/[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 454 by ph10, Tue Sep 22 09:42:11 2009 UTC revision 1031 by ph10, Sat Sep 8 15:59:01 2012 UTC
# Line 1  Line 1 
1  .TH PCREAPI 3  .TH PCREAPI 3 "07 September 2012" "PCRE 8.32"
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
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
# Line 25  PCRE - Perl-compatible regular expressio Line 27  PCRE - Perl-compatible regular expressio
27  .ti +5n  .ti +5n
28  .B const char **\fIerrptr\fP);  .B const char **\fIerrptr\fP);
29  .PP  .PP
30    .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,
# Line 38  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    .
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 82  PCRE - Perl-compatible regular expressio Line 90  PCRE - Perl-compatible regular expressio
90  .B void pcre_free_substring(const char *\fIstringptr\fP);  .B void pcre_free_substring(const char *\fIstringptr\fP);
91  .PP  .PP
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
106  .B const unsigned char *pcre_maketables(void);  .B const unsigned char *pcre_maketables(void);
107  .PP  .PP
# Line 89  PCRE - Perl-compatible regular expressio Line 109  PCRE - Perl-compatible regular expressio
109  .ti +5n  .ti +5n
110  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
111  .PP  .PP
 .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  
 .B *\fIfirstcharptr\fP);  
 .PP  
112  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
113  .PP  .PP
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  .B char *pcre_version(void);  .B const char *pcre_version(void);
117  .PP  .PP
118    .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
128  .B void (*pcre_free)(void *);  .B void (*pcre_free)(void *);
# Line 109  PCRE - Perl-compatible regular expressio Line 134  PCRE - Perl-compatible regular expressio
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
# Line 146  documentation, and the Line 206  documentation, and the
206  .\"  .\"
207  documentation describes how to compile and run it.  documentation describes how to compile and run it.
208  .P  .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
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
# Line 180  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 231  PCRE supports five different conventions Line 302  PCRE supports five different conventions
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, any of the three preceding, or any  character, the two-character sequence CRLF, any of the three preceding, or any
304  Unicode newline sequence. The Unicode newline sequences are the three just  Unicode newline sequence. The Unicode newline sequences are the three just
305  mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,  mentioned, plus the single characters VT (vertical tab, U+000B), FF (form feed,
306  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS  U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
307  (paragraph separator, U+2029).  (paragraph separator, U+2029).
308  .P  .P
# Line 276  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 287  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. However, compiling a regular expression with one version of PCRE  documentation, which includes a description of the
369  for use with a different version is not guaranteed to work and may cause  \fBpcre_pattern_to_host_byte_order()\fP function. However, compiling a regular
370  crashes.  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 values that are supported in
426  are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY.  ASCII/Unicode environments are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for
427  Though they are derived from ASCII, the same values are returned in EBCDIC  ANYCRLF, and -1 for ANY. In EBCDIC environments, CR, ANYCRLF, and ANY yield the
428  environments. The default should normally correspond to the standard sequence  same values. However, the value for LF is normally 21, though some EBCDIC
429  for your operating system.  environments use 37. The corresponding values for CRLF are 3349 and 3365. The
430    default should normally correspond to the standard sequence for your operating
431    system.
432  .sp  .sp
433    PCRE_CONFIG_BSR    PCRE_CONFIG_BSR
434  .sp  .sp
# Line 337  or CRLF. The default can be overridden w Line 440  or CRLF. The default can be overridden w
440    PCRE_CONFIG_LINK_SIZE    PCRE_CONFIG_LINK_SIZE
441  .sp  .sp
442  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
443  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
444  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
445  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
446  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.
447    Larger values allow larger regular expressions to be compiled, at the expense
448    of slower matching.
449  .sp  .sp
450    PCRE_CONFIG_POSIX_MALLOC_THRESHOLD    PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
451  .sp  .sp
# Line 395  avoiding the use of the stack. Line 500  avoiding the use of the stack.
500  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
501  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
502  the two interfaces is that \fBpcre_compile2()\fP has an additional argument,  the two interfaces is that \fBpcre_compile2()\fP has an additional argument,
503  \fIerrorcodeptr\fP, via which a numerical error code can be returned.  \fIerrorcodeptr\fP, via which a numerical error code can be returned. To avoid
504    too much repetition, we refer just to \fBpcre_compile()\fP below, but the
505    information applies equally to \fBpcre_compile2()\fP.
506  .P  .P
507  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
508  \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 412  argument, which is an address (see below Line 519  argument, which is an address (see below
519  The \fIoptions\fP argument contains various bit settings that affect the  The \fIoptions\fP argument contains various bit settings that affect the
520  compilation. It should be zero if no options are required. The available  compilation. It should be zero if no options are required. The available
521  options are described below. Some of them (in particular, those that are  options are described below. Some of them (in particular, those that are
522  compatible with Perl, but also some others) can also be set and unset from  compatible with Perl, but some others as well) can also be set and unset from
523  within the pattern (see the detailed description in the  within the pattern (see the detailed description in the
524  .\" HREF  .\" HREF
525  \fBpcrepattern\fP  \fBpcrepattern\fP
526  .\"  .\"
527  documentation). For those options that can be different in different parts of  documentation). For those options that can be different in different parts of
528  the pattern, the contents of the \fIoptions\fP argument specifies their initial  the pattern, the contents of the \fIoptions\fP argument specifies their
529  settings at the start of compilation and execution. The PCRE_ANCHORED and  settings at the start of compilation and execution. The PCRE_ANCHORED,
530  PCRE_NEWLINE_\fIxxx\fP options can be set at the time of matching as well as at  PCRE_BSR_\fIxxx\fP, PCRE_NEWLINE_\fIxxx\fP, PCRE_NO_UTF8_CHECK, and
531    PCRE_NO_START_OPTIMIZE options can be set at the time of matching as well as at
532  compile time.  compile time.
533  .P  .P
534  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
535  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
536  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
537  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
538  not try to free it. The byte offset from the start of the pattern to the  not try to free it. Normally, the offset from the start of the pattern to the
539  character that was being processes when the error was discovered is placed in  byte that was being processed when the error was discovered is placed in the
540  the variable pointed to by \fIerroffset\fP, which must not be NULL. If it is,  variable pointed to by \fIerroffset\fP, which must not be NULL (if it is, an
541  an immediate error is given. Some errors are not detected until checks are  immediate error is given). However, for an invalid UTF-8 string, the offset is
542  carried out when the whole pattern has been scanned; in this case the offset is  that of the first byte of the failing character.
543  set to the end of the pattern.  .P
544    Some errors are not detected until the whole pattern has been scanned; in these
545    cases, the offset passed back is the length of the pattern. Note that the
546    offset is in bytes, not characters, even in UTF-8 mode. It may sometimes point
547    into the middle of a UTF-8 character.
548  .P  .P
549  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
550  \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 511  pattern. Line 623  pattern.
623  .sp  .sp
624    PCRE_DOTALL    PCRE_DOTALL
625  .sp  .sp
626  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
627  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
628  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,
629  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
630  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
631  the setting of this option.  (?s) option setting. A negative class such as [^a] always matches newline
632    characters, independent of the setting of this option.
633  .sp  .sp
634    PCRE_DUPNAMES    PCRE_DUPNAMES
635  .sp  .sp
# Line 531  documentation. Line 644  documentation.
644  .sp  .sp
645    PCRE_EXTENDED    PCRE_EXTENDED
646  .sp  .sp
647  If this bit is set, whitespace data characters in the pattern are totally  If this bit is set, white space data characters in the pattern are totally
648  ignored except when escaped or inside a character class. Whitespace does not  ignored except when escaped or inside a character class. White space does not
649  include the VT character (code 11). In addition, characters between an  include the VT character (code 11). In addition, characters between an
650  unescaped # outside a character class and the next newline, inclusive, are also  unescaped # outside a character class and the next newline, inclusive, are also
651  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
652  pattern by a (?x) option setting.  pattern by a (?x) option setting.
653  .P  .P
654    Which characters are interpreted as newlines is controlled by the options
655    passed to \fBpcre_compile()\fP or by a special sequence at the start of the
656    pattern, as described in the section entitled
657    .\" HTML <a href="pcrepattern.html#newlines">
658    .\" </a>
659    "Newline conventions"
660    .\"
661    in the \fBpcrepattern\fP documentation. Note that the end of this type of
662    comment is a literal newline sequence in the pattern; escape sequences that
663    happen to represent a newline do not count.
664    .P
665  This option makes it possible to include comments inside complicated patterns.  This option makes it possible to include comments inside complicated patterns.
666  Note, however, that this applies only to data characters. Whitespace characters  Note, however, that this applies only to data characters. White space characters
667  may never appear within special character sequences in a pattern, for example  may never appear within special character sequences in a pattern, for example
668  within the sequence (?( which introduces a conditional subpattern.  within the sequence (?( that introduces a conditional subpattern.
669  .sp  .sp
670    PCRE_EXTRA    PCRE_EXTRA
671  .sp  .sp
# Line 551  set, any backslash in a pattern that is Line 675  set, any backslash in a pattern that is
675  special meaning causes an error, thus reserving these combinations for future  special meaning causes an error, thus reserving these combinations for future
676  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
677  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
678  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
679  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)
680    option setting within a pattern.
681  .sp  .sp
682    PCRE_FIRSTLINE    PCRE_FIRSTLINE
683  .sp  .sp
# Line 573  character). Thus, the pattern AB]CD beco Line 698  character). Thus, the pattern AB]CD beco
698  string (by default this causes the current matching alternative to fail). A  string (by default this causes the current matching alternative to fail). A
699  pattern such as (\e1)(a) succeeds when this option is set (assuming it can find  pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
700  an "a" in the subject), whereas it fails by default, for Perl compatibility.  an "a" in the subject), whereas it fails by default, for Perl compatibility.
701    .P
702    (3) \eU matches an upper case "U" character; by default \eU causes a compile
703    time error (Perl uses \eU to upper case subsequent characters).
704    .P
705    (4) \eu matches a lower case "u" character unless it is followed by four
706    hexadecimal digits, in which case the hexadecimal number defines the code point
707    to match. By default, \eu causes a compile time error (Perl uses it to upper
708    case the following character).
709    .P
710    (5) \ex matches a lower case "x" character unless it is followed by two
711    hexadecimal digits, in which case the hexadecimal number defines the code point
712    to match. By default, as in Perl, a hexadecimal number is always expected after
713    \ex, but it may have zero, one, or two digits (so, for example, \exz matches a
714    binary zero character followed by z).
715  .sp  .sp
716    PCRE_MULTILINE    PCRE_MULTILINE
717  .sp  .sp
# Line 602  indicated by a single character (CR or L Line 741  indicated by a single character (CR or L
741  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
742  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three  CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
743  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies  preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
744  that any Unicode newline sequence should be recognized. The Unicode newline  that any Unicode newline sequence should be recognized.
745  sequences are the three just mentioned, plus the single characters VT (vertical  .P
746  tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line  In an ASCII/Unicode environment, the Unicode newline sequences are the three
747  separator, U+2028), and PS (paragraph separator, U+2029). The last two are  just mentioned, plus the single characters VT (vertical tab, U+000B), FF (form
748    feed, U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
749    (paragraph separator, U+2029). For the 8-bit library, the last two are
750  recognized only in UTF-8 mode.  recognized only in UTF-8 mode.
751  .P  .P
752    When PCRE is compiled to run in an EBCDIC (mainframe) environment, the code for
753    CR is 0x0d, the same as ASCII. However, the character code for LF is normally
754    0x15, though in some EBCDIC environments 0x25 is used. Whichever of these is
755    not LF is made to correspond to Unicode's NEL character. EBCDIC codes are all
756    less than 256. For more details, see the
757    .\" HREF
758    \fBpcrebuild\fP
759    .\"
760    documentation.
761    .P
762  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
763  as a number, giving eight possibilities. Currently only six are used (default  as a number, giving eight possibilities. Currently only six are used (default
764  plus the five 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
# Line 615  option, the combination may or may not b Line 766  option, the combination may or may not b
766  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
767  other combinations may yield unused numbers and cause an error.  other combinations may yield unused numbers and cause an error.
768  .P  .P
769  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
770  pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character  compiling is when PCRE_EXTENDED is set. CR and LF are white space characters,
771  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
772  line break sequence. In other circumstances, line break sequences are treated  indicates a comment that lasts until after the next line break sequence. In
773  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
774  as whitespace characters and are therefore ignored.  data.
775  .P  .P
776  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
777  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 633  were followed by ?: but named parenthese Line 784  were followed by ?: but named parenthese
784  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
785  in Perl.  in Perl.
786  .sp  .sp
787      NO_START_OPTIMIZE
788    .sp
789    This is an option that acts at matching time; that is, it is really an option
790    for \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP. If it is set at compile time,
791    it is remembered with the compiled pattern and assumed at matching time. For
792    details see the discussion of PCRE_NO_START_OPTIMIZE
793    .\" HTML <a href="#execoptions">
794    .\" </a>
795    below.
796    .\"
797    .sp
798      PCRE_UCP
799    .sp
800    This option changes the way PCRE processes \eB, \eb, \eD, \ed, \eS, \es, \eW,
801    \ew, and some of the POSIX character classes. By default, only ASCII characters
802    are recognized, but if PCRE_UCP is set, Unicode properties are used instead to
803    classify characters. More details are given in the section on
804    .\" HTML <a href="pcre.html#genericchartypes">
805    .\" </a>
806    generic character types
807    .\"
808    in the
809    .\" HREF
810    \fBpcrepattern\fP
811    .\"
812    page. If you set PCRE_UCP, matching one of the items it affects takes much
813    longer. The option is available only if PCRE has been compiled with Unicode
814    property support.
815    .sp
816    PCRE_UNGREEDY    PCRE_UNGREEDY
817  .sp  .sp
818  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 642  with Perl. It can also be set by a (?U) Line 822  with Perl. It can also be set by a (?U)
822    PCRE_UTF8    PCRE_UTF8
823  .sp  .sp
824  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
825  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
826  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
827  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
828  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  
829  .\" HREF  .\" HREF
830  \fBpcre\fP  \fBpcreunicode\fP
831  .\"  .\"
832  page.  page.
833  .sp  .sp
834    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
835  .sp  .sp
836  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
837  automatically checked. There is a discussion about the  string is automatically checked. There is a discussion about the
838  .\" HTML <a href="pcre.html#utf8strings">  .\" HTML <a href="pcreunicode.html#utf8strings">
839  .\" </a>  .\" </a>
840  validity of UTF-8 strings  validity of UTF-8 strings
841  .\"  .\"
842  in the main  in the
843  .\" HREF  .\" HREF
844  \fBpcre\fP  \fBpcreunicode\fP
845  .\"  .\"
846  page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP  page. If an invalid UTF-8 sequence is found, \fBpcre_compile()\fP returns an
847  returns an error. If you already know that your pattern is valid, and you want  error. If you already know that your pattern is valid, and you want to skip
848  to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK  this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK option.
849  option. When it is set, the effect of passing an invalid UTF-8 string as a  When it is set, the effect of passing an invalid UTF-8 string as a pattern is
850  pattern is undefined. It may cause your program to crash. Note that this option  undefined. It may cause your program to crash. Note that this option can also
851  can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress  be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress the
852  the UTF-8 validity checking of subject strings.  validity checking of subject strings.
853  .  .
854  .  .
855  .SH "COMPILATION ERROR CODES"  .SH "COMPILATION ERROR CODES"
# Line 682  the UTF-8 validity checking of subject s Line 857  the UTF-8 validity checking of subject s
857  .sp  .sp
858  The following table lists the error codes than may be returned by  The following table lists the error codes than may be returned by
859  \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
860  both compiling functions. As PCRE has developed, some error codes have fallen  both compiling functions. Note that error messages are always 8-bit ASCII
861  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
862    fallen out of use. To avoid confusion, they have not been re-used.
863  .sp  .sp
864     0  no error     0  no error
865     1  \e at end of pattern     1  \e at end of pattern
# Line 717  out of use. To avoid confusion, they hav Line 893  out of use. To avoid confusion, they hav
893    29  (?R or (?[+-]digits must be followed by )    29  (?R or (?[+-]digits must be followed by )
894    30  unknown POSIX class name    30  unknown POSIX class name
895    31  POSIX collating elements are not supported    31  POSIX collating elements are not supported
896    32  this version of PCRE is not compiled with PCRE_UTF8 support    32  this version of PCRE is compiled without UTF support
897    33  [this code is not in use]    33  [this code is not in use]
898    34  character value in \ex{...} sequence is too large    34  character value in \ex{...} sequence is too large
899    35  invalid condition (?(0)    35  invalid condition (?(0)
900    36  \eC not allowed in lookbehind assertion    36  \eC not allowed in lookbehind assertion
901    37  PCRE does not support \eL, \el, \eN, \eU, or \eu    37  PCRE does not support \eL, \el, \eN{name}, \eU, or \eu
902    38  number after (?C is > 255    38  number after (?C is > 255
903    39  closing ) for (?C expected    39  closing ) for (?C expected
904    40  recursive call could loop indefinitely    40  recursive call could loop indefinitely
905    41  unrecognized character after (?P    41  unrecognized character after (?P
906    42  syntax error in subpattern name (missing terminator)    42  syntax error in subpattern name (missing terminator)
907    43  two named subpatterns have the same name    43  two named subpatterns have the same name
908    44  invalid UTF-8 string    44  invalid UTF-8 string (specifically UTF-8)
909    45  support for \eP, \ep, and \eX has not been compiled    45  support for \eP, \ep, and \eX has not been compiled
910    46  malformed \eP or \ep sequence    46  malformed \eP or \ep sequence
911    47  unknown property name after \eP or \ep    47  unknown property name after \eP or \ep
912    48  subpattern name is too long (maximum 32 characters)    48  subpattern name is too long (maximum 32 characters)
913    49  too many named subpatterns (maximum 10000)    49  too many named subpatterns (maximum 10000)
914    50  [this code is not in use]    50  [this code is not in use]
915    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
916    52  internal error: overran compiling workspace    52  internal error: overran compiling workspace
917    53  internal error: previously-checked referenced subpattern not found    53  internal error: previously-checked referenced subpattern
918            not found
919    54  DEFINE group contains more than one branch    54  DEFINE group contains more than one branch
920    55  repeating a DEFINE group is not allowed    55  repeating a DEFINE group is not allowed
921    56  inconsistent NEWLINE options    56  inconsistent NEWLINE options
922    57  \eg is not followed by a braced, angle-bracketed, or quoted    57  \eg is not followed by a braced, angle-bracketed, or quoted
923          name/number or by a plain number          name/number or by a plain number
924    58  a numbered reference must not be zero    58  a numbered reference must not be zero
925    59  (*VERB) with an argument is not supported    59  an argument is not allowed for (*ACCEPT), (*FAIL), or (*COMMIT)
926    60  (*VERB) not recognized    60  (*VERB) not recognized
927    61  number is too big    61  number is too big
928    62  subpattern name expected    62  subpattern name expected
929    63  digit expected after (?+    63  digit expected after (?+
930    64  ] is an invalid data character in JavaScript compatibility mode    64  ] is an invalid data character in JavaScript compatibility mode
931      65  different names for subpatterns of the same number are
932            not allowed
933      66  (*MARK) must have an argument
934      67  this version of PCRE is not compiled with Unicode property
935            support
936      68  \ec must be followed by an ASCII character
937      69  \ek is not followed by a braced, angle-bracketed, or quoted name
938      70  internal error: unknown opcode in find_fixedlength()
939      71  \eN is not supported in a class
940      72  too many forward references
941      73  disallowed Unicode code point (>= 0xd800 && <= 0xdfff)
942      74  invalid UTF-16 string (specifically UTF-16)
943      75  name is too long in (*MARK), (*PRUNE), (*SKIP), or (*THEN)
944      76  character value in \eu.... sequence is too large
945  .sp  .sp
946  The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may  The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
947  be used if the limits were changed when PCRE was built.  be used if the limits were changed when PCRE was built.
948  .  .
949  .  .
950    .\" HTML <a name="studyingapattern"></a>
951  .SH "STUDYING A PATTERN"  .SH "STUDYING A PATTERN"
952  .rs  .rs
953  .sp  .sp
# Line 772  help speed up matching, \fBpcre_study()\ Line 964  help speed up matching, \fBpcre_study()\
964  results of the study.  results of the study.
965  .P  .P
966  The returned value from \fBpcre_study()\fP can be passed directly to  The returned value from \fBpcre_study()\fP can be passed directly to
967  \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
968  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
969  described  passed; these are described
970  .\" HTML <a href="#extradata">  .\" HTML <a href="#extradata">
971  .\" </a>  .\" </a>
972  below  below
973  .\"  .\"
974  in the section on matching a pattern.  in the section on matching a pattern.
975  .P  .P
976  If studying the pattern does not produce any additional information  If studying the pattern does not produce any useful information,
977  \fBpcre_study()\fP returns NULL. In that circumstance, if the calling program  \fBpcre_study()\fP returns NULL by default. In that circumstance, if the
978  wants to pass any of the other fields to \fBpcre_exec()\fP, it must set up its  calling program wants to pass any of the other fields to \fBpcre_exec()\fP or
979  own \fBpcre_extra\fP block.  \fBpcre_dfa_exec()\fP, it must set up its own \fBpcre_extra\fP block. However,
980  .P  if \fBpcre_study()\fP is called with the PCRE_STUDY_EXTRA_NEEDED option, it
981  The second argument of \fBpcre_study()\fP contains option bits. At present, no  returns a \fBpcre_extra\fP block even if studying did not find any additional
982  options are defined, and this argument should always be zero.  information. It may still return NULL, however, if an error occurs in
983    \fBpcre_study()\fP.
984    .P
985    The second argument of \fBpcre_study()\fP contains option bits. There are three
986    further options in addition to PCRE_STUDY_EXTRA_NEEDED:
987    .sp
988      PCRE_STUDY_JIT_COMPILE
989      PCRE_STUDY_JIT_PARTIAL_HARD_COMPILE
990      PCRE_STUDY_JIT_PARTIAL_SOFT_COMPILE
991    .sp
992    If any of these are set, and the just-in-time compiler is available, the
993    pattern is further compiled into machine code that executes much faster than
994    the \fBpcre_exec()\fP interpretive matching function. If the just-in-time
995    compiler is not available, these options are ignored. All undefined bits in the
996    \fIoptions\fP argument must be zero.
997    .P
998    JIT compilation is a heavyweight optimization. It can take some time for
999    patterns to be analyzed, and for one-off matches and simple patterns the
1000    benefit of faster execution might be offset by a much slower study time.
1001    Not all patterns can be optimized by the JIT compiler. For those that cannot be
1002    handled, matching automatically falls back to the \fBpcre_exec()\fP
1003    interpreter. For more details, see the
1004    .\" HREF
1005    \fBpcrejit\fP
1006    .\"
1007    documentation.
1008  .P  .P
1009  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
1010  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 796  static string that is part of the librar Line 1013  static string that is part of the librar
1013  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
1014  sure that it has run successfully.  sure that it has run successfully.
1015  .P  .P
1016  This is a typical call to \fBpcre_study\fP():  When you are finished with a pattern, you can free the memory used for the
1017    study data by calling \fBpcre_free_study()\fP. This function was added to the
1018    API for release 8.20. For earlier versions, the memory could be freed with
1019    \fBpcre_free()\fP, just like the pattern itself. This will still work in cases
1020    where JIT optimization is not used, but it is advisable to change to the new
1021    function when convenient.
1022    .P
1023    This is a typical way in which \fBpcre_study\fP() is used (except that in a
1024    real application there should be tests for errors):
1025  .sp  .sp
1026    pcre_extra *pe;    int rc;
1027    pe = pcre_study(    pcre *re;
1028      pcre_extra *sd;
1029      re = pcre_compile("pattern", 0, &error, &erroroffset, NULL);
1030      sd = pcre_study(
1031      re,             /* result of pcre_compile() */      re,             /* result of pcre_compile() */
1032      0,              /* no options exist */      0,              /* no options */
1033      &error);        /* set to NULL or points to a message */      &error);        /* set to NULL or points to a message */
1034  .sp    rc = pcre_exec(   /* see below for details of pcre_exec() options */
1035  At present, studying a pattern is useful only for non-anchored patterns that do      re, sd, "subject", 7, 0, 0, ovector, 30);
1036  not have a single fixed starting character. A bitmap of possible starting    ...
1037  bytes is created.    pcre_free_study(sd);
1038      pcre_free(re);
1039    .sp
1040    Studying a pattern does two things: first, a lower bound for the length of
1041    subject string that is needed to match the pattern is computed. This does not
1042    mean that there are any strings of that length that match, but it does
1043    guarantee that no shorter strings match. The value is used to avoid wasting
1044    time by trying to match strings that are shorter than the lower bound. You can
1045    find out the value in a calling program via the \fBpcre_fullinfo()\fP function.
1046    .P
1047    Studying a pattern is also useful for non-anchored patterns that do not have a
1048    single fixed starting character. A bitmap of possible starting bytes is
1049    created. This speeds up finding a position in the subject at which to start
1050    matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.)
1051    .P
1052    These two optimizations apply to both \fBpcre_exec()\fP and
1053    \fBpcre_dfa_exec()\fP, and the information is also used by the JIT compiler.
1054    The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option
1055    when calling \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP, but if this is done,
1056    JIT execution is also disabled. You might want to do this if your pattern
1057    contains callouts or (*MARK) and you want to make use of these facilities in
1058    cases where matching fails. See the discussion of PCRE_NO_START_OPTIMIZE
1059    .\" HTML <a href="#execoptions">
1060    .\" </a>
1061    below.
1062    .\"
1063  .  .
1064  .  .
1065  .\" HTML <a name="localesupport"></a>  .\" HTML <a name="localesupport"></a>
# Line 815  bytes is created. Line 1068  bytes is created.
1068  .sp  .sp
1069  PCRE handles caseless matching, and determines whether characters are letters,  PCRE handles caseless matching, and determines whether characters are letters,
1070  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
1071  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
1072  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
1073  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
1074  support. The use of locales with Unicode is discouraged. If you are handling  Unicode character property support. Alternatively, the PCRE_UCP option can be
1075  characters with codes greater than 128, you should either use UTF-8 and  set at compile time; this causes \ew and friends to use Unicode property
1076  Unicode, or use locales, but not try to mix the two.  support instead of built-in tables. The use of locales with Unicode is
1077    discouraged. If you are handling characters with codes greater than 128, you
1078    should either use UTF-8 and Unicode, or use locales, but not try to mix the
1079    two.
1080  .P  .P
1081  PCRE contains an internal set of tables that are used when the final argument  PCRE contains an internal set of tables that are used when the final argument
1082  of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.  of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
# Line 865  one in which it was compiled. Passing ta Line 1121  one in which it was compiled. Passing ta
1121  below in the section on matching a pattern.  below in the section on matching a pattern.
1122  .  .
1123  .  .
1124    .\" HTML <a name="infoaboutpattern"></a>
1125  .SH "INFORMATION ABOUT A PATTERN"  .SH "INFORMATION ABOUT A PATTERN"
1126  .rs  .rs
1127  .sp  .sp
# Line 873  below in the section on matching a patte Line 1130  below in the section on matching a patte
1130  .B int \fIwhat\fP, void *\fIwhere\fP);  .B int \fIwhat\fP, void *\fIwhere\fP);
1131  .PP  .PP
1132  The \fBpcre_fullinfo()\fP function returns information about a compiled  The \fBpcre_fullinfo()\fP function returns information about a compiled
1133  pattern. It replaces the obsolete \fBpcre_info()\fP function, which is  pattern. It replaces the \fBpcre_info()\fP function, which was removed from the
1134  nevertheless retained for backwards compability (and is documented below).  library at version 8.30, after more than 10 years of obsolescence.
1135  .P  .P
1136  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
1137  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 883  information is required, and the fourth Line 1140  information is required, and the fourth
1140  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
1141  the following negative numbers:  the following negative numbers:
1142  .sp  .sp
1143    PCRE_ERROR_NULL       the argument \fIcode\fP was NULL    PCRE_ERROR_NULL           the argument \fIcode\fP was NULL
1144                          the argument \fIwhere\fP was NULL                              the argument \fIwhere\fP was NULL
1145    PCRE_ERROR_BADMAGIC   the "magic number" was not found    PCRE_ERROR_BADMAGIC       the "magic number" was not found
1146    PCRE_ERROR_BADOPTION  the value of \fIwhat\fP was invalid    PCRE_ERROR_BADENDIANNESS  the pattern was compiled with different
1147                                endianness
1148      PCRE_ERROR_BADOPTION      the value of \fIwhat\fP was invalid
1149  .sp  .sp
1150  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
1151  check against passing an arbitrary memory pointer. Here is a typical call of  check against passing an arbitrary memory pointer. The endianness error can
1152  \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
1153    a typical call of \fBpcre_fullinfo()\fP, to obtain the length of the compiled
1154    pattern:
1155  .sp  .sp
1156    int rc;    int rc;
1157    size_t length;    size_t length;
1158    rc = pcre_fullinfo(    rc = pcre_fullinfo(
1159      re,               /* result of pcre_compile() */      re,               /* result of pcre_compile() */
1160      pe,               /* result of pcre_study(), or NULL */      sd,               /* result of pcre_study(), or NULL */
1161      PCRE_INFO_SIZE,   /* what is required */      PCRE_INFO_SIZE,   /* what is required */
1162      &length);         /* where to put the data */      &length);         /* where to put the data */
1163  .sp  .sp
# Line 924  a NULL table pointer. Line 1185  a NULL table pointer.
1185  .sp  .sp
1186    PCRE_INFO_FIRSTBYTE    PCRE_INFO_FIRSTBYTE
1187  .sp  .sp
1188  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
1189  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,
1190  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
1191  still recognized for backwards compatibility.)  variable.
1192    .P
1193    If there is a fixed first value, for example, the letter "c" from a pattern
1194    such as (cat|cow|coyote), its value is returned. In the 8-bit library, the
1195    value is always less than 256; in the 16-bit library the value can be up to
1196    0xffff.
1197  .P  .P
1198  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  
1199  .sp  .sp
1200  (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
1201  starts with "^", or  starts with "^", or
# Line 945  returned. For anchored patterns, -2 is r Line 1210  returned. For anchored patterns, -2 is r
1210    PCRE_INFO_FIRSTTABLE    PCRE_INFO_FIRSTTABLE
1211  .sp  .sp
1212  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
1213  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
1214  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
1215  fourth argument should point to an \fBunsigned char *\fP variable.  fourth argument should point to an \fBunsigned char *\fP variable.
1216  .sp  .sp
# Line 961  Return 1 if the (?J) or (?-J) option set Line 1226  Return 1 if the (?J) or (?-J) option set
1226  0. The fourth argument should point to an \fBint\fP variable. (?J) and  0. The fourth argument should point to an \fBint\fP variable. (?J) and
1227  (?-J) set and unset the local PCRE_DUPNAMES option, respectively.  (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
1228  .sp  .sp
1229      PCRE_INFO_JIT
1230    .sp
1231    Return 1 if the pattern was studied with one of the JIT options, and
1232    just-in-time compiling was successful. The fourth argument should point to an
1233    \fBint\fP variable. A return value of 0 means that JIT support is not available
1234    in this version of PCRE, or that the pattern was not studied with a JIT option,
1235    or that the JIT compiler could not handle this particular pattern. See the
1236    .\" HREF
1237    \fBpcrejit\fP
1238    .\"
1239    documentation for details of what can and cannot be handled.
1240    .sp
1241      PCRE_INFO_JITSIZE
1242    .sp
1243    If the pattern was successfully studied with a JIT option, return the size of
1244    the JIT compiled code, otherwise return zero. The fourth argument should point
1245    to a \fBsize_t\fP variable.
1246    .sp
1247    PCRE_INFO_LASTLITERAL    PCRE_INFO_LASTLITERAL
1248  .sp  .sp
1249  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
1250  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
1251  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
1252  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
1253  follows something of variable length. For example, for the pattern  only if it follows something of variable length. For example, for the pattern
1254  /^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
1255  is -1.  is -1.
1256  .sp  .sp
1257      PCRE_INFO_MAXLOOKBEHIND
1258    .sp
1259    Return the number of characters (NB not bytes) in the longest lookbehind
1260    assertion in the pattern. Note that the simple assertions \eb and \eB require a
1261    one-character lookbehind. This information is useful when doing multi-segment
1262    matching using the partial matching facilities.
1263    .sp
1264      PCRE_INFO_MINLENGTH
1265    .sp
1266    If the pattern was studied and a minimum length for matching subject strings
1267    was computed, its value is returned. Otherwise the returned value is -1. The
1268    value is a number of characters, which in UTF-8 mode may be different from the
1269    number of bytes. The fourth argument should point to an \fBint\fP variable. A
1270    non-negative value is a lower bound to the length of any matching string. There
1271    may not be any strings of that length that do actually match, but every string
1272    that does match is at least that long.
1273    .sp
1274    PCRE_INFO_NAMECOUNT    PCRE_INFO_NAMECOUNT
1275    PCRE_INFO_NAMEENTRYSIZE    PCRE_INFO_NAMEENTRYSIZE
1276    PCRE_INFO_NAMETABLE    PCRE_INFO_NAMETABLE
# Line 989  The map consists of a number of fixed-si Line 1289  The map consists of a number of fixed-si
1289  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
1290  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
1291  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
1292  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
1293  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,
1294  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
1295  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
1296  their parentheses numbers. For example, consider the following pattern (assume  of the entry is the corresponding name, zero terminated.
1297  PCRE_EXTENDED is set, so white space - including newlines - is ignored):  .P
1298    The names are in alphabetical order. Duplicate names may appear if (?| is used
1299    to create multiple groups with the same number, as described in the
1300    .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
1301    .\" </a>
1302    section on duplicate subpattern numbers
1303    .\"
1304    in the
1305    .\" HREF
1306    \fBpcrepattern\fP
1307    .\"
1308    page. Duplicate names for subpatterns with different numbers are permitted only
1309    if PCRE_DUPNAMES is set. In all cases of duplicate names, they appear in the
1310    table in the order in which they were found in the pattern. In the absence of
1311    (?| this is the order of increasing number; when (?| is used this is not
1312    necessarily the case because later subpatterns may have lower numbers.
1313    .P
1314    As a simple example of the name/number table, consider the following pattern
1315    after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white
1316    space - including newlines - is ignored):
1317  .sp  .sp
1318  .\" JOIN  .\" JOIN
1319    (?<date> (?<year>(\ed\ed)?\ed\ed) -    (?<date> (?<year>(\ed\ed)?\ed\ed) -
# Line 1049  For such patterns, the PCRE_ANCHORED bit Line 1368  For such patterns, the PCRE_ANCHORED bit
1368  .sp  .sp
1369    PCRE_INFO_SIZE    PCRE_INFO_SIZE
1370  .sp  .sp
1371  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
1372  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
1373  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
1374  variable.  \fBpcre_compile()\fP. The value that is passed as the argument to
1375    \fBpcre_malloc()\fP when \fBpcre_compile()\fP is getting memory in which to
1376    place the compiled data is the value returned by this option plus the size of
1377    the \fBpcre\fP structure. Studying a compiled pattern, with or without JIT,
1378    does not alter the value returned by this option.
1379  .sp  .sp
1380    PCRE_INFO_STUDYSIZE    PCRE_INFO_STUDYSIZE
1381  .sp  .sp
1382  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
1383  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
1384  \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
1385  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
1386  \fBsize_t\fP variable.  to record information that will speed up matching (see the section entitled
1387  .  .\" HTML <a href="#studyingapattern">
1388  .  .\" </a>
1389  .SH "OBSOLETE INFO FUNCTION"  "Studying a pattern"
1390  .rs  .\"
1391  .sp  above). The format of the \fIstudy_data\fP block is private, but its length
1392  .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
1393  .B *\fIfirstcharptr\fP);  .\" HREF
1394  .PP  \fBpcreprecompile\fP
1395  The \fBpcre_info()\fP function is now obsolete because its interface is too  .\"
1396  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).  
1397  .  .
1398  .  .
1399  .SH "REFERENCE COUNTS"  .SH "REFERENCE COUNTS"
# Line 1121  is different. (This seems a highly unlik Line 1430  is different. (This seems a highly unlik
1430  .P  .P
1431  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
1432  compiled pattern, which is passed in the \fIcode\fP argument. If the  compiled pattern, which is passed in the \fIcode\fP argument. If the
1433  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
1434  \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
1435  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
1436  also an alternative matching function, which is described  different subject strings with the same pattern.
1437    .P
1438    This function is the main matching facility of the library, and it operates in
1439    a Perl-like manner. For specialist use there is also an alternative matching
1440    function, which is described
1441  .\" HTML <a href="#dfamatch">  .\" HTML <a href="#dfamatch">
1442  .\" </a>  .\" </a>
1443  below  below
# Line 1155  Here is an example of a simple call to \ Line 1468  Here is an example of a simple call to \
1468      ovector,        /* vector of integers for substring information */      ovector,        /* vector of integers for substring information */
1469      30);            /* number of elements (NOT size in bytes) */      30);            /* number of elements (NOT size in bytes) */
1470  .  .
1471    .
1472  .\" HTML <a name="extradata"></a>  .\" HTML <a name="extradata"></a>
1473  .SS "Extra data for \fBpcre_exec()\fR"  .SS "Extra data for \fBpcre_exec()\fR"
1474  .rs  .rs
# Line 1167  fields (not necessarily in this order): Line 1481  fields (not necessarily in this order):
1481  .sp  .sp
1482    unsigned long int \fIflags\fP;    unsigned long int \fIflags\fP;
1483    void *\fIstudy_data\fP;    void *\fIstudy_data\fP;
1484      void *\fIexecutable_jit\fP;
1485    unsigned long int \fImatch_limit\fP;    unsigned long int \fImatch_limit\fP;
1486    unsigned long int \fImatch_limit_recursion\fP;    unsigned long int \fImatch_limit_recursion\fP;
1487    void *\fIcallout_data\fP;    void *\fIcallout_data\fP;
1488    const unsigned char *\fItables\fP;    const unsigned char *\fItables\fP;
1489      unsigned char **\fImark\fP;
1490  .sp  .sp
1491  The \fIflags\fP field is a bitmap that specifies which of the other fields  In the 16-bit version of this structure, the \fImark\fP field has type
1492  are set. The flag bits are:  "PCRE_UCHAR16 **".
1493    .P
1494    The \fIflags\fP field is used to specify which of the other fields are set. The
1495    flag bits are:
1496  .sp  .sp
1497    PCRE_EXTRA_STUDY_DATA    PCRE_EXTRA_CALLOUT_DATA
1498      PCRE_EXTRA_EXECUTABLE_JIT
1499      PCRE_EXTRA_MARK
1500    PCRE_EXTRA_MATCH_LIMIT    PCRE_EXTRA_MATCH_LIMIT
1501    PCRE_EXTRA_MATCH_LIMIT_RECURSION    PCRE_EXTRA_MATCH_LIMIT_RECURSION
1502    PCRE_EXTRA_CALLOUT_DATA    PCRE_EXTRA_STUDY_DATA
1503    PCRE_EXTRA_TABLES    PCRE_EXTRA_TABLES
1504  .sp  .sp
1505  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
1506  \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
1507  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
1508  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 other
1509    fields and their corresponding flag bits.
1510  .P  .P
1511  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
1512  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,
1513  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
1514  classic example is the use of nested unlimited repeats.  classic example is a pattern that uses nested unlimited repeats.
1515  .P  .P
1516  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly  Internally, \fBpcre_exec()\fP uses a function called \fBmatch()\fP, which it
1517  (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
1518  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
1519  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
1520  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
1521  string.  in the subject string.
1522    .P
1523    When \fBpcre_exec()\fP is called with a pattern that was successfully studied
1524    with a JIT option, the way that the matching is executed is entirely different.
1525    However, there is still the possibility of runaway matching that goes on for a
1526    very long time, and so the \fImatch_limit\fP value is also used in this case
1527    (but in a different way) to limit how long the matching can continue.
1528  .P  .P
1529  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
1530  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 1211  limits the depth of recursion. The recur Line 1539  limits the depth of recursion. The recur
1539  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.
1540  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.
1541  .P  .P
1542  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
1543  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
1544  amount of heap memory that can be used.  stack, the amount of heap memory that can be used. This limit is not relevant,
1545    and is ignored, when matching is done using JIT compiled code.
1546  .P  .P
1547  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
1548  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 1242  called. See the Line 1571  called. See the
1571  \fBpcreprecompile\fP  \fBpcreprecompile\fP
1572  .\"  .\"
1573  documentation for a discussion of saving compiled patterns for later use.  documentation for a discussion of saving compiled patterns for later use.
1574    .P
1575    If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must
1576    be set to point to a suitable variable. If the pattern contains any
1577    backtracking control verbs such as (*MARK:NAME), and the execution ends up with
1578    a name to pass back, a pointer to the name string (zero terminated) is placed
1579    in the variable pointed to by the \fImark\fP field. The names are within the
1580    compiled pattern; if you wish to retain such a name you must copy it before
1581    freeing the memory of a compiled pattern. If there is no name to pass back, the
1582    variable pointed to by the \fImark\fP field is set to NULL. For details of the
1583    backtracking control verbs, see the section entitled
1584    .\" HTML <a href="pcrepattern#backtrackcontrol">
1585    .\" </a>
1586    "Backtracking control"
1587    .\"
1588    in the
1589    .\" HREF
1590    \fBpcrepattern\fP
1591    .\"
1592    documentation.
1593    .
1594  .  .
1595  .\" HTML <a name="execoptions"></a>  .\" HTML <a name="execoptions"></a>
1596  .SS "Option bits for \fBpcre_exec()\fP"  .SS "Option bits for \fBpcre_exec()\fP"
# Line 1250  documentation for a discussion of saving Line 1599  documentation for a discussion of saving
1599  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
1600  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,
1601  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
1602  PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and  PCRE_NO_START_OPTIMIZE, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, and
1603  PCRE_PARTIAL_HARD.  PCRE_PARTIAL_SOFT.
1604    .P
1605    If the pattern was successfully studied with one of the just-in-time (JIT)
1606    compile options, the only supported options for JIT execution are
1607    PCRE_NO_UTF8_CHECK, PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY,
1608    PCRE_NOTEMPTY_ATSTART, PCRE_PARTIAL_HARD, and PCRE_PARTIAL_SOFT. If an
1609    unsupported option is used, JIT execution is disabled and the normal
1610    interpretive code in \fBpcre_exec()\fP is run.
1611  .sp  .sp
1612    PCRE_ANCHORED    PCRE_ANCHORED
1613  .sp  .sp
# Line 1332  valid, so PCRE searches further into the Line 1688  valid, so PCRE searches further into the
1688  .sp  .sp
1689    PCRE_NOTEMPTY_ATSTART    PCRE_NOTEMPTY_ATSTART
1690  .sp  .sp
1691  This is like PCRE_NOTEMPTY, except that an empty string match that is not at  This is like PCRE_NOTEMPTY, except that an empty string match that is not at
1692  the start of the subject is permitted. If the pattern is anchored, such a match  the start of the subject is permitted. If the pattern is anchored, such a match
1693  can occur only if the pattern contains \eK.  can occur only if the pattern contains \eK.
1694  .P  .P
# Line 1347  the Line 1703  the
1703  .\" HREF  .\" HREF
1704  \fBpcredemo\fP  \fBpcredemo\fP
1705  .\"  .\"
1706  sample program.  sample program. In the most general case, you have to check to see if the
1707    newline convention recognizes CRLF as a newline, and if so, and the current
1708    character is CR followed by LF, advance the starting offset by two characters
1709    instead of one.
1710  .sp  .sp
1711    PCRE_NO_START_OPTIMIZE    PCRE_NO_START_OPTIMIZE
1712  .sp  .sp
1713  There are a number of optimizations that \fBpcre_exec()\fP uses at the start of  There are a number of optimizations that \fBpcre_exec()\fP uses at the start of
1714  a match, in order to speed up the process. For example, if it is known that a  a match, in order to speed up the process. For example, if it is known that an
1715  match must start with a specific character, it searches the subject for that  unanchored match must start with a specific character, it searches the subject
1716  character, and fails immediately if it cannot find it, without actually running  for that character, and fails immediately if it cannot find it, without
1717  the main matching function. When callouts are in use, these optimizations can  actually running the main matching function. This means that a special item
1718  cause them to be skipped. This option disables the "start-up" optimizations,  such as (*COMMIT) at the start of a pattern is not considered until after a
1719  causing performance to suffer, but ensuring that the callouts do occur.  suitable starting point for the match has been found. When callouts or (*MARK)
1720    items are in use, these "start-up" optimizations can cause them to be skipped
1721    if the pattern is never actually used. The start-up optimizations are in effect
1722    a pre-scan of the subject that takes place before the pattern is run.
1723    .P
1724    The PCRE_NO_START_OPTIMIZE option disables the start-up optimizations, possibly
1725    causing performance to suffer, but ensuring that in cases where the result is
1726    "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)
1727    are considered at every possible starting position in the subject string. If
1728    PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching
1729    time. The use of PCRE_NO_START_OPTIMIZE disables JIT execution; when it is set,
1730    matching is always done using interpretively.
1731    .P
1732    Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.
1733    Consider the pattern
1734    .sp
1735      (*COMMIT)ABC
1736    .sp
1737    When this is compiled, PCRE records the fact that a match must start with the
1738    character "A". Suppose the subject string is "DEFABC". The start-up
1739    optimization scans along the subject, finds "A" and runs the first match
1740    attempt from there. The (*COMMIT) item means that the pattern must match the
1741    current starting position, which in this case, it does. However, if the same
1742    match is run with PCRE_NO_START_OPTIMIZE set, the initial scan along the
1743    subject string does not happen. The first match attempt is run starting from
1744    "D" and when this fails, (*COMMIT) prevents any further matches being tried, so
1745    the overall result is "no match". If the pattern is studied, more start-up
1746    optimizations may be used. For example, a minimum length for the subject may be
1747    recorded. Consider the pattern
1748    .sp
1749      (*MARK:A)(X|Y)
1750    .sp
1751    The minimum length for a match is one character. If the subject is "ABC", there
1752    will be attempts to match "ABC", "BC", "C", and then finally an empty string.
1753    If the pattern is studied, the final attempt does not take place, because PCRE
1754    knows that the subject is too short, and so the (*MARK) is never encountered.
1755    In this case, studying the pattern does not affect the overall match result,
1756    which is still "no match", but it does affect the auxiliary information that is
1757    returned.
1758  .sp  .sp
1759    PCRE_NO_UTF8_CHECK    PCRE_NO_UTF8_CHECK
1760  .sp  .sp
1761  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
1762  string is automatically checked when \fBpcre_exec()\fP is subsequently called.  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
1763  The value of \fIstartoffset\fP is also checked to ensure that it points to the  The entire string is checked before any other processing takes place. The value
1764  start of a UTF-8 character. There is a discussion about the validity of UTF-8  of \fIstartoffset\fP is also checked to ensure that it points to the start of a
1765  strings in the  UTF-8 character. There is a discussion about the
1766  .\" HTML <a href="pcre.html#utf8strings">  .\" HTML <a href="pcreunicode.html#utf8strings">
1767  .\" </a>  .\" </a>
1768  section on UTF-8 support  validity of UTF-8 strings
1769  .\"  .\"
1770  in the main  in the
1771  .\" HREF  .\" HREF
1772  \fBpcre\fP  \fBpcreunicode\fP
1773  .\"  .\"
1774  page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns  page. If an invalid sequence of bytes is found, \fBpcre_exec()\fP returns the
1775  the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,  error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a
1776  PCRE_ERROR_BADUTF8_OFFSET is returned.  truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both
1777    cases, information about the precise nature of the error may also be returned
1778    (see the descriptions of these errors in the section entitled \fIError return
1779    values from\fP \fBpcre_exec()\fP
1780    .\" HTML <a href="#errorlist">
1781    .\" </a>
1782    below).
1783    .\"
1784    If \fIstartoffset\fP contains a value that does not point to the start of a
1785    UTF-8 character (or to the end of the subject), PCRE_ERROR_BADUTF8_OFFSET is
1786    returned.
1787  .P  .P
1788  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
1789  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
1790  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
1791  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
1792  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
1793  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
1794  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
1795  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
1796  UTF-8 character, is undefined. Your program may crash.  undefined. Your program may crash.
1797  .sp  .sp
1798    PCRE_PARTIAL_HARD    PCRE_PARTIAL_HARD
1799    PCRE_PARTIAL_SOFT    PCRE_PARTIAL_SOFT
1800  .sp  .sp
1801  These options turn on the partial matching feature. For backwards  These options turn on the partial matching feature. For backwards
1802  compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match  compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match
1803  occurs if the end of the subject string is reached successfully, but there are  occurs if the end of the subject string is reached successfully, but there are
1804  not enough subject characters to complete the match. If this happens when  not enough subject characters to complete the match. If this happens when
1805  PCRE_PARTIAL_HARD is set, \fBpcre_exec()\fP immediately returns  PCRE_PARTIAL_SOFT (but not PCRE_PARTIAL_HARD) is set, matching continues by
1806  PCRE_ERROR_PARTIAL. Otherwise, if PCRE_PARTIAL_SOFT is set, matching continues  testing any remaining alternatives. Only if no complete match can be found is
1807  by testing any other alternatives. Only if they all fail is PCRE_ERROR_PARTIAL  PCRE_ERROR_PARTIAL returned instead of PCRE_ERROR_NOMATCH. In other words,
1808  returned (instead of PCRE_ERROR_NOMATCH). The portion of the string that  PCRE_PARTIAL_SOFT says that the caller is prepared to handle a partial match,
1809  was inspected when the partial match was found is set as the first matching  but only if no complete match can be found.
1810  string. There is a more detailed discussion in the  .P
1811    If PCRE_PARTIAL_HARD is set, it overrides PCRE_PARTIAL_SOFT. In this case, if a
1812    partial match is found, \fBpcre_exec()\fP immediately returns
1813    PCRE_ERROR_PARTIAL, without considering any other alternatives. In other words,
1814    when PCRE_PARTIAL_HARD is set, a partial match is considered to be more
1815    important that an alternative complete match.
1816    .P
1817    In both cases, the portion of the string that was inspected when the partial
1818    match was found is set as the first matching string. There is a more detailed
1819    discussion of partial and multi-segment matching, with examples, in the
1820  .\" HREF  .\" HREF
1821  \fBpcrepartial\fP  \fBpcrepartial\fP
1822  .\"  .\"
1823  documentation.  documentation.
1824  .  .
1825    .
1826  .SS "The string to be matched by \fBpcre_exec()\fP"  .SS "The string to be matched by \fBpcre_exec()\fP"
1827  .rs  .rs
1828  .sp  .sp
1829  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
1830  \fIsubject\fP, a length (in bytes) in \fIlength\fP, and a starting byte offset  \fIsubject\fP, a length in bytes in \fIlength\fP, and a starting byte offset
1831  in \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of  in \fIstartoffset\fP. If this is negative or greater than the length of the
1832  a UTF-8 character. Unlike the pattern string, the subject may contain binary  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting
1833  zero bytes. When the starting offset is zero, the search for a match starts at  offset is zero, the search for a match starts at the beginning of the subject,
1834  the 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
1835    point to the start of a UTF-8 character (or the end of the subject). Unlike the
1836    pattern string, the subject may contain binary zero bytes.
1837  .P  .P
1838  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
1839  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 1434  start of the subject, which is deemed to Line 1853  start of the subject, which is deemed to
1853  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
1854  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.
1855  .P  .P
1856    Finding all the matches in a subject is tricky when the pattern can match an
1857    empty string. It is possible to emulate Perl's /g behaviour by first trying the
1858    match again at the same offset, with the PCRE_NOTEMPTY_ATSTART and
1859    PCRE_ANCHORED options, and then if that fails, advancing the starting offset
1860    and trying an ordinary match again. There is some code that demonstrates how to
1861    do this in the
1862    .\" HREF
1863    \fBpcredemo\fP
1864    .\"
1865    sample program. In the most general case, you have to check to see if the
1866    newline convention recognizes CRLF as a newline, and if so, and the current
1867    character is CR followed by LF, advance the starting offset by two characters
1868    instead of one.
1869    .P
1870  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
1871  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
1872  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.
1873  .  .
1874    .
1875  .SS "How \fBpcre_exec()\fP returns captured substrings"  .SS "How \fBpcre_exec()\fP returns captured substrings"
1876  .rs  .rs
1877  .sp  .sp
# Line 1481  string that it matched that is returned. Line 1915  string that it matched that is returned.
1915  .P  .P
1916  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
1917  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
1918  returns a value of zero. If the substring offsets are not of interest,  returns a value of zero. If neither the actual string matched nor any captured
1919  \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
1920  \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
1921  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
1922  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
1923  advisable to supply an \fIovector\fP.  is usually advisable to supply an \fIovector\fP of reasonable size.
1924    .P
1925    There are some cases where zero is returned (indicating vector overflow) when
1926    in fact the vector is exactly the right size for the final match. For example,
1927    consider the pattern
1928    .sp
1929      (a)(?:(b)c|bd)
1930    .sp
1931    If a vector of 6 elements (allowing for only 1 captured substring) is given
1932    with subject string "abd", \fBpcre_exec()\fP will try to set the second
1933    captured string, thereby recording a vector overflow, before failing to match
1934    "c" and backing up to try the second alternative. The zero return, however,
1935    does correctly indicate that the maximum number of slots (namely 2) have been
1936    filled. In similar cases where there is temporary overflow, but the final
1937    number of used slots is actually less than the maximum, a non-zero value is
1938    returned.
1939  .P  .P
1940  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
1941  subpatterns there are in a compiled pattern. The smallest size for  subpatterns there are in a compiled pattern. The smallest size for
1942  \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
1943  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 1504  Offset values that correspond to unused Line 1953  Offset values that correspond to unused
1953  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
1954  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
1955  return from the function is 2, because the highest used capturing subpattern  return from the function is 2, because the highest used capturing subpattern
1956  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
1957  capturing subpatterns if you wish (assuming the vector is large enough, of  (assuming the vector is large enough, of course) are set to -1.
1958  course).  .P
1959    \fBNote\fP: Elements in the first two-thirds of \fIovector\fP that do not
1960    correspond to capturing parentheses in the pattern are never changed. That is,
1961    if a pattern contains \fIn\fP capturing parentheses, no more than
1962    \fIovector[0]\fP to \fIovector[2n+1]\fP are set by \fBpcre_exec()\fP. The other
1963    elements (in the first two-thirds) retain whatever values they previously had.
1964  .P  .P
1965  Some convenience functions are provided for extracting the captured substrings  Some convenience functions are provided for extracting the captured substrings
1966  as separate strings. These are described below.  as separate strings. These are described below.
1967  .  .
1968    .
1969  .\" HTML <a name="errorlist"></a>  .\" HTML <a name="errorlist"></a>
1970  .SS "Error return values from \fBpcre_exec()\fP"  .SS "Error return values from \fBpcre_exec()\fP"
1971  .rs  .rs
# Line 1552  If a pattern contains back references, b Line 2007  If a pattern contains back references, b
2007  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
2008  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
2009  automatically freed at the end of matching.  automatically freed at the end of matching.
2010    .P
2011    This error is also given if \fBpcre_stack_malloc()\fP fails in
2012    \fBpcre_exec()\fP. This can happen only when PCRE has been compiled with
2013    \fB--disable-stack-for-recursion\fP.
2014  .sp  .sp
2015    PCRE_ERROR_NOSUBSTRING    (-7)    PCRE_ERROR_NOSUBSTRING    (-7)
2016  .sp  .sp
# Line 1576  documentation for details. Line 2035  documentation for details.
2035  .sp  .sp
2036    PCRE_ERROR_BADUTF8        (-10)    PCRE_ERROR_BADUTF8        (-10)
2037  .sp  .sp
2038  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,
2039    and the PCRE_NO_UTF8_CHECK option was not set. If the size of the output vector
2040    (\fIovecsize\fP) is at least 2, the byte offset to the start of the the invalid
2041    UTF-8 character is placed in the first element, and a reason code is placed in
2042    the second element. The reason codes are listed in the
2043    .\" HTML <a href="#badutf8reasons">
2044    .\" </a>
2045    following section.
2046    .\"
2047    For backward compatibility, if PCRE_PARTIAL_HARD is set and the problem is a
2048    truncated UTF-8 character at the end of the subject (reason codes 1 to 5),
2049    PCRE_ERROR_SHORTUTF8 is returned instead of PCRE_ERROR_BADUTF8.
2050  .sp  .sp
2051    PCRE_ERROR_BADUTF8_OFFSET (-11)    PCRE_ERROR_BADUTF8_OFFSET (-11)
2052  .sp  .sp
2053  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
2054  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
2055    \fIstartoffset\fP did not point to the beginning of a UTF-8 character or the
2056    end of the subject.
2057  .sp  .sp
2058    PCRE_ERROR_PARTIAL        (-12)    PCRE_ERROR_PARTIAL        (-12)
2059  .sp  .sp
# Line 1595  documentation for details of partial mat Line 2067  documentation for details of partial mat
2067  .sp  .sp
2068  This code is no longer in use. It was formerly returned when the PCRE_PARTIAL  This code is no longer in use. It was formerly returned when the PCRE_PARTIAL
2069  option was used with a compiled pattern containing items that were not  option was used with a compiled pattern containing items that were not
2070  supported for partial matching. From release 8.00 onwards, there are no  supported for partial matching. From release 8.00 onwards, there are no
2071  restrictions on partial matching.  restrictions on partial matching.
2072  .sp  .sp
2073    PCRE_ERROR_INTERNAL       (-14)    PCRE_ERROR_INTERNAL       (-14)
# Line 1616  description above. Line 2088  description above.
2088    PCRE_ERROR_BADNEWLINE     (-23)    PCRE_ERROR_BADNEWLINE     (-23)
2089  .sp  .sp
2090  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.  An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
2091    .sp
2092      PCRE_ERROR_BADOFFSET      (-24)
2093    .sp
2094    The value of \fIstartoffset\fP was negative or greater than the length of the
2095    subject, that is, the value in \fIlength\fP.
2096    .sp
2097      PCRE_ERROR_SHORTUTF8      (-25)
2098    .sp
2099    This error is returned instead of PCRE_ERROR_BADUTF8 when the subject string
2100    ends with a truncated UTF-8 character and the PCRE_PARTIAL_HARD option is set.
2101    Information about the failure is returned as for PCRE_ERROR_BADUTF8. It is in
2102    fact sufficient to detect this case, but this special error code for
2103    PCRE_PARTIAL_HARD precedes the implementation of returned information; it is
2104    retained for backwards compatibility.
2105    .sp
2106      PCRE_ERROR_RECURSELOOP    (-26)
2107    .sp
2108    This error is returned when \fBpcre_exec()\fP detects a recursion loop within
2109    the pattern. Specifically, it means that either the whole pattern or a
2110    subpattern has been called recursively for the second time at the same position
2111    in the subject string. Some simple patterns that might do this are detected and
2112    faulted at compile time, but more complicated cases, in particular mutual
2113    recursions between two different subpatterns, cannot be detected until run
2114    time.
2115    .sp
2116      PCRE_ERROR_JIT_STACKLIMIT (-27)
2117    .sp
2118    This error is returned when a pattern that was successfully studied using a
2119    JIT compile option is being matched, but the memory available for the
2120    just-in-time processing stack is not large enough. See the
2121    .\" HREF
2122    \fBpcrejit\fP
2123    .\"
2124    documentation for more details.
2125    .sp
2126      PCRE_ERROR_BADMODE        (-28)
2127    .sp
2128    This error is given if a pattern that was compiled by the 8-bit library is
2129    passed to a 16-bit library function, or vice versa.
2130    .sp
2131      PCRE_ERROR_BADENDIANNESS  (-29)
2132    .sp
2133    This error is given if a pattern that was compiled and saved is reloaded on a
2134    host with different endianness. The utility function
2135    \fBpcre_pattern_to_host_byte_order()\fP can be used to convert such a pattern
2136    so that it runs on the new host.
2137    .P
2138    Error numbers -16 to -20, -22, and -30 are not used by \fBpcre_exec()\fP.
2139    .
2140    .
2141    .\" HTML <a name="badutf8reasons"></a>
2142    .SS "Reason codes for invalid UTF-8 strings"
2143    .rs
2144    .sp
2145    This section applies only to the 8-bit library. The corresponding information
2146    for the 16-bit library is given in the
2147    .\" HREF
2148    \fBpcre16\fP
2149    .\"
2150    page.
2151  .P  .P
2152  Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.  When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or
2153    PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at
2154    least 2, the offset of the start of the invalid UTF-8 character is placed in
2155    the first output vector element (\fIovector[0]\fP) and a reason code is placed
2156    in the second element (\fIovector[1]\fP). The reason codes are given names in
2157    the \fBpcre.h\fP header file:
2158    .sp
2159      PCRE_UTF8_ERR1
2160      PCRE_UTF8_ERR2
2161      PCRE_UTF8_ERR3
2162      PCRE_UTF8_ERR4
2163      PCRE_UTF8_ERR5
2164    .sp
2165    The string ends with a truncated UTF-8 character; the code specifies how many
2166    bytes are missing (1 to 5). Although RFC 3629 restricts UTF-8 characters to be
2167    no longer than 4 bytes, the encoding scheme (originally defined by RFC 2279)
2168    allows for up to 6 bytes, and this is checked first; hence the possibility of
2169    4 or 5 missing bytes.
2170    .sp
2171      PCRE_UTF8_ERR6
2172      PCRE_UTF8_ERR7
2173      PCRE_UTF8_ERR8
2174      PCRE_UTF8_ERR9
2175      PCRE_UTF8_ERR10
2176    .sp
2177    The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the
2178    character do not have the binary value 0b10 (that is, either the most
2179    significant bit is 0, or the next bit is 1).
2180    .sp
2181      PCRE_UTF8_ERR11
2182      PCRE_UTF8_ERR12
2183    .sp
2184    A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long;
2185    these code points are excluded by RFC 3629.
2186    .sp
2187      PCRE_UTF8_ERR13
2188    .sp
2189    A 4-byte character has a value greater than 0x10fff; these code points are
2190    excluded by RFC 3629.
2191    .sp
2192      PCRE_UTF8_ERR14
2193    .sp
2194    A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of
2195    code points are reserved by RFC 3629 for use with UTF-16, and so are excluded
2196    from UTF-8.
2197    .sp
2198      PCRE_UTF8_ERR15
2199      PCRE_UTF8_ERR16
2200      PCRE_UTF8_ERR17
2201      PCRE_UTF8_ERR18
2202      PCRE_UTF8_ERR19
2203    .sp
2204    A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a
2205    value that can be represented by fewer bytes, which is invalid. For example,
2206    the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just
2207    one byte.
2208    .sp
2209      PCRE_UTF8_ERR20
2210    .sp
2211    The two most significant bits of the first byte of a character have the binary
2212    value 0b10 (that is, the most significant bit is 1 and the second is 0). Such a
2213    byte can only validly occur as the second or subsequent byte of a multi-byte
2214    character.
2215    .sp
2216      PCRE_UTF8_ERR21
2217    .sp
2218    The first byte of a character has the value 0xfe or 0xff. These values can
2219    never occur in a valid UTF-8 string.
2220  .  .
2221  .  .
2222  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
# Line 1767  then call \fBpcre_copy_substring()\fP or Line 2366  then call \fBpcre_copy_substring()\fP or
2366  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,  appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
2367  the behaviour may not be what you want (see the next section).  the behaviour may not be what you want (see the next section).
2368  .P  .P
2369  \fBWarning:\fP If the pattern uses the "(?|" feature to set up multiple  \fBWarning:\fP If the pattern uses the (?| feature to set up multiple
2370  subpatterns with the same number, you cannot use names to distinguish them,  subpatterns with the same number, as described in the
2371  because names are not included in the compiled code. The matching process uses  .\" HTML <a href="pcrepattern.html#dupsubpatternnumber">
2372  only numbers.  .\" </a>
2373    section on duplicate subpattern numbers
2374    .\"
2375    in the
2376    .\" HREF
2377    \fBpcrepattern\fP
2378    .\"
2379    page, you cannot use names to distinguish the different subpatterns, because
2380    names are not included in the compiled code. The matching process uses only
2381    numbers. For this reason, the use of different names for subpatterns of the
2382    same number causes an error at compile time.
2383    .
2384  .  .
2385  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
2386  .rs  .rs
# Line 1780  only numbers. Line 2390  only numbers.
2390  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);  .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
2391  .PP  .PP
2392  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
2393  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
2394  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
2395  example is shown in the  such subpatterns are named, they are required to use the same names.)
2396    .P
2397    Normally, patterns with duplicate names are such that in any one match, only
2398    one of the named subpatterns participates. An example is shown in the
2399  .\" HREF  .\" HREF
2400  \fBpcrepattern\fP  \fBpcrepattern\fP
2401  .\"  .\"
# Line 1802  fourth are pointers to variables which a Line 2415  fourth are pointers to variables which a
2415  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
2416  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
2417  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
2418  described above in the section entitled \fIInformation about a pattern\fP.  described above in the section entitled \fIInformation about a pattern\fP
2419    .\" HTML <a href="#infoaboutpattern">
2420    .\" </a>
2421    above.
2422    .\"
2423  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
2424  numbers, and hence the captured data, if any.  numbers, and hence the captured data, if any.
2425  .  .
# Line 1829  other alternatives. Ultimately, when it Line 2446  other alternatives. Ultimately, when it
2446  will yield PCRE_ERROR_NOMATCH.  will yield PCRE_ERROR_NOMATCH.
2447  .  .
2448  .  .
2449    .SH "OBTAINING AN ESTIMATE OF STACK USAGE"
2450    .rs
2451    .sp
2452    Matching certain patterns using \fBpcre_exec()\fP can use a lot of process
2453    stack, which in certain environments can be rather limited in size. Some users
2454    find it helpful to have an estimate of the amount of stack that is used by
2455    \fBpcre_exec()\fP, to help them set recursion limits, as described in the
2456    .\" HREF
2457    \fBpcrestack\fP
2458    .\"
2459    documentation. The estimate that is output by \fBpcretest\fP when called with
2460    the \fB-m\fP and \fB-C\fP options is obtained by calling \fBpcre_exec\fP with
2461    the values NULL, NULL, NULL, -999, and -999 for its first five arguments.
2462    .P
2463    Normally, if its first argument is NULL, \fBpcre_exec()\fP immediately returns
2464    the negative error code PCRE_ERROR_NULL, but with this special combination of
2465    arguments, it returns instead a negative number whose absolute value is the
2466    approximate stack frame size in bytes. (A negative number is used so that it is
2467    clear that no match has happened.) The value is approximate because in some
2468    cases, recursive calls to \fBpcre_exec()\fP occur when there are one or two
2469    additional variables on the stack.
2470    .P
2471    If PCRE has been compiled to use the heap instead of the stack for recursion,
2472    the value returned is the size of each block that is obtained from the heap.
2473    .
2474    .
2475  .\" HTML <a name="dfamatch"></a>  .\" HTML <a name="dfamatch"></a>
2476  .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"  .SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
2477  .rs  .rs
# Line 1846  a compiled pattern, using a matching alg Line 2489  a compiled pattern, using a matching alg
2489  just once, and does not backtrack. This has different characteristics to the  just once, and does not backtrack. This has different characteristics to the
2490  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
2491  patterns are not supported. Nevertheless, there are times when this kind of  patterns are not supported. Nevertheless, there are times when this kind of
2492  matching can be useful. For a discussion of the two matching algorithms, and a  matching can be useful. For a discussion of the two matching algorithms, and a
2493  list of features that \fBpcre_dfa_exec()\fP does not support, see the  list of features that \fBpcre_dfa_exec()\fP does not support, see the
2494  .\" HREF  .\" HREF
2495  \fBpcrematching\fP  \fBpcrematching\fP
# Line 1887  Here is an example of a simple call to \ Line 2530  Here is an example of a simple call to \
2530  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
2531  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,
2532  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,  PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NOTEMPTY_ATSTART,
2533  PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST,  PCRE_NO_UTF8_CHECK, PCRE_BSR_ANYCRLF, PCRE_BSR_UNICODE, PCRE_NO_START_OPTIMIZE,
2534  and PCRE_DFA_RESTART. All but the last four of these are exactly the same as  PCRE_PARTIAL_HARD, PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART.
2535  for \fBpcre_exec()\fP, so their description is not repeated here.  All but the last four of these are exactly the same as for \fBpcre_exec()\fP,
2536    so their description is not repeated here.
2537  .sp  .sp
2538    PCRE_PARTIAL_HARD    PCRE_PARTIAL_HARD
2539    PCRE_PARTIAL_SOFT    PCRE_PARTIAL_SOFT
2540  .sp  .sp
2541  These have the same general effect as they do for \fBpcre_exec()\fP, but the  These have the same general effect as they do for \fBpcre_exec()\fP, but the
2542  details are slightly different. When PCRE_PARTIAL_HARD is set for  details are slightly different. When PCRE_PARTIAL_HARD is set for
# Line 1904  is converted into PCRE_ERROR_PARTIAL if Line 2548  is converted into PCRE_ERROR_PARTIAL if
2548  there have been no complete matches, but there is still at least one matching  there have been no complete matches, but there is still at least one matching
2549  possibility. The portion of the string that was inspected when the longest  possibility. The portion of the string that was inspected when the longest
2550  partial match was found is set as the first matching string in both cases.  partial match was found is set as the first matching string in both cases.
2551    There is a more detailed discussion of partial and multi-segment matching, with
2552    examples, in the
2553    .\" HREF
2554    \fBpcrepartial\fP
2555    .\"
2556    documentation.
2557  .sp  .sp
2558    PCRE_DFA_SHORTEST    PCRE_DFA_SHORTEST
2559  .sp  .sp
# Line 1925  match. There is more discussion of this Line 2575  match. There is more discussion of this
2575  .\"  .\"
2576  documentation.  documentation.
2577  .  .
2578    .
2579  .SS "Successful returns from \fBpcre_dfa_exec()\fP"  .SS "Successful returns from \fBpcre_dfa_exec()\fP"
2580  .rs  .rs
2581  .sp  .sp
# Line 1956  returns data, even though the meaning of Line 2607  returns data, even though the meaning of
2607  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
2608  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
2609  \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
2610  the longest matches.  the longest matches. Unlike \fBpcre_exec()\fP, \fBpcre_dfa_exec()\fP can use
2611    the entire \fIovector\fP for returning matched strings.
2612    .
2613  .  .
2614  .SS "Error returns from \fBpcre_dfa_exec()\fP"  .SS "Error returns from \fBpcre_dfa_exec()\fP"
2615  .rs  .rs
# Line 1985  group. These are not supported. Line 2638  group. These are not supported.
2638    PCRE_ERROR_DFA_UMLIMIT    (-18)    PCRE_ERROR_DFA_UMLIMIT    (-18)
2639  .sp  .sp
2640  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
2641  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
2642  supported (it is meaningless).  \fImatch_limit_recursion\fP fields. This is not supported (these fields are
2643    meaningless for DFA matching).
2644  .sp  .sp
2645    PCRE_ERROR_DFA_WSSIZE     (-19)    PCRE_ERROR_DFA_WSSIZE     (-19)
2646  .sp  .sp
# Line 1999  When a recursive subpattern is processed Line 2653  When a recursive subpattern is processed
2653  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
2654  error is given if the output vector is not large enough. This should be  error is given if the output vector is not large enough. This should be
2655  extremely rare, as a vector of size 1000 is used.  extremely rare, as a vector of size 1000 is used.
2656    .sp
2657      PCRE_ERROR_DFA_BADRESTART (-30)
2658    .sp
2659    When \fBpcre_dfa_exec()\fP is called with the \fBPCRE_DFA_RESTART\fP option,
2660    some plausibility checks are made on the contents of the workspace, which
2661    should contain data about the previous partial match. If any of these checks
2662    fail, this error is given.
2663  .  .
2664  .  .
2665  .SH "SEE ALSO"  .SH "SEE ALSO"
2666  .rs  .rs
2667  .sp  .sp
2668  \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),  \fBpcre16\fP(3), \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
2669  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),  \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
2670  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).  \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
2671  .  .
# Line 2023  Cambridge CB2 3QH, England. Line 2684  Cambridge CB2 3QH, England.
2684  .rs  .rs
2685  .sp  .sp
2686  .nf  .nf
2687  Last updated: 22 September 2009  Last updated: 07 September 2012
2688  Copyright (c) 1997-2009 University of Cambridge.  Copyright (c) 1997-2012 University of Cambridge.
2689  .fi  .fi

Legend:
Removed from v.454  
changed lines
  Added in v.1031

  ViewVC Help
Powered by ViewVC 1.1.5