/[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 642 by ph10, Thu Jul 28 18:59:40 2011 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  .P
189  In a Windows environment, if you want to statically link an application program  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  against a non-dll \fBpcre.a\fP file, you must define PCRE_STATIC before
# Line 152  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 186  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 237  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 282  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 293  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 312  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 343  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 429  documentation). For those options that c Line 528  documentation). For those options that c
528  the pattern, the contents of the \fIoptions\fP argument specifies their  the pattern, the contents of the \fIoptions\fP argument specifies their
529  settings at the start of compilation and execution. The PCRE_ANCHORED,  settings at the start of compilation and execution. The PCRE_ANCHORED,
530  PCRE_BSR_\fIxxx\fP, PCRE_NEWLINE_\fIxxx\fP, PCRE_NO_UTF8_CHECK, and  PCRE_BSR_\fIxxx\fP, PCRE_NEWLINE_\fIxxx\fP, PCRE_NO_UTF8_CHECK, and
531  PCRE_NO_START_OPT options can be set at the time of matching as well as at  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.
# Line 440  not try to free it. Normally, the offset Line 539  not try to free it. Normally, the offset
539  byte that was being processed when the error was discovered is placed in the  byte that was being processed when the error was discovered is placed in the
540  variable pointed to by \fIerroffset\fP, which must not be NULL (if it is, an  variable pointed to by \fIerroffset\fP, which must not be NULL (if it is, an
541  immediate error is given). However, for an invalid UTF-8 string, the offset is  immediate error is given). However, for an invalid UTF-8 string, the offset is
542  that of the first byte of the failing character. Also, some errors are not  that of the first byte of the failing character.
 detected until checks are carried out when the whole pattern has been scanned;  
 in these cases the offset passed back is the length of the pattern.  
543  .P  .P
544  Note that the offset is in bytes, not characters, even in UTF-8 mode. It may  Some errors are not detected until the whole pattern has been scanned; in these
545  sometimes point into the middle of a UTF-8 character.  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 545  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
# Line 564  comment is a literal newline sequence in Line 663  comment is a literal newline sequence in
663  happen to represent a newline do not count.  happen to represent a newline do not count.
664  .P  .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 (?( that introduces a conditional subpattern.  within the sequence (?( that introduces a conditional subpattern.
669  .sp  .sp
# Line 599  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 628  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 642  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is Line 767  PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is
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 in a pattern is specially recognized when  The only time that a line break in a pattern is specially recognized when
770  compiling is when PCRE_EXTENDED is set. CR and LF are whitespace characters,  compiling is when PCRE_EXTENDED is set. CR and LF are white space characters,
771  and so are ignored in this mode. Also, an unescaped # outside a character class  and so are ignored in this mode. Also, an unescaped # outside a character class
772  indicates a comment that lasts until after the next line break sequence. In  indicates a comment that lasts until after the next line break sequence. In
773  other circumstances, line break sequences in patterns are treated as literal  other circumstances, line break sequences in patterns are treated as literal
# Line 697  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 737  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 772  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    53  internal error: previously-checked referenced subpattern
918          not found          not found
# Line 810  out of use. To avoid confusion, they hav Line 931  out of use. To avoid confusion, they hav
931    65  different names for subpatterns of the same number are    65  different names for subpatterns of the same number are
932          not allowed          not allowed
933    66  (*MARK) must have an argument    66  (*MARK) must have an argument
934    67  this version of PCRE is not compiled with PCRE_UCP support    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 842  below Line 974  below
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 useful 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 or  calling program wants to pass any of the other fields to \fBpcre_exec()\fP or
979  \fBpcre_dfa_exec()\fP, it must set up its 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 856  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      rc = pcre_exec(   /* see below for details of pcre_exec() options */
1035        re, sd, "subject", 7, 0, 0, ovector, 30);
1036      ...
1037      pcre_free_study(sd);
1038      pcre_free(re);
1039  .sp  .sp
1040  Studying a pattern does two things: first, a lower bound for the length of  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  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  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 by  guarantee that no shorter strings match. The value is used to avoid wasting
1044  \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP to avoid wasting time by trying to  time by trying to match strings that are shorter than the lower bound. You can
1045  match strings that are shorter than the lower bound. You can find out the value  find out the value in a calling program via the \fBpcre_fullinfo()\fP function.
 in a calling program via the \fBpcre_fullinfo()\fP function.  
1046  .P  .P
1047  Studying a pattern is also useful for non-anchored patterns that do not have a  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  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  created. This speeds up finding a position in the subject at which to start
1050  matching.  matching. (In 16-bit mode, the bitmap is used for 16-bit values less than 256.)
1051  .P  .P
1052  The two optimizations just described can be disabled by setting the  These two optimizations apply to both \fBpcre_exec()\fP and
1053  PCRE_NO_START_OPTIMIZE option when calling \fBpcre_exec()\fP or  \fBpcre_dfa_exec()\fP, and the information is also used by the JIT compiler.
1054  \fBpcre_dfa_exec()\fP. You might want to do this if your pattern contains  The optimizations can be disabled by setting the PCRE_NO_START_OPTIMIZE option
1055  callouts or (*MARK), and you want to make use of these facilities in cases  when calling \fBpcre_exec()\fP or \fBpcre_dfa_exec()\fP, but if this is done,
1056  where matching fails. See the discussion of PCRE_NO_START_OPTIMIZE  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">  .\" HTML <a href="#execoptions">
1060  .\" </a>  .\" </a>
1061  below.  below.
# Line 894  below. Line 1068  below.
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. By default, higher-valued codes never match escapes such as \ew  with codes less than 128. By default, higher-valued codes never match escapes
1073  or \ed, but they can be tested with \ep if PCRE is built with Unicode character  such as \ew or \ed, but they can be tested with \ep if PCRE is built with
1074  property support. Alternatively, the PCRE_UCP option can be set at compile  Unicode character property support. Alternatively, the PCRE_UCP option can be
1075  time; this causes \ew and friends to use Unicode property support instead of  set at compile time; this causes \ew and friends to use Unicode property
1076  built-in tables. The use of locales with Unicode is discouraged. If you are  support instead of built-in tables. The use of locales with Unicode is
1077  handling characters with codes greater than 128, you should either use UTF-8  discouraged. If you are handling characters with codes greater than 128, you
1078  and Unicode, or use locales, but not try to mix the two.  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 955  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 965  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 1006  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  .P
1193  If there is a fixed first byte, for example, from a pattern such as  If there is a fixed first value, for example, the letter "c" from a pattern
1194  (cat|cow|coyote), its value is returned. Otherwise, if either  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
1198    If there is no fixed first value, and 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 1027  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 1043  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    PCRE_INFO_MINLENGTH
1265  .sp  .sp
1266  If the pattern was studied and a minimum length for matching subject strings  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  was computed, its value is returned. Otherwise the returned value is -1. The
1268  value is a number of characters, not bytes (this may be relevant in UTF-8  value is a number of characters, which in UTF-8 mode may be different from the
1269  mode). The fourth argument should point to an \fBint\fP variable. A  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  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  may not be any strings of that length that do actually match, but every string
1272  that does match is at least that long.  that does match is at least that long.
# Line 1081  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.  most significant byte first. In the 16-bit library, the pointer points to
1295    16-bit data units, the first of which contains the parenthesis number. The rest
1296    of the entry is the corresponding name, zero terminated.
1297  .P  .P
1298  The names are in alphabetical order. Duplicate names may appear if (?| is used  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  to create multiple groups with the same number, as described in the
# Line 1102  table in the order in which they were fo Line 1312  table in the order in which they were fo
1312  necessarily the case because later subpatterns may have lower numbers.  necessarily the case because later subpatterns may have lower numbers.
1313  .P  .P
1314  As a simple example of the name/number table, consider the following pattern  As a simple example of the name/number table, consider the following pattern
1315  (assume PCRE_EXTENDED is set, so white space - including newlines - is  after compilation by the 8-bit library (assume PCRE_EXTENDED is set, so white
1316  ignored):  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 1158  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
 \fBpcre_malloc()\fP when PCRE was getting memory into which to place the data  
 created by \fBpcre_study()\fP. If \fBpcre_extra\fP is NULL, or there is no  
1384  study data, zero is returned. The fourth argument should point to a  study data, zero is returned. The fourth argument should point to a
1385  \fBsize_t\fP variable.  \fBsize_t\fP variable. The \fIstudy_data\fP field is set by \fBpcre_study()\fP
1386  .  to record information that will speed up matching (see the section entitled
1387  .  .\" HTML <a href="#studyingapattern">
1388  .SH "OBSOLETE INFO FUNCTION"  .\" </a>
1389  .rs  "Studying a pattern"
1390  .sp  .\"
1391  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int  above). The format of the \fIstudy_data\fP block is private, but its length
1392  .B *\fIfirstcharptr\fP);  is made available via this option so that it can be saved and restored (see the
1393  .PP  .\" HREF
1394  The \fBpcre_info()\fP function is now obsolete because its interface is too  \fBpcreprecompile\fP
1395  restrictive to return all the available data about a compiled pattern. New  .\"
1396  programs should use \fBpcre_fullinfo()\fP instead. The yield of  documentation for details).
 \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 1232  is different. (This seems a highly unlik Line 1431  is different. (This seems a highly unlik
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 was 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 1265  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 1277  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;    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
   PCRE_EXTRA_MARK  
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 a pattern that uses 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 1323  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 1356  called. See the Line 1573  called. See the
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  .P
1575  If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must  If PCRE_EXTRA_MARK is set in the \fIflags\fP field, the \fImark\fP field must
1576  be set to point to a \fBchar *\fP variable. If the pattern contains any  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  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  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  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  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  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 set to NULL. For details of the  variable pointed to by the \fImark\fP field is set to NULL. For details of the
1583  backtracking control verbs, see the section entitled  backtracking control verbs, see the section entitled
1584  .\" HTML <a href="pcrepattern#backtrackcontrol">  .\" HTML <a href="pcrepattern#backtrackcontrol">
1585  .\" </a>  .\" </a>
# Line 1382  documentation. Line 1599  documentation.
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 1502  causing performance to suffer, but ensur Line 1726  causing performance to suffer, but ensur
1726  "no match", the callouts do occur, and that items such as (*COMMIT) and (*MARK)  "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  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  PCRE_NO_START_OPTIMIZE is set at compile time, it cannot be unset at matching
1729  time.  time. The use of PCRE_NO_START_OPTIMIZE disables JIT execution; when it is set,
1730    matching is always done using interpretively.
1731  .P  .P
1732  Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.  Setting PCRE_NO_START_OPTIMIZE can change the outcome of a matching operation.
1733  Consider the pattern  Consider the pattern
# Line 1535  returned. Line 1760  returned.
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 or, if PCRE_PARTIAL_HARD is set and the problem is  error PCRE_ERROR_BADUTF8 or, if PCRE_PARTIAL_HARD is set and the problem is a
1776  a truncated UTF-8 character at the end of the subject, PCRE_ERROR_SHORTUTF8. In  truncated character at the end of the subject, PCRE_ERROR_SHORTUTF8. In both
1777  both cases, information about the precise nature of the error may also be  cases, information about the precise nature of the error may also be returned
1778  returned (see the descriptions of these errors in the section entitled \fIError  (see the descriptions of these errors in the section entitled \fIError return
1779  return values from\fP \fBpcre_exec()\fP  values from\fP \fBpcre_exec()\fP
1780  .\" HTML <a href="#errorlist">  .\" HTML <a href="#errorlist">
1781  .\" </a>  .\" </a>
1782  below).  below).
# Line 1565  checks for performance reasons, you can Line 1790  checks for performance reasons, you can
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 (or the  the value of \fIstartoffset\fP points to the start of a character (or the end
1794  end of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an  of the subject). When PCRE_NO_UTF8_CHECK is set, the effect of passing an
1795  invalid UTF-8 string as a subject or an invalid value of \fIstartoffset\fP is  invalid string as a subject or an invalid value of \fIstartoffset\fP is
1796  undefined. Your program may crash.  undefined. Your program may crash.
1797  .sp  .sp
1798    PCRE_PARTIAL_HARD    PCRE_PARTIAL_HARD
# Line 1602  documentation. Line 1827  documentation.
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. If this is negative or greater than the length of the  in \fIstartoffset\fP. If this is negative or greater than the length of the
1832  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting  subject, \fBpcre_exec()\fP returns PCRE_ERROR_BADOFFSET. When the starting
1833  offset is zero, the search for a match starts at the beginning of the subject,  offset is zero, the search for a match starts at the beginning of the subject,
# Line 1690  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_fullinfo()\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
# Line 1716  return from the function is 2, because t Line 1956  return from the function is 2, because t
1956  number is 1, and the offsets for for the second and third capturing subpatterns  number is 1, and the offsets for for the second and third capturing subpatterns
1957  (assuming the vector is large enough, of course) are set to -1.  (assuming the vector is large enough, of course) are set to -1.
1958  .P  .P
1959  \fBNote\fP: Elements of \fIovector\fP that do not correspond to capturing  \fBNote\fP: Elements in the first two-thirds of \fIovector\fP that do not
1960  parentheses in the pattern are never changed. That is, if a pattern contains  correspond to capturing parentheses in the pattern are never changed. That is,
1961  \fIn\fP capturing parentheses, no more than \fIovector[0]\fP to  if a pattern contains \fIn\fP capturing parentheses, no more than
1962  \fIovector[2n+1]\fP are set by \fBpcre_exec()\fP. The other elements retain  \fIovector[0]\fP to \fIovector[2n+1]\fP are set by \fBpcre_exec()\fP. The other
1963  whatever values they previously had.  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.
# Line 1810  PCRE_ERROR_SHORTUTF8 is returned instead Line 2050  PCRE_ERROR_SHORTUTF8 is returned instead
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 checked and found to  The UTF-8 byte sequence that was passed as a subject was checked and found to
2054  be valid (the PCRE_NO_UTF8_CHECK option was not set), but the value of  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  \fIstartoffset\fP did not point to the beginning of a UTF-8 character or the
2056  end of the subject.  end of the subject.
# Line 1865  retained for backwards compatibility. Line 2105  retained for backwards compatibility.
2105  .sp  .sp
2106    PCRE_ERROR_RECURSELOOP    (-26)    PCRE_ERROR_RECURSELOOP    (-26)
2107  .sp  .sp
2108  This error is returned when \fBpcre_exec()\fP detects a recursion loop within  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  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  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  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  faulted at compile time, but more complicated cases, in particular mutual
2113  recursions between two different subpatterns, cannot be detected until run  recursions between two different subpatterns, cannot be detected until run
2114  time.  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  .P
2138  Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.  Error numbers -16 to -20, -22, and -30 are not used by \fBpcre_exec()\fP.
2139  .  .
2140  .  .
2141  .\" HTML <a name="badutf8reasons"></a>  .\" HTML <a name="badutf8reasons"></a>
2142  .SS "Reason codes for invalid UTF-8 strings"  .SS "Reason codes for invalid UTF-8 strings"
2143  .rs  .rs
2144  .sp  .sp
2145  When \fBpcre_exec()\fP returns either PCRE_ERROR_BADUTF8 or  This section applies only to the 8-bit library. The corresponding information
2146  PCRE_ERROR_SHORTUTF8, and the size of the output vector (\fIovecsize\fP) is at  for the 16-bit library is given in the
2147  least 2, the offset of the start of the invalid UTF-8 character is placed in  .\" HREF
2148  the first output vector element (\fIovector[0]\fP) and a reason code is placed  \fBpcre16\fP
2149    .\"
2150    page.
2151    .P
2152    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  in the second element (\fIovector[1]\fP). The reason codes are given names in
2157  the \fBpcre.h\fP header file:  the \fBpcre.h\fP header file:
2158  .sp  .sp
# Line 1893  the \fBpcre.h\fP header file: Line 2162  the \fBpcre.h\fP header file:
2162    PCRE_UTF8_ERR4    PCRE_UTF8_ERR4
2163    PCRE_UTF8_ERR5    PCRE_UTF8_ERR5
2164  .sp  .sp
2165  The string ends with a truncated UTF-8 character; the code specifies how many  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  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)  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  allows for up to 6 bytes, and this is checked first; hence the possibility of
2169  4 or 5 missing bytes.  4 or 5 missing bytes.
2170  .sp  .sp
2171    PCRE_UTF8_ERR6    PCRE_UTF8_ERR6
# Line 1905  allows for up to 6 bytes, and this is ch Line 2174  allows for up to 6 bytes, and this is ch
2174    PCRE_UTF8_ERR9    PCRE_UTF8_ERR9
2175    PCRE_UTF8_ERR10    PCRE_UTF8_ERR10
2176  .sp  .sp
2177  The two most significant bits of the 2nd, 3rd, 4th, 5th, or 6th byte of the  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  character do not have the binary value 0b10 (that is, either the most
2179  significant bit is 0, or the next bit is 1).  significant bit is 0, or the next bit is 1).
2180  .sp  .sp
2181    PCRE_UTF8_ERR11    PCRE_UTF8_ERR11
2182    PCRE_UTF8_ERR12    PCRE_UTF8_ERR12
2183  .sp  .sp
2184  A character that is valid by the RFC 2279 rules is either 5 or 6 bytes long;  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.  these code points are excluded by RFC 3629.
2186  .sp  .sp
2187    PCRE_UTF8_ERR13    PCRE_UTF8_ERR13
2188  .sp  .sp
2189  A 4-byte character has a value greater than 0x10fff; these code points are  A 4-byte character has a value greater than 0x10fff; these code points are
2190  excluded by RFC 3629.  excluded by RFC 3629.
2191  .sp  .sp
2192    PCRE_UTF8_ERR14    PCRE_UTF8_ERR14
2193  .sp  .sp
2194  A 3-byte character has a value in the range 0xd800 to 0xdfff; this range of  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  code points are reserved by RFC 3629 for use with UTF-16, and so are excluded
2196  from UTF-8.  from UTF-8.
2197  .sp  .sp
2198    PCRE_UTF8_ERR15    PCRE_UTF8_ERR15
2199    PCRE_UTF8_ERR16    PCRE_UTF8_ERR16
2200    PCRE_UTF8_ERR17    PCRE_UTF8_ERR17
2201    PCRE_UTF8_ERR18    PCRE_UTF8_ERR18
2202    PCRE_UTF8_ERR19    PCRE_UTF8_ERR19
2203  .sp  .sp
2204  A 2-, 3-, 4-, 5-, or 6-byte character is "overlong", that is, it codes for a  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,  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  the two bytes 0xc0, 0xae give the value 0x2e, whose correct coding uses just
2207  one byte.  one byte.
2208  .sp  .sp
2209    PCRE_UTF8_ERR20    PCRE_UTF8_ERR20
2210  .sp  .sp
2211  The two most significant bits of the first byte of a character have the binary  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  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  byte can only validly occur as the second or subsequent byte of a multi-byte
2214  character.  character.
2215  .sp  .sp
# Line 2112  names are not included in the compiled c Line 2381  names are not included in the compiled c
2381  numbers. For this reason, the use of different names for subpatterns of the  numbers. For this reason, the use of different names for subpatterns of the
2382  same number causes an error at compile time.  same number causes an error at compile time.
2383  .  .
2384    .
2385  .SH "DUPLICATE SUBPATTERN NAMES"  .SH "DUPLICATE SUBPATTERN NAMES"
2386  .rs  .rs
2387  .sp  .sp
# Line 2176  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 2311  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"
# Line 2341  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 2355  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 2379  Cambridge CB2 3QH, England. Line 2684  Cambridge CB2 3QH, England.
2684  .rs  .rs
2685  .sp  .sp
2686  .nf  .nf
2687  Last updated: 28 July 2011  Last updated: 07 September 2012
2688  Copyright (c) 1997-2011 University of Cambridge.  Copyright (c) 1997-2012 University of Cambridge.
2689  .fi  .fi

Legend:
Removed from v.642  
changed lines
  Added in v.1031

  ViewVC Help
Powered by ViewVC 1.1.5