forked from Mirrors/freeswitch
1790 lines
74 KiB
Groff
1790 lines
74 KiB
Groff
|
.TH PCREAPI 3
|
||
|
|
.SH NAME
|
||
|
|
PCRE - Perl-compatible regular expressions
|
||
|
|
.SH "PCRE NATIVE API"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
.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,
|
||
|
|
.ti +5n
|
||
|
|
.B const char **\fIerrptr\fP, int *\fIerroffset\fP,
|
||
|
|
.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,
|
||
|
|
.ti +5n
|
||
|
|
.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
|
||
|
|
.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,
|
||
|
|
.ti +5n
|
||
|
|
.B int \fIstringcount\fP, const char *\fIstringname\fP,
|
||
|
|
.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,
|
||
|
|
.ti +5n
|
||
|
|
.B int \fIstringcount\fP, const char *\fIstringname\fP,
|
||
|
|
.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
|
||
|
|
.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);"
|
||
|
|
.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
|
||
|
|
also a set of wrapper functions that correspond to the POSIX regular expression
|
||
|
|
API. These are described in the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcreposix\fP
|
||
|
|
.\"
|
||
|
|
documentation. Both of these APIs define a set of C function calls. A C++
|
||
|
|
wrapper is distributed with PCRE. It is documented in the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrecpp\fP
|
||
|
|
.\"
|
||
|
|
page.
|
||
|
|
.P
|
||
|
|
The native API C function prototypes are defined in the header file
|
||
|
|
\fBpcre.h\fP, and on Unix systems the library itself is called \fBlibpcre\fP.
|
||
|
|
It can normally be accessed by adding \fB-lpcre\fP to the command for linking
|
||
|
|
an application that uses PCRE. The header file defines the macros PCRE_MAJOR
|
||
|
|
and PCRE_MINOR to contain the major and minor release numbers for the library.
|
||
|
|
Applications can use these to include support for different releases of PCRE.
|
||
|
|
.P
|
||
|
|
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
|
||
|
|
distribution. The
|
||
|
|
.\" HREF
|
||
|
|
\fBpcresample\fP
|
||
|
|
.\"
|
||
|
|
documentation describes how to 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. The alternative algorithm finds all possible matches (at a given
|
||
|
|
point in the subject). However, this algorithm does not return captured
|
||
|
|
substrings. A description of the two matching algorithms and their advantages
|
||
|
|
and disadvantages is given in the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrematching\fP
|
||
|
|
.\"
|
||
|
|
documentation.
|
||
|
|
.P
|
||
|
|
In addition to the main compiling and matching functions, there are convenience
|
||
|
|
functions for extracting captured substrings from a subject string that is
|
||
|
|
matched by \fBpcre_exec()\fP. They are:
|
||
|
|
.sp
|
||
|
|
\fBpcre_copy_substring()\fP
|
||
|
|
\fBpcre_copy_named_substring()\fP
|
||
|
|
\fBpcre_get_substring()\fP
|
||
|
|
\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.
|
||
|
|
.P
|
||
|
|
The function \fBpcre_maketables()\fP is used to build a set of character tables
|
||
|
|
in the current locale for passing to \fBpcre_compile()\fP, \fBpcre_exec()\fP,
|
||
|
|
or \fBpcre_dfa_exec()\fP. This is an optional facility that is provided for
|
||
|
|
specialist use. Most commonly, no special tables are passed, in which case
|
||
|
|
internal tables that are generated when PCRE is built are used.
|
||
|
|
.P
|
||
|
|
The function \fBpcre_fullinfo()\fP is used to find out information about a
|
||
|
|
compiled pattern; \fBpcre_info()\fP is an obsolete version that returns only
|
||
|
|
some of the available information, but is retained for backwards compatibility.
|
||
|
|
The function \fBpcre_version()\fP returns a pointer to a string containing the
|
||
|
|
version of PCRE and its date of release.
|
||
|
|
.P
|
||
|
|
The function \fBpcre_refcount()\fP maintains a reference count in a data block
|
||
|
|
containing a compiled pattern. This is provided for the benefit of
|
||
|
|
object-oriented applications.
|
||
|
|
.P
|
||
|
|
The global variables \fBpcre_malloc\fP and \fBpcre_free\fP initially contain
|
||
|
|
the entry points of the standard \fBmalloc()\fP and \fBfree()\fP functions,
|
||
|
|
respectively. PCRE calls the memory management functions via these variables,
|
||
|
|
so a calling program can replace them if it wishes to intercept the calls. This
|
||
|
|
should be done before calling any PCRE functions.
|
||
|
|
.P
|
||
|
|
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. See the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrebuild\fP
|
||
|
|
.\"
|
||
|
|
documentation for details of how to do this. It is a non-standard way of
|
||
|
|
building PCRE, for use in environments that have limited stacks. Because of the
|
||
|
|
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
|
||
|
|
points during a matching operation. Details are given in the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrecallout\fP
|
||
|
|
.\"
|
||
|
|
documentation.
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.SH NEWLINES
|
||
|
|
PCRE supports three different conventions for indicating line breaks in
|
||
|
|
strings: a single CR character, a single LF character, or the two-character
|
||
|
|
sequence CRLF. All three are used as "standard" by different operating systems.
|
||
|
|
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.
|
||
|
|
.sp
|
||
|
|
In the PCRE documentation the word "newline" is used to mean "the character or
|
||
|
|
pair of characters that indicate a line break".
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.SH MULTITHREADING
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
The PCRE functions can be used in multi-threading applications, with the
|
||
|
|
proviso that the memory management functions pointed to by \fBpcre_malloc\fP,
|
||
|
|
\fBpcre_free\fP, \fBpcre_stack_malloc\fP, and \fBpcre_stack_free\fP, and the
|
||
|
|
callout function pointed to by \fBpcre_callout\fP, are shared by all threads.
|
||
|
|
.P
|
||
|
|
The compiled form of a regular expression is not altered during matching, so
|
||
|
|
the same compiled pattern can safely be used by several threads at once.
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.SH "SAVING PRECOMPILED PATTERNS FOR LATER USE"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
The compiled form of a regular expression can be saved and re-used at a later
|
||
|
|
time, possibly by a different program, and even on a host other than the one on
|
||
|
|
which it was compiled. Details are given in the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcreprecompile\fP
|
||
|
|
.\"
|
||
|
|
documentation.
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.SH "CHECKING BUILD-TIME OPTIONS"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
.B int pcre_config(int \fIwhat\fP, void *\fIwhere\fP);
|
||
|
|
.PP
|
||
|
|
The function \fBpcre_config()\fP makes it possible for a PCRE client to
|
||
|
|
discover which optional features have been compiled into the PCRE library. The
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrebuild\fP
|
||
|
|
.\"
|
||
|
|
documentation has more details about these optional features.
|
||
|
|
.P
|
||
|
|
The first argument for \fBpcre_config()\fP is an integer, specifying which
|
||
|
|
information is required; the second argument is a pointer to a variable into
|
||
|
|
which the information is placed. The following information is available:
|
||
|
|
.sp
|
||
|
|
PCRE_CONFIG_UTF8
|
||
|
|
.sp
|
||
|
|
The output is an integer that is set to one if UTF-8 support is available;
|
||
|
|
otherwise it is set to zero.
|
||
|
|
.sp
|
||
|
|
PCRE_CONFIG_UNICODE_PROPERTIES
|
||
|
|
.sp
|
||
|
|
The output is an integer that is set to one if support for Unicode character
|
||
|
|
properties is available; otherwise it is set to zero.
|
||
|
|
.sp
|
||
|
|
PCRE_CONFIG_NEWLINE
|
||
|
|
.sp
|
||
|
|
The output is an integer whose value specifies the default character sequence
|
||
|
|
that is recognized as meaning "newline". The three values that are supported
|
||
|
|
are: 10 for LF, 13 for CR, and 3338 for CRLF. The default should normally be
|
||
|
|
the standard sequence for your operating system.
|
||
|
|
.sp
|
||
|
|
PCRE_CONFIG_LINK_SIZE
|
||
|
|
.sp
|
||
|
|
The output is an integer that contains the number of bytes used for internal
|
||
|
|
linkage in compiled regular expressions. The value is 2, 3, or 4. Larger values
|
||
|
|
allow larger regular expressions to be compiled, at the expense of slower
|
||
|
|
matching. The default value of 2 is sufficient for all but the most massive
|
||
|
|
patterns, since it allows the compiled pattern to be up to 64K in size.
|
||
|
|
.sp
|
||
|
|
PCRE_CONFIG_POSIX_MALLOC_THRESHOLD
|
||
|
|
.sp
|
||
|
|
The output is an integer that contains the threshold above which the POSIX
|
||
|
|
interface uses \fBmalloc()\fP for output vectors. Further details are given in
|
||
|
|
the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcreposix\fP
|
||
|
|
.\"
|
||
|
|
documentation.
|
||
|
|
.sp
|
||
|
|
PCRE_CONFIG_MATCH_LIMIT
|
||
|
|
.sp
|
||
|
|
The output is an 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 an 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
|
||
|
|
\fBpcre_exec()\fP is implemented by recursive function calls that use the stack
|
||
|
|
to remember their state. This is the usual way that PCRE is compiled. The
|
||
|
|
output is zero if PCRE was compiled to use blocks of data on the heap instead
|
||
|
|
of recursive function calls. In this case, \fBpcre_stack_malloc\fP and
|
||
|
|
\fBpcre_stack_free\fP are called to manage memory blocks on the heap, thus
|
||
|
|
avoiding the use of the stack.
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.SH "COMPILING A PATTERN"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
.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);
|
||
|
|
.sp
|
||
|
|
.B pcre *pcre_compile2(const char *\fIpattern\fP, int \fIoptions\fP,
|
||
|
|
.ti +5n
|
||
|
|
.B int *\fIerrorcodeptr\fP,
|
||
|
|
.ti +5n
|
||
|
|
.B const char **\fIerrptr\fP, int *\fIerroffset\fP,
|
||
|
|
.ti +5n
|
||
|
|
.B const unsigned char *\fItableptr\fP);
|
||
|
|
.P
|
||
|
|
Either of the functions \fBpcre_compile()\fP or \fBpcre_compile2()\fP can be
|
||
|
|
called to compile a pattern into an internal form. The only difference between
|
||
|
|
the two interfaces is that \fBpcre_compile2()\fP has an additional argument,
|
||
|
|
\fIerrorcodeptr\fP, via which a numerical error code can be returned.
|
||
|
|
.P
|
||
|
|
The pattern is a C string terminated by a binary zero, and is passed in the
|
||
|
|
\fIpattern\fP argument. A pointer to a single block of memory that is obtained
|
||
|
|
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 (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
|
||
|
|
compilation. It should be zero if no options are required. The available
|
||
|
|
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
|
||
|
|
the detailed description in the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrepattern\fP
|
||
|
|
.\"
|
||
|
|
documentation). For these options, the contents of the \fIoptions\fP argument
|
||
|
|
specifies their initial settings at the start of compilation and execution. The
|
||
|
|
PCRE_ANCHORED and 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. This is a static string that is part of the library. You must
|
||
|
|
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
|
||
|
|
\fIerrorcodeptr\fP argument is not NULL, a non-zero error code number is
|
||
|
|
returned via this argument in the event of an error. This is in addition to the
|
||
|
|
textual error message. Error codes and messages are listed below.
|
||
|
|
.P
|
||
|
|
If the final argument, \fItableptr\fP, is NULL, PCRE uses a default set of
|
||
|
|
character tables that are built when PCRE is compiled, using the default C
|
||
|
|
locale. Otherwise, \fItableptr\fP must be an address that is the result of a
|
||
|
|
call to \fBpcre_maketables()\fP. This value is stored with the compiled
|
||
|
|
pattern, and used again by \fBpcre_exec()\fP, unless another table pointer is
|
||
|
|
passed to it. For more discussion, see the section on locale support below.
|
||
|
|
.P
|
||
|
|
This code fragment shows a typical straightforward call to \fBpcre_compile()\fP:
|
||
|
|
.sp
|
||
|
|
pcre *re;
|
||
|
|
const char *error;
|
||
|
|
int erroffset;
|
||
|
|
re = pcre_compile(
|
||
|
|
"^A.*Z", /* the pattern */
|
||
|
|
0, /* default options */
|
||
|
|
&error, /* for error message */
|
||
|
|
&erroffset, /* for error offset */
|
||
|
|
NULL); /* use default character tables */
|
||
|
|
.sp
|
||
|
|
The following names for option bits are defined in the \fBpcre.h\fP header
|
||
|
|
file:
|
||
|
|
.sp
|
||
|
|
PCRE_ANCHORED
|
||
|
|
.sp
|
||
|
|
If this bit is set, the pattern is forced to be "anchored", that is, it is
|
||
|
|
constrained to match only at the first matching point in the string that is
|
||
|
|
being searched (the "subject string"). This effect can also be achieved by
|
||
|
|
appropriate constructs in the pattern itself, which is the only way to do it in
|
||
|
|
Perl.
|
||
|
|
.sp
|
||
|
|
PCRE_AUTO_CALLOUT
|
||
|
|
.sp
|
||
|
|
If this bit is set, \fBpcre_compile()\fP automatically inserts callout items,
|
||
|
|
all with number 255, before each pattern item. For discussion of the callout
|
||
|
|
facility, see the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrecallout\fP
|
||
|
|
.\"
|
||
|
|
documentation.
|
||
|
|
.sp
|
||
|
|
PCRE_CASELESS
|
||
|
|
.sp
|
||
|
|
If this bit is set, letters in the pattern match both upper and lower case
|
||
|
|
letters. It is equivalent to Perl's /i option, and it can be changed within a
|
||
|
|
pattern by a (?i) option setting. In UTF-8 mode, PCRE always understands the
|
||
|
|
concept of case for characters whose values are less than 128, so caseless
|
||
|
|
matching is always possible. For characters with higher values, the concept of
|
||
|
|
case is supported if PCRE is compiled with Unicode property support, but not
|
||
|
|
otherwise. If you want to use caseless matching for characters 128 and above,
|
||
|
|
you must ensure that PCRE is compiled with Unicode property support as well as
|
||
|
|
with UTF-8 support.
|
||
|
|
.sp
|
||
|
|
PCRE_DOLLAR_ENDONLY
|
||
|
|
.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 a newline at the end of the string (but not before any other
|
||
|
|
newlines). The PCRE_DOLLAR_ENDONLY option is ignored if PCRE_MULTILINE is set.
|
||
|
|
There is no equivalent to this option in Perl, and no way to set it within a
|
||
|
|
pattern.
|
||
|
|
.sp
|
||
|
|
PCRE_DOTALL
|
||
|
|
.sp
|
||
|
|
If this bit is set, a dot metacharater in the pattern matches all characters,
|
||
|
|
including those that indicate newline. Without it, a dot does not match when
|
||
|
|
the current position is at a newline. This option is equivalent to Perl's /s
|
||
|
|
option, and it can be changed within a pattern by a (?s) option setting. A
|
||
|
|
negative class such as [^a] always matches newlines, 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, inclusive, are also
|
||
|
|
ignored. This is equivalent to Perl's /x option, and it can be changed within a
|
||
|
|
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
|
||
|
|
may never appear within special character sequences in a pattern, for example
|
||
|
|
within the sequence (?( which introduces a conditional subpattern.
|
||
|
|
.sp
|
||
|
|
PCRE_EXTRA
|
||
|
|
.sp
|
||
|
|
This option was invented in order to turn on additional functionality of PCRE
|
||
|
|
that is incompatible with Perl, but it is currently of very little use. When
|
||
|
|
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. (Perl can, however, be persuaded to
|
||
|
|
give a warning for this.) There are at present no other features controlled by
|
||
|
|
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 in the subject string, though the matched text may continue
|
||
|
|
over the newline.
|
||
|
|
.sp
|
||
|
|
PCRE_MULTILINE
|
||
|
|
.sp
|
||
|
|
By default, PCRE treats the subject string as consisting of a single line of
|
||
|
|
characters (even if it actually contains newlines). The "start of line"
|
||
|
|
metacharacter (^) matches only at the start of the string, while the "end of
|
||
|
|
line" metacharacter ($) matches only at the end of the string, or before a
|
||
|
|
terminating newline (unless PCRE_DOLLAR_ENDONLY is set). This is the same as
|
||
|
|
Perl.
|
||
|
|
.P
|
||
|
|
When PCRE_MULTILINE it is set, the "start of line" and "end of line" constructs
|
||
|
|
match immediately following or immediately before internal newlines in the
|
||
|
|
subject string, respectively, as well as at the very start and end. This is
|
||
|
|
equivalent to Perl's /m option, and it can be changed within a pattern by a
|
||
|
|
(?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
|
||
|
|
.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 both of them
|
||
|
|
specifies that a newline is indicated by the two-character CRLF sequence. For
|
||
|
|
convenience, PCRE_NEWLINE_CRLF is defined to contain both bits. The only time
|
||
|
|
that a line break is relevant 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 newline.
|
||
|
|
.P
|
||
|
|
The newline option 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
|
||
|
|
the pattern. Any opening parenthesis that is not followed by ? behaves as if it
|
||
|
|
were followed by ?: but named parentheses can still be used for capturing (and
|
||
|
|
they acquire numbers in the usual way). There is no equivalent of this option
|
||
|
|
in Perl.
|
||
|
|
.sp
|
||
|
|
PCRE_UNGREEDY
|
||
|
|
.sp
|
||
|
|
This option inverts the "greediness" of the quantifiers so that they are not
|
||
|
|
greedy by default, but become greedy if followed by "?". It is not compatible
|
||
|
|
with Perl. It can also be set by a (?U) option setting within the pattern.
|
||
|
|
.sp
|
||
|
|
PCRE_UTF8
|
||
|
|
.sp
|
||
|
|
This option causes PCRE to regard both the pattern and the subject as strings
|
||
|
|
of UTF-8 characters instead of single-byte character strings. However, it is
|
||
|
|
available only when PCRE is built to include UTF-8 support. If not, the use
|
||
|
|
of this option provokes an error. Details of how this option changes the
|
||
|
|
behaviour of PCRE are given in the
|
||
|
|
.\" HTML <a href="pcre.html#utf8support">
|
||
|
|
.\" </a>
|
||
|
|
section on UTF-8 support
|
||
|
|
.\"
|
||
|
|
in the main
|
||
|
|
.\" HREF
|
||
|
|
\fBpcre\fP
|
||
|
|
.\"
|
||
|
|
page.
|
||
|
|
.sp
|
||
|
|
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,
|
||
|
|
\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"
|
||
|
|
.rs
|
||
|
|
.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.
|
||
|
|
.sp
|
||
|
|
0 no error
|
||
|
|
1 \e at end of pattern
|
||
|
|
2 \ec at end of pattern
|
||
|
|
3 unrecognized character follows \e
|
||
|
|
4 numbers out of order in {} quantifier
|
||
|
|
5 number too big in {} quantifier
|
||
|
|
6 missing terminating ] for character class
|
||
|
|
7 invalid escape sequence in character class
|
||
|
|
8 range out of order in character class
|
||
|
|
9 nothing to repeat
|
||
|
|
10 operand of unlimited repeat could match the empty string
|
||
|
|
11 internal error: unexpected repeat
|
||
|
|
12 unrecognized character after (?
|
||
|
|
13 POSIX named classes are supported only within a class
|
||
|
|
14 missing )
|
||
|
|
15 reference to non-existent subpattern
|
||
|
|
16 erroffset passed as NULL
|
||
|
|
17 unknown option bit(s) set
|
||
|
|
18 missing ) after comment
|
||
|
|
19 parentheses nested too deeply
|
||
|
|
20 regular expression too large
|
||
|
|
21 failed to get memory
|
||
|
|
22 unmatched parentheses
|
||
|
|
23 internal error: code overflow
|
||
|
|
24 unrecognized character after (?<
|
||
|
|
25 lookbehind assertion is not fixed length
|
||
|
|
26 malformed number or name after (?(
|
||
|
|
27 conditional group contains more than two branches
|
||
|
|
28 assertion expected after (?(
|
||
|
|
29 (?R or (?digits must be followed by )
|
||
|
|
30 unknown POSIX class name
|
||
|
|
31 POSIX collating elements are not supported
|
||
|
|
32 this version of PCRE is not compiled with PCRE_UTF8 support
|
||
|
|
33 spare error
|
||
|
|
34 character value in \ex{...} sequence is too large
|
||
|
|
35 invalid condition (?(0)
|
||
|
|
36 \eC not allowed in lookbehind assertion
|
||
|
|
37 PCRE does not support \eL, \el, \eN, \eU, or \eu
|
||
|
|
38 number after (?C is > 255
|
||
|
|
39 closing ) for (?C expected
|
||
|
|
40 recursive call could loop indefinitely
|
||
|
|
41 unrecognized character after (?P
|
||
|
|
42 syntax error after (?P
|
||
|
|
43 two named subpatterns have the same name
|
||
|
|
44 invalid UTF-8 string
|
||
|
|
45 support for \eP, \ep, and \eX has not been compiled
|
||
|
|
46 malformed \eP or \ep sequence
|
||
|
|
47 unknown property name after \eP or \ep
|
||
|
|
48 subpattern name is too long (maximum 32 characters)
|
||
|
|
49 too many named subpatterns (maximum 10,000)
|
||
|
|
50 repeated subpattern is too long
|
||
|
|
51 octal value is greater than \e377 (not in UTF-8 mode)
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.SH "STUDYING A PATTERN"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
.B pcre_extra *pcre_study(const pcre *\fIcode\fP, int \fIoptions\fP
|
||
|
|
.ti +5n
|
||
|
|
.B const char **\fIerrptr\fP);
|
||
|
|
.PP
|
||
|
|
If a compiled pattern is going to be used several times, it is worth spending
|
||
|
|
more time analyzing it in order to speed up the time taken for matching. The
|
||
|
|
function \fBpcre_study()\fP takes a pointer to a compiled pattern as its first
|
||
|
|
argument. If studying the pattern produces additional information that will
|
||
|
|
help speed up matching, \fBpcre_study()\fP returns a pointer to a
|
||
|
|
\fBpcre_extra\fP block, in which the \fIstudy_data\fP field points to the
|
||
|
|
results of the study.
|
||
|
|
.P
|
||
|
|
The returned value from \fBpcre_study()\fP can be passed directly to
|
||
|
|
\fBpcre_exec()\fP. However, a \fBpcre_extra\fP block also contains other
|
||
|
|
fields that can be set by the caller before the block is passed; these are
|
||
|
|
described
|
||
|
|
.\" HTML <a href="#extradata">
|
||
|
|
.\" </a>
|
||
|
|
below
|
||
|
|
.\"
|
||
|
|
in the section on matching a pattern.
|
||
|
|
.P
|
||
|
|
If studying the pattern does not produce any additional information
|
||
|
|
\fBpcre_study()\fP returns NULL. In that circumstance, if the calling program
|
||
|
|
wants to pass any of the other fields to \fBpcre_exec()\fP, it must set up its
|
||
|
|
own \fBpcre_extra\fP block.
|
||
|
|
.P
|
||
|
|
The second argument of \fBpcre_study()\fP contains option bits. At present, no
|
||
|
|
options are defined, and this argument should always be zero.
|
||
|
|
.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 is set to point to a textual error message. This is a
|
||
|
|
static string that is part of the library. You must not try to free it. You
|
||
|
|
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
|
||
|
|
pcre_extra *pe;
|
||
|
|
pe = pcre_study(
|
||
|
|
re, /* result of pcre_compile() */
|
||
|
|
0, /* no options exist */
|
||
|
|
&error); /* set to NULL or points to a message */
|
||
|
|
.sp
|
||
|
|
At present, studying a pattern is useful only for non-anchored patterns that do
|
||
|
|
not have a single fixed starting character. A bitmap of possible starting
|
||
|
|
bytes is created.
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.\" HTML <a name="localesupport"></a>
|
||
|
|
.SH "LOCALE SUPPORT"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
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. The use of locales with Unicode is discouraged.
|
||
|
|
.P
|
||
|
|
An internal set of tables is created in the default C locale when PCRE is
|
||
|
|
built. This is used when the final argument of \fBpcre_compile()\fP is NULL,
|
||
|
|
and is sufficient for many applications. An alternative set of tables can,
|
||
|
|
however, be supplied. 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
|
||
|
|
to \fBpcre_compile()\fP or \fBpcre_exec()\fP as often as necessary. For
|
||
|
|
example, to build and use tables that are appropriate for the French locale
|
||
|
|
(where accented characters with values greater than 128 are treated as letters),
|
||
|
|
the following code could be used:
|
||
|
|
.sp
|
||
|
|
setlocale(LC_CTYPE, "fr_FR");
|
||
|
|
tables = pcre_maketables();
|
||
|
|
re = pcre_compile(..., tables);
|
||
|
|
.sp
|
||
|
|
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
|
||
|
|
needed.
|
||
|
|
.P
|
||
|
|
The pointer that is passed to \fBpcre_compile()\fP is saved with the compiled
|
||
|
|
pattern, and the same tables are used via this pointer by \fBpcre_study()\fP
|
||
|
|
and normally also by \fBpcre_exec()\fP. Thus, by default, for any single
|
||
|
|
pattern, compilation, studying and matching all happen in the same locale, but
|
||
|
|
different patterns can be compiled in different locales.
|
||
|
|
.P
|
||
|
|
It is possible to pass a table pointer or NULL (indicating the use of the
|
||
|
|
internal tables) to \fBpcre_exec()\fP. Although not intended for this purpose,
|
||
|
|
this facility could be used to match a pattern in a different locale from the
|
||
|
|
one in which it was compiled. Passing table pointers at run time is discussed
|
||
|
|
below in the section on matching a pattern.
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.SH "INFORMATION ABOUT A PATTERN"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
.B int pcre_fullinfo(const pcre *\fIcode\fP, "const pcre_extra *\fIextra\fP,"
|
||
|
|
.ti +5n
|
||
|
|
.B int \fIwhat\fP, void *\fIwhere\fP);
|
||
|
|
.PP
|
||
|
|
The \fBpcre_fullinfo()\fP function returns information about a compiled
|
||
|
|
pattern. It replaces the obsolete \fBpcre_info()\fP function, which is
|
||
|
|
nevertheless retained for backwards compability (and is documented below).
|
||
|
|
.P
|
||
|
|
The first argument for \fBpcre_fullinfo()\fP is a pointer to the compiled
|
||
|
|
pattern. The second argument is the result of \fBpcre_study()\fP, or NULL if
|
||
|
|
the pattern was not studied. The third argument specifies which piece of
|
||
|
|
information is required, and the fourth argument is a pointer to a variable
|
||
|
|
to receive the data. The yield of the function is zero for success, or one of
|
||
|
|
the following negative numbers:
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_NULL the argument \fIcode\fP was NULL
|
||
|
|
the argument \fIwhere\fP was NULL
|
||
|
|
PCRE_ERROR_BADMAGIC the "magic number" was not found
|
||
|
|
PCRE_ERROR_BADOPTION the value of \fIwhat\fP was invalid
|
||
|
|
.sp
|
||
|
|
The "magic number" is placed at the start of each compiled pattern as an simple
|
||
|
|
check against passing an arbitrary memory pointer. Here is a typical call of
|
||
|
|
\fBpcre_fullinfo()\fP, to obtain the length of the compiled pattern:
|
||
|
|
.sp
|
||
|
|
int rc;
|
||
|
|
size_t length;
|
||
|
|
rc = pcre_fullinfo(
|
||
|
|
re, /* result of pcre_compile() */
|
||
|
|
pe, /* result of pcre_study(), or NULL */
|
||
|
|
PCRE_INFO_SIZE, /* what is required */
|
||
|
|
&length); /* where to put the data */
|
||
|
|
.sp
|
||
|
|
The possible values for the third argument are defined in \fBpcre.h\fP, and are
|
||
|
|
as follows:
|
||
|
|
.sp
|
||
|
|
PCRE_INFO_BACKREFMAX
|
||
|
|
.sp
|
||
|
|
Return the number of the highest back reference in the pattern. The fourth
|
||
|
|
argument should point to an \fBint\fP variable. Zero is returned if there are
|
||
|
|
no back references.
|
||
|
|
.sp
|
||
|
|
PCRE_INFO_CAPTURECOUNT
|
||
|
|
.sp
|
||
|
|
Return the number of capturing subpatterns in the pattern. The fourth argument
|
||
|
|
should point to an \fBint\fP variable.
|
||
|
|
.sp
|
||
|
|
PCRE_INFO_DEFAULT_TABLES
|
||
|
|
.sp
|
||
|
|
Return a pointer to the internal default character tables within PCRE. The
|
||
|
|
fourth argument should point to an \fBunsigned char *\fP variable. This
|
||
|
|
information call is provided for internal use by the \fBpcre_study()\fP
|
||
|
|
function. External callers can cause PCRE to use its internal tables by passing
|
||
|
|
a NULL table pointer.
|
||
|
|
.sp
|
||
|
|
PCRE_INFO_FIRSTBYTE
|
||
|
|
.sp
|
||
|
|
Return information about the first byte of any matched string, for a
|
||
|
|
non-anchored pattern. The fourth argument should point to an \fBint\fP
|
||
|
|
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). Otherwise, if either
|
||
|
|
.sp
|
||
|
|
(a) the pattern was compiled with the PCRE_MULTILINE option, and every branch
|
||
|
|
starts with "^", or
|
||
|
|
.sp
|
||
|
|
(b) every branch of the pattern starts with ".*" and PCRE_DOTALL is not set
|
||
|
|
(if it were set, the pattern would be anchored),
|
||
|
|
.sp
|
||
|
|
-1 is returned, indicating that the pattern matches only at the start of a
|
||
|
|
subject string or after any newline within the string. Otherwise -2 is
|
||
|
|
returned. For anchored patterns, -2 is returned.
|
||
|
|
.sp
|
||
|
|
PCRE_INFO_FIRSTTABLE
|
||
|
|
.sp
|
||
|
|
If the pattern was studied, and this resulted in the construction of a 256-bit
|
||
|
|
table indicating a fixed set of bytes for the first byte in any matching
|
||
|
|
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_LASTLITERAL
|
||
|
|
.sp
|
||
|
|
Return the value of the rightmost literal byte that must exist in any matched
|
||
|
|
string, other than at its start, if such a byte has been recorded. The fourth
|
||
|
|
argument should point to an \fBint\fP variable. If there is no such byte, -1 is
|
||
|
|
returned. For anchored patterns, a last literal byte is recorded only if it
|
||
|
|
follows something of variable length. For example, for the pattern
|
||
|
|
/^a\ed+z\ed+/ the returned value is "z", but for /^a\edz\ed/ the returned value
|
||
|
|
is -1.
|
||
|
|
.sp
|
||
|
|
PCRE_INFO_NAMECOUNT
|
||
|
|
PCRE_INFO_NAMEENTRYSIZE
|
||
|
|
PCRE_INFO_NAMETABLE
|
||
|
|
.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. Several convenience functions such as
|
||
|
|
\fBpcre_get_named_substring()\fP are provided for extracting captured
|
||
|
|
substrings by name. It is also possible to extract the data directly, by first
|
||
|
|
converting the name to a number in order to access the correct pointers in the
|
||
|
|
output vector (described with \fBpcre_exec()\fP below). To do the conversion,
|
||
|
|
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
|
||
|
|
entry; both of these return an \fBint\fP value. The entry size depends on the
|
||
|
|
length of the longest name. PCRE_INFO_NAMETABLE returns a pointer to the first
|
||
|
|
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. 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) -
|
||
|
|
(?P<month>\ed\ed) - (?P<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
|
||
|
|
bytes shows in hexadecimal, and undefined bytes shown as ??:
|
||
|
|
.sp
|
||
|
|
00 01 d a t e 00 ??
|
||
|
|
00 05 d a y 00 ?? ??
|
||
|
|
00 04 m o n t h 00
|
||
|
|
00 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 the entries is likely to be
|
||
|
|
different for each compiled pattern.
|
||
|
|
.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.
|
||
|
|
.P
|
||
|
|
A pattern is automatically anchored by PCRE if all of its top-level
|
||
|
|
alternatives begin with one of the following:
|
||
|
|
.sp
|
||
|
|
^ unless PCRE_MULTILINE is set
|
||
|
|
\eA always
|
||
|
|
\eG always
|
||
|
|
.\" JOIN
|
||
|
|
.* if PCRE_DOTALL is set and there are no back
|
||
|
|
references to the subpattern in which .* appears
|
||
|
|
.sp
|
||
|
|
For such patterns, the PCRE_ANCHORED bit is set in the options returned by
|
||
|
|
\fBpcre_fullinfo()\fP.
|
||
|
|
.sp
|
||
|
|
PCRE_INFO_SIZE
|
||
|
|
.sp
|
||
|
|
Return the size of the compiled pattern, that is, the value that was passed as
|
||
|
|
the argument to \fBpcre_malloc()\fP when PCRE was getting memory in which to
|
||
|
|
place the compiled data. The fourth argument should point to a \fBsize_t\fP
|
||
|
|
variable.
|
||
|
|
.sp
|
||
|
|
PCRE_INFO_STUDYSIZE
|
||
|
|
.sp
|
||
|
|
Return the size of the data block pointed to by the \fIstudy_data\fP field in
|
||
|
|
a \fBpcre_extra\fP block. That is, it is the value that was passed to
|
||
|
|
\fBpcre_malloc()\fP when PCRE was getting memory into which to place the data
|
||
|
|
created by \fBpcre_study()\fP. The fourth argument should point to a
|
||
|
|
\fBsize_t\fP variable.
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.SH "OBSOLETE INFO FUNCTION"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
.B int pcre_info(const pcre *\fIcode\fP, int *\fIoptptr\fP, int
|
||
|
|
.B *\fIfirstcharptr\fP);
|
||
|
|
.PP
|
||
|
|
The \fBpcre_info()\fP function is now obsolete because its interface is too
|
||
|
|
restrictive to return all the available data about a compiled pattern. New
|
||
|
|
programs should use \fBpcre_fullinfo()\fP instead. The yield of
|
||
|
|
\fBpcre_info()\fP is the number of capturing subpatterns, or one of the
|
||
|
|
following negative numbers:
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_NULL the argument \fIcode\fP was NULL
|
||
|
|
PCRE_ERROR_BADMAGIC the "magic number" was not found
|
||
|
|
.sp
|
||
|
|
If the \fIoptptr\fP argument is not NULL, a copy of the options with which the
|
||
|
|
pattern was compiled is placed in the integer it points to (see
|
||
|
|
PCRE_INFO_OPTIONS above).
|
||
|
|
.P
|
||
|
|
If the pattern is not anchored and the \fIfirstcharptr\fP argument is not NULL,
|
||
|
|
it is used to pass back information about the first character of any matched
|
||
|
|
string (see PCRE_INFO_FIRSTBYTE above).
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.SH "REFERENCE COUNTS"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
.B int pcre_refcount(pcre *\fIcode\fP, int \fIadjust\fP);
|
||
|
|
.PP
|
||
|
|
The \fBpcre_refcount()\fP function is used to maintain a reference count in the
|
||
|
|
data block that contains a compiled pattern. It is provided for the benefit of
|
||
|
|
applications that operate in an object-oriented manner, where different parts
|
||
|
|
of the application may be using the same compiled pattern, but you want to free
|
||
|
|
the block when they are all done.
|
||
|
|
.P
|
||
|
|
When a pattern is compiled, the reference count field is initialized to zero.
|
||
|
|
It is changed only by calling this function, whose action is to add the
|
||
|
|
\fIadjust\fP value (which may be positive or negative) to it. The yield of the
|
||
|
|
function is the new value. However, the value of the count is constrained to
|
||
|
|
lie between 0 and 65535, inclusive. If the new value is outside these limits,
|
||
|
|
it is forced to the appropriate limit value.
|
||
|
|
.P
|
||
|
|
Except when it is zero, the reference count is not correctly preserved if a
|
||
|
|
pattern is compiled on one host and then transferred to a host whose byte-order
|
||
|
|
is different. (This seems a highly unlikely scenario.)
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.SH "MATCHING A PATTERN: THE TRADITIONAL FUNCTION"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
.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);
|
||
|
|
.P
|
||
|
|
The function \fBpcre_exec()\fP is called to match a subject string against a
|
||
|
|
compiled pattern, which is passed in the \fIcode\fP argument. If the
|
||
|
|
pattern has been studied, the result of the study should be passed in the
|
||
|
|
\fIextra\fP argument. This function is the main matching facility of the
|
||
|
|
library, and it operates in a Perl-like manner. For specialist use there is
|
||
|
|
also an alternative matching function, which is described
|
||
|
|
.\" HTML <a href="#dfamatch">
|
||
|
|
.\" </a>
|
||
|
|
below
|
||
|
|
.\"
|
||
|
|
in the section about the \fBpcre_dfa_exec()\fP function.
|
||
|
|
.P
|
||
|
|
In most applications, the pattern will have been compiled (and optionally
|
||
|
|
studied) in the same process that calls \fBpcre_exec()\fP. However, it is
|
||
|
|
possible to save compiled patterns and study data, and then use them later
|
||
|
|
in different processes, possibly even on different hosts. For a discussion
|
||
|
|
about this, see the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcreprecompile\fP
|
||
|
|
.\"
|
||
|
|
documentation.
|
||
|
|
.P
|
||
|
|
Here is an example of a simple call to \fBpcre_exec()\fP:
|
||
|
|
.sp
|
||
|
|
int rc;
|
||
|
|
int ovector[30];
|
||
|
|
rc = pcre_exec(
|
||
|
|
re, /* result of pcre_compile() */
|
||
|
|
NULL, /* we didn't study the pattern */
|
||
|
|
"some string", /* the subject string */
|
||
|
|
11, /* the length of the subject string */
|
||
|
|
0, /* start at offset 0 in the subject */
|
||
|
|
0, /* default options */
|
||
|
|
ovector, /* vector of integers for substring information */
|
||
|
|
30); /* number of elements (NOT size in bytes) */
|
||
|
|
.
|
||
|
|
.\" HTML <a name="extradata"></a>
|
||
|
|
.SS "Extra data for \fBpcre_exec()\fR"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
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 \fBpcre_extra\fP block contains the following
|
||
|
|
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
|
||
|
|
The \fIflags\fP field is a bitmap that specifies which of the other fields
|
||
|
|
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
|
||
|
|
Other flag bits should be set to zero. The \fIstudy_data\fP field is set in the
|
||
|
|
\fBpcre_extra\fP block that is returned by \fBpcre_study()\fP, together with
|
||
|
|
the appropriate flag bit. You should not set this yourself, but you may add to
|
||
|
|
the block by setting the other fields and their corresponding flag bits.
|
||
|
|
.P
|
||
|
|
The \fImatch_limit\fP field provides a means of preventing PCRE from using up a
|
||
|
|
vast amount of resources when running patterns that are not going to match,
|
||
|
|
but which have a very large number of possibilities in their search trees. The
|
||
|
|
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 set by \fImatch_limit\fP is imposed on the
|
||
|
|
number of times this function is called during a match, which has the effect of
|
||
|
|
limiting the amount of backtracking that can take place. For patterns that are
|
||
|
|
not anchored, the count restarts from zero for each position in the subject
|
||
|
|
string.
|
||
|
|
.P
|
||
|
|
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
|
||
|
|
override the default by suppling \fBpcre_exec()\fP with a \fBpcre_extra\fP
|
||
|
|
block in which \fImatch_limit\fP is set, and PCRE_EXTRA_MATCH_LIMIT is set in
|
||
|
|
the \fIflags\fP field. If the limit is exceeded, \fBpcre_exec()\fP returns
|
||
|
|
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
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrecallout\fP
|
||
|
|
.\"
|
||
|
|
documentation.
|
||
|
|
.P
|
||
|
|
The \fItables\fP field is used to pass a character tables pointer to
|
||
|
|
\fBpcre_exec()\fP; this overrides the value that is stored with the compiled
|
||
|
|
pattern. A non-NULL value is stored with the compiled pattern only if custom
|
||
|
|
tables were supplied to \fBpcre_compile()\fP via its \fItableptr\fP argument.
|
||
|
|
If NULL is passed to \fBpcre_exec()\fP using this mechanism, it forces PCRE's
|
||
|
|
internal tables to be used. This facility is helpful when re-using patterns
|
||
|
|
that have been saved after compiling with an external set of tables, because
|
||
|
|
the external tables might be at a different address when \fBpcre_exec()\fP is
|
||
|
|
called. See the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcreprecompile\fP
|
||
|
|
.\"
|
||
|
|
documentation for a discussion of saving compiled patterns for later use.
|
||
|
|
.
|
||
|
|
.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_NEWLINE_\fIxxx\fP,
|
||
|
|
PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK and PCRE_PARTIAL.
|
||
|
|
.sp
|
||
|
|
PCRE_ANCHORED
|
||
|
|
.sp
|
||
|
|
The PCRE_ANCHORED option limits \fBpcre_exec()\fP to matching at the first
|
||
|
|
matching position. If a pattern was compiled with PCRE_ANCHORED, or turned out
|
||
|
|
to be anchored by virtue of its contents, it cannot be made unachored at
|
||
|
|
matching time.
|
||
|
|
.sp
|
||
|
|
PCRE_NEWLINE_CR
|
||
|
|
PCRE_NEWLINE_LF
|
||
|
|
PCRE_NEWLINE_CRLF
|
||
|
|
.sp
|
||
|
|
These options override the newline definition that was chosen or defaulted when
|
||
|
|
the pattern was compiled. For details, see the description \fBpcre_compile()\fP
|
||
|
|
above. During matching, the newline choice affects the behaviour of the dot,
|
||
|
|
circumflex, and dollar metacharacters.
|
||
|
|
.sp
|
||
|
|
PCRE_NOTBOL
|
||
|
|
.sp
|
||
|
|
This option specifies that first character of the subject string is not the
|
||
|
|
beginning of a line, so the circumflex metacharacter should not match before
|
||
|
|
it. Setting this without PCRE_MULTILINE (at compile time) causes circumflex
|
||
|
|
never to match. This option affects only the behaviour of the circumflex
|
||
|
|
metacharacter. It does not affect \eA.
|
||
|
|
.sp
|
||
|
|
PCRE_NOTEOL
|
||
|
|
.sp
|
||
|
|
This option specifies that the end of the subject string is not the end of a
|
||
|
|
line, so the dollar metacharacter should not match it nor (except in multiline
|
||
|
|
mode) a newline immediately before it. Setting this without PCRE_MULTILINE (at
|
||
|
|
compile time) causes dollar never to match. This option affects only the
|
||
|
|
behaviour of the dollar metacharacter. It does not affect \eZ or \ez.
|
||
|
|
.sp
|
||
|
|
PCRE_NOTEMPTY
|
||
|
|
.sp
|
||
|
|
An empty string is not considered to be a valid match if this option is set. If
|
||
|
|
there are alternatives in the pattern, they are tried. If all the alternatives
|
||
|
|
match the empty string, the entire match fails. For example, if the pattern
|
||
|
|
.sp
|
||
|
|
a?b?
|
||
|
|
.sp
|
||
|
|
is applied to a string not beginning with "a" or "b", it matches the empty
|
||
|
|
string at the start of the subject. With PCRE_NOTEMPTY set, this match is not
|
||
|
|
valid, so PCRE searches further into the string for occurrences of "a" or "b".
|
||
|
|
.P
|
||
|
|
Perl has no direct equivalent of PCRE_NOTEMPTY, but it does make a special case
|
||
|
|
of a pattern match of the empty string within its \fBsplit()\fP function, and
|
||
|
|
when using the /g modifier. It is possible to emulate Perl's behaviour after
|
||
|
|
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.
|
||
|
|
.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,
|
||
|
|
\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
|
||
|
|
calling \fBpcre_exec()\fP. You might want to do this for the second and
|
||
|
|
subsequent calls to \fBpcre_exec()\fP if you are making repeated calls to find
|
||
|
|
all the matches in a single subject string. However, you should be sure that
|
||
|
|
the value of \fIstartoffset\fP points to the start of a UTF-8 character. When
|
||
|
|
PCRE_NO_UTF8_CHECK is set, the effect of passing an invalid UTF-8 string as a
|
||
|
|
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
|
||
|
|
.sp
|
||
|
|
This option turns on the partial matching feature. If the subject string fails
|
||
|
|
to match the pattern, but at some point during the matching process the end of
|
||
|
|
the subject was reached (that is, the subject partially matches the pattern and
|
||
|
|
the failure to match occurred only because there were not enough subject
|
||
|
|
characters), \fBpcre_exec()\fP returns PCRE_ERROR_PARTIAL instead of
|
||
|
|
PCRE_ERROR_NOMATCH. When PCRE_PARTIAL is used, there are restrictions on what
|
||
|
|
may appear in the pattern. These are discussed in the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrepartial\fP
|
||
|
|
.\"
|
||
|
|
documentation.
|
||
|
|
.
|
||
|
|
.SS "The string to be matched by \fBpcre_exec()\fP"
|
||
|
|
.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
|
||
|
|
\fIstartoffset\fP. In UTF-8 mode, the byte offset must point to the start of a
|
||
|
|
UTF-8 character. Unlike the pattern string, the subject may contain binary zero
|
||
|
|
bytes. When the starting offset is zero, the search for a match starts at 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.
|
||
|
|
Setting \fIstartoffset\fP differs from just passing over a shortened string and
|
||
|
|
setting PCRE_NOTBOL in the case of a pattern that begins with any kind of
|
||
|
|
lookbehind. For example, consider the pattern
|
||
|
|
.sp
|
||
|
|
\eBiss\eB
|
||
|
|
.sp
|
||
|
|
which finds occurrences of "iss" in the middle of words. (\eB matches only if
|
||
|
|
the current position in the subject is not a word boundary.) When applied to
|
||
|
|
the string "Mississipi" the first call to \fBpcre_exec()\fP finds the first
|
||
|
|
occurrence. If \fBpcre_exec()\fP is called again with just the remainder of the
|
||
|
|
subject, namely "issipi", it does not match, because \eB is always false at the
|
||
|
|
start of the subject, which is deemed to be a word boundary. However, if
|
||
|
|
\fBpcre_exec()\fP is passed the entire string again, but with \fIstartoffset\fP
|
||
|
|
set to 4, it finds the second occurrence of "iss" because it is able to look
|
||
|
|
behind the starting point to discover that it is preceded by a letter.
|
||
|
|
.P
|
||
|
|
If a non-zero starting offset is passed when the pattern is anchored, one
|
||
|
|
attempt to match at the given offset is made. This can only succeed if the
|
||
|
|
pattern does not require the match to be at the start of the subject.
|
||
|
|
.
|
||
|
|
.SS "How \fBpcre_exec()\fP returns captured substrings"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
In general, a pattern matches a certain portion of the subject, and in
|
||
|
|
addition, further substrings from the subject may be picked out by parts of the
|
||
|
|
pattern. Following the usage in Jeffrey Friedl's book, this is called
|
||
|
|
"capturing" in what follows, and the phrase "capturing subpattern" is used for
|
||
|
|
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
|
||
|
|
whose address is passed in \fIovector\fP. The number of elements in the vector
|
||
|
|
is passed in \fIovecsize\fP, which must be a non-negative number. \fBNote\fP:
|
||
|
|
this 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
|
||
|
|
\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
|
||
|
|
pair is set to the offset of the first character in a substring, and the second
|
||
|
|
is set to the offset of the first character after the end of a substring. The
|
||
|
|
first pair, \fIovector[0]\fP and \fIovector[1]\fP, identify the portion of the
|
||
|
|
subject string matched by the entire pattern. The next pair is used for the
|
||
|
|
first capturing subpattern, and so on. The value returned by \fBpcre_exec()\fP
|
||
|
|
is one more than the highest numbered pair that has been set. For example, if
|
||
|
|
two substrings have been captured, the returned value is 3. If there are no
|
||
|
|
capturing subpatterns, the return value from a successful match is 1,
|
||
|
|
indicating that just the first pair of offsets has been set.
|
||
|
|
.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
|
||
|
|
interest, \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
|
||
|
|
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 "Error return values from \fBpcre_exec()\fP"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
If \fBpcre_exec()\fP fails, it returns a negative number. The following are
|
||
|
|
defined in the header file:
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_NOMATCH (-1)
|
||
|
|
.sp
|
||
|
|
The subject string did not match the pattern.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_NULL (-2)
|
||
|
|
.sp
|
||
|
|
Either \fIcode\fP or \fIsubject\fP was passed as NULL, or \fIovector\fP was
|
||
|
|
NULL and \fIovecsize\fP was not zero.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_BADOPTION (-3)
|
||
|
|
.sp
|
||
|
|
An unrecognized bit was set in the \fIoptions\fP argument.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_BADMAGIC (-4)
|
||
|
|
.sp
|
||
|
|
PCRE stores a 4-byte "magic number" at the start of the compiled code, to catch
|
||
|
|
the case when it is passed a junk pointer and to detect when a pattern that was
|
||
|
|
compiled in an environment of one endianness is run in an environment with the
|
||
|
|
other endianness. This is the error that PCRE gives when the magic number is
|
||
|
|
not present.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_UNKNOWN_NODE (-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
|
||
|
|
of the compiled pattern.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_NOMEMORY (-6)
|
||
|
|
.sp
|
||
|
|
If a pattern contains back references, but the \fIovector\fP that is passed to
|
||
|
|
\fBpcre_exec()\fP is not big enough to remember the referenced substrings, PCRE
|
||
|
|
gets a block of memory at the start of matching to use for this purpose. If the
|
||
|
|
call via \fBpcre_malloc()\fP fails, this error is given. The memory is
|
||
|
|
automatically freed at the end of matching.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_NOSUBSTRING (-7)
|
||
|
|
.sp
|
||
|
|
This error is used by the \fBpcre_copy_substring()\fP,
|
||
|
|
\fBpcre_get_substring()\fP, and \fBpcre_get_substring_list()\fP functions (see
|
||
|
|
below). It is never returned by \fBpcre_exec()\fP.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_MATCHLIMIT (-8)
|
||
|
|
.sp
|
||
|
|
The backtracking limit, as specified by the \fImatch_limit\fP field in a
|
||
|
|
\fBpcre_extra\fP structure (or defaulted) was reached. See the description
|
||
|
|
above.
|
||
|
|
.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_CALLOUT (-9)
|
||
|
|
.sp
|
||
|
|
This error is never generated by \fBpcre_exec()\fP itself. It is provided for
|
||
|
|
use by callout functions that want to yield a distinctive error code. See the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrecallout\fP
|
||
|
|
.\"
|
||
|
|
documentation for details.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_BADUTF8 (-10)
|
||
|
|
.sp
|
||
|
|
A string that contains an invalid UTF-8 byte sequence was passed as a subject.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_BADUTF8_OFFSET (-11)
|
||
|
|
.sp
|
||
|
|
The UTF-8 byte sequence that was passed as a subject was valid, but the value
|
||
|
|
of \fIstartoffset\fP did not point to the beginning of a UTF-8 character.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_PARTIAL (-12)
|
||
|
|
.sp
|
||
|
|
The subject string did not match, but it did match partially. See the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrepartial\fP
|
||
|
|
.\"
|
||
|
|
documentation for details of partial matching.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_BADPARTIAL (-13)
|
||
|
|
.sp
|
||
|
|
The PCRE_PARTIAL option was used with a compiled pattern containing items that
|
||
|
|
are not supported for partial matching. See the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrepartial\fP
|
||
|
|
.\"
|
||
|
|
documentation for details of partial matching.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_INTERNAL (-14)
|
||
|
|
.sp
|
||
|
|
An unexpected internal error has occurred. This error could be caused by a bug
|
||
|
|
in PCRE or by overwriting of the compiled pattern.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_BADCOUNT (-15)
|
||
|
|
.sp
|
||
|
|
This error is given if the value of the \fIovecsize\fP argument is negative.
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.SH "EXTRACTING CAPTURED SUBSTRINGS BY NUMBER"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
.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_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
|
||
|
|
Captured substrings can be accessed directly by using the offsets returned by
|
||
|
|
\fBpcre_exec()\fP in \fIovector\fP. For convenience, the functions
|
||
|
|
\fBpcre_copy_substring()\fP, \fBpcre_get_substring()\fP, and
|
||
|
|
\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.
|
||
|
|
.P
|
||
|
|
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,
|
||
|
|
\fIovector\fP is a pointer to the vector of integer offsets that was passed to
|
||
|
|
\fBpcre_exec()\fP, and \fIstringcount\fP is the number of substrings that were
|
||
|
|
captured by the match, including the substring that matched the entire regular
|
||
|
|
expression. This is the value returned by \fBpcre_exec()\fP if it is greater
|
||
|
|
than zero. If \fBpcre_exec()\fP returned zero, indicating that it ran out of
|
||
|
|
space in \fIovector\fP, the value passed as \fIstringcount\fP should be the
|
||
|
|
number of elements in the vector divided by three.
|
||
|
|
.P
|
||
|
|
The functions \fBpcre_copy_substring()\fP and \fBpcre_get_substring()\fP
|
||
|
|
extract a single substring, whose number is given as \fIstringnumber\fP. A
|
||
|
|
value of zero extracts the substring that matched the entire pattern, whereas
|
||
|
|
higher values extract the captured substrings. For \fBpcre_copy_substring()\fP,
|
||
|
|
the string is placed in \fIbuffer\fP, whose length is given by
|
||
|
|
\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
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_NOMEMORY (-6)
|
||
|
|
.sp
|
||
|
|
The buffer was too small for \fBpcre_copy_substring()\fP, or the attempt to get
|
||
|
|
memory failed for \fBpcre_get_substring()\fP.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_NOSUBSTRING (-7)
|
||
|
|
.sp
|
||
|
|
There is no substring whose number is \fIstringnumber\fP.
|
||
|
|
.P
|
||
|
|
The \fBpcre_get_substring_list()\fP function extracts all available substrings
|
||
|
|
and builds a list of pointers to them. All this is done in a single block of
|
||
|
|
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
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_NOMEMORY (-6)
|
||
|
|
.sp
|
||
|
|
if the attempt to get the memory block failed.
|
||
|
|
.P
|
||
|
|
When any of these functions encounter a substring that is unset, which can
|
||
|
|
happen when capturing subpattern number \fIn+1\fP matches some part of the
|
||
|
|
subject, but subpattern \fIn\fP has not been used at all, they return an empty
|
||
|
|
string. This can be distinguished from a genuine zero-length substring by
|
||
|
|
inspecting the appropriate offset in \fIovector\fP, which is negative for unset
|
||
|
|
substrings.
|
||
|
|
.P
|
||
|
|
The two convenience functions \fBpcre_free_substring()\fP and
|
||
|
|
\fBpcre_free_substring_list()\fP can be used to free the memory returned by
|
||
|
|
a previous call of \fBpcre_get_substring()\fP or
|
||
|
|
\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 that cannot use
|
||
|
|
\fBpcre_free\fP directly; it is for these cases that the functions are
|
||
|
|
provided.
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.SH "EXTRACTING CAPTURED SUBSTRINGS BY NAME"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
.B int pcre_get_stringnumber(const pcre *\fIcode\fP,
|
||
|
|
.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,
|
||
|
|
.ti +5n
|
||
|
|
.B int \fIstringcount\fP, const char *\fIstringname\fP,
|
||
|
|
.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,
|
||
|
|
.ti +5n
|
||
|
|
.B int \fIstringcount\fP, const char *\fIstringname\fP,
|
||
|
|
.ti +5n
|
||
|
|
.B const char **\fIstringptr\fP);
|
||
|
|
.PP
|
||
|
|
To extract a substring by name, you first have to find associated number.
|
||
|
|
For example, for this pattern
|
||
|
|
.sp
|
||
|
|
(a+)b(?P<xxx>\ed+)...
|
||
|
|
.sp
|
||
|
|
the number of the subpattern called "xxx" is 2. If the name is known to be
|
||
|
|
unique (PCRE_DUPNAMES was not set), you can find the number from the name by
|
||
|
|
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
|
||
|
|
Given the number, you can extract the substring directly, or use one of the
|
||
|
|
functions described in the previous section. For convenience, there are also
|
||
|
|
two functions that do the whole job.
|
||
|
|
.P
|
||
|
|
Most of the arguments of \fBpcre_copy_named_substring()\fP and
|
||
|
|
\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
|
||
|
|
First, instead of a substring number, a substring name is given. Second, there
|
||
|
|
is an extra argument, given at the start, which is a pointer to the compiled
|
||
|
|
pattern. This is needed in order to gain access to the name-to-number
|
||
|
|
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
|
||
|
|
appropriate.
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.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. 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, an empty string 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.
|
||
|
|
.sp
|
||
|
|
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 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"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
The traditional matching function uses a similar algorithm to Perl, which stops
|
||
|
|
when it finds the first match, starting at a given point in the subject. If you
|
||
|
|
want to find all possible matches, or the longest possible match, consider
|
||
|
|
using the alternative matching function (see below) instead. If you cannot use
|
||
|
|
the alternative function, but still need to find all possible matches, you
|
||
|
|
can kludge it up by making use of the callout facility, which is described in
|
||
|
|
the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrecallout\fP
|
||
|
|
.\"
|
||
|
|
documentation.
|
||
|
|
.P
|
||
|
|
What you have to do is to insert a callout right at the end of the pattern.
|
||
|
|
When your callout function is called, extract and save the current matched
|
||
|
|
substring. Then return 1, which forces \fBpcre_exec()\fP to backtrack and try
|
||
|
|
other alternatives. Ultimately, when it runs out of matches, \fBpcre_exec()\fP
|
||
|
|
will yield PCRE_ERROR_NOMATCH.
|
||
|
|
.
|
||
|
|
.
|
||
|
|
.\" HTML <a name="dfamatch"></a>
|
||
|
|
.SH "MATCHING A PATTERN: THE ALTERNATIVE FUNCTION"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
.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,
|
||
|
|
.ti +5n
|
||
|
|
.B int \fIoptions\fP, int *\fIovector\fP, int \fIovecsize\fP,
|
||
|
|
.ti +5n
|
||
|
|
.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
|
||
|
|
characteristics to the normal algorithm, and is not compatible with Perl. Some
|
||
|
|
of the features of PCRE patterns are not supported. Nevertheless, there are
|
||
|
|
times when this kind of matching can be useful. For a discussion of the two
|
||
|
|
matching algorithms, see the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrematching\fP
|
||
|
|
.\"
|
||
|
|
documentation.
|
||
|
|
.P
|
||
|
|
The arguments for the \fBpcre_dfa_exec()\fP function are the same as for
|
||
|
|
\fBpcre_exec()\fP, plus two extras. The \fIovector\fP argument is used in a
|
||
|
|
different way, and this is described below. The other common arguments are used
|
||
|
|
in the same way as for \fBpcre_exec()\fP, so their description is not repeated
|
||
|
|
here.
|
||
|
|
.P
|
||
|
|
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 potential matches.
|
||
|
|
.P
|
||
|
|
Here is an example of a simple call to \fBpcre_dfa_exec()\fP:
|
||
|
|
.sp
|
||
|
|
int rc;
|
||
|
|
int ovector[10];
|
||
|
|
int wspace[20];
|
||
|
|
rc = pcre_dfa_exec(
|
||
|
|
re, /* result of pcre_compile() */
|
||
|
|
NULL, /* we didn't study the pattern */
|
||
|
|
"some string", /* the subject string */
|
||
|
|
11, /* the length of the subject string */
|
||
|
|
0, /* start at offset 0 in the subject */
|
||
|
|
0, /* default options */
|
||
|
|
ovector, /* vector of integers for substring information */
|
||
|
|
10, /* number of elements (NOT size in bytes) */
|
||
|
|
wspace, /* working space vector */
|
||
|
|
20); /* number of elements (NOT size in bytes) */
|
||
|
|
.
|
||
|
|
.SS "Option bits for \fBpcre_dfa_exec()\fP"
|
||
|
|
.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_NEWLINE_\fIxxx\fP,
|
||
|
|
PCRE_NOTBOL, PCRE_NOTEOL, PCRE_NOTEMPTY, PCRE_NO_UTF8_CHECK, PCRE_PARTIAL,
|
||
|
|
PCRE_DFA_SHORTEST, and PCRE_DFA_RESTART. All but the last three of these are
|
||
|
|
the same as for \fBpcre_exec()\fP, so their description is not repeated here.
|
||
|
|
.sp
|
||
|
|
PCRE_PARTIAL
|
||
|
|
.sp
|
||
|
|
This has the same general effect as it does for \fBpcre_exec()\fP, but the
|
||
|
|
details are slightly different. When PCRE_PARTIAL is set for
|
||
|
|
\fBpcre_dfa_exec()\fP, 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 partial match is set as the first
|
||
|
|
matching string.
|
||
|
|
.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,
|
||
|
|
this is necessarily the shortest possible match at the first possible 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
|
||
|
|
a partial match, it is possible to call it again, with additional subject
|
||
|
|
characters, and have it continue with the same match. The PCRE_DFA_RESTART
|
||
|
|
option requests this action; when it is set, the \fIworkspace\fP and
|
||
|
|
\fIwscount\fP options must reference the same vector as before because data
|
||
|
|
about the match so far is left in them after a partial match. There is more
|
||
|
|
discussion of this facility in the
|
||
|
|
.\" HREF
|
||
|
|
\fBpcrepartial\fP
|
||
|
|
.\"
|
||
|
|
documentation.
|
||
|
|
.
|
||
|
|
.SS "Successful returns from \fBpcre_dfa_exec()\fP"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
When \fBpcre_dfa_exec()\fP succeeds, it may have matched more than one
|
||
|
|
substring in the subject. Note, however, that all the matches from one run of
|
||
|
|
the function start at the same point in the subject. The shorter matches are
|
||
|
|
all initial substrings of the longer matches. For example, if the pattern
|
||
|
|
.sp
|
||
|
|
<.*>
|
||
|
|
.sp
|
||
|
|
is matched against the string
|
||
|
|
.sp
|
||
|
|
This is <something> <something else> <something further> no more
|
||
|
|
.sp
|
||
|
|
the three matched strings are
|
||
|
|
.sp
|
||
|
|
<something>
|
||
|
|
<something> <something else>
|
||
|
|
<something> <something else> <something further>
|
||
|
|
.sp
|
||
|
|
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 offset. (Space could have been saved by giving this only once, but it was
|
||
|
|
decided to retain some compatibility with the way \fBpcre_exec()\fP 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
|
||
|
|
\fIovector\fP, the yield of the function is zero, and the vector is filled with
|
||
|
|
the longest matches.
|
||
|
|
.
|
||
|
|
.SS "Error returns from \fBpcre_dfa_exec()\fP"
|
||
|
|
.rs
|
||
|
|
.sp
|
||
|
|
The \fBpcre_dfa_exec()\fP function returns a negative number when it fails.
|
||
|
|
Many of the errors are the same as for \fBpcre_exec()\fP, and these are
|
||
|
|
described
|
||
|
|
.\" HTML <a href="#errorlist">
|
||
|
|
.\" </a>
|
||
|
|
above.
|
||
|
|
.\"
|
||
|
|
There are in addition the following errors that are specific to
|
||
|
|
\fBpcre_dfa_exec()\fP:
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_DFA_UITEM (-16)
|
||
|
|
.sp
|
||
|
|
This return is given if \fBpcre_dfa_exec()\fP encounters an item in the pattern
|
||
|
|
that it does not support, for instance, the use of \eC or a back reference.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_DFA_UCOND (-17)
|
||
|
|
.sp
|
||
|
|
This return is given if \fBpcre_dfa_exec()\fP encounters a condition item in a
|
||
|
|
pattern that uses a back reference for the condition. This is not supported.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_DFA_UMLIMIT (-18)
|
||
|
|
.sp
|
||
|
|
This return is given if \fBpcre_dfa_exec()\fP is called with an \fIextra\fP
|
||
|
|
block that contains a setting of the \fImatch_limit\fP field. This is not
|
||
|
|
supported (it is meaningless).
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_DFA_WSSIZE (-19)
|
||
|
|
.sp
|
||
|
|
This return is given if \fBpcre_dfa_exec()\fP runs out of space in the
|
||
|
|
\fIworkspace\fP vector.
|
||
|
|
.sp
|
||
|
|
PCRE_ERROR_DFA_RECURSE (-20)
|
||
|
|
.sp
|
||
|
|
When a recursive subpattern is processed, the matching function calls itself
|
||
|
|
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: 08 June 2006
|
||
|
|
.br
|
||
|
|
Copyright (c) 1997-2006 University of Cambridge.
|