/[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 93 by nigel, Sat Feb 24 21:41:42 2007 UTC revision 203 by ph10, Fri Aug 3 10:09:57 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  .  .
# Line 246  documentation. Line 221  documentation.
221  .SH NEWLINES  .SH NEWLINES
222  .rs  .rs
223  .sp  .sp
224  PCRE supports four different conventions for indicating line breaks in  PCRE supports five different conventions for indicating line breaks in
225  strings: a single CR (carriage return) character, a single LF (linefeed)  strings: a single CR (carriage return) character, a single LF (linefeed)
226  character, the two-character sequence CRLF, or any Unicode newline sequence.  character, the two-character sequence CRLF, any of the three preceding, or any
227  The Unicode newline sequences are the three just mentioned, plus the single  Unicode newline sequence. The Unicode newline sequences are the three just
228  characters VT (vertical tab, U+000B), FF (formfeed, U+000C), NEL (next line,  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
229  U+0085), LS (line separator, U+2028), and PS (paragraph separator, U+2029).  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
230    (paragraph separator, U+2029).
231  .P  .P
232  Each of the first three conventions is used by at least one operating system as  Each of the first three conventions is used by at least one operating system as
233  its standard newline sequence. When PCRE is built, a default can be specified.  its standard newline sequence. When PCRE is built, a default can be specified.
# Line 289  which it was compiled. Details are given Line 265  which it was compiled. Details are given
265  .\" HREF  .\" HREF
266  \fBpcreprecompile\fP  \fBpcreprecompile\fP
267  .\"  .\"
268  documentation.  documentation. However, compiling a regular expression with one version of PCRE
269    for use with a different version is not guaranteed to work and may cause
270    crashes.
271  .  .
272  .  .
273  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 322  properties is available; otherwise it is Line 300  properties is available; otherwise it is
300  .sp  .sp
301  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
302  that is recognized as meaning "newline". The four values that are supported  that is recognized as meaning "newline". The four values that are supported
303  are: 10 for LF, 13 for CR, 3338 for CRLF, and -1 for ANY. The default should  are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY. The
304  normally be the standard sequence for your operating system.  default should normally be the standard sequence for your operating system.
305  .sp  .sp
306    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
307  .sp  .sp
# Line 557  occurrences of ^ or $ in a pattern, sett Line 535  occurrences of ^ or $ in a pattern, sett
535    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
536    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
537    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
538      PCRE_NEWLINE_ANYCRLF
539    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
540  .sp  .sp
541  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
542  was built. Setting the first or the second specifies that a newline is  was built. Setting the first or the second specifies that a newline is
543  indicated by a single character (CR or LF, respectively). Setting  indicated by a single character (CR or LF, respectively). Setting
544  PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character  PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
545  CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
546  sequence should be recognized. The Unicode newline sequences are the three just  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
547  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,  that any Unicode newline sequence should be recognized. The Unicode newline
548  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS  sequences are the three just mentioned, plus the single characters VT (vertical
549  (paragraph separator, U+2029). The last two are recognized only in UTF-8 mode.  tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
550    separator, U+2028), and PS (paragraph separator, U+2029). The last two are
551    recognized only in UTF-8 mode.
552  .P  .P
553  The newline setting in the options word uses three bits that are treated  The newline setting in the options word uses three bits that are treated
554  as a number, giving eight possibilities. Currently only five are used (default  as a number, giving eight possibilities. Currently only six are used (default
555  plus the four values above). This means that if you set more than one newline  plus the five values above). This means that if you set more than one newline
556  option, the combination may or may not be sensible. For example,  option, the combination may or may not be sensible. For example,
557  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
558  other combinations yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
559  .P  .P
560  The only time that a line break is specially recognized when compiling a  The only time that a line break is specially recognized when compiling a
561  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
# Line 667  out of use. To avoid confusion, they hav Line 648  out of use. To avoid confusion, they hav
648    26  malformed number or name after (?(    26  malformed number or name after (?(
649    27  conditional group contains more than two branches    27  conditional group contains more than two branches
650    28  assertion expected after (?(    28  assertion expected after (?(
651    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
652    30  unknown POSIX class name    30  unknown POSIX class name
653    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
654    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is not compiled with PCRE_UTF8 support
# Line 688  out of use. To avoid confusion, they hav Line 669  out of use. To avoid confusion, they hav
669    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
670    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
671    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10,000)
672    50  repeated subpattern is too long    50  [this code is not in use]
673    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 (not in UTF-8 mode)
674    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
675    53  internal error: previously-checked referenced subpattern not found    53  internal error: previously-checked referenced subpattern not found
676    54  DEFINE group contains more than one branch    54  DEFINE group contains more than one branch
677    55  repeating a DEFINE group is not allowed    55  repeating a DEFINE group is not allowed
678    56  inconsistent NEWLINE options"    56  inconsistent NEWLINE options"
679      57  \eg is not followed by a braced name or an optionally braced
680            non-zero number
681      58  (?+ or (?- or (?(+ or (?(- must be followed by a non-zero number
682  .  .
683  .  .
684  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
# Line 754  bytes is created. Line 738  bytes is created.
738  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
739  .rs  .rs
740  .sp  .sp
741  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
742  digits, or whatever, by reference to a set of tables, indexed by character  digits, or whatever, by reference to a set of tables, indexed by character
743  value. When running in UTF-8 mode, this applies only to characters with codes  value. When running in UTF-8 mode, this applies only to characters with codes
744  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but
745  can be tested with \ep if PCRE is built with Unicode character property  can be tested with \ep if PCRE is built with Unicode character property
746  support. The use of locales with Unicode is discouraged.  support. The use of locales with Unicode is discouraged. If you are handling
747  .P  characters with codes greater than 128, you should either use UTF-8 and
748  An internal set of tables is created in the default C locale when PCRE is  Unicode, or use locales, but not try to mix the two.
749  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
750  and is sufficient for many applications. An alternative set of tables can,  PCRE contains an internal set of tables that are used when the final argument
751  however, be supplied. These may be created in a different locale from the  of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
752  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
753  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
754    default "C" locale of the local system, which may cause them to be different.
755    .P
756    The internal tables can always be overridden by tables supplied by the
757    application that calls PCRE. These may be created in a different locale from
758    the default. As more and more applications change to using Unicode, the need
759    for this locale support is expected to die away.
760  .P  .P
761  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
762  which has no arguments, in the relevant locale. The result can then be passed  which has no arguments, in the relevant locale. The result can then be passed
# Line 779  the following code could be used: Line 769  the following code could be used:
769    tables = pcre_maketables();    tables = pcre_maketables();
770    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
771  .sp  .sp
772    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
773    are using Windows, the name for the French locale is "french".
774    .P
775  When \fBpcre_maketables()\fP runs, the tables are built in memory that is  When \fBpcre_maketables()\fP runs, the tables are built in memory that is
776  obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure  obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure
777  that the memory containing the tables remains available for as long as it is  that the memory containing the tables remains available for as long as it is
# Line 881  table indicating a fixed set of bytes fo Line 874  table indicating a fixed set of bytes fo
874  string, a pointer to the table is returned. Otherwise NULL is returned. The  string, a pointer to the table is returned. Otherwise NULL is returned. The
875  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
876  .sp  .sp
877      PCRE_INFO_JCHANGED
878    .sp
879    Return 1 if the (?J) option setting is used in the pattern, otherwise 0. The
880    fourth argument should point to an \fBint\fP variable. The (?J) internal option
881    setting changes the local PCRE_DUPNAMES option.
882    .sp
883    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
884  .sp  .sp
885  Return the value of the rightmost literal byte that must exist in any matched  Return the value of the rightmost literal byte that must exist in any matched
# Line 933  When writing code to extract data from n Line 932  When writing code to extract data from n
932  name-to-number map, remember that the length of the entries is likely to be  name-to-number map, remember that the length of the entries is likely to be
933  different for each compiled pattern.  different for each compiled pattern.
934  .sp  .sp
935      PCRE_INFO_OKPARTIAL
936    .sp
937    Return 1 if the pattern can be used for partial matching, otherwise 0. The
938    fourth argument should point to an \fBint\fP variable. The
939    .\" HREF
940    \fBpcrepartial\fP
941    .\"
942    documentation lists the restrictions that apply to patterns when partial
943    matching is used.
944    .sp
945    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
946  .sp  .sp
947  Return a copy of the options with which the pattern was compiled. The fourth  Return a copy of the options with which the pattern was compiled. The fourth
948  argument should point to an \fBunsigned long int\fP variable. These option bits  argument should point to an \fBunsigned long int\fP variable. These option bits
949  are those specified in the call to \fBpcre_compile()\fP, modified by any  are those specified in the call to \fBpcre_compile()\fP, modified by any
950  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
951    they are the options that will be in force when matching starts. For example,
952    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
953    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
954  .P  .P
955  A pattern is automatically anchored by PCRE if all of its top-level  A pattern is automatically anchored by PCRE if all of its top-level
956  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 1166  matching time. Line 1178  matching time.
1178    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1179    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1180    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1181      PCRE_NEWLINE_ANYCRLF
1182    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
1183  .sp  .sp
1184  These options override the newline definition that was chosen or defaulted when  These options override the newline definition that was chosen or defaulted when
# Line 1173  the pattern was compiled. For details, s Line 1186  the pattern was compiled. For details, s
1186  \fBpcre_compile()\fP above. During matching, the newline choice affects the  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1187  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1188  the way the match position is advanced after a match failure for an unanchored  the way the match position is advanced after a match failure for an unanchored
1189  pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt  pattern. When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is
1190  fails when the current position is at a CRLF sequence, the match position is  set, and a match attempt fails when the current position is at a CRLF sequence,
1191  advanced by two characters instead of one, in other words, to after the CRLF.  the match position is advanced by two characters instead of one, in other
1192    words, to after the CRLF.
1193  .sp  .sp
1194    PCRE_NOTBOL    PCRE_NOTBOL
1195  .sp  .sp
# Line 1452  The internal recursion limit, as specifi Line 1466  The internal recursion limit, as specifi
1466  field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the  field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1467  description above.  description above.
1468  .sp  .sp
   PCRE_ERROR_NULLWSLIMIT    (-22)  
 .sp  
 When a group that can match an empty substring is repeated with an unbounded  
 upper limit, the subject position at the start of the group must be remembered,  
 so that a test for an empty string can be made when the end of the group is  
 reached. Some workspace is required for this; if it runs out, this error is  
 given.  
 .sp  
1469    PCRE_ERROR_BADNEWLINE     (-23)    PCRE_ERROR_BADNEWLINE     (-23)
1470  .sp  .sp
1471  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1472  .P  .P
1473  Error numbers -16 to -20 are not used by \fBpcre_exec()\fP.  Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
1474  .  .
1475  .  .
1476  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1476  Error numbers -16 to -20 are not used by Line 1482  Error numbers -16 to -20 are not used by
1482  .ti +5n  .ti +5n
1483  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1484  .PP  .PP
 .br  
1485  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1486  .ti +5n  .ti +5n
1487  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1488  .ti +5n  .ti +5n
1489  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1490  .PP  .PP
 .br  
1491  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1492  .ti +5n  .ti +5n
1493  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
# Line 1569  provided. Line 1573  provided.
1573  .ti +5n  .ti +5n
1574  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1575  .PP  .PP
 .br  
1576  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1577  .ti +5n  .ti +5n
1578  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1578  provided. Line 1581  provided.
1581  .ti +5n  .ti +5n
1582  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1583  .PP  .PP
 .br  
1584  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1585  .ti +5n  .ti +5n
1586  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1614  pattern. This is needed in order to gain Line 1616  pattern. This is needed in order to gain
1616  translation table.  translation table.
1617  .P  .P
1618  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1619  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1620  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1621    the behaviour may not be what you want (see the next section).
1622  .  .
1623  .  .
1624  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
# Line 1632  example is shown in the Line 1635  example is shown in the
1635  .\" HREF  .\" HREF
1636  \fBpcrepattern\fP  \fBpcrepattern\fP
1637  .\"  .\"
1638  documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP  documentation.
1639  and \fBpcre_get_named_substring()\fP return the first substring corresponding  .P
1640  to the given name that is set. If none are set, an empty string is returned.  When duplicates are present, \fBpcre_copy_named_substring()\fP and
1641  The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are  \fBpcre_get_named_substring()\fP return the first substring corresponding to
1642  associated with the name, but it is not defined which it is.  the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
1643  .sp  returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
1644    returns one of the numbers that are associated with the name, but it is not
1645    defined which it is.
1646    .P
1647  If you want to get full details of all captured substrings for a given name,  If you want to get full details of all captured substrings for a given name,
1648  you must use the \fBpcre_get_stringtable_entries()\fP function. The first  you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1649  argument is the compiled pattern, and the second is the name. The third and  argument is the compiled pattern, and the second is the name. The third and
# Line 1846  extremely rare, as a vector of size 1000 Line 1852  extremely rare, as a vector of size 1000
1852  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1853  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1854  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1855  .P  .
1856  .in 0  .
1857  Last updated: 30 November 2006  .SH AUTHOR
1858  .br  .rs
1859  Copyright (c) 1997-2006 University of Cambridge.  .sp
1860    .nf
1861    Philip Hazel
1862    University Computing Service
1863    Cambridge CB2 3QH, England.
1864    .fi
1865    .
1866    .
1867    .SH REVISION
1868    .rs
1869    .sp
1870    .nf
1871    Last updated: 30 July 2007
1872    Copyright (c) 1997-2007 University of Cambridge.
1873    .fi

Legend:
Removed from v.93  
changed lines
  Added in v.203

  ViewVC Help
Powered by ViewVC 1.1.5