point in the  matching. The alternative algorithm finds all possible matches (at a given
148  subject), not just one. However, this algorithm does not return captured  point in the subject), and scans the subject just once. However, this algorithm
149  substrings. A description of the two matching algorithms and their advantages  does not return captured substrings. A description of the two matching
150  and disadvantages is given in the  algorithms and their advantages and disadvantages is given in the
151  .\" HREF  .\" HREF
152  \fBpcrematching\fP  \fBpcrematching\fP
153  .\"  .\"
# Line 183  matched by \fBpcre_exec()\fP. They are: Line 163  matched by \fBpcre_exec()\fP. They are:
163    \fBpcre_get_named_substring()\fP    \fBpcre_get_named_substring()\fP
164    \fBpcre_get_substring_list()\fP    \fBpcre_get_substring_list()\fP
165    \fBpcre_get_stringnumber()\fP    \fBpcre_get_stringnumber()\fP
166      \fBpcre_get_stringtable_entries()\fP
167  .sp  .sp
168  \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also  \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also
169  provided, to free the memory used for extracted strings.  provided, to free the memory used for extracted strings.
# Line 212  should be done before calling any PCRE f Line 193  should be done before calling any PCRE f
193  The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also  The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also
194  indirections to memory management functions. These special functions are used  indirections to memory management functions. These special functions are used
195  only when PCRE is compiled to use the heap for remembering data, instead of  only when PCRE is compiled to use the heap for remembering data, instead of
196  recursive function calls, when running the \fBpcre_exec()\fP function. This is  recursive function calls, when running the \fBpcre_exec()\fP function. See the
197  a non-standard way of building PCRE, for use in environments that have limited  .\" HREF
198  stacks. Because of the greater use of memory management, it runs more slowly.  \fBpcrebuild\fP
199  Separate functions are provided so that special-purpose external code can be  .\"
200  used for this case. When used, these functions are always called in a  documentation for details of how to do this. It is a non-standard way of
201  stack-like manner (last obtained, first freed), and always for memory blocks of  building PCRE, for use in environments that have limited stacks. Because of the
202  the same size.  greater use of memory management, it runs more slowly. Separate functions are
203    provided so that special-purpose external code can be used for this case. When
204    used, these functions are always called in a stack-like manner (last obtained,
205    first freed), and always for memory blocks of the same size. There is a
206    discussion about PCRE's stack usage in the
207    .\" HREF
208    \fBpcrestack\fP
209    .\"
210    documentation.
211  .P  .P
212  The global variable \fBpcre_callout\fP initially contains NULL. It can be set  The global variable \fBpcre_callout\fP initially contains NULL. It can be set
213  by the caller to a "callout" function, which PCRE will then call at specified  by the caller to a "callout" function, which PCRE will then call at specified
# Line 229  points during a matching operation. Deta Line 218  points during a matching operation. Deta
218  documentation.  documentation.
219  .  .
220  .  .
221    .\" HTML <a name="newlines"></a>
222    .SH NEWLINES
223    .rs
224    .sp
225    PCRE supports five different conventions for indicating line breaks in
226    strings: a single CR (carriage return) character, a single LF (linefeed)
227    character, the two-character sequence CRLF, any of the three preceding, or any
228    Unicode newline sequence. The Unicode newline sequences are the three just
229    mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
230    U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
231    (paragraph separator, U+2029).
232    .P
233    Each of the first three conventions is used by at least one operating system as
234    its standard newline sequence. When PCRE is built, a default can be specified.
235    The default default is LF, which is the Unix standard. When PCRE is run, the
236    default can be overridden, either when a pattern is compiled, or when it is
237    matched.
238    .P
239    At compile time, the newline convention can be specified by the \fIoptions\fP
240    argument of \fBpcre_compile()\fP, or it can be specified by special text at the
241    start of the pattern itself; this overrides any other settings. See the
242    .\" HREF
243    \fBpcrepattern\fP
244    .\"
245    page for details of the special character sequences.
246    .P
247    In the PCRE documentation the word "newline" is used to mean "the character or
248    pair of characters that indicate a line break". The choice of newline
249    convention affects the handling of the dot, circumflex, and dollar
250    metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
251    recognized line ending sequence, the match position advancement for a
252    non-anchored pattern. There is more detail about this in the
253    .\" HTML <a href="#execoptions">
254    .\" </a>
255    section on \fBpcre_exec()\fP options
256    .\"
257    below.
258    .P
259    The choice of newline convention does not affect the interpretation of
260    the \en or \er escape sequences, nor does it affect what \eR matches, which is
261    controlled in a similar way, but by separate options.
262    .
263    .
264  .SH MULTITHREADING  .SH MULTITHREADING
265  .rs  .rs
266  .sp  .sp
# Line 250  which it was compiled. Details are given Line 282  which it was compiled. Details are given
282  .\" HREF  .\" HREF
283  \fBpcreprecompile\fP  \fBpcreprecompile\fP
284  .\"  .\"
285  documentation.  documentation. However, compiling a regular expression with one version of PCRE
286    for use with a different version is not guaranteed to work and may cause
287    crashes.
288  .  .
289  .  .
290  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 281  properties is available; otherwise it is Line 315  properties is available; otherwise it is
315  .sp  .sp
316    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
317  .sp  .sp
318  The output is an integer that is set to the value of the code that is used for  The output is an integer whose value specifies the default character sequence
319  the newline character. It is either linefeed (10) or carriage return (13), and  that is recognized as meaning "newline". The four values that are supported
320  should normally be the standard character for your operating system.  are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY.
321    Though they are derived from ASCII, the same values are returned in EBCDIC
322    environments. The default should normally correspond to the standard sequence
323    for your operating system.
324    .sp
325      PCRE_CONFIG_BSR
326    .sp
327    The output is an integer whose value indicates what character sequences the \eR
328    escape sequence matches by default. A value of 0 means that \eR matches any
329    Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
330    or CRLF. The default can be overridden when a pattern is compiled or matched.
331  .sp  .sp
332    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
333  .sp  .sp
# Line 305  documentation. Line 349  documentation.
349  .sp  .sp
350    PCRE_CONFIG_MATCH_LIMIT    PCRE_CONFIG_MATCH_LIMIT
351  .sp  .sp
352  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
353  internal matching function calls in a \fBpcre_exec()\fP execution. Further  internal matching function calls in a \fBpcre_exec()\fP execution. Further
354  details are given with \fBpcre_exec()\fP below.  details are given with \fBpcre_exec()\fP below.
355  .sp  .sp
356    PCRE_CONFIG_MATCH_LIMIT_RECURSION    PCRE_CONFIG_MATCH_LIMIT_RECURSION
357  .sp  .sp
358  The output is an integer that gives the default limit for the depth of  The output is a long integer that gives the default limit for the depth of
359  recursion when calling the internal matching function in a \fBpcre_exec()\fP  recursion when calling the internal matching function in a \fBpcre_exec()\fP
360  execution. Further details are given with \fBpcre_exec()\fP below.  execution. Further details are given with \fBpcre_exec()\fP below.
361  .sp  .sp
# Line 353  The pattern is a C string terminated by Line 397  The pattern is a C string terminated by
397  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
398  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
399  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
400  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.
401  .P  .P
402  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
403  depend on memory location, the complete \fBpcre\fP data block is not  depend on memory location, the complete \fBpcre\fP data block is not
404  fully relocatable, because it may contain a copy of the \fItableptr\fP  fully relocatable, because it may contain a copy of the \fItableptr\fP
405  argument, which is an address (see below).  argument, which is an address (see below).
406  .P  .P
407  The \fIoptions\fP argument contains independent bits that affect the  The \fIoptions\fP argument contains various bit settings that affect the
408  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
409  options are described below. Some of them, in particular, those that are  options are described below. Some of them (in particular, those that are
410  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
411  the detailed description in the  within the pattern (see the detailed description in the
412  .\" HREF  .\" HREF
413  \fBpcrepattern\fP  \fBpcrepattern\fP
414  .\"  .\"
415  documentation). For these options, the contents of the \fIoptions\fP argument  documentation). For those options that can be different in different parts of
416  specifies their initial settings at the start of compilation and execution. The  the pattern, the contents of the \fIoptions\fP argument specifies their initial
417  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
418  time.  PCRE_NEWLINE_\fIxxx\fP options can be set at the time of matching as well as at
419    compile time.
420  .P  .P
421  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
422  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
# Line 426  facility, see the Line 471  facility, see the
471  .\"  .\"
472  documentation.  documentation.
473  .sp  .sp
474      PCRE_BSR_ANYCRLF
475      PCRE_BSR_UNICODE
476    .sp
477    These options (which are mutually exclusive) control what the \eR escape
478    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
479    match any Unicode newline sequence. The default is specified when PCRE is
480    built. It can be overridden from within the pattern, or by setting an option
481    when a compiled pattern is matched.
482    .sp
483    PCRE_CASELESS    PCRE_CASELESS
484  .sp  .sp
485  If this bit is set, letters in the pattern match both upper and lower case  If this bit is set, letters in the pattern match both upper and lower case
# Line 442  with UTF-8 support. Line 496  with UTF-8 support.
496  .sp  .sp
497  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
498  end of the subject string. Without this option, a dollar also matches  end of the subject string. Without this option, a dollar also matches
499  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
500  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.
501  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
502  a pattern.  pattern.
503  .sp  .sp
504    PCRE_DOTALL    PCRE_DOTALL
505  .sp  .sp
506  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,
507  including newlines. Without it, newlines are excluded. This option is  including those that indicate newline. Without it, a dot does not match when
508  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
509  (?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
510  character, independent of the setting of this option.  negative class such as [^a] always matches newline characters, independent of
511    the setting of this option.
512    .sp
513      PCRE_DUPNAMES
514    .sp
515    If this bit is set, names used to identify capturing subpatterns need not be
516    unique. This can be helpful for certain types of pattern when it is known that
517    only one instance of the named subpattern can ever be matched. There are more
518    details of named subpatterns below; see also the
519    .\" HREF
520    \fBpcrepattern\fP
521    .\"
522    documentation.
523  .sp  .sp
524    PCRE_EXTENDED    PCRE_EXTENDED
525  .sp  .sp
526  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
527  ignored except when escaped or inside a character class. Whitespace does not  ignored except when escaped or inside a character class. Whitespace does not
528  include the VT character (code 11). In addition, characters between an  include the VT character (code 11). In addition, characters between an
529  unescaped # outside a character class and the next newline character,  unescaped # outside a character class and the next newline, inclusive, are also
530  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
531  be changed within a pattern by a (?x) option setting.  pattern by a (?x) option setting.
532  .P  .P
533  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
534  Note, however, that this applies only to data characters. Whitespace characters  Note, however, that this applies only to data characters. Whitespace characters
# Line 476  that is incompatible with Perl, but it i Line 542  that is incompatible with Perl, but it i
542  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
543  special meaning causes an error, thus reserving these combinations for future  special meaning causes an error, thus reserving these combinations for future
544  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
545  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
546  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
547  pattern.  this option. It can also be set by a (?X) option setting within a pattern.
548  .sp  .sp
549    PCRE_FIRSTLINE    PCRE_FIRSTLINE
550  .sp  .sp
551  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
552  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
553  continue over the newline.  over the newline.
554    .sp
555      PCRE_JAVASCRIPT_COMPAT
556    .sp
557    If this option is set, PCRE's behaviour is changed in some ways so that it is
558    compatible with JavaScript rather than Perl. The changes are as follows:
559    .P
560    (1) A lone closing square bracket in a pattern causes a compile-time error,
561    because this is illegal in JavaScript (by default it is treated as a data
562    character). Thus, the pattern AB]CD becomes illegal when this option is set.
563    .P
564    (2) At run time, a back reference to an unset subpattern group matches an empty
565    string (by default this causes the current matching alternative to fail). A
566    pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
567    an "a" in the subject), whereas it fails by default, for Perl compatibility.
568  .sp  .sp
569    PCRE_MULTILINE    PCRE_MULTILINE
570  .sp  .sp
# Line 496  terminating newline (unless PCRE_DOLLAR_ Line 576  terminating newline (unless PCRE_DOLLAR_
576  Perl.  Perl.
577  .P  .P
578  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
579  match immediately following or immediately before any newline in the subject  match immediately following or immediately before internal newlines in the
580  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
581  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
582  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
583  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
584  .sp  .sp
585      PCRE_NEWLINE_CR
586      PCRE_NEWLINE_LF
587      PCRE_NEWLINE_CRLF
588      PCRE_NEWLINE_ANYCRLF
589      PCRE_NEWLINE_ANY
590    .sp
591    These options override the default newline definition that was chosen when PCRE
592    was built. Setting the first or the second specifies that a newline is
593    indicated by a single character (CR or LF, respectively). Setting
594    PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
595    CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
596    preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
597    that any Unicode newline sequence should be recognized. The Unicode newline
598    sequences are the three just mentioned, plus the single characters VT (vertical
599    tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
600    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
601    recognized only in UTF-8 mode.
602    .P
603    The newline setting in the options word uses three bits that are treated
604    as a number, giving eight possibilities. Currently only six are used (default
605    plus the five values above). This means that if you set more than one newline
606    option, the combination may or may not be sensible. For example,
607    PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
608    other combinations may yield unused numbers and cause an error.
609    .P
610    The only time that a line break is specially recognized when compiling a
611    pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
612    class is encountered. This indicates a comment that lasts until after the next
613    line break sequence. In other circumstances, line break sequences are treated
614    as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
615    as whitespace characters and are therefore ignored.
616    .P
617    The newline option that is set at compile time becomes the default that is used
618    for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
619    .sp
620    PCRE_NO_AUTO_CAPTURE    PCRE_NO_AUTO_CAPTURE
621  .sp  .sp
622  If this option is set, it disables the use of numbered capturing parentheses in  If this option is set, it disables the use of numbered capturing parentheses in
# Line 536  page. Line 651  page.
651    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
652  .sp  .sp
653  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
654  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
655  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
656  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
657  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
658  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
659  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
660  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
661  strings.  \fBpcre\fP
662    .\"
663    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
664    returns an error. If you already know that your pattern is valid, and you want
665    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
666    option. When it is set, the effect of passing an invalid UTF-8 string as a
667    pattern is undefined. It may cause your program to crash. Note that this option
668    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
669    the UTF-8 validity checking of subject strings.
670  .  .
671  .  .
672  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 551  strings. Line 674  strings.
674  .sp  .sp
675  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
676  \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
677  both compiling functions.  both compiling functions. As PCRE has developed, some error codes have fallen
678    out of use. To avoid confusion, they have not been re-used.
679  .sp  .sp
680     0  no error     0  no error
681     1  \e at end of pattern     1  \e at end of pattern
# Line 563  both compiling functions. Line 687  both compiling functions.
687     7  invalid escape sequence in character class     7  invalid escape sequence in character class
688     8  range out of order in character class     8  range out of order in character class
689     9  nothing to repeat     9  nothing to repeat
690    10  operand of unlimited repeat could match the empty string    10  [this code is not in use]
691    11  internal error: unexpected repeat    11  internal error: unexpected repeat
692    12  unrecognized character after (?    12  unrecognized character after (? or (?-
693    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
694    14  missing )    14  missing )
695    15  reference to non-existent subpattern    15  reference to non-existent subpattern
696    16  erroffset passed as NULL    16  erroffset passed as NULL
697    17  unknown option bit(s) set    17  unknown option bit(s) set
698    18  missing ) after comment    18  missing ) after comment
699    19  parentheses nested too deeply    19  [this code is not in use]
700    20  regular expression too large    20  regular expression is too large
701    21  failed to get memory    21  failed to get memory
702    22  unmatched parentheses    22  unmatched parentheses
703    23  internal error: code overflow    23  internal error: code overflow
704    24  unrecognized character after (?<    24  unrecognized character after (?<
705    25  lookbehind assertion is not fixed length    25  lookbehind assertion is not fixed length
706    26  malformed number after (?(    26  malformed number or name after (?(
707    27  conditional group contains more than two branches    27  conditional group contains more than two branches
708    28  assertion expected after (?(    28  assertion expected after (?(
709    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
710    30  unknown POSIX class name    30  unknown POSIX class name
711    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
712    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
713    33  spare error    33  [this code is not in use]
714    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
715    35  invalid condition (?(0)    35  invalid condition (?(0)
716    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
# Line 595  both compiling functions. Line 719  both compiling functions.
719    39  closing ) for (?C expected    39  closing ) for (?C expected
720    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
721    41  unrecognized character after (?P    41  unrecognized character after (?P
722    42  syntax error after (?P    42  syntax error in subpattern name (missing terminator)
723    43  two named groups have the same name    43  two named subpatterns have the same name
724    44  invalid UTF-8 string    44  invalid UTF-8 string
725    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
726    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
727    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
728      48  subpattern name is too long (maximum 32 characters)
729      49  too many named subpatterns (maximum 10000)
730      50  [this code is not in use]
731      51  octal value is greater than \e377 (not in UTF-8 mode)
732      52  internal error: overran compiling workspace
733      53  internal error: previously-checked referenced subpattern not found
734      54  DEFINE group contains more than one branch
735      55  repeating a DEFINE group is not allowed
736      56  inconsistent NEWLINE options
737      57  \eg is not followed by a braced, angle-bracketed, or quoted
738            name/number or by a plain number
739      58  a numbered reference must not be zero
740      59  (*VERB) with an argument is not supported
741      60  (*VERB) not recognized
742      61  number is too big
743      62  subpattern name expected
744      63  digit expected after (?+
745      64  ] is an invalid data character in JavaScript compatibility mode
746    .sp
747    The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
748    be used if the limits were changed when PCRE was built.
749  .  .
750  .  .
751  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 660  bytes is created. Line 805  bytes is created.
805  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
806  .rs  .rs
807  .sp  .sp
808  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
809  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
810  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
811  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
812  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
813  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
814  .P  characters with codes greater than 128, you should either use UTF-8 and
815  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.
816  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
817  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
818  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.
819  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
820  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
821    default "C" locale of the local system, which may cause them to be different.
822    .P
823    The internal tables can always be overridden by tables supplied by the
824    application that calls PCRE. These may be created in a different locale from
825    the default. As more and more applications change to using Unicode, the need
826    for this locale support is expected to die away.
827  .P  .P
828  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
829  which has no arguments, in the relevant locale. The result can then be passed  which has no arguments, in the relevant locale. The result can then be passed
# Line 685  the following code could be used: Line 836  the following code could be used:
836    tables = pcre_maketables();    tables = pcre_maketables();
837    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
838  .sp  .sp
839    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
840    are using Windows, the name for the French locale is "french".
841    .P
842  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
843  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
844  that the memory containing the tables remains available for as long as it is  that the memory containing the tables remains available for as long as it is
# Line 731  check against passing an arbitrary memor Line 885  check against passing an arbitrary memor
885  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
886  .sp  .sp
887    int rc;    int rc;
888    unsigned long int length;    size_t length;
889    rc = pcre_fullinfo(    rc = pcre_fullinfo(
890      re,               /* result of pcre_compile() */      re,               /* result of pcre_compile() */
891      pe,               /* result of pcre_study(), or NULL */      pe,               /* result of pcre_study(), or NULL */
# Line 763  a NULL table pointer. Line 917  a NULL table pointer.
917    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
918  .sp  .sp
919  Return information about the first byte of any matched string, for a  Return information about the first byte of any matched string, for a
920  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
921  old name is still recognized for backwards compatibility.)  variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
922    still recognized for backwards compatibility.)
923  .P  .P
924  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
925  (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  
926  .sp  .sp
927  (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
928  starts with "^", or  starts with "^", or
# Line 787  table indicating a fixed set of bytes fo Line 941  table indicating a fixed set of bytes fo
941  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
942  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
943  .sp  .sp
944      PCRE_INFO_HASCRORLF
945    .sp
946    Return 1 if the pattern contains any explicit matches for CR or LF characters,
947    otherwise 0. The fourth argument should point to an \fBint\fP variable. An
948    explicit match is either a literal CR or LF character, or \er or \en.
949    .sp
950      PCRE_INFO_JCHANGED
951    .sp
952    Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
953    0. The fourth argument should point to an \fBint\fP variable. (?J) and
954    (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
955    .sp
956    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
957  .sp  .sp
958  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 803  is -1. Line 969  is -1.
969  .sp  .sp
970  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
971  names are just an additional way of identifying the parentheses, which still  names are just an additional way of identifying the parentheses, which still
972  acquire numbers. A convenience function called \fBpcre_get_named_substring()\fP  acquire numbers. Several convenience functions such as
973  is provided for extracting an individual captured substring by name. It is also  \fBpcre_get_named_substring()\fP are provided for extracting captured
974  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
975  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
976  \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,
977  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
978    values.
979  .P  .P
980  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
981  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 817  length of the longest name. PCRE_INFO_NA Line 984  length of the longest name. PCRE_INFO_NA
984  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
985  are the number of the capturing parenthesis, most significant byte first. The  are the number of the capturing parenthesis, most significant byte first. The
986  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
987  alphabetical order. For example, consider the following pattern (assume  alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of
988    their parentheses numbers. For example, consider the following pattern (assume
989  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  PCRE_EXTENDED is set, so white space - including newlines - is ignored):
990  .sp  .sp
991  .\" JOIN  .\" JOIN
992    (?P<date> (?P<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
993    (?P<month>\ed\ed) - (?P<day>\ed\ed) )    (?<month>\ed\ed) - (?<day>\ed\ed) )
994  .sp  .sp
995  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
996  in the table is eight bytes long. The table is as follows, with non-printing  in the table is eight bytes long. The table is as follows, with non-printing
# Line 834  bytes shows in hexadecimal, and undefine Line 1002  bytes shows in hexadecimal, and undefine
1002    00 02 y  e  a  r  00 ??    00 02 y  e  a  r  00 ??
1003  .sp  .sp
1004  When writing code to extract data from named subpatterns using the  When writing code to extract data from named subpatterns using the
1005  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
1006  different for each compiled pattern.  different for each compiled pattern.
1007  .sp  .sp
1008      PCRE_INFO_OKPARTIAL
1009    .sp
1010    Return 1 if the pattern can be used for partial matching, otherwise 0. The
1011    fourth argument should point to an \fBint\fP variable. From release 8.00, this
1012    always returns 1, because the restrictions that previously applied to partial
1013    matching have been lifted. The
1014    .\" HREF
1015    \fBpcrepartial\fP
1016    .\"
1017    documentation gives details of partial matching.
1018    .sp
1019    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
1020  .sp  .sp
1021  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
1022  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
1023  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
1024  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
1025    they are the options that will be in force when matching starts. For example,
1026    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1027    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
1028  .P  .P
1029  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
1030  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 1053  called. See the Line 1235  called. See the
1235  .\"  .\"
1236  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1237  .  .
1238    .\" HTML <a name="execoptions"></a>
1239  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1240  .rs  .rs
1241  .sp  .sp
1242  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
1243  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,
1244  PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_START_OPTIMIZE,
1245    PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
1246  .sp  .sp
1247    PCRE_ANCHORED    PCRE_ANCHORED
1248  .sp  .sp
# Line 1067  matching position. If a pattern was comp Line 1251  matching position. If a pattern was comp
1251  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
1252  matching time.  matching time.
1253  .sp  .sp
1254      PCRE_BSR_ANYCRLF
1255      PCRE_BSR_UNICODE
1256    .sp
1257    These options (which are mutually exclusive) control what the \eR escape
1258    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1259    match any Unicode newline sequence. These options override the choice that was
1260    made or defaulted when the pattern was compiled.
1261    .sp
1262      PCRE_NEWLINE_CR
1263      PCRE_NEWLINE_LF
1264      PCRE_NEWLINE_CRLF
1265      PCRE_NEWLINE_ANYCRLF
1266      PCRE_NEWLINE_ANY
1267    .sp
1268    These options override the newline definition that was chosen or defaulted when
1269    the pattern was compiled. For details, see the description of
1270    \fBpcre_compile()\fP above. During matching, the newline choice affects the
1271    behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1272    the way the match position is advanced after a match failure for an unanchored
1273    pattern.
1274    .P
1275    When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
1276    match attempt for an unanchored pattern fails when the current position is at a
1277    CRLF sequence, and the pattern contains no explicit matches for CR or LF
1278    characters, the match position is advanced by two characters instead of one, in
1279    other words, to after the CRLF.
1280    .P
1281    The above rule is a compromise that makes the most common cases work as
1282    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1283    set), it does not match the string "\er\enA" because, after failing at the
1284    start, it skips both the CR and the LF before retrying. However, the pattern
1285    [\er\en]A does match that string, because it contains an explicit CR or LF
1286    reference, and so advances only by one character after the first failure.
1287    .P
1288    An explicit match for CR of LF is either a literal appearance of one of those
1289    characters, or one of the \er or \en escape sequences. Implicit matches such as
1290    [^X] do not count, nor does \es (which includes CR and LF in the characters
1291    that it matches).
1292    .P
1293    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1294    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1295    .sp
1296    PCRE_NOTBOL    PCRE_NOTBOL
1297  .sp  .sp
1298  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 1103  PCRE_NOTEMPTY and PCRE_ANCHORED, and the Line 1329  PCRE_NOTEMPTY and PCRE_ANCHORED, and the
1329  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
1330  code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.  code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.
1331  .sp  .sp
1332      PCRE_NO_START_OPTIMIZE
1333    .sp
1334    There are a number of optimizations that \fBpcre_exec()\fP uses at the start of
1335    a match, in order to speed up the process. For example, if it is known that a
1336    match must start with a specific character, it searches the subject for that
1337    character, and fails immediately if it cannot find it, without actually running
1338    the main matching function. When callouts are in use, these optimizations can
1339    cause them to be skipped. This option disables the "start-up" optimizations,
1340    causing performance to suffer, but ensuring that the callouts do occur.
1341    .sp
1342    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
1343  .sp  .sp
1344  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
1345  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1346  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
1347  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
1348  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1349  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1350    .\" </a>
1351    section on UTF-8 support
1352    .\"
1353    in the main
1354    .\" HREF
1355    \fBpcre\fP
1356    .\"
1357    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1358    the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1359    PCRE_ERROR_BADUTF8_OFFSET is returned.
1360  .P  .P
1361  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
1362  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 1129  to match the pattern, but at some point Line 1375  to match the pattern, but at some point
1375  the subject was reached (that is, the subject partially matches the pattern and  the subject was reached (that is, the subject partially matches the pattern and
1376  the failure to match occurred only because there were not enough subject  the failure to match occurred only because there were not enough subject
1377  characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of  characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of
1378  PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what  PCRE_ERROR_NOMATCH. The portion of the string that provided the longest partial
1379  may appear in the pattern. These are discussed in the  match is set as the first matching string. There is further discussion in the
1380  .\" HREF  .\" HREF
1381  \fBpcrepartial\fP  \fBpcrepartial\fP
1382  .\"  .\"
# Line 1140  documentation. Line 1386  documentation.
1386  .rs  .rs
1387  .sp  .sp
1388  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
1389  \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
1390  \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
1391  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
1392  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
1393  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.
1394  .P  .P
1395  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
1396  same subject by calling \fBpcre_exec()\fP again after a previous success.  same subject by calling \fBpcre_exec()\fP again after a previous success.
# Line 1178  pattern. Following the usage in Jeffrey Line 1424  pattern. Following the usage in Jeffrey
1424  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
1425  kinds of parenthesized subpattern that do not cause substrings to be captured.  kinds of parenthesized subpattern that do not cause substrings to be captured.
1426  .P  .P
1427  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
1428  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
1429  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
1430  this argument is NOT the size of \fIovector\fP in bytes.  argument is NOT the size of \fIovector\fP in bytes.
1431  .P  .P
1432  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,
1433  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
1434  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1435  and is not available for passing back information. The length passed in  and is not available for passing back information. The number passed in
1436  \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
1437  rounded down.  rounded down.
1438  .P  .P
1439  When a match is successful, information about captured substrings is returned  When a match is successful, information about captured substrings is returned
1440  in pairs of integers, starting at the beginning of \fIovector\fP, and  in pairs of integers, starting at the beginning of \fIovector\fP, and
1441  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
1442  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
1443  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
1444  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
1445  subject string matched by the entire pattern. The next pair is used for the  mode. They are not character counts.
1446  first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP  .P
1447  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
1448  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
1449  just the first pair of offsets has been set.  used for the first capturing subpattern, and so on. The value returned by
1450  .P  \fBpcre_exec()\fP is one more than the highest numbered pair that has been set.
1451  Some convenience functions are provided for extracting the captured substrings  For example, if two substrings have been captured, the returned value is 3. If
1452  as separate strings. These are described in the following section.  there are no capturing subpatterns, the return value from a successful match is
1453  .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.  
1454  .P  .P
1455  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
1456  string that it matched that is returned.  string that it matched that is returned.
1457  .P  .P
1458  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
1459  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
1460  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,
1461  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
1462  \fIovecsize\fP as zero. However, if the pattern contains back references and  \fIovecsize\fP as zero. However, if the pattern contains back references and
1463  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
1464  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
1465  advisable to supply an \fIovector\fP.  advisable to supply an \fIovector\fP.
1466  .P  .P
1467  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
1468  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
1469  \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
1470  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.
1471    .P
1472    It is possible for capturing subpattern number \fIn+1\fP to match some part of
1473    the subject when subpattern \fIn\fP has not been used at all. For example, if
1474    the string "abc" is matched against the pattern (a|(z))(bc) the return from the
1475    function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
1476    happens, both values in the offset pairs corresponding to unused subpatterns
1477    are set to -1.
1478    .P
1479    Offset values that correspond to unused subpatterns at the end of the
1480    expression are also set to -1. For example, if the string "abc" is matched
1481    against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1482    return from the function is 2, because the highest used capturing subpattern
1483    number is 1. However, you can refer to the offsets for the second and third
1484    capturing subpatterns if you wish (assuming the vector is large enough, of
1485    course).
1486    .P
1487    Some convenience functions are provided for extracting the captured substrings
1488    as separate strings. These are described below.
1489  .  .
1490  .\" HTML <a name="errorlist"></a>  .\" HTML <a name="errorlist"></a>
1491  .SS "Return values from \fBpcre_exec()\fP"  .SS "Error return values from \fBpcre_exec()\fP"
1492  .rs  .rs
1493  .sp  .sp
1494  If \fBpcre_exec()\fP fails, it returns a negative number. The following are  If \fBpcre_exec()\fP fails, it returns a negative number. The following are
# Line 1256  compiled in an environment of one endian Line 1515  compiled in an environment of one endian
1515  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
1516  not present.  not present.
1517  .sp  .sp
1518    PCRE_ERROR_UNKNOWN_NODE   (-5)    PCRE_ERROR_UNKNOWN_OPCODE (-5)
1519  .sp  .sp
1520  While running the pattern match, an unknown item was encountered in the  While running the pattern match, an unknown item was encountered in the
1521  compiled pattern. This error could be caused by a bug in PCRE or by overwriting  compiled pattern. This error could be caused by a bug in PCRE or by overwriting
# Line 1282  The backtracking limit, as specified by Line 1541  The backtracking limit, as specified by
1541  \fBpcre_extra\fP structure (or defaulted) was reached. See the description  \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1542  above.  above.
1543  .sp  .sp
   PCRE_ERROR_RECURSIONLIMIT (-21)  
 .sp  
 The internal recursion limit, as specified by the \fImatch_limit_recursion\fP  
 field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the  
 description above.  
 .sp  
1544    PCRE_ERROR_CALLOUT        (-9)    PCRE_ERROR_CALLOUT        (-9)
1545  .sp  .sp
1546  This error is never generated by \fBpcre_exec()\fP itself. It is provided for  This error is never generated by \fBpcre_exec()\fP itself. It is provided for
# Line 1316  documentation for details of partial mat Line 1569  documentation for details of partial mat
1569  .sp  .sp
1570    PCRE_ERROR_BADPARTIAL     (-13)    PCRE_ERROR_BADPARTIAL     (-13)
1571  .sp  .sp
1572  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
1573  are not supported for partial matching. See the  option was used with a compiled pattern containing items that were not
1574  .\" HREF  supported for partial matching. From release 8.00 onwards, there are no
1575  \fBpcrepartial\fP  restrictions on partial matching.
 .\"  
 documentation for details of partial matching.  
1576  .sp  .sp
1577    PCRE_ERROR_INTERNAL       (-14)    PCRE_ERROR_INTERNAL       (-14)
1578  .sp  .sp
# Line 1331  in PCRE or by overwriting of the compile Line 1582  in PCRE or by overwriting of the compile
1582    PCRE_ERROR_BADCOUNT       (-15)    PCRE_ERROR_BADCOUNT       (-15)
1583  .sp  .sp
1584  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.
1585    .sp
1586      PCRE_ERROR_RECURSIONLIMIT (-21)
1587    .sp
1588    The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1589    field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1590    description above.
1591    .sp
1592      PCRE_ERROR_BADNEWLINE     (-23)
1593    .sp
1594    An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1595    .P
1596    Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1597  .  .
1598  .  .
1599  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1342  This error is given if the value of the Line 1605  This error is given if the value of the
1605  .ti +5n  .ti +5n
1606  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1607  .PP  .PP
 .br  
1608  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1609  .ti +5n  .ti +5n
1610  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1611  .ti +5n  .ti +5n
1612  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1613  .PP  .PP
 .br  
1614  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1615  .ti +5n  .ti +5n
1616  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
# Line 1360  Captured substrings can be accessed dire Line 1621  Captured substrings can be accessed dire
1621  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
1622  as new, separate, zero-terminated strings. These functions identify substrings  as new, separate, zero-terminated strings. These functions identify substrings
1623  by number. The next section describes functions for extracting named  by number. The next section describes functions for extracting named
1624  substrings. A substring that contains a binary zero is correctly extracted and  substrings.
1625  has a further zero added on the end, but the result is not, of course,  .P
1626  a C string.  A substring that contains a binary zero is correctly extracted and has a
1627    further zero added on the end, but the result is not, of course, a C string.
1628    However, you can process such a string by referring to the length that is
1629    returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
1630    Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
1631    for handling strings containing binary zeros, because the end of the final
1632    string is not independently indicated.
1633  .P  .P
1634  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:
1635  \fIsubject\fP is the subject string that has just been successfully matched,  \fIsubject\fP is the subject string that has just been successfully matched,
# Line 1382  the string is placed in \fIbuffer\fP, wh Line 1649  the string is placed in \fIbuffer\fP, wh
1649  \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
1650  obtained via \fBpcre_malloc\fP, and its address is returned via  obtained via \fBpcre_malloc\fP, and its address is returned via
1651  \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
1652  including the terminating zero, or one of  including the terminating zero, or one of these error codes:
1653  .sp  .sp
1654    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1655  .sp  .sp
# Line 1398  and builds a list of pointers to them. A Line 1665  and builds a list of pointers to them. A
1665  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
1666  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
1667  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
1668  function is zero if all went well, or  function is zero if all went well, or the error code
1669  .sp  .sp
1670    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1671  .sp  .sp
# Line 1417  a previous call of \fBpcre_get_substring Line 1684  a previous call of \fBpcre_get_substring
1684  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
1685  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
1686  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
1687  linked via a special interface to another programming language which cannot use  linked via a special interface to another programming language that cannot use
1688  \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
1689  provided.  provided.
1690  .  .
# Line 1429  provided. Line 1696  provided.
1696  .ti +5n  .ti +5n
1697  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1698  .PP  .PP
 .br  
1699  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1700  .ti +5n  .ti +5n
1701  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1438  provided. Line 1704  provided.
1704  .ti +5n  .ti +5n
1705  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1706  .PP  .PP
 .br  
1707  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1708  .ti +5n  .ti +5n
1709  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1450  provided. Line 1715  provided.
1715  To extract a substring by name, you first have to find associated number.  To extract a substring by name, you first have to find associated number.
1716  For example, for this pattern  For example, for this pattern
1717  .sp  .sp
1718    (a+)b(?P<xxx>\ed+)...    (a+)b(?<xxx>\ed+)...
1719  .sp  .sp
1720  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
1721  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
1722  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
1723    pattern, and the second is the name. The yield of the function is the
1724  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
1725  that name.  that name.
1726  .P  .P
# Line 1462  Given the number, you can extract the su Line 1728  Given the number, you can extract the su
1728  functions described in the previous section. For convenience, there are also  functions described in the previous section. For convenience, there are also
1729  two functions that do the whole job.  two functions that do the whole job.
1730  .P  .P
1731  Most of the arguments of \fIpcre_copy_named_substring()\fP and  Most of the arguments of \fBpcre_copy_named_substring()\fP and
1732  \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
1733  functions that extract by number. As these are described in the previous  functions that extract by number. As these are described in the previous
1734  section, they are not re-described here. There are just two differences:  section, they are not re-described here. There are just two differences:
1735  .P  .P
# Line 1473  pattern. This is needed in order to gain Line 1739  pattern. This is needed in order to gain
1739  translation table.  translation table.
1740  .P  .P
1741  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1742  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1743  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1744    the behaviour may not be what you want (see the next section).
1745    .P
1746    \fBWarning:\fP If the pattern uses the "(?|" feature to set up multiple
1747    subpatterns with the same number, you cannot use names to distinguish them,
1748    because names are not included in the compiled code. The matching process uses
1749    only numbers.
1750    .
1751    .SH "DUPLICATE SUBPATTERN NAMES"
1752    .rs
1753    .sp
1754    .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
1755    .ti +5n
1756    .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
1757    .PP
1758    When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
1759    are not required to be unique. Normally, patterns with duplicate names are such
1760    that in any one match, only one of the named subpatterns participates. An
1761    example is shown in the
1762    .\" HREF
1763    \fBpcrepattern\fP
1764    .\"
1765    documentation.
1766    .P
1767    When duplicates are present, \fBpcre_copy_named_substring()\fP and
1768    \fBpcre_get_named_substring()\fP return the first substring corresponding to
1769    the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
1770    returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1771    returns one of the numbers that are associated with the name, but it is not
1772    defined which it is.
1773    .P
1774    If you want to get full details of all captured substrings for a given name,
1775    you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1776    argument is the compiled pattern, and the second is the name. The third and
1777    fourth are pointers to variables which are updated by the function. After it
1778    has run, they point to the first and last entries in the name-to-number table
1779    for the given name. The function itself returns the length of each entry, or
1780    PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1781    described above in the section entitled \fIInformation about a pattern\fP.
1782    Given all the relevant entries for the name, you can extract each of their
1783    numbers, and hence the captured data, if any.
1784  .  .
1785  .  .
1786  .SH "FINDING ALL POSSIBLE MATCHES"  .SH "FINDING ALL POSSIBLE MATCHES"
# Line 1512  will yield PCRE_ERROR_NOMATCH. Line 1818  will yield PCRE_ERROR_NOMATCH.
1818  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
1819  .P  .P
1820  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
1821  a compiled pattern, using a "DFA" matching algorithm. This has different  a compiled pattern, using a matching algorithm that scans the subject string
1822  characteristics to the normal algorithm, and is not compatible with Perl. Some  just once, and does not backtrack. This has different characteristics to the
1823  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
1824  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
1825  matching algorithms, see the  matching can be useful. For a discussion of the two matching algorithms, see
1826    the
1827  .\" HREF  .\" HREF
1828  \fBpcrematching\fP  \fBpcrematching\fP
1829  .\"  .\"
# Line 1531  here. Line 1838  here.
1838  The two additional arguments provide workspace for the function. The workspace  The two additional arguments provide workspace for the function. The workspace
1839  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
1840  multiple paths through the pattern tree. More workspace will be needed for  multiple paths through the pattern tree. More workspace will be needed for
1841  patterns and subjects where there are a lot of possible matches.  patterns and subjects where there are a lot of potential matches.
1842  .P  .P
1843  Here is an example of a simple call to \fBpcre_dfa_exec()\fP:  Here is an example of a simple call to \fBpcre_dfa_exec()\fP:
1844  .sp  .sp
# Line 1554  Here is an example of a simple call to \ Line 1861  Here is an example of a simple call to \
1861  .rs  .rs
1862  .sp  .sp
1863  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
1864  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,
1865  PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,
1866  PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are  PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are
1867  the same as for \fBpcre_exec()\fP, so their description is not repeated here.  exactly the same as for \fBpcre_exec()\fP, so their description is not repeated
1868    here.
1869  .sp  .sp
1870    PCRE_PARTIAL    PCRE_PARTIAL
1871  .sp  .sp
# Line 1566  details are slightly different. When PCR Line 1874  details are slightly different. When PCR
1874  \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into  \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into
1875  PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no  PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no
1876  complete matches, but there is still at least one matching possibility. The  complete matches, but there is still at least one matching possibility. The
1877  portion of the string that provided the partial match is set as the first  portion of the string that provided the longest partial match is set as the
1878  matching string.  first matching string.
1879  .sp  .sp
1880    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
1881  .sp  .sp
1882  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
1883  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
1884  this is necessarily the shortest possible match at the first possible matching  works, this is necessarily the shortest possible match at the first possible
1885  point in the subject string.  matching point in the subject string.
1886  .sp  .sp
1887    PCRE_DFA_RESTART    PCRE_DFA_RESTART
1888  .sp  .sp
# Line 1613  the three matched strings are Line 1921  the three matched strings are
1921  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
1922  the number of matched substrings. The substrings themselves are returned in  the number of matched substrings. The substrings themselves are returned in
1923  \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
1924  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
1925  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,
1926  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
1927  data, even though the meaning of the strings is different.)  returns data, even though the meaning of the strings is different.)
1928  .P  .P
1929  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
1930  matching string is given first. If there were too many matches to fit into  matching string is given first. If there were too many matches to fit into
# Line 1643  that it does not support, for instance, Line 1951  that it does not support, for instance,
1951  .sp  .sp
1952    PCRE_ERROR_DFA_UCOND      (-17)    PCRE_ERROR_DFA_UCOND      (-17)
1953  .sp  .sp
1954  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
1955  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
1956    group. These are not supported.
1957  .sp  .sp
1958    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
1959  .sp  .sp
# Line 1663  When a recursive subpattern is processed Line 1972  When a recursive subpattern is processed
1972  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1973  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
1974  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
1975  .P  .
1976  .in 0  .
1977  Last updated: 18 January 2006  .SH "SEE ALSO"
1978  .br  .rs
1979  Copyright (c) 1997-2006 University of Cambridge.  .sp
1980    \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1981    \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1982    \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1983    .
1984    .
1985    .SH AUTHOR
1986    .rs
1987    .sp
1988    .nf
1989    Philip Hazel
1990    University Computing Service
1991    Cambridge CB2 3QH, England.
1992    .fi
1993    .
1994    .
1995    .SH REVISION
1996    .rs
1997    .sp
1998    .nf
1999    Last updated: 26 August 2009
2000    Copyright (c) 1997-2009 University of Cambridge.
2001    .fi

Legend:
Removed from v.87  
changed lines
  Added in v.426

  ViewVC Help
Powered by ViewVC 1.1.5