/[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 197 by ph10, Tue Jul 31 10:50:18 2007 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 164  documentation describes how to run it. Line 144  documentation describes how to 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    .SH NEWLINES
222    .rs
223    .sp
224    PCRE supports five different conventions for indicating line breaks in
225    strings: a single CR (carriage return) character, a single LF (linefeed)
226    character, the two-character sequence CRLF, any of the three preceding, or any
227    Unicode newline sequence. The Unicode newline sequences are the three just
228    mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
229    U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
230    (paragraph separator, U+2029).
231    .P
232    Each of the first three conventions is used by at least one operating system as
233    its standard newline sequence. When PCRE is built, a default can be specified.
234    The default default is LF, which is the Unix standard. When PCRE is run, the
235    default can be overridden, either when a pattern is compiled, or when it is
236    matched.
237    .P
238    In the PCRE documentation the word "newline" is used to mean "the character or
239    pair of characters that indicate a line break". The choice of newline
240    convention affects the handling of the dot, circumflex, and dollar
241    metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
242    recognized line ending sequence, the match position advancement for a
243    non-anchored pattern. The choice of newline convention does not affect the
244    interpretation of the \en or \er escape sequences.
245    .
246    .
247  .SH MULTITHREADING  .SH MULTITHREADING
248  .rs  .rs
249  .sp  .sp
# Line 250  which it was compiled. Details are given Line 265  which it was compiled. Details are given
265  .\" HREF  .\" HREF
266  \fBpcreprecompile\fP  \fBpcreprecompile\fP
267  .\"  .\"
268  documentation.  documentation. However, compiling a regular expression with one version of PCRE
269    for use with a different version is not guaranteed to work and may cause
270    crashes.
271  .  .
272  .  .
273  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 281  properties is available; otherwise it is Line 298  properties is available; otherwise it is
298  .sp  .sp
299    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
300  .sp  .sp
301  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
302  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
303  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. The
304    default should normally be the standard sequence for your operating system.
305  .sp  .sp
306    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
307  .sp  .sp
# Line 353  The pattern is a C string terminated by Line 371  The pattern is a C string terminated by
371  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
372  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
373  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
374  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.
375  .P  .P
376  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
377  depend on memory location, the complete \fBpcre\fP data block is not  depend on memory location, the complete \fBpcre\fP data block is not
378  fully relocatable, because it may contain a copy of the \fItableptr\fP  fully relocatable, because it may contain a copy of the \fItableptr\fP
379  argument, which is an address (see below).  argument, which is an address (see below).
380  .P  .P
381  The \fIoptions\fP argument contains independent bits that affect the  The \fIoptions\fP argument contains various bit settings that affect the
382  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
383  options are described below. Some of them, in particular, those that are  options are described below. Some of them, in particular, those that are
384  compatible with Perl, can also be set and unset from within the pattern (see  compatible with Perl, can also be set and unset from within the pattern (see
# Line 370  the detailed description in the Line 388  the detailed description in the
388  .\"  .\"
389  documentation). For these options, the contents of the \fIoptions\fP argument  documentation). For these options, the contents of the \fIoptions\fP argument
390  specifies their initial settings at the start of compilation and execution. The  specifies their initial settings at the start of compilation and execution. The
391  PCRE_ANCHORED option can be set at the time of matching as well as at compile  PCRE_ANCHORED and PCRE_NEWLINE_\fIxxx\fP options can be set at the time of
392  time.  matching as well as at compile time.
393  .P  .P
394  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
395  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
# Line 442  with UTF-8 support. Line 460  with UTF-8 support.
460  .sp  .sp
461  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
462  end of the subject string. Without this option, a dollar also matches  end of the subject string. Without this option, a dollar also matches
463  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
464  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.
465  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
466  a pattern.  pattern.
467  .sp  .sp
468    PCRE_DOTALL    PCRE_DOTALL
469  .sp  .sp
470  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,
471  including newlines. Without it, newlines are excluded. This option is  including those that indicate newline. Without it, a dot does not match when
472  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
473  (?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
474  character, independent of the setting of this option.  negative class such as [^a] always matches newline characters, independent of
475    the setting of this option.
476    .sp
477      PCRE_DUPNAMES
478    .sp
479    If this bit is set, names used to identify capturing subpatterns need not be
480    unique. This can be helpful for certain types of pattern when it is known that
481    only one instance of the named subpattern can ever be matched. There are more
482    details of named subpatterns below; see also the
483    .\" HREF
484    \fBpcrepattern\fP
485    .\"
486    documentation.
487  .sp  .sp
488    PCRE_EXTENDED    PCRE_EXTENDED
489  .sp  .sp
490  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
491  ignored except when escaped or inside a character class. Whitespace does not  ignored except when escaped or inside a character class. Whitespace does not
492  include the VT character (code 11). In addition, characters between an  include the VT character (code 11). In addition, characters between an
493  unescaped # outside a character class and the next newline character,  unescaped # outside a character class and the next newline, inclusive, are also
494  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
495  be changed within a pattern by a (?x) option setting.  pattern by a (?x) option setting.
496  .P  .P
497  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
498  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 506  that is incompatible with Perl, but it i
506  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
507  special meaning causes an error, thus reserving these combinations for future  special meaning causes an error, thus reserving these combinations for future
508  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
509  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
510  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
511  pattern.  this option. It can also be set by a (?X) option setting within a pattern.
512  .sp  .sp
513    PCRE_FIRSTLINE    PCRE_FIRSTLINE
514  .sp  .sp
515  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
516  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
517  continue over the newline.  over the newline.
518  .sp  .sp
519    PCRE_MULTILINE    PCRE_MULTILINE
520  .sp  .sp
# Line 496  terminating newline (unless PCRE_DOLLAR_ Line 526  terminating newline (unless PCRE_DOLLAR_
526  Perl.  Perl.
527  .P  .P
528  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
529  match immediately following or immediately before any newline in the subject  match immediately following or immediately before internal newlines in the
530  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
531  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
532  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
533  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
534  .sp  .sp
535      PCRE_NEWLINE_CR
536      PCRE_NEWLINE_LF
537      PCRE_NEWLINE_CRLF
538      PCRE_NEWLINE_ANYCRLF
539      PCRE_NEWLINE_ANY
540    .sp
541    These options override the default newline definition that was chosen when PCRE
542    was built. Setting the first or the second specifies that a newline is
543    indicated by a single character (CR or LF, respectively). Setting
544    PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
545    CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
546    preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
547    that any Unicode newline sequence should be recognized. The Unicode newline
548    sequences are the three just mentioned, plus the single characters VT (vertical
549    tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
550    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
551    recognized only in UTF-8 mode.
552    .P
553    The newline setting in the options word uses three bits that are treated
554    as a number, giving eight possibilities. Currently only six are used (default
555    plus the five values above). This means that if you set more than one newline
556    option, the combination may or may not be sensible. For example,
557    PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
558    other combinations may yield unused numbers and cause an error.
559    .P
560    The only time that a line break is specially recognized when compiling a
561    pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
562    class is encountered. This indicates a comment that lasts until after the next
563    line break sequence. In other circumstances, line break sequences are treated
564    as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
565    as whitespace characters and are therefore ignored.
566    .P
567    The newline option that is set at compile time becomes the default that is used
568    for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
569    .sp
570    PCRE_NO_AUTO_CAPTURE    PCRE_NO_AUTO_CAPTURE
571  .sp  .sp
572  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 551  strings. Line 616  strings.
616  .sp  .sp
617  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
618  \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
619  both compiling functions.  both compiling functions. As PCRE has developed, some error codes have fallen
620    out of use. To avoid confusion, they have not been re-used.
621  .sp  .sp
622     0  no error     0  no error
623     1  \e at end of pattern     1  \e at end of pattern
# Line 563  both compiling functions. Line 629  both compiling functions.
629     7  invalid escape sequence in character class     7  invalid escape sequence in character class
630     8  range out of order in character class     8  range out of order in character class
631     9  nothing to repeat     9  nothing to repeat
632    10  operand of unlimited repeat could match the empty string    10  [this code is not in use]
633    11  internal error: unexpected repeat    11  internal error: unexpected repeat
634    12  unrecognized character after (?    12  unrecognized character after (?
635    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
# Line 572  both compiling functions. Line 638  both compiling functions.
638    16  erroffset passed as NULL    16  erroffset passed as NULL
639    17  unknown option bit(s) set    17  unknown option bit(s) set
640    18  missing ) after comment    18  missing ) after comment
641    19  parentheses nested too deeply    19  [this code is not in use]
642    20  regular expression too large    20  regular expression too large
643    21  failed to get memory    21  failed to get memory
644    22  unmatched parentheses    22  unmatched parentheses
645    23  internal error: code overflow    23  internal error: code overflow
646    24  unrecognized character after (?<    24  unrecognized character after (?<
647    25  lookbehind assertion is not fixed length    25  lookbehind assertion is not fixed length
648    26  malformed number after (?(    26  malformed number or name after (?(
649    27  conditional group contains more than two branches    27  conditional group contains more than two branches
650    28  assertion expected after (?(    28  assertion expected after (?(
651    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
652    30  unknown POSIX class name    30  unknown POSIX class name
653    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
654    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
655    33  spare error    33  [this code is not in use]
656    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
657    35  invalid condition (?(0)    35  invalid condition (?(0)
658    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
# Line 595  both compiling functions. Line 661  both compiling functions.
661    39  closing ) for (?C expected    39  closing ) for (?C expected
662    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
663    41  unrecognized character after (?P    41  unrecognized character after (?P
664    42  syntax error after (?P    42  syntax error in subpattern name (missing terminator)
665    43  two named groups have the same name    43  two named subpatterns have the same name
666    44  invalid UTF-8 string    44  invalid UTF-8 string
667    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
668    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
669    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
670      48  subpattern name is too long (maximum 32 characters)
671      49  too many named subpatterns (maximum 10,000)
672      50  repeated subpattern is too long
673      51  octal value is greater than \e377 (not in UTF-8 mode)
674      52  internal error: overran compiling workspace
675      53  internal error: previously-checked referenced subpattern not found
676      54  DEFINE group contains more than one branch
677      55  repeating a DEFINE group is not allowed
678      56  inconsistent NEWLINE options"
679      57  \eg is not followed by a braced name or an optionally braced
680            non-zero number
681      58  (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number
682  .  .
683  .  .
684  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 660  bytes is created. Line 738  bytes is created.
738  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
739  .rs  .rs
740  .sp  .sp
741  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
742  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
743  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
744  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
745  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
746  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
747  .P  characters with codes greater than 128, you should either use UTF-8 and
748  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.
749  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
750  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
751  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.
752  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
753  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
754    default "C" locale of the local system, which may cause them to be different.
755    .P
756    The internal tables can always be overridden by tables supplied by the
757    application that calls PCRE. These may be created in a different locale from
758    the default. As more and more applications change to using Unicode, the need
759    for this locale support is expected to die away.
760  .P  .P
761  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
762  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 769  the following code could be used:
769    tables = pcre_maketables();    tables = pcre_maketables();
770    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
771  .sp  .sp
772    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
773    are using Windows, the name for the French locale is "french".
774    .P
775  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
776  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
777  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 818  check against passing an arbitrary memor
818  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
819  .sp  .sp
820    int rc;    int rc;
821    unsigned long int length;    size_t length;
822    rc = pcre_fullinfo(    rc = pcre_fullinfo(
823      re,               /* result of pcre_compile() */      re,               /* result of pcre_compile() */
824      pe,               /* result of pcre_study(), or NULL */      pe,               /* result of pcre_study(), or NULL */
# Line 763  a NULL table pointer. Line 850  a NULL table pointer.
850    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
851  .sp  .sp
852  Return information about the first byte of any matched string, for a  Return information about the first byte of any matched string, for a
853  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
854  old name is still recognized for backwards compatibility.)  variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
855    still recognized for backwards compatibility.)
856  .P  .P
857  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
858  (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  
859  .sp  .sp
860  (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
861  starts with "^", or  starts with "^", or
# Line 787  table indicating a fixed set of bytes fo Line 874  table indicating a fixed set of bytes fo
874  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
875  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
876  .sp  .sp
877      PCRE_INFO_JCHANGED
878    .sp
879    Return 1 if the (?J) option setting is used in the pattern, otherwise 0. The
880    fourth argument should point to an \fBint\fP variable. The (?J) internal option
881    setting changes the local PCRE_DUPNAMES option.
882    .sp
883    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
884  .sp  .sp
885  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 896  is -1.
896  .sp  .sp
897  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
898  names are just an additional way of identifying the parentheses, which still  names are just an additional way of identifying the parentheses, which still
899  acquire numbers. A convenience function called \fBpcre_get_named_substring()\fP  acquire numbers. Several convenience functions such as
900  is provided for extracting an individual captured substring by name. It is also  \fBpcre_get_named_substring()\fP are provided for extracting captured
901  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
902  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
903  \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,
904  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
905    values.
906  .P  .P
907  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
908  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 911  length of the longest name. PCRE_INFO_NA
911  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
912  are the number of the capturing parenthesis, most significant byte first. The  are the number of the capturing parenthesis, most significant byte first. The
913  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
914  alphabetical order. For example, consider the following pattern (assume  alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of
915    their parentheses numbers. For example, consider the following pattern (assume
916  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  PCRE_EXTENDED is set, so white space - including newlines - is ignored):
917  .sp  .sp
918  .\" JOIN  .\" JOIN
919    (?P<date> (?P<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
920    (?P<month>\ed\ed) - (?P<day>\ed\ed) )    (?<month>\ed\ed) - (?<day>\ed\ed) )
921  .sp  .sp
922  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
923  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 929  bytes shows in hexadecimal, and undefine
929    00 02 y  e  a  r  00 ??    00 02 y  e  a  r  00 ??
930  .sp  .sp
931  When writing code to extract data from named subpatterns using the  When writing code to extract data from named subpatterns using the
932  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
933  different for each compiled pattern.  different for each compiled pattern.
934  .sp  .sp
935      PCRE_INFO_OKPARTIAL
936    .sp
937    Return 1 if the pattern can be used for partial matching, otherwise 0. The
938    fourth argument should point to an \fBint\fP variable. The
939    .\" HREF
940    \fBpcrepartial\fP
941    .\"
942    documentation lists the restrictions that apply to patterns when partial
943    matching is used.
944    .sp
945    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
946  .sp  .sp
947  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
948  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
949  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
950  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
951    they are the options that will be in force when matching starts. For example,
952    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
953    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
954  .P  .P
955  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
956  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 1057  documentation for a discussion of saving Line 1165  documentation for a discussion of saving
1165  .rs  .rs
1166  .sp  .sp
1167  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
1168  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,
1169  PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
1170  .sp  .sp
1171    PCRE_ANCHORED    PCRE_ANCHORED
1172  .sp  .sp
# Line 1067  matching position. If a pattern was comp Line 1175  matching position. If a pattern was comp
1175  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
1176  matching time.  matching time.
1177  .sp  .sp
1178      PCRE_NEWLINE_CR
1179      PCRE_NEWLINE_LF
1180      PCRE_NEWLINE_CRLF
1181      PCRE_NEWLINE_ANYCRLF
1182      PCRE_NEWLINE_ANY
1183    .sp
1184    These options override the newline definition that was chosen or defaulted when
1185    the pattern was compiled. For details, see the description of
1186    \fBpcre_compile()\fP above. During matching, the newline choice affects the
1187    behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1188    the way the match position is advanced after a match failure for an unanchored
1189    pattern. When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is
1190    set, and a match attempt fails when the current position is at a CRLF sequence,
1191    the match position is advanced by two characters instead of one, in other
1192    words, to after the CRLF.
1193    .sp
1194    PCRE_NOTBOL    PCRE_NOTBOL
1195  .sp  .sp
1196  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 1198  is set to the offset of the first charac Line 1322  is set to the offset of the first charac
1322  first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the  first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the
1323  subject string matched by the entire pattern. The next pair is used for the  subject string matched by the entire pattern. The next pair is used for the
1324  first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP  first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP
1325  is the number of pairs that have been set. If there are no capturing  is one more than the highest numbered pair that has been set. For example, if
1326  subpatterns, the return value from a successful match is 1, indicating that  two substrings have been captured, the returned value is 3. If there are no
1327  just the first pair of offsets has been set.  capturing subpatterns, the return value from a successful match is 1,
1328  .P  indicating that just the first pair of offsets has been set.
 Some convenience functions are provided for extracting the captured substrings  
 as separate strings. These are described in the following section.  
 .P  
 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.  
1329  .P  .P
1330  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
1331  string that it matched that is returned.  string that it matched that is returned.
# Line 1223  the \fIovector\fP is not big enough to r Line 1339  the \fIovector\fP is not big enough to r
1339  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
1340  advisable to supply an \fIovector\fP.  advisable to supply an \fIovector\fP.
1341  .P  .P
1342  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
1343  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
1344  \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
1345  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.
1346    .P
1347    It is possible for capturing subpattern number \fIn+1\fP to match some part of
1348    the subject when subpattern \fIn\fP has not been used at all. For example, if
1349    the string "abc" is matched against the pattern (a|(z))(bc) the return from the
1350    function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
1351    happens, both values in the offset pairs corresponding to unused subpatterns
1352    are set to -1.
1353    .P
1354    Offset values that correspond to unused subpatterns at the end of the
1355    expression are also set to -1. For example, if the string "abc" is matched
1356    against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1357    return from the function is 2, because the highest used capturing subpattern
1358    number is 1. However, you can refer to the offsets for the second and third
1359    capturing subpatterns if you wish (assuming the vector is large enough, of
1360    course).
1361    .P
1362    Some convenience functions are provided for extracting the captured substrings
1363    as separate strings. These are described below.
1364  .  .
1365  .\" HTML <a name="errorlist"></a>  .\" HTML <a name="errorlist"></a>
1366  .SS "Return values from \fBpcre_exec()\fP"  .SS "Error return values from \fBpcre_exec()\fP"
1367  .rs  .rs
1368  .sp  .sp
1369  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 1390  compiled in an environment of one endian
1390  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
1391  not present.  not present.
1392  .sp  .sp
1393    PCRE_ERROR_UNKNOWN_NODE   (-5)    PCRE_ERROR_UNKNOWN_OPCODE (-5)
1394  .sp  .sp
1395  While running the pattern match, an unknown item was encountered in the  While running the pattern match, an unknown item was encountered in the
1396  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 1416  The backtracking limit, as specified by
1416  \fBpcre_extra\fP structure (or defaulted) was reached. See the description  \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1417  above.  above.
1418  .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  
1419    PCRE_ERROR_CALLOUT        (-9)    PCRE_ERROR_CALLOUT        (-9)
1420  .sp  .sp
1421  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 1331  in PCRE or by overwriting of the compile Line 1459  in PCRE or by overwriting of the compile
1459    PCRE_ERROR_BADCOUNT       (-15)    PCRE_ERROR_BADCOUNT       (-15)
1460  .sp  .sp
1461  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.
1462    .sp
1463      PCRE_ERROR_RECURSIONLIMIT (-21)
1464    .sp
1465    The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1466    field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1467    description above.
1468    .sp
1469      PCRE_ERROR_BADNEWLINE     (-23)
1470    .sp
1471    An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1472    .P
1473    Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1474  .  .
1475  .  .
1476  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1342  This error is given if the value of the Line 1482  This error is given if the value of the
1482  .ti +5n  .ti +5n
1483  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1484  .PP  .PP
 .br  
1485  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1486  .ti +5n  .ti +5n
1487  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1488  .ti +5n  .ti +5n
1489  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1490  .PP  .PP
 .br  
1491  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1492  .ti +5n  .ti +5n
1493  .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 1498  Captured substrings can be accessed dire
1498  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
1499  as new, separate, zero-terminated strings. These functions identify substrings  as new, separate, zero-terminated strings. These functions identify substrings
1500  by number. The next section describes functions for extracting named  by number. The next section describes functions for extracting named
1501  substrings. A substring that contains a binary zero is correctly extracted and  substrings.
1502  has a further zero added on the end, but the result is not, of course,  .P
1503  a C string.  A substring that contains a binary zero is correctly extracted and has a
1504    further zero added on the end, but the result is not, of course, a C string.
1505    However, you can process such a string by referring to the length that is
1506    returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
1507    Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
1508    for handling strings containing binary zeros, because the end of the final
1509    string is not independently indicated.
1510  .P  .P
1511  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:
1512  \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 1526  the string is placed in \fIbuffer\fP, wh
1526  \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
1527  obtained via \fBpcre_malloc\fP, and its address is returned via  obtained via \fBpcre_malloc\fP, and its address is returned via
1528  \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
1529  including the terminating zero, or one of  including the terminating zero, or one of these error codes:
1530  .sp  .sp
1531    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1532  .sp  .sp
# Line 1398  and builds a list of pointers to them. A Line 1542  and builds a list of pointers to them. A
1542  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
1543  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
1544  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
1545  function is zero if all went well, or  function is zero if all went well, or the error code
1546  .sp  .sp
1547    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1548  .sp  .sp
# Line 1417  a previous call of \fBpcre_get_substring Line 1561  a previous call of \fBpcre_get_substring
1561  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
1562  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
1563  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
1564  linked via a special interface to another programming language which cannot use  linked via a special interface to another programming language that cannot use
1565  \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
1566  provided.  provided.
1567  .  .
# Line 1429  provided. Line 1573  provided.
1573  .ti +5n  .ti +5n
1574  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1575  .PP  .PP
 .br  
1576  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1577  .ti +5n  .ti +5n
1578  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1438  provided. Line 1581  provided.
1581  .ti +5n  .ti +5n
1582  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1583  .PP  .PP
 .br  
1584  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1585  .ti +5n  .ti +5n
1586  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1450  provided. Line 1592  provided.
1592  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.
1593  For example, for this pattern  For example, for this pattern
1594  .sp  .sp
1595    (a+)b(?P<xxx>\ed+)...    (a+)b(?<xxx>\ed+)...
1596  .sp  .sp
1597  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
1598  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
1599  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
1600    pattern, and the second is the name. The yield of the function is the
1601  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
1602  that name.  that name.
1603  .P  .P
# Line 1462  Given the number, you can extract the su Line 1605  Given the number, you can extract the su
1605  functions described in the previous section. For convenience, there are also  functions described in the previous section. For convenience, there are also
1606  two functions that do the whole job.  two functions that do the whole job.
1607  .P  .P
1608  Most of the arguments of \fIpcre_copy_named_substring()\fP and  Most of the arguments of \fBpcre_copy_named_substring()\fP and
1609  \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
1610  functions that extract by number. As these are described in the previous  functions that extract by number. As these are described in the previous
1611  section, they are not re-described here. There are just two differences:  section, they are not re-described here. There are just two differences:
1612  .P  .P
# Line 1473  pattern. This is needed in order to gain Line 1616  pattern. This is needed in order to gain
1616  translation table.  translation table.
1617  .P  .P
1618  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1619  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1620  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1621    the behaviour may not be what you want (see the next section).
1622    .
1623    .
1624    .SH "DUPLICATE SUBPATTERN NAMES"
1625    .rs
1626    .sp
1627    .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
1628    .ti +5n
1629    .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
1630    .PP
1631    When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
1632    are not required to be unique. Normally, patterns with duplicate names are such
1633    that in any one match, only one of the named subpatterns participates. An
1634    example is shown in the
1635    .\" HREF
1636    \fBpcrepattern\fP
1637    .\"
1638    documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP
1639    and \fBpcre_get_named_substring()\fP return the first substring corresponding
1640    to the given name that is set. If none are set, an empty string is returned.
1641    The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are
1642    associated with the name, but it is not defined which it is.
1643    .sp
1644    If you want to get full details of all captured substrings for a given name,
1645    you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1646    argument is the compiled pattern, and the second is the name. The third and
1647    fourth are pointers to variables which are updated by the function. After it
1648    has run, they point to the first and last entries in the name-to-number table
1649    for the given name. The function itself returns the length of each entry, or
1650    PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1651    described above in the section entitled \fIInformation about a pattern\fP.
1652    Given all the relevant entries for the name, you can extract each of their
1653    numbers, and hence the captured data, if any.
1654  .  .
1655  .  .
1656  .SH "FINDING ALL POSSIBLE MATCHES"  .SH "FINDING ALL POSSIBLE MATCHES"
# Line 1512  will yield PCRE_ERROR_NOMATCH. Line 1688  will yield PCRE_ERROR_NOMATCH.
1688  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
1689  .P  .P
1690  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
1691  a compiled pattern, using a "DFA" matching algorithm. This has different  a compiled pattern, using a matching algorithm that scans the subject string
1692  characteristics to the normal algorithm, and is not compatible with Perl. Some  just once, and does not backtrack. This has different characteristics to the
1693  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
1694  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
1695  matching algorithms, see the  matching can be useful. For a discussion of the two matching algorithms, see
1696    the
1697  .\" HREF  .\" HREF
1698  \fBpcrematching\fP  \fBpcrematching\fP
1699  .\"  .\"
# Line 1531  here. Line 1708  here.
1708  The two additional arguments provide workspace for the function. The workspace  The two additional arguments provide workspace for the function. The workspace
1709  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
1710  multiple paths through the pattern tree. More workspace will be needed for  multiple paths through the pattern tree. More workspace will be needed for
1711  patterns and subjects where there are a lot of possible matches.  patterns and subjects where there are a lot of potential matches.
1712  .P  .P
1713  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:
1714  .sp  .sp
# Line 1554  Here is an example of a simple call to \ Line 1731  Here is an example of a simple call to \
1731  .rs  .rs
1732  .sp  .sp
1733  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
1734  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,
1735  PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,
1736  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
1737  the same as for \fBpcre_exec()\fP, so their description is not repeated here.  the same as for \fBpcre_exec()\fP, so their description is not repeated here.
1738  .sp  .sp
# Line 1572  matching string. Line 1749  matching string.
1749    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
1750  .sp  .sp
1751  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
1752  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
1753  this is necessarily the shortest possible match at the first possible matching  works, this is necessarily the shortest possible match at the first possible
1754  point in the subject string.  matching point in the subject string.
1755  .sp  .sp
1756    PCRE_DFA_RESTART    PCRE_DFA_RESTART
1757  .sp  .sp
# Line 1613  the three matched strings are Line 1790  the three matched strings are
1790  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
1791  the number of matched substrings. The substrings themselves are returned in  the number of matched substrings. The substrings themselves are returned in
1792  \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
1793  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
1794  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,
1795  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
1796  data, even though the meaning of the strings is different.)  returns data, even though the meaning of the strings is different.)
1797  .P  .P
1798  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
1799  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 1820  that it does not support, for instance,
1820  .sp  .sp
1821    PCRE_ERROR_DFA_UCOND      (-17)    PCRE_ERROR_DFA_UCOND      (-17)
1822  .sp  .sp
1823  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
1824  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
1825    group. These are not supported.
1826  .sp  .sp
1827    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
1828  .sp  .sp
# Line 1663  When a recursive subpattern is processed Line 1841  When a recursive subpattern is processed
1841  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1842  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
1843  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
1844  .P  .
1845  .in 0  .
1846  Last updated: 18 January 2006  .SH "SEE ALSO"
1847  .br  .rs
1848  Copyright (c) 1997-2006 University of Cambridge.  .sp
1849    \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1850    \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1851    \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1852    .
1853    .
1854    .SH AUTHOR
1855    .rs
1856    .sp
1857    .nf
1858    Philip Hazel
1859    University Computing Service
1860    Cambridge CB2 3QH, England.
1861    .fi
1862    .
1863    .
1864    .SH REVISION
1865    .rs
1866    .sp
1867    .nf
1868    Last updated: 30 July 2007
1869    Copyright (c) 1997-2007 University of Cambridge.
1870    .fi

Legend:
Removed from v.87  
changed lines
  Added in v.197

  ViewVC Help
Powered by ViewVC 1.1.5