[Nagiosplug-checkins] nagiosplug/lib regcomp.c,NONE,1.1 regex.c,NONE,1.1 regex.h,NONE,1.1 regex.o,NONE,1.1 regex_internal.c,NONE,1.1 regex_internal.h,NONE,1.1 regexec.c,NONE,1.1 strcase.h,NONE,1.1 .cvsignore,1.3,1.4
Ton Voon
tonvoon at users.sourceforge.net
Thu May 25 05:34:18 CEST 2006
- Previous message: [Nagiosplug-checkins] nagiosplug/m4 ls-mntd-fs.m4,1.2,1.3
- Next message: [Nagiosplug-checkins] nagiosplug/plugins check_apt.c,1.5,1.6 check_snmp.c,1.59,1.60 check_smtp.c,1.50,1.51 check_http.c,1.89,1.90
- Messages sorted by:
[ date ]
[ thread ]
[ subject ]
[ author ]
Update of /cvsroot/nagiosplug/nagiosplug/lib
In directory sc8-pr-cvs7.sourceforge.net:/tmp/cvs-serv20401/lib
Modified Files:
.cvsignore
Added Files:
regcomp.c regex.c regex.h regex.o regex_internal.c
regex_internal.h regexec.c strcase.h
Log Message:
Use coreutils' regexp libraries, so regexp always available now
Index: .cvsignore
===================================================================
RCS file: /cvsroot/nagiosplug/nagiosplug/lib/.cvsignore,v
retrieving revision 1.3
retrieving revision 1.4
diff -u -d -r1.3 -r1.4
--- .cvsignore 6 Aug 2003 14:26:27 -0000 1.3
+++ .cvsignore 25 May 2006 12:33:24 -0000 1.4
@@ -1,20 +1,4 @@
Makefile
Makefile.in
.deps
-codeset.m4
-gettext.m4
-glibc21.m4
-iconv.m4
-intdiv0.m4
-inttypes-pri.m4
-inttypes.m4
-inttypes_h.m4
-isc-posix.m4
-lcmessage.m4
-lib-ld.m4
-lib-link.m4
-lib-prefix.m4
-progtest.m4
-stdint_h.m4
-uintmax_t.m4
-ulonglong.m4
+getopt.h
--- NEW FILE: regexec.c ---
/* Extended regular expression matching and search library.
Copyright (C) 2002, 2003, 2004, 2005 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Isamu Hasegawa <isamu at yamato.ibm.com>.
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. */
[...4294 lines suppressed...]
new_entry->node = node;
new_entry->str_idx = str_idx;
++subtop->nlasts;
}
return new_entry;
}
static void
internal_function
sift_ctx_init (re_sift_context_t *sctx,
re_dfastate_t **sifted_sts,
re_dfastate_t **limited_sts,
Idx last_node, Idx last_str_idx)
{
sctx->sifted_states = sifted_sts;
sctx->limited_states = limited_sts;
sctx->last_node = last_node;
sctx->last_str_idx = last_str_idx;
re_node_set_init_empty (&sctx->limits);
}
--- NEW FILE: strcase.h ---
/* Case-insensitive string comparison functions.
Copyright (C) 1995-1996, 2001, 2003, 2005 Free Software Foundation, Inc.
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 _STRCASE_H
#define _STRCASE_H
#include <stddef.h>
#ifdef __cplusplus
extern "C" {
#endif
/* Compare strings S1 and S2, ignoring case, returning less than, equal to or
greater than zero if S1 is lexicographically less than, equal to or greater
than S2.
Note: This function may, in multibyte locales, return 0 for strings of
different lengths! */
extern int strcasecmp (const char *s1, const char *s2);
/* Compare no more than N characters of strings S1 and S2, ignoring case,
returning less than, equal to or greater than zero if S1 is
lexicographically less than, equal to or greater than S2.
Note: This function can not work correctly in multibyte locales. */
extern int strncasecmp (const char *s1, const char *s2, size_t n);
#ifdef __cplusplus
}
#endif
#endif /* _STRCASE_H */
--- NEW FILE: regex.c ---
/* Extended regular expression matching and search library.
Copyright (C) 2002, 2003 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Isamu Hasegawa <isamu at yamato.ibm.com>.
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. */
#ifdef HAVE_CONFIG_H
# include <config.h>
#endif
#ifdef _LIBC
/* We have to keep the namespace clean. */
# define regfree(preg) __regfree (preg)
# define regexec(pr, st, nm, pm, ef) __regexec (pr, st, nm, pm, ef)
# define regcomp(preg, pattern, cflags) __regcomp (preg, pattern, cflags)
# define regerror(errcode, preg, errbuf, errbuf_size) \
__regerror(errcode, preg, errbuf, errbuf_size)
# define re_set_registers(bu, re, nu, st, en) \
__re_set_registers (bu, re, nu, st, en)
# define re_match_2(bufp, string1, size1, string2, size2, pos, regs, stop) \
__re_match_2 (bufp, string1, size1, string2, size2, pos, regs, stop)
# define re_match(bufp, string, size, pos, regs) \
__re_match (bufp, string, size, pos, regs)
# define re_search(bufp, string, size, startpos, range, regs) \
__re_search (bufp, string, size, startpos, range, regs)
# define re_compile_pattern(pattern, length, bufp) \
__re_compile_pattern (pattern, length, bufp)
# define re_set_syntax(syntax) __re_set_syntax (syntax)
# define re_search_2(bufp, st1, s1, st2, s2, startpos, range, regs, stop) \
__re_search_2 (bufp, st1, s1, st2, s2, startpos, range, regs, stop)
# define re_compile_fastmap(bufp) __re_compile_fastmap (bufp)
# include "../locale/localeinfo.h"
#endif
/* On some systems, limits.h sets RE_DUP_MAX to a lower value than
GNU regex allows. Include it before <regex.h>, which correctly
#undefs RE_DUP_MAX and sets it to the right value. */
#include <limits.h>
#include <regex.h>
#include "regex_internal.h"
#include "regex_internal.c"
#include "regcomp.c"
#include "regexec.c"
/* Binary backward compatibility. */
#if _LIBC
# include <shlib-compat.h>
# if SHLIB_COMPAT (libc, GLIBC_2_0, GLIBC_2_3)
link_warning (re_max_failures, "the 're_max_failures' variable is obsolete and will go away.")
int re_max_failures = 2000;
# endif
#endif
--- NEW FILE: regex.o ---
(This appears to be a binary file; contents omitted.)
--- NEW FILE: regex.h ---
/* Definitions for data structures and routines for the regular
expression library.
Copyright (C) 1985,1989-93,1995-98,2000,2001,2002,2003,2005
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 _REGEX_SOURCE to get definitions that are incompatible with
POSIX. */
#if (!defined _REGEX_SOURCE \
&& (defined _GNU_SOURCE \
|| (!defined _POSIX_C_SOURCE && !defined _POSIX_SOURCE \
&& !defined _XOPEN_SOURCE)))
# define _REGEX_SOURCE 1
#endif
#if defined _REGEX_SOURCE && defined VMS
/* VMS doesn't have `size_t' in <sys/types.h>, even though POSIX says it
should be there. */
# include <stddef.h>
#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. This is a bit odd (and many common
POSIX platforms set it to the more-sensible ssize_t) but we might
as well conform. We don't know of any hosts where ssize_t is wider
than off_t, so off_t is safe. */
typedef off_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;
/* If this bit is not set, then \ inside a bracket expression is literal.
If set, then such a \ quotes the following character. */
#define REG_BACKSLASH_ESCAPE_IN_LISTS 1ul
/* 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 REG_BK_PLUS_QM (1ul << 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 REG_CHAR_CLASSES (1ul << 2)
/* 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 REG_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 REG_CONTEXT_INDEP_ANCHORS (1ul << 3)
/* 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 REG_CONTEXT_INDEP_OPS (1ul << 4)
/* If this bit is set, then *, +, ?, and { cannot be first in an re or
immediately after an alternation or begin-group operator. */
#define REG_CONTEXT_INVALID_OPS (1ul << 5)
/* If this bit is set, then . matches newline.
If not set, then it doesn't. */
#define REG_DOT_NEWLINE (1ul << 6)
/* If this bit is set, then . doesn't match NUL.
If not set, then it does. */
#define REG_DOT_NOT_NULL (1ul << 7)
/* If this bit is set, nonmatching lists [^...] do not match newline.
If not set, they do. */
#define REG_HAT_LISTS_NOT_NEWLINE (1ul << 8)
/* If this bit is set, either \{...\} or {...} defines an
interval, depending on REG_NO_BK_BRACES.
If not set, \{, \}, {, and } are literals. */
#define REG_INTERVALS (1ul << 9)
/* If this bit is set, +, ? and | aren't recognized as operators.
If not set, they are. */
#define REG_LIMITED_OPS (1ul << 10)
/* If this bit is set, newline is an alternation operator.
If not set, newline is literal. */
#define REG_NEWLINE_ALT (1ul << 11)
/* If this bit is set, then `{...}' defines an interval, and \{ and \}
are literals.
If not set, then `\{...\}' defines an interval. */
#define REG_NO_BK_BRACES (1ul << 12)
/* If this bit is set, (...) defines a group, and \( and \) are literals.
If not set, \(...\) defines a group, and ( and ) are literals. */
#define REG_NO_BK_PARENS (1ul << 13)
/* If this bit is set, then \<digit> matches <digit>.
If not set, then \<digit> is a back-reference. */
#define REG_NO_BK_REFS (1ul << 14)
/* 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 REG_NO_BK_VBAR (1ul << 15)
/* 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, the containing range is empty and does not match any string. */
#define REG_NO_EMPTY_RANGES (1ul << 16)
/* If this bit is set, then an unmatched ) is ordinary.
If not set, then an unmatched ) is invalid. */
#define REG_UNMATCHED_RIGHT_PAREN_ORD (1ul << 17)
/* If this bit is set, succeed as soon as we match the whole pattern,
without further backtracking. */
#define REG_NO_POSIX_BACKTRACKING (1ul << 18)
/* If this bit is set, do not process the GNU regex operators.
If not set, then the GNU regex operators are recognized. */
#define REG_NO_GNU_OPS (1ul << 19)
/* 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 REG_DEBUG (1ul << 20)
/* 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 REG_INVALID_INTERVAL_ORD (1ul << 21)
/* If this bit is set, then ignore case when matching.
If not set, then case is significant. */
#define REG_IGNORE_CASE (1ul << 22)
/* This bit is used internally like REG_CONTEXT_INDEP_ANCHORS but only
for ^, because it is difficult to scan the regex backwards to find
whether ^ should be special. */
#define REG_CARET_ANCHORS_HERE (1ul << 23)
/* If this bit is set, then \{ cannot be first in an bre or
immediately after an alternation or begin-group operator. */
#define REG_CONTEXT_INVALID_DUP (1ul << 24)
/* If this bit is set, then no_sub will be set to 1 during
re_compile_pattern. */
#define REG_NO_SUB (1ul << 25)
/* 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;
/* 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 REG_SYNTAX_EMACS 0
#define REG_SYNTAX_AWK \
(REG_BACKSLASH_ESCAPE_IN_LISTS | REG_DOT_NOT_NULL \
| REG_NO_BK_PARENS | REG_NO_BK_REFS \
| REG_NO_BK_VBAR | REG_NO_EMPTY_RANGES \
| REG_DOT_NEWLINE | REG_CONTEXT_INDEP_ANCHORS \
| REG_UNMATCHED_RIGHT_PAREN_ORD | REG_NO_GNU_OPS)
#define REG_SYNTAX_GNU_AWK \
((REG_SYNTAX_POSIX_EXTENDED | REG_BACKSLASH_ESCAPE_IN_LISTS \
| REG_DEBUG) \
& ~(REG_DOT_NOT_NULL | REG_INTERVALS | REG_CONTEXT_INDEP_OPS \
| REG_CONTEXT_INVALID_OPS ))
#define REG_SYNTAX_POSIX_AWK \
(REG_SYNTAX_POSIX_EXTENDED | REG_BACKSLASH_ESCAPE_IN_LISTS \
| REG_INTERVALS | REG_NO_GNU_OPS)
#define REG_SYNTAX_GREP \
(REG_BK_PLUS_QM | REG_CHAR_CLASSES \
| REG_HAT_LISTS_NOT_NEWLINE | REG_INTERVALS \
| REG_NEWLINE_ALT)
#define REG_SYNTAX_EGREP \
(REG_CHAR_CLASSES | REG_CONTEXT_INDEP_ANCHORS \
| REG_CONTEXT_INDEP_OPS | REG_HAT_LISTS_NOT_NEWLINE \
| REG_NEWLINE_ALT | REG_NO_BK_PARENS \
| REG_NO_BK_VBAR)
#define REG_SYNTAX_POSIX_EGREP \
(REG_SYNTAX_EGREP | REG_INTERVALS | REG_NO_BK_BRACES \
| REG_INVALID_INTERVAL_ORD)
/* P1003.2/D11.2, section 4.20.7.1, lines 5078ff. */
#define REG_SYNTAX_ED REG_SYNTAX_POSIX_BASIC
#define REG_SYNTAX_SED REG_SYNTAX_POSIX_BASIC
/* Syntax bits common to both basic and extended POSIX regex syntax. */
#define _REG_SYNTAX_POSIX_COMMON \
(REG_CHAR_CLASSES | REG_DOT_NEWLINE | REG_DOT_NOT_NULL \
| REG_INTERVALS | REG_NO_EMPTY_RANGES)
#define REG_SYNTAX_POSIX_BASIC \
(_REG_SYNTAX_POSIX_COMMON | REG_BK_PLUS_QM | REG_CONTEXT_INVALID_DUP)
/* Differs from ..._POSIX_BASIC only in that REG_BK_PLUS_QM becomes
REG_LIMITED_OPS, i.e., \? \+ \| are not recognized. Actually, this
isn't minimal, since other operators, such as \`, aren't disabled. */
#define REG_SYNTAX_POSIX_MINIMAL_BASIC \
(_REG_SYNTAX_POSIX_COMMON | REG_LIMITED_OPS)
#define REG_SYNTAX_POSIX_EXTENDED \
(_REG_SYNTAX_POSIX_COMMON | REG_CONTEXT_INDEP_ANCHORS \
| REG_CONTEXT_INDEP_OPS | REG_NO_BK_BRACES \
| REG_NO_BK_PARENS | REG_NO_BK_VBAR \
| REG_CONTEXT_INVALID_OPS | REG_UNMATCHED_RIGHT_PAREN_ORD)
/* Differs from ..._POSIX_EXTENDED in that REG_CONTEXT_INDEP_OPS is
removed and REG_NO_BK_REFS is added. */
#define REG_SYNTAX_POSIX_MINIMAL_EXTENDED \
(_REG_SYNTAX_POSIX_COMMON | REG_CONTEXT_INDEP_ANCHORS \
| REG_CONTEXT_INVALID_OPS | REG_NO_BK_BRACES \
| REG_NO_BK_PARENS | REG_NO_BK_REFS \
| REG_NO_BK_VBAR | REG_UNMATCHED_RIGHT_PAREN_ORD)
/* [[[end syntaxes]]] */
/* Maximum number of duplicates an interval can allow. This is
distinct from RE_DUP_MAX, to conform to POSIX name space rules and
to avoid collisions with <limits.h>. */
#define REG_DUP_MAX 32767
/* 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. */
#define REG_ENOSYS _REG_ENOSYS
_REG_NOERROR, /* Success. */
#define REG_NOERROR _REG_NOERROR
_REG_NOMATCH, /* Didn't find a match (for regexec). */
#define REG_NOMATCH _REG_NOMATCH
/* POSIX regcomp return error codes. (In the order listed in the
standard.) */
_REG_BADPAT, /* Invalid pattern. */
#define REG_BADPAT _REG_BADPAT
_REG_ECOLLATE, /* Inalid collating element. */
#define REG_ECOLLATE _REG_ECOLLATE
_REG_ECTYPE, /* Invalid character class name. */
#define REG_ECTYPE _REG_ECTYPE
_REG_EESCAPE, /* Trailing backslash. */
#define REG_EESCAPE _REG_EESCAPE
_REG_ESUBREG, /* Invalid back reference. */
#define REG_ESUBREG _REG_ESUBREG
_REG_EBRACK, /* Unmatched left bracket. */
#define REG_EBRACK _REG_EBRACK
_REG_EPAREN, /* Parenthesis imbalance. */
#define REG_EPAREN _REG_EPAREN
_REG_EBRACE, /* Unmatched \{. */
#define REG_EBRACE _REG_EBRACE
_REG_BADBR, /* Invalid contents of \{\}. */
#define REG_BADBR _REG_BADBR
_REG_ERANGE, /* Invalid range end. */
#define REG_ERANGE _REG_ERANGE
_REG_ESPACE, /* Ran out of memory. */
#define REG_ESPACE _REG_ESPACE
_REG_BADRPT, /* No preceding re for repetition op. */
#define REG_BADRPT _REG_BADRPT
/* Error codes we've added. */
_REG_EEND, /* Premature end. */
#define REG_EEND _REG_EEND
_REG_ESIZE, /* Compiled pattern bigger than 2^16 bytes. */
#define REG_ESIZE _REG_ESIZE
_REG_ERPAREN /* Unmatched ) or \); not returned from regcomp. */
#define REG_ERPAREN _REG_ERPAREN
} reg_errcode_t;
/* In the traditional GNU implementation, regex.h defined member names
like `buffer' that POSIX does not allow. These members now have
names with leading `re_' (e.g., `re_buffer'). Support the old
names only if _REGEX_SOURCE is defined. New programs should use
the new names. */
#ifdef _REGEX_SOURCE
# 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 REG_TRANSLATE_TYPE. In the traditional GNU
implementation, this macro was named RE_TRANSLATE_TYPE, but POSIX
does not allow this. Support the old name only if _REGEX_SOURCE
and if the new name is not defined. New programs should use the new
name. */
#ifndef REG_TRANSLATE_TYPE
# if defined _REGEX_SOURCE && defined RE_TRANSLATE_TYPE
# define REG_TRANSLATE_TYPE RE_TRANSLATE_TYPE
# else
# define REG_TRANSLATE_TYPE char *
# endif
#endif
/* This data structure represents a compiled pattern. Before calling
the pattern compiler), the fields `re_buffer', `re_allocated', `re_fastmap',
`re_translate', and `re_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
{
/* [[[begin 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 `re_buffer' points. */
__re_long_size_t _REG_RE_NAME (allocated);
/* Number of bytes actually used in `re_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 REG_UNALLOCATED, allocate space in the `regs' structure
for `max (REG_NREGS, re_nsub + 1)' groups.
If REG_REALLOCATE, reallocate space if necessary.
If REG_FIXED, use what's there. */
#define REG_UNALLOCATED 0
#define REG_REALLOCATE 1
#define REG_FIXED 2
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 REG_UNALLOCATED in the pattern buffer,
`re_match_2' returns information about at least this many registers
the first time a `regs' structure is passed. */
#ifndef REG_NREGS
# define REG_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->re_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". */
#ifndef __restrict
# if ! (2 < __GNUC__ || (2 == __GNUC__ && 95 <= __GNUC_MINOR__))
# if defined restrict || 199901L <= __STDC_VERSION__
# define __restrict restrict
# else
# define __restrict
# endif
# endif
#endif
/* gcc 3.1 and up support the [restrict] syntax, but g++ doesn't. */
#ifndef __restrict_arr
# if (__GNUC__ > 3 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 1)) && !defined __cplusplus
# 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 _REGEX_SOURCE
/* Define the POSIX-compatible member names in terms of the
incompatible (and deprecated) names established by _REG_RE_NAME.
New programs should use the re_* names. */
# define re_allocated allocated
# define re_buffer buffer
# define re_can_be_null can_be_null
# define re_fastmap fastmap
# define re_fastmap_accurate fastmap_accurate
# define re_newline_anchor newline_anchor
# define re_no_sub no_sub
# define re_not_bol not_bol
# define re_not_eol not_eol
# define re_regs_allocated regs_allocated
# define re_syntax syntax
# define re_translate translate
# define re_used used
/* Similarly for _REG_RM_NAME. */
# define rm_end end
# define rm_num_regs num_regs
# define rm_start start
/* Undef RE_DUP_MAX first, in case the user has already included a
<limits.h> with an incompatible definition.
On GNU systems, the most common spelling for RE_DUP_MAX's value in
<limits.h> is (0x7ffff), so define RE_DUP_MAX to that, not to
REG_DUP_MAX. This avoid some duplicate-macro-definition warnings
with programs that include <limits.h> after this file.
New programs should not assume that regex.h defines RE_DUP_MAX; to
get the value of RE_DUP_MAX, they should instead include <limits.h>
and possibly invoke the sysconf function. */
# undef RE_DUP_MAX
# define RE_DUP_MAX (0x7fff)
/* Define the following symbols for backward source compatibility.
These symbols violate the POSIX name space rules, and new programs
should avoid them. */
# define REGS_FIXED REG_FIXED
# define REGS_REALLOCATE REG_REALLOCATE
# define REGS_UNALLOCATED REG_UNALLOCATED
# define RE_BACKSLASH_ESCAPE_IN_LISTS REG_BACKSLASH_ESCAPE_IN_LISTS
# define RE_BK_PLUS_QM REG_BK_PLUS_QM
# define RE_CARET_ANCHORS_HERE REG_CARET_ANCHORS_HERE
# define RE_CHAR_CLASSES REG_CHAR_CLASSES
# define RE_CONTEXT_INDEP_ANCHORS REG_CONTEXT_INDEP_ANCHORS
# define RE_CONTEXT_INDEP_OPS REG_CONTEXT_INDEP_OPS
# define RE_CONTEXT_INVALID_DUP REG_CONTEXT_INVALID_DUP
# define RE_CONTEXT_INVALID_OPS REG_CONTEXT_INVALID_OPS
# define RE_DEBUG REG_DEBUG
# define RE_DOT_NEWLINE REG_DOT_NEWLINE
# define RE_DOT_NOT_NULL REG_DOT_NOT_NULL
# define RE_HAT_LISTS_NOT_NEWLINE REG_HAT_LISTS_NOT_NEWLINE
# define RE_ICASE REG_IGNORE_CASE /* avoid collision with REG_ICASE */
# define RE_INTERVALS REG_INTERVALS
# define RE_INVALID_INTERVAL_ORD REG_INVALID_INTERVAL_ORD
# define RE_LIMITED_OPS REG_LIMITED_OPS
# define RE_NEWLINE_ALT REG_NEWLINE_ALT
# define RE_NO_BK_BRACES REG_NO_BK_BRACES
# define RE_NO_BK_PARENS REG_NO_BK_PARENS
# define RE_NO_BK_REFS REG_NO_BK_REFS
# define RE_NO_BK_VBAR REG_NO_BK_VBAR
# define RE_NO_EMPTY_RANGES REG_NO_EMPTY_RANGES
# define RE_NO_GNU_OPS REG_NO_GNU_OPS
# define RE_NO_POSIX_BACKTRACKING REG_NO_POSIX_BACKTRACKING
# define RE_NO_SUB REG_NO_SUB
# define RE_NREGS REG_NREGS
# define RE_SYNTAX_AWK REG_SYNTAX_AWK
# define RE_SYNTAX_ED REG_SYNTAX_ED
# define RE_SYNTAX_EGREP REG_SYNTAX_EGREP
# define RE_SYNTAX_EMACS REG_SYNTAX_EMACS
# define RE_SYNTAX_GNU_AWK REG_SYNTAX_GNU_AWK
# define RE_SYNTAX_GREP REG_SYNTAX_GREP
# define RE_SYNTAX_POSIX_AWK REG_SYNTAX_POSIX_AWK
# define RE_SYNTAX_POSIX_BASIC REG_SYNTAX_POSIX_BASIC
# define RE_SYNTAX_POSIX_EGREP REG_SYNTAX_POSIX_EGREP
# define RE_SYNTAX_POSIX_EXTENDED REG_SYNTAX_POSIX_EXTENDED
# define RE_SYNTAX_POSIX_MINIMAL_BASIC REG_SYNTAX_POSIX_MINIMAL_BASIC
# define RE_SYNTAX_POSIX_MINIMAL_EXTENDED REG_SYNTAX_POSIX_MINIMAL_EXTENDED
# define RE_SYNTAX_SED REG_SYNTAX_SED
# define RE_UNMATCHED_RIGHT_PAREN_ORD REG_UNMATCHED_RIGHT_PAREN_ORD
# ifndef RE_TRANSLATE_TYPE
# define RE_TRANSLATE_TYPE REG_TRANSLATE_TYPE
# endif
#endif /* defined _REGEX_SOURCE */
#ifdef __cplusplus
}
#endif /* C++ */
#endif /* regex.h */
/*
Local variables:
make-backup-files: t
version-control: t
trim-versions-without-asking: nil
End:
*/
--- NEW FILE: regcomp.c ---
/* Extended regular expression matching and search library.
Copyright (C) 2002, 2003, 2004, 2005 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Isamu Hasegawa <isamu at yamato.ibm.com>.
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. */
[...3740 lines suppressed...]
{
node = node->left;
p_new = &dup_node->left;
}
else
{
const bin_tree_t *prev = NULL;
while (node->right == prev || node->right == NULL)
{
prev = node;
node = node->parent;
dup_node = dup_node->parent;
if (!node)
return dup_root;
}
node = node->right;
p_new = &dup_node->right;
}
}
}
--- NEW FILE: regex_internal.h ---
/* Extended regular expression matching and search library.
Copyright (C) 2002, 2003, 2004, 2005 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Isamu Hasegawa <isamu at yamato.ibm.com>.
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_INTERNAL_H
#define _REGEX_INTERNAL_H 1
#include <assert.h>
#include <ctype.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#ifndef _LIBC
# include "strcase.h"
#endif
#if defined HAVE_LANGINFO_H || defined HAVE_LANGINFO_CODESET || defined _LIBC
# include <langinfo.h>
#endif
#if defined HAVE_LOCALE_H || defined _LIBC
# include <locale.h>
#endif
#if defined HAVE_WCHAR_H || defined _LIBC
# include <wchar.h>
#endif /* HAVE_WCHAR_H || _LIBC */
#if defined HAVE_WCTYPE_H || defined _LIBC
# include <wctype.h>
#endif /* HAVE_WCTYPE_H || _LIBC */
#if defined _LIBC
# include <bits/libc-lock.h>
#else
# define __libc_lock_define(CLASS,NAME)
# define __libc_lock_init(NAME) do { } while (0)
# define __libc_lock_lock(NAME) do { } while (0)
# define __libc_lock_unlock(NAME) do { } while (0)
#endif
/* In case that the system doesn't have isblank(). */
#if !defined _LIBC && !defined HAVE_ISBLANK && !defined isblank
# define isblank(ch) ((ch) == ' ' || (ch) == '\t')
#endif
#ifdef _LIBC
# ifndef _RE_DEFINE_LOCALE_FUNCTIONS
# define _RE_DEFINE_LOCALE_FUNCTIONS 1
# include <locale/localeinfo.h>
# include <locale/elem-hash.h>
# include <locale/coll-lookup.h>
# endif
#endif
/* This is for other GNU distributions with internationalized messages. */
#if (HAVE_LIBINTL_H && ENABLE_NLS) || defined _LIBC
# include <libintl.h>
# ifdef _LIBC
# undef gettext
# define gettext(msgid) \
INTUSE(__dcgettext) (_libc_intl_domainname, msgid, LC_MESSAGES)
# endif
#else
# define gettext(msgid) (msgid)
#endif
#ifndef gettext_noop
/* This define is so xgettext can find the internationalizable
strings. */
# define gettext_noop(String) String
#endif
#if (defined MB_CUR_MAX && HAVE_LOCALE_H && HAVE_WCTYPE_H && HAVE_WCHAR_H && HAVE_WCRTOMB && HAVE_MBRTOWC && HAVE_WCSCOLL) || _LIBC
# define RE_ENABLE_I18N
#endif
#if __GNUC__ >= 3
# define BE(expr, val) __builtin_expect (expr, val)
#else
# define BE(expr, val) (expr)
#endif
/* Number of single byte character. */
#define SBC_MAX 256
#define COLL_ELEM_LEN_MAX 8
/* The character which represents newline. */
#define NEWLINE_CHAR '\n'
#define WIDE_NEWLINE_CHAR L'\n'
/* Rename to standard API for using out of glibc. */
#ifndef _LIBC
# define __wctype wctype
# define __iswctype iswctype
# define __btowc btowc
# ifndef __mempcpy
# define __mempcpy mempcpy
# endif
# define __wcrtomb wcrtomb
# define __regfree regfree
# define attribute_hidden
#endif /* not _LIBC */
#if __GNUC__ >= 4 || (__GNUC__ == 3 && __GNUC_MINOR__ >= 1)
# define __attribute(arg) __attribute__ (arg)
#else
# define __attribute(arg)
#endif
extern const char __re_error_msgid[] attribute_hidden;
extern const size_t __re_error_msgid_idx[] attribute_hidden;
typedef __re_idx_t Idx;
/* Special return value for failure to match. */
#define REG_MISSING ((Idx) -1)
/* Special return value for internal error. */
#define REG_ERROR ((Idx) -2)
/* Test whether N is a valid index, and is not one of the above. */
#ifdef _REGEX_LARGE_OFFSETS
# define REG_VALID_INDEX(n) ((Idx) (n) < REG_ERROR)
#else
# define REG_VALID_INDEX(n) (0 <= (n))
#endif
/* Test whether N is a valid nonzero index. */
#ifdef _REGEX_LARGE_OFFSETS
# define REG_VALID_NONZERO_INDEX(n) ((Idx) ((n) - 1) < (Idx) (REG_ERROR - 1))
#else
# define REG_VALID_NONZERO_INDEX(n) (0 < (n))
#endif
/* A hash value, suitable for computing hash tables. */
typedef __re_size_t re_hashval_t;
/* An integer used to represent a set of bits. It must be unsigned,
and must be at least as wide as unsigned int. */
typedef unsigned long int bitset_word;
/* Maximum value of a bitset word. It must be useful in preprocessor
contexts, and must be consistent with bitset_word. */
#define BITSET_WORD_MAX ULONG_MAX
/* Number of bits in a bitset word. Avoid greater-than-32-bit
integers and unconditional shifts by more than 31 bits, as they're
not portable. */
#if BITSET_WORD_MAX == 0xffffffff
# define BITSET_WORD_BITS 32
#elif BITSET_WORD_MAX >> 31 >> 5 == 1
# define BITSET_WORD_BITS 36
#elif BITSET_WORD_MAX >> 31 >> 16 == 1
# define BITSET_WORD_BITS 48
#elif BITSET_WORD_MAX >> 31 >> 28 == 1
# define BITSET_WORD_BITS 60
#elif BITSET_WORD_MAX >> 31 >> 31 >> 1 == 1
# define BITSET_WORD_BITS 64
#elif BITSET_WORD_MAX >> 31 >> 31 >> 9 == 1
# define BITSET_WORD_BITS 72
#elif BITSET_WORD_MAX >> 31 >> 31 >> 31 >> 31 >> 3 == 1
# define BITSET_WORD_BITS 128
#elif BITSET_WORD_MAX >> 31 >> 31 >> 31 >> 31 >> 31 >> 31 >> 31 >> 31 >> 7 == 1
# define BITSET_WORD_BITS 256
#elif BITSET_WORD_MAX >> 31 >> 31 >> 31 >> 31 >> 31 >> 31 >> 31 >> 31 >> 7 > 1
# define BITSET_WORD_BITS 257 /* any value > SBC_MAX will do here */
# if BITSET_WORD_BITS <= SBC_MAX
# error "Invalid SBC_MAX"
# endif
#else
# error "Add case for new bitset_word size"
#endif
/* Number of bitset words in a bitset. */
#define BITSET_WORDS ((SBC_MAX + BITSET_WORD_BITS - 1) / BITSET_WORD_BITS)
typedef bitset_word bitset[BITSET_WORDS];
typedef bitset_word *re_bitset_ptr_t;
typedef const bitset_word *re_const_bitset_ptr_t;
#define PREV_WORD_CONSTRAINT 0x0001
#define PREV_NOTWORD_CONSTRAINT 0x0002
#define NEXT_WORD_CONSTRAINT 0x0004
#define NEXT_NOTWORD_CONSTRAINT 0x0008
#define PREV_NEWLINE_CONSTRAINT 0x0010
#define NEXT_NEWLINE_CONSTRAINT 0x0020
#define PREV_BEGBUF_CONSTRAINT 0x0040
#define NEXT_ENDBUF_CONSTRAINT 0x0080
#define WORD_DELIM_CONSTRAINT 0x0100
#define NOT_WORD_DELIM_CONSTRAINT 0x0200
typedef enum
{
INSIDE_WORD = PREV_WORD_CONSTRAINT | NEXT_WORD_CONSTRAINT,
WORD_FIRST = PREV_NOTWORD_CONSTRAINT | NEXT_WORD_CONSTRAINT,
WORD_LAST = PREV_WORD_CONSTRAINT | NEXT_NOTWORD_CONSTRAINT,
INSIDE_NOTWORD = PREV_NOTWORD_CONSTRAINT | NEXT_NOTWORD_CONSTRAINT,
LINE_FIRST = PREV_NEWLINE_CONSTRAINT,
LINE_LAST = NEXT_NEWLINE_CONSTRAINT,
BUF_FIRST = PREV_BEGBUF_CONSTRAINT,
BUF_LAST = NEXT_ENDBUF_CONSTRAINT,
WORD_DELIM = WORD_DELIM_CONSTRAINT,
NOT_WORD_DELIM = NOT_WORD_DELIM_CONSTRAINT
} re_context_type;
typedef struct
{
Idx alloc;
Idx nelem;
Idx *elems;
} re_node_set;
typedef enum
{
NON_TYPE = 0,
/* Node type, These are used by token, node, tree. */
CHARACTER = 1,
END_OF_RE = 2,
SIMPLE_BRACKET = 3,
OP_BACK_REF = 4,
OP_PERIOD = 5,
#ifdef RE_ENABLE_I18N
COMPLEX_BRACKET = 6,
OP_UTF8_PERIOD = 7,
#endif /* RE_ENABLE_I18N */
/* We define EPSILON_BIT as a macro so that OP_OPEN_SUBEXP is used
when the debugger shows values of this enum type. */
#define EPSILON_BIT 8
OP_OPEN_SUBEXP = EPSILON_BIT | 0,
OP_CLOSE_SUBEXP = EPSILON_BIT | 1,
OP_ALT = EPSILON_BIT | 2,
OP_DUP_ASTERISK = EPSILON_BIT | 3,
ANCHOR = EPSILON_BIT | 4,
/* Tree type, these are used only by tree. */
CONCAT = 16,
SUBEXP = 17,
/* Token type, these are used only by token. */
OP_DUP_PLUS = 18,
OP_DUP_QUESTION,
OP_OPEN_BRACKET,
OP_CLOSE_BRACKET,
OP_CHARSET_RANGE,
OP_OPEN_DUP_NUM,
OP_CLOSE_DUP_NUM,
OP_NON_MATCH_LIST,
OP_OPEN_COLL_ELEM,
OP_CLOSE_COLL_ELEM,
OP_OPEN_EQUIV_CLASS,
OP_CLOSE_EQUIV_CLASS,
OP_OPEN_CHAR_CLASS,
OP_CLOSE_CHAR_CLASS,
OP_WORD,
OP_NOTWORD,
OP_SPACE,
OP_NOTSPACE,
BACK_SLASH
} re_token_type_t;
#ifdef RE_ENABLE_I18N
typedef struct
{
/* Multibyte characters. */
wchar_t *mbchars;
/* Collating symbols. */
# ifdef _LIBC
int32_t *coll_syms;
# endif
/* Equivalence classes. */
# ifdef _LIBC
int32_t *equiv_classes;
# endif
/* Range expressions. */
# ifdef _LIBC
uint32_t *range_starts;
uint32_t *range_ends;
# else /* not _LIBC */
wchar_t *range_starts;
wchar_t *range_ends;
# endif /* not _LIBC */
/* Character classes. */
wctype_t *char_classes;
/* If this character set is the non-matching list. */
unsigned int non_match : 1;
/* # of multibyte characters. */
Idx nmbchars;
/* # of collating symbols. */
Idx ncoll_syms;
/* # of equivalence classes. */
Idx nequiv_classes;
/* # of range expressions. */
Idx nranges;
/* # of character classes. */
Idx nchar_classes;
} re_charset_t;
#endif /* RE_ENABLE_I18N */
typedef struct
{
union
{
unsigned char c; /* for CHARACTER */
re_bitset_ptr_t sbcset; /* for SIMPLE_BRACKET */
#ifdef RE_ENABLE_I18N
re_charset_t *mbcset; /* for COMPLEX_BRACKET */
#endif /* RE_ENABLE_I18N */
Idx idx; /* for BACK_REF */
re_context_type ctx_type; /* for ANCHOR */
} opr;
#if __GNUC__ >= 2
re_token_type_t type : 8;
#else
re_token_type_t type;
#endif
unsigned int constraint : 10; /* context constraint */
unsigned int duplicated : 1;
unsigned int opt_subexp : 1;
#ifdef RE_ENABLE_I18N
unsigned int accept_mb : 1;
/* These 2 bits can be moved into the union if needed (e.g. if running out
of bits; move opr.c to opr.c.c and move the flags to opr.c.flags). */
unsigned int mb_partial : 1;
#endif
unsigned int word_char : 1;
} re_token_t;
#define IS_EPSILON_NODE(type) ((type) & EPSILON_BIT)
struct re_string_t
{
/* Indicate the raw buffer which is the original string passed as an
argument of regexec(), re_search(), etc.. */
const unsigned char *raw_mbs;
/* Store the multibyte string. In case of "case insensitive mode" like
REG_ICASE, upper cases of the string are stored, otherwise MBS points
the same address that RAW_MBS points. */
unsigned char *mbs;
#ifdef RE_ENABLE_I18N
/* Store the wide character string which is corresponding to MBS. */
wint_t *wcs;
Idx *offsets;
mbstate_t cur_state;
#endif
/* Index in RAW_MBS. Each character mbs[i] corresponds to
raw_mbs[raw_mbs_idx + i]. */
Idx raw_mbs_idx;
/* The length of the valid characters in the buffers. */
Idx valid_len;
/* The corresponding number of bytes in raw_mbs array. */
Idx valid_raw_len;
/* The length of the buffers MBS and WCS. */
Idx bufs_len;
/* The index in MBS, which is updated by re_string_fetch_byte. */
Idx cur_idx;
/* length of RAW_MBS array. */
Idx raw_len;
/* This is RAW_LEN - RAW_MBS_IDX + VALID_LEN - VALID_RAW_LEN. */
Idx len;
/* End of the buffer may be shorter than its length in the cases such
as re_match_2, re_search_2. Then, we use STOP for end of the buffer
instead of LEN. */
Idx raw_stop;
/* This is RAW_STOP - RAW_MBS_IDX adjusted through OFFSETS. */
Idx stop;
/* The context of mbs[0]. We store the context independently, since
the context of mbs[0] may be different from raw_mbs[0], which is
the beginning of the input string. */
unsigned int tip_context;
/* The translation passed as a part of an argument of re_compile_pattern. */
unsigned REG_TRANSLATE_TYPE trans;
/* Copy of re_dfa_t's word_char. */
re_const_bitset_ptr_t word_char;
/* true if REG_ICASE. */
unsigned char icase;
unsigned char is_utf8;
unsigned char map_notascii;
unsigned char mbs_allocated;
unsigned char offsets_needed;
unsigned char newline_anchor;
unsigned char word_ops_used;
int mb_cur_max;
};
typedef struct re_string_t re_string_t;
struct re_dfa_t;
typedef struct re_dfa_t re_dfa_t;
#ifndef _LIBC
# ifdef __i386__
# define internal_function __attribute ((regparm (3), stdcall))
# else
# define internal_function
# endif
#endif
static reg_errcode_t re_string_realloc_buffers (re_string_t *pstr,
Idx new_buf_len)
internal_function;
#ifdef RE_ENABLE_I18N
static void build_wcs_buffer (re_string_t *pstr) internal_function;
static reg_errcode_t build_wcs_upper_buffer (re_string_t *pstr)
internal_function;
#endif /* RE_ENABLE_I18N */
static void build_upper_buffer (re_string_t *pstr) internal_function;
static void re_string_translate_buffer (re_string_t *pstr) internal_function;
static unsigned int re_string_context_at (const re_string_t *input,
Idx idx, int eflags)
internal_function __attribute ((pure));
#define re_string_peek_byte(pstr, offset) \
((pstr)->mbs[(pstr)->cur_idx + offset])
#define re_string_fetch_byte(pstr) \
((pstr)->mbs[(pstr)->cur_idx++])
#define re_string_first_byte(pstr, idx) \
((idx) == (pstr)->valid_len || (pstr)->wcs[idx] != WEOF)
#define re_string_is_single_byte_char(pstr, idx) \
((pstr)->wcs[idx] != WEOF && ((pstr)->valid_len == (idx) + 1 \
|| (pstr)->wcs[(idx) + 1] != WEOF))
#define re_string_eoi(pstr) ((pstr)->stop <= (pstr)->cur_idx)
#define re_string_cur_idx(pstr) ((pstr)->cur_idx)
#define re_string_get_buffer(pstr) ((pstr)->mbs)
#define re_string_length(pstr) ((pstr)->len)
#define re_string_byte_at(pstr,idx) ((pstr)->mbs[idx])
#define re_string_skip_bytes(pstr,idx) ((pstr)->cur_idx += (idx))
#define re_string_set_index(pstr,idx) ((pstr)->cur_idx = (idx))
#include <alloca.h>
#ifndef _LIBC
# if HAVE_ALLOCA
/* The OS usually guarantees only one guard page at the bottom of the stack,
and a page size can be as small as 4096 bytes. So we cannot safely
allocate anything larger than 4096 bytes. Also care for the possibility
of a few compiler-allocated temporary stack slots. */
# define __libc_use_alloca(n) ((n) < 4032)
# else
/* alloca is implemented with malloc, so just use malloc. */
# define __libc_use_alloca(n) 0
# endif
#endif
#define re_malloc(t,n) ((t *) malloc ((n) * sizeof (t)))
#define re_xmalloc(t,n) ((t *) re_xnmalloc (n, sizeof (t)))
#define re_calloc(t,n) ((t *) calloc (n, sizeof (t)))
#define re_realloc(p,t,n) ((t *) realloc (p, (n) * sizeof (t)))
#define re_xrealloc(p,t,n) ((t *) re_xnrealloc (p, n, sizeof (t)))
#define re_x2realloc(p,t,pn) ((t *) re_x2nrealloc (p, pn, sizeof (t)))
#define re_free(p) free (p)
#ifndef SIZE_MAX
# define SIZE_MAX ((size_t) -1)
#endif
/* Return true if an array of N objects, each of size S, cannot exist
due to size arithmetic overflow. S must be nonzero. */
static inline bool
re_alloc_oversized (size_t n, size_t s)
{
return BE (SIZE_MAX / s < n, 0);
}
/* Return true if an array of (2 * N + 1) objects, each of size S,
cannot exist due to size arithmetic overflow. S must be nonzero. */
static inline bool
re_x2alloc_oversized (size_t n, size_t s)
{
return BE ((SIZE_MAX / s - 1) / 2 < n, 0);
}
/* Allocate an array of N objects, each with S bytes of memory,
dynamically, with error checking. S must be nonzero. */
static inline void *
re_xnmalloc (size_t n, size_t s)
{
return re_alloc_oversized (n, s) ? NULL : malloc (n * s);
}
/* Change the size of an allocated block of memory P to an array of N
objects each of S bytes, with error checking. S must be nonzero. */
static inline void *
re_xnrealloc (void *p, size_t n, size_t s)
{
return re_alloc_oversized (n, s) ? NULL : realloc (p, n * s);
}
/* Reallocate a block of memory P to an array of (2 * (*PN) + 1)
objects each of S bytes, with error checking. S must be nonzero.
If the allocation is successful, set *PN to the new allocation
count and return the resulting pointer. Otherwise, return
NULL. */
static inline void *
re_x2nrealloc (void *p, size_t *pn, size_t s)
{
if (re_x2alloc_oversized (*pn, s))
return NULL;
else
{
/* Add 1 in case *PN is zero. */
size_t n1 = 2 * *pn + 1;
p = realloc (p, n1 * s);
if (BE (p != NULL, 1))
*pn = n1;
return p;
}
}
struct bin_tree_t
{
struct bin_tree_t *parent;
struct bin_tree_t *left;
struct bin_tree_t *right;
struct bin_tree_t *first;
struct bin_tree_t *next;
re_token_t token;
/* `node_idx' is the index in dfa->nodes, if `type' == 0.
Otherwise `type' indicate the type of this node. */
Idx node_idx;
};
typedef struct bin_tree_t bin_tree_t;
#define BIN_TREE_STORAGE_SIZE \
((1024 - sizeof (void *)) / sizeof (bin_tree_t))
struct bin_tree_storage_t
{
struct bin_tree_storage_t *next;
bin_tree_t data[BIN_TREE_STORAGE_SIZE];
};
typedef struct bin_tree_storage_t bin_tree_storage_t;
#define CONTEXT_WORD 1
#define CONTEXT_NEWLINE (CONTEXT_WORD << 1)
#define CONTEXT_BEGBUF (CONTEXT_NEWLINE << 1)
#define CONTEXT_ENDBUF (CONTEXT_BEGBUF << 1)
#define IS_WORD_CONTEXT(c) ((c) & CONTEXT_WORD)
#define IS_NEWLINE_CONTEXT(c) ((c) & CONTEXT_NEWLINE)
#define IS_BEGBUF_CONTEXT(c) ((c) & CONTEXT_BEGBUF)
#define IS_ENDBUF_CONTEXT(c) ((c) & CONTEXT_ENDBUF)
#define IS_ORDINARY_CONTEXT(c) ((c) == 0)
#define IS_WORD_CHAR(ch) (isalnum (ch) || (ch) == '_')
#define IS_NEWLINE(ch) ((ch) == NEWLINE_CHAR)
#define IS_WIDE_WORD_CHAR(ch) (iswalnum (ch) || (ch) == L'_')
#define IS_WIDE_NEWLINE(ch) ((ch) == WIDE_NEWLINE_CHAR)
#define NOT_SATISFY_PREV_CONSTRAINT(constraint,context) \
((((constraint) & PREV_WORD_CONSTRAINT) && !IS_WORD_CONTEXT (context)) \
|| ((constraint & PREV_NOTWORD_CONSTRAINT) && IS_WORD_CONTEXT (context)) \
|| ((constraint & PREV_NEWLINE_CONSTRAINT) && !IS_NEWLINE_CONTEXT (context))\
|| ((constraint & PREV_BEGBUF_CONSTRAINT) && !IS_BEGBUF_CONTEXT (context)))
#define NOT_SATISFY_NEXT_CONSTRAINT(constraint,context) \
((((constraint) & NEXT_WORD_CONSTRAINT) && !IS_WORD_CONTEXT (context)) \
|| (((constraint) & NEXT_NOTWORD_CONSTRAINT) && IS_WORD_CONTEXT (context)) \
|| (((constraint) & NEXT_NEWLINE_CONSTRAINT) && !IS_NEWLINE_CONTEXT (context)) \
|| (((constraint) & NEXT_ENDBUF_CONSTRAINT) && !IS_ENDBUF_CONTEXT (context)))
struct re_dfastate_t
{
re_hashval_t hash;
re_node_set nodes;
re_node_set non_eps_nodes;
re_node_set inveclosure;
re_node_set *entrance_nodes;
struct re_dfastate_t **trtable, **word_trtable;
unsigned int context : 4;
unsigned int halt : 1;
/* If this state can accept `multi byte'.
Note that we refer to multibyte characters, and multi character
collating elements as `multi byte'. */
unsigned int accept_mb : 1;
/* If this state has backreference node(s). */
unsigned int has_backref : 1;
unsigned int has_constraint : 1;
};
typedef struct re_dfastate_t re_dfastate_t;
struct re_state_table_entry
{
Idx num;
Idx alloc;
re_dfastate_t **array;
};
/* Array type used in re_sub_match_last_t and re_sub_match_top_t. */
typedef struct
{
Idx next_idx;
Idx alloc;
re_dfastate_t **array;
} state_array_t;
/* Store information about the node NODE whose type is OP_CLOSE_SUBEXP. */
typedef struct
{
Idx node;
Idx str_idx; /* The position NODE match at. */
state_array_t path;
} re_sub_match_last_t;
/* Store information about the node NODE whose type is OP_OPEN_SUBEXP.
And information about the node, whose type is OP_CLOSE_SUBEXP,
corresponding to NODE is stored in LASTS. */
typedef struct
{
Idx str_idx;
Idx node;
state_array_t *path;
Idx alasts; /* Allocation size of LASTS. */
Idx nlasts; /* The number of LASTS. */
re_sub_match_last_t **lasts;
} re_sub_match_top_t;
struct re_backref_cache_entry
{
Idx node;
Idx str_idx;
Idx subexp_from;
Idx subexp_to;
char more;
char unused;
unsigned short int eps_reachable_subexps_map;
};
typedef struct
{
/* The string object corresponding to the input string. */
re_string_t input;
#if defined _LIBC || (defined __STDC_VERSION__ && __STDC_VERSION__ >= 199901L)
re_dfa_t *const dfa;
#else
re_dfa_t *dfa;
#endif
/* EFLAGS of the argument of regexec. */
int eflags;
/* Where the matching ends. */
Idx match_last;
Idx last_node;
/* The state log used by the matcher. */
re_dfastate_t **state_log;
Idx state_log_top;
/* Back reference cache. */
Idx nbkref_ents;
Idx abkref_ents;
struct re_backref_cache_entry *bkref_ents;
int max_mb_elem_len;
Idx nsub_tops;
Idx asub_tops;
re_sub_match_top_t **sub_tops;
} re_match_context_t;
typedef struct
{
re_dfastate_t **sifted_states;
re_dfastate_t **limited_states;
Idx last_node;
Idx last_str_idx;
re_node_set limits;
} re_sift_context_t;
struct re_fail_stack_ent_t
{
Idx idx;
Idx node;
regmatch_t *regs;
re_node_set eps_via_nodes;
};
struct re_fail_stack_t
{
Idx num;
Idx alloc;
struct re_fail_stack_ent_t *stack;
};
struct re_dfa_t
{
re_token_t *nodes;
Idx nodes_alloc;
Idx nodes_len;
Idx *nexts;
Idx *org_indices;
re_node_set *edests;
re_node_set *eclosures;
re_node_set *inveclosures;
struct re_state_table_entry *state_table;
re_dfastate_t *init_state;
re_dfastate_t *init_state_word;
re_dfastate_t *init_state_nl;
re_dfastate_t *init_state_begbuf;
bin_tree_t *str_tree;
bin_tree_storage_t *str_tree_storage;
re_bitset_ptr_t sb_char;
int str_tree_storage_idx;
/* number of subexpressions `re_nsub' is in regex_t. */
re_hashval_t state_hash_mask;
Idx init_node;
Idx nbackref; /* The number of backreference in this dfa. */
/* Bitmap expressing which backreference is used. */
bitset_word used_bkref_map;
bitset_word completed_bkref_map;
unsigned int has_plural_match : 1;
/* If this dfa has "multibyte node", which is a backreference or
a node which can accept multibyte character or multi character
collating element. */
unsigned int has_mb_node : 1;
unsigned int is_utf8 : 1;
unsigned int map_notascii : 1;
unsigned int word_ops_used : 1;
int mb_cur_max;
bitset word_char;
reg_syntax_t syntax;
Idx *subexp_map;
#ifdef DEBUG
char* re_str;
#endif
__libc_lock_define (, lock)
};
#define re_node_set_init_empty(set) memset (set, '\0', sizeof (re_node_set))
#define re_node_set_remove(set,id) \
(re_node_set_remove_at (set, re_node_set_contains (set, id) - 1))
#define re_node_set_empty(p) ((p)->nelem = 0)
#define re_node_set_free(set) re_free ((set)->elems)
static void free_state (re_dfastate_t *state) internal_function;
typedef enum
{
SB_CHAR,
MB_CHAR,
EQUIV_CLASS,
COLL_SYM,
CHAR_CLASS
} bracket_elem_type;
typedef struct
{
bracket_elem_type type;
union
{
unsigned char ch;
unsigned char *name;
wchar_t wch;
} opr;
} bracket_elem_t;
/* Inline functions for bitset operation. */
static inline void
bitset_set (bitset set, Idx i)
{
set[i / BITSET_WORD_BITS] |= (bitset_word) 1 << i % BITSET_WORD_BITS;
}
static inline void
bitset_clear (bitset set, Idx i)
{
set[i / BITSET_WORD_BITS] &= ~ ((bitset_word) 1 << i % BITSET_WORD_BITS);
}
static inline bool
bitset_contain (const bitset set, Idx i)
{
return (set[i / BITSET_WORD_BITS] >> i % BITSET_WORD_BITS) & 1;
}
static inline void
bitset_empty (bitset set)
{
memset (set, 0, sizeof (bitset));
}
static inline void
bitset_set_all (bitset set)
{
memset (set, -1, sizeof (bitset_word) * (SBC_MAX / BITSET_WORD_BITS));
if (SBC_MAX % BITSET_WORD_BITS != 0)
set[BITSET_WORDS - 1] =
((bitset_word) 1 << SBC_MAX % BITSET_WORD_BITS) - 1;
}
static inline void
bitset_copy (bitset dest, const bitset src)
{
memcpy (dest, src, sizeof (bitset));
}
static inline void
bitset_not (bitset set)
{
int i;
for (i = 0; i < SBC_MAX / BITSET_WORD_BITS; ++i)
set[i] = ~set[i];
if (SBC_MAX % BITSET_WORD_BITS != 0)
set[BITSET_WORDS - 1] =
((((bitset_word) 1 << SBC_MAX % BITSET_WORD_BITS) - 1)
& ~set[BITSET_WORDS - 1]);
}
static inline void
bitset_merge (bitset dest, const bitset src)
{
int i;
for (i = 0; i < BITSET_WORDS; ++i)
dest[i] |= src[i];
}
static inline void
bitset_mask (bitset dest, const bitset src)
{
int i;
for (i = 0; i < BITSET_WORDS; ++i)
dest[i] &= src[i];
}
#if defined RE_ENABLE_I18N
/* Inline functions for re_string. */
static inline int
internal_function __attribute ((pure))
re_string_char_size_at (const re_string_t *pstr, Idx idx)
{
int byte_idx;
if (pstr->mb_cur_max == 1)
return 1;
for (byte_idx = 1; idx + byte_idx < pstr->valid_len; ++byte_idx)
if (pstr->wcs[idx + byte_idx] != WEOF)
break;
return byte_idx;
}
static inline wint_t
internal_function __attribute ((pure))
re_string_wchar_at (const re_string_t *pstr, Idx idx)
{
if (pstr->mb_cur_max == 1)
return (wint_t) pstr->mbs[idx];
return (wint_t) pstr->wcs[idx];
}
static int
internal_function __attribute ((pure))
re_string_elem_size_at (const re_string_t *pstr, Idx idx)
{
#ifdef _LIBC
const unsigned char *p, *extra;
const int32_t *table, *indirect;
int32_t tmp;
# include <locale/weight.h>
uint_fast32_t nrules = _NL_CURRENT_WORD (LC_COLLATE, _NL_COLLATE_NRULES);
if (nrules != 0)
{
table = (const int32_t *) _NL_CURRENT (LC_COLLATE, _NL_COLLATE_TABLEMB);
extra = (const unsigned char *)
_NL_CURRENT (LC_COLLATE, _NL_COLLATE_EXTRAMB);
indirect = (const int32_t *) _NL_CURRENT (LC_COLLATE,
_NL_COLLATE_INDIRECTMB);
p = pstr->mbs + idx;
tmp = findidx (&p);
return p - pstr->mbs - idx;
}
else
#endif /* _LIBC */
return 1;
}
#endif /* RE_ENABLE_I18N */
#endif /* _REGEX_INTERNAL_H */
--- NEW FILE: regex_internal.c ---
/* Extended regular expression matching and search library.
Copyright (C) 2002, 2003, 2004, 2005 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Isamu Hasegawa <isamu at yamato.ibm.com>.
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. */
[...1617 lines suppressed...]
}
return newstate;
}
static void
internal_function
free_state (re_dfastate_t *state)
{
re_node_set_free (&state->non_eps_nodes);
re_node_set_free (&state->inveclosure);
if (state->entrance_nodes != &state->nodes)
{
re_node_set_free (state->entrance_nodes);
re_free (state->entrance_nodes);
}
re_node_set_free (&state->nodes);
re_free (state->word_trtable);
re_free (state->trtable);
re_free (state);
}
- Previous message: [Nagiosplug-checkins] nagiosplug/m4 ls-mntd-fs.m4,1.2,1.3
- Next message: [Nagiosplug-checkins] nagiosplug/plugins check_apt.c,1.5,1.6 check_snmp.c,1.59,1.60 check_smtp.c,1.50,1.51 check_http.c,1.89,1.90
- Messages sorted by:
[ date ]
[ thread ]
[ subject ]
[ author ]
More information about the Commits
mailing list