/[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 91 by nigel, Sat Feb 24 21:41:34 2007 UTC revision 99 by ph10, Tue Mar 6 12:27:42 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
 .br  
68  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
69  .ti +5n  .ti +5n
70  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
71  .PP  .PP
 .br  
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 170  documentation describes how to run it. Line 145  documentation describes how to run it.
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. The alternative algorithm finds all possible matches (at a given  matching. The alternative algorithm finds all possible matches (at a given
148  point in the subject). 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 244  documentation. Line 219  documentation.
219  .  .
220  .  .
221  .SH NEWLINES  .SH NEWLINES
222  PCRE supports three different conventions for indicating line breaks in  .rs
 strings: a single CR character, a single LF character, or the two-character  
 sequence CRLF. All three are used as "standard" by different operating systems.  
 When PCRE is built, a default can be specified. The default default is LF,  
 which is the Unix standard. When PCRE is run, the default can be overridden,  
 either when a pattern is compiled, or when it is matched.  
223  .sp  .sp
224    PCRE supports four 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, or any Unicode newline sequence.
227    The Unicode newline sequences are the three just mentioned, plus the single
228    characters VT (vertical tab, U+000B), FF (formfeed, U+000C), NEL (next line,
229    U+0085), LS (line separator, U+2028), and PS (paragraph separator, U+2029).
230    .P
231    Each of the first three conventions is used by at least one operating system as
232    its standard newline sequence. When PCRE is built, a default can be specified.
233    The default default is LF, which is the Unix standard. When PCRE is run, the
234    default can be overridden, either when a pattern is compiled, or when it is
235    matched.
236    .P
237  In the PCRE documentation the word "newline" is used to mean "the character or  In the PCRE documentation the word "newline" is used to mean "the character or
238  pair of characters that indicate a line break".  pair of characters that indicate a line break". The choice of newline
239    convention affects the handling of the dot, circumflex, and dollar
240    metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
241    recognized line ending sequence, the match position advancement for a
242    non-anchored pattern. The choice of newline convention does not affect the
243    interpretation of the \en or \er escape sequences.
244  .  .
245  .  .
246  .SH MULTITHREADING  .SH MULTITHREADING
# Line 308  properties is available; otherwise it is Line 296  properties is available; otherwise it is
296    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
297  .sp  .sp
298  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
299  that is recognized as meaning "newline". The three values that are supported  that is recognized as meaning "newline". The four values that are supported
300  are: 10 for LF, 13 for CR, and 3338 for CRLF. The default should normally be  are: 10 for LF, 13 for CR, 3338 for CRLF, and -1 for ANY. The default should
301  the standard sequence for your operating system.  normally be the standard sequence for your operating system.
302  .sp  .sp
303    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
304  .sp  .sp
# Line 387  depend on memory location, the complete Line 375  depend on memory location, the complete
375  fully relocatable, because it may contain a copy of the \fItableptr\fP  fully relocatable, because it may contain a copy of the \fItableptr\fP
376  argument, which is an address (see below).  argument, which is an address (see below).
377  .P  .P
378  The \fIoptions\fP argument contains independent bits that affect the  The \fIoptions\fP argument contains various bit settings that affect the
379  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
380  options are described below. Some of them, in particular, those that are  options are described below. Some of them, in particular, those that are
381  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 480  If this bit is set, a dot metacharater i Line 468  If this bit is set, a dot metacharater i
468  including those that indicate newline. Without it, a dot does not match when  including those that indicate newline. Without it, a dot does not match when
469  the current position is at a newline. This option is equivalent to Perl's /s  the current position is at a newline. This option is equivalent to Perl's /s
470  option, and it can be changed within a pattern by a (?s) option setting. A  option, and it can be changed within a pattern by a (?s) option setting. A
471  negative class such as [^a] always matches newlines, independent of the setting  negative class such as [^a] always matches newline characters, independent of
472  of this option.  the setting of this option.
473  .sp  .sp
474    PCRE_DUPNAMES    PCRE_DUPNAMES
475  .sp  .sp
# Line 544  occurrences of ^ or $ in a pattern, sett Line 532  occurrences of ^ or $ in a pattern, sett
532    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
533    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
534    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
535      PCRE_NEWLINE_ANY
536  .sp  .sp
537  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
538  was built. Setting the first or the second specifies that a newline is  was built. Setting the first or the second specifies that a newline is
539  indicated by a single character (CR or LF, respectively). Setting both of them  indicated by a single character (CR or LF, respectively). Setting
540  specifies that a newline is indicated by the two-character CRLF sequence. For  PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
541  convenience, PCRE_NEWLINE_CRLF is defined to contain both bits. The only time  CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline
542  that a line break is relevant when compiling a pattern is if PCRE_EXTENDED is  sequence should be recognized. The Unicode newline sequences are the three just
543  set, and an unescaped # outside a character class is encountered. This  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
544  indicates a comment that lasts until after the next newline.  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
545    (paragraph separator, U+2029). The last two are recognized only in UTF-8 mode.
546    .P
547    The newline setting in the options word uses three bits that are treated
548    as a number, giving eight possibilities. Currently only five are used (default
549    plus the four values above). This means that if you set more than one newline
550    option, the combination may or may not be sensible. For example,
551    PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
552    other combinations yield unused numbers and cause an error.
553    .P
554    The only time that a line break is specially recognized when compiling a
555    pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
556    class is encountered. This indicates a comment that lasts until after the next
557    line break sequence. In other circumstances, line break sequences are treated
558    as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
559    as whitespace characters and are therefore ignored.
560  .P  .P
561  The newline option set at compile time becomes the default that is used for  The newline option that is set at compile time becomes the default that is used
562  \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.  for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
563  .sp  .sp
564    PCRE_NO_AUTO_CAPTURE    PCRE_NO_AUTO_CAPTURE
565  .sp  .sp
# Line 606  strings. Line 610  strings.
610  .sp  .sp
611  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
612  \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
613  both compiling functions.  both compiling functions. As PCRE has developed, some error codes have fallen
614    out of use. To avoid confusion, they have not been re-used.
615  .sp  .sp
616     0  no error     0  no error
617     1  \e at end of pattern     1  \e at end of pattern
# Line 618  both compiling functions. Line 623  both compiling functions.
623     7  invalid escape sequence in character class     7  invalid escape sequence in character class
624     8  range out of order in character class     8  range out of order in character class
625     9  nothing to repeat     9  nothing to repeat
626    10  operand of unlimited repeat could match the empty string    10  [this code is not in use]
627    11  internal error: unexpected repeat    11  internal error: unexpected repeat
628    12  unrecognized character after (?    12  unrecognized character after (?
629    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
# Line 627  both compiling functions. Line 632  both compiling functions.
632    16  erroffset passed as NULL    16  erroffset passed as NULL
633    17  unknown option bit(s) set    17  unknown option bit(s) set
634    18  missing ) after comment    18  missing ) after comment
635    19  parentheses nested too deeply    19  [this code is not in use]
636    20  regular expression too large    20  regular expression too large
637    21  failed to get memory    21  failed to get memory
638    22  unmatched parentheses    22  unmatched parentheses
# Line 641  both compiling functions. Line 646  both compiling functions.
646    30  unknown POSIX class name    30  unknown POSIX class name
647    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
648    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
649    33  spare error    33  [this code is not in use]
650    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
651    35  invalid condition (?(0)    35  invalid condition (?(0)
652    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
# Line 650  both compiling functions. Line 655  both compiling functions.
655    39  closing ) for (?C expected    39  closing ) for (?C expected
656    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
657    41  unrecognized character after (?P    41  unrecognized character after (?P
658    42  syntax error after (?P    42  syntax error in subpattern name (missing terminator)
659    43  two named subpatterns have the same name    43  two named subpatterns have the same name
660    44  invalid UTF-8 string    44  invalid UTF-8 string
661    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
# Line 660  both compiling functions. Line 665  both compiling functions.
665    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10,000)
666    50  repeated subpattern is too long    50  repeated subpattern is too long
667    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
668      52  internal error: overran compiling workspace
669      53  internal error: previously-checked referenced subpattern not found
670      54  DEFINE group contains more than one branch
671      55  repeating a DEFINE group is not allowed
672      56  inconsistent NEWLINE options"
673  .  .
674  .  .
675  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 827  variable. (This option used to be called Line 837  variable. (This option used to be called
837  still recognized for backwards compatibility.)  still recognized for backwards compatibility.)
838  .P  .P
839  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
840  (cat|cow|coyote). Otherwise, if either  (cat|cow|coyote), its value is returned. Otherwise, if either
841  .sp  .sp
842  (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
843  starts with "^", or  starts with "^", or
# Line 882  their parentheses numbers. For example, Line 892  their parentheses numbers. For example,
892  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  PCRE_EXTENDED is set, so white space - including newlines - is ignored):
893  .sp  .sp
894  .\" JOIN  .\" JOIN
895    (?P<date> (?P<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
896    (?P<month>\ed\ed) - (?P<day>\ed\ed) )    (?<month>\ed\ed) - (?<day>\ed\ed) )
897  .sp  .sp
898  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
899  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 1131  matching time. Line 1141  matching time.
1141    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1142    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1143    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1144      PCRE_NEWLINE_ANY
1145  .sp  .sp
1146  These options override the newline definition that was chosen or defaulted when  These options override the newline definition that was chosen or defaulted when
1147  the pattern was compiled. For details, see the description \fBpcre_compile()\fP  the pattern was compiled. For details, see the description of
1148  above. During matching, the newline choice affects the behaviour of the dot,  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1149  circumflex, and dollar metacharacters.  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1150    the way the match position is advanced after a match failure for an unanchored
1151    pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt
1152    fails when the current position is at a CRLF sequence, the match position is
1153    advanced by two characters instead of one, in other words, to after the CRLF.
1154  .sp  .sp
1155    PCRE_NOTBOL    PCRE_NOTBOL
1156  .sp  .sp
# Line 1336  compiled in an environment of one endian Line 1351  compiled in an environment of one endian
1351  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
1352  not present.  not present.
1353  .sp  .sp
1354    PCRE_ERROR_UNKNOWN_NODE   (-5)    PCRE_ERROR_UNKNOWN_OPCODE (-5)
1355  .sp  .sp
1356  While running the pattern match, an unknown item was encountered in the  While running the pattern match, an unknown item was encountered in the
1357  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 1362  The backtracking limit, as specified by Line 1377  The backtracking limit, as specified by
1377  \fBpcre_extra\fP structure (or defaulted) was reached. See the description  \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1378  above.  above.
1379  .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  
1380    PCRE_ERROR_CALLOUT        (-9)    PCRE_ERROR_CALLOUT        (-9)
1381  .sp  .sp
1382  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 1411  in PCRE or by overwriting of the compile Line 1420  in PCRE or by overwriting of the compile
1420    PCRE_ERROR_BADCOUNT       (-15)    PCRE_ERROR_BADCOUNT       (-15)
1421  .sp  .sp
1422  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.
1423    .sp
1424      PCRE_ERROR_RECURSIONLIMIT (-21)
1425    .sp
1426    The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1427    field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1428    description above.
1429    .sp
1430      PCRE_ERROR_NULLWSLIMIT    (-22)
1431    .sp
1432    When a group that can match an empty substring is repeated with an unbounded
1433    upper limit, the subject position at the start of the group must be remembered,
1434    so that a test for an empty string can be made when the end of the group is
1435    reached. Some workspace is required for this; if it runs out, this error is
1436    given.
1437    .sp
1438      PCRE_ERROR_BADNEWLINE     (-23)
1439    .sp
1440    An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1441    .P
1442    Error numbers -16 to -20 are not used by \fBpcre_exec()\fP.
1443  .  .
1444  .  .
1445  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1422  This error is given if the value of the Line 1451  This error is given if the value of the
1451  .ti +5n  .ti +5n
1452  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1453  .PP  .PP
 .br  
1454  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1455  .ti +5n  .ti +5n
1456  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1457  .ti +5n  .ti +5n
1458  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1459  .PP  .PP
 .br  
1460  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1461  .ti +5n  .ti +5n
1462  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
# Line 1468  the string is placed in \fIbuffer\fP, wh Line 1495  the string is placed in \fIbuffer\fP, wh
1495  \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
1496  obtained via \fBpcre_malloc\fP, and its address is returned via  obtained via \fBpcre_malloc\fP, and its address is returned via
1497  \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
1498  including the terminating zero, or one of  including the terminating zero, or one of these error codes:
1499  .sp  .sp
1500    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1501  .sp  .sp
# Line 1484  and builds a list of pointers to them. A Line 1511  and builds a list of pointers to them. A
1511  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
1512  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
1513  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
1514  function is zero if all went well, or  function is zero if all went well, or the error code
1515  .sp  .sp
1516    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1517  .sp  .sp
# Line 1515  provided. Line 1542  provided.
1542  .ti +5n  .ti +5n
1543  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1544  .PP  .PP
 .br  
1545  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1546  .ti +5n  .ti +5n
1547  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1524  provided. Line 1550  provided.
1550  .ti +5n  .ti +5n
1551  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1552  .PP  .PP
 .br  
1553  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1554  .ti +5n  .ti +5n
1555  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1536  provided. Line 1561  provided.
1561  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.
1562  For example, for this pattern  For example, for this pattern
1563  .sp  .sp
1564    (a+)b(?P<xxx>\ed+)...    (a+)b(?<xxx>\ed+)...
1565  .sp  .sp
1566  the number of the subpattern called "xxx" is 2. If the name is known to be  the number of the subpattern called "xxx" is 2. If the name is known to be
1567  unique (PCRE_DUPNAMES was not set), you can find the number from the name by  unique (PCRE_DUPNAMES was not set), you can find the number from the name by
# Line 1590  argument is the compiled pattern, and th Line 1615  argument is the compiled pattern, and th
1615  fourth are pointers to variables which are updated by the function. After it  fourth are pointers to variables which are updated by the function. After it
1616  has run, they point to the first and last entries in the name-to-number table  has run, they point to the first and last entries in the name-to-number table
1617  for the given name. The function itself returns the length of each entry, or  for the given name. The function itself returns the length of each entry, or
1618  PCRE_ERROR_NOSUBSTRING if there are none. The format of the table is described  PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1619  above in the section entitled \fIInformation about a pattern\fP. Given all the  described above in the section entitled \fIInformation about a pattern\fP.
1620  relevant entries for the name, you can extract each of their numbers, and hence  Given all the relevant entries for the name, you can extract each of their
1621  the captured data, if any.  numbers, and hence the captured data, if any.
1622  .  .
1623  .  .
1624  .SH "FINDING ALL POSSIBLE MATCHES"  .SH "FINDING ALL POSSIBLE MATCHES"
# Line 1631  will yield PCRE_ERROR_NOMATCH. Line 1656  will yield PCRE_ERROR_NOMATCH.
1656  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
1657  .P  .P
1658  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
1659  a compiled pattern, using a "DFA" matching algorithm. This has different  a compiled pattern, using a matching algorithm that scans the subject string
1660  characteristics to the normal algorithm, and is not compatible with Perl. Some  just once, and does not backtrack. This has different characteristics to the
1661  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
1662  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
1663  matching algorithms, see the  matching can be useful. For a discussion of the two matching algorithms, see
1664    the
1665  .\" HREF  .\" HREF
1666  \fBpcrematching\fP  \fBpcrematching\fP
1667  .\"  .\"
# Line 1691  matching string. Line 1717  matching string.
1717    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
1718  .sp  .sp
1719  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
1720  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
1721  this is necessarily the shortest possible match at the first possible matching  works, this is necessarily the shortest possible match at the first possible
1722  point in the subject string.  matching point in the subject string.
1723  .sp  .sp
1724    PCRE_DFA_RESTART    PCRE_DFA_RESTART
1725  .sp  .sp
# Line 1732  the three matched strings are Line 1758  the three matched strings are
1758  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
1759  the number of matched substrings. The substrings themselves are returned in  the number of matched substrings. The substrings themselves are returned in
1760  \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
1761  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
1762  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,
1763  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
1764  data, even though the meaning of the strings is different.)  returns data, even though the meaning of the strings is different.)
1765  .P  .P
1766  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
1767  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 1762  that it does not support, for instance, Line 1788  that it does not support, for instance,
1788  .sp  .sp
1789    PCRE_ERROR_DFA_UCOND      (-17)    PCRE_ERROR_DFA_UCOND      (-17)
1790  .sp  .sp
1791  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
1792  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
1793    group. These are not supported.
1794  .sp  .sp
1795    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
1796  .sp  .sp
# Line 1782  When a recursive subpattern is processed Line 1809  When a recursive subpattern is processed
1809  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1810  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
1811  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
1812  .P  .
1813  .in 0  .
1814  Last updated: 08 June 2006  .SH "SEE ALSO"
1815  .br  .rs
1816  Copyright (c) 1997-2006 University of Cambridge.  .sp
1817    \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1818    \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1819    \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1820    .
1821    .
1822    .SH AUTHOR
1823    .rs
1824    .sp
1825    .nf
1826    Philip Hazel
1827    University Computing Service
1828    Cambridge CB2 3QH, England.
1829    .fi
1830    .
1831    .
1832    .SH REVISION
1833    .rs
1834    .sp
1835    .nf
1836    Last updated: 06 March 2007
1837    Copyright (c) 1997-2007 University of Cambridge.
1838    .fi

Legend:
Removed from v.91  
changed lines
  Added in v.99

  ViewVC Help
Powered by ViewVC 1.1.5