/[pcre]/code/trunk/doc/pcreapi.3

Diff of /code/trunk/doc/pcreapi.3

Parent Directory | Revision Log | View Patch Patch

-revision 77 by nigel,
Sat Feb 24 21:40:45 2007 UTC
+revision 429 by ph10,
Tue Sep  1 16:10:16 2009 UTC
 Line 1
- .TH PCRE 3
+ .TH PCREAPI 3
  .SH NAME
  PCRE - Perl-compatible regular expressions
  .SH "PCRE NATIVE API"
 Line 7 
 PCRE - Perl-compatible regular expressio
  .B #include <pcre.h>
  .PP
  .SM
- .br
  .B pcre *pcre_compile(const char *\fIpattern\fP, int \fIoptions\fP,
  .ti +5n
  .B const char **\fIerrptr\fP, int *\fIerroffset\fP,
  .ti +5n
  .B const unsigned char *\fItableptr\fP);
  .PP
- .br
  .B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
  .ti +5n
  .B int *\fIerrorcodeptr\fP,
-Line 23 
 PCRE - Perl-compatible regular expressio
+Line 21 
 PCRE - Perl-compatible regular expressio
  .ti +5n
  .B const unsigned char *\fItableptr\fP);
  .PP
- .br
  .B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP,
  .ti +5n
  .B const char **\fIerrptr\fP);
  .PP
- .br
  .B int pcre_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
  .ti +5n
  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
  .ti +5n
  .B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP);
  .PP
- .br
  .B int pcre_dfa_exec(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
  .ti +5n
  .B "const char *\fIsubject\fP," int \fIlength\fP, int \fIstartoffset\fP,
-Line 44 
 PCRE - Perl-compatible regular expressio
+Line 39 
 PCRE - Perl-compatible regular expressio
  .ti +5n
  .B int *\fIworkspace\fP, int \fIwscount\fP);
  .PP
- .br
  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
  .ti +5n
  .B const char *\fIsubject\fP, int *\fIovector\fP,
-Line 53 
 PCRE - Perl-compatible regular expressio
+Line 47 
 PCRE - Perl-compatible regular expressio
  .ti +5n
  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
  .PP
- .br
  .B int pcre_copy_substring(const char *\fIsubject\fP, int *\fIovector\fP,
  .ti +5n
  .B int \fIstringcount\fP, int \fIstringnumber\fP, char *\fIbuffer\fP,
  .ti +5n
  .B int \fIbuffersize\fP);
  .PP
- .br
  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
  .ti +5n
  .B const char *\fIsubject\fP, int *\fIovector\fP,
-Line 69 
 PCRE - Perl-compatible regular expressio
+Line 61 
 PCRE - Perl-compatible regular expressio
  .ti +5n
  .B const char **\fIstringptr\fP);
  .PP
- .br
  .B int pcre_get_stringnumber(const pcre *\fIcode\fP,
  .ti +5n
  .B const char *\fIname\fP);
  .PP
- .br
+ .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
+ .ti +5n
+ .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
+ .PP
  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
  .ti +5n
  .B int \fIstringcount\fP, int \fIstringnumber\fP,
  .ti +5n
  .B const char **\fIstringptr\fP);
  .PP
- .br
  .B int pcre_get_substring_list(const char *\fIsubject\fP,
  .ti +5n
  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
  .PP
- .br
  .B void pcre_free_substring(const char *\fIstringptr\fP);
  .PP
- .br
  .B void pcre_free_substring_list(const char **\fIstringptr\fP);
  .PP
- .br
  .B const unsigned char *pcre_maketables(void);
  .PP
- .br
  .B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
  .ti +5n
  .B int \fIwhat\fP, void *\fIwhere\fP);
  .PP
- .br
  .B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
  .B *\fIfirstcharptr\fP);
  .PP
- .br
  .B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
  .PP
- .br
  .B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
  .PP
- .br
  .B char *pcre_version(void);
  .PP
- .br
  .B void *(*pcre_malloc)(size_t);
  .PP
- .br
  .B void (*pcre_free)(void *);
  .PP
- .br
  .B void *(*pcre_stack_malloc)(size_t);
  .PP
- .br
  .B void (*pcre_stack_free)(void *);
  .PP
- .br
  .B int (*pcre_callout)(pcre_callout_block *);
  .
  .
  .SH "PCRE API OVERVIEW"
  .rs
  .sp
- PCRE has its own native API, which is described in this document. There is
+ PCRE has its own native API, which is described in this document. There are
- also a set of wrapper functions that correspond to the POSIX regular expression
+ also some wrapper functions that correspond to the POSIX regular expression
  API. These are described in the
  .\" HREF
  \fBpcreposix\fP
-Line 155 
 Applications can use these to include su
+Line 135 
 Applications can use these to include su
  The functions \fBpcre_compile()\fP, \fBpcre_compile2()\fP, \fBpcre_study()\fP,
  and \fBpcre_exec()\fP are used for compiling and matching regular expressions
  in a Perl-compatible manner. A sample program that demonstrates the simplest
- way of using them is provided in the file called \fIpcredemo.c\fP in the source
+ way of using them is provided in the file called \fIpcredemo.c\fP in the PCRE
- distribution. The
+ source distribution. A listing of this program is given in the
+ .\" HREF
+ \fBpcredemo\fP
+ .\"
+ documentation, and the
  .\" HREF
  \fBpcresample\fP
  .\"
- documentation describes how to run it.
+ documentation describes how to compile and run it.
  .P
  A second matching function, \fBpcre_dfa_exec()\fP, which is not
  Perl-compatible, is also provided. This uses a different algorithm for the
- matching. This allows it to find all possible matches (at a given point in the
+ matching. The alternative algorithm finds all possible matches (at a given
- subject), not just one. However, this algorithm does not return captured
+ point in the subject), and scans the subject just once. However, this algorithm
- substrings. A description of the two matching algorithms and their advantages
+ does not return captured substrings. A description of the two matching
- and disadvantages is given in the
+ algorithms and their advantages and disadvantages is given in the
  .\" HREF
  \fBpcrematching\fP
  .\"
-Line 183 
 matched by \fBpcre_exec()\fP. They are:
+Line 167 
 matched by \fBpcre_exec()\fP. They are:
    \fBpcre_get_named_substring()\fP
    \fBpcre_get_substring_list()\fP
    \fBpcre_get_stringnumber()\fP
+   \fBpcre_get_stringtable_entries()\fP
  .sp
  \fBpcre_free_substring()\fP and \fBpcre_free_substring_list()\fP are also
  provided, to free the memory used for extracted strings.
-Line 212 
 should be done before calling any PCRE f
+Line 197 
 should be done before calling any PCRE f
  The global variables \fBpcre_stack_malloc\fP and \fBpcre_stack_free\fP are also
  indirections to memory management functions. These special functions are used
  only when PCRE is compiled to use the heap for remembering data, instead of
- recursive function calls, when running the \fBpcre_exec()\fP function. This is
+ recursive function calls, when running the \fBpcre_exec()\fP function. See the
- a non-standard way of building PCRE, for use in environments that have limited
+ .\" HREF
- stacks. Because of the greater use of memory management, it runs more slowly.
+ \fBpcrebuild\fP
- Separate functions are provided so that special-purpose external code can be
+ .\"
- used for this case. When used, these functions are always called in a
+ documentation for details of how to do this. It is a non-standard way of
- stack-like manner (last obtained, first freed), and always for memory blocks of
+ building PCRE, for use in environments that have limited stacks. Because of the
- the same size.
+ greater use of memory management, it runs more slowly. Separate functions are
+ provided so that special-purpose external code can be used for this case. When
+ used, these functions are always called in a stack-like manner (last obtained,
+ first freed), and always for memory blocks of the same size. There is a
+ discussion about PCRE's stack usage in the
+ .\" HREF
+ \fBpcrestack\fP
+ .\"
+ documentation.
  .P
  The global variable \fBpcre_callout\fP initially contains NULL. It can be set
  by the caller to a "callout" function, which PCRE will then call at specified
-Line 229 
 points during a matching operation. Deta
+Line 222 
 points during a matching operation. Deta
  documentation.
  .
  .
+ .\" HTML <a name="newlines"></a>
+ .SH NEWLINES
+ .rs
+ .sp
+ PCRE supports five different conventions for indicating line breaks in
+ strings: a single CR (carriage return) character, a single LF (linefeed)
+ character, the two-character sequence CRLF, any of the three preceding, or any
+ Unicode newline sequence. The Unicode newline sequences are the three just
+ mentioned, plus the single characters VT (vertical tab, U+000B), FF (formfeed,
+ U+000C), NEL (next line, U+0085), LS (line separator, U+2028), and PS
+ (paragraph separator, U+2029).
+ .P
+ Each of the first three conventions is used by at least one operating system as
+ its standard newline sequence. When PCRE is built, a default can be specified.
+ The default default is LF, which is the Unix standard. When PCRE is run, the
+ default can be overridden, either when a pattern is compiled, or when it is
+ matched.
+ .P
+ At compile time, the newline convention can be specified by the \fIoptions\fP
+ argument of \fBpcre_compile()\fP, or it can be specified by special text at the
+ start of the pattern itself; this overrides any other settings. See the
+ .\" HREF
+ \fBpcrepattern\fP
+ .\"
+ page for details of the special character sequences.
+ .P
+ In the PCRE documentation the word "newline" is used to mean "the character or
+ pair of characters that indicate a line break". The choice of newline
+ convention affects the handling of the dot, circumflex, and dollar
+ metacharacters, the handling of #-comments in /x mode, and, when CRLF is a
+ recognized line ending sequence, the match position advancement for a
+ non-anchored pattern. There is more detail about this in the
+ .\" HTML <a href="#execoptions">
+ .\" </a>
+ section on \fBpcre_exec()\fP options
+ .\"
+ below.
+ .P
+ The choice of newline convention does not affect the interpretation of
+ the \en or \er escape sequences, nor does it affect what \eR matches, which is
+ controlled in a similar way, but by separate options.
+ .
+ .
  .SH MULTITHREADING
  .rs
  .sp
-Line 250 
 which it was compiled. Details are given
+Line 286 
 which it was compiled. Details are given
  .\" HREF
  \fBpcreprecompile\fP
  .\"
- documentation.
+ documentation. However, compiling a regular expression with one version of PCRE
+ for use with a different version is not guaranteed to work and may cause
+ crashes.
  .
  .
  .SH "CHECKING BUILD-TIME OPTIONS"
-Line 281 
 properties is available; otherwise it is
+Line 319 
 properties is available; otherwise it is
  .sp
    PCRE_CONFIG_NEWLINE
  .sp
- The output is an integer that is set to the value of the code that is used for
+ The output is an integer whose value specifies the default character sequence
- the newline character. It is either linefeed (10) or carriage return (13), and
+ that is recognized as meaning "newline". The four values that are supported
- should normally be the standard character for your operating system.
+ are: 10 for LF, 13 for CR, 3338 for CRLF, -2 for ANYCRLF, and -1 for ANY.
+ Though they are derived from ASCII, the same values are returned in EBCDIC
+ environments. The default should normally correspond to the standard sequence
+ for your operating system.
+ .sp
+   PCRE_CONFIG_BSR
+ .sp
+ The output is an integer whose value indicates what character sequences the \eR
+ escape sequence matches by default. A value of 0 means that \eR matches any
+ Unicode line ending sequence; a value of 1 means that \eR matches only CR, LF,
+ or CRLF. The default can be overridden when a pattern is compiled or matched.
  .sp
    PCRE_CONFIG_LINK_SIZE
  .sp
-Line 305 
 documentation.
+Line 353 
 documentation.
  .sp
    PCRE_CONFIG_MATCH_LIMIT
  .sp
- The output is an integer that gives the default limit for the number of
+ The output is a long integer that gives the default limit for the number of
  internal matching function calls in a \fBpcre_exec()\fP execution. Further
  details are given with \fBpcre_exec()\fP below.
  .sp
+   PCRE_CONFIG_MATCH_LIMIT_RECURSION
+ .sp
+ The output is a long integer that gives the default limit for the depth of
+ recursion when calling the internal matching function in a \fBpcre_exec()\fP
+ execution. Further details are given with \fBpcre_exec()\fP below.
+ .sp
    PCRE_CONFIG_STACKRECURSE
  .sp
  The output is an integer that is set to one if internal recursion when running
-Line 347 
 The pattern is a C string terminated by
+Line 401 
 The pattern is a C string terminated by
  via \fBpcre_malloc\fP is returned. This contains the compiled code and related
  data. The \fBpcre\fP type is defined for the returned block; this is a typedef
  for a structure whose contents are not externally defined. It is up to the
- caller to free the memory when it is no longer required.
+ caller to free the memory (via \fBpcre_free\fP) when it is no longer required.
  .P
  Although the compiled code of a PCRE regex is relocatable, that is, it does not
  depend on memory location, the complete \fBpcre\fP data block is not
  fully relocatable, because it may contain a copy of the \fItableptr\fP
  argument, which is an address (see below).
  .P
- The \fIoptions\fP argument contains independent bits that affect the
+ The \fIoptions\fP argument contains various bit settings that affect the
  compilation. It should be zero if no options are required. The available
- options are described below. Some of them, in particular, those that are
+ options are described below. Some of them (in particular, those that are
- compatible with Perl, can also be set and unset from within the pattern (see
+ compatible with Perl, but also some others) can also be set and unset from
- the detailed description in the
+ within the pattern (see the detailed description in the
  .\" HREF
  \fBpcrepattern\fP
  .\"
- documentation). For these options, the contents of the \fIoptions\fP argument
+ documentation). For those options that can be different in different parts of
- specifies their initial settings at the start of compilation and execution. The
+ the pattern, the contents of the \fIoptions\fP argument specifies their initial
- PCRE_ANCHORED option can be set at the time of matching as well as at compile
+ settings at the start of compilation and execution. The PCRE_ANCHORED and
- time.
+ PCRE_NEWLINE_\fIxxx\fP options can be set at the time of matching as well as at
+ compile time.
  .P
  If \fIerrptr\fP is NULL, \fBpcre_compile()\fP returns NULL immediately.
  Otherwise, if compilation of a pattern fails, \fBpcre_compile()\fP returns
  NULL, and sets the variable pointed to by \fIerrptr\fP to point to a textual
- error message. The offset from the start of the pattern to the character where
+ error message. This is a static string that is part of the library. You must
- the error was discovered is placed in the variable pointed to by
+ not try to free it. The offset from the start of the pattern to the character
+ where the error was discovered is placed in the variable pointed to by
  \fIerroffset\fP, which must not be NULL. If it is, an immediate error is given.
  .P
  If \fBpcre_compile2()\fP is used instead of \fBpcre_compile()\fP, and the
-Line 419 
 facility, see the
+Line 475 
 facility, see the
  .\"
  documentation.
  .sp
+   PCRE_BSR_ANYCRLF
+   PCRE_BSR_UNICODE
+ .sp
+ These options (which are mutually exclusive) control what the \eR escape
+ sequence matches. The choice is either to match only CR, LF, or CRLF, or to
+ match any Unicode newline sequence. The default is specified when PCRE is
+ built. It can be overridden from within the pattern, or by setting an option
+ when a compiled pattern is matched.
+ .sp
    PCRE_CASELESS
  .sp
  If this bit is set, letters in the pattern match both upper and lower case
-Line 435 
 with UTF-8 support.
+Line 500 
 with UTF-8 support.
  .sp
  If this bit is set, a dollar metacharacter in the pattern matches only at the
  end of the subject string. Without this option, a dollar also matches
- immediately before the final character if it is a newline (but not before any
+ immediately before a newline at the end of the string (but not before any other
- other newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is
+ newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set.
- set. There is no equivalent to this option in Perl, and no way to set it within
+ There is no equivalent to this option in Perl, and no way to set it within a
- a pattern.
+ pattern.
  .sp
    PCRE_DOTALL
  .sp
  If this bit is set, a dot metacharater in the pattern matches all characters,
- including newlines. Without it, newlines are excluded. This option is
+ including those that indicate newline. Without it, a dot does not match when
- equivalent to Perl's /s option, and it can be changed within a pattern by a
+ the current position is at a newline. This option is equivalent to Perl's /s
- (?s) option setting. A negative class such as [^a] always matches a newline
+ option, and it can be changed within a pattern by a (?s) option setting. A
- character, independent of the setting of this option.
+ negative class such as [^a] always matches newline characters, independent of
+ the setting of this option.
+ .sp
+   PCRE_DUPNAMES
+ .sp
+ If this bit is set, names used to identify capturing subpatterns need not be
+ unique. This can be helpful for certain types of pattern when it is known that
+ only one instance of the named subpattern can ever be matched. There are more
+ details of named subpatterns below; see also the
+ .\" HREF
+ \fBpcrepattern\fP
+ .\"
+ documentation.
  .sp
    PCRE_EXTENDED
  .sp
  If this bit is set, whitespace data characters in the pattern are totally
  ignored except when escaped or inside a character class. Whitespace does not
  include the VT character (code 11). In addition, characters between an
- unescaped # outside a character class and the next newline character,
+ unescaped # outside a character class and the next newline, inclusive, are also
- inclusive, are also ignored. This is equivalent to Perl's /x option, and it can
+ ignored. This is equivalent to Perl's /x option, and it can be changed within a
- be changed within a pattern by a (?x) option setting.
+ pattern by a (?x) option setting.
  .P
  This option makes it possible to include comments inside complicated patterns.
  Note, however, that this applies only to data characters. Whitespace characters
-Line 469 
 that is incompatible with Perl, but it i
+Line 546 
 that is incompatible with Perl, but it i
  set, any backslash in a pattern that is followed by a letter that has no
  special meaning causes an error, thus reserving these combinations for future
  expansion. By default, as in Perl, a backslash followed by a letter with no
- special meaning is treated as a literal. There are at present no other features
+ special meaning is treated as a literal. (Perl can, however, be persuaded to
- controlled by this option. It can also be set by a (?X) option setting within a
+ give a warning for this.) There are at present no other features controlled by
- pattern.
+ this option. It can also be set by a (?X) option setting within a pattern.
  .sp
    PCRE_FIRSTLINE
  .sp
  If this option is set, an unanchored pattern is required to match before or at
- the first newline character in the subject string, though the matched text may
+ the first newline in the subject string, though the matched text may continue
- continue over the newline.
+ over the newline.
+ .sp
+   PCRE_JAVASCRIPT_COMPAT
+ .sp
+ If this option is set, PCRE's behaviour is changed in some ways so that it is
+ compatible with JavaScript rather than Perl. The changes are as follows:
+ .P
+ (1) A lone closing square bracket in a pattern causes a compile-time error,
+ because this is illegal in JavaScript (by default it is treated as a data
+ character). Thus, the pattern AB]CD becomes illegal when this option is set.
+ .P
+ (2) At run time, a back reference to an unset subpattern group matches an empty
+ string (by default this causes the current matching alternative to fail). A
+ pattern such as (\e1)(a) succeeds when this option is set (assuming it can find
+ an "a" in the subject), whereas it fails by default, for Perl compatibility.
  .sp
    PCRE_MULTILINE
  .sp
-Line 489 
 terminating newline (unless PCRE_DOLLAR_
+Line 580 
 terminating newline (unless PCRE_DOLLAR_
  Perl.
  .P
  When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
- match immediately following or immediately before any newline in the subject
+ match immediately following or immediately before internal newlines in the
- string, respectively, as well as at the very start and end. This is equivalent
+ subject string, respectively, as well as at the very start and end. This is
- to Perl's /m option, and it can be changed within a pattern by a (?m) option
+ equivalent to Perl's /m option, and it can be changed within a pattern by a
- setting. If there are no "\en" characters in a subject string, or no
+ (?m) option setting. If there are no newlines in a subject string, or no
  occurrences of ^ or $ in a pattern, setting PCRE_MULTILINE has no effect.
  .sp
+   PCRE_NEWLINE_CR
+   PCRE_NEWLINE_LF
+   PCRE_NEWLINE_CRLF
+   PCRE_NEWLINE_ANYCRLF
+   PCRE_NEWLINE_ANY
+ .sp
+ These options override the default newline definition that was chosen when PCRE
+ was built. Setting the first or the second specifies that a newline is
+ indicated by a single character (CR or LF, respectively). Setting
+ PCRE_NEWLINE_CRLF specifies that a newline is indicated by the two-character
+ CRLF sequence. Setting PCRE_NEWLINE_ANYCRLF specifies that any of the three
+ preceding sequences should be recognized. Setting PCRE_NEWLINE_ANY specifies
+ that any Unicode newline sequence should be recognized. The Unicode newline
+ sequences are the three just mentioned, plus the single characters VT (vertical
+ tab, U+000B), FF (formfeed, U+000C), NEL (next line, U+0085), LS (line
+ separator, U+2028), and PS (paragraph separator, U+2029). The last two are
+ recognized only in UTF-8 mode.
+ .P
+ The newline setting in the options word uses three bits that are treated
+ as a number, giving eight possibilities. Currently only six are used (default
+ plus the five values above). This means that if you set more than one newline
+ option, the combination may or may not be sensible. For example,
+ PCRE_NEWLINE_CR with PCRE_NEWLINE_LF is equivalent to PCRE_NEWLINE_CRLF, but
+ other combinations may yield unused numbers and cause an error.
+ .P
+ The only time that a line break is specially recognized when compiling a
+ pattern is if PCRE_EXTENDED is set, and an unescaped # outside a character
+ class is encountered. This indicates a comment that lasts until after the next
+ line break sequence. In other circumstances, line break sequences are treated
+ as literal data, except that in PCRE_EXTENDED mode, both CR and LF are treated
+ as whitespace characters and are therefore ignored.
+ .P
+ The newline option that is set at compile time becomes the default that is used
+ for \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, but it can be overridden.
+ .sp
    PCRE_NO_AUTO_CAPTURE
  .sp
  If this option is set, it disables the use of numbered capturing parentheses in
-Line 529 
 page.
+Line 655 
 page.
    PCRE_NO_UTF8_CHECK
  .sp
  When PCRE_UTF8 is set, the validity of the pattern as a UTF-8 string is
- automatically checked. If an invalid UTF-8 sequence of bytes is found,
+ automatically checked. There is a discussion about the
- \fBpcre_compile()\fP returns an error. If you already know that your pattern is
+ .\" HTML <a href="pcre.html#utf8strings">
- valid, and you want to skip this check for performance reasons, you can set the
+ .\" </a>
- PCRE_NO_UTF8_CHECK option. When it is set, the effect of passing an invalid
+ validity of UTF-8 strings
- UTF-8 string as a pattern is undefined. It may cause your program to crash.
+ .\"
- Note that this option can also be passed to \fBpcre_exec()\fP and
+ in the main
- \fBpcre_dfa_exec()\fP, to suppress the UTF-8 validity checking of subject
+ .\" HREF
- strings.
+ \fBpcre\fP
+ .\"
+ page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_compile()\fP
+ returns an error. If you already know that your pattern is valid, and you want
+ to skip this check for performance reasons, you can set the PCRE_NO_UTF8_CHECK
+ option. When it is set, the effect of passing an invalid UTF-8 string as a
+ pattern is undefined. It may cause your program to crash. Note that this option
+ can also be passed to \fBpcre_exec()\fP and \fBpcre_dfa_exec()\fP, to suppress
+ the UTF-8 validity checking of subject strings.
  .
  .
  .SH "COMPILATION ERROR CODES"
-Line 544 
 strings.
+Line 678 
 strings.
  .sp
  The following table lists the error codes than may be returned by
  \fBpcre_compile2()\fP, along with the error messages that may be returned by
- both compiling functions.
+ both compiling functions. As PCRE has developed, some error codes have fallen
+ out of use. To avoid confusion, they have not been re-used.
  .sp
  no error
  \e at end of pattern
-Line 556 
 both compiling functions.
+Line 691 
 both compiling functions.
  invalid escape sequence in character class
  range out of order in character class
  nothing to repeat
- operand of unlimited repeat could match the empty string
+ [this code is not in use]
  internal error: unexpected repeat
- unrecognized character after (?
+ unrecognized character after (? or (?-
  POSIX named classes are supported only within a class
  missing )
  reference to non-existent subpattern
  erroffset passed as NULL
  unknown option bit(s) set
  missing ) after comment
- parentheses nested too deeply
+ [this code is not in use]
- regular expression too large
+ regular expression is too large
  failed to get memory
  unmatched parentheses
  internal error: code overflow
  unrecognized character after (?<
  lookbehind assertion is not fixed length
- malformed number after (?(
+ malformed number or name after (?(
  conditional group contains more than two branches
  assertion expected after (?(
- (?R or (?digits must be followed by )
+ (?R or (?[+-]digits must be followed by )
  unknown POSIX class name
  POSIX collating elements are not supported
  this version of PCRE is not compiled with PCRE_UTF8 support
- spare error
+ [this code is not in use]
  character value in \ex{...} sequence is too large
  invalid condition (?(0)
  \eC not allowed in lookbehind assertion
-Line 588 
 both compiling functions.
+Line 723 
 both compiling functions.
  closing ) for (?C expected
  recursive call could loop indefinitely
  unrecognized character after (?P
- syntax error after (?P
+ syntax error in subpattern name (missing terminator)
- two named groups have the same name
+ two named subpatterns have the same name
  invalid UTF-8 string
  support for \eP, \ep, and \eX has not been compiled
  malformed \eP or \ep sequence
  unknown property name after \eP or \ep
+ subpattern name is too long (maximum 32 characters)
+ too many named subpatterns (maximum 10000)
+ [this code is not in use]
+ octal value is greater than \e377 (not in UTF-8 mode)
+ internal error: overran compiling workspace
+ internal error: previously-checked referenced subpattern not found
+ DEFINE group contains more than one branch
+ repeating a DEFINE group is not allowed
+ inconsistent NEWLINE options
+ \eg is not followed by a braced, angle-bracketed, or quoted
+         name/number or by a plain number
+ a numbered reference must not be zero
+ (*VERB) with an argument is not supported
+ (*VERB) not recognized
+ number is too big
+ subpattern name expected
+ digit expected after (?+
+ ] is an invalid data character in JavaScript compatibility mode
+ .sp
+ The numbers 32 and 10000 in errors 48 and 49 are defaults; different values may
+ be used if the limits were changed when PCRE was built.
  .
  .
  .SH "STUDYING A PATTERN"
-Line 631 
 options are defined, and this argument s
+Line 787 
 options are defined, and this argument s
  .P
  The third argument for \fBpcre_study()\fP is a pointer for an error message. If
  studying succeeds (even if no data is returned), the variable it points to is
- set to NULL. Otherwise it points to a textual error message. You should
+ set to NULL. Otherwise it is set to point to a textual error message. This is a
- therefore test the error pointer for NULL after calling \fBpcre_study()\fP, to
+ static string that is part of the library. You must not try to free it. You
- be sure that it has run successfully.
+ should test the error pointer for NULL after calling \fBpcre_study()\fP, to be
+ sure that it has run successfully.
  .P
  This is a typical call to \fBpcre_study\fP():
  .sp
-Line 652 
 bytes is created.
+Line 809 
 bytes is created.
  .SH "LOCALE SUPPORT"
  .rs
  .sp
- PCRE handles caseless matching, and determines whether characters are letters
+ PCRE handles caseless matching, and determines whether characters are letters,
  digits, or whatever, by reference to a set of tables, indexed by character
  value. When running in UTF-8 mode, this applies only to characters with codes
  less than 128. Higher-valued codes never match escapes such as \ew or \ed, but
  can be tested with \ep if PCRE is built with Unicode character property
- support.
+ support. The use of locales with Unicode is discouraged. If you are handling
- .P
+ characters with codes greater than 128, you should either use UTF-8 and
- An internal set of tables is created in the default C locale when PCRE is
+ Unicode, or use locales, but not try to mix the two.
- built. This is used when the final argument of \fBpcre_compile()\fP is NULL,
+ .P
- and is sufficient for many applications. An alternative set of tables can,
+ PCRE contains an internal set of tables that are used when the final argument
- however, be supplied. These may be created in a different locale from the
+ of \fBpcre_compile()\fP is NULL. These are sufficient for many applications.
- default. As more and more applications change to using Unicode, the need for
+ Normally, the internal tables recognize only ASCII characters. However, when
- this locale support is expected to die away.
+ PCRE is built, it is possible to cause the internal tables to be rebuilt in the
+ default "C" locale of the local system, which may cause them to be different.
+ .P
+ The internal tables can always be overridden by tables supplied by the
+ application that calls PCRE. These may be created in a different locale from
+ the default. As more and more applications change to using Unicode, the need
+ for this locale support is expected to die away.
  .P
  External tables are built by calling the \fBpcre_maketables()\fP function,
  which has no arguments, in the relevant locale. The result can then be passed
-Line 677 
 the following code could be used:
+Line 840 
 the following code could be used:
    tables = pcre_maketables();
    re = pcre_compile(..., tables);
  .sp
+ The locale name "fr_FR" is used on Linux and other Unix-like systems; if you
+ are using Windows, the name for the French locale is "french".
+ .P
  When \fBpcre_maketables()\fP runs, the tables are built in memory that is
  obtained via \fBpcre_malloc\fP. It is the caller's responsibility to ensure
  that the memory containing the tables remains available for as long as it is
-Line 723 
 check against passing an arbitrary memor
+Line 889 
 check against passing an arbitrary memor
  \fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
  .sp
    int rc;
-   unsigned long int length;
+   size_t length;
    rc = pcre_fullinfo(
      re,               /* result of pcre_compile() */
      pe,               /* result of pcre_study(), or NULL */
-Line 755 
 a NULL table pointer.
+Line 921 
 a NULL table pointer.
    PCRE_INFO_FIRSTBYTE
  .sp
  Return information about the first byte of any matched string, for a
- non-anchored pattern. (This option used to be called PCRE_INFO_FIRSTCHAR; the
+ non-anchored pattern. The fourth argument should point to an \fBint\fP
- old name is still recognized for backwards compatibility.)
+ variable. (This option used to be called PCRE_INFO_FIRSTCHAR; the old name is
+ still recognized for backwards compatibility.)
  .P
  If there is a fixed first byte, for example, from a pattern such as
- (cat|cow|coyote), it is returned in the integer pointed to by \fIwhere\fP.
+ (cat|cow|coyote), its value is returned. Otherwise, if either
- Otherwise, if either
  .sp
  (a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
  starts with "^", or
-Line 779 
 table indicating a fixed set of bytes fo
+Line 945 
 table indicating a fixed set of bytes fo
  string, a pointer to the table is returned. Otherwise NULL is returned. The
  fourth argument should point to an \fBunsigned char *\fP variable.
  .sp
+   PCRE_INFO_HASCRORLF
+ .sp
+ Return 1 if the pattern contains any explicit matches for CR or LF characters,
+ otherwise 0. The fourth argument should point to an \fBint\fP variable. An
+ explicit match is either a literal CR or LF character, or \er or \en.
+ .sp
+   PCRE_INFO_JCHANGED
+ .sp
+ Return 1 if the (?J) or (?-J) option setting is used in the pattern, otherwise
+. The fourth argument should point to an \fBint\fP variable. (?J) and
+ (?-J) set and unset the local PCRE_DUPNAMES option, respectively.
+ .sp
    PCRE_INFO_LASTLITERAL
  .sp
  Return the value of the rightmost literal byte that must exist in any matched
-Line 795 
 is -1.
+Line 973 
 is -1.
  .sp
  PCRE supports the use of named as well as numbered capturing parentheses. The
  names are just an additional way of identifying the parentheses, which still
- acquire numbers. A convenience function called \fBpcre_get_named_substring()\fP
+ acquire numbers. Several convenience functions such as
- is provided for extracting an individual captured substring by name. It is also
+ \fBpcre_get_named_substring()\fP are provided for extracting captured
- possible to extract the data directly, by first converting the name to a number
+ substrings by name. It is also possible to extract the data directly, by first
- in order to access the correct pointers in the output vector (described with
+ converting the name to a number in order to access the correct pointers in the
- \fBpcre_exec()\fP below). To do the conversion, you need to use the
+ output vector (described with \fBpcre_exec()\fP below). To do the conversion,
- name-to-number map, which is described by these three values.
+ you need to use the name-to-number map, which is described by these three
+ values.
  .P
  The map consists of a number of fixed-size entries. PCRE_INFO_NAMECOUNT gives
  the number of entries, and PCRE_INFO_NAMEENTRYSIZE gives the size of each
-Line 809 
 length of the longest name. PCRE_INFO_NA
+Line 988 
 length of the longest name. PCRE_INFO_NA
  entry of the table (a pointer to \fBchar\fP). The first two bytes of each entry
  are the number of the capturing parenthesis, most significant byte first. The
  rest of the entry is the corresponding name, zero terminated. The names are in
- alphabetical order. For example, consider the following pattern (assume
+ alphabetical order. When PCRE_DUPNAMES is set, duplicate names are in order of
+ their parentheses numbers. For example, consider the following pattern (assume
  PCRE_EXTENDED is set, so white space - including newlines - is ignored):
  .sp
  .\" JOIN
-   (?P<date> (?P<year>(\ed\ed)?\ed\ed) -
+   (?<date> (?<year>(\ed\ed)?\ed\ed) -
-   (?P<month>\ed\ed) - (?P<day>\ed\ed) )
+   (?<month>\ed\ed) - (?<day>\ed\ed) )
  .sp
  There are four named subpatterns, so the table has four entries, and each entry
  in the table is eight bytes long. The table is as follows, with non-printing
-Line 826 
 bytes shows in hexadecimal, and undefine
+Line 1006 
 bytes shows in hexadecimal, and undefine
 02 y  e  a  r  00 ??
  .sp
  When writing code to extract data from named subpatterns using the
- name-to-number map, remember that the length of each entry is likely to be
+ name-to-number map, remember that the length of the entries is likely to be
  different for each compiled pattern.
  .sp
+   PCRE_INFO_OKPARTIAL
+ .sp
+ Return 1 if the pattern can be used for partial matching, otherwise 0. The
+ fourth argument should point to an \fBint\fP variable. From release 8.00, this
+ always returns 1, because the restrictions that previously applied to partial
+ matching have been lifted. The
+ .\" HREF
+ \fBpcrepartial\fP
+ .\"
+ documentation gives details of partial matching.
+ .sp
    PCRE_INFO_OPTIONS
  .sp
  Return a copy of the options with which the pattern was compiled. The fourth
  argument should point to an \fBunsigned long int\fP variable. These option bits
  are those specified in the call to \fBpcre_compile()\fP, modified by any
- top-level option settings within the pattern itself.
+ top-level option settings at the start of the pattern itself. In other words,
+ they are the options that will be in force when matching starts. For example,
+ if the pattern /(?im)abc(?-i)d/ is compiled with the PCRE_EXTENDED option, the
+ result is PCRE_CASELESS, PCRE_MULTILINE, and PCRE_EXTENDED.
  .P
  A pattern is automatically anchored by PCRE if all of its top-level
  alternatives begin with one of the following:
-Line 964 
 Here is an example of a simple call to \
+Line 1158 
 Here is an example of a simple call to \
  If the \fIextra\fP argument is not NULL, it must point to a \fBpcre_extra\fP
  data block. The \fBpcre_study()\fP function returns such a block (when it
  doesn't return NULL), but you can also create one for yourself, and pass
- additional information in it. The fields in a \fBpcre_extra\fP block are as
+ additional information in it. The \fBpcre_extra\fP block contains the following
- follows:
+ fields (not necessarily in this order):
  .sp
    unsigned long int \fIflags\fP;
    void *\fIstudy_data\fP;
    unsigned long int \fImatch_limit\fP;
+   unsigned long int \fImatch_limit_recursion\fP;
    void *\fIcallout_data\fP;
    const unsigned char *\fItables\fP;
  .sp
-Line 978 
 are set. The flag bits are:
+Line 1173 
 are set. The flag bits are:
  .sp
    PCRE_EXTRA_STUDY_DATA
    PCRE_EXTRA_MATCH_LIMIT
+   PCRE_EXTRA_MATCH_LIMIT_RECURSION
    PCRE_EXTRA_CALLOUT_DATA
    PCRE_EXTRA_TABLES
  .sp
-Line 992 
 but which have a very large number of po
+Line 1188 
 but which have a very large number of po
  classic example is the use of nested unlimited repeats.
  .P
  Internally, PCRE uses a function called \fBmatch()\fP which it calls repeatedly
- (sometimes recursively). The limit is imposed on the number of times this
+ (sometimes recursively). The limit set by \fImatch_limit\fP is imposed on the
- function is called during a match, which has the effect of limiting the amount
+ number of times this function is called during a match, which has the effect of
- of recursion and backtracking that can take place. For patterns that are not
+ limiting the amount of backtracking that can take place. For patterns that are
- anchored, the count starts from zero for each position in the subject string.
+ not anchored, the count restarts from zero for each position in the subject
+ string.
  .P
- The default limit for the library can be set when PCRE is built; the default
+ The default value for the limit can be set when PCRE is built; the default
  default is 10 million, which handles all but the most extreme cases. You can
- reduce the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP block
+ override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP
- in which \fImatch_limit\fP is set to a smaller value, and
+ block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in
- PCRE_EXTRA_MATCH_LIMIT is set in the \fIflags\fP field. If the limit is
+ the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns
- exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_MATCHLIMIT.
+ PCRE_ERROR_MATCHLIMIT.
+ .P
+ The \fImatch_limit_recursion\fP field is similar to \fImatch_limit\fP, but
+ instead of limiting the total number of times that \fBmatch()\fP is called, it
+ limits the depth of recursion. The recursion depth is a smaller number than the
+ total number of calls, because not all calls to \fBmatch()\fP are recursive.
+ This limit is of use only if it is set smaller than \fImatch_limit\fP.
+ .P
+ Limiting the recursion depth limits the amount of stack that can be used, or,
+ when PCRE has been compiled to use memory on the heap instead of the stack, the
+ amount of heap memory that can be used.
+ .P
+ The default value for \fImatch_limit_recursion\fP can be set when PCRE is
+ built; the default default is the same value as the default for
+ \fImatch_limit\fP. You can override the default by suppling \fBpcre_exec()\fP
+ with a \fBpcre_extra\fP block in which \fImatch_limit_recursion\fP is set, and
+ PCRE_EXTRA_MATCH_LIMIT_RECURSION is set in the \fIflags\fP field. If the limit
+ is exceeded, \fBpcre_exec()\fP returns PCRE_ERROR_RECURSIONLIMIT.
  .P
  The \fIpcre_callout\fP field is used in conjunction with the "callout" feature,
  which is described in the
-Line 1025 
 called. See the
+Line 1239 
 called. See the
  .\"
  documentation for a discussion of saving compiled patterns for later use.
  .
+ .\" HTML <a name="execoptions"></a>
  .SS "Option bits for \fBpcre_exec()\fP"
  .rs
  .sp
  The unused bits of the \fIoptions\fP argument for \fBpcre_exec()\fP must be
- zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NOTBOL,
+ zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
- PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
+ PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_START_OPTIMIZE,
+ PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_SOFT, and PCRE_PARTIAL_HARD.
  .sp
    PCRE_ANCHORED
  .sp
-Line 1039 
 matching position. If a pattern was comp
+Line 1255 
 matching position. If a pattern was comp
  to be anchored by virtue of its contents, it cannot be made unachored at
  matching time.
  .sp
+   PCRE_BSR_ANYCRLF
+   PCRE_BSR_UNICODE
+ .sp
+ These options (which are mutually exclusive) control what the \eR escape
+ sequence matches. The choice is either to match only CR, LF, or CRLF, or to
+ match any Unicode newline sequence. These options override the choice that was
+ made or defaulted when the pattern was compiled.
+ .sp
+   PCRE_NEWLINE_CR
+   PCRE_NEWLINE_LF
+   PCRE_NEWLINE_CRLF
+   PCRE_NEWLINE_ANYCRLF
+   PCRE_NEWLINE_ANY
+ .sp
+ These options override the newline definition that was chosen or defaulted when
+ the pattern was compiled. For details, see the description of
+ \fBpcre_compile()\fP above. During matching, the newline choice affects the
+ behaviour of the dot, circumflex, and dollar metacharacters. It may also alter
+ the way the match position is advanced after a match failure for an unanchored
+ pattern.
+ .P
+ When PCRE_NEWLINE_CRLF, PCRE_NEWLINE_ANYCRLF, or PCRE_NEWLINE_ANY is set, and a
+ match attempt for an unanchored pattern fails when the current position is at a
+ CRLF sequence, and the pattern contains no explicit matches for CR or LF
+ characters, the match position is advanced by two characters instead of one, in
+ other words, to after the CRLF.
+ .P
+ The above rule is a compromise that makes the most common cases work as
+ expected. For example, if the pattern is .+A (and the PCRE_DOTALL option is not
+ set), it does not match the string "\er\enA" because, after failing at the
+ start, it skips both the CR and the LF before retrying. However, the pattern
+ [\er\en]A does match that string, because it contains an explicit CR or LF
+ reference, and so advances only by one character after the first failure.
+ .P
+ An explicit match for CR of LF is either a literal appearance of one of those
+ characters, or one of the \er or \en escape sequences. Implicit matches such as
+ [^X] do not count, nor does \es (which includes CR and LF in the characters
+ that it matches).
+ .P
+ Notwithstanding the above, anomalous effects may still occur when CRLF is a
+ valid newline sequence and explicit \er or \en escapes appear in the pattern.
+ .sp
    PCRE_NOTBOL
  .sp
  This option specifies that first character of the subject string is not the
-Line 1073 
 when using the /g modifier. It is possib
+Line 1331 
 when using the /g modifier. It is possib
  matching a null string by first trying the match again at the same offset with
  PCRE_NOTEMPTY and PCRE_ANCHORED, and then if that fails by advancing the
  starting offset (see below) and trying an ordinary match again. There is some
- code that demonstrates how to do this in the \fIpcredemo.c\fP sample program.
+ code that demonstrates how to do this in the
+ .\" HREF
+ \fBpcredemo\fP
+ .\"
+ sample program.
+ .sp
+   PCRE_NO_START_OPTIMIZE
+ .sp
+ There are a number of optimizations that \fBpcre_exec()\fP uses at the start of
+ a match, in order to speed up the process. For example, if it is known that a
+ match must start with a specific character, it searches the subject for that
+ character, and fails immediately if it cannot find it, without actually running
+ the main matching function. When callouts are in use, these optimizations can
+ cause them to be skipped. This option disables the "start-up" optimizations,
+ causing performance to suffer, but ensuring that the callouts do occur.
  .sp
    PCRE_NO_UTF8_CHECK
  .sp
  When PCRE_UTF8 is set at compile time, the validity of the subject as a UTF-8
  string is automatically checked when \fBpcre_exec()\fP is subsequently called.
  The value of \fIstartoffset\fP is also checked to ensure that it points to the
- start of a UTF-8 character. If an invalid UTF-8 sequence of bytes is found,
+ start of a UTF-8 character. There is a discussion about the validity of UTF-8
- \fBpcre_exec()\fP returns the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP
+ strings in the
- contains an invalid value, PCRE_ERROR_BADUTF8_OFFSET is returned.
+ .\" HTML <a href="pcre.html#utf8strings">
+ .\" </a>
+ section on UTF-8 support
+ .\"
+ in the main
+ .\" HREF
+ \fBpcre\fP
+ .\"
+ page. If an invalid UTF-8 sequence of bytes is found, \fBpcre_exec()\fP returns
+ the error PCRE_ERROR_BADUTF8. If \fIstartoffset\fP contains an invalid value,
+ PCRE_ERROR_BADUTF8_OFFSET is returned.
  .P
  If you already know that your subject is valid, and you want to skip these
  checks for performance reasons, you can set the PCRE_NO_UTF8_CHECK option when
-Line 1094 
 PCRE_NO_UTF8_CHECK is set, the effect of
+Line 1376 
 PCRE_NO_UTF8_CHECK is set, the effect of
  subject, or a value of \fIstartoffset\fP that does not point to the start of a
  UTF-8 character, is undefined. Your program may crash.
  .sp
-   PCRE_PARTIAL
+   PCRE_PARTIAL_HARD
+   PCRE_PARTIAL_SOFT
  .sp
- This option turns on the partial matching feature. If the subject string fails
+ These options turn on the partial matching feature. For backwards
- to match the pattern, but at some point during the matching process the end of
+ compatibility, PCRE_PARTIAL is a synonym for PCRE_PARTIAL_SOFT. A partial match
- the subject was reached (that is, the subject partially matches the pattern and
+ occurs if the end of the subject string is reached successfully, but there are
- the failure to match occurred only because there were not enough subject
+ not enough subject characters to complete the match. If this happens when
- characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of
+ PCRE_PARTIAL_HARD is set, \fBpcre_exec()\fP immediately returns
- PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what
+ PCRE_ERROR_PARTIAL. Otherwise, if PCRE_PARTIAL_SOFT is set, matching continues
- may appear in the pattern. These are discussed in the
+ by testing any other alternatives. Only if they all fail is PCRE_ERROR_PARTIAL
+ returned (instead of PCRE_ERROR_NOMATCH). The portion of the string that
+ provided the partial match is set as the first matching string. There is a more
+ detailed discussion in the
  .\" HREF
  \fBpcrepartial\fP
  .\"
-Line 1112 
 documentation.
+Line 1398 
 documentation.
  .rs
  .sp
  The subject string is passed to \fBpcre_exec()\fP as a pointer in
- \fIsubject\fP, a length in \fIlength\fP, and a starting byte offset in
+ \fIsubject\fP, a length (in bytes) in \fIlength\fP, and a starting byte offset
- \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a
+ in \fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of
- UTF-8 character. Unlike the pattern string, the subject may contain binary zero
+ a UTF-8 character. Unlike the pattern string, the subject may contain binary
- bytes. When the starting offset is zero, the search for a match starts at the
+ zero bytes. When the starting offset is zero, the search for a match starts at
- beginning of the subject, and this is by far the most common case.
+ the beginning of the subject, and this is by far the most common case.
  .P
  A non-zero starting offset is useful when searching for another match in the
  same subject by calling \fBpcre_exec()\fP again after a previous success.
-Line 1150 
 pattern. Following the usage in Jeffrey
+Line 1436 
 pattern. Following the usage in Jeffrey
  a fragment of a pattern that picks out a substring. PCRE supports several other
  kinds of parenthesized subpattern that do not cause substrings to be captured.
  .P
- Captured substrings are returned to the caller via a vector of integer offsets
+ Captured substrings are returned to the caller via a vector of integers whose
- whose address is passed in \fIovector\fP. The number of elements in the vector
+ address is passed in \fIovector\fP. The number of elements in the vector is
- is passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP:
+ passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP: this
- this argument is NOT the size of \fIovector\fP in bytes.
+ argument is NOT the size of \fIovector\fP in bytes.
  .P
  The first two-thirds of the vector is used to pass back captured substrings,
  each substring using a pair of integers. The remaining third of the vector is
  used as workspace by \fBpcre_exec()\fP while matching capturing subpatterns,
- and is not available for passing back information. The length passed in
+ and is not available for passing back information. The number passed in
  \fIovecsize\fP should always be a multiple of three. If it is not, it is
  rounded down.
  .P
  When a match is successful, information about captured substrings is returned
  in pairs of integers, starting at the beginning of \fIovector\fP, and
- continuing up to two-thirds of its length at the most. The first element of a
+ continuing up to two-thirds of its length at the most. The first element of
- pair is set to the offset of the first character in a substring, and the second
+ each pair is set to the byte offset of the first character in a substring, and
- is set to the offset of the first character after the end of a substring. The
+ the second is set to the byte offset of the first character after the end of a
- first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the
+ substring. \fBNote\fP: these values are always byte offsets, even in UTF-8
- subject string matched by the entire pattern. The next pair is used for the
+ mode. They are not character counts.
- first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP
+ .P
- is the number of pairs that have been set. If there are no capturing
+ The first pair of integers, \fIovector[0]\fP and \fIovector[1]\fP, identify the
- subpatterns, the return value from a successful match is 1, indicating that
+ portion of the subject string matched by the entire pattern. The next pair is
- just the first pair of offsets has been set.
+ used for the first capturing subpattern, and so on. The value returned by
- .P
+ \fBpcre_exec()\fP is one more than the highest numbered pair that has been set.
- Some convenience functions are provided for extracting the captured substrings
+ For example, if two substrings have been captured, the returned value is 3. If
- as separate strings. These are described in the following section.
+ there are no capturing subpatterns, the return value from a successful match is
- .P
+, indicating that just the first pair of offsets has been set.
- It is possible for an capturing subpattern number \fIn+1\fP to match some
- part of the subject when subpattern \fIn\fP has not been used at all. For
- example, if the string "abc" is matched against the pattern (a|(z))(bc)
- subpatterns 1 and 3 are matched, but 2 is not. When this happens, both offset
- values corresponding to the unused subpattern are set to -1.
  .P
  If a capturing subpattern is matched repeatedly, it is the last portion of the
  string that it matched that is returned.
  .P
  If the vector is too small to hold all the captured substring offsets, it is
  used as far as possible (up to two-thirds of its length), and the function
- returns a value of zero. In particular, if the substring offsets are not of
+ returns a value of zero. If the substring offsets are not of interest,
- interest, \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and
+ \fBpcre_exec()\fP may be called with \fIovector\fP passed as NULL and
  \fIovecsize\fP as zero. However, if the pattern contains back references and
  the \fIovector\fP is not big enough to remember the related substrings, PCRE
  has to get additional memory for use during matching. Thus it is usually
  advisable to supply an \fIovector\fP.
  .P
- Note that \fBpcre_info()\fP can be used to find out how many capturing
+ The \fBpcre_info()\fP function can be used to find out how many capturing
  subpatterns there are in a compiled pattern. The smallest size for
  \fIovector\fP that will allow for \fIn\fP captured substrings, in addition to
  the offsets of the substring matched by the whole pattern, is (\fIn\fP+1)*3.
+ .P
+ It is possible for capturing subpattern number \fIn+1\fP to match some part of
+ the subject when subpattern \fIn\fP has not been used at all. For example, if
+ the string "abc" is matched against the pattern (a|(z))(bc) the return from the
+ function is 4, and subpatterns 1 and 3 are matched, but 2 is not. When this
+ happens, both values in the offset pairs corresponding to unused subpatterns
+ are set to -1.
+ .P
+ Offset values that correspond to unused subpatterns at the end of the
+ expression are also set to -1. For example, if the string "abc" is matched
+ against the pattern (abc)(x(yz)?)? subpatterns 2 and 3 are not matched. The
+ return from the function is 2, because the highest used capturing subpattern
+ number is 1. However, you can refer to the offsets for the second and third
+ capturing subpatterns if you wish (assuming the vector is large enough, of
+ course).
+ .P
+ Some convenience functions are provided for extracting the captured substrings
+ as separate strings. These are described below.
  .
  .\" HTML <a name="errorlist"></a>
- .SS "Return values from \fBpcre_exec()\fP"
+ .SS "Error return values from \fBpcre_exec()\fP"
  .rs
  .sp
  If \fBpcre_exec()\fP fails, it returns a negative number. The following are
-Line 1228 
 compiled in an environment of one endian
+Line 1527 
 compiled in an environment of one endian
  other endianness. This is the error that PCRE gives when the magic number is
  not present.
  .sp
-   PCRE_ERROR_UNKNOWN_NODE   (-5)
+   PCRE_ERROR_UNKNOWN_OPCODE (-5)
  .sp
  While running the pattern match, an unknown item was encountered in the
  compiled pattern. This error could be caused by a bug in PCRE or by overwriting
-Line 1250 
 below). It is never returned by \fBpcre_
+Line 1549 
 below). It is never returned by \fBpcre_
  .sp
    PCRE_ERROR_MATCHLIMIT     (-8)
  .sp
- The recursion and backtracking limit, as specified by the \fImatch_limit\fP
+ The backtracking limit, as specified by the \fImatch_limit\fP field in a
- field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
+ \fBpcre_extra\fP structure (or defaulted) was reached. See the description
- description above.
+ above.
  .sp
    PCRE_ERROR_CALLOUT        (-9)
  .sp
-Line 1282 
 documentation for details of partial mat
+Line 1581 
 documentation for details of partial mat
  .sp
    PCRE_ERROR_BADPARTIAL     (-13)
  .sp
- The PCRE_PARTIAL option was used with a compiled pattern containing items that
+ This code is no longer in use. It was formerly returned when the PCRE_PARTIAL
- are not supported for partial matching. See the
+ option was used with a compiled pattern containing items that were not
- .\" HREF
+ supported for partial matching. From release 8.00 onwards, there are no
- \fBpcrepartial\fP
+ restrictions on partial matching.
- .\"
- documentation for details of partial matching.
  .sp
    PCRE_ERROR_INTERNAL       (-14)
  .sp
-Line 1297 
 in PCRE or by overwriting of the compile
+Line 1594 
 in PCRE or by overwriting of the compile
    PCRE_ERROR_BADCOUNT       (-15)
  .sp
  This error is given if the value of the \fIovecsize\fP argument is negative.
+ .sp
+   PCRE_ERROR_RECURSIONLIMIT (-21)
+ .sp
+ The internal recursion limit, as specified by the \fImatch_limit_recursion\fP
+ field in a \fBpcre_extra\fP structure (or defaulted) was reached. See the
+ description above.
+ .sp
+   PCRE_ERROR_BADNEWLINE     (-23)
+ .sp
+ An invalid combination of PCRE_NEWLINE_\fIxxx\fP options was given.
+ .P
+ Error numbers -16 to -20 and -22 are not used by \fBpcre_exec()\fP.
  .
  .
  .SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
-Line 1308 
 This error is given if the value of the
+Line 1617 
 This error is given if the value of the
  .ti +5n
  .B int \fIbuffersize\fP);
  .PP
- .br
  .B int pcre_get_substring(const char *\fIsubject\fP, int *\fIovector\fP,
  .ti +5n
  .B int \fIstringcount\fP, int \fIstringnumber\fP,
  .ti +5n
  .B const char **\fIstringptr\fP);
  .PP
- .br
  .B int pcre_get_substring_list(const char *\fIsubject\fP,
  .ti +5n
  .B int *\fIovector\fP, int \fIstringcount\fP, "const char ***\fIlistptr\fP);"
-Line 1326 
 Captured substrings can be accessed dire
+Line 1633 
 Captured substrings can be accessed dire
  \fBpcre_get_substring_list()\fP are provided for extracting captured substrings
  as new, separate, zero-terminated strings. These functions identify substrings
  by number. The next section describes functions for extracting named
- substrings. A substring that contains a binary zero is correctly extracted and
+ substrings.
- has a further zero added on the end, but the result is not, of course,
+ .P
- a C string.
+ A substring that contains a binary zero is correctly extracted and has a
+ further zero added on the end, but the result is not, of course, a C string.
+ However, you can process such a string by referring to the length that is
+ returned by \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP.
+ Unfortunately, the interface to \fBpcre_get_substring_list()\fP is not adequate
+ for handling strings containing binary zeros, because the end of the final
+ string is not independently indicated.
  .P
  The first three arguments are the same for all three of these functions:
  \fIsubject\fP is the subject string that has just been successfully matched,
-Line 1348 
 the string is placed in \fIbuffer\fP, wh
+Line 1661 
 the string is placed in \fIbuffer\fP, wh
  \fIbuffersize\fP, while for \fBpcre_get_substring()\fP a new block of memory is
  obtained via \fBpcre_malloc\fP, and its address is returned via
  \fIstringptr\fP. The yield of the function is the length of the string, not
- including the terminating zero, or one of
+ including the terminating zero, or one of these error codes:
  .sp
    PCRE_ERROR_NOMEMORY       (-6)
  .sp
-Line 1364 
 and builds a list of pointers to them. A
+Line 1677 
 and builds a list of pointers to them. A
  memory that is obtained via \fBpcre_malloc\fP. The address of the memory block
  is returned via \fIlistptr\fP, which is also the start of the list of string
  pointers. The end of the list is marked by a NULL pointer. The yield of the
- function is zero if all went well, or
+ function is zero if all went well, or the error code
  .sp
    PCRE_ERROR_NOMEMORY       (-6)
  .sp
-Line 1383 
 a previous call of \fBpcre_get_substring
+Line 1696 
 a previous call of \fBpcre_get_substring
  \fBpcre_get_substring_list()\fP, respectively. They do nothing more than call
  the function pointed to by \fBpcre_free\fP, which of course could be called
  directly from a C program. However, PCRE is used in some situations where it is
- linked via a special interface to another programming language which cannot use
+ linked via a special interface to another programming language that cannot use
  \fBpcre_free\fP directly; it is for these cases that the functions are
  provided.
  .
-Line 1395 
 provided.
+Line 1708 
 provided.
  .ti +5n
  .B const char *\fIname\fP);
  .PP
- .br
  .B int pcre_copy_named_substring(const pcre *\fIcode\fP,
  .ti +5n
  .B const char *\fIsubject\fP, int *\fIovector\fP,
-Line 1404 
 provided.
+Line 1716 
 provided.
  .ti +5n
  .B char *\fIbuffer\fP, int \fIbuffersize\fP);
  .PP
- .br
  .B int pcre_get_named_substring(const pcre *\fIcode\fP,
  .ti +5n
  .B const char *\fIsubject\fP, int *\fIovector\fP,
-Line 1418 
 For example, for this pattern
+Line 1729 
 For example, for this pattern
  .sp
    (a+)b(?<xxx>\ed+)...
  .sp
- the number of the subpattern called "xxx" is 2. You can find the number from
+ the number of the subpattern called "xxx" is 2. If the name is known to be
- the name by calling \fBpcre_get_stringnumber()\fP. The first argument is the
+ unique (PCRE_DUPNAMES was not set), you can find the number from the name by
- compiled pattern, and the second is the name. The yield of the function is the
+ calling \fBpcre_get_stringnumber()\fP. The first argument is the compiled
+ pattern, and the second is the name. The yield of the function is the
  subpattern number, or PCRE_ERROR_NOSUBSTRING (-7) if there is no subpattern of
  that name.
  .P
-Line 1428 
 Given the number, you can extract the su
+Line 1740 
 Given the number, you can extract the su
  functions described in the previous section. For convenience, there are also
  two functions that do the whole job.
  .P
- Most of the arguments of \fIpcre_copy_named_substring()\fP and
+ Most of the arguments of \fBpcre_copy_named_substring()\fP and
- \fIpcre_get_named_substring()\fP are the same as those for the similarly named
+ \fBpcre_get_named_substring()\fP are the same as those for the similarly named
  functions that extract by number. As these are described in the previous
  section, they are not re-described here. There are just two differences:
  .P
-Line 1439 
 pattern. This is needed in order to gain
+Line 1751 
 pattern. This is needed in order to gain
  translation table.
  .P
  These functions call \fBpcre_get_stringnumber()\fP, and if it succeeds, they
- then call \fIpcre_copy_substring()\fP or \fIpcre_get_substring()\fP, as
+ then call \fBpcre_copy_substring()\fP or \fBpcre_get_substring()\fP, as
- appropriate.
+ appropriate. \fBNOTE:\fP If PCRE_DUPNAMES is set and there are duplicate names,
+ the behaviour may not be what you want (see the next section).
+ .P
+ \fBWarning:\fP If the pattern uses the "(?|" feature to set up multiple
+ subpatterns with the same number, you cannot use names to distinguish them,
+ because names are not included in the compiled code. The matching process uses
+ only numbers.
+ .
+ .SH "DUPLICATE SUBPATTERN NAMES"
+ .rs
+ .sp
+ .B int pcre_get_stringtable_entries(const pcre *\fIcode\fP,
+ .ti +5n
+ .B const char *\fIname\fP, char **\fIfirst\fP, char **\fIlast\fP);
+ .PP
+ When a pattern is compiled with the PCRE_DUPNAMES option, names for subpatterns
+ are not required to be unique. Normally, patterns with duplicate names are such
+ that in any one match, only one of the named subpatterns participates. An
+ example is shown in the
+ .\" HREF
+ \fBpcrepattern\fP
+ .\"
+ documentation.
+ .P
+ When duplicates are present, \fBpcre_copy_named_substring()\fP and
+ \fBpcre_get_named_substring()\fP return the first substring corresponding to
+ the given name that is set. If none are set, PCRE_ERROR_NOSUBSTRING (-7) is
+ returned; no data is returned. The \fBpcre_get_stringnumber()\fP function
+ returns one of the numbers that are associated with the name, but it is not
+ defined which it is.
+ .P
+ If you want to get full details of all captured substrings for a given name,
+ you must use the \fBpcre_get_stringtable_entries()\fP function. The first
+ argument is the compiled pattern, and the second is the name. The third and
+ fourth are pointers to variables which are updated by the function. After it
+ has run, they point to the first and last entries in the name-to-number table
+ for the given name. The function itself returns the length of each entry, or
+ PCRE_ERROR_NOSUBSTRING (-7) if there are none. The format of the table is
+ described above in the section entitled \fIInformation about a pattern\fP.
+ Given all the relevant entries for the name, you can extract each of their
+ numbers, and hence the captured data, if any.
  .
  .
  .SH "FINDING ALL POSSIBLE MATCHES"
-Line 1478 
 will yield PCRE_ERROR_NOMATCH.
+Line 1830 
 will yield PCRE_ERROR_NOMATCH.
  .B int *\fIworkspace\fP, int \fIwscount\fP);
  .P
  The function \fBpcre_dfa_exec()\fP is called to match a subject string against
- a compiled pattern, using a "DFA" matching algorithm. This has different
+ a compiled pattern, using a matching algorithm that scans the subject string
- characteristics to the normal algorithm, and is not compatible with Perl. Some
+ just once, and does not backtrack. This has different characteristics to the
- of the features of PCRE patterns are not supported. Nevertheless, there are
+ normal algorithm, and is not compatible with Perl. Some of the features of PCRE
- times when this kind of matching can be useful. For a discussion of the two
+ patterns are not supported. Nevertheless, there are times when this kind of
- matching algorithms, see the
+ matching can be useful. For a discussion of the two matching algorithms, see
+ the
  .\" HREF
  \fBpcrematching\fP
  .\"
-Line 1497 
 here.
+Line 1850 
 here.
  The two additional arguments provide workspace for the function. The workspace
  vector should contain at least 20 elements. It is used for keeping track of
  multiple paths through the pattern tree. More workspace will be needed for
- patterns and subjects where there are a lot of possible matches.
+ patterns and subjects where there are a lot of potential matches.
  .P
- Here is an example of a simple call to \fBpcre_exec()\fP:
+ Here is an example of a simple call to \fBpcre_dfa_exec()\fP:
  .sp
    int rc;
    int ovector[10];
    int wspace[20];
-   rc = pcre_exec(
+   rc = pcre_dfa_exec(
      re,             /* result of pcre_compile() */
      NULL,           /* we didn't study the pattern */
      "some string",  /* the subject string */
-Line 1520 
 Here is an example of a simple call to \
+Line 1873 
 Here is an example of a simple call to \
  .rs
  .sp
  The unused bits of the \fIoptions\fP argument for \fBpcre_dfa_exec()\fP must be
- zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NOTBOL,
+ zero. The only bits that may be set are PCRE_ANCHORED, PCRE_NEWLINE_\fIxxx\fP,
- PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,
+ PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL_HARD,
- PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are
+ PCRE_PARTIAL_SOFT, PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last
- the same as for \fBpcre_exec()\fP, so their description is not repeated here.
+ four of these are exactly the same as for \fBpcre_exec()\fP, so their
- .sp
+ description is not repeated here.
-   PCRE_PARTIAL
+ .sp
- .sp
+   PCRE_PARTIAL_HARD
- This has the same general effect as it does for \fBpcre_exec()\fP, but the
+   PCRE_PARTIAL_SOFT
- details are slightly different. When PCRE_PARTIAL is set for
+ .sp
- \fBpcre_dfa_exec()\fP, the return code PCRE_ERROR_NOMATCH is converted into
+ These have the same general effect as they do for \fBpcre_exec()\fP, but the
- PCRE_ERROR_PARTIAL if the end of the subject is reached, there have been no
+ details are slightly different. When PCRE_PARTIAL_HARD is set for
- complete matches, but there is still at least one matching possibility. The
+ \fBpcre_dfa_exec()\fP, it returns PCRE_ERROR_PARTIAL if the end of the subject
- portion of the string that provided the partial match is set as the first
+ is reached and there is still at least one matching possibility that requires
- matching string.
+ additional characters. This happens even if some complete matches have also
+ been found. When PCRE_PARTIAL_SOFT is set, the return code PCRE_ERROR_NOMATCH
+ is converted into PCRE_ERROR_PARTIAL if the end of the subject is reached,
+ there have been no complete matches, but there is still at least one matching
+ possibility. The portion of the string that provided the longest partial match
+ is set as the first matching string in both cases.
  .sp
    PCRE_DFA_SHORTEST
  .sp
  Setting the PCRE_DFA_SHORTEST option causes the matching algorithm to stop as
- soon as it has found one match. Because of the way the DFA algorithm works,
+ soon as it has found one match. Because of the way the alternative algorithm
- this is necessarily the shortest possible match at the first possible matching
+ works, this is necessarily the shortest possible match at the first possible
- point in the subject string.
+ matching point in the subject string.
  .sp
    PCRE_DFA_RESTART
  .sp
- When \fBpcre_dfa_exec()\fP is called with the PCRE_PARTIAL option, and returns
+ When \fBpcre_dfa_exec()\fP returns a partial match, it is possible to call it
- a partial match, it is possible to call it again, with additional subject
+ again, with additional subject characters, and have it continue with the same
- characters, and have it continue with the same match. The PCRE_DFA_RESTART
+ match. The PCRE_DFA_RESTART option requests this action; when it is set, the
- option requests this action; when it is set, the \fIworkspace\fP and
+ \fIworkspace\fP and \fIwscount\fP options must reference the same vector as
- \fIwscount\fP options must reference the same vector as before because data
+ before because data about the match so far is left in them after a partial
- about the match so far is left in them after a partial match. There is more
+ match. There is more discussion of this facility in the
- discussion of this facility in the
  .\" HREF
  \fBpcrepartial\fP
  .\"
-Line 1579 
 the three matched strings are
+Line 1936 
 the three matched strings are
  On success, the yield of the function is a number greater than zero, which is
  the number of matched substrings. The substrings themselves are returned in
  \fIovector\fP. Each string uses two elements; the first is the offset to the
- start, and the second is the offset to the end. All the strings have the same
+ start, and the second is the offset to the end. In fact, all the strings have
- start offset. (Space could have been saved by giving this only once, but it was
+ the same start offset. (Space could have been saved by giving this only once,
- decided to retain some compatibility with the way \fBpcre_exec()\fP returns
+ but it was decided to retain some compatibility with the way \fBpcre_exec()\fP
- data, even though the meaning of the strings is different.)
+ returns data, even though the meaning of the strings is different.)
  .P
  The strings are returned in reverse order of length; that is, the longest
  matching string is given first. If there were too many matches to fit into
-Line 1609 
 that it does not support, for instance,
+Line 1966 
 that it does not support, for instance,
  .sp
    PCRE_ERROR_DFA_UCOND      (-17)
  .sp
- This return is given if \fBpcre_dfa_exec()\fP encounters a condition item in a
+ This return is given if \fBpcre_dfa_exec()\fP encounters a condition item that
- pattern that uses a back reference for the condition. This is not supported.
+ uses a back reference for the condition, or a test for recursion in a specific
+ group. These are not supported.
  .sp
    PCRE_ERROR_DFA_UMLIMIT    (-18)
  .sp
-Line 1629 
 When a recursive subpattern is processed
+Line 1987 
 When a recursive subpattern is processed
  recursively, using private vectors for \fIovector\fP and \fIworkspace\fP. This
  error is given if the output vector is not large enough. This should be
  extremely rare, as a vector of size 1000 is used.
- .P
+ .
- .in 0
+ .
- Last updated: 16 May 2005
+ .SH "SEE ALSO"
- .br
+ .rs
- Copyright (c) 1997-2005 University of Cambridge.
+ .sp
+ \fBpcrebuild\fP(3), \fBpcrecallout\fP(3), \fBpcrecpp(3)\fP(3),
+ \fBpcrematching\fP(3), \fBpcrepartial\fP(3), \fBpcreposix\fP(3),
+ \fBpcreprecompile\fP(3), \fBpcresample\fP(3), \fBpcrestack\fP(3).
+ .
+ .
+ .SH AUTHOR
+ .rs
+ .sp
+ .nf
+ Philip Hazel
+ University Computing Service
+ Cambridge CB2 3QH, England.
+ .fi
+ .
+ .
+ .SH REVISION
+ .rs
+ .sp
+ .nf
+ Last updated: 01 September 2009
+ Copyright (c) 1997-2009 University of Cambridge.
+ .fi

 Legend:



Removed from v.77
 


changed lines


 
Added in v.429
 Legend:



Removed from v.77
 


changed lines


 
Added in v.429
-Removed from v.77
+Added in v.429

webmaster@exim.org	ViewVC Help
Powered by ViewVC 1.1.12