/[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 227 by ph10, Tue Aug 21 15:00:15 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    .\" 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. The choice of newline convention does not affect the interpretation of
258    the \en or \er escape sequences.
259    .
260    .
261  .SH MULTITHREADING  .SH MULTITHREADING
262  .rs  .rs
263  .sp  .sp
# Line 250  which it was compiled. Details are given Line 279  which it was compiled. Details are given
279  .\" HREF  .\" HREF
280  \fBpcreprecompile\fP  \fBpcreprecompile\fP
281  .\"  .\"
282  documentation.  documentation. However, compiling a regular expression with one version of PCRE
283    for use with a different version is not guaranteed to work and may cause
284    crashes.
285  .  .
286  .  .
287  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 281  properties is available; otherwise it is Line 312  properties is available; otherwise it is
312  .sp  .sp
313    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
314  .sp  .sp
315  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
316  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
317  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
318    default should normally be the standard sequence for your operating system.
319  .sp  .sp
320    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
321  .sp  .sp
# Line 353  The pattern is a C string terminated by Line 385  The pattern is a C string terminated by
385  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
386  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
387  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
388  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.
389  .P  .P
390  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
391  depend on memory location, the complete \fBpcre\fP data block is not  depend on memory location, the complete \fBpcre\fP data block is not
392  fully relocatable, because it may contain a copy of the \fItableptr\fP  fully relocatable, because it may contain a copy of the \fItableptr\fP
393  argument, which is an address (see below).  argument, which is an address (see below).
394  .P  .P
395  The \fIoptions\fP argument contains independent bits that affect the  The \fIoptions\fP argument contains various bit settings that affect the
396  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
397  options are described below. Some of them, in particular, those that are  options are described below. Some of them, in particular, those that are
398  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 402  the detailed description in the
402  .\"  .\"
403  documentation). For these options, the contents of the \fIoptions\fP argument  documentation). For these options, the contents of the \fIoptions\fP argument
404  specifies their initial settings at the start of compilation and execution. The  specifies their initial settings at the start of compilation and execution. The
405  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
406  time.  matching as well as at compile time.
407  .P  .P
408  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
409  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 474  with UTF-8 support.
474  .sp  .sp
475  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
476  end of the subject string. Without this option, a dollar also matches  end of the subject string. Without this option, a dollar also matches
477  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
478  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.
479  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
480  a pattern.  pattern.
481  .sp  .sp
482    PCRE_DOTALL    PCRE_DOTALL
483  .sp  .sp
484  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,
485  including newlines. Without it, newlines are excluded. This option is  including those that indicate newline. Without it, a dot does not match when
486  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
487  (?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
488  character, independent of the setting of this option.  negative class such as [^a] always matches newline characters, independent of
489    the setting of this option.
490    .sp
491      PCRE_DUPNAMES
492    .sp
493    If this bit is set, names used to identify capturing subpatterns need not be
494    unique. This can be helpful for certain types of pattern when it is known that
495    only one instance of the named subpattern can ever be matched. There are more
496    details of named subpatterns below; see also the
497    .\" HREF
498    \fBpcrepattern\fP
499    .\"
500    documentation.
501  .sp  .sp
502    PCRE_EXTENDED    PCRE_EXTENDED
503  .sp  .sp
504  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
505  ignored except when escaped or inside a character class. Whitespace does not  ignored except when escaped or inside a character class. Whitespace does not
506  include the VT character (code 11). In addition, characters between an  include the VT character (code 11). In addition, characters between an
507  unescaped # outside a character class and the next newline character,  unescaped # outside a character class and the next newline, inclusive, are also
508  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
509  be changed within a pattern by a (?x) option setting.  pattern by a (?x) option setting.
510  .P  .P
511  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
512  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 520  that is incompatible with Perl, but it i
520  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
521  special meaning causes an error, thus reserving these combinations for future  special meaning causes an error, thus reserving these combinations for future
522  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
523  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
524  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
525  pattern.  this option. It can also be set by a (?X) option setting within a pattern.
526  .sp  .sp
527    PCRE_FIRSTLINE    PCRE_FIRSTLINE
528  .sp  .sp
529  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
530  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
531  continue over the newline.  over the newline.
532  .sp  .sp
533    PCRE_MULTILINE    PCRE_MULTILINE
534  .sp  .sp
# Line 496  terminating newline (unless PCRE_DOLLAR_ Line 540  terminating newline (unless PCRE_DOLLAR_
540  Perl.  Perl.
541  .P  .P
542  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
543  match immediately following or immediately before any newline in the subject  match immediately following or immediately before internal newlines in the
544  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
545  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
546  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
547  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
548  .sp  .sp
549      PCRE_NEWLINE_CR
550      PCRE_NEWLINE_LF
551      PCRE_NEWLINE_CRLF
552      PCRE_NEWLINE_ANYCRLF
553      PCRE_NEWLINE_ANY
554    .sp
555    These options override the default newline definition that was chosen when PCRE
556    was built. Setting the first or the second specifies that a newline is
557    indicated by a single character (CR or LF, respectively). Setting
558    PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
559    CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
560    preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
561    that any Unicode newline sequence should be recognized. The Unicode newline
562    sequences are the three just mentioned, plus the single characters VT (vertical
563    tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
564    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
565    recognized only in UTF-8 mode.
566    .P
567    The newline setting in the options word uses three bits that are treated
568    as a number, giving eight possibilities. Currently only six are used (default
569    plus the five values above). This means that if you set more than one newline
570    option, the combination may or may not be sensible. For example,
571    PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
572    other combinations may yield unused numbers and cause an error.
573    .P
574    The only time that a line break is specially recognized when compiling a
575    pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
576    class is encountered. This indicates a comment that lasts until after the next
577    line break sequence. In other circumstances, line break sequences are treated
578    as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
579    as whitespace characters and are therefore ignored.
580    .P
581    The newline option that is set at compile time becomes the default that is used
582    for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
583    .sp
584    PCRE_NO_AUTO_CAPTURE    PCRE_NO_AUTO_CAPTURE
585  .sp  .sp
586  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 615  page.
615    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
616  .sp  .sp
617  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
618  automatically checked. If an invalid UTF-8 sequence of bytes is found,  automatically checked. There is a discussion about the
619  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcre.html#utf8strings">
620  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
621  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
622  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
623  Note that this option can also be passed to \fBpcre_exec()\fP and  in the main
624  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
625  strings.  \fBpcre\fP
626    .\"
627    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
628    returns an error. If you already know that your pattern is valid, and you want
629    to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
630    option. When it is set, the effect of passing an invalid UTF-8 string as a
631    pattern is undefined. It may cause your program to crash. Note that this option
632    can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
633    the UTF-8 validity checking of subject strings.
634  .  .
635  .  .
636  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 551  strings. Line 638  strings.
638  .sp  .sp
639  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
640  \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
641  both compiling functions.  both compiling functions. As PCRE has developed, some error codes have fallen
642    out of use. To avoid confusion, they have not been re-used.
643  .sp  .sp
644     0  no error     0  no error
645     1  \e at end of pattern     1  \e at end of pattern
# Line 563  both compiling functions. Line 651  both compiling functions.
651     7  invalid escape sequence in character class     7  invalid escape sequence in character class
652     8  range out of order in character class     8  range out of order in character class
653     9  nothing to repeat     9  nothing to repeat
654    10  operand of unlimited repeat could match the empty string    10  [this code is not in use]
655    11  internal error: unexpected repeat    11  internal error: unexpected repeat
656    12  unrecognized character after (?    12  unrecognized character after (?
657    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 660  both compiling functions.
660    16  erroffset passed as NULL    16  erroffset passed as NULL
661    17  unknown option bit(s) set    17  unknown option bit(s) set
662    18  missing ) after comment    18  missing ) after comment
663    19  parentheses nested too deeply    19  [this code is not in use]
664    20  regular expression too large    20  regular expression too large
665    21  failed to get memory    21  failed to get memory
666    22  unmatched parentheses    22  unmatched parentheses
667    23  internal error: code overflow    23  internal error: code overflow
668    24  unrecognized character after (?<    24  unrecognized character after (?<
669    25  lookbehind assertion is not fixed length    25  lookbehind assertion is not fixed length
670    26  malformed number after (?(    26  malformed number or name after (?(
671    27  conditional group contains more than two branches    27  conditional group contains more than two branches
672    28  assertion expected after (?(    28  assertion expected after (?(
673    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
674    30  unknown POSIX class name    30  unknown POSIX class name
675    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
676    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
677    33  spare error    33  [this code is not in use]
678    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
679    35  invalid condition (?(0)    35  invalid condition (?(0)
680    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
# Line 595  both compiling functions. Line 683  both compiling functions.
683    39  closing ) for (?C expected    39  closing ) for (?C expected
684    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
685    41  unrecognized character after (?P    41  unrecognized character after (?P
686    42  syntax error after (?P    42  syntax error in subpattern name (missing terminator)
687    43  two named groups have the same name    43  two named subpatterns have the same name
688    44  invalid UTF-8 string    44  invalid UTF-8 string
689    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
690    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
691    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
692      48  subpattern name is too long (maximum 32 characters)
693      49  too many named subpatterns (maximum 10,000)
694      50  [this code is not in use]
695      51  octal value is greater than \e377 (not in UTF-8 mode)
696      52  internal error: overran compiling workspace
697      53  internal error: previously-checked referenced subpattern not found
698      54  DEFINE group contains more than one branch
699      55  repeating a DEFINE group is not allowed
700      56  inconsistent NEWLINE options"
701      57  \eg is not followed by a braced name or an optionally braced
702            non-zero number
703      58  (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number
704  .  .
705  .  .
706  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 660  bytes is created. Line 760  bytes is created.
760  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
761  .rs  .rs
762  .sp  .sp
763  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
764  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
765  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
766  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
767  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
768  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
769  .P  characters with codes greater than 128, you should either use UTF-8 and
770  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.
771  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
772  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
773  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.
774  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
775  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
776    default "C" locale of the local system, which may cause them to be different.
777    .P
778    The internal tables can always be overridden by tables supplied by the
779    application that calls PCRE. These may be created in a different locale from
780    the default. As more and more applications change to using Unicode, the need
781    for this locale support is expected to die away.
782  .P  .P
783  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
784  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 791  the following code could be used:
791    tables = pcre_maketables();    tables = pcre_maketables();
792    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
793  .sp  .sp
794    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
795    are using Windows, the name for the French locale is "french".
796    .P
797  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
798  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
799  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 840  check against passing an arbitrary memor
840  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
841  .sp  .sp
842    int rc;    int rc;
843    unsigned long int length;    size_t length;
844    rc = pcre_fullinfo(    rc = pcre_fullinfo(
845      re,               /* result of pcre_compile() */      re,               /* result of pcre_compile() */
846      pe,               /* result of pcre_study(), or NULL */      pe,               /* result of pcre_study(), or NULL */
# Line 763  a NULL table pointer. Line 872  a NULL table pointer.
872    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
873  .sp  .sp
874  Return information about the first byte of any matched string, for a  Return information about the first byte of any matched string, for a
875  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
876  old name is still recognized for backwards compatibility.)  variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
877    still recognized for backwards compatibility.)
878  .P  .P
879  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
880  (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  
881  .sp  .sp
882  (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
883  starts with "^", or  starts with "^", or
# Line 787  table indicating a fixed set of bytes fo Line 896  table indicating a fixed set of bytes fo
896  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
897  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
898  .sp  .sp
899      PCRE_INFO_HASCRORLF
900    .sp
901    Return 1 if the pattern contains any explicit matches for CR or LF characters,
902    otherwise 0. The fourth argument should point to an \fBint\fP variable.
903    .sp
904      PCRE_INFO_JCHANGED
905    .sp
906    Return 1 if the (?J) option setting is used in the pattern, otherwise 0. The
907    fourth argument should point to an \fBint\fP variable. The (?J) internal option
908    setting changes the local PCRE_DUPNAMES option.
909    .sp
910    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
911  .sp  .sp
912  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 923  is -1.
923  .sp  .sp
924  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
925  names are just an additional way of identifying the parentheses, which still  names are just an additional way of identifying the parentheses, which still
926  acquire numbers. A convenience function called \fBpcre_get_named_substring()\fP  acquire numbers. Several convenience functions such as
927  is provided for extracting an individual captured substring by name. It is also  \fBpcre_get_named_substring()\fP are provided for extracting captured
928  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
929  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
930  \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,
931  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
932    values.
933  .P  .P
934  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
935  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 938  length of the longest name. PCRE_INFO_NA
938  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
939  are the number of the capturing parenthesis, most significant byte first. The  are the number of the capturing parenthesis, most significant byte first. The
940  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
941  alphabetical order. For example, consider the following pattern (assume  alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of
942    their parentheses numbers. For example, consider the following pattern (assume
943  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  PCRE_EXTENDED is set, so white space - including newlines - is ignored):
944  .sp  .sp
945  .\" JOIN  .\" JOIN
946    (?P<date> (?P<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
947    (?P<month>\ed\ed) - (?P<day>\ed\ed) )    (?<month>\ed\ed) - (?<day>\ed\ed) )
948  .sp  .sp
949  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
950  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 956  bytes shows in hexadecimal, and undefine
956    00 02 y  e  a  r  00 ??    00 02 y  e  a  r  00 ??
957  .sp  .sp
958  When writing code to extract data from named subpatterns using the  When writing code to extract data from named subpatterns using the
959  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
960  different for each compiled pattern.  different for each compiled pattern.
961  .sp  .sp
962      PCRE_INFO_OKPARTIAL
963    .sp
964    Return 1 if the pattern can be used for partial matching, otherwise 0. The
965    fourth argument should point to an \fBint\fP variable. The
966    .\" HREF
967    \fBpcrepartial\fP
968    .\"
969    documentation lists the restrictions that apply to patterns when partial
970    matching is used.
971    .sp
972    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
973  .sp  .sp
974  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
975  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
976  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
977  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
978    they are the options that will be in force when matching starts. For example,
979    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
980    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
981  .P  .P
982  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
983  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 1053  called. See the Line 1188  called. See the
1188  .\"  .\"
1189  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1190  .  .
1191    .\" HTML <a name="execoptions"></a>
1192  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1193  .rs  .rs
1194  .sp  .sp
1195  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
1196  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,
1197  PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
1198  .sp  .sp
1199    PCRE_ANCHORED    PCRE_ANCHORED
1200  .sp  .sp
# Line 1067  matching position. If a pattern was comp Line 1203  matching position. If a pattern was comp
1203  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
1204  matching time.  matching time.
1205  .sp  .sp
1206      PCRE_NEWLINE_CR
1207      PCRE_NEWLINE_LF
1208      PCRE_NEWLINE_CRLF
1209      PCRE_NEWLINE_ANYCRLF
1210      PCRE_NEWLINE_ANY
1211    .sp
1212    These options override the newline definition that was chosen or defaulted when
1213    the pattern was compiled. For details, see the description of
1214    \fBpcre_compile()\fP above. During matching, the newline choice affects the
1215    behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1216    the way the match position is advanced after a match failure for an unanchored
1217    pattern.
1218    .P
1219    When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
1220    match attempt for an unanchored pattern fails when the current position is at a
1221    CRLF sequence, and the pattern contains no explicit matches for CR or NL
1222    characters, the match position is advanced by two characters instead of one, in
1223    other words, to after the CRLF.
1224    .P
1225    The above rule is a compromise that makes the most common cases work as
1226    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1227    set), it does not match the string "\er\enA" because, after failing at the
1228    start, it skips both the CR and the LF before retrying. However, the pattern
1229    [\er\en]A does match that string, because it contains an explicit CR or LF
1230    reference, and so advances only by one character after the first failure.
1231    Note than an explicit CR or LF reference occurs for negated character classes
1232    such as [^X] because they can match CR or LF characters.
1233    .P
1234    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1235    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1236    .sp
1237    PCRE_NOTBOL    PCRE_NOTBOL
1238  .sp  .sp
1239  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 1108  code that demonstrates how to do this in Line 1275  code that demonstrates how to do this in
1275  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
1276  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1277  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
1278  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
1279  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1280  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HTML <a href="pcre.html#utf8strings">
1281    .\" </a>
1282    section on UTF-8 support
1283    .\"
1284    in the main
1285    .\" HREF
1286    \fBpcre\fP
1287    .\"
1288    page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
1289    the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
1290    PCRE_ERROR_BADUTF8_OFFSET is returned.
1291  .P  .P
1292  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
1293  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 1198  is set to the offset of the first charac Line 1375  is set to the offset of the first charac
1375  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
1376  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
1377  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
1378  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
1379  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
1380  just the first pair of offsets has been set.  capturing subpatterns, the return value from a successful match is 1,
1381  .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.  
1382  .P  .P
1383  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
1384  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 1392  the \fIovector\fP is not big enough to r
1392  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
1393  advisable to supply an \fIovector\fP.  advisable to supply an \fIovector\fP.
1394  .P  .P
1395  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
1396  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
1397  \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
1398  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.
1399    .P
1400    It is possible for capturing subpattern number \fIn+1\fP to match some part of
1401    the subject when subpattern \fIn\fP has not been used at all. For example, if
1402    the string "abc" is matched against the pattern (a|(z))(bc) the return from the
1403    function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
1404    happens, both values in the offset pairs corresponding to unused subpatterns
1405    are set to -1.
1406    .P
1407    Offset values that correspond to unused subpatterns at the end of the
1408    expression are also set to -1. For example, if the string "abc" is matched
1409    against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1410    return from the function is 2, because the highest used capturing subpattern
1411    number is 1. However, you can refer to the offsets for the second and third
1412    capturing subpatterns if you wish (assuming the vector is large enough, of
1413    course).
1414    .P
1415    Some convenience functions are provided for extracting the captured substrings
1416    as separate strings. These are described below.
1417  .  .
1418  .\" HTML <a name="errorlist"></a>  .\" HTML <a name="errorlist"></a>
1419  .SS "Return values from \fBpcre_exec()\fP"  .SS "Error return values from \fBpcre_exec()\fP"
1420  .rs  .rs
1421  .sp  .sp
1422  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 1443  compiled in an environment of one endian
1443  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
1444  not present.  not present.
1445  .sp  .sp
1446    PCRE_ERROR_UNKNOWN_NODE   (-5)    PCRE_ERROR_UNKNOWN_OPCODE (-5)
1447  .sp  .sp
1448  While running the pattern match, an unknown item was encountered in the  While running the pattern match, an unknown item was encountered in the
1449  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 1469  The backtracking limit, as specified by
1469  \fBpcre_extra\fP structure (or defaulted) was reached. See the description  \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1470  above.  above.
1471  .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  
1472    PCRE_ERROR_CALLOUT        (-9)    PCRE_ERROR_CALLOUT        (-9)
1473  .sp  .sp
1474  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 1512  in PCRE or by overwriting of the compile
1512    PCRE_ERROR_BADCOUNT       (-15)    PCRE_ERROR_BADCOUNT       (-15)
1513  .sp  .sp
1514  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.
1515    .sp
1516      PCRE_ERROR_RECURSIONLIMIT (-21)
1517    .sp
1518    The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1519    field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1520    description above.
1521    .sp
1522      PCRE_ERROR_BADNEWLINE     (-23)
1523    .sp
1524    An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1525    .P
1526    Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1527  .  .
1528  .  .
1529  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1342  This error is given if the value of the Line 1535  This error is given if the value of the
1535  .ti +5n  .ti +5n
1536  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1537  .PP  .PP
 .br  
1538  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1539  .ti +5n  .ti +5n
1540  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1541  .ti +5n  .ti +5n
1542  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1543  .PP  .PP
 .br  
1544  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1545  .ti +5n  .ti +5n
1546  .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 1551  Captured substrings can be accessed dire
1551  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
1552  as new, separate, zero-terminated strings. These functions identify substrings  as new, separate, zero-terminated strings. These functions identify substrings
1553  by number. The next section describes functions for extracting named  by number. The next section describes functions for extracting named
1554  substrings. A substring that contains a binary zero is correctly extracted and  substrings.
1555  has a further zero added on the end, but the result is not, of course,  .P
1556  a C string.  A substring that contains a binary zero is correctly extracted and has a
1557    further zero added on the end, but the result is not, of course, a C string.
1558    However, you can process such a string by referring to the length that is
1559    returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
1560    Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
1561    for handling strings containing binary zeros, because the end of the final
1562    string is not independently indicated.
1563  .P  .P
1564  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:
1565  \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 1579  the string is placed in \fIbuffer\fP, wh
1579  \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
1580  obtained via \fBpcre_malloc\fP, and its address is returned via  obtained via \fBpcre_malloc\fP, and its address is returned via
1581  \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
1582  including the terminating zero, or one of  including the terminating zero, or one of these error codes:
1583  .sp  .sp
1584    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1585  .sp  .sp
# Line 1398  and builds a list of pointers to them. A Line 1595  and builds a list of pointers to them. A
1595  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
1596  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
1597  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
1598  function is zero if all went well, or  function is zero if all went well, or the error code
1599  .sp  .sp
1600    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1601  .sp  .sp
# Line 1417  a previous call of \fBpcre_get_substring Line 1614  a previous call of \fBpcre_get_substring
1614  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
1615  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
1616  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
1617  linked via a special interface to another programming language which cannot use  linked via a special interface to another programming language that cannot use
1618  \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
1619  provided.  provided.
1620  .  .
# Line 1429  provided. Line 1626  provided.
1626  .ti +5n  .ti +5n
1627  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1628  .PP  .PP
 .br  
1629  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1630  .ti +5n  .ti +5n
1631  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1438  provided. Line 1634  provided.
1634  .ti +5n  .ti +5n
1635  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1636  .PP  .PP
 .br  
1637  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1638  .ti +5n  .ti +5n
1639  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1450  provided. Line 1645  provided.
1645  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.
1646  For example, for this pattern  For example, for this pattern
1647  .sp  .sp
1648    (a+)b(?P<xxx>\ed+)...    (a+)b(?<xxx>\ed+)...
1649  .sp  .sp
1650  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
1651  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
1652  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
1653    pattern, and the second is the name. The yield of the function is the
1654  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
1655  that name.  that name.
1656  .P  .P
# Line 1462  Given the number, you can extract the su Line 1658  Given the number, you can extract the su
1658  functions described in the previous section. For convenience, there are also  functions described in the previous section. For convenience, there are also
1659  two functions that do the whole job.  two functions that do the whole job.
1660  .P  .P
1661  Most of the arguments of \fIpcre_copy_named_substring()\fP and  Most of the arguments of \fBpcre_copy_named_substring()\fP and
1662  \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
1663  functions that extract by number. As these are described in the previous  functions that extract by number. As these are described in the previous
1664  section, they are not re-described here. There are just two differences:  section, they are not re-described here. There are just two differences:
1665  .P  .P
# Line 1473  pattern. This is needed in order to gain Line 1669  pattern. This is needed in order to gain
1669  translation table.  translation table.
1670  .P  .P
1671  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1672  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1673  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1674    the behaviour may not be what you want (see the next section).
1675    .
1676    .
1677    .SH "DUPLICATE SUBPATTERN NAMES"
1678    .rs
1679    .sp
1680    .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
1681    .ti +5n
1682    .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
1683    .PP
1684    When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
1685    are not required to be unique. Normally, patterns with duplicate names are such
1686    that in any one match, only one of the named subpatterns participates. An
1687    example is shown in the
1688    .\" HREF
1689    \fBpcrepattern\fP
1690    .\"
1691    documentation.
1692    .P
1693    When duplicates are present, \fBpcre_copy_named_substring()\fP and
1694    \fBpcre_get_named_substring()\fP return the first substring corresponding to
1695    the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
1696    returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1697    returns one of the numbers that are associated with the name, but it is not
1698    defined which it is.
1699    .P
1700    If you want to get full details of all captured substrings for a given name,
1701    you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1702    argument is the compiled pattern, and the second is the name. The third and
1703    fourth are pointers to variables which are updated by the function. After it
1704    has run, they point to the first and last entries in the name-to-number table
1705    for the given name. The function itself returns the length of each entry, or
1706    PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1707    described above in the section entitled \fIInformation about a pattern\fP.
1708    Given all the relevant entries for the name, you can extract each of their
1709    numbers, and hence the captured data, if any.
1710  .  .
1711  .  .
1712  .SH "FINDING ALL POSSIBLE MATCHES"  .SH "FINDING ALL POSSIBLE MATCHES"
# Line 1512  will yield PCRE_ERROR_NOMATCH. Line 1744  will yield PCRE_ERROR_NOMATCH.
1744  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
1745  .P  .P
1746  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
1747  a compiled pattern, using a "DFA" matching algorithm. This has different  a compiled pattern, using a matching algorithm that scans the subject string
1748  characteristics to the normal algorithm, and is not compatible with Perl. Some  just once, and does not backtrack. This has different characteristics to the
1749  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
1750  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
1751  matching algorithms, see the  matching can be useful. For a discussion of the two matching algorithms, see
1752    the
1753  .\" HREF  .\" HREF
1754  \fBpcrematching\fP  \fBpcrematching\fP
1755  .\"  .\"
# Line 1531  here. Line 1764  here.
1764  The two additional arguments provide workspace for the function. The workspace  The two additional arguments provide workspace for the function. The workspace
1765  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
1766  multiple paths through the pattern tree. More workspace will be needed for  multiple paths through the pattern tree. More workspace will be needed for
1767  patterns and subjects where there are a lot of possible matches.  patterns and subjects where there are a lot of potential matches.
1768  .P  .P
1769  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:
1770  .sp  .sp
# Line 1554  Here is an example of a simple call to \ Line 1787  Here is an example of a simple call to \
1787  .rs  .rs
1788  .sp  .sp
1789  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
1790  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,
1791  PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,
1792  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
1793  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.
1794  .sp  .sp
# Line 1572  matching string. Line 1805  matching string.
1805    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
1806  .sp  .sp
1807  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
1808  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
1809  this is necessarily the shortest possible match at the first possible matching  works, this is necessarily the shortest possible match at the first possible
1810  point in the subject string.  matching point in the subject string.
1811  .sp  .sp
1812    PCRE_DFA_RESTART    PCRE_DFA_RESTART
1813  .sp  .sp
# Line 1613  the three matched strings are Line 1846  the three matched strings are
1846  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
1847  the number of matched substrings. The substrings themselves are returned in  the number of matched substrings. The substrings themselves are returned in
1848  \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
1849  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
1850  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,
1851  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
1852  data, even though the meaning of the strings is different.)  returns data, even though the meaning of the strings is different.)
1853  .P  .P
1854  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
1855  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 1876  that it does not support, for instance,
1876  .sp  .sp
1877    PCRE_ERROR_DFA_UCOND      (-17)    PCRE_ERROR_DFA_UCOND      (-17)
1878  .sp  .sp
1879  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
1880  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
1881    group. These are not supported.
1882  .sp  .sp
1883    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
1884  .sp  .sp
# Line 1663  When a recursive subpattern is processed Line 1897  When a recursive subpattern is processed
1897  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1898  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
1899  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
1900  .P  .
1901  .in 0  .
1902  Last updated: 18 January 2006  .SH "SEE ALSO"
1903  .br  .rs
1904  Copyright (c) 1997-2006 University of Cambridge.  .sp
1905    \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1906    \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1907    \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1908    .
1909    .
1910    .SH AUTHOR
1911    .rs
1912    .sp
1913    .nf
1914    Philip Hazel
1915    University Computing Service
1916    Cambridge CB2 3QH, England.
1917    .fi
1918    .
1919    .
1920    .SH REVISION
1921    .rs
1922    .sp
1923    .nf
1924    Last updated: 21 August 2007
1925    Copyright (c) 1997-2007 University of Cambridge.
1926    .fi

Legend:
Removed from v.87  
changed lines
  Added in v.227

  ViewVC Help
Powered by ViewVC 1.1.5