676 lines
25 KiB
C
676 lines
25 KiB
C
/* Definitions for data structures and routines for the regular
|
||
expression library.
|
||
Copyright (C) 1985, 1989, 1990, 1991, 1992, 1993, 1995, 1996, 1997, 1998,
|
||
2000, 2001, 2002, 2003, 2005, 2006, 2009, 2010 Free Software Foundation,
|
||
Inc.
|
||
This file is part of the GNU C Library.
|
||
|
||
This program is free software; you can redistribute it and/or modify
|
||
it under the terms of the GNU General Public License as published by
|
||
the Free Software Foundation; either version 2, or (at your option)
|
||
any later version.
|
||
|
||
This program is distributed in the hope that it will be useful,
|
||
but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||
GNU General Public License for more details.
|
||
|
||
You should have received a copy of the GNU General Public License along
|
||
with this program; if not, write to the Free Software Foundation,
|
||
Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */
|
||
|
||
#ifndef _REGEX_H
|
||
#define _REGEX_H 1
|
||
|
||
#include <sys/types.h>
|
||
|
||
/* Allow the use in C++ code. */
|
||
#ifdef __cplusplus
|
||
extern "C" {
|
||
#endif
|
||
|
||
/* Define __USE_GNU_REGEX to declare GNU extensions that violate the
|
||
POSIX name space rules. */
|
||
#undef __USE_GNU_REGEX
|
||
#if (defined _GNU_SOURCE \
|
||
|| (!defined _POSIX_C_SOURCE && !defined _POSIX_SOURCE \
|
||
&& !defined _XOPEN_SOURCE))
|
||
# define __USE_GNU_REGEX 1
|
||
#endif
|
||
|
||
#ifdef _REGEX_LARGE_OFFSETS
|
||
|
||
/* Use types and values that are wide enough to represent signed and
|
||
unsigned byte offsets in memory. This currently works only when
|
||
the regex code is used outside of the GNU C library; it is not yet
|
||
supported within glibc itself, and glibc users should not define
|
||
_REGEX_LARGE_OFFSETS. */
|
||
|
||
/* The type of the offset of a byte within a string.
|
||
For historical reasons POSIX 1003.1-2004 requires that regoff_t be
|
||
at least as wide as off_t. However, many common POSIX platforms set
|
||
regoff_t to the more-sensible ssize_t and the Open Group has
|
||
signalled its intention to change the requirement to be that
|
||
regoff_t be at least as wide as ptrdiff_t and ssize_t; see XBD ERN
|
||
60 (2005-08-25). We don't know of any hosts where ssize_t or
|
||
ptrdiff_t is wider than ssize_t, so ssize_t is safe. */
|
||
typedef ssize_t regoff_t;
|
||
|
||
/* The type of nonnegative object indexes. Traditionally, GNU regex
|
||
uses 'int' for these. Code that uses __re_idx_t should work
|
||
regardless of whether the type is signed. */
|
||
typedef size_t __re_idx_t;
|
||
|
||
/* The type of object sizes. */
|
||
typedef size_t __re_size_t;
|
||
|
||
/* The type of object sizes, in places where the traditional code
|
||
uses unsigned long int. */
|
||
typedef size_t __re_long_size_t;
|
||
|
||
#else
|
||
|
||
/* Use types that are binary-compatible with the traditional GNU regex
|
||
implementation, which mishandles strings longer than INT_MAX. */
|
||
|
||
typedef int regoff_t;
|
||
typedef int __re_idx_t;
|
||
typedef unsigned int __re_size_t;
|
||
typedef unsigned long int __re_long_size_t;
|
||
|
||
#endif
|
||
|
||
/* The following two types have to be signed and unsigned integer type
|
||
wide enough to hold a value of a pointer. For most ANSI compilers
|
||
ptrdiff_t and size_t should be likely OK. Still size of these two
|
||
types is 2 for Microsoft C. Ugh... */
|
||
typedef long int s_reg_t;
|
||
typedef unsigned long int active_reg_t;
|
||
|
||
/* The following bits are used to determine the regexp syntax we
|
||
recognize. The set/not-set meanings are chosen so that Emacs syntax
|
||
remains the value 0. The bits are given in alphabetical order, and
|
||
the definitions shifted by one from the previous bit; thus, when we
|
||
add or remove a bit, only one other definition need change. */
|
||
typedef unsigned long int reg_syntax_t;
|
||
|
||
#ifdef __USE_GNU_REGEX
|
||
|
||
/* If this bit is not set, then \ inside a bracket expression is literal.
|
||
If set, then such a \ quotes the following character. */
|
||
# define RE_BACKSLASH_ESCAPE_IN_LISTS ((unsigned long int) 1)
|
||
|
||
/* If this bit is not set, then + and ? are operators, and \+ and \? are
|
||
literals.
|
||
If set, then \+ and \? are operators and + and ? are literals. */
|
||
# define RE_BK_PLUS_QM (RE_BACKSLASH_ESCAPE_IN_LISTS << 1)
|
||
|
||
/* If this bit is set, then character classes are supported. They are:
|
||
[:alpha:], [:upper:], [:lower:], [:digit:], [:alnum:], [:xdigit:],
|
||
[:space:], [:print:], [:punct:], [:graph:], and [:cntrl:].
|
||
If not set, then character classes are not supported. */
|
||
# define RE_CHAR_CLASSES (RE_BK_PLUS_QM << 1)
|
||
|
||
/* If this bit is set, then ^ and $ are always anchors (outside bracket
|
||
expressions, of course).
|
||
If this bit is not set, then it depends:
|
||
^ is an anchor if it is at the beginning of a regular
|
||
expression or after an open-group or an alternation operator;
|
||
$ is an anchor if it is at the end of a regular expression, or
|
||
before a close-group or an alternation operator.
|
||
|
||
This bit could be (re)combined with RE_CONTEXT_INDEP_OPS, because
|
||
POSIX draft 11.2 says that * etc. in leading positions is undefined.
|
||
We already implemented a previous draft which made those constructs
|
||
invalid, though, so we haven't changed the code back. */
|
||
# define RE_CONTEXT_INDEP_ANCHORS (RE_CHAR_CLASSES << 1)
|
||
|
||
/* If this bit is set, then special characters are always special
|
||
regardless of where they are in the pattern.
|
||
If this bit is not set, then special characters are special only in
|
||
some contexts; otherwise they are ordinary. Specifically,
|
||
* + ? and intervals are only special when not after the beginning,
|
||
open-group, or alternation operator. */
|
||
# define RE_CONTEXT_INDEP_OPS (RE_CONTEXT_INDEP_ANCHORS << 1)
|
||
|
||
/* If this bit is set, then *, +, ?, and { cannot be first in an re or
|
||
immediately after an alternation or begin-group operator. */
|
||
# define RE_CONTEXT_INVALID_OPS (RE_CONTEXT_INDEP_OPS << 1)
|
||
|
||
/* If this bit is set, then . matches newline.
|
||
If not set, then it doesn't. */
|
||
# define RE_DOT_NEWLINE (RE_CONTEXT_INVALID_OPS << 1)
|
||
|
||
/* If this bit is set, then . doesn't match NUL.
|
||
If not set, then it does. */
|
||
# define RE_DOT_NOT_NULL (RE_DOT_NEWLINE << 1)
|
||
|
||
/* If this bit is set, nonmatching lists [^...] do not match newline.
|
||
If not set, they do. */
|
||
# define RE_HAT_LISTS_NOT_NEWLINE (RE_DOT_NOT_NULL << 1)
|
||
|
||
/* If this bit is set, either \{...\} or {...} defines an
|
||
interval, depending on RE_NO_BK_BRACES.
|
||
If not set, \{, \}, {, and } are literals. */
|
||
# define RE_INTERVALS (RE_HAT_LISTS_NOT_NEWLINE << 1)
|
||
|
||
/* If this bit is set, +, ? and | aren't recognized as operators.
|
||
If not set, they are. */
|
||
# define RE_LIMITED_OPS (RE_INTERVALS << 1)
|
||
|
||
/* If this bit is set, newline is an alternation operator.
|
||
If not set, newline is literal. */
|
||
# define RE_NEWLINE_ALT (RE_LIMITED_OPS << 1)
|
||
|
||
/* If this bit is set, then `{...}' defines an interval, and \{ and \}
|
||
are literals.
|
||
If not set, then `\{...\}' defines an interval. */
|
||
# define RE_NO_BK_BRACES (RE_NEWLINE_ALT << 1)
|
||
|
||
/* If this bit is set, (...) defines a group, and \( and \) are literals.
|
||
If not set, \(...\) defines a group, and ( and ) are literals. */
|
||
# define RE_NO_BK_PARENS (RE_NO_BK_BRACES << 1)
|
||
|
||
/* If this bit is set, then \<digit> matches <digit>.
|
||
If not set, then \<digit> is a back-reference. */
|
||
# define RE_NO_BK_REFS (RE_NO_BK_PARENS << 1)
|
||
|
||
/* If this bit is set, then | is an alternation operator, and \| is literal.
|
||
If not set, then \| is an alternation operator, and | is literal. */
|
||
# define RE_NO_BK_VBAR (RE_NO_BK_REFS << 1)
|
||
|
||
/* If this bit is set, then an ending range point collating higher
|
||
than the starting range point, as in [z-a], is invalid.
|
||
If not set, then when ending range point collates higher than the
|
||
starting range point, the range is ignored. */
|
||
# define RE_NO_EMPTY_RANGES (RE_NO_BK_VBAR << 1)
|
||
|
||
/* If this bit is set, then an unmatched ) is ordinary.
|
||
If not set, then an unmatched ) is invalid. */
|
||
# define RE_UNMATCHED_RIGHT_PAREN_ORD (RE_NO_EMPTY_RANGES << 1)
|
||
|
||
/* If this bit is set, succeed as soon as we match the whole pattern,
|
||
without further backtracking. */
|
||
# define RE_NO_POSIX_BACKTRACKING (RE_UNMATCHED_RIGHT_PAREN_ORD << 1)
|
||
|
||
/* If this bit is set, do not process the GNU regex operators.
|
||
If not set, then the GNU regex operators are recognized. */
|
||
# define RE_NO_GNU_OPS (RE_NO_POSIX_BACKTRACKING << 1)
|
||
|
||
/* If this bit is set, turn on internal regex debugging.
|
||
If not set, and debugging was on, turn it off.
|
||
This only works if regex.c is compiled -DDEBUG.
|
||
We define this bit always, so that all that's needed to turn on
|
||
debugging is to recompile regex.c; the calling code can always have
|
||
this bit set, and it won't affect anything in the normal case. */
|
||
# define RE_DEBUG (RE_NO_GNU_OPS << 1)
|
||
|
||
/* If this bit is set, a syntactically invalid interval is treated as
|
||
a string of ordinary characters. For example, the ERE 'a{1' is
|
||
treated as 'a\{1'. */
|
||
# define RE_INVALID_INTERVAL_ORD (RE_DEBUG << 1)
|
||
|
||
/* If this bit is set, then ignore case when matching.
|
||
If not set, then case is significant. */
|
||
# define RE_ICASE (RE_INVALID_INTERVAL_ORD << 1)
|
||
|
||
/* This bit is used internally like RE_CONTEXT_INDEP_ANCHORS but only
|
||
for ^, because it is difficult to scan the regex backwards to find
|
||
whether ^ should be special. */
|
||
# define RE_CARET_ANCHORS_HERE (RE_ICASE << 1)
|
||
|
||
/* If this bit is set, then \{ cannot be first in an bre or
|
||
immediately after an alternation or begin-group operator. */
|
||
# define RE_CONTEXT_INVALID_DUP (RE_CARET_ANCHORS_HERE << 1)
|
||
|
||
/* If this bit is set, then no_sub will be set to 1 during
|
||
re_compile_pattern. */
|
||
# define RE_NO_SUB (RE_CONTEXT_INVALID_DUP << 1)
|
||
|
||
#endif /* defined __USE_GNU_REGEX */
|
||
|
||
/* This global variable defines the particular regexp syntax to use (for
|
||
some interfaces). When a regexp is compiled, the syntax used is
|
||
stored in the pattern buffer, so changing this does not affect
|
||
already-compiled regexps. */
|
||
extern reg_syntax_t re_syntax_options;
|
||
|
||
#ifdef __USE_GNU_REGEX
|
||
/* Define combinations of the above bits for the standard possibilities.
|
||
(The [[[ comments delimit what gets put into the Texinfo file, so
|
||
don't delete them!) */
|
||
/* [[[begin syntaxes]]] */
|
||
# define RE_SYNTAX_EMACS 0
|
||
|
||
# define RE_SYNTAX_AWK \
|
||
(RE_BACKSLASH_ESCAPE_IN_LISTS | RE_DOT_NOT_NULL \
|
||
| RE_NO_BK_PARENS | RE_NO_BK_REFS \
|
||
| RE_NO_BK_VBAR | RE_NO_EMPTY_RANGES \
|
||
| RE_DOT_NEWLINE | RE_CONTEXT_INDEP_ANCHORS \
|
||
| RE_UNMATCHED_RIGHT_PAREN_ORD | RE_NO_GNU_OPS)
|
||
|
||
# define RE_SYNTAX_GNU_AWK \
|
||
((RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS | RE_DEBUG) \
|
||
& ~(RE_DOT_NOT_NULL | RE_INTERVALS | RE_CONTEXT_INDEP_OPS \
|
||
| RE_CONTEXT_INVALID_OPS ))
|
||
|
||
# define RE_SYNTAX_POSIX_AWK \
|
||
(RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS \
|
||
| RE_INTERVALS | RE_NO_GNU_OPS)
|
||
|
||
# define RE_SYNTAX_GREP \
|
||
(RE_BK_PLUS_QM | RE_CHAR_CLASSES \
|
||
| RE_HAT_LISTS_NOT_NEWLINE | RE_INTERVALS \
|
||
| RE_NEWLINE_ALT)
|
||
|
||
# define RE_SYNTAX_EGREP \
|
||
(RE_CHAR_CLASSES | RE_CONTEXT_INDEP_ANCHORS \
|
||
| RE_CONTEXT_INDEP_OPS | RE_HAT_LISTS_NOT_NEWLINE \
|
||
| RE_NEWLINE_ALT | RE_NO_BK_PARENS \
|
||
| RE_NO_BK_VBAR)
|
||
|
||
# define RE_SYNTAX_POSIX_EGREP \
|
||
(RE_SYNTAX_EGREP | RE_INTERVALS | RE_NO_BK_BRACES \
|
||
| RE_INVALID_INTERVAL_ORD)
|
||
|
||
/* P1003.2/D11.2, section 4.20.7.1, lines 5078ff. */
|
||
# define RE_SYNTAX_ED RE_SYNTAX_POSIX_BASIC
|
||
|
||
# define RE_SYNTAX_SED RE_SYNTAX_POSIX_BASIC
|
||
|
||
/* Syntax bits common to both basic and extended POSIX regex syntax. */
|
||
# define _RE_SYNTAX_POSIX_COMMON \
|
||
(RE_CHAR_CLASSES | RE_DOT_NEWLINE | RE_DOT_NOT_NULL \
|
||
| RE_INTERVALS | RE_NO_EMPTY_RANGES)
|
||
|
||
# define RE_SYNTAX_POSIX_BASIC \
|
||
(_RE_SYNTAX_POSIX_COMMON | RE_BK_PLUS_QM | RE_CONTEXT_INVALID_DUP)
|
||
|
||
/* Differs from ..._POSIX_BASIC only in that RE_BK_PLUS_QM becomes
|
||
RE_LIMITED_OPS, i.e., \? \+ \| are not recognized. Actually, this
|
||
isn't minimal, since other operators, such as \`, aren't disabled. */
|
||
# define RE_SYNTAX_POSIX_MINIMAL_BASIC \
|
||
(_RE_SYNTAX_POSIX_COMMON | RE_LIMITED_OPS)
|
||
|
||
# define RE_SYNTAX_POSIX_EXTENDED \
|
||
(_RE_SYNTAX_POSIX_COMMON | RE_CONTEXT_INDEP_ANCHORS \
|
||
| RE_CONTEXT_INDEP_OPS | RE_NO_BK_BRACES \
|
||
| RE_NO_BK_PARENS | RE_NO_BK_VBAR \
|
||
| RE_CONTEXT_INVALID_OPS | RE_UNMATCHED_RIGHT_PAREN_ORD)
|
||
|
||
/* Differs from ..._POSIX_EXTENDED in that RE_CONTEXT_INDEP_OPS is
|
||
removed and RE_NO_BK_REFS is added. */
|
||
# define RE_SYNTAX_POSIX_MINIMAL_EXTENDED \
|
||
(_RE_SYNTAX_POSIX_COMMON | RE_CONTEXT_INDEP_ANCHORS \
|
||
| RE_CONTEXT_INVALID_OPS | RE_NO_BK_BRACES \
|
||
| RE_NO_BK_PARENS | RE_NO_BK_REFS \
|
||
| RE_NO_BK_VBAR | RE_UNMATCHED_RIGHT_PAREN_ORD)
|
||
/* [[[end syntaxes]]] */
|
||
|
||
#endif /* defined __USE_GNU_REGEX */
|
||
|
||
#ifdef __USE_GNU_REGEX
|
||
|
||
/* Maximum number of duplicates an interval can allow. POSIX-conforming
|
||
systems might define this in <limits.h>, but we want our
|
||
value, so remove any previous define. */
|
||
# ifdef RE_DUP_MAX
|
||
# undef RE_DUP_MAX
|
||
# endif
|
||
|
||
/* RE_DUP_MAX is 2**15 - 1 because an earlier implementation stored
|
||
the counter as a 2-byte signed integer. This is no longer true, so
|
||
RE_DUP_MAX could be increased to (INT_MAX / 10 - 1), or to
|
||
((SIZE_MAX - 2) / 10 - 1) if _REGEX_LARGE_OFFSETS is defined.
|
||
However, there would be a huge performance problem if someone
|
||
actually used a pattern like a\{214748363\}, so RE_DUP_MAX retains
|
||
its historical value. */
|
||
# define RE_DUP_MAX (0x7fff)
|
||
|
||
#endif /* defined __USE_GNU_REGEX */
|
||
|
||
|
||
/* POSIX `cflags' bits (i.e., information for `regcomp'). */
|
||
|
||
/* If this bit is set, then use extended regular expression syntax.
|
||
If not set, then use basic regular expression syntax. */
|
||
#define REG_EXTENDED 1
|
||
|
||
/* If this bit is set, then ignore case when matching.
|
||
If not set, then case is significant. */
|
||
#define REG_ICASE (1 << 1)
|
||
|
||
/* If this bit is set, then anchors do not match at newline
|
||
characters in the string.
|
||
If not set, then anchors do match at newlines. */
|
||
#define REG_NEWLINE (1 << 2)
|
||
|
||
/* If this bit is set, then report only success or fail in regexec.
|
||
If not set, then returns differ between not matching and errors. */
|
||
#define REG_NOSUB (1 << 3)
|
||
|
||
|
||
/* POSIX `eflags' bits (i.e., information for regexec). */
|
||
|
||
/* If this bit is set, then the beginning-of-line operator doesn't match
|
||
the beginning of the string (presumably because it's not the
|
||
beginning of a line).
|
||
If not set, then the beginning-of-line operator does match the
|
||
beginning of the string. */
|
||
#define REG_NOTBOL 1
|
||
|
||
/* Like REG_NOTBOL, except for the end-of-line. */
|
||
#define REG_NOTEOL (1 << 1)
|
||
|
||
/* Use PMATCH[0] to delimit the start and end of the search in the
|
||
buffer. */
|
||
#define REG_STARTEND (1 << 2)
|
||
|
||
|
||
/* If any error codes are removed, changed, or added, update the
|
||
`__re_error_msgid' table in regcomp.c. */
|
||
|
||
typedef enum
|
||
{
|
||
_REG_ENOSYS = -1, /* This will never happen for this implementation. */
|
||
_REG_NOERROR = 0, /* Success. */
|
||
_REG_NOMATCH, /* Didn't find a match (for regexec). */
|
||
|
||
/* POSIX regcomp return error codes. (In the order listed in the
|
||
standard.) */
|
||
_REG_BADPAT, /* Invalid pattern. */
|
||
_REG_ECOLLATE, /* Invalid collating element. */
|
||
_REG_ECTYPE, /* Invalid character class name. */
|
||
_REG_EESCAPE, /* Trailing backslash. */
|
||
_REG_ESUBREG, /* Invalid back reference. */
|
||
_REG_EBRACK, /* Unmatched left bracket. */
|
||
_REG_EPAREN, /* Parenthesis imbalance. */
|
||
_REG_EBRACE, /* Unmatched \{. */
|
||
_REG_BADBR, /* Invalid contents of \{\}. */
|
||
_REG_ERANGE, /* Invalid range end. */
|
||
_REG_ESPACE, /* Ran out of memory. */
|
||
_REG_BADRPT, /* No preceding re for repetition op. */
|
||
|
||
/* Error codes we've added. */
|
||
_REG_EEND, /* Premature end. */
|
||
_REG_ESIZE, /* Compiled pattern bigger than 2^16 bytes. */
|
||
_REG_ERPAREN /* Unmatched ) or \); not returned from regcomp. */
|
||
} reg_errcode_t;
|
||
|
||
#ifdef _XOPEN_SOURCE
|
||
# define REG_ENOSYS _REG_ENOSYS
|
||
#endif
|
||
#define REG_NOERROR _REG_NOERROR
|
||
#define REG_NOMATCH _REG_NOMATCH
|
||
#define REG_BADPAT _REG_BADPAT
|
||
#define REG_ECOLLATE _REG_ECOLLATE
|
||
#define REG_ECTYPE _REG_ECTYPE
|
||
#define REG_EESCAPE _REG_EESCAPE
|
||
#define REG_ESUBREG _REG_ESUBREG
|
||
#define REG_EBRACK _REG_EBRACK
|
||
#define REG_EPAREN _REG_EPAREN
|
||
#define REG_EBRACE _REG_EBRACE
|
||
#define REG_BADBR _REG_BADBR
|
||
#define REG_ERANGE _REG_ERANGE
|
||
#define REG_ESPACE _REG_ESPACE
|
||
#define REG_BADRPT _REG_BADRPT
|
||
#define REG_EEND _REG_EEND
|
||
#define REG_ESIZE _REG_ESIZE
|
||
#define REG_ERPAREN _REG_ERPAREN
|
||
|
||
/* struct re_pattern_buffer normally uses member names like `buffer'
|
||
that POSIX does not allow. In POSIX mode these members have names
|
||
with leading `re_' (e.g., `re_buffer'). */
|
||
#ifdef __USE_GNU_REGEX
|
||
# define _REG_RE_NAME(id) id
|
||
# define _REG_RM_NAME(id) id
|
||
#else
|
||
# define _REG_RE_NAME(id) re_##id
|
||
# define _REG_RM_NAME(id) rm_##id
|
||
#endif
|
||
|
||
/* The user can specify the type of the re_translate member by
|
||
defining the macro RE_TRANSLATE_TYPE, which defaults to unsigned
|
||
char *. This pollutes the POSIX name space, so in POSIX mode just
|
||
use unsigned char *. */
|
||
#ifdef __USE_GNU_REGEX
|
||
# ifndef RE_TRANSLATE_TYPE
|
||
# define RE_TRANSLATE_TYPE unsigned char *
|
||
# endif
|
||
# define REG_TRANSLATE_TYPE RE_TRANSLATE_TYPE
|
||
#else
|
||
# define REG_TRANSLATE_TYPE unsigned char *
|
||
#endif
|
||
|
||
/* This data structure represents a compiled pattern. Before calling
|
||
the pattern compiler, the fields `buffer', `allocated', `fastmap',
|
||
`translate', and `no_sub' can be set. After the pattern has been
|
||
compiled, the `re_nsub' field is available. All other fields are
|
||
private to the regex routines. */
|
||
|
||
struct re_pattern_buffer
|
||
{
|
||
/* Space that holds the compiled pattern. It is declared as
|
||
`unsigned char *' because its elements are sometimes used as
|
||
array indexes. */
|
||
unsigned char *_REG_RE_NAME (buffer);
|
||
|
||
/* Number of bytes to which `buffer' points. */
|
||
__re_long_size_t _REG_RE_NAME (allocated);
|
||
|
||
/* Number of bytes actually used in `buffer'. */
|
||
__re_long_size_t _REG_RE_NAME (used);
|
||
|
||
/* Syntax setting with which the pattern was compiled. */
|
||
reg_syntax_t _REG_RE_NAME (syntax);
|
||
|
||
/* Pointer to a fastmap, if any, otherwise zero. re_search uses the
|
||
fastmap, if there is one, to skip over impossible starting points
|
||
for matches. */
|
||
char *_REG_RE_NAME (fastmap);
|
||
|
||
/* Either a translate table to apply to all characters before
|
||
comparing them, or zero for no translation. The translation is
|
||
applied to a pattern when it is compiled and to a string when it
|
||
is matched. */
|
||
REG_TRANSLATE_TYPE _REG_RE_NAME (translate);
|
||
|
||
/* Number of subexpressions found by the compiler. */
|
||
size_t re_nsub;
|
||
|
||
/* Zero if this pattern cannot match the empty string, one else.
|
||
Well, in truth it's used only in `re_search_2', to see whether or
|
||
not we should use the fastmap, so we don't set this absolutely
|
||
perfectly; see `re_compile_fastmap' (the `duplicate' case). */
|
||
unsigned int _REG_RE_NAME (can_be_null) : 1;
|
||
|
||
/* If REGS_UNALLOCATED, allocate space in the `regs' structure
|
||
for `max (RE_NREGS, re_nsub + 1)' groups.
|
||
If REGS_REALLOCATE, reallocate space if necessary.
|
||
If REGS_FIXED, use what's there. */
|
||
#ifdef __USE_GNU_REGEX
|
||
# define REGS_UNALLOCATED 0
|
||
# define REGS_REALLOCATE 1
|
||
# define REGS_FIXED 2
|
||
#endif
|
||
unsigned int _REG_RE_NAME (regs_allocated) : 2;
|
||
|
||
/* Set to zero when `regex_compile' compiles a pattern; set to one
|
||
by `re_compile_fastmap' if it updates the fastmap. */
|
||
unsigned int _REG_RE_NAME (fastmap_accurate) : 1;
|
||
|
||
/* If set, `re_match_2' does not return information about
|
||
subexpressions. */
|
||
unsigned int _REG_RE_NAME (no_sub) : 1;
|
||
|
||
/* If set, a beginning-of-line anchor doesn't match at the beginning
|
||
of the string. */
|
||
unsigned int _REG_RE_NAME (not_bol) : 1;
|
||
|
||
/* Similarly for an end-of-line anchor. */
|
||
unsigned int _REG_RE_NAME (not_eol) : 1;
|
||
|
||
/* If true, an anchor at a newline matches. */
|
||
unsigned int _REG_RE_NAME (newline_anchor) : 1;
|
||
|
||
/* [[[end pattern_buffer]]] */
|
||
};
|
||
|
||
typedef struct re_pattern_buffer regex_t;
|
||
|
||
/* This is the structure we store register match data in. See
|
||
regex.texinfo for a full description of what registers match. */
|
||
struct re_registers
|
||
{
|
||
__re_size_t _REG_RM_NAME (num_regs);
|
||
regoff_t *_REG_RM_NAME (start);
|
||
regoff_t *_REG_RM_NAME (end);
|
||
};
|
||
|
||
|
||
/* If `regs_allocated' is REGS_UNALLOCATED in the pattern buffer,
|
||
`re_match_2' returns information about at least this many registers
|
||
the first time a `regs' structure is passed. */
|
||
#if !defined RE_NREGS && defined __USE_GNU_REGEX
|
||
# define RE_NREGS 30
|
||
#endif
|
||
|
||
|
||
/* POSIX specification for registers. Aside from the different names than
|
||
`re_registers', POSIX uses an array of structures, instead of a
|
||
structure of arrays. */
|
||
typedef struct
|
||
{
|
||
regoff_t rm_so; /* Byte offset from string's start to substring's start. */
|
||
regoff_t rm_eo; /* Byte offset from string's start to substring's end. */
|
||
} regmatch_t;
|
||
|
||
/* Declarations for routines. */
|
||
|
||
/* Sets the current default syntax to SYNTAX, and return the old syntax.
|
||
You can also simply assign to the `re_syntax_options' variable. */
|
||
extern reg_syntax_t re_set_syntax (reg_syntax_t __syntax);
|
||
|
||
/* Compile the regular expression PATTERN, with length LENGTH
|
||
and syntax given by the global `re_syntax_options', into the buffer
|
||
BUFFER. Return NULL if successful, and an error string if not. */
|
||
extern const char *re_compile_pattern (const char *__pattern, size_t __length,
|
||
struct re_pattern_buffer *__buffer);
|
||
|
||
|
||
/* Compile a fastmap for the compiled pattern in BUFFER; used to
|
||
accelerate searches. Return 0 if successful and -2 if was an
|
||
internal error. */
|
||
extern int re_compile_fastmap (struct re_pattern_buffer *__buffer);
|
||
|
||
|
||
/* Search in the string STRING (with length LENGTH) for the pattern
|
||
compiled into BUFFER. Start searching at position START, for RANGE
|
||
characters. Return the starting position of the match, -1 for no
|
||
match, or -2 for an internal error. Also return register
|
||
information in REGS (if REGS and BUFFER->no_sub are nonzero). */
|
||
extern regoff_t re_search (struct re_pattern_buffer *__buffer,
|
||
const char *__string, __re_idx_t __length,
|
||
__re_idx_t __start, regoff_t __range,
|
||
struct re_registers *__regs);
|
||
|
||
|
||
/* Like `re_search', but search in the concatenation of STRING1 and
|
||
STRING2. Also, stop searching at index START + STOP. */
|
||
extern regoff_t re_search_2 (struct re_pattern_buffer *__buffer,
|
||
const char *__string1, __re_idx_t __length1,
|
||
const char *__string2, __re_idx_t __length2,
|
||
__re_idx_t __start, regoff_t __range,
|
||
struct re_registers *__regs,
|
||
__re_idx_t __stop);
|
||
|
||
|
||
/* Like `re_search', but return how many characters in STRING the regexp
|
||
in BUFFER matched, starting at position START. */
|
||
extern regoff_t re_match (struct re_pattern_buffer *__buffer,
|
||
const char *__string, __re_idx_t __length,
|
||
__re_idx_t __start, struct re_registers *__regs);
|
||
|
||
|
||
/* Relates to `re_match' as `re_search_2' relates to `re_search'. */
|
||
extern regoff_t re_match_2 (struct re_pattern_buffer *__buffer,
|
||
const char *__string1, __re_idx_t __length1,
|
||
const char *__string2, __re_idx_t __length2,
|
||
__re_idx_t __start, struct re_registers *__regs,
|
||
__re_idx_t __stop);
|
||
|
||
|
||
/* Set REGS to hold NUM_REGS registers, storing them in STARTS and
|
||
ENDS. Subsequent matches using BUFFER and REGS will use this memory
|
||
for recording register information. STARTS and ENDS must be
|
||
allocated with malloc, and must each be at least `NUM_REGS * sizeof
|
||
(regoff_t)' bytes long.
|
||
|
||
If NUM_REGS == 0, then subsequent matches should allocate their own
|
||
register data.
|
||
|
||
Unless this function is called, the first search or match using
|
||
PATTERN_BUFFER will allocate its own register data, without
|
||
freeing the old data. */
|
||
extern void re_set_registers (struct re_pattern_buffer *__buffer,
|
||
struct re_registers *__regs,
|
||
__re_size_t __num_regs,
|
||
regoff_t *__starts, regoff_t *__ends);
|
||
|
||
#if defined _REGEX_RE_COMP || defined _LIBC
|
||
# ifndef _CRAY
|
||
/* 4.2 bsd compatibility. */
|
||
extern char *re_comp (const char *);
|
||
extern int re_exec (const char *);
|
||
# endif
|
||
#endif
|
||
|
||
/* GCC 2.95 and later have "__restrict"; C99 compilers have
|
||
"restrict", and "configure" may have defined "restrict".
|
||
Other compilers use __restrict, __restrict__, and _Restrict, and
|
||
'configure' might #define 'restrict' to those words, so pick a
|
||
different name. */
|
||
#ifndef _Restrict_
|
||
# if 199901L <= __STDC_VERSION__
|
||
# define _Restrict_ restrict
|
||
# elif 2 < __GNUC__ || (2 == __GNUC__ && 95 <= __GNUC_MINOR__)
|
||
# define _Restrict_ __restrict
|
||
# else
|
||
# define _Restrict_
|
||
# endif
|
||
#endif
|
||
/* gcc 3.1 and up support the [restrict] syntax. Don't trust
|
||
sys/cdefs.h's definition of __restrict_arr, though, as it
|
||
mishandles gcc -ansi -pedantic. */
|
||
#ifndef _Restrict_arr_
|
||
# if ((199901L <= __STDC_VERSION__ \
|
||
|| ((3 < __GNUC__ || (3 == __GNUC__ && 1 <= __GNUC_MINOR__)) \
|
||
&& !__STRICT_ANSI__)) \
|
||
&& !defined __GNUG__)
|
||
# define _Restrict_arr_ _Restrict_
|
||
# else
|
||
# define _Restrict_arr_
|
||
# endif
|
||
#endif
|
||
|
||
/* POSIX compatibility. */
|
||
extern int regcomp (regex_t *_Restrict_ __preg,
|
||
const char *_Restrict_ __pattern,
|
||
int __cflags);
|
||
|
||
extern int regexec (const regex_t *_Restrict_ __preg,
|
||
const char *_Restrict_ __string, size_t __nmatch,
|
||
regmatch_t __pmatch[_Restrict_arr_],
|
||
int __eflags);
|
||
|
||
extern size_t regerror (int __errcode, const regex_t *_Restrict_ __preg,
|
||
char *_Restrict_ __errbuf, size_t __errbuf_size);
|
||
|
||
extern void regfree (regex_t *__preg);
|
||
|
||
|
||
#ifdef __cplusplus
|
||
}
|
||
#endif /* C++ */
|
||
|
||
#endif /* regex.h */
|