/[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 921 by ph10, Sat Feb 18 18:45:55 2012 UTC
# Line 1  Line 1 
1  .TH PCREAPI 3  .TH PCREAPI 3
2  .SH NAME  .SH NAME
3  PCRE - Perl-compatible regular expressions  PCRE - Perl-compatible regular expressions
 .SH "PCRE NATIVE API"  
 .rs  
4  .sp  .sp
5  .B #include <pcre.h>  .B #include <pcre.h>
6  .PP  .
7    .
8    .SH "PCRE NATIVE API BASIC FUNCTIONS"
9    .rs
10    .sp
11  .SM  .SM
 .br  
12  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
13  .ti +5n  .ti +5n
14  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
15  .ti +5n  .ti +5n
16  .B const unsigned char *\fItableptr\fP);  .B const unsigned char *\fItableptr\fP);
17  .PP  .PP
 .br  
18  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
19  .ti +5n  .ti +5n
20  .B int *\fIerrorcodeptr\fP,  .B int *\fIerrorcodeptr\fP,
# Line 23  PCRE - Perl-compatible regular expressio Line 23  PCRE - Perl-compatible regular expressio
23  .ti +5n  .ti +5n
24  .B const unsigned char *\fItableptr\fP);  .B const unsigned char *\fItableptr\fP);
25  .PP  .PP
 .br  
26  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,
27  .ti +5n  .ti +5n
28  .B const char **\fIerrptr\fP);  .B const char **\fIerrptr\fP);
29  .PP  .PP
30  .br  .B void pcre_free_study(pcre_extra *\fIextra\fP);
31    .PP
32  .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,"
33  .ti +5n  .ti +5n
34  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
35  .ti +5n  .ti +5n
36  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
37  .PP  .PP
 .br  
38  .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,"
39  .ti +5n  .ti +5n
40  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
# Line 43  PCRE - Perl-compatible regular expressio Line 42  PCRE - Perl-compatible regular expressio
42  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
43  .ti +5n  .ti +5n
44  .B int *\fIworkspace\fP, int \fIwscount\fP);  .B int *\fIworkspace\fP, int \fIwscount\fP);
45  .PP  .
46  .br  .
47    .SH "PCRE NATIVE API STRING EXTRACTION FUNCTIONS"
48    .rs
49    .sp
50  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
51  .ti +5n  .ti +5n
52  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 53  PCRE - Perl-compatible regular expressio Line 55  PCRE - Perl-compatible regular expressio
55  .ti +5n  .ti +5n
56  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
57  .PP  .PP
 .br  
58  .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
59  .ti +5n  .ti +5n
60  .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
61  .ti +5n  .ti +5n
62  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
63  .PP  .PP
 .br  
64  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
65  .ti +5n  .ti +5n
66  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 69  PCRE - Perl-compatible regular expressio Line 69  PCRE - Perl-compatible regular expressio
69  .ti +5n  .ti +5n
70  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
71  .PP  .PP
 .br  
72  .B int pcre_get_stringnumber(const pcre *\fIcode\fP,  .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
73  .ti +5n  .ti +5n
74  .B const char *\fIname\fP);  .B const char *\fIname\fP);
75  .PP  .PP
 .br  
76  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,  .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
77  .ti +5n  .ti +5n
78  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
79  .PP  .PP
 .br  
80  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
81  .ti +5n  .ti +5n
82  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
83  .ti +5n  .ti +5n
84  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
85  .PP  .PP
 .br  
86  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
87  .ti +5n  .ti +5n
88  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
89  .PP  .PP
 .br  
90  .B void pcre_free_substring(const char *\fIstringptr\fP);  .B void pcre_free_substring(const char *\fIstringptr\fP);
91  .PP  .PP
 .br  
92  .B void pcre_free_substring_list(const char **\fIstringptr\fP);  .B void pcre_free_substring_list(const char **\fIstringptr\fP);
93    .
94    .
95    .SH "PCRE NATIVE API AUXILIARY FUNCTIONS"
96    .rs
97    .sp
98    .B pcre_jit_stack *pcre_jit_stack_alloc(int \fIstartsize\fP, int \fImaxsize\fP);
99    .PP
100    .B void pcre_jit_stack_free(pcre_jit_stack *\fIstack\fP);
101    .PP
102    .B void pcre_assign_jit_stack(pcre_extra *\fIextra\fP,
103    .ti +5n
104    .B pcre_jit_callback \fIcallback\fP, void *\fIdata\fP);
105  .PP  .PP
 .br  
106  .B const unsigned char *pcre_maketables(void);  .B const unsigned char *pcre_maketables(void);
107  .PP  .PP
 .br  
108  .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,"
109  .ti +5n  .ti +5n
110  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
111  .PP  .PP
 .br  
 .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  
 .B *\fIfirstcharptr\fP);  
 .PP  
 .br  
112  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
113  .PP  .PP
 .br  
114  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
115  .PP  .PP
116  .br  .B const char *pcre_version(void);
 .B char *pcre_version(void);  
117  .PP  .PP
118  .br  .B int pcre_pattern_to_host_byte_order(pcre *\fIcode\fP,
119    .ti +5n
120    .B pcre_extra *\fIextra\fP, const unsigned char *\fItables\fP);
121    .
122    .
123    .SH "PCRE NATIVE API INDIRECTED FUNCTIONS"
124    .rs
125    .sp
126  .B void *(*pcre_malloc)(size_t);  .B void *(*pcre_malloc)(size_t);
127  .PP  .PP
 .br  
128  .B void (*pcre_free)(void *);  .B void (*pcre_free)(void *);
129  .PP  .PP
 .br  
130  .B void *(*pcre_stack_malloc)(size_t);  .B void *(*pcre_stack_malloc)(size_t);
131  .PP  .PP
 .br  
132  .B void (*pcre_stack_free)(void *);  .B void (*pcre_stack_free)(void *);
133  .PP  .PP
 .br  
134  .B int (*pcre_callout)(pcre_callout_block *);  .B int (*pcre_callout)(pcre_callout_block *);
135  .  .
136  .  .
137    .SH "PCRE 8-BIT AND 16-BIT LIBRARIES"
138    .rs
139    .sp
140    From release 8.30, PCRE can be compiled as a library for handling 16-bit
141    character strings as well as, or instead of, the original library that handles
142    8-bit character strings. To avoid too much complication, this document
143    describes the 8-bit versions of the functions, with only occasional references
144    to the 16-bit library.
145    .P
146    The 16-bit functions operate in the same way as their 8-bit counterparts; they
147    just use different data types for their arguments and results, and their names
148    start with \fBpcre16_\fP instead of \fBpcre_\fP. For every option that has UTF8
149    in its name (for example, PCRE_UTF8), there is a corresponding 16-bit name with
150    UTF8 replaced by UTF16. This facility is in fact just cosmetic; the 16-bit
151    option names define the same bit values.
152    .P
153    References to bytes and UTF-8 in this document should be read as references to
154    16-bit data quantities and UTF-16 when using the 16-bit library, unless
155    specified otherwise. More details of the specific differences for the 16-bit
156    library are given in the
157    .\" HREF
158    \fBpcre16\fP
159    .\"
160    page.
161    .
162    .
163  .SH "PCRE API OVERVIEW"  .SH "PCRE API OVERVIEW"
164  .rs  .rs
165  .sp  .sp
166  PCRE has its own native API, which is described in this document. There are  PCRE has its own native API, which is described in this document. There are
167  also some wrapper functions that correspond to the POSIX regular expression  also some wrapper functions (for the 8-bit library only) that correspond to the
168  API. These are described in the  POSIX regular expression API, but they do not give access to all the
169    functionality. They are described in the
170  .\" HREF  .\" HREF
171  \fBpcreposix\fP  \fBpcreposix\fP
172  .\"  .\"
173  documentation. Both of these APIs define a set of C function calls. A C++  documentation. Both of these APIs define a set of C function calls. A C++
174  wrapper is distributed with PCRE. It is documented in the  wrapper (again for the 8-bit library only) is also distributed with PCRE. It is
175    documented in the
176  .\" HREF  .\" HREF
177  \fBpcrecpp\fP  \fBpcrecpp\fP
178  .\"  .\"
179  page.  page.
180  .P  .P
181  The native API C function prototypes are defined in the header file  The native API C function prototypes are defined in the header file
182  \fBpcre.h\fP, and on Unix systems the library itself is called \fBlibpcre\fP.  \fBpcre.h\fP, and on Unix-like systems the (8-bit) library itself is called
183  It can normally be accessed by adding \fB-lpcre\fP to the command for linking  \fBlibpcre\fP. It can normally be accessed by adding \fB-lpcre\fP to the
184  an application that uses PCRE. The header file defines the macros PCRE_MAJOR  command for linking an application that uses PCRE. The header file defines the
185  and PCRE_MINOR to contain the major and minor release numbers for the library.  macros PCRE_MAJOR and PCRE_MINOR to contain the major and minor release numbers
186  Applications can use these to include support for different releases of PCRE.  for the library. Applications can use these to include support for different
187    releases of PCRE.
188    .P
189    In a Windows environment, if you want to statically link an application program
190    against a non-dll \fBpcre.a\fP file, you must define PCRE_STATIC before
191    including \fBpcre.h\fP or \fBpcrecpp.h\fP, because otherwise the
192    \fBpcre_malloc()\fP and \fBpcre_free()\fP exported functions will be declared
193    \fB__declspec(dllimport)\fP, with unwanted results.
194  .P  .P
195  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,
196  and \fBpcre_exec()\fP are used for compiling and matching regular expressions  and \fBpcre_exec()\fP are used for compiling and matching regular expressions
197  in a Perl-compatible manner. A sample program that demonstrates the simplest  in a Perl-compatible manner. A sample program that demonstrates the simplest
198  way of using them is provided in the file called \fIpcredemo.c\fP in the source  way of using them is provided in the file called \fIpcredemo.c\fP in the PCRE
199  distribution. The  source distribution. A listing of this program is given in the
200    .\" HREF
201    \fBpcredemo\fP
202    .\"
203    documentation, and the
204  .\" HREF  .\" HREF
205  \fBpcresample\fP  \fBpcresample\fP
206  .\"  .\"
207  documentation describes how to run it.  documentation describes how to compile and run it.
208    .P
209    Just-in-time compiler support is an optional feature of PCRE that can be built
210    in appropriate hardware environments. It greatly speeds up the matching
211    performance of many patterns. Simple programs can easily request that it be
212    used if available, by setting an option that is ignored when it is not
213    relevant. More complicated programs might need to make use of the functions
214    \fBpcre_jit_stack_alloc()\fP, \fBpcre_jit_stack_free()\fP, and
215    \fBpcre_assign_jit_stack()\fP in order to control the JIT code's memory usage.
216    These functions are discussed in the
217    .\" HREF
218    \fBpcrejit\fP
219    .\"
220    documentation.
221  .P  .P
222  A second matching function, \fBpcre_dfa_exec()\fP, which is not  A second matching function, \fBpcre_dfa_exec()\fP, which is not
223  Perl-compatible, is also provided. This uses a different algorithm for the  Perl-compatible, is also provided. This uses a different algorithm for the
224  matching. The alternative algorithm finds all possible matches (at a given  matching. The alternative algorithm finds all possible matches (at a given
225  point in the subject), and scans the subject just once. However, this algorithm  point in the subject), and scans the subject just once (unless there are
226  does not return captured substrings. A description of the two matching  lookbehind assertions). However, this algorithm does not return captured
227  algorithms and their advantages and disadvantages is given in the  substrings. A description of the two matching algorithms and their advantages
228    and disadvantages is given in the
229  .\" HREF  .\" HREF
230  \fBpcrematching\fP  \fBpcrematching\fP
231  .\"  .\"
# Line 200  specialist use. Most commonly, no specia Line 253  specialist use. Most commonly, no specia
253  internal tables that are generated when PCRE is built are used.  internal tables that are generated when PCRE is built are used.
254  .P  .P
255  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
256  compiled pattern; \fBpcre_info()\fP is an obsolete version that returns only  compiled pattern. The function \fBpcre_version()\fP returns a pointer to a
257  some of the available information, but is retained for backwards compatibility.  string containing the version of PCRE and its date of release.
 The function \fBpcre_version()\fP returns a pointer to a string containing the  
 version of PCRE and its date of release.  
258  .P  .P
259  The function \fBpcre_refcount()\fP maintains a reference count in a data block  The function \fBpcre_refcount()\fP maintains a reference count in a data block
260  containing a compiled pattern. This is provided for the benefit of  containing a compiled pattern. This is provided for the benefit of
# Line 243  points during a matching operation. Deta Line 294  points during a matching operation. Deta
294  documentation.  documentation.
295  .  .
296  .  .
297    .\" HTML <a name="newlines"></a>
298  .SH NEWLINES  .SH NEWLINES
299  .rs  .rs
300  .sp  .sp
301  PCRE supports four different conventions for indicating line breaks in  PCRE supports five different conventions for indicating line breaks in
302  strings: a single CR (carriage return) character, a single LF (linefeed)  strings: a single CR (carriage return) character, a single LF (linefeed)
303  character, the two-character sequence CRLF, or any Unicode newline sequence.  character, the two-character sequence CRLF, any of the three preceding, or any
304  The Unicode newline sequences are the three just mentioned, plus the single  Unicode newline sequence. The Unicode newline sequences are the three just
305  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,
306  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
307    (paragraph separator, U+2029).
308  .P  .P
309  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
310  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 259  The default default is LF, which is the Line 312  The default default is LF, which is the
312  default can be overridden, either when a pattern is compiled, or when it is  default can be overridden, either when a pattern is compiled, or when it is
313  matched.  matched.
314  .P  .P
315    At compile time, the newline convention can be specified by the \fIoptions\fP
316    argument of \fBpcre_compile()\fP, or it can be specified by special text at the
317    start of the pattern itself; this overrides any other settings. See the
318    .\" HREF
319    \fBpcrepattern\fP
320    .\"
321    page for details of the special character sequences.
322    .P
323  In the PCRE documentation the word "newline" is used to mean "the character or  In the PCRE documentation the word "newline" is used to mean "the character or
324  pair of characters that indicate a line break". The choice of newline  pair of characters that indicate a line break". The choice of newline
325  convention affects the handling of the dot, circumflex, and dollar  convention affects the handling of the dot, circumflex, and dollar
326  metacharacters, the handling of #-comments in /x mode, and, when CRLF is a  metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
327  recognized line ending sequence, the match position advancement for a  recognized line ending sequence, the match position advancement for a
328  non-anchored pattern. The choice of newline convention does not affect the  non-anchored pattern. There is more detail about this in the
329  interpretation of the \en or \er escape sequences.  .\" HTML <a href="#execoptions">
330    .\" </a>
331    section on \fBpcre_exec()\fP options
332    .\"
333    below.
334    .P
335    The choice of newline convention does not affect the interpretation of
336    the \en or \er escape sequences, nor does it affect what \eR matches, which is
337    controlled in a similar way, but by separate options.
338  .  .
339  .  .
340  .SH MULTITHREADING  .SH MULTITHREADING
# Line 278  callout function pointed to by \fBpcre_c Line 347  callout function pointed to by \fBpcre_c
347  .P  .P
348  The compiled form of a regular expression is not altered during matching, so  The compiled form of a regular expression is not altered during matching, so
349  the same compiled pattern can safely be used by several threads at once.  the same compiled pattern can safely be used by several threads at once.
350    .P
351    If the just-in-time optimization feature is being used, it needs separate
352    memory stack areas for each thread. See the
353    .\" HREF
354    \fBpcrejit\fP
355    .\"
356    documentation for more details.
357  .  .
358  .  .
359  .SH "SAVING PRECOMPILED PATTERNS FOR LATER USE"  .SH "SAVING PRECOMPILED PATTERNS FOR LATER USE"
# Line 289  which it was compiled. Details are given Line 365  which it was compiled. Details are given
365  .\" HREF  .\" HREF
366  \fBpcreprecompile\fP  \fBpcreprecompile\fP
367  .\"  .\"
368  documentation.  documentation, which includes a description of the
369    \fBpcre_pattern_to_host_byte_order()\fP function. However, compiling a regular
370    expression with one version of PCRE for use with a different version is not
371    guaranteed to work and may cause crashes.
372  .  .
373  .  .
374  .SH "CHECKING BUILD-TIME OPTIONS"  .SH "CHECKING BUILD-TIME OPTIONS"
# Line 306  documentation has more details about the Line 385  documentation has more details about the
385  .P  .P
386  The first argument for \fBpcre_config()\fP is an integer, specifying which  The first argument for \fBpcre_config()\fP is an integer, specifying which
387  information is required; the second argument is a pointer to a variable into  information is required; the second argument is a pointer to a variable into
388  which the information is placed. The following information is available:  which the information is placed. The returned value is zero on success, or the
389    negative error code PCRE_ERROR_BADOPTION if the value in the first argument is
390    not recognized. The following information is available:
391  .sp  .sp
392    PCRE_CONFIG_UTF8    PCRE_CONFIG_UTF8
393  .sp  .sp
394  The output is an integer that is set to one if UTF-8 support is available;  The output is an integer that is set to one if UTF-8 support is available;
395  otherwise it is set to zero.  otherwise it is set to zero. If this option is given to the 16-bit version of
396    this function, \fBpcre16_config()\fP, the result is PCRE_ERROR_BADOPTION.
397    .sp
398      PCRE_CONFIG_UTF16
399    .sp
400    The output is an integer that is set to one if UTF-16 support is available;
401    otherwise it is set to zero. This value should normally be given to the 16-bit
402    version of this function, \fBpcre16_config()\fP. If it is given to the 8-bit
403    version of this function, the result is PCRE_ERROR_BADOPTION.
404  .sp  .sp
405    PCRE_CONFIG_UNICODE_PROPERTIES    PCRE_CONFIG_UNICODE_PROPERTIES
406  .sp  .sp
407  The output is an integer that is set to one if support for Unicode character  The output is an integer that is set to one if support for Unicode character
408  properties is available; otherwise it is set to zero.  properties is available; otherwise it is set to zero.
409  .sp  .sp
410      PCRE_CONFIG_JIT
411    .sp
412    The output is an integer that is set to one if support for just-in-time
413    compiling is available; otherwise it is set to zero.
414    .sp
415      PCRE_CONFIG_JITTARGET
416    .sp
417    The output is a pointer to a zero-terminated "const char *" string. If JIT
418    support is available, the string contains the name of the architecture for
419    which the JIT compiler is configured, for example "x86 32bit (little endian +
420    unaligned)". If JIT support is not available, the result is NULL.
421    .sp
422    PCRE_CONFIG_NEWLINE    PCRE_CONFIG_NEWLINE
423  .sp  .sp
424  The output is an integer whose value specifies the default character sequence  The output is an integer whose value specifies the default character sequence
425  that is recognized as meaning "newline". The four values that are supported  that is recognized as meaning "newline". The four values that are supported
426  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.
427  normally be the standard sequence for your operating system.  Though they are derived from ASCII, the same values are returned in EBCDIC
428    environments. The default should normally correspond to the standard sequence
429    for your operating system.
430    .sp
431      PCRE_CONFIG_BSR
432    .sp
433    The output is an integer whose value indicates what character sequences the \eR
434    escape sequence matches by default. A value of 0 means that \eR matches any
435    Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
436    or CRLF. The default can be overridden when a pattern is compiled or matched.
437  .sp  .sp
438    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
439  .sp  .sp
440  The output is an integer that contains the number of bytes used for internal  The output is an integer that contains the number of bytes used for internal
441  linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values  linkage in compiled regular expressions. For the 8-bit library, the value can
442  allow larger regular expressions to be compiled, at the expense of slower  be 2, 3, or 4. For the 16-bit library, the value is either 2 or 4 and is still
443  matching. The default value of 2 is sufficient for all but the most massive  a number of bytes. The default value of 2 is sufficient for all but the most
444  patterns, since it allows the compiled pattern to be up to 64K in size.  massive patterns, since it allows the compiled pattern to be up to 64K in size.
445    Larger values allow larger regular expressions to be compiled, at the expense
446    of slower matching.
447  .sp  .sp
448    PCRE_CONFIG_POSIX_MALLOC_THRESHOLD    PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
449  .sp  .sp
# Line 345  documentation. Line 457  documentation.
457  .sp  .sp
458    PCRE_CONFIG_MATCH_LIMIT    PCRE_CONFIG_MATCH_LIMIT
459  .sp  .sp
460  The output is an integer that gives the default limit for the number of  The output is a long integer that gives the default limit for the number of
461  internal matching function calls in a \fBpcre_exec()\fP execution. Further  internal matching function calls in a \fBpcre_exec()\fP execution. Further
462  details are given with \fBpcre_exec()\fP below.  details are given with \fBpcre_exec()\fP below.
463  .sp  .sp
464    PCRE_CONFIG_MATCH_LIMIT_RECURSION    PCRE_CONFIG_MATCH_LIMIT_RECURSION
465  .sp  .sp
466  The output is an integer that gives the default limit for the depth of  The output is a long integer that gives the default limit for the depth of
467  recursion when calling the internal matching function in a \fBpcre_exec()\fP  recursion when calling the internal matching function in a \fBpcre_exec()\fP
468  execution. Further details are given with \fBpcre_exec()\fP below.  execution. Further details are given with \fBpcre_exec()\fP below.
469  .sp  .sp
# Line 386  avoiding the use of the stack. Line 498  avoiding the use of the stack.
498  Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be  Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be
499  called to compile a pattern into an internal form. The only difference between  called to compile a pattern into an internal form. The only difference between
500  the two interfaces is that \fBpcre_compile2()\fP has an additional argument,  the two interfaces is that \fBpcre_compile2()\fP has an additional argument,
501  \fIerrorcodeptr\fP, via which a numerical error code can be returned.  \fIerrorcodeptr\fP, via which a numerical error code can be returned. To avoid
502    too much repetition, we refer just to \fBpcre_compile()\fP below, but the
503    information applies equally to \fBpcre_compile2()\fP.
504  .P  .P
505  The pattern is a C string terminated by a binary zero, and is passed in the  The pattern is a C string terminated by a binary zero, and is passed in the
506  \fIpattern\fP argument. A pointer to a single block of memory that is obtained  \fIpattern\fP argument. A pointer to a single block of memory that is obtained
# Line 402  argument, which is an address (see below Line 516  argument, which is an address (see below
516  .P  .P
517  The \fIoptions\fP argument contains various bit settings that affect the  The \fIoptions\fP argument contains various bit settings that affect the
518  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
519  options are described below. Some of them, in particular, those that are  options are described below. Some of them (in particular, those that are
520  compatible with Perl, can also be set and unset from within the pattern (see  compatible with Perl, but some others as well) can also be set and unset from
521  the detailed description in the  within the pattern (see the detailed description in the
522  .\" HREF  .\" HREF
523  \fBpcrepattern\fP  \fBpcrepattern\fP
524  .\"  .\"
525  documentation). For these options, the contents of the \fIoptions\fP argument  documentation). For those options that can be different in different parts of
526  specifies their initial settings at the start of compilation and execution. The  the pattern, the contents of the \fIoptions\fP argument specifies their
527  PCRE_ANCHORED and PCRE_NEWLINE_\fIxxx\fP options can be set at the time of  settings at the start of compilation and execution. The PCRE_ANCHORED,
528  matching as well as at compile time.  PCRE_BSR_\fIxxx\fP, PCRE_NEWLINE_\fIxxx\fP, PCRE_NO_UTF8_CHECK, and
529    PCRE_NO_START_OPT options can be set at the time of matching as well as at
530    compile time.
531  .P  .P
532  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
533  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
534  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
535  error message. This is a static string that is part of the library. You must  error message. This is a static string that is part of the library. You must
536  not try to free it. The offset from the start of the pattern to the character  not try to free it. Normally, the offset from the start of the pattern to the
537  where the error was discovered is placed in the variable pointed to by  byte that was being processed when the error was discovered is placed in the
538  \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.  variable pointed to by \fIerroffset\fP, which must not be NULL (if it is, an
539    immediate error is given). However, for an invalid UTF-8 string, the offset is
540    that of the first byte of the failing character.
541    .P
542    Some errors are not detected until the whole pattern has been scanned; in these
543    cases, the offset passed back is the length of the pattern. Note that the
544    offset is in bytes, not characters, even in UTF-8 mode. It may sometimes point
545    into the middle of a UTF-8 character.
546  .P  .P
547  If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the  If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the
548  \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is  \fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is
# Line 466  facility, see the Line 589  facility, see the
589  .\"  .\"
590  documentation.  documentation.
591  .sp  .sp
592      PCRE_BSR_ANYCRLF
593      PCRE_BSR_UNICODE
594    .sp
595    These options (which are mutually exclusive) control what the \eR escape
596    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
597    match any Unicode newline sequence. The default is specified when PCRE is
598    built. It can be overridden from within the pattern, or by setting an option
599    when a compiled pattern is matched.
600    .sp
601    PCRE_CASELESS    PCRE_CASELESS
602  .sp  .sp
603  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
# Line 489  pattern. Line 621  pattern.
621  .sp  .sp
622    PCRE_DOTALL    PCRE_DOTALL
623  .sp  .sp
624  If this bit is set, a dot metacharater in the pattern matches all characters,  If this bit is set, a dot metacharacter in the pattern matches a character of
625  including those that indicate newline. Without it, a dot does not match when  any value, including one that indicates a newline. However, it only ever
626  the current position is at a newline. This option is equivalent to Perl's /s  matches one character, even if newlines are coded as CRLF. Without this option,
627  option, and it can be changed within a pattern by a (?s) option setting. A  a dot does not match when the current position is at a newline. This option is
628  negative class such as [^a] always matches newline characters, independent of  equivalent to Perl's /s option, and it can be changed within a pattern by a
629  the setting of this option.  (?s) option setting. A negative class such as [^a] always matches newline
630    characters, independent of the setting of this option.
631  .sp  .sp
632    PCRE_DUPNAMES    PCRE_DUPNAMES
633  .sp  .sp
# Line 516  unescaped # outside a character class an Line 649  unescaped # outside a character class an
649  ignored. This is equivalent to Perl's /x option, and it can be changed within a  ignored. This is equivalent to Perl's /x option, and it can be changed within a
650  pattern by a (?x) option setting.  pattern by a (?x) option setting.
651  .P  .P
652    Which characters are interpreted as newlines is controlled by the options
653    passed to \fBpcre_compile()\fP or by a special sequence at the start of the
654    pattern, as described in the section entitled
655    .\" HTML <a href="pcrepattern.html#newlines">
656    .\" </a>
657    "Newline conventions"
658    .\"
659    in the \fBpcrepattern\fP documentation. Note that the end of this type of
660    comment is a literal newline sequence in the pattern; escape sequences that
661    happen to represent a newline do not count.
662    .P
663  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
664  Note, however, that this applies only to data characters. Whitespace characters  Note, however, that this applies only to data characters. Whitespace characters
665  may never appear within special character sequences in a pattern, for example  may never appear within special character sequences in a pattern, for example
666  within the sequence (?( which introduces a conditional subpattern.  within the sequence (?( that introduces a conditional subpattern.
667  .sp  .sp
668    PCRE_EXTRA    PCRE_EXTRA
669  .sp  .sp
# Line 529  set, any backslash in a pattern that is Line 673  set, any backslash in a pattern that is
673  special meaning causes an error, thus reserving these combinations for future  special meaning causes an error, thus reserving these combinations for future
674  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
675  special meaning is treated as a literal. (Perl can, however, be persuaded to  special meaning is treated as a literal. (Perl can, however, be persuaded to
676  give a warning for this.) There are at present no other features controlled by  give an error for this, by running it with the -w option.) There are at present
677  this option. It can also be set by a (?X) option setting within a pattern.  no other features controlled by this option. It can also be set by a (?X)
678    option setting within a pattern.
679  .sp  .sp
680    PCRE_FIRSTLINE    PCRE_FIRSTLINE
681  .sp  .sp
# Line 538  If this option is set, an unanchored pat Line 683  If this option is set, an unanchored pat
683  the first newline in the subject string, though the matched text may continue  the first newline in the subject string, though the matched text may continue
684  over the newline.  over the newline.
685  .sp  .sp
686      PCRE_JAVASCRIPT_COMPAT
687    .sp
688    If this option is set, PCRE's behaviour is changed in some ways so that it is
689    compatible with JavaScript rather than Perl. The changes are as follows:
690    .P
691    (1) A lone closing square bracket in a pattern causes a compile-time error,
692    because this is illegal in JavaScript (by default it is treated as a data
693    character). Thus, the pattern AB]CD becomes illegal when this option is set.
694    .P
695    (2) At run time, a back reference to an unset subpattern group matches an empty
696    string (by default this causes the current matching alternative to fail). A
697    pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
698    an "a" in the subject), whereas it fails by default, for Perl compatibility.
699    .P
700    (3) \eU matches an upper case "U" character; by default \eU causes a compile
701    time error (Perl uses \eU to upper case subsequent characters).
702    .P
703    (4) \eu matches a lower case "u" character unless it is followed by four
704    hexadecimal digits, in which case the hexadecimal number defines the code point
705    to match. By default, \eu causes a compile time error (Perl uses it to upper
706    case the following character).
707    .P
708    (5) \ex matches a lower case "x" character unless it is followed by two
709    hexadecimal digits, in which case the hexadecimal number defines the code point
710    to match. By default, as in Perl, a hexadecimal number is always expected after
711    \ex, but it may have zero, one, or two digits (so, for example, \exz matches a
712    binary zero character followed by z).
713    .sp
714    PCRE_MULTILINE    PCRE_MULTILINE
715  .sp  .sp
716  By default, PCRE treats the subject string as consisting of a single line of  By default, PCRE treats the subject string as consisting of a single line of
# Line 557  occurrences of ^ or $ in a pattern, sett Line 730  occurrences of ^ or $ in a pattern, sett
730    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
731    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
732    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
733      PCRE_NEWLINE_ANYCRLF
734    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
735  .sp  .sp
736  These options override the default newline definition that was chosen when PCRE  These options override the default newline definition that was chosen when PCRE
737  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
738  indicated by a single character (CR or LF, respectively). Setting  indicated by a single character (CR or LF, respectively). Setting
739  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
740  CRLF sequence. Setting PCRE_NEWLINE_ANY specifies that any Unicode newline  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
741  sequence should be recognized. The Unicode newline sequences are the three just  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
742  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,  that any Unicode newline sequence should be recognized. The Unicode newline
743  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
744  (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
745    separator, U+2028), and PS (paragraph separator, U+2029). For the 8-bit
746    library, the last two are recognized only in UTF-8 mode.
747  .P  .P
748  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
749  as a number, giving eight possibilities. Currently only five are used (default  as a number, giving eight possibilities. Currently only six are used (default
750  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
751  option, the combination may or may not be sensible. For example,  option, the combination may or may not be sensible. For example,
752  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
753  other combinations yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
754  .P  .P
755  The only time that a line break is specially recognized when compiling a  The only time that a line break in a pattern is specially recognized when
756  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character  compiling is when PCRE_EXTENDED is set. CR and LF are whitespace characters,
757  class is encountered. This indicates a comment that lasts until after the next  and so are ignored in this mode. Also, an unescaped # outside a character class
758  line break sequence. In other circumstances, line break sequences are treated  indicates a comment that lasts until after the next line break sequence. In
759  as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated  other circumstances, line break sequences in patterns are treated as literal
760  as whitespace characters and are therefore ignored.  data.
761  .P  .P
762  The newline option that is set at compile time becomes the default that is used  The newline option that is set at compile time becomes the default that is used
763  for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.  for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
# Line 594  were followed by ?: but named parenthese Line 770  were followed by ?: but named parenthese
770  they acquire numbers in the usual way). There is no equivalent of this option  they acquire numbers in the usual way). There is no equivalent of this option
771  in Perl.  in Perl.
772  .sp  .sp
773      NO_START_OPTIMIZE
774    .sp
775    This is an option that acts at matching time; that is, it is really an option
776    for \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. If it is set at compile time,
777    it is remembered with the compiled pattern and assumed at matching time. For
778    details see the discussion of PCRE_NO_START_OPTIMIZE
779    .\" HTML <a href="#execoptions">
780    .\" </a>
781    below.
782    .\"
783    .sp
784      PCRE_UCP
785    .sp
786    This option changes the way PCRE processes \eB, \eb, \eD, \ed, \eS, \es, \eW,
787    \ew, and some of the POSIX character classes. By default, only ASCII characters
788    are recognized, but if PCRE_UCP is set, Unicode properties are used instead to
789    classify characters. More details are given in the section on
790    .\" HTML <a href="pcre.html#genericchartypes">
791    .\" </a>
792    generic character types
793    .\"
794    in the
795    .\" HREF
796    \fBpcrepattern\fP
797    .\"
798    page. If you set PCRE_UCP, matching one of the items it affects takes much
799    longer. The option is available only if PCRE has been compiled with Unicode
800    property support.
801    .sp
802    PCRE_UNGREEDY    PCRE_UNGREEDY
803  .sp  .sp
804  This option inverts the "greediness" of the quantifiers so that they are not  This option inverts the "greediness" of the quantifiers so that they are not
# Line 603  with Perl. It can also be set by a (?U) Line 808  with Perl. It can also be set by a (?U)
808    PCRE_UTF8    PCRE_UTF8
809  .sp  .sp
810  This option causes PCRE to regard both the pattern and the subject as strings  This option causes PCRE to regard both the pattern and the subject as strings
811  of UTF-8 characters instead of single-byte character strings. However, it is  of UTF-8 characters instead of single-byte strings. However, it is available
812  available only when PCRE is built to include UTF-8 support. If not, the use  only when PCRE is built to include UTF support. If not, the use of this option
813  of this option provokes an error. Details of how this option changes the  provokes an error. Details of how this option changes the behaviour of PCRE are
814  behaviour of PCRE are given in the  given in the
 .\" HTML <a href="pcre.html#utf8support">  
 .\" </a>  
 section on UTF-8 support  
 .\"  
 in the main  
815  .\" HREF  .\" HREF
816  \fBpcre\fP  \fBpcreunicode\fP
817  .\"  .\"
818  page.  page.
819  .sp  .sp
820    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
821  .sp  .sp
822  When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is  When PCRE_UTF8 is set, the validity of the pattern as a UTF-8
823  automatically checked. If an invalid UTF-8 sequence of bytes is found,  string is automatically checked. There is a discussion about the
824  \fBpcre_compile()\fP returns an error. If you already know that your pattern is  .\" HTML <a href="pcreunicode.html#utf8strings">
825  valid, and you want to skip this check for performance reasons, you can set the  .\" </a>
826  PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid  validity of UTF-8 strings
827  UTF-8 string as a pattern is undefined. It may cause your program to crash.  .\"
828  Note that this option can also be passed to \fBpcre_exec()\fP and  in the
829  \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject  .\" HREF
830  strings.  \fBpcreunicode\fP
831    .\"
832    page. If an invalid UTF-8 sequence is found, \fBpcre_compile()\fP returns an
833    error. If you already know that your pattern is valid, and you want to skip
834    this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option.
835    When it is set, the effect of passing an invalid UTF-8 string as a pattern is
836    undefined. It may cause your program to crash. Note that this option can also
837    be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress the
838    validity checking of subject strings.
839  .  .
840  .  .
841  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 635  strings. Line 843  strings.
843  .sp  .sp
844  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
845  \fBpcre_compile2()\fP, along with the error messages that may be returned by  \fBpcre_compile2()\fP, along with the error messages that may be returned by
846  both compiling functions. As PCRE has developed, some error codes have fallen  both compiling functions. Note that error messages are always 8-bit ASCII
847  out of use. To avoid confusion, they have not been re-used.  strings, even in 16-bit mode. As PCRE has developed, some error codes have
848    fallen out of use. To avoid confusion, they have not been re-used.
849  .sp  .sp
850     0  no error     0  no error
851     1  \e at end of pattern     1  \e at end of pattern
# Line 650  out of use. To avoid confusion, they hav Line 859  out of use. To avoid confusion, they hav
859     9  nothing to repeat     9  nothing to repeat
860    10  [this code is not in use]    10  [this code is not in use]
861    11  internal error: unexpected repeat    11  internal error: unexpected repeat
862    12  unrecognized character after (?    12  unrecognized character after (? or (?-
863    13  POSIX named classes are supported only within a class    13  POSIX named classes are supported only within a class
864    14  missing )    14  missing )
865    15  reference to non-existent subpattern    15  reference to non-existent subpattern
# Line 658  out of use. To avoid confusion, they hav Line 867  out of use. To avoid confusion, they hav
867    17  unknown option bit(s) set    17  unknown option bit(s) set
868    18  missing ) after comment    18  missing ) after comment
869    19  [this code is not in use]    19  [this code is not in use]
870    20  regular expression too large    20  regular expression is too large
871    21  failed to get memory    21  failed to get memory
872    22  unmatched parentheses    22  unmatched parentheses
873    23  internal error: code overflow    23  internal error: code overflow
# Line 667  out of use. To avoid confusion, they hav Line 876  out of use. To avoid confusion, they hav
876    26  malformed number or name after (?(    26  malformed number or name after (?(
877    27  conditional group contains more than two branches    27  conditional group contains more than two branches
878    28  assertion expected after (?(    28  assertion expected after (?(
879    29  (?R or (?digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
880    30  unknown POSIX class name    30  unknown POSIX class name
881    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
882    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is compiled without UTF support
883    33  [this code is not in use]    33  [this code is not in use]
884    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
885    35  invalid condition (?(0)    35  invalid condition (?(0)
886    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
887    37  PCRE does not support \eL, \el, \eN, \eU, or \eu    37  PCRE does not support \eL, \el, \eN{name}, \eU, or \eu
888    38  number after (?C is > 255    38  number after (?C is > 255
889    39  closing ) for (?C expected    39  closing ) for (?C expected
890    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
891    41  unrecognized character after (?P    41  unrecognized character after (?P
892    42  syntax error in subpattern name (missing terminator)    42  syntax error in subpattern name (missing terminator)
893    43  two named subpatterns have the same name    43  two named subpatterns have the same name
894    44  invalid UTF-8 string    44  invalid UTF-8 string (specifically UTF-8)
895    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
896    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
897    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
898    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
899    49  too many named subpatterns (maximum 10,000)    49  too many named subpatterns (maximum 10000)
900    50  repeated subpattern is too long    50  [this code is not in use]
901    51  octal value is greater than \e377 (not in UTF-8 mode)    51  octal value is greater than \e377 in 8-bit non-UTF-8 mode
902    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
903    53  internal error: previously-checked referenced subpattern not found    53  internal error: previously-checked referenced subpattern
904            not found
905    54  DEFINE group contains more than one branch    54  DEFINE group contains more than one branch
906    55  repeating a DEFINE group is not allowed    55  repeating a DEFINE group is not allowed
907    56  inconsistent NEWLINE options"    56  inconsistent NEWLINE options
908      57  \eg is not followed by a braced, angle-bracketed, or quoted
909            name/number or by a plain number
910      58  a numbered reference must not be zero
911      59  an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
912      60  (*VERB) not recognized
913      61  number is too big
914      62  subpattern name expected
915      63  digit expected after (?+
916      64  ] is an invalid data character in JavaScript compatibility mode
917      65  different names for subpatterns of the same number are
918            not allowed
919      66  (*MARK) must have an argument
920      67  this version of PCRE is not compiled with Unicode property
921            support
922      68  \ec must be followed by an ASCII character
923      69  \ek is not followed by a braced, angle-bracketed, or quoted name
924      70  internal error: unknown opcode in find_fixedlength()
925      71  \eN is not supported in a class
926      72  too many forward references
927      73  disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
928      74  invalid UTF-16 string (specifically UTF-16)
929    .sp
930    The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
931    be used if the limits were changed when PCRE was built.
932  .  .
933  .  .
934    .\" HTML <a name="studyingapattern"></a>
935  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
936  .rs  .rs
937  .sp  .sp
# Line 713  help speed up matching, \fBpcre_study()\ Line 948  help speed up matching, \fBpcre_study()\
948  results of the study.  results of the study.
949  .P  .P
950  The returned value from \fBpcre_study()\fP can be passed directly to  The returned value from \fBpcre_study()\fP can be passed directly to
951  \fBpcre_exec()\fP. However, a \fBpcre_extra\fP block also contains other  \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. However, a \fBpcre_extra\fP block
952  fields that can be set by the caller before the block is passed; these are  also contains other fields that can be set by the caller before the block is
953  described  passed; these are described
954  .\" HTML <a href="#extradata">  .\" HTML <a href="#extradata">
955  .\" </a>  .\" </a>
956  below  below
957  .\"  .\"
958  in the section on matching a pattern.  in the section on matching a pattern.
959  .P  .P
960  If studying the pattern does not produce any additional information  If studying the pattern does not produce any useful information,
961  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program
962  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 or
963  own \fBpcre_extra\fP block.  \fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block.
964  .P  .P
965  The second argument of \fBpcre_study()\fP contains option bits. At present, no  The second argument of \fBpcre_study()\fP contains option bits. There are three
966  options are defined, and this argument should always be zero.  options:
967    .sp
968      PCRE_STUDY_JIT_COMPILE
969      PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE
970      PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE
971    .sp
972    If any of these are set, and the just-in-time compiler is available, the
973    pattern is further compiled into machine code that executes much faster than
974    the \fBpcre_exec()\fP interpretive matching function. If the just-in-time
975    compiler is not available, these options are ignored. All other bits in the
976    \fIoptions\fP argument must be zero.
977    .P
978    JIT compilation is a heavyweight optimization. It can take some time for
979    patterns to be analyzed, and for one-off matches and simple patterns the
980    benefit of faster execution might be offset by a much slower study time.
981    Not all patterns can be optimized by the JIT compiler. For those that cannot be
982    handled, matching automatically falls back to the \fBpcre_exec()\fP
983    interpreter. For more details, see the
984    .\" HREF
985    \fBpcrejit\fP
986    .\"
987    documentation.
988  .P  .P
989  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
990  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
# Line 737  static string that is part of the librar Line 993  static string that is part of the librar
993  should test the error pointer for NULL after calling \fBpcre_study()\fP, to be  should test the error pointer for NULL after calling \fBpcre_study()\fP, to be
994  sure that it has run successfully.  sure that it has run successfully.
995  .P  .P
996  This is a typical call to \fBpcre_study\fP():  When you are finished with a pattern, you can free the memory used for the
997    study data by calling \fBpcre_free_study()\fP. This function was added to the
998    API for release 8.20. For earlier versions, the memory could be freed with
999    \fBpcre_free()\fP, just like the pattern itself. This will still work in cases
1000    where JIT optimization is not used, but it is advisable to change to the new
1001    function when convenient.
1002    .P
1003    This is a typical way in which \fBpcre_study\fP() is used (except that in a
1004    real application there should be tests for errors):
1005  .sp  .sp
1006    pcre_extra *pe;    int rc;
1007    pe = pcre_study(    pcre *re;
1008      pcre_extra *sd;
1009      re = pcre_compile("pattern", 0, &error, &erroroffset, NULL);
1010      sd = pcre_study(
1011      re,             /* result of pcre_compile() */      re,             /* result of pcre_compile() */
1012      0,              /* no options exist */      0,              /* no options */
1013      &error);        /* set to NULL or points to a message */      &error);        /* set to NULL or points to a message */
1014  .sp    rc = pcre_exec(   /* see below for details of pcre_exec() options */
1015  At present, studying a pattern is useful only for non-anchored patterns that do      re, sd, "subject", 7, 0, 0, ovector, 30);
1016  not have a single fixed starting character. A bitmap of possible starting    ...
1017  bytes is created.    pcre_free_study(sd);
1018      pcre_free(re);
1019    .sp
1020    Studying a pattern does two things: first, a lower bound for the length of
1021    subject string that is needed to match the pattern is computed. This does not
1022    mean that there are any strings of that length that match, but it does
1023    guarantee that no shorter strings match. The value is used by
1024    \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP to avoid wasting time by trying to
1025    match strings that are shorter than the lower bound. You can find out the value
1026    in a calling program via the \fBpcre_fullinfo()\fP function.
1027    .P
1028    Studying a pattern is also useful for non-anchored patterns that do not have a
1029    single fixed starting character. A bitmap of possible starting bytes is
1030    created. This speeds up finding a position in the subject at which to start
1031    matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.)
1032    .P
1033    These two optimizations apply to both \fBpcre_exec()\fP and
1034    \fBpcre_dfa_exec()\fP, and the information is also used by the JIT compiler.
1035    The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option
1036    when calling \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP, but if this is done,
1037    JIT execution is also disabled. You might want to do this if your pattern
1038    contains callouts or (*MARK) and you want to make use of these facilities in
1039    cases where matching fails. See the discussion of PCRE_NO_START_OPTIMIZE
1040    .\" HTML <a href="#execoptions">
1041    .\" </a>
1042    below.
1043    .\"
1044  .  .
1045  .  .
1046  .\" HTML <a name="localesupport"></a>  .\" HTML <a name="localesupport"></a>
1047  .SH "LOCALE SUPPORT"  .SH "LOCALE SUPPORT"
1048  .rs  .rs
1049  .sp  .sp
1050  PCRE handles caseless matching, and determines whether characters are letters  PCRE handles caseless matching, and determines whether characters are letters,
1051  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
1052  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
1053  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but  with codes less than 128. By default, higher-valued codes never match escapes
1054  can be tested with \ep if PCRE is built with Unicode character property  such as \ew or \ed, but they can be tested with \ep if PCRE is built with
1055  support. The use of locales with Unicode is discouraged.  Unicode character property support. Alternatively, the PCRE_UCP option can be
1056  .P  set at compile time; this causes \ew and friends to use Unicode property
1057  An internal set of tables is created in the default C locale when PCRE is  support instead of built-in tables. The use of locales with Unicode is
1058  built. This is used when the final argument of \fBpcre_compile()\fP is NULL,  discouraged. If you are handling characters with codes greater than 128, you
1059  and is sufficient for many applications. An alternative set of tables can,  should either use UTF-8 and Unicode, or use locales, but not try to mix the
1060  however, be supplied. These may be created in a different locale from the  two.
1061  default. As more and more applications change to using Unicode, the need for  .P
1062  this locale support is expected to die away.  PCRE contains an internal set of tables that are used when the final argument
1063    of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
1064    Normally, the internal tables recognize only ASCII characters. However, when
1065    PCRE is built, it is possible to cause the internal tables to be rebuilt in the
1066    default "C" locale of the local system, which may cause them to be different.
1067    .P
1068    The internal tables can always be overridden by tables supplied by the
1069    application that calls PCRE. These may be created in a different locale from
1070    the default. As more and more applications change to using Unicode, the need
1071    for this locale support is expected to die away.
1072  .P  .P
1073  External tables are built by calling the \fBpcre_maketables()\fP function,  External tables are built by calling the \fBpcre_maketables()\fP function,
1074  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 1081  the following code could be used:
1081    tables = pcre_maketables();    tables = pcre_maketables();
1082    re = pcre_compile(..., tables);    re = pcre_compile(..., tables);
1083  .sp  .sp
1084    The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
1085    are using Windows, the name for the French locale is "french".
1086    .P
1087  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
1088  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
1089  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 797  one in which it was compiled. Passing ta Line 1102  one in which it was compiled. Passing ta
1102  below in the section on matching a pattern.  below in the section on matching a pattern.
1103  .  .
1104  .  .
1105    .\" HTML <a name="infoaboutpattern"></a>
1106  .SH "INFORMATION ABOUT A PATTERN"  .SH "INFORMATION ABOUT A PATTERN"
1107  .rs  .rs
1108  .sp  .sp
# Line 805  below in the section on matching a patte Line 1111  below in the section on matching a patte
1111  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
1112  .PP  .PP
1113  The \fBpcre_fullinfo()\fP function returns information about a compiled  The \fBpcre_fullinfo()\fP function returns information about a compiled
1114  pattern. It replaces the obsolete \fBpcre_info()\fP function, which is  pattern. It replaces the \fBpcre_info()\fP function, which was removed from the
1115  nevertheless retained for backwards compability (and is documented below).  library at version 8.30, after more than 10 years of obsolescence.
1116  .P  .P
1117  The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled  The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled
1118  pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if  pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if
# Line 815  information is required, and the fourth Line 1121  information is required, and the fourth
1121  to receive the data. The yield of the function is zero for success, or one of  to receive the data. The yield of the function is zero for success, or one of
1122  the following negative numbers:  the following negative numbers:
1123  .sp  .sp
1124    PCRE_ERROR_NULL       the argument \fIcode\fP was NULL    PCRE_ERROR_NULL           the argument \fIcode\fP was NULL
1125                          the argument \fIwhere\fP was NULL                              the argument \fIwhere\fP was NULL
1126    PCRE_ERROR_BADMAGIC   the "magic number" was not found    PCRE_ERROR_BADMAGIC       the "magic number" was not found
1127    PCRE_ERROR_BADOPTION  the value of \fIwhat\fP was invalid    PCRE_ERROR_BADENDIANNESS  the pattern was compiled with different
1128                                endianness
1129      PCRE_ERROR_BADOPTION      the value of \fIwhat\fP was invalid
1130  .sp  .sp
1131  The "magic number" is placed at the start of each compiled pattern as an simple  The "magic number" is placed at the start of each compiled pattern as an simple
1132  check against passing an arbitrary memory pointer. Here is a typical call of  check against passing an arbitrary memory pointer. The endianness error can
1133  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:  occur if a compiled pattern is saved and reloaded on a different host. Here is
1134    a typical call of \fBpcre_fullinfo()\fP, to obtain the length of the compiled
1135    pattern:
1136  .sp  .sp
1137    int rc;    int rc;
1138    size_t length;    size_t length;
1139    rc = pcre_fullinfo(    rc = pcre_fullinfo(
1140      re,               /* result of pcre_compile() */      re,               /* result of pcre_compile() */
1141      pe,               /* result of pcre_study(), or NULL */      sd,               /* result of pcre_study(), or NULL */
1142      PCRE_INFO_SIZE,   /* what is required */      PCRE_INFO_SIZE,   /* what is required */
1143      &length);         /* where to put the data */      &length);         /* where to put the data */
1144  .sp  .sp
# Line 856  a NULL table pointer. Line 1166  a NULL table pointer.
1166  .sp  .sp
1167    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
1168  .sp  .sp
1169  Return information about the first byte of any matched string, for a  Return information about the first data unit of any matched string, for a
1170  non-anchored pattern. The fourth argument should point to an \fBint\fP  non-anchored pattern. (The name of this option refers to the 8-bit library,
1171  variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is  where data units are bytes.) The fourth argument should point to an \fBint\fP
1172  still recognized for backwards compatibility.)  variable.
1173    .P
1174    If there is a fixed first value, for example, the letter "c" from a pattern
1175    such as (cat|cow|coyote), its value is returned. In the 8-bit library, the
1176    value is always less than 256; in the 16-bit library the value can be up to
1177    0xffff.
1178  .P  .P
1179  If there is a fixed first byte, for example, from a pattern such as  If there is no fixed first value, and if either
 (cat|cow|coyote), its value is returned. Otherwise, if either  
1180  .sp  .sp
1181  (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
1182  starts with "^", or  starts with "^", or
# Line 877  returned. For anchored patterns, -2 is r Line 1191  returned. For anchored patterns, -2 is r
1191    PCRE_INFO_FIRSTTABLE    PCRE_INFO_FIRSTTABLE
1192  .sp  .sp
1193  If the pattern was studied, and this resulted in the construction of a 256-bit  If the pattern was studied, and this resulted in the construction of a 256-bit
1194  table indicating a fixed set of bytes for the first byte in any matching  table indicating a fixed set of values for the first data unit in any matching
1195  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
1196  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
1197  .sp  .sp
1198      PCRE_INFO_HASCRORLF
1199    .sp
1200    Return 1 if the pattern contains any explicit matches for CR or LF characters,
1201    otherwise 0. The fourth argument should point to an \fBint\fP variable. An
1202    explicit match is either a literal CR or LF character, or \er or \en.
1203    .sp
1204      PCRE_INFO_JCHANGED
1205    .sp
1206    Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
1207    0. The fourth argument should point to an \fBint\fP variable. (?J) and
1208    (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
1209    .sp
1210      PCRE_INFO_JIT
1211    .sp
1212    Return 1 if the pattern was studied with one of the JIT options, and
1213    just-in-time compiling was successful. The fourth argument should point to an
1214    \fBint\fP variable. A return value of 0 means that JIT support is not available
1215    in this version of PCRE, or that the pattern was not studied with a JIT option,
1216    or that the JIT compiler could not handle this particular pattern. See the
1217    .\" HREF
1218    \fBpcrejit\fP
1219    .\"
1220    documentation for details of what can and cannot be handled.
1221    .sp
1222      PCRE_INFO_JITSIZE
1223    .sp
1224    If the pattern was successfully studied with a JIT option, return the size of
1225    the JIT compiled code, otherwise return zero. The fourth argument should point
1226    to a \fBsize_t\fP variable.
1227    .sp
1228    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
1229  .sp  .sp
1230  Return the value of the rightmost literal byte that must exist in any matched  Return the value of the rightmost literal data unit that must exist in any
1231  string, other than at its start, if such a byte has been recorded. The fourth  matched string, other than at its start, if such a value has been recorded. The
1232  argument should point to an \fBint\fP variable. If there is no such byte, -1 is  fourth argument should point to an \fBint\fP variable. If there is no such
1233  returned. For anchored patterns, a last literal byte is recorded only if it  value, -1 is returned. For anchored patterns, a last literal value is recorded
1234  follows something of variable length. For example, for the pattern  only if it follows something of variable length. For example, for the pattern
1235  /^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value  /^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value
1236  is -1.  is -1.
1237  .sp  .sp
1238      PCRE_INFO_MINLENGTH
1239    .sp
1240    If the pattern was studied and a minimum length for matching subject strings
1241    was computed, its value is returned. Otherwise the returned value is -1. The
1242    value is a number of characters, which in UTF-8 mode may be different from the
1243    number of bytes. The fourth argument should point to an \fBint\fP variable. A
1244    non-negative value is a lower bound to the length of any matching string. There
1245    may not be any strings of that length that do actually match, but every string
1246    that does match is at least that long.
1247    .sp
1248    PCRE_INFO_NAMECOUNT    PCRE_INFO_NAMECOUNT
1249    PCRE_INFO_NAMEENTRYSIZE    PCRE_INFO_NAMEENTRYSIZE
1250    PCRE_INFO_NAMETABLE    PCRE_INFO_NAMETABLE
# Line 909  The map consists of a number of fixed-si Line 1263  The map consists of a number of fixed-si
1263  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
1264  entry; both of these return an \fBint\fP value. The entry size depends on the  entry; both of these return an \fBint\fP value. The entry size depends on the
1265  length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first  length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
1266  entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry  entry of the table. This is a pointer to \fBchar\fP in the 8-bit library, where
1267  are the number of the capturing parenthesis, most significant byte first. The  the first two bytes of each entry are the number of the capturing parenthesis,
1268  rest of the entry is the corresponding name, zero terminated. The names are in  most significant byte first. In the 16-bit library, the pointer points to
1269  alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of  16-bit data units, the first of which contains the parenthesis number. The rest
1270  their parentheses numbers. For example, consider the following pattern (assume  of the entry is the corresponding name, zero terminated.
1271  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  .P
1272    The names are in alphabetical order. Duplicate names may appear if (?| is used
1273    to create multiple groups with the same number, as described in the
1274    .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
1275    .\" </a>
1276    section on duplicate subpattern numbers
1277    .\"
1278    in the
1279    .\" HREF
1280    \fBpcrepattern\fP
1281    .\"
1282    page. Duplicate names for subpatterns with different numbers are permitted only
1283    if PCRE_DUPNAMES is set. In all cases of duplicate names, they appear in the
1284    table in the order in which they were found in the pattern. In the absence of
1285    (?| this is the order of increasing number; when (?| is used this is not
1286    necessarily the case because later subpatterns may have lower numbers.
1287    .P
1288    As a simple example of the name/number table, consider the following pattern
1289    after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white
1290    space - including newlines - is ignored):
1291  .sp  .sp
1292  .\" JOIN  .\" JOIN
1293    (?<date> (?<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
# Line 933  When writing code to extract data from n Line 1306  When writing code to extract data from n
1306  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
1307  different for each compiled pattern.  different for each compiled pattern.
1308  .sp  .sp
1309      PCRE_INFO_OKPARTIAL
1310    .sp
1311    Return 1 if the pattern can be used for partial matching with
1312    \fBpcre_exec()\fP, otherwise 0. The fourth argument should point to an
1313    \fBint\fP variable. From release 8.00, this always returns 1, because the
1314    restrictions that previously applied to partial matching have been lifted. The
1315    .\" HREF
1316    \fBpcrepartial\fP
1317    .\"
1318    documentation gives details of partial matching.
1319    .sp
1320    PCRE_INFO_OPTIONS    PCRE_INFO_OPTIONS
1321  .sp  .sp
1322  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
1323  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
1324  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
1325  top-level option settings within the pattern itself.  top-level option settings at the start of the pattern itself. In other words,
1326    they are the options that will be in force when matching starts. For example,
1327    if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
1328    result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
1329  .P  .P
1330  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
1331  alternatives begin with one of the following:  alternatives begin with one of the following:
# Line 955  For such patterns, the PCRE_ANCHORED bit Line 1342  For such patterns, the PCRE_ANCHORED bit
1342  .sp  .sp
1343    PCRE_INFO_SIZE    PCRE_INFO_SIZE
1344  .sp  .sp
1345  Return the size of the compiled pattern, that is, the value that was passed as  Return the size of the compiled pattern in bytes (for both libraries). The
1346  the argument to \fBpcre_malloc()\fP when PCRE was getting memory in which to  fourth argument should point to a \fBsize_t\fP variable. This value does not
1347  place the compiled data. The fourth argument should point to a \fBsize_t\fP  include the size of the \fBpcre\fP structure that is returned by
1348  variable.  \fBpcre_compile()\fP. The value that is passed as the argument to
1349    \fBpcre_malloc()\fP when \fBpcre_compile()\fP is getting memory in which to
1350    place the compiled data is the value returned by this option plus the size of
1351    the \fBpcre\fP structure. Studying a compiled pattern, with or without JIT,
1352    does not alter the value returned by this option.
1353  .sp  .sp
1354    PCRE_INFO_STUDYSIZE    PCRE_INFO_STUDYSIZE
1355  .sp  .sp
1356  Return the size of the data block pointed to by the \fIstudy_data\fP field in  Return the size in bytes of the data block pointed to by the \fIstudy_data\fP
1357  a \fBpcre_extra\fP block. That is, it is the value that was passed to  field in a \fBpcre_extra\fP block. If \fBpcre_extra\fP is NULL, or there is no
1358  \fBpcre_malloc()\fP when PCRE was getting memory into which to place the data  study data, zero is returned. The fourth argument should point to a
1359  created by \fBpcre_study()\fP. The fourth argument should point to a  \fBsize_t\fP variable. The \fIstudy_data\fP field is set by \fBpcre_study()\fP
1360  \fBsize_t\fP variable.  to record information that will speed up matching (see the section entitled
1361  .  .\" HTML <a href="#studyingapattern">
1362  .  .\" </a>
1363  .SH "OBSOLETE INFO FUNCTION"  "Studying a pattern"
1364  .rs  .\"
1365  .sp  above). The format of the \fIstudy_data\fP block is private, but its length
1366  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  is made available via this option so that it can be saved and restored (see the
1367  .B *\fIfirstcharptr\fP);  .\" HREF
1368  .PP  \fBpcreprecompile\fP
1369  The \fBpcre_info()\fP function is now obsolete because its interface is too  .\"
1370  restrictive to return all the available data about a compiled pattern. New  documentation for details).
 programs should use \fBpcre_fullinfo()\fP instead. The yield of  
 \fBpcre_info()\fP is the number of capturing subpatterns, or one of the  
 following negative numbers:  
 .sp  
   PCRE_ERROR_NULL       the argument \fIcode\fP was NULL  
   PCRE_ERROR_BADMAGIC   the "magic number" was not found  
 .sp  
 If the \fIoptptr\fP argument is not NULL, a copy of the options with which the  
 pattern was compiled is placed in the integer it points to (see  
 PCRE_INFO_OPTIONS above).  
 .P  
 If the pattern is not anchored and the \fIfirstcharptr\fP argument is not NULL,  
 it is used to pass back information about the first character of any matched  
 string (see PCRE_INFO_FIRSTBYTE above).  
1371  .  .
1372  .  .
1373  .SH "REFERENCE COUNTS"  .SH "REFERENCE COUNTS"
# Line 1027  is different. (This seems a highly unlik Line 1404  is different. (This seems a highly unlik
1404  .P  .P
1405  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
1406  compiled pattern, which is passed in the \fIcode\fP argument. If the  compiled pattern, which is passed in the \fIcode\fP argument. If the
1407  pattern has been studied, the result of the study should be passed in the  pattern was studied, the result of the study should be passed in the
1408  \fIextra\fP argument. This function is the main matching facility of the  \fIextra\fP argument. You can call \fBpcre_exec()\fP with the same \fIcode\fP
1409  library, and it operates in a Perl-like manner. For specialist use there is  and \fIextra\fP arguments as many times as you like, in order to match
1410  also an alternative matching function, which is described  different subject strings with the same pattern.
1411    .P
1412    This function is the main matching facility of the library, and it operates in
1413    a Perl-like manner. For specialist use there is also an alternative matching
1414    function, which is described
1415  .\" HTML <a href="#dfamatch">  .\" HTML <a href="#dfamatch">
1416  .\" </a>  .\" </a>
1417  below  below
# Line 1061  Here is an example of a simple call to \ Line 1442  Here is an example of a simple call to \
1442      ovector,        /* vector of integers for substring information */      ovector,        /* vector of integers for substring information */
1443      30);            /* number of elements (NOT size in bytes) */      30);            /* number of elements (NOT size in bytes) */
1444  .  .
1445    .
1446  .\" HTML <a name="extradata"></a>  .\" HTML <a name="extradata"></a>
1447  .SS "Extra data for \fBpcre_exec()\fR"  .SS "Extra data for \fBpcre_exec()\fR"
1448  .rs  .rs
# Line 1073  fields (not necessarily in this order): Line 1455  fields (not necessarily in this order):
1455  .sp  .sp
1456    unsigned long int \fIflags\fP;    unsigned long int \fIflags\fP;
1457    void *\fIstudy_data\fP;    void *\fIstudy_data\fP;
1458      void *\fIexecutable_jit\fP;
1459    unsigned long int \fImatch_limit\fP;    unsigned long int \fImatch_limit\fP;
1460    unsigned long int \fImatch_limit_recursion\fP;    unsigned long int \fImatch_limit_recursion\fP;
1461    void *\fIcallout_data\fP;    void *\fIcallout_data\fP;
1462    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1463      unsigned char **\fImark\fP;
1464  .sp  .sp
1465    In the 16-bit version of this structure, the \fImark\fP field has type
1466    "PCRE_UCHAR16 **".
1467    .P
1468  The \fIflags\fP field is a bitmap that specifies which of the other fields  The \fIflags\fP field is a bitmap that specifies which of the other fields
1469  are set. The flag bits are:  are set. The flag bits are:
1470  .sp  .sp
1471    PCRE_EXTRA_STUDY_DATA    PCRE_EXTRA_STUDY_DATA
1472      PCRE_EXTRA_EXECUTABLE_JIT
1473    PCRE_EXTRA_MATCH_LIMIT    PCRE_EXTRA_MATCH_LIMIT
1474    PCRE_EXTRA_MATCH_LIMIT_RECURSION    PCRE_EXTRA_MATCH_LIMIT_RECURSION
1475    PCRE_EXTRA_CALLOUT_DATA    PCRE_EXTRA_CALLOUT_DATA
1476    PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
1477      PCRE_EXTRA_MARK
1478  .sp  .sp
1479  Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the  Other flag bits should be set to zero. The \fIstudy_data\fP field and sometimes
1480  \fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with  the \fIexecutable_jit\fP field are set in the \fBpcre_extra\fP block that is
1481  the appropriate flag bit. You should not set this yourself, but you may add to  returned by \fBpcre_study()\fP, together with the appropriate flag bits. You
1482  the block by setting the other fields and their corresponding flag bits.  should not set these yourself, but you may add to the block by setting the
1483    other fields and their corresponding flag bits.
1484  .P  .P
1485  The \fImatch_limit\fP field provides a means of preventing PCRE from using up a  The \fImatch_limit\fP field provides a means of preventing PCRE from using up a
1486  vast amount of resources when running patterns that are not going to match,  vast amount of resources when running patterns that are not going to match,
1487  but which have a very large number of possibilities in their search trees. The  but which have a very large number of possibilities in their search trees. The
1488  classic example is the use of nested unlimited repeats.  classic example is a pattern that uses nested unlimited repeats.
1489  .P  .P
1490  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly  Internally, \fBpcre_exec()\fP uses a function called \fBmatch()\fP, which it
1491  (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the  calls repeatedly (sometimes recursively). The limit set by \fImatch_limit\fP is
1492  number of times this function is called during a match, which has the effect of  imposed on the number of times this function is called during a match, which
1493  limiting the amount of backtracking that can take place. For patterns that are  has the effect of limiting the amount of backtracking that can take place. For
1494  not anchored, the count restarts from zero for each position in the subject  patterns that are not anchored, the count restarts from zero for each position
1495  string.  in the subject string.
1496    .P
1497    When \fBpcre_exec()\fP is called with a pattern that was successfully studied
1498    with a JIT option, the way that the matching is executed is entirely different.
1499    However, there is still the possibility of runaway matching that goes on for a
1500    very long time, and so the \fImatch_limit\fP value is also used in this case
1501    (but in a different way) to limit how long the matching can continue.
1502  .P  .P
1503  The default value for the limit can be set when PCRE is built; the default  The default value for the limit can be set when PCRE is built; the default
1504  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
# Line 1117  limits the depth of recursion. The recur Line 1513  limits the depth of recursion. The recur
1513  total number of calls, because not all calls to \fBmatch()\fP are recursive.  total number of calls, because not all calls to \fBmatch()\fP are recursive.
1514  This limit is of use only if it is set smaller than \fImatch_limit\fP.  This limit is of use only if it is set smaller than \fImatch_limit\fP.
1515  .P  .P
1516  Limiting the recursion depth limits the amount of stack that can be used, or,  Limiting the recursion depth limits the amount of machine stack that can be
1517  when PCRE has been compiled to use memory on the heap instead of the stack, the  used, or, when PCRE has been compiled to use memory on the heap instead of the
1518  amount of heap memory that can be used.  stack, the amount of heap memory that can be used. This limit is not relevant,
1519    and is ignored, when matching is done using JIT compiled code.
1520  .P  .P
1521  The default value for \fImatch_limit_recursion\fP can be set when PCRE is  The default value for \fImatch_limit_recursion\fP can be set when PCRE is
1522  built; the default default is the same value as the default for  built; the default default is the same value as the default for
# Line 1128  with a \fBpcre_extra\fP block in which \ Line 1525  with a \fBpcre_extra\fP block in which \
1525  PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit  PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
1526  is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.  is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
1527  .P  .P
1528  The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,  The \fIcallout_data\fP field is used in conjunction with the "callout" feature,
1529  which is described in the  and is described in the
1530  .\" HREF  .\" HREF
1531  \fBpcrecallout\fP  \fBpcrecallout\fP
1532  .\"  .\"
# Line 1148  called. See the Line 1545  called. See the
1545  \fBpcreprecompile\fP  \fBpcreprecompile\fP
1546  .\"  .\"
1547  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1548    .P
1549    If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must
1550    be set to point to a suitable variable. If the pattern contains any
1551    backtracking control verbs such as (*MARK:NAME), and the execution ends up with
1552    a name to pass back, a pointer to the name string (zero terminated) is placed
1553    in the variable pointed to by the \fImark\fP field. The names are within the
1554    compiled pattern; if you wish to retain such a name you must copy it before
1555    freeing the memory of a compiled pattern. If there is no name to pass back, the
1556    variable pointed to by the \fImark\fP field is set to NULL. For details of the
1557    backtracking control verbs, see the section entitled
1558    .\" HTML <a href="pcrepattern#backtrackcontrol">
1559    .\" </a>
1560    "Backtracking control"
1561    .\"
1562    in the
1563    .\" HREF
1564    \fBpcrepattern\fP
1565    .\"
1566    documentation.
1567    .
1568  .  .
1569    .\" HTML <a name="execoptions"></a>
1570  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
1571  .rs  .rs
1572  .sp  .sp
1573  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
1574  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
1575  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
1576    PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and
1577    PCRE_PARTIAL_SOFT.
1578    .P
1579    If the pattern was successfully studied with one of the just-in-time (JIT)
1580    compile options, the only supported options for JIT execution are
1581    PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY,
1582    PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an
1583    unsupported option is used, JIT execution is disabled and the normal
1584    interpretive code in \fBpcre_exec()\fP is run.
1585  .sp  .sp
1586    PCRE_ANCHORED    PCRE_ANCHORED
1587  .sp  .sp
# Line 1163  matching position. If a pattern was comp Line 1590  matching position. If a pattern was comp
1590  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
1591  matching time.  matching time.
1592  .sp  .sp
1593      PCRE_BSR_ANYCRLF
1594      PCRE_BSR_UNICODE
1595    .sp
1596    These options (which are mutually exclusive) control what the \eR escape
1597    sequence matches. The choice is either to match only CR, LF, or CRLF, or to
1598    match any Unicode newline sequence. These options override the choice that was
1599    made or defaulted when the pattern was compiled.
1600    .sp
1601    PCRE_NEWLINE_CR    PCRE_NEWLINE_CR
1602    PCRE_NEWLINE_LF    PCRE_NEWLINE_LF
1603    PCRE_NEWLINE_CRLF    PCRE_NEWLINE_CRLF
1604      PCRE_NEWLINE_ANYCRLF
1605    PCRE_NEWLINE_ANY    PCRE_NEWLINE_ANY
1606  .sp  .sp
1607  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 1609  the pattern was compiled. For details, s
1609  \fBpcre_compile()\fP above. During matching, the newline choice affects the  \fBpcre_compile()\fP above. During matching, the newline choice affects the
1610  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter  behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
1611  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
1612  pattern. When PCRE_NEWLINE_CRLF or PCRE_NEWLINE_ANY is set, and a match attempt  pattern.
1613  fails when the current position is at a CRLF sequence, the match position is  .P
1614  advanced by two characters instead of one, in other words, to after the CRLF.  When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
1615    match attempt for an unanchored pattern fails when the current position is at a
1616    CRLF sequence, and the pattern contains no explicit matches for CR or LF
1617    characters, the match position is advanced by two characters instead of one, in
1618    other words, to after the CRLF.
1619    .P
1620    The above rule is a compromise that makes the most common cases work as
1621    expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
1622    set), it does not match the string "\er\enA" because, after failing at the
1623    start, it skips both the CR and the LF before retrying. However, the pattern
1624    [\er\en]A does match that string, because it contains an explicit CR or LF
1625    reference, and so advances only by one character after the first failure.
1626    .P
1627    An explicit match for CR of LF is either a literal appearance of one of those
1628    characters, or one of the \er or \en escape sequences. Implicit matches such as
1629    [^X] do not count, nor does \es (which includes CR and LF in the characters
1630    that it matches).
1631    .P
1632    Notwithstanding the above, anomalous effects may still occur when CRLF is a
1633    valid newline sequence and explicit \er or \en escapes appear in the pattern.
1634  .sp  .sp
1635    PCRE_NOTBOL    PCRE_NOTBOL
1636  .sp  .sp
# Line 1201  match the empty string, the entire match Line 1656  match the empty string, the entire match
1656  .sp  .sp
1657    a?b?    a?b?
1658  .sp  .sp
1659  is applied to a string not beginning with "a" or "b", it matches the empty  is applied to a string not beginning with "a" or "b", it matches an empty
1660  string at the start of the subject. With PCRE_NOTEMPTY set, this match is not  string at the start of the subject. With PCRE_NOTEMPTY set, this match is not
1661  valid, so PCRE searches further into the string for occurrences of "a" or "b".  valid, so PCRE searches further into the string for occurrences of "a" or "b".
1662  .P  .sp
1663  Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case    PCRE_NOTEMPTY_ATSTART
1664  of a pattern match of the empty string within its \fBsplit()\fP function, and  .sp
1665  when using the /g modifier. It is possible to emulate Perl's behaviour after  This is like PCRE_NOTEMPTY, except that an empty string match that is not at
1666  matching a null string by first trying the match again at the same offset with  the start of the subject is permitted. If the pattern is anchored, such a match
1667  PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the  can occur only if the pattern contains \eK.
1668  starting offset (see below) and trying an ordinary match again. There is some  .P
1669  code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.  Perl has no direct equivalent of PCRE_NOTEMPTY or PCRE_NOTEMPTY_ATSTART, but it
1670    does make a special case of a pattern match of the empty string within its
1671    \fBsplit()\fP function, and when using the /g modifier. It is possible to
1672    emulate Perl's behaviour after matching a null string by first trying the match
1673    again at the same offset with PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED, and then
1674    if that fails, by advancing the starting offset (see below) and trying an
1675    ordinary match again. There is some code that demonstrates how to do this in
1676    the
1677    .\" HREF
1678    \fBpcredemo\fP
1679    .\"
1680    sample program. In the most general case, you have to check to see if the
1681    newline convention recognizes CRLF as a newline, and if so, and the current
1682    character is CR followed by LF, advance the starting offset by two characters
1683    instead of one.
1684    .sp
1685      PCRE_NO_START_OPTIMIZE
1686    .sp
1687    There are a number of optimizations that \fBpcre_exec()\fP uses at the start of
1688    a match, in order to speed up the process. For example, if it is known that an
1689    unanchored match must start with a specific character, it searches the subject
1690    for that character, and fails immediately if it cannot find it, without
1691    actually running the main matching function. This means that a special item
1692    such as (*COMMIT) at the start of a pattern is not considered until after a
1693    suitable starting point for the match has been found. When callouts or (*MARK)
1694    items are in use, these "start-up" optimizations can cause them to be skipped
1695    if the pattern is never actually used. The start-up optimizations are in effect
1696    a pre-scan of the subject that takes place before the pattern is run.
1697    .P
1698    The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly
1699    causing performance to suffer, but ensuring that in cases where the result is
1700    "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)
1701    are considered at every possible starting position in the subject string. If
1702    PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching
1703    time. The use of PCRE_NO_START_OPTIMIZE disables JIT execution; when it is set,
1704    matching is always done using interpretively.
1705    .P
1706    Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.
1707    Consider the pattern
1708    .sp
1709      (*COMMIT)ABC
1710    .sp
1711    When this is compiled, PCRE records the fact that a match must start with the
1712    character "A". Suppose the subject string is "DEFABC". The start-up
1713    optimization scans along the subject, finds "A" and runs the first match
1714    attempt from there. The (*COMMIT) item means that the pattern must match the
1715    current starting position, which in this case, it does. However, if the same
1716    match is run with PCRE_NO_START_OPTIMIZE set, the initial scan along the
1717    subject string does not happen. The first match attempt is run starting from
1718    "D" and when this fails, (*COMMIT) prevents any further matches being tried, so
1719    the overall result is "no match". If the pattern is studied, more start-up
1720    optimizations may be used. For example, a minimum length for the subject may be
1721    recorded. Consider the pattern
1722    .sp
1723      (*MARK:A)(X|Y)
1724    .sp
1725    The minimum length for a match is one character. If the subject is "ABC", there
1726    will be attempts to match "ABC", "BC", "C", and then finally an empty string.
1727    If the pattern is studied, the final attempt does not take place, because PCRE
1728    knows that the subject is too short, and so the (*MARK) is never encountered.
1729    In this case, studying the pattern does not affect the overall match result,
1730    which is still "no match", but it does affect the auxiliary information that is
1731    returned.
1732  .sp  .sp
1733    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
1734  .sp  .sp
1735  When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8  When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
1736  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1737  The value of \fIstartoffset\fP is also checked to ensure that it points to the  The value of \fIstartoffset\fP is also checked to ensure that it points to the
1738  start of a UTF-8 character. If an invalid UTF-8 sequence of bytes is found,  start of a UTF-8 character. There is a discussion about the validity of UTF-8
1739  \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP  strings in the
1740  contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.  .\" HREF
1741    \fBpcreunicode\fP
1742    .\"
1743    page. If an invalid sequence of bytes is found, \fBpcre_exec()\fP returns the
1744    error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a
1745    truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both
1746    cases, information about the precise nature of the error may also be returned
1747    (see the descriptions of these errors in the section entitled \fIError return
1748    values from\fP \fBpcre_exec()\fP
1749    .\" HTML <a href="#errorlist">
1750    .\" </a>
1751    below).
1752    .\"
1753    If \fIstartoffset\fP contains a value that does not point to the start of a
1754    UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is
1755    returned.
1756  .P  .P
1757  If you already know that your subject is valid, and you want to skip these  If you already know that your subject is valid, and you want to skip these
1758  checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when  checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
1759  calling \fBpcre_exec()\fP. You might want to do this for the second and  calling \fBpcre_exec()\fP. You might want to do this for the second and
1760  subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find  subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find
1761  all the matches in a single subject string. However, you should be sure that  all the matches in a single subject string. However, you should be sure that
1762  the value of \fIstartoffset\fP points to the start of a UTF-8 character. When  the value of \fIstartoffset\fP points to the start of a character (or the end
1763  PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a  of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an
1764  subject, or a value of \fIstartoffset\fP that does not point to the start of a  invalid string as a subject or an invalid value of \fIstartoffset\fP is
1765  UTF-8 character, is undefined. Your program may crash.  undefined. Your program may crash.
1766  .sp  .sp
1767    PCRE_PARTIAL    PCRE_PARTIAL_HARD
1768  .sp    PCRE_PARTIAL_SOFT
1769  This option turns on the partial matching feature. If the subject string fails  .sp
1770  to match the pattern, but at some point during the matching process the end of  These options turn on the partial matching feature. For backwards
1771  the subject was reached (that is, the subject partially matches the pattern and  compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match
1772  the failure to match occurred only because there were not enough subject  occurs if the end of the subject string is reached successfully, but there are
1773  characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of  not enough subject characters to complete the match. If this happens when
1774  PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what  PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, matching continues by
1775  may appear in the pattern. These are discussed in the  testing any remaining alternatives. Only if no complete match can be found is
1776    PCRE_ERROR_PARTIAL returned instead of PCRE_ERROR_NOMATCH. In other words,
1777    PCRE_PARTIAL_SOFT says that the caller is prepared to handle a partial match,
1778    but only if no complete match can be found.
1779    .P
1780    If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a
1781    partial match is found, \fBpcre_exec()\fP immediately returns
1782    PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words,
1783    when PCRE_PARTIAL_HARD is set, a partial match is considered to be more
1784    important that an alternative complete match.
1785    .P
1786    In both cases, the portion of the string that was inspected when the partial
1787    match was found is set as the first matching string. There is a more detailed
1788    discussion of partial and multi-segment matching, with examples, in the
1789  .\" HREF  .\" HREF
1790  \fBpcrepartial\fP  \fBpcrepartial\fP
1791  .\"  .\"
1792  documentation.  documentation.
1793  .  .
1794    .
1795  .SS "The string to be matched by \fBpcre_exec()\fP"  .SS "The string to be matched by \fBpcre_exec()\fP"
1796  .rs  .rs
1797  .sp  .sp
1798  The subject string is passed to \fBpcre_exec()\fP as a pointer in  The subject string is passed to \fBpcre_exec()\fP as a pointer in
1799  \fIsubject\fP, a length in \fIlength\fP, and a starting byte offset in  \fIsubject\fP, a length in bytes in \fIlength\fP, and a starting byte offset
1800  \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a  in \fIstartoffset\fP. If this is negative or greater than the length of the
1801  UTF-8 character. Unlike the pattern string, the subject may contain binary zero  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting
1802  bytes. When the starting offset is zero, the search for a match starts at the  offset is zero, the search for a match starts at the beginning of the subject,
1803  beginning of the subject, and this is by far the most common case.  and this is by far the most common case. In UTF-8 mode, the byte offset must
1804    point to the start of a UTF-8 character (or the end of the subject). Unlike the
1805    pattern string, the subject may contain binary zero bytes.
1806  .P  .P
1807  A non-zero starting offset is useful when searching for another match in the  A non-zero starting offset is useful when searching for another match in the
1808  same subject by calling \fBpcre_exec()\fP again after a previous success.  same subject by calling \fBpcre_exec()\fP again after a previous success.
# Line 1274  start of the subject, which is deemed to Line 1822  start of the subject, which is deemed to
1822  set to 4, it finds the second occurrence of "iss" because it is able to look  set to 4, it finds the second occurrence of "iss" because it is able to look
1823  behind the starting point to discover that it is preceded by a letter.  behind the starting point to discover that it is preceded by a letter.
1824  .P  .P
1825    Finding all the matches in a subject is tricky when the pattern can match an
1826    empty string. It is possible to emulate Perl's /g behaviour by first trying the
1827    match again at the same offset, with the PCRE_NOTEMPTY_ATSTART and
1828    PCRE_ANCHORED options, and then if that fails, advancing the starting offset
1829    and trying an ordinary match again. There is some code that demonstrates how to
1830    do this in the
1831    .\" HREF
1832    \fBpcredemo\fP
1833    .\"
1834    sample program. In the most general case, you have to check to see if the
1835    newline convention recognizes CRLF as a newline, and if so, and the current
1836    character is CR followed by LF, advance the starting offset by two characters
1837    instead of one.
1838    .P
1839  If a non-zero starting offset is passed when the pattern is anchored, one  If a non-zero starting offset is passed when the pattern is anchored, one
1840  attempt to match at the given offset is made. This can only succeed if the  attempt to match at the given offset is made. This can only succeed if the
1841  pattern does not require the match to be at the start of the subject.  pattern does not require the match to be at the start of the subject.
1842  .  .
1843    .
1844  .SS "How \fBpcre_exec()\fP returns captured substrings"  .SS "How \fBpcre_exec()\fP returns captured substrings"
1845  .rs  .rs
1846  .sp  .sp
# Line 1288  pattern. Following the usage in Jeffrey Line 1851  pattern. Following the usage in Jeffrey
1851  a fragment of a pattern that picks out a substring. PCRE supports several other  a fragment of a pattern that picks out a substring. PCRE supports several other
1852  kinds of parenthesized subpattern that do not cause substrings to be captured.  kinds of parenthesized subpattern that do not cause substrings to be captured.
1853  .P  .P
1854  Captured substrings are returned to the caller via a vector of integer offsets  Captured substrings are returned to the caller via a vector of integers whose
1855  whose address is passed in \fIovector\fP. The number of elements in the vector  address is passed in \fIovector\fP. The number of elements in the vector is
1856  is passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP:  passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP: this
1857  this argument is NOT the size of \fIovector\fP in bytes.  argument is NOT the size of \fIovector\fP in bytes.
1858  .P  .P
1859  The first two-thirds of the vector is used to pass back captured substrings,  The first two-thirds of the vector is used to pass back captured substrings,
1860  each substring using a pair of integers. The remaining third of the vector is  each substring using a pair of integers. The remaining third of the vector is
1861  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
1862  and is not available for passing back information. The length passed in  and is not available for passing back information. The number passed in
1863  \fIovecsize\fP should always be a multiple of three. If it is not, it is  \fIovecsize\fP should always be a multiple of three. If it is not, it is
1864  rounded down.  rounded down.
1865  .P  .P
1866  When a match is successful, information about captured substrings is returned  When a match is successful, information about captured substrings is returned
1867  in pairs of integers, starting at the beginning of \fIovector\fP, and  in pairs of integers, starting at the beginning of \fIovector\fP, and
1868  continuing up to two-thirds of its length at the most. The first element of a  continuing up to two-thirds of its length at the most. The first element of
1869  pair is set to the offset of the first character in a substring, and the second  each pair is set to the byte offset of the first character in a substring, and
1870  is set to the offset of the first character after the end of a substring. The  the second is set to the byte offset of the first character after the end of a
1871  first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the  substring. \fBNote\fP: these values are always byte offsets, even in UTF-8
1872  subject string matched by the entire pattern. The next pair is used for the  mode. They are not character counts.
1873  first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP  .P
1874  is one more than the highest numbered pair that has been set. For example, if  The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the
1875  two substrings have been captured, the returned value is 3. If there are no  portion of the subject string matched by the entire pattern. The next pair is
1876  capturing subpatterns, the return value from a successful match is 1,  used for the first capturing subpattern, and so on. The value returned by
1877  indicating that just the first pair of offsets has been set.  \fBpcre_exec()\fP is one more than the highest numbered pair that has been set.
1878    For example, if two substrings have been captured, the returned value is 3. If
1879    there are no capturing subpatterns, the return value from a successful match is
1880    1, indicating that just the first pair of offsets has been set.
1881  .P  .P
1882  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
1883  string that it matched that is returned.  string that it matched that is returned.
1884  .P  .P
1885  If the vector is too small to hold all the captured substring offsets, it is  If the vector is too small to hold all the captured substring offsets, it is
1886  used as far as possible (up to two-thirds of its length), and the function  used as far as possible (up to two-thirds of its length), and the function
1887  returns a value of zero. In particular, if the substring offsets are not of  returns a value of zero. If neither the actual string matched not any captured
1888  interest, \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and  substrings are of interest, \fBpcre_exec()\fP may be called with \fIovector\fP
1889  \fIovecsize\fP as zero. However, if the pattern contains back references and  passed as NULL and \fIovecsize\fP as zero. However, if the pattern contains
1890  the \fIovector\fP is not big enough to remember the related substrings, PCRE  back references and the \fIovector\fP is not big enough to remember the related
1891  has to get additional memory for use during matching. Thus it is usually  substrings, PCRE has to get additional memory for use during matching. Thus it
1892  advisable to supply an \fIovector\fP.  is usually advisable to supply an \fIovector\fP of reasonable size.
1893    .P
1894    There are some cases where zero is returned (indicating vector overflow) when
1895    in fact the vector is exactly the right size for the final match. For example,
1896    consider the pattern
1897    .sp
1898      (a)(?:(b)c|bd)
1899    .sp
1900    If a vector of 6 elements (allowing for only 1 captured substring) is given
1901    with subject string "abd", \fBpcre_exec()\fP will try to set the second
1902    captured string, thereby recording a vector overflow, before failing to match
1903    "c" and backing up to try the second alternative. The zero return, however,
1904    does correctly indicate that the maximum number of slots (namely 2) have been
1905    filled. In similar cases where there is temporary overflow, but the final
1906    number of used slots is actually less than the maximum, a non-zero value is
1907    returned.
1908  .P  .P
1909  The \fBpcre_info()\fP function can be used to find out how many capturing  The \fBpcre_fullinfo()\fP function can be used to find out how many capturing
1910  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
1911  \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
1912  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.
# Line 1341  Offset values that correspond to unused Line 1922  Offset values that correspond to unused
1922  expression are also set to -1. For example, if the string "abc" is matched  expression are also set to -1. For example, if the string "abc" is matched
1923  against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The  against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
1924  return from the function is 2, because the highest used capturing subpattern  return from the function is 2, because the highest used capturing subpattern
1925  number is 1. However, you can refer to the offsets for the second and third  number is 1, and the offsets for for the second and third capturing subpatterns
1926  capturing subpatterns if you wish (assuming the vector is large enough, of  (assuming the vector is large enough, of course) are set to -1.
1927  course).  .P
1928    \fBNote\fP: Elements in the first two-thirds of \fIovector\fP that do not
1929    correspond to capturing parentheses in the pattern are never changed. That is,
1930    if a pattern contains \fIn\fP capturing parentheses, no more than
1931    \fIovector[0]\fP to \fIovector[2n+1]\fP are set by \fBpcre_exec()\fP. The other
1932    elements (in the first two-thirds) retain whatever values they previously had.
1933  .P  .P
1934  Some convenience functions are provided for extracting the captured substrings  Some convenience functions are provided for extracting the captured substrings
1935  as separate strings. These are described below.  as separate strings. These are described below.
1936  .  .
1937    .
1938  .\" HTML <a name="errorlist"></a>  .\" HTML <a name="errorlist"></a>
1939  .SS "Error return values from \fBpcre_exec()\fP"  .SS "Error return values from \fBpcre_exec()\fP"
1940  .rs  .rs
# Line 1389  If a pattern contains back references, b Line 1976  If a pattern contains back references, b
1976  gets a block of memory at the start of matching to use for this purpose. If the  gets a block of memory at the start of matching to use for this purpose. If the
1977  call via \fBpcre_malloc()\fP fails, this error is given. The memory is  call via \fBpcre_malloc()\fP fails, this error is given. The memory is
1978  automatically freed at the end of matching.  automatically freed at the end of matching.
1979    .P
1980    This error is also given if \fBpcre_stack_malloc()\fP fails in
1981    \fBpcre_exec()\fP. This can happen only when PCRE has been compiled with
1982    \fB--disable-stack-for-recursion\fP.
1983  .sp  .sp
1984    PCRE_ERROR_NOSUBSTRING    (-7)    PCRE_ERROR_NOSUBSTRING    (-7)
1985  .sp  .sp
# Line 1413  documentation for details. Line 2004  documentation for details.
2004  .sp  .sp
2005    PCRE_ERROR_BADUTF8        (-10)    PCRE_ERROR_BADUTF8        (-10)
2006  .sp  .sp
2007  A string that contains an invalid UTF-8 byte sequence was passed as a subject.  A string that contains an invalid UTF-8 byte sequence was passed as a subject,
2008    and the PCRE_NO_UTF8_CHECK option was not set. If the size of the output vector
2009    (\fIovecsize\fP) is at least 2, the byte offset to the start of the the invalid
2010    UTF-8 character is placed in the first element, and a reason code is placed in
2011    the second element. The reason codes are listed in the
2012    .\" HTML <a href="#badutf8reasons">
2013    .\" </a>
2014    following section.
2015    .\"
2016    For backward compatibility, if PCRE_PARTIAL_HARD is set and the problem is a
2017    truncated UTF-8 character at the end of the subject (reason codes 1 to 5),
2018    PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8.
2019  .sp  .sp
2020    PCRE_ERROR_BADUTF8_OFFSET (-11)    PCRE_ERROR_BADUTF8_OFFSET (-11)
2021  .sp  .sp
2022  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 checked and found to
2023  of \fIstartoffset\fP did not point to the beginning of a UTF-8 character.  be valid (the PCRE_NO_UTF8_CHECK option was not set), but the value of
2024    \fIstartoffset\fP did not point to the beginning of a UTF-8 character or the
2025    end of the subject.
2026  .sp  .sp
2027    PCRE_ERROR_PARTIAL        (-12)    PCRE_ERROR_PARTIAL        (-12)
2028  .sp  .sp
# Line 1430  documentation for details of partial mat Line 2034  documentation for details of partial mat
2034  .sp  .sp
2035    PCRE_ERROR_BADPARTIAL     (-13)    PCRE_ERROR_BADPARTIAL     (-13)
2036  .sp  .sp
2037  The PCRE_PARTIAL option was used with a compiled pattern containing items that  This code is no longer in use. It was formerly returned when the PCRE_PARTIAL
2038  are not supported for partial matching. See the  option was used with a compiled pattern containing items that were not
2039  .\" HREF  supported for partial matching. From release 8.00 onwards, there are no
2040  \fBpcrepartial\fP  restrictions on partial matching.
 .\"  
 documentation for details of partial matching.  
2041  .sp  .sp
2042    PCRE_ERROR_INTERNAL       (-14)    PCRE_ERROR_INTERNAL       (-14)
2043  .sp  .sp
# Line 1452  The internal recursion limit, as specifi Line 2054  The internal recursion limit, as specifi
2054  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
2055  description above.  description above.
2056  .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  
2057    PCRE_ERROR_BADNEWLINE     (-23)    PCRE_ERROR_BADNEWLINE     (-23)
2058  .sp  .sp
2059  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
2060    .sp
2061      PCRE_ERROR_BADOFFSET      (-24)
2062    .sp
2063    The value of \fIstartoffset\fP was negative or greater than the length of the
2064    subject, that is, the value in \fIlength\fP.
2065    .sp
2066      PCRE_ERROR_SHORTUTF8      (-25)
2067    .sp
2068    This error is returned instead of PCRE_ERROR_BADUTF8 when the subject string
2069    ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD option is set.
2070    Information about the failure is returned as for PCRE_ERROR_BADUTF8. It is in
2071    fact sufficient to detect this case, but this special error code for
2072    PCRE_PARTIAL_HARD precedes the implementation of returned information; it is
2073    retained for backwards compatibility.
2074    .sp
2075      PCRE_ERROR_RECURSELOOP    (-26)
2076    .sp
2077    This error is returned when \fBpcre_exec()\fP detects a recursion loop within
2078    the pattern. Specifically, it means that either the whole pattern or a
2079    subpattern has been called recursively for the second time at the same position
2080    in the subject string. Some simple patterns that might do this are detected and
2081    faulted at compile time, but more complicated cases, in particular mutual
2082    recursions between two different subpatterns, cannot be detected until run
2083    time.
2084    .sp
2085      PCRE_ERROR_JIT_STACKLIMIT (-27)
2086    .sp
2087    This error is returned when a pattern that was successfully studied using the
2088    PCRE_STUDY_JIT_COMPILE option is being matched, but the memory available for
2089    the just-in-time processing stack is not large enough. See the
2090    .\" HREF
2091    \fBpcrejit\fP
2092    .\"
2093    documentation for more details.
2094    .sp
2095      PCRE_ERROR_BADMODE (-28)
2096    .sp
2097    This error is given if a pattern that was compiled by the 8-bit library is
2098    passed to a 16-bit library function, or vice versa.
2099    .sp
2100      PCRE_ERROR_BADENDIANNESS (-29)
2101    .sp
2102    This error is given if a pattern that was compiled and saved is reloaded on a
2103    host with different endianness. The utility function
2104    \fBpcre_pattern_to_host_byte_order()\fP can be used to convert such a pattern
2105    so that it runs on the new host.
2106    .P
2107    Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
2108    .
2109    .
2110    .\" HTML <a name="badutf8reasons"></a>
2111    .SS "Reason codes for invalid UTF-8 strings"
2112    .rs
2113    .sp
2114    This section applies only to the 8-bit library. The corresponding information
2115    for the 16-bit library is given in the
2116    .\" HREF
2117    \fBpcre16\fP
2118    .\"
2119    page.
2120  .P  .P
2121  Error numbers -16 to -20 are not used by \fBpcre_exec()\fP.  When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or
2122    PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at
2123    least 2, the offset of the start of the invalid UTF-8 character is placed in
2124    the first output vector element (\fIovector[0]\fP) and a reason code is placed
2125    in the second element (\fIovector[1]\fP). The reason codes are given names in
2126    the \fBpcre.h\fP header file:
2127    .sp
2128      PCRE_UTF8_ERR1
2129      PCRE_UTF8_ERR2
2130      PCRE_UTF8_ERR3
2131      PCRE_UTF8_ERR4
2132      PCRE_UTF8_ERR5
2133    .sp
2134    The string ends with a truncated UTF-8 character; the code specifies how many
2135    bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be
2136    no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279)
2137    allows for up to 6 bytes, and this is checked first; hence the possibility of
2138    4 or 5 missing bytes.
2139    .sp
2140      PCRE_UTF8_ERR6
2141      PCRE_UTF8_ERR7
2142      PCRE_UTF8_ERR8
2143      PCRE_UTF8_ERR9
2144      PCRE_UTF8_ERR10
2145    .sp
2146    The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the
2147    character do not have the binary value 0b10 (that is, either the most
2148    significant bit is 0, or the next bit is 1).
2149    .sp
2150      PCRE_UTF8_ERR11
2151      PCRE_UTF8_ERR12
2152    .sp
2153    A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long;
2154    these code points are excluded by RFC 3629.
2155    .sp
2156      PCRE_UTF8_ERR13
2157    .sp
2158    A 4-byte character has a value greater than 0x10fff; these code points are
2159    excluded by RFC 3629.
2160    .sp
2161      PCRE_UTF8_ERR14
2162    .sp
2163    A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of
2164    code points are reserved by RFC 3629 for use with UTF-16, and so are excluded
2165    from UTF-8.
2166    .sp
2167      PCRE_UTF8_ERR15
2168      PCRE_UTF8_ERR16
2169      PCRE_UTF8_ERR17
2170      PCRE_UTF8_ERR18
2171      PCRE_UTF8_ERR19
2172    .sp
2173    A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a
2174    value that can be represented by fewer bytes, which is invalid. For example,
2175    the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just
2176    one byte.
2177    .sp
2178      PCRE_UTF8_ERR20
2179    .sp
2180    The two most significant bits of the first byte of a character have the binary
2181    value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a
2182    byte can only validly occur as the second or subsequent byte of a multi-byte
2183    character.
2184    .sp
2185      PCRE_UTF8_ERR21
2186    .sp
2187    The first byte of a character has the value 0xfe or 0xff. These values can
2188    never occur in a valid UTF-8 string.
2189  .  .
2190  .  .
2191  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1476  Error numbers -16 to -20 are not used by Line 2197  Error numbers -16 to -20 are not used by
2197  .ti +5n  .ti +5n
2198  .B int \fIbuffersize\fP);  .B int \fIbuffersize\fP);
2199  .PP  .PP
 .br  
2200  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
2201  .ti +5n  .ti +5n
2202  .B int \fIstringcount\fP, int \fIstringnumber\fP,  .B int \fIstringcount\fP, int \fIstringnumber\fP,
2203  .ti +5n  .ti +5n
2204  .B const char **\fIstringptr\fP);  .B const char **\fIstringptr\fP);
2205  .PP  .PP
 .br  
2206  .B int pcre_get_substring_list(const char *\fIsubject\fP,  .B int pcre_get_substring_list(const char *\fIsubject\fP,
2207  .ti +5n  .ti +5n
2208  .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 2288  provided.
2288  .ti +5n  .ti +5n
2289  .B const char *\fIname\fP);  .B const char *\fIname\fP);
2290  .PP  .PP
 .br  
2291  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
2292  .ti +5n  .ti +5n
2293  .B const char *\fIsubject\fP, int *\fIovector\fP,  .B const char *\fIsubject\fP, int *\fIovector\fP,
# Line 1578  provided. Line 2296  provided.
2296  .ti +5n  .ti +5n
2297  .B char *\fIbuffer\fP, int \fIbuffersize\fP);  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
2298  .PP  .PP
 .br  
2299  .B int pcre_get_named_substring(const pcre *\fIcode\fP,  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
2300  .ti +5n  .ti +5n
2301  .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 2331  pattern. This is needed in order to gain
2331  translation table.  translation table.
2332  .P  .P
2333  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
2334  then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as  then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
2335  appropriate.  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
2336    the behaviour may not be what you want (see the next section).
2337    .P
2338    \fBWarning:\fP If the pattern uses the (?| feature to set up multiple
2339    subpatterns with the same number, as described in the
2340    .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
2341    .\" </a>
2342    section on duplicate subpattern numbers
2343    .\"
2344    in the
2345    .\" HREF
2346    \fBpcrepattern\fP
2347    .\"
2348    page, you cannot use names to distinguish the different subpatterns, because
2349    names are not included in the compiled code. The matching process uses only
2350    numbers. For this reason, the use of different names for subpatterns of the
2351    same number causes an error at compile time.
2352  .  .
2353  .  .
2354  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
# Line 1626  appropriate. Line 2359  appropriate.
2359  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
2360  .PP  .PP
2361  When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns  When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
2362  are not required to be unique. Normally, patterns with duplicate names are such  are not required to be unique. (Duplicate names are always allowed for
2363  that in any one match, only one of the named subpatterns participates. An  subpatterns with the same number, created by using the (?| feature. Indeed, if
2364  example is shown in the  such subpatterns are named, they are required to use the same names.)
2365    .P
2366    Normally, patterns with duplicate names are such that in any one match, only
2367    one of the named subpatterns participates. An example is shown in the
2368  .\" HREF  .\" HREF
2369  \fBpcrepattern\fP  \fBpcrepattern\fP
2370  .\"  .\"
2371  documentation. When duplicates are present, \fBpcre_copy_named_substring()\fP  documentation.
2372  and \fBpcre_get_named_substring()\fP return the first substring corresponding  .P
2373  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
2374  The \fBpcre_get_stringnumber()\fP function returns one of the numbers that are  \fBpcre_get_named_substring()\fP return the first substring corresponding to
2375  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
2376  .sp  returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
2377    returns one of the numbers that are associated with the name, but it is not
2378    defined which it is.
2379    .P
2380  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,
2381  you must use the \fBpcre_get_stringtable_entries()\fP function. The first  you must use the \fBpcre_get_stringtable_entries()\fP function. The first
2382  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 1645  fourth are pointers to variables which a Line 2384  fourth are pointers to variables which a
2384  has run, they point to the first and last entries in the name-to-number table  has run, they point to the first and last entries in the name-to-number table
2385  for the given name. The function itself returns the length of each entry, or  for the given name. The function itself returns the length of each entry, or
2386  PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is  PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
2387  described above in the section entitled \fIInformation about a pattern\fP.  described above in the section entitled \fIInformation about a pattern\fP
2388    .\" HTML <a href="#infoaboutpattern">
2389    .\" </a>
2390    above.
2391    .\"
2392  Given all the relevant entries for the name, you can extract each of their  Given all the relevant entries for the name, you can extract each of their
2393  numbers, and hence the captured data, if any.  numbers, and hence the captured data, if any.
2394  .  .
# Line 1672  other alternatives. Ultimately, when it Line 2415  other alternatives. Ultimately, when it
2415  will yield PCRE_ERROR_NOMATCH.  will yield PCRE_ERROR_NOMATCH.
2416  .  .
2417  .  .
2418    .SH "OBTAINING AN ESTIMATE OF STACK USAGE"
2419    .rs
2420    .sp
2421    Matching certain patterns using \fBpcre_exec()\fP can use a lot of process
2422    stack, which in certain environments can be rather limited in size. Some users
2423    find it helpful to have an estimate of the amount of stack that is used by
2424    \fBpcre_exec()\fP, to help them set recursion limits, as described in the
2425    .\" HREF
2426    \fBpcrestack\fP
2427    .\"
2428    documentation. The estimate that is output by \fBpcretest\fP when called with
2429    the \fB-m\fP and \fB-C\fP options is obtained by calling \fBpcre_exec\fP with
2430    the values NULL, NULL, NULL, -999, and -999 for its first five arguments.
2431    .P
2432    Normally, if its first argument is NULL, \fBpcre_exec()\fP immediately returns
2433    the negative error code PCRE_ERROR_NULL, but with this special combination of
2434    arguments, it returns instead a negative number whose absolute value is the
2435    approximate stack frame size in bytes. (A negative number is used so that it is
2436    clear that no match has happened.) The value is approximate because in some
2437    cases, recursive calls to \fBpcre_exec()\fP occur when there are one or two
2438    additional variables on the stack.
2439    .P
2440    If PCRE has been compiled to use the heap instead of the stack for recursion,
2441    the value returned is the size of each block that is obtained from the heap.
2442    .
2443    .
2444  .\" HTML <a name="dfamatch"></a>  .\" HTML <a name="dfamatch"></a>
2445  .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"  .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
2446  .rs  .rs
# Line 1689  a compiled pattern, using a matching alg Line 2458  a compiled pattern, using a matching alg
2458  just once, and does not backtrack. This has different characteristics to the  just once, and does not backtrack. This has different characteristics to the
2459  normal algorithm, and is not compatible with Perl. Some of the features of PCRE  normal algorithm, and is not compatible with Perl. Some of the features of PCRE
2460  patterns are not supported. Nevertheless, there are times when this kind of  patterns are not supported. Nevertheless, there are times when this kind of
2461  matching can be useful. For a discussion of the two matching algorithms, see  matching can be useful. For a discussion of the two matching algorithms, and a
2462  the  list of features that \fBpcre_dfa_exec()\fP does not support, see the
2463  .\" HREF  .\" HREF
2464  \fBpcrematching\fP  \fBpcrematching\fP
2465  .\"  .\"
# Line 1729  Here is an example of a simple call to \ Line 2498  Here is an example of a simple call to \
2498  .sp  .sp
2499  The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be  The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be
2500  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,  zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
2501  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
2502  PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are  PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE,
2503  the same as for \fBpcre_exec()\fP, so their description is not repeated here.  PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART.
2504  .sp  All but the last four of these are exactly the same as for \fBpcre_exec()\fP,
2505    PCRE_PARTIAL  so their description is not repeated here.
2506  .sp  .sp
2507  This has the same general effect as it does for \fBpcre_exec()\fP, but the    PCRE_PARTIAL_HARD
2508  details are slightly different. When PCRE_PARTIAL is set for    PCRE_PARTIAL_SOFT
2509  \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into  .sp
2510  PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no  These have the same general effect as they do for \fBpcre_exec()\fP, but the
2511  complete matches, but there is still at least one matching possibility. The  details are slightly different. When PCRE_PARTIAL_HARD is set for
2512  portion of the string that provided the partial match is set as the first  \fBpcre_dfa_exec()\fP, it returns PCRE_ERROR_PARTIAL if the end of the subject
2513  matching string.  is reached and there is still at least one matching possibility that requires
2514    additional characters. This happens even if some complete matches have also
2515    been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH
2516    is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached,
2517    there have been no complete matches, but there is still at least one matching
2518    possibility. The portion of the string that was inspected when the longest
2519    partial match was found is set as the first matching string in both cases.
2520    There is a more detailed discussion of partial and multi-segment matching, with
2521    examples, in the
2522    .\" HREF
2523    \fBpcrepartial\fP
2524    .\"
2525    documentation.
2526  .sp  .sp
2527    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
2528  .sp  .sp
# Line 1752  matching point in the subject string. Line 2533  matching point in the subject string.
2533  .sp  .sp
2534    PCRE_DFA_RESTART    PCRE_DFA_RESTART
2535  .sp  .sp
2536  When \fBpcre_dfa_exec()\fP is called with the PCRE_PARTIAL option, and returns  When \fBpcre_dfa_exec()\fP returns a partial match, it is possible to call it
2537  a partial match, it is possible to call it again, with additional subject  again, with additional subject characters, and have it continue with the same
2538  characters, and have it continue with the same match. The PCRE_DFA_RESTART  match. The PCRE_DFA_RESTART option requests this action; when it is set, the
2539  option requests this action; when it is set, the \fIworkspace\fP and  \fIworkspace\fP and \fIwscount\fP options must reference the same vector as
2540  \fIwscount\fP options must reference the same vector as before because data  before because data about the match so far is left in them after a partial
2541  about the match so far is left in them after a partial match. There is more  match. There is more discussion of this facility in the
 discussion of this facility in the  
2542  .\" HREF  .\" HREF
2543  \fBpcrepartial\fP  \fBpcrepartial\fP
2544  .\"  .\"
2545  documentation.  documentation.
2546  .  .
2547    .
2548  .SS "Successful returns from \fBpcre_dfa_exec()\fP"  .SS "Successful returns from \fBpcre_dfa_exec()\fP"
2549  .rs  .rs
2550  .sp  .sp
# Line 1795  returns data, even though the meaning of Line 2576  returns data, even though the meaning of
2576  The strings are returned in reverse order of length; that is, the longest  The strings are returned in reverse order of length; that is, the longest
2577  matching string is given first. If there were too many matches to fit into  matching string is given first. If there were too many matches to fit into
2578  \fIovector\fP, the yield of the function is zero, and the vector is filled with  \fIovector\fP, the yield of the function is zero, and the vector is filled with
2579  the longest matches.  the longest matches. Unlike \fBpcre_exec()\fP, \fBpcre_dfa_exec()\fP can use
2580    the entire \fIovector\fP for returning matched strings.
2581    .
2582  .  .
2583  .SS "Error returns from \fBpcre_dfa_exec()\fP"  .SS "Error returns from \fBpcre_dfa_exec()\fP"
2584  .rs  .rs
# Line 1824  group. These are not supported. Line 2607  group. These are not supported.
2607    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
2608  .sp  .sp
2609  This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP  This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP
2610  block that contains a setting of the \fImatch_limit\fP field. This is not  block that contains a setting of the \fImatch_limit\fP or
2611  supported (it is meaningless).  \fImatch_limit_recursion\fP fields. This is not supported (these fields are
2612    meaningless for DFA matching).
2613  .sp  .sp
2614    PCRE_ERROR_DFA_WSSIZE     (-19)    PCRE_ERROR_DFA_WSSIZE     (-19)
2615  .sp  .sp
# Line 1843  extremely rare, as a vector of size 1000 Line 2627  extremely rare, as a vector of size 1000
2627  .SH "SEE ALSO"  .SH "SEE ALSO"
2628  .rs  .rs
2629  .sp  .sp
2630  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcre16\fP(3), \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
2631  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
2632  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
2633  .P  .
2634  .in 0  .
2635  Last updated: 30 November 2006  .SH AUTHOR
2636  .br  .rs
2637  Copyright (c) 1997-2006 University of Cambridge.  .sp
2638    .nf
2639    Philip Hazel
2640    University Computing Service
2641    Cambridge CB2 3QH, England.
2642    .fi
2643    .
2644    .
2645    .SH REVISION
2646    .rs
2647    .sp
2648    .nf
2649    Last updated: 18 February 2012
2650    Copyright (c) 1997-2012 University of Cambridge.
2651    .fi

Legend:
Removed from v.93  
changed lines
  Added in v.921

  ViewVC Help
Powered by ViewVC 1.1.5