/[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 75 by nigel, Sat Feb 24 21:40:37 2007 UTC revision 142 by ph10, Fri Mar 30 15:55:18 2007 UTC
# Line 1  Line 1 
1  .TH PCRE 3  .TH PCREAPI 3
2  .SH NAME  .SH NAME
3  PCRE - Perl-compatible regular expressions  PCRE - Perl-compatible regular expressions
4  .SH "PCRE NATIVE API"  .SH "PCRE NATIVE API"
# 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
16  .br  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
17    .ti +5n
18    .B int *\fIerrorcodeptr\fP,
19    .ti +5n
20    .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
21    .ti +5n
22    .B const unsigned char *\fItableptr\fP);
23    .PP
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
34  .br  .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
35    .ti +5n
36    .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
37    .ti +5n
38    .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
39    .ti +5n
40    .B int *\fIworkspace\fP, int \fIwscount\fP);
41    .PP
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 35  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 51  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
95  .br  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
96    .PP
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 also  PCRE has its own native API, which is described in this document. There are
116  a set of wrapper functions that correspond to the POSIX regular expression API.  also some wrapper functions that correspond to the POSIX regular expression
117  These are described in the  API. These are described in the
118  .\" HREF  .\" HREF
119  \fBpcreposix\fP  \fBpcreposix\fP
120  .\"  .\"
121  documentation.  documentation. Both of these APIs define a set of C function calls. A C++
122    wrapper is distributed with PCRE. It is documented in the
123    .\" HREF
124    \fBpcrecpp\fP
125    .\"
126    page.
127  .P  .P
128  The native API function prototypes are defined in the header file \fBpcre.h\fP,  The native API C function prototypes are defined in the header file
129  and on Unix systems the library itself is called \fBlibpcre\fP. It can  \fBpcre.h\fP, and on Unix systems the library itself is called \fBlibpcre\fP.
130  normally be accessed by adding \fB-lpcre\fP to the command for linking an  It can normally be accessed by adding \fB-lpcre\fP to the command for linking
131  application that uses PCRE. The header file defines the macros PCRE_MAJOR and  an application that uses PCRE. The header file defines the macros PCRE_MAJOR
132  PCRE_MINOR to contain the major and minor release numbers for the library.  and PCRE_MINOR to contain the major and minor release numbers for the library.
133  Applications can use these to include support for different releases of PCRE.  Applications can use these to include support for different releases of PCRE.
134  .P  .P
135  The functions \fBpcre_compile()\fP, \fBpcre_study()\fP, and \fBpcre_exec()\fP  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,
136  are used for compiling and matching regular expressions. A sample program that  and \fBpcre_exec()\fP are used for compiling and matching regular expressions
137  demonstrates the simplest way of using them is provided in the file called  in a Perl-compatible manner. A sample program that demonstrates the simplest
138  \fIpcredemo.c\fP in the source distribution. The  way of using them is provided in the file called \fIpcredemo.c\fP in the source
139    distribution. The
140  .\" HREF  .\" HREF
141  \fBpcresample\fP  \fBpcresample\fP
142  .\"  .\"
143  documentation describes how to run it.  documentation describes how to run it.
144  .P  .P
145    A second matching function, \fBpcre_dfa_exec()\fP, which is not
146    Perl-compatible, is also provided. This uses a different algorithm for the
147    matching. The alternative algorithm finds all possible matches (at a given
148    point in the subject), and scans the subject just once. However, this algorithm
149    does not return captured substrings. A description of the two matching
150    algorithms and their advantages and disadvantages is given in the
151    .\" HREF
152    \fBpcrematching\fP
153    .\"
154    documentation.
155    .P
156  In addition to the main compiling and matching functions, there are convenience  In addition to the main compiling and matching functions, there are convenience
157  functions for extracting captured substrings from a matched subject string.  functions for extracting captured substrings from a subject string that is
158  They are:  matched by \fBpcre_exec()\fP. They are:
159  .sp  .sp
160    \fBpcre_copy_substring()\fP    \fBpcre_copy_substring()\fP
161    \fBpcre_copy_named_substring()\fP    \fBpcre_copy_named_substring()\fP
# Line 145  They are: Line 163  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.
170  .P  .P
171  The function \fBpcre_maketables()\fP is used to build a set of character tables  The function \fBpcre_maketables()\fP is used to build a set of character tables
172  in the current locale for passing to \fBpcre_compile()\fP or \fBpcre_exec()\fP.  in the current locale for passing to \fBpcre_compile()\fP, \fBpcre_exec()\fP,
173  This is an optional facility that is provided for specialist use. Most  or \fBpcre_dfa_exec()\fP. This is an optional facility that is provided for
174  commonly, no special tables are passed, in which case internal tables that are  specialist use. Most commonly, no special tables are passed, in which case
175  generated when PCRE is built are used.  internal tables that are generated when PCRE is built are used.
176  .P  .P
177  The function \fBpcre_fullinfo()\fP is used to find out information about a  The function \fBpcre_fullinfo()\fP is used to find out information about a
178  compiled pattern; \fBpcre_info()\fP is an obsolete version that returns only  compiled pattern; \fBpcre_info()\fP is an obsolete version that returns only
# Line 161  some of the available information, but i Line 180  some of the available information, but i
180  The function \fBpcre_version()\fP returns a pointer to a string containing the  The function \fBpcre_version()\fP returns a pointer to a string containing the
181  version of PCRE and its date of release.  version of PCRE and its date of release.
182  .P  .P
183    The function \fBpcre_refcount()\fP maintains a reference count in a data block
184    containing a compiled pattern. This is provided for the benefit of
185    object-oriented applications.
186    .P
187  The global variables \fBpcre_malloc\fP and \fBpcre_free\fP initially contain  The global variables \fBpcre_malloc\fP and \fBpcre_free\fP initially contain
188  the entry points of the standard \fBmalloc()\fP and \fBfree()\fP functions,  the entry points of the standard \fBmalloc()\fP and \fBfree()\fP functions,
189  respectively. PCRE calls the memory management functions via these variables,  respectively. PCRE calls the memory management functions via these variables,
# Line 170  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. This is a non-standard way of building PCRE, for use  recursive function calls, when running the \fBpcre_exec()\fP function. See the
197  in environments that have limited stacks. Because of the greater use of memory  .\" HREF
198  management, it runs more slowly. Separate functions are provided so that  \fBpcrebuild\fP
199  special-purpose external code can be used for this case. When used, these  .\"
200  functions are always called in a stack-like manner (last obtained, first  documentation for details of how to do this. It is a non-standard way of
201  freed), and always for memory blocks of the same size.  building PCRE, for use in environments that have limited stacks. Because of the
202    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 186  points during a matching operation. Deta Line 218  points during a matching operation. Deta
218  documentation.  documentation.
219  .  .
220  .  .
221    .SH NEWLINES
222    .rs
223    .sp
224    PCRE supports 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
238    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
247  .rs  .rs
248  .sp  .sp
# Line 238  properties is available; otherwise it is Line 295  properties is available; otherwise it is
295  .sp  .sp
296    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
297  .sp  .sp
298  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
299  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
300  should normally be the standard character for your operating system.  are: 10 for LF, 13 for CR, 3338 for CRLF, and -1 for ANY. The default should
301    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 266  The output is an integer that gives the Line 324  The output is an integer that gives the
324  internal matching function calls in a \fBpcre_exec()\fP execution. Further  internal matching function calls in a \fBpcre_exec()\fP execution. Further
325  details are given with \fBpcre_exec()\fP below.  details are given with \fBpcre_exec()\fP below.
326  .sp  .sp
327      PCRE_CONFIG_MATCH_LIMIT_RECURSION
328    .sp
329    The output is an integer that gives the default limit for the depth of
330    recursion when calling the internal matching function in a \fBpcre_exec()\fP
331    execution. Further details are given with \fBpcre_exec()\fP below.
332    .sp
333    PCRE_CONFIG_STACKRECURSE    PCRE_CONFIG_STACKRECURSE
334  .sp  .sp
335  The output is an integer that is set to one if internal recursion is  The output is an integer that is set to one if internal recursion when running
336  implemented by recursive function calls that use the stack to remember their  \fBpcre_exec()\fP is implemented by recursive function calls that use the stack
337  state. This is the usual way that PCRE is compiled. The output is zero if PCRE  to remember their state. This is the usual way that PCRE is compiled. The
338  was compiled to use blocks of data on the heap instead of recursive function  output is zero if PCRE was compiled to use blocks of data on the heap instead
339  calls. In this case, \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are  of recursive function calls. In this case, \fBpcre_stack_malloc\fP and
340  called to manage memory blocks on the heap, thus avoiding the use of the stack.  \fBpcre_stack_free\fP are called to manage memory blocks on the heap, thus
341    avoiding the use of the stack.
342  .  .
343  .  .
344  .SH "COMPILING A PATTERN"  .SH "COMPILING A PATTERN"
# Line 284  called to manage memory blocks on the he Line 349  called to manage memory blocks on the he
349  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
350  .ti +5n  .ti +5n
351  .B const unsigned char *\fItableptr\fP);  .B const unsigned char *\fItableptr\fP);
352    .sp
353    .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
354    .ti +5n
355    .B int *\fIerrorcodeptr\fP,
356    .ti +5n
357    .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
358    .ti +5n
359    .B const unsigned char *\fItableptr\fP);
360  .P  .P
361  The function \fBpcre_compile()\fP is called to compile a pattern into an  Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be
362  internal form. The pattern is a C string terminated by a binary zero, and  called to compile a pattern into an internal form. The only difference between
363  is passed in the \fIpattern\fP argument. A pointer to a single block of memory  the two interfaces is that \fBpcre_compile2()\fP has an additional argument,
364  that is obtained via \fBpcre_malloc\fP is returned. This contains the compiled  \fIerrorcodeptr\fP, via which a numerical error code can be returned.
365  code and related data. The \fBpcre\fP type is defined for the returned block;  .P
366  this is a typedef for a structure whose contents are not externally defined. It  The pattern is a C string terminated by a binary zero, and is passed in the
367  is up to the caller to free the memory when it is no longer required.  \fIpattern\fP argument. A pointer to a single block of memory that is obtained
368    via \fBpcre_malloc\fP is returned. This contains the compiled code and related
369    data. The \fBpcre\fP type is defined for the returned block; this is a typedef
370    for a structure whose contents are not externally defined. It is up to the
371    caller to free the memory (via \fBpcre_free\fP) when it is no longer required.
372  .P  .P
373  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
374  depend on memory location, the complete \fBpcre\fP data block is not  depend on memory location, the complete \fBpcre\fP data block is not
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 308  the detailed description in the Line 385  the detailed description in the
385  .\"  .\"
386  documentation). For these options, the contents of the \fIoptions\fP argument  documentation). For these options, the contents of the \fIoptions\fP argument
387  specifies their initial settings at the start of compilation and execution. The  specifies their initial settings at the start of compilation and execution. The
388  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
389  time.  matching as well as at compile time.
390  .P  .P
391  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
392  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
393  NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual  NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual
394  error message. The offset from the start of the pattern to the character where  error message. This is a static string that is part of the library. You must
395  the error was discovered is placed in the variable pointed to by  not try to free it. The offset from the start of the pattern to the character
396    where the error was discovered is placed in the variable pointed to by
397  \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.  \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.
398  .P  .P
399    If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the
400    \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is
401    returned via this argument in the event of an error. This is in addition to the
402    textual error message. Error codes and messages are listed below.
403    .P
404  If the final argument, \fItableptr\fP, is NULL, PCRE uses a default set of  If the final argument, \fItableptr\fP, is NULL, PCRE uses a default set of
405  character tables that are built when PCRE is compiled, using the default C  character tables that are built when PCRE is compiled, using the default C
406  locale. Otherwise, \fItableptr\fP must be an address that is the result of a  locale. Otherwise, \fItableptr\fP must be an address that is the result of a
# Line 362  documentation. Line 445  documentation.
445  .sp  .sp
446  If this bit is set, letters in the pattern match both upper and lower case  If this bit is set, letters in the pattern match both upper and lower case
447  letters. It is equivalent to Perl's /i option, and it can be changed within a  letters. It is equivalent to Perl's /i option, and it can be changed within a
448  pattern by a (?i) option setting. When running in UTF-8 mode, case support for  pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the
449  high-valued characters is available only when PCRE is built with Unicode  concept of case for characters whose values are less than 128, so caseless
450  character property support.  matching is always possible. For characters with higher values, the concept of
451    case is supported if PCRE is compiled with Unicode property support, but not
452    otherwise. If you want to use caseless matching for characters 128 and above,
453    you must ensure that PCRE is compiled with Unicode property support as well as
454    with UTF-8 support.
455  .sp  .sp
456    PCRE_DOLLAR_ENDONLY    PCRE_DOLLAR_ENDONLY
457  .sp  .sp
458  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
459  end of the subject string. Without this option, a dollar also matches  end of the subject string. Without this option, a dollar also matches
460  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
461  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.
462  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
463  a pattern.  pattern.
464  .sp  .sp
465    PCRE_DOTALL    PCRE_DOTALL
466  .sp  .sp
467  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,
468  including newlines. Without it, newlines are excluded. This option is  including those that indicate newline. Without it, a dot does not match when
469  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
470  (?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
471  character, independent of the setting of this option.  negative class such as [^a] always matches newline characters, independent of
472    the setting of this option.
473    .sp
474      PCRE_DUPNAMES
475    .sp
476    If this bit is set, names used to identify capturing subpatterns need not be
477    unique. This can be helpful for certain types of pattern when it is known that
478    only one instance of the named subpattern can ever be matched. There are more
479    details of named subpatterns below; see also the
480    .\" HREF
481    \fBpcrepattern\fP
482    .\"
483    documentation.
484  .sp  .sp
485    PCRE_EXTENDED    PCRE_EXTENDED
486  .sp  .sp
487  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
488  ignored except when escaped or inside a character class. Whitespace does not  ignored except when escaped or inside a character class. Whitespace does not
489  include the VT character (code 11). In addition, characters between an  include the VT character (code 11). In addition, characters between an
490  unescaped # outside a character class and the next newline character,  unescaped # outside a character class and the next newline, inclusive, are also
491  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
492  be changed within a pattern by a (?x) option setting.  pattern by a (?x) option setting.
493  .P  .P
494  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
495  Note, however, that this applies only to data characters. Whitespace characters  Note, however, that this applies only to data characters. Whitespace characters
# Line 404  that is incompatible with Perl, but it i Line 503  that is incompatible with Perl, but it i
503  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
504  special meaning causes an error, thus reserving these combinations for future  special meaning causes an error, thus reserving these combinations for future
505  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
506  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
507  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
508  pattern.  this option. It can also be set by a (?X) option setting within a pattern.
509    .sp
510      PCRE_FIRSTLINE
511    .sp
512    If this option is set, an unanchored pattern is required to match before or at
513    the first newline in the subject string, though the matched text may continue
514    over the newline.
515  .sp  .sp
516    PCRE_MULTILINE    PCRE_MULTILINE
517  .sp  .sp
# Line 418  terminating newline (unless PCRE_DOLLAR_ Line 523  terminating newline (unless PCRE_DOLLAR_
523  Perl.  Perl.
524  .P  .P
525  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
526  match immediately following or immediately before any newline in the subject  match immediately following or immediately before internal newlines in the
527  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
528  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
529  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
530  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
531  .sp  .sp
532      PCRE_NEWLINE_CR
533      PCRE_NEWLINE_LF
534      PCRE_NEWLINE_CRLF
535      PCRE_NEWLINE_ANY
536    .sp
537    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
539    indicated by a single character (CR or LF, respectively). Setting
540    PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
541    CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline
542    sequence should be recognized. The Unicode newline sequences are the three just
543    mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
544    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
561    The newline option that is set at compile time becomes the default that is used
562    for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
563    .sp
564    PCRE_NO_AUTO_CAPTURE    PCRE_NO_AUTO_CAPTURE
565  .sp  .sp
566  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 463  automatically checked. If an invalid UTF Line 600  automatically checked. If an invalid UTF
600  valid, and you want to skip this check for performance reasons, you can set the  valid, and you want to skip this check for performance reasons, you can set the
601  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid
602  UTF-8 string as a pattern is undefined. It may cause your program to crash.  UTF-8 string as a pattern is undefined. It may cause your program to crash.
603  Note that this option can also be passed to \fBpcre_exec()\fP, to suppress the  Note that this option can also be passed to \fBpcre_exec()\fP and
604  UTF-8 validity checking of subject strings.  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject
605    strings.
606    .
607    .
608    .SH "COMPILATION ERROR CODES"
609    .rs
610    .sp
611    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
613    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
616       0  no error
617       1  \e at end of pattern
618       2  \ec at end of pattern
619       3  unrecognized character follows \e
620       4  numbers out of order in {} quantifier
621       5  number too big in {} quantifier
622       6  missing terminating ] for character class
623       7  invalid escape sequence in character class
624       8  range out of order in character class
625       9  nothing to repeat
626      10  [this code is not in use]
627      11  internal error: unexpected repeat
628      12  unrecognized character after (?
629      13  POSIX named classes are supported only within a class
630      14  missing )
631      15  reference to non-existent subpattern
632      16  erroffset passed as NULL
633      17  unknown option bit(s) set
634      18  missing ) after comment
635      19  [this code is not in use]
636      20  regular expression too large
637      21  failed to get memory
638      22  unmatched parentheses
639      23  internal error: code overflow
640      24  unrecognized character after (?<
641      25  lookbehind assertion is not fixed length
642      26  malformed number or name after (?(
643      27  conditional group contains more than two branches
644      28  assertion expected after (?(
645      29  (?R or (?digits must be followed by )
646      30  unknown POSIX class name
647      31  POSIX collating elements are not supported
648      32  this version of PCRE is not compiled with PCRE_UTF8 support
649      33  [this code is not in use]
650      34  character value in \ex{...} sequence is too large
651      35  invalid condition (?(0)
652      36  \eC not allowed in lookbehind assertion
653      37  PCRE does not support \eL, \el, \eN, \eU, or \eu
654      38  number after (?C is > 255
655      39  closing ) for (?C expected
656      40  recursive call could loop indefinitely
657      41  unrecognized character after (?P
658      42  syntax error in subpattern name (missing terminator)
659      43  two named subpatterns have the same name
660      44  invalid UTF-8 string
661      45  support for \eP, \ep, and \eX has not been compiled
662      46  malformed \eP or \ep sequence
663      47  unknown property name after \eP or \ep
664      48  subpattern name is too long (maximum 32 characters)
665      49  too many named subpatterns (maximum 10,000)
666      50  repeated subpattern is too long
667      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"
676  .rs  .rs
677  .sp  .sp
678  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP
679  .ti +5n  .ti +5n
680  .B const char **\fIerrptr\fP);  .B const char **\fIerrptr\fP);
681  .PP  .PP
# Line 492  below Line 697  below
697  .\"  .\"
698  in the section on matching a pattern.  in the section on matching a pattern.
699  .P  .P
700  If studying the pattern does not produce any additional information,  If studying the pattern does not produce any additional information
701  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program
702  wants to pass any of the other fields to \fBpcre_exec()\fP, it must set up its  wants to pass any of the other fields to \fBpcre_exec()\fP, it must set up its
703  own \fBpcre_extra\fP block.  own \fBpcre_extra\fP block.
# Line 502  options are defined, and this argument s Line 707  options are defined, and this argument s
707  .P  .P
708  The third argument for \fBpcre_study()\fP is a pointer for an error message. If  The third argument for \fBpcre_study()\fP is a pointer for an error message. If
709  studying succeeds (even if no data is returned), the variable it points to is  studying succeeds (even if no data is returned), the variable it points to is
710  set to NULL. Otherwise it points to a textual error message. You should  set to NULL. Otherwise it is set to point to a textual error message. This is a
711  therefore test the error pointer for NULL after calling \fBpcre_study()\fP, to  static string that is part of the library. You must not try to free it. You
712  be sure that it has run successfully.  should test the error pointer for NULL after calling \fBpcre_study()\fP, to be
713    sure that it has run successfully.
714  .P  .P
715  This is a typical call to \fBpcre_study\fP():  This is a typical call to \fBpcre_study\fP():
716  .sp  .sp
# Line 525  bytes is created. Line 731  bytes is created.
731  .sp  .sp
732  PCRE handles caseless matching, and determines whether characters are letters,  PCRE handles caseless matching, and determines whether characters are letters,
733  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
734  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
735  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
736  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
737  support.)  support. The use of locales with Unicode is discouraged. If you are handling
738  .P  characters with codes greater than 128, you should either use UTF-8 and
739  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.
740  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  .P
741  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
742  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.
743  default. As more and more applications change to using Unicode, the need for  Normally, the internal tables recognize only ASCII characters. However, when
744  this locale support is expected to die away.  PCRE is built, it is possible to cause the internal tables to be rebuilt in the
745    default "C" locale of the local system, which may cause them to be different.
746    .P
747    The internal tables can always be overridden by tables supplied by the
748    application that calls PCRE. These may be created in a different locale from
749    the default. As more and more applications change to using Unicode, the need
750    for this locale support is expected to die away.
751  .P  .P
752  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
753  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 548  the following code could be used: Line 760  the following code could be used:
760    tables = pcre_maketables();    tables = pcre_maketables();
761    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
762  .sp  .sp
763    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
764    are using Windows, the name for the French locale is "french".
765    .P
766  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
767  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
768  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 594  check against passing an arbitrary memor Line 809  check against passing an arbitrary memor
809  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
810  .sp  .sp
811    int rc;    int rc;
812    unsigned long int length;    size_t length;
813    rc = pcre_fullinfo(    rc = pcre_fullinfo(
814      re,               /* result of pcre_compile() */      re,               /* result of pcre_compile() */
815      pe,               /* result of pcre_study(), or NULL */      pe,               /* result of pcre_study(), or NULL */
# Line 615  no back references. Line 830  no back references.
830  Return the number of capturing subpatterns in the pattern. The fourth argument  Return the number of capturing subpatterns in the pattern. The fourth argument
831  should point to an \fBint\fP variable.  should point to an \fBint\fP variable.
832  .sp  .sp
833    PCRE_INFO_DEFAULTTABLES    PCRE_INFO_DEFAULT_TABLES
834  .sp  .sp
835  Return a pointer to the internal default character tables within PCRE. The  Return a pointer to the internal default character tables within PCRE. The
836  fourth argument should point to an \fBunsigned char *\fP variable. This  fourth argument should point to an \fBunsigned char *\fP variable. This
# Line 626  a NULL table pointer. Line 841  a NULL table pointer.
841    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
842  .sp  .sp
843  Return information about the first byte of any matched string, for a  Return information about the first byte of any matched string, for a
844  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
845  old name is still recognized for backwards compatibility.)  variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
846    still recognized for backwards compatibility.)
847  .P  .P
848  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
849  (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  
850  .sp  .sp
851  (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
852  starts with "^", or  starts with "^", or
# Line 666  is -1. Line 881  is -1.
881  .sp  .sp
882  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
883  names are just an additional way of identifying the parentheses, which still  names are just an additional way of identifying the parentheses, which still
884  acquire numbers. A convenience function called \fBpcre_get_named_substring()\fP  acquire numbers. Several convenience functions such as
885  is provided for extracting an individual captured substring by name. It is also  \fBpcre_get_named_substring()\fP are provided for extracting captured
886  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
887  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
888  \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,
889  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
890    values.
891  .P  .P
892  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
893  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 680  length of the longest name. PCRE_INFO_NA Line 896  length of the longest name. PCRE_INFO_NA
896  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
897  are the number of the capturing parenthesis, most significant byte first. The  are the number of the capturing parenthesis, most significant byte first. The
898  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
899  alphabetical order. For example, consider the following pattern (assume  alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of
900    their parentheses numbers. For example, consider the following pattern (assume
901  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  PCRE_EXTENDED is set, so white space - including newlines - is ignored):
902  .sp  .sp
903  .\" JOIN  .\" JOIN
904    (?P<date> (?P<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
905    (?P<month>\ed\ed) - (?P<day>\ed\ed) )    (?<month>\ed\ed) - (?<day>\ed\ed) )
906  .sp  .sp
907  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
908  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 697  bytes shows in hexadecimal, and undefine Line 914  bytes shows in hexadecimal, and undefine
914    00 02 y  e  a  r  00 ??    00 02 y  e  a  r  00 ??
915  .sp  .sp
916  When writing code to extract data from named subpatterns using the  When writing code to extract data from named subpatterns using the
917  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
918  different for each compiled pattern.  different for each compiled pattern.
919  .sp  .sp
920    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
# Line 760  it is used to pass back information abou Line 977  it is used to pass back information abou
977  string (see PCRE_INFO_FIRSTBYTE above).  string (see PCRE_INFO_FIRSTBYTE above).
978  .  .
979  .  .
980  .SH "MATCHING A PATTERN"  .SH "REFERENCE COUNTS"
981    .rs
982    .sp
983    .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
984    .PP
985    The \fBpcre_refcount()\fP function is used to maintain a reference count in the
986    data block that contains a compiled pattern. It is provided for the benefit of
987    applications that operate in an object-oriented manner, where different parts
988    of the application may be using the same compiled pattern, but you want to free
989    the block when they are all done.
990    .P
991    When a pattern is compiled, the reference count field is initialized to zero.
992    It is changed only by calling this function, whose action is to add the
993    \fIadjust\fP value (which may be positive or negative) to it. The yield of the
994    function is the new value. However, the value of the count is constrained to
995    lie between 0 and 65535, inclusive. If the new value is outside these limits,
996    it is forced to the appropriate limit value.
997    .P
998    Except when it is zero, the reference count is not correctly preserved if a
999    pattern is compiled on one host and then transferred to a host whose byte-order
1000    is different. (This seems a highly unlikely scenario.)
1001    .
1002    .
1003    .SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION"
1004  .rs  .rs
1005  .sp  .sp
1006  .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,"
# Line 772  string (see PCRE_INFO_FIRSTBYTE above). Line 1012  string (see PCRE_INFO_FIRSTBYTE above).
1012  The function \fBpcre_exec()\fP is called to match a subject string against a  The function \fBpcre_exec()\fP is called to match a subject string against a
1013  compiled pattern, which is passed in the \fIcode\fP argument. If the  compiled pattern, which is passed in the \fIcode\fP argument. If the
1014  pattern has been studied, the result of the study should be passed in the  pattern has been studied, the result of the study should be passed in the
1015  \fIextra\fP argument.  \fIextra\fP argument. This function is the main matching facility of the
1016    library, and it operates in a Perl-like manner. For specialist use there is
1017    also an alternative matching function, which is described
1018    .\" HTML <a href="#dfamatch">
1019    .\" </a>
1020    below
1021    .\"
1022    in the section about the \fBpcre_dfa_exec()\fP function.
1023  .P  .P
1024  In most applications, the pattern will have been compiled (and optionally  In most applications, the pattern will have been compiled (and optionally
1025  studied) in the same process that calls \fBpcre_exec()\fP. However, it is  studied) in the same process that calls \fBpcre_exec()\fP. However, it is
# Line 796  Here is an example of a simple call to \ Line 1043  Here is an example of a simple call to \
1043      0,              /* start at offset 0 in the subject */      0,              /* start at offset 0 in the subject */
1044      0,              /* default options */      0,              /* default options */
1045      ovector,        /* vector of integers for substring information */      ovector,        /* vector of integers for substring information */
1046      30);            /* number of elements in the vector (NOT size in bytes) */      30);            /* number of elements (NOT size in bytes) */
1047  .  .
1048  .\" HTML <a name="extradata"></a>  .\" HTML <a name="extradata"></a>
1049  .SS "Extra data for \fBpcre_exec()\fR"  .SS "Extra data for \fBpcre_exec()\fR"
# Line 805  Here is an example of a simple call to \ Line 1052  Here is an example of a simple call to \
1052  If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP  If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP
1053  data block. The \fBpcre_study()\fP function returns such a block (when it  data block. The \fBpcre_study()\fP function returns such a block (when it
1054  doesn't return NULL), but you can also create one for yourself, and pass  doesn't return NULL), but you can also create one for yourself, and pass
1055  additional information in it. The fields in a \fBpcre_extra\fP block are as  additional information in it. The \fBpcre_extra\fP block contains the following
1056  follows:  fields (not necessarily in this order):
1057  .sp  .sp
1058    unsigned long int \fIflags\fP;    unsigned long int \fIflags\fP;
1059    void *\fIstudy_data\fP;    void *\fIstudy_data\fP;
1060    unsigned long int \fImatch_limit\fP;    unsigned long int \fImatch_limit\fP;
1061      unsigned long int \fImatch_limit_recursion\fP;
1062    void *\fIcallout_data\fP;    void *\fIcallout_data\fP;
1063    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1064  .sp  .sp
# Line 819  are set. The flag bits are: Line 1067  are set. The flag bits are:
1067  .sp  .sp
1068    PCRE_EXTRA_STUDY_DATA    PCRE_EXTRA_STUDY_DATA
1069    PCRE_EXTRA_MATCH_LIMIT    PCRE_EXTRA_MATCH_LIMIT
1070      PCRE_EXTRA_MATCH_LIMIT_RECURSION
1071    PCRE_EXTRA_CALLOUT_DATA    PCRE_EXTRA_CALLOUT_DATA
1072    PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
1073  .sp  .sp
# Line 833  but which have a very large number of po Line 1082  but which have a very large number of po
1082  classic example is the use of nested unlimited repeats.  classic example is the use of nested unlimited repeats.
1083  .P  .P
1084  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly
1085  (sometimes recursively). The limit is imposed on the number of times this  (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the
1086  function is called during a match, which has the effect of limiting the amount  number of times this function is called during a match, which has the effect of
1087  of recursion and backtracking that can take place. For patterns that are not  limiting the amount of backtracking that can take place. For patterns that are
1088  anchored, the count starts from zero for each position in the subject string.  not anchored, the count restarts from zero for each position in the subject
1089    string.
1090  .P  .P
1091  The default limit for the library can be set when PCRE is built; the default  The default value for the limit can be set when PCRE is built; the default
1092  default is 10 million, which handles all but the most extreme cases. You can  default is 10 million, which handles all but the most extreme cases. You can
1093  reduce the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP block  override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP
1094  in which \fImatch_limit\fP is set to a smaller value, and  block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in
1095  PCRE_EXTRA_MATCH_LIMIT is set in the \fIflags\fP field. If the limit is  the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns
1096  exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_MATCHLIMIT.  PCRE_ERROR_MATCHLIMIT.
1097    .P
1098    The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but
1099    instead of limiting the total number of times that \fBmatch()\fP is called, it
1100    limits the depth of recursion. The recursion depth is a smaller number than the
1101    total number of calls, because not all calls to \fBmatch()\fP are recursive.
1102    This limit is of use only if it is set smaller than \fImatch_limit\fP.
1103    .P
1104    Limiting the recursion depth limits the amount of stack that can be used, or,
1105    when PCRE has been compiled to use memory on the heap instead of the stack, the
1106    amount of heap memory that can be used.
1107    .P
1108    The default value for \fImatch_limit_recursion\fP can be set when PCRE is
1109    built; the default default is the same value as the default for
1110    \fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP
1111    with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and
1112    PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
1113    is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1114  .P  .P
1115  The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,  The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,
1116  which is described in the  which is described in the
# Line 870  documentation for a discussion of saving Line 1137  documentation for a discussion of saving
1137  .rs  .rs
1138  .sp  .sp
1139  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
1140  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,
1141  PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
1142  .sp  .sp
1143    PCRE_ANCHORED    PCRE_ANCHORED
1144  .sp  .sp
# Line 880  matching position. If a pattern was comp Line 1147  matching position. If a pattern was comp
1147  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
1148  matching time.  matching time.
1149  .sp  .sp
1150      PCRE_NEWLINE_CR
1151      PCRE_NEWLINE_LF
1152      PCRE_NEWLINE_CRLF
1153      PCRE_NEWLINE_ANY
1154    .sp
1155    These options override the newline definition that was chosen or defaulted when
1156    the pattern was compiled. For details, see the description of
1157    \fBpcre_compile()\fP above. During matching, the newline choice affects the
1158    behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1159    the way the match position is advanced after a match failure for an unanchored
1160    pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt
1161    fails when the current position is at a CRLF sequence, the match position is
1162    advanced by two characters instead of one, in other words, to after the CRLF.
1163    .sp
1164    PCRE_NOTBOL    PCRE_NOTBOL
1165  .sp  .sp
1166  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 1011  is set to the offset of the first charac Line 1292  is set to the offset of the first charac
1292  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
1293  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
1294  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
1295  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
1296  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
1297  just the first pair of offsets has been set.  capturing subpatterns, the return value from a successful match is 1,
1298  .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.  
1299  .P  .P
1300  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
1301  string that it matched that is returned.  string that it matched that is returned.
# Line 1036  the \fIovector\fP is not big enough to r Line 1309  the \fIovector\fP is not big enough to r
1309  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
1310  advisable to supply an \fIovector\fP.  advisable to supply an \fIovector\fP.
1311  .P  .P
1312  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
1313  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
1314  \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
1315  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.
1316    .P
1317    It is possible for capturing subpattern number \fIn+1\fP to match some part of
1318    the subject when subpattern \fIn\fP has not been used at all. For example, if
1319    the string "abc" is matched against the pattern (a|(z))(bc) the return from the
1320    function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
1321    happens, both values in the offset pairs corresponding to unused subpatterns
1322    are set to -1.
1323    .P
1324    Offset values that correspond to unused subpatterns at the end of the
1325    expression are also set to -1. For example, if the string "abc" is matched
1326    against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1327    return from the function is 2, because the highest used capturing subpattern
1328    number is 1. However, you can refer to the offsets for the second and third
1329    capturing subpatterns if you wish (assuming the vector is large enough, of
1330    course).
1331    .P
1332    Some convenience functions are provided for extracting the captured substrings
1333    as separate strings. These are described below.
1334  .  .
1335  .SS "Return values from \fBpcre_exec()\fP"  .\" HTML <a name="errorlist"></a>
1336    .SS "Error return values from \fBpcre_exec()\fP"
1337  .rs  .rs
1338  .sp  .sp
1339  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 1068  compiled in an environment of one endian Line 1360  compiled in an environment of one endian
1360  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
1361  not present.  not present.
1362  .sp  .sp
1363    PCRE_ERROR_UNKNOWN_NODE   (-5)    PCRE_ERROR_UNKNOWN_OPCODE (-5)
1364  .sp  .sp
1365  While running the pattern match, an unknown item was encountered in the  While running the pattern match, an unknown item was encountered in the
1366  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 1090  below). It is never returned by \fBpcre_ Line 1382  below). It is never returned by \fBpcre_
1382  .sp  .sp
1383    PCRE_ERROR_MATCHLIMIT     (-8)    PCRE_ERROR_MATCHLIMIT     (-8)
1384  .sp  .sp
1385  The recursion and backtracking limit, as specified by the \fImatch_limit\fP  The backtracking limit, as specified by the \fImatch_limit\fP field in a
1386  field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the  \fBpcre_extra\fP structure (or defaulted) was reached. See the description
1387  description above.  above.
1388  .sp  .sp
1389    PCRE_ERROR_CALLOUT        (-9)    PCRE_ERROR_CALLOUT        (-9)
1390  .sp  .sp
# Line 1112  A string that contains an invalid UTF-8 Line 1404  A string that contains an invalid UTF-8
1404  The UTF-8 byte sequence that was passed as a subject was valid, but the value  The UTF-8 byte sequence that was passed as a subject was valid, but the value
1405  of \fIstartoffset\fP did not point to the beginning of a UTF-8 character.  of \fIstartoffset\fP did not point to the beginning of a UTF-8 character.
1406  .sp  .sp
1407    PCRE_ERROR_PARTIAL (-12)    PCRE_ERROR_PARTIAL        (-12)
1408  .sp  .sp
1409  The subject string did not match, but it did match partially. See the  The subject string did not match, but it did match partially. See the
1410  .\" HREF  .\" HREF
# Line 1120  The subject string did not match, but it Line 1412  The subject string did not match, but it
1412  .\"  .\"
1413  documentation for details of partial matching.  documentation for details of partial matching.
1414  .sp  .sp
1415    PCRE_ERROR_BAD_PARTIAL (-13)    PCRE_ERROR_BADPARTIAL     (-13)
1416  .sp  .sp
1417  The PCRE_PARTIAL option was used with a compiled pattern containing items that  The PCRE_PARTIAL option was used with a compiled pattern containing items that
1418  are not supported for partial matching. See the  are not supported for partial matching. See the
# Line 1129  are not supported for partial matching. Line 1421  are not supported for partial matching.
1421  .\"  .\"
1422  documentation for details of partial matching.  documentation for details of partial matching.
1423  .sp  .sp
1424    PCRE_ERROR_INTERNAL (-14)    PCRE_ERROR_INTERNAL       (-14)
1425  .sp  .sp
1426  An unexpected internal error has occurred. This error could be caused by a bug  An unexpected internal error has occurred. This error could be caused by a bug
1427  in PCRE or by overwriting of the compiled pattern.  in PCRE or by overwriting of the compiled pattern.
1428  .sp  .sp
1429    PCRE_ERROR_BADCOUNT (-15)    PCRE_ERROR_BADCOUNT       (-15)
1430  .sp  .sp
1431  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.
1432    .sp
1433      PCRE_ERROR_RECURSIONLIMIT (-21)
1434    .sp
1435    The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
1436    field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
1437    description above.
1438    .sp
1439      PCRE_ERROR_NULLWSLIMIT    (-22)
1440    .sp
1441    When a group that can match an empty substring is repeated with an unbounded
1442    upper limit, the subject position at the start of the group must be remembered,
1443    so that a test for an empty string can be made when the end of the group is
1444    reached. Some workspace is required for this; if it runs out, this error is
1445    given.
1446    .sp
1447      PCRE_ERROR_BADNEWLINE     (-23)
1448    .sp
1449    An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
1450    .P
1451    Error numbers -16 to -20 are not used by \fBpcre_exec()\fP.
1452  .  .
1453  .  .
1454  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1148  This error is given if the value of the Line 1460  This error is given if the value of the
1460  .ti +5n  .ti +5n
1461  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
1462  .PP  .PP
 .br  
1463  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
1464  .ti +5n  .ti +5n
1465  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
1466  .ti +5n  .ti +5n
1467  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
1468  .PP  .PP
 .br  
1469  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
1470  .ti +5n  .ti +5n
1471  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
# Line 1166  Captured substrings can be accessed dire Line 1476  Captured substrings can be accessed dire
1476  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
1477  as new, separate, zero-terminated strings. These functions identify substrings  as new, separate, zero-terminated strings. These functions identify substrings
1478  by number. The next section describes functions for extracting named  by number. The next section describes functions for extracting named
1479  substrings. A substring that contains a binary zero is correctly extracted and  substrings.
1480  has a further zero added on the end, but the result is not, of course,  .P
1481  a C string.  A substring that contains a binary zero is correctly extracted and has a
1482    further zero added on the end, but the result is not, of course, a C string.
1483    However, you can process such a string by referring to the length that is
1484    returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
1485    Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
1486    for handling strings containing binary zeros, because the end of the final
1487    string is not independently indicated.
1488  .P  .P
1489  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:
1490  \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 1188  the string is placed in \fIbuffer\fP, wh Line 1504  the string is placed in \fIbuffer\fP, wh
1504  \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
1505  obtained via \fBpcre_malloc\fP, and its address is returned via  obtained via \fBpcre_malloc\fP, and its address is returned via
1506  \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
1507  including the terminating zero, or one of  including the terminating zero, or one of these error codes:
1508  .sp  .sp
1509    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1510  .sp  .sp
# Line 1204  and builds a list of pointers to them. A Line 1520  and builds a list of pointers to them. A
1520  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
1521  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
1522  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
1523  function is zero if all went well, or  function is zero if all went well, or the error code
1524  .sp  .sp
1525    PCRE_ERROR_NOMEMORY       (-6)    PCRE_ERROR_NOMEMORY       (-6)
1526  .sp  .sp
# Line 1223  a previous call of \fBpcre_get_substring Line 1539  a previous call of \fBpcre_get_substring
1539  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
1540  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
1541  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
1542  linked via a special interface to another programming language which cannot use  linked via a special interface to another programming language that cannot use
1543  \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
1544  provided.  provided.
1545  .  .
# Line 1235  provided. Line 1551  provided.
1551  .ti +5n  .ti +5n
1552  .B const char *\fIname\fP);  .B const char *\fIname\fP);
1553  .PP  .PP
 .br  
1554  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
1555  .ti +5n  .ti +5n
1556  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1244  provided. Line 1559  provided.
1559  .ti +5n  .ti +5n
1560  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
1561  .PP  .PP
 .br  
1562  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
1563  .ti +5n  .ti +5n
1564  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1258  For example, for this pattern Line 1572  For example, for this pattern
1572  .sp  .sp
1573    (a+)b(?<xxx>\ed+)...    (a+)b(?<xxx>\ed+)...
1574  .sp  .sp
1575  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
1576  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
1577  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
1578    pattern, and the second is the name. The yield of the function is the
1579  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
1580  that name.  that name.
1581  .P  .P
# Line 1268  Given the number, you can extract the su Line 1583  Given the number, you can extract the su
1583  functions described in the previous section. For convenience, there are also  functions described in the previous section. For convenience, there are also
1584  two functions that do the whole job.  two functions that do the whole job.
1585  .P  .P
1586  Most of the arguments of \fIpcre_copy_named_substring()\fP and  Most of the arguments of \fBpcre_copy_named_substring()\fP and
1587  \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
1588  functions that extract by number. As these are described in the previous  functions that extract by number. As these are described in the previous
1589  section, they are not re-described here. There are just two differences:  section, they are not re-described here. There are just two differences:
1590  .P  .P
# Line 1279  pattern. This is needed in order to gain Line 1594  pattern. This is needed in order to gain
1594  translation table.  translation table.
1595  .P  .P
1596  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
1597  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
1598  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
1599    the behaviour may not be what you want (see the next section).
1600    .
1601    .
1602    .SH "DUPLICATE SUBPATTERN NAMES"
1603    .rs
1604    .sp
1605    .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
1606    .ti +5n
1607    .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
1608    .PP
1609    When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
1610    are not required to be unique. Normally, patterns with duplicate names are such
1611    that in any one match, only one of the named subpatterns participates. An
1612    example is shown in the
1613    .\" HREF
1614    \fBpcrepattern\fP
1615    .\"
1616    documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP
1617    and \fBpcre_get_named_substring()\fP return the first substring corresponding
1618    to the given name that is set. If none are set, an empty string is returned.
1619    The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are
1620    associated with the name, but it is not defined which it is.
1621    .sp
1622    If you want to get full details of all captured substrings for a given name,
1623    you must use the \fBpcre_get_stringtable_entries()\fP function. The first
1624    argument is the compiled pattern, and the second is the name. The third and
1625    fourth are pointers to variables which are updated by the function. After it
1626    has run, they point to the first and last entries in the name-to-number table
1627    for the given name. The function itself returns the length of each entry, or
1628    PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
1629    described above in the section entitled \fIInformation about a pattern\fP.
1630    Given all the relevant entries for the name, you can extract each of their
1631    numbers, and hence the captured data, if any.
1632    .
1633    .
1634    .SH "FINDING ALL POSSIBLE MATCHES"
1635    .rs
1636    .sp
1637    The traditional matching function uses a similar algorithm to Perl, which stops
1638    when it finds the first match, starting at a given point in the subject. If you
1639    want to find all possible matches, or the longest possible match, consider
1640    using the alternative matching function (see below) instead. If you cannot use
1641    the alternative function, but still need to find all possible matches, you
1642    can kludge it up by making use of the callout facility, which is described in
1643    the
1644    .\" HREF
1645    \fBpcrecallout\fP
1646    .\"
1647    documentation.
1648    .P
1649    What you have to do is to insert a callout right at the end of the pattern.
1650    When your callout function is called, extract and save the current matched
1651    substring. Then return 1, which forces \fBpcre_exec()\fP to backtrack and try
1652    other alternatives. Ultimately, when it runs out of matches, \fBpcre_exec()\fP
1653    will yield PCRE_ERROR_NOMATCH.
1654    .
1655    .
1656    .\" HTML <a name="dfamatch"></a>
1657    .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
1658    .rs
1659    .sp
1660    .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
1661    .ti +5n
1662    .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
1663    .ti +5n
1664    .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
1665    .ti +5n
1666    .B int *\fIworkspace\fP, int \fIwscount\fP);
1667  .P  .P
1668  .in 0  The function \fBpcre_dfa_exec()\fP is called to match a subject string against
1669  Last updated: 09 September 2004  a compiled pattern, using a matching algorithm that scans the subject string
1670  .br  just once, and does not backtrack. This has different characteristics to the
1671  Copyright (c) 1997-2004 University of Cambridge.  normal algorithm, and is not compatible with Perl. Some of the features of PCRE
1672    patterns are not supported. Nevertheless, there are times when this kind of
1673    matching can be useful. For a discussion of the two matching algorithms, see
1674    the
1675    .\" HREF
1676    \fBpcrematching\fP
1677    .\"
1678    documentation.
1679    .P
1680    The arguments for the \fBpcre_dfa_exec()\fP function are the same as for
1681    \fBpcre_exec()\fP, plus two extras. The \fIovector\fP argument is used in a
1682    different way, and this is described below. The other common arguments are used
1683    in the same way as for \fBpcre_exec()\fP, so their description is not repeated
1684    here.
1685    .P
1686    The two additional arguments provide workspace for the function. The workspace
1687    vector should contain at least 20 elements. It is used for keeping track of
1688    multiple paths through the pattern tree. More workspace will be needed for
1689    patterns and subjects where there are a lot of potential matches.
1690    .P
1691    Here is an example of a simple call to \fBpcre_dfa_exec()\fP:
1692    .sp
1693      int rc;
1694      int ovector[10];
1695      int wspace[20];
1696      rc = pcre_dfa_exec(
1697        re,             /* result of pcre_compile() */
1698        NULL,           /* we didn't study the pattern */
1699        "some string",  /* the subject string */
1700        11,             /* the length of the subject string */
1701        0,              /* start at offset 0 in the subject */
1702        0,              /* default options */
1703        ovector,        /* vector of integers for substring information */
1704        10,             /* number of elements (NOT size in bytes) */
1705        wspace,         /* working space vector */
1706        20);            /* number of elements (NOT size in bytes) */
1707    .
1708    .SS "Option bits for \fBpcre_dfa_exec()\fP"
1709    .rs
1710    .sp
1711    The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be
1712    zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1713    PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,
1714    PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are
1715    the same as for \fBpcre_exec()\fP, so their description is not repeated here.
1716    .sp
1717      PCRE_PARTIAL
1718    .sp
1719    This has the same general effect as it does for \fBpcre_exec()\fP, but the
1720    details are slightly different. When PCRE_PARTIAL is set for
1721    \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into
1722    PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no
1723    complete matches, but there is still at least one matching possibility. The
1724    portion of the string that provided the partial match is set as the first
1725    matching string.
1726    .sp
1727      PCRE_DFA_SHORTEST
1728    .sp
1729    Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
1730    soon as it has found one match. Because of the way the alternative algorithm
1731    works, this is necessarily the shortest possible match at the first possible
1732    matching point in the subject string.
1733    .sp
1734      PCRE_DFA_RESTART
1735    .sp
1736    When \fBpcre_dfa_exec()\fP is called with the PCRE_PARTIAL option, and returns
1737    a partial match, it is possible to call it again, with additional subject
1738    characters, and have it continue with the same match. The PCRE_DFA_RESTART
1739    option requests this action; when it is set, the \fIworkspace\fP and
1740    \fIwscount\fP options must reference the same vector as before because data
1741    about the match so far is left in them after a partial match. There is more
1742    discussion of this facility in the
1743    .\" HREF
1744    \fBpcrepartial\fP
1745    .\"
1746    documentation.
1747    .
1748    .SS "Successful returns from \fBpcre_dfa_exec()\fP"
1749    .rs
1750    .sp
1751    When \fBpcre_dfa_exec()\fP succeeds, it may have matched more than one
1752    substring in the subject. Note, however, that all the matches from one run of
1753    the function start at the same point in the subject. The shorter matches are
1754    all initial substrings of the longer matches. For example, if the pattern
1755    .sp
1756      <.*>
1757    .sp
1758    is matched against the string
1759    .sp
1760      This is <something> <something else> <something further> no more
1761    .sp
1762    the three matched strings are
1763    .sp
1764      <something>
1765      <something> <something else>
1766      <something> <something else> <something further>
1767    .sp
1768    On success, the yield of the function is a number greater than zero, which is
1769    the number of matched substrings. The substrings themselves are returned in
1770    \fIovector\fP. Each string uses two elements; the first is the offset to the
1771    start, and the second is the offset to the end. In fact, all the strings have
1772    the same start offset. (Space could have been saved by giving this only once,
1773    but it was decided to retain some compatibility with the way \fBpcre_exec()\fP
1774    returns data, even though the meaning of the strings is different.)
1775    .P
1776    The strings are returned in reverse order of length; that is, the longest
1777    matching string is given first. If there were too many matches to fit into
1778    \fIovector\fP, the yield of the function is zero, and the vector is filled with
1779    the longest matches.
1780    .
1781    .SS "Error returns from \fBpcre_dfa_exec()\fP"
1782    .rs
1783    .sp
1784    The \fBpcre_dfa_exec()\fP function returns a negative number when it fails.
1785    Many of the errors are the same as for \fBpcre_exec()\fP, and these are
1786    described
1787    .\" HTML <a href="#errorlist">
1788    .\" </a>
1789    above.
1790    .\"
1791    There are in addition the following errors that are specific to
1792    \fBpcre_dfa_exec()\fP:
1793    .sp
1794      PCRE_ERROR_DFA_UITEM      (-16)
1795    .sp
1796    This return is given if \fBpcre_dfa_exec()\fP encounters an item in the pattern
1797    that it does not support, for instance, the use of \eC or a back reference.
1798    .sp
1799      PCRE_ERROR_DFA_UCOND      (-17)
1800    .sp
1801    This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that
1802    uses a back reference for the condition, or a test for recursion in a specific
1803    group. These are not supported.
1804    .sp
1805      PCRE_ERROR_DFA_UMLIMIT    (-18)
1806    .sp
1807    This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP
1808    block that contains a setting of the \fImatch_limit\fP field. This is not
1809    supported (it is meaningless).
1810    .sp
1811      PCRE_ERROR_DFA_WSSIZE     (-19)
1812    .sp
1813    This return is given if \fBpcre_dfa_exec()\fP runs out of space in the
1814    \fIworkspace\fP vector.
1815    .sp
1816      PCRE_ERROR_DFA_RECURSE    (-20)
1817    .sp
1818    When a recursive subpattern is processed, the matching function calls itself
1819    recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
1820    error is given if the output vector is not large enough. This should be
1821    extremely rare, as a vector of size 1000 is used.
1822    .
1823    .
1824    .SH "SEE ALSO"
1825    .rs
1826    .sp
1827    \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
1828    \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
1829    \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
1830    .
1831    .
1832    .SH AUTHOR
1833    .rs
1834    .sp
1835    .nf
1836    Philip Hazel
1837    University Computing Service
1838    Cambridge CB2 3QH, England.
1839    .fi
1840    .
1841    .
1842    .SH REVISION
1843    .rs
1844    .sp
1845    .nf
1846    Last updated: 06 March 2007
1847    Copyright (c) 1997-2007 University of Cambridge.
1848    .fi

Legend:
Removed from v.75  
changed lines
  Added in v.142

  ViewVC Help
Powered by ViewVC 1.1.5