mirror of
https://git.savannah.gnu.org/git/coreutils.git
synced 2026-11-17 18:02:09 +03:00
Switch to Isamu Hasegawa's implementation of regex, which is
now in gnulib.
This commit is contained in:
1 parent
36a263effc
commit
ce3bb28d95
9 files changed
+10949
-8347
No files matched your search
@@ -1,3 +1,14 @@
|
||||
2005-07-07 Paul Eggert <eggert@cs.ucla.edu>
|
||||
|
||||
Switch to Isamu Hasegawa's implementation of regex, which is
|
||||
now in gnulib.
|
||||
* regcomp.c, regex_internal.c, regex_internal.h, regexec.c:
|
||||
New files, from gnulib.
|
||||
* regex.h, regex.c: Sync from gnulib.
|
||||
* Makefile.am (libcoreutils_a_SOURCES): Remove regex.h; gnulib
|
||||
now does this automatically for us.
|
||||
* .cppi-disable: Add regcomp.c, regex_internal.c, regex_internal.h.
|
||||
|
||||
2005-07-04 Paul Eggert <eggert@cs.ucla.edu>
|
||||
|
||||
* verify.h (GL_CONCAT0, GL_CONCAT): Define unconditionally; don't
|
||||
|
||||
+3925
File diff suppressed because it is too large.
Load diff
+67
-8274
File diff suppressed because it is too large.
Load diff
+71
-35
@@ -16,7 +16,7 @@
|
||||
|
||||
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. */
|
||||
Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */
|
||||
|
||||
#ifndef _REGEX_H
|
||||
#define _REGEX_H 1
|
||||
@@ -169,6 +169,19 @@ typedef unsigned long int reg_syntax_t;
|
||||
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)
|
||||
|
||||
/* 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
|
||||
@@ -193,7 +206,7 @@ extern reg_syntax_t re_syntax_options;
|
||||
& ~(RE_DOT_NOT_NULL | RE_INTERVALS | RE_CONTEXT_INDEP_OPS \
|
||||
| RE_CONTEXT_INVALID_OPS ))
|
||||
|
||||
#define RE_SYNTAX_POSIX_AWK \
|
||||
#define RE_SYNTAX_POSIX_AWK \
|
||||
(RE_SYNTAX_POSIX_EXTENDED | RE_BACKSLASH_ESCAPE_IN_LISTS \
|
||||
| RE_INTERVALS | RE_NO_GNU_OPS)
|
||||
|
||||
@@ -223,7 +236,7 @@ extern reg_syntax_t re_syntax_options;
|
||||
| RE_INTERVALS | RE_NO_EMPTY_RANGES)
|
||||
|
||||
#define RE_SYNTAX_POSIX_BASIC \
|
||||
(_RE_SYNTAX_POSIX_COMMON | RE_BK_PLUS_QM)
|
||||
(_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
|
||||
@@ -288,6 +301,10 @@ extern reg_syntax_t re_syntax_options;
|
||||
/* 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_msg' table in regex.c. */
|
||||
@@ -303,7 +320,7 @@ typedef enum
|
||||
/* POSIX regcomp return error codes. (In the order listed in the
|
||||
standard.) */
|
||||
REG_BADPAT, /* Invalid pattern. */
|
||||
REG_ECOLLATE, /* Not implemented. */
|
||||
REG_ECOLLATE, /* Inalid collating element. */
|
||||
REG_ECTYPE, /* Invalid character class name. */
|
||||
REG_EESCAPE, /* Trailing backslash. */
|
||||
REG_ESUBREG, /* Invalid back reference. */
|
||||
@@ -434,21 +451,38 @@ typedef struct
|
||||
|
||||
/* Declarations for routines. */
|
||||
|
||||
/* To avoid duplicating every routine declaration -- once with a
|
||||
prototype (if we are ANSI), and once without (if we aren't) -- we
|
||||
use the following macro to declare argument types. This
|
||||
unfortunately clutters up the declarations a bit, but I think it's
|
||||
worth it. */
|
||||
|
||||
#if __STDC__
|
||||
|
||||
# define _RE_ARGS(args) args
|
||||
|
||||
#else /* not __STDC__ */
|
||||
|
||||
# define _RE_ARGS(args) ()
|
||||
|
||||
#endif /* not __STDC__ */
|
||||
|
||||
/* 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);
|
||||
extern reg_syntax_t re_set_syntax _RE_ARGS ((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);
|
||||
extern const char *re_compile_pattern
|
||||
_RE_ARGS ((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);
|
||||
extern int re_compile_fastmap _RE_ARGS ((struct re_pattern_buffer *buffer));
|
||||
|
||||
|
||||
/* Search in the string STRING (with length LENGTH) for the pattern
|
||||
@@ -456,29 +490,31 @@ extern int re_compile_fastmap (struct re_pattern_buffer *buffer);
|
||||
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 int re_search (struct re_pattern_buffer *buffer, const char *string,
|
||||
int length, int start, int range,
|
||||
struct re_registers *regs);
|
||||
extern int re_search
|
||||
_RE_ARGS ((struct re_pattern_buffer *buffer, const char *string,
|
||||
int length, int start, int 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 int re_search_2 (struct re_pattern_buffer *buffer, const char *string1,
|
||||
int length1, const char *string2, int length2,
|
||||
int start, int range, struct re_registers *regs,
|
||||
int stop);
|
||||
extern int re_search_2
|
||||
_RE_ARGS ((struct re_pattern_buffer *buffer, const char *string1,
|
||||
int length1, const char *string2, int length2,
|
||||
int start, int range, struct re_registers *regs, int stop));
|
||||
|
||||
|
||||
/* Like `re_search', but return how many characters in STRING the regexp
|
||||
in BUFFER matched, starting at position START. */
|
||||
extern int re_match (struct re_pattern_buffer *buffer, const char *string,
|
||||
int length, int start, struct re_registers *regs);
|
||||
extern int re_match
|
||||
_RE_ARGS ((struct re_pattern_buffer *buffer, const char *string,
|
||||
int length, int start, struct re_registers *regs));
|
||||
|
||||
|
||||
/* Relates to `re_match' as `re_search_2' relates to `re_search'. */
|
||||
extern int re_match_2 (struct re_pattern_buffer *buffer, const char *string1,
|
||||
int length1, const char *string2, int length2,
|
||||
int start, struct re_registers *regs, int stop);
|
||||
extern int re_match_2
|
||||
_RE_ARGS ((struct re_pattern_buffer *buffer, const char *string1,
|
||||
int length1, const char *string2, int length2,
|
||||
int start, struct re_registers *regs, int stop));
|
||||
|
||||
|
||||
/* Set REGS to hold NUM_REGS registers, storing them in STARTS and
|
||||
@@ -493,15 +529,15 @@ extern int re_match_2 (struct re_pattern_buffer *buffer, const char *string1,
|
||||
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, unsigned num_regs,
|
||||
regoff_t *starts, regoff_t *ends);
|
||||
extern void re_set_registers
|
||||
_RE_ARGS ((struct re_pattern_buffer *buffer, struct re_registers *regs,
|
||||
unsigned 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 *);
|
||||
extern char *re_comp _RE_ARGS ((const char *));
|
||||
extern int re_exec _RE_ARGS ((const char *));
|
||||
# endif
|
||||
#endif
|
||||
|
||||
@@ -526,19 +562,19 @@ extern int re_exec (const char *);
|
||||
#endif
|
||||
|
||||
/* POSIX compatibility. */
|
||||
extern int regcomp (regex_t *__restrict __preg,
|
||||
const char *__restrict __pattern,
|
||||
int __cflags);
|
||||
extern int regcomp _RE_ARGS ((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 int regexec _RE_ARGS ((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 *__preg,
|
||||
char *__errbuf, size_t __errbuf_size);
|
||||
extern size_t regerror _RE_ARGS ((int __errcode, const regex_t *__preg,
|
||||
char *__errbuf, size_t __errbuf_size));
|
||||
|
||||
extern void regfree (regex_t *__preg);
|
||||
extern void regfree _RE_ARGS ((regex_t *__preg));
|
||||
|
||||
|
||||
#ifdef __cplusplus
|
||||
|
||||
File diff suppressed because it is too large.
Load diff
@@ -0,0 +1,808 @@
|
||||
/* 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@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 <stdio.h>
|
||||
#include <stdlib.h>
|
||||
#include <string.h>
|
||||
|
||||
#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)
|
||||
# define inline
|
||||
#endif
|
||||
|
||||
/* Number of bits in a byte. */
|
||||
#define BYTE_BITS 8
|
||||
/* 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 */
|
||||
|
||||
#ifdef __GNUC__
|
||||
# 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;
|
||||
|
||||
/* Number of bits in an unsinged int. */
|
||||
#define UINT_BITS (sizeof (unsigned int) * BYTE_BITS)
|
||||
/* Number of unsigned int in an bit_set. */
|
||||
#define BITSET_UINTS ((SBC_MAX + UINT_BITS - 1) / UINT_BITS)
|
||||
typedef unsigned int bitset[BITSET_UINTS];
|
||||
typedef unsigned int *re_bitset_ptr_t;
|
||||
typedef const unsigned int *re_const_bitset_ptr_t;
|
||||
|
||||
#define bitset_set(set,i) (set[i / UINT_BITS] |= 1 << i % UINT_BITS)
|
||||
#define bitset_clear(set,i) (set[i / UINT_BITS] &= ~(1 << i % UINT_BITS))
|
||||
#define bitset_contain(set,i) (set[i / UINT_BITS] & (1 << i % UINT_BITS))
|
||||
#define bitset_empty(set) memset (set, 0, sizeof (unsigned int) * BITSET_UINTS)
|
||||
#define bitset_set_all(set) \
|
||||
memset (set, 255, sizeof (unsigned int) * BITSET_UINTS)
|
||||
#define bitset_copy(dest,src) \
|
||||
memcpy (dest, src, sizeof (unsigned int) * BITSET_UINTS)
|
||||
static inline void bitset_not (bitset set);
|
||||
static inline void bitset_merge (bitset dest, const bitset src);
|
||||
static inline void bitset_not_merge (bitset dest, const bitset src);
|
||||
static inline void bitset_mask (bitset dest, const bitset src);
|
||||
|
||||
#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
|
||||
{
|
||||
int alloc;
|
||||
int nelem;
|
||||
int *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. */
|
||||
int nmbchars;
|
||||
|
||||
/* # of collating symbols. */
|
||||
int ncoll_syms;
|
||||
|
||||
/* # of equivalence classes. */
|
||||
int nequiv_classes;
|
||||
|
||||
/* # of range expressions. */
|
||||
int nranges;
|
||||
|
||||
/* # of character classes. */
|
||||
int 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 */
|
||||
int 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;
|
||||
int *offsets;
|
||||
mbstate_t cur_state;
|
||||
#endif
|
||||
/* Index in RAW_MBS. Each character mbs[i] corresponds to
|
||||
raw_mbs[raw_mbs_idx + i]. */
|
||||
int raw_mbs_idx;
|
||||
/* The length of the valid characters in the buffers. */
|
||||
int valid_len;
|
||||
/* The corresponding number of bytes in raw_mbs array. */
|
||||
int valid_raw_len;
|
||||
/* The length of the buffers MBS and WCS. */
|
||||
int bufs_len;
|
||||
/* The index in MBS, which is updated by re_string_fetch_byte. */
|
||||
int cur_idx;
|
||||
/* length of RAW_MBS array. */
|
||||
int raw_len;
|
||||
/* This is RAW_LEN - RAW_MBS_IDX + VALID_LEN - VALID_RAW_LEN. */
|
||||
int 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. */
|
||||
int raw_stop;
|
||||
/* This is RAW_STOP - RAW_MBS_IDX adjusted through OFFSETS. */
|
||||
int 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 RE_TRANSLATE_TYPE trans;
|
||||
/* Copy of re_dfa_t's word_char. */
|
||||
re_const_bitset_ptr_t word_char;
|
||||
/* 1 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
|
||||
|
||||
#ifndef RE_NO_INTERNAL_PROTOTYPES
|
||||
static reg_errcode_t re_string_allocate (re_string_t *pstr, const char *str,
|
||||
int len, int init_len,
|
||||
RE_TRANSLATE_TYPE trans, int icase,
|
||||
const re_dfa_t *dfa)
|
||||
internal_function;
|
||||
static reg_errcode_t re_string_construct (re_string_t *pstr, const char *str,
|
||||
int len, RE_TRANSLATE_TYPE trans,
|
||||
int icase, const re_dfa_t *dfa)
|
||||
internal_function;
|
||||
static reg_errcode_t re_string_reconstruct (re_string_t *pstr, int idx,
|
||||
int eflags) internal_function;
|
||||
static reg_errcode_t re_string_realloc_buffers (re_string_t *pstr,
|
||||
int new_buf_len)
|
||||
internal_function;
|
||||
# ifdef RE_ENABLE_I18N
|
||||
static void build_wcs_buffer (re_string_t *pstr) internal_function;
|
||||
static int 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 void re_string_destruct (re_string_t *pstr) internal_function;
|
||||
# ifdef RE_ENABLE_I18N
|
||||
static int re_string_elem_size_at (const re_string_t *pstr, int idx)
|
||||
internal_function __attribute ((pure));
|
||||
static inline int re_string_char_size_at (const re_string_t *pstr, int idx)
|
||||
internal_function __attribute ((pure));
|
||||
static inline wint_t re_string_wchar_at (const re_string_t *pstr, int idx)
|
||||
internal_function __attribute ((pure));
|
||||
# endif /* RE_ENABLE_I18N */
|
||||
static unsigned int re_string_context_at (const re_string_t *input, int idx,
|
||||
int eflags)
|
||||
internal_function __attribute ((pure));
|
||||
static unsigned char re_string_peek_byte_case (const re_string_t *pstr,
|
||||
int idx)
|
||||
internal_function __attribute ((pure));
|
||||
static unsigned char re_string_fetch_byte_case (re_string_t *pstr)
|
||||
internal_function __attribute ((pure));
|
||||
#endif
|
||||
#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))
|
||||
|
||||
#define re_malloc(t,n) ((t *) malloc ((n) * sizeof (t)))
|
||||
#define re_realloc(p,t,n) ((t *) realloc (p, (n) * sizeof (t)))
|
||||
#define re_free(p) free (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. */
|
||||
int 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
|
||||
{
|
||||
unsigned int 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
|
||||
{
|
||||
int num;
|
||||
int alloc;
|
||||
re_dfastate_t **array;
|
||||
};
|
||||
|
||||
/* Array type used in re_sub_match_last_t and re_sub_match_top_t. */
|
||||
|
||||
typedef struct
|
||||
{
|
||||
int next_idx;
|
||||
int alloc;
|
||||
re_dfastate_t **array;
|
||||
} state_array_t;
|
||||
|
||||
/* Store information about the node NODE whose type is OP_CLOSE_SUBEXP. */
|
||||
|
||||
typedef struct
|
||||
{
|
||||
int node;
|
||||
int 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
|
||||
{
|
||||
int str_idx;
|
||||
int node;
|
||||
int next_last_offset;
|
||||
state_array_t *path;
|
||||
int alasts; /* Allocation size of LASTS. */
|
||||
int nlasts; /* The number of LASTS. */
|
||||
re_sub_match_last_t **lasts;
|
||||
} re_sub_match_top_t;
|
||||
|
||||
struct re_backref_cache_entry
|
||||
{
|
||||
int node;
|
||||
int str_idx;
|
||||
int subexp_from;
|
||||
int 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. */
|
||||
int match_last;
|
||||
int last_node;
|
||||
/* The state log used by the matcher. */
|
||||
re_dfastate_t **state_log;
|
||||
int state_log_top;
|
||||
/* Back reference cache. */
|
||||
int nbkref_ents;
|
||||
int abkref_ents;
|
||||
struct re_backref_cache_entry *bkref_ents;
|
||||
int max_mb_elem_len;
|
||||
int nsub_tops;
|
||||
int 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;
|
||||
int last_node;
|
||||
int last_str_idx;
|
||||
re_node_set limits;
|
||||
} re_sift_context_t;
|
||||
|
||||
struct re_fail_stack_ent_t
|
||||
{
|
||||
int idx;
|
||||
int node;
|
||||
regmatch_t *regs;
|
||||
re_node_set eps_via_nodes;
|
||||
};
|
||||
|
||||
struct re_fail_stack_t
|
||||
{
|
||||
int num;
|
||||
int alloc;
|
||||
struct re_fail_stack_ent_t *stack;
|
||||
};
|
||||
|
||||
struct re_dfa_t
|
||||
{
|
||||
re_token_t *nodes;
|
||||
int nodes_alloc;
|
||||
int nodes_len;
|
||||
int *nexts;
|
||||
int *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. */
|
||||
unsigned int state_hash_mask;
|
||||
int states_alloc;
|
||||
int init_node;
|
||||
int nbackref; /* The number of backreference in this dfa. */
|
||||
|
||||
/* Bitmap expressing which backreference is used. */
|
||||
unsigned int used_bkref_map;
|
||||
unsigned int 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;
|
||||
int *subexp_map;
|
||||
#ifdef DEBUG
|
||||
char* re_str;
|
||||
#endif
|
||||
__libc_lock_define (, lock)
|
||||
};
|
||||
|
||||
#ifndef RE_NO_INTERNAL_PROTOTYPES
|
||||
static reg_errcode_t re_node_set_alloc (re_node_set *set, int size) internal_function;
|
||||
static reg_errcode_t re_node_set_init_1 (re_node_set *set, int elem) internal_function;
|
||||
static reg_errcode_t re_node_set_init_2 (re_node_set *set, int elem1,
|
||||
int elem2) internal_function;
|
||||
#define re_node_set_init_empty(set) memset (set, '\0', sizeof (re_node_set))
|
||||
static reg_errcode_t re_node_set_init_copy (re_node_set *dest,
|
||||
const re_node_set *src) internal_function;
|
||||
static reg_errcode_t re_node_set_add_intersect (re_node_set *dest,
|
||||
const re_node_set *src1,
|
||||
const re_node_set *src2) internal_function;
|
||||
static reg_errcode_t re_node_set_init_union (re_node_set *dest,
|
||||
const re_node_set *src1,
|
||||
const re_node_set *src2) internal_function;
|
||||
static reg_errcode_t re_node_set_merge (re_node_set *dest,
|
||||
const re_node_set *src) internal_function;
|
||||
static int re_node_set_insert (re_node_set *set, int elem) internal_function;
|
||||
static int re_node_set_insert_last (re_node_set *set,
|
||||
int elem) internal_function;
|
||||
static int re_node_set_compare (const re_node_set *set1,
|
||||
const re_node_set *set2)
|
||||
internal_function __attribute ((pure));
|
||||
static int re_node_set_contains (const re_node_set *set, int elem)
|
||||
internal_function __attribute ((pure));
|
||||
static void re_node_set_remove_at (re_node_set *set, int idx) internal_function;
|
||||
#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 int re_dfa_add_node (re_dfa_t *dfa, re_token_t token) internal_function;
|
||||
static re_dfastate_t *re_acquire_state (reg_errcode_t *err, re_dfa_t *dfa,
|
||||
const re_node_set *nodes) internal_function;
|
||||
static re_dfastate_t *re_acquire_state_context (reg_errcode_t *err,
|
||||
re_dfa_t *dfa,
|
||||
const re_node_set *nodes,
|
||||
unsigned int context) internal_function;
|
||||
static void free_state (re_dfastate_t *state) internal_function;
|
||||
#endif
|
||||
|
||||
|
||||
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_not (bitset set)
|
||||
{
|
||||
int bitset_i;
|
||||
for (bitset_i = 0; bitset_i < BITSET_UINTS; ++bitset_i)
|
||||
set[bitset_i] = ~set[bitset_i];
|
||||
}
|
||||
|
||||
static inline void
|
||||
bitset_merge (bitset dest, const bitset src)
|
||||
{
|
||||
int bitset_i;
|
||||
for (bitset_i = 0; bitset_i < BITSET_UINTS; ++bitset_i)
|
||||
dest[bitset_i] |= src[bitset_i];
|
||||
}
|
||||
|
||||
static inline void
|
||||
bitset_not_merge (bitset dest, const bitset src)
|
||||
{
|
||||
int i;
|
||||
for (i = 0; i < BITSET_UINTS; ++i)
|
||||
dest[i] |= ~src[i];
|
||||
}
|
||||
|
||||
static inline void
|
||||
bitset_mask (bitset dest, const bitset src)
|
||||
{
|
||||
int bitset_i;
|
||||
for (bitset_i = 0; bitset_i < BITSET_UINTS; ++bitset_i)
|
||||
dest[bitset_i] &= src[bitset_i];
|
||||
}
|
||||
|
||||
#if defined RE_ENABLE_I18N && !defined RE_NO_INTERNAL_PROTOTYPES
|
||||
/* Inline functions for re_string. */
|
||||
static inline int
|
||||
internal_function
|
||||
re_string_char_size_at (const re_string_t *pstr, int 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
|
||||
re_string_wchar_at (const re_string_t *pstr, int idx)
|
||||
{
|
||||
if (pstr->mb_cur_max == 1)
|
||||
return (wint_t) pstr->mbs[idx];
|
||||
return (wint_t) pstr->wcs[idx];
|
||||
}
|
||||
|
||||
static int
|
||||
internal_function
|
||||
re_string_elem_size_at (const re_string_t *pstr, int 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 */
|
||||
+4338
File diff suppressed because it is too large.
Load diff
@@ -1,3 +1,9 @@
|
||||
2005-07-07 Paul Eggert <eggert@cs.ucla.edu>
|
||||
|
||||
Switch to Isamu Hasegawa's implementation of regex, which is
|
||||
now in gnulib.
|
||||
* regex.m4: Import from gnulib.
|
||||
|
||||
2005-07-04 Paul Eggert <eggert@cs.ucla.edu>
|
||||
|
||||
* prereq.m4 (gl_PREREQ): Don't require gl_TYPEOF; no longer needed.
|
||||
|
||||
+50
-38
@@ -1,6 +1,6 @@
|
||||
#serial 22
|
||||
#serial 23
|
||||
|
||||
# Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2003, 2004 Free
|
||||
# Copyright (C) 1996, 1997, 1998, 1999, 2000, 2001, 2003, 2004, 2005 Free
|
||||
# Software Foundation, Inc.
|
||||
#
|
||||
# This file is free software; the Free Software Foundation
|
||||
@@ -19,6 +19,10 @@ dnl Usage: gl_INCLUDED_REGEX([lib/regex.c])
|
||||
dnl
|
||||
AC_DEFUN([gl_INCLUDED_REGEX],
|
||||
[
|
||||
AC_LIBSOURCES(
|
||||
[regcomp.c, regex.c, regex.h,
|
||||
regex_internal.c, regex_internal.h, regexec.c])
|
||||
|
||||
dnl Even packages that don't use regex.c can use this macro.
|
||||
dnl Of course, for them it doesn't do anything.
|
||||
|
||||
@@ -31,9 +35,10 @@ AC_DEFUN([gl_INCLUDED_REGEX],
|
||||
# regex.c. The first failing regular expression is from `Spencer ere
|
||||
# test #75' in grep-2.3.
|
||||
AC_CACHE_CHECK([for working re_compile_pattern],
|
||||
jm_cv_func_working_re_compile_pattern,
|
||||
AC_TRY_RUN(
|
||||
[#include <stdio.h>
|
||||
[gl_cv_func_working_re_compile_pattern],
|
||||
[AC_TRY_RUN(
|
||||
[[
|
||||
#include <stdio.h>
|
||||
#include <string.h>
|
||||
#include <regex.h>
|
||||
int
|
||||
@@ -44,12 +49,12 @@ AC_DEFUN([gl_INCLUDED_REGEX],
|
||||
struct re_registers regs;
|
||||
re_set_syntax (RE_SYNTAX_POSIX_EGREP);
|
||||
memset (®ex, 0, sizeof (regex));
|
||||
[s = re_compile_pattern ("a[[:@:>@:]]b\n", 9, ®ex);]
|
||||
s = re_compile_pattern ("a[:@:>@:]b\n", 9, ®ex);
|
||||
/* This should fail with _Invalid character class name_ error. */
|
||||
if (!s)
|
||||
exit (1);
|
||||
|
||||
/* This should succeed, but doesn't for e.g. glibc-2.1.3. */
|
||||
/* This should succeed, but does not for e.g. glibc-2.1.3. */
|
||||
memset (®ex, 0, sizeof (regex));
|
||||
s = re_compile_pattern ("{1", 2, ®ex);
|
||||
|
||||
@@ -59,11 +64,11 @@ AC_DEFUN([gl_INCLUDED_REGEX],
|
||||
/* The following example is derived from a problem report
|
||||
against gawk from Jorge Stolfi <stolfi@ic.unicamp.br>. */
|
||||
memset (®ex, 0, sizeof (regex));
|
||||
s = re_compile_pattern ("[[an\371]]*n", 7, ®ex);
|
||||
s = re_compile_pattern ("[an\371]*n", 7, ®ex);
|
||||
if (s)
|
||||
exit (1);
|
||||
|
||||
/* This should match, but doesn't for e.g. glibc-2.2.1. */
|
||||
/* This should match, but does not for e.g. glibc-2.2.1. */
|
||||
if (re_match (®ex, "an", 2, 0, ®s) != 2)
|
||||
exit (1);
|
||||
|
||||
@@ -72,34 +77,50 @@ AC_DEFUN([gl_INCLUDED_REGEX],
|
||||
if (s)
|
||||
exit (1);
|
||||
|
||||
/* The version of regex.c in e.g. GNU libc-2.2.93 didn't
|
||||
/* The version of regex.c in e.g. GNU libc-2.2.93 did not
|
||||
work with a negative RANGE argument. */
|
||||
if (re_search (®ex, "wxy", 3, 2, -2, ®s) != 1)
|
||||
exit (1);
|
||||
|
||||
/* The version of regex.c in older versions of gnulib
|
||||
* ignored RE_ICASE. Detect that problem too. */
|
||||
memset (®ex, 0, sizeof (regex));
|
||||
re_set_syntax(RE_SYNTAX_EMACS|RE_ICASE);
|
||||
s = re_compile_pattern ("x", 1, ®ex);
|
||||
if (s)
|
||||
exit (1);
|
||||
|
||||
if (re_search (®ex, "WXY", 3, 0, 3, ®s) < 0)
|
||||
exit (1);
|
||||
|
||||
/* REG_STARTEND was added to glibc on 2004-01-15.
|
||||
Reject older versions. */
|
||||
if (! REG_STARTEND)
|
||||
exit (1);
|
||||
|
||||
exit (0);
|
||||
}
|
||||
],
|
||||
jm_cv_func_working_re_compile_pattern=yes,
|
||||
jm_cv_func_working_re_compile_pattern=no,
|
||||
dnl When crosscompiling, assume it's broken.
|
||||
jm_cv_func_working_re_compile_pattern=no))
|
||||
if test $jm_cv_func_working_re_compile_pattern = yes; then
|
||||
]],
|
||||
[gl_cv_func_working_re_compile_pattern=yes],
|
||||
[gl_cv_func_working_re_compile_pattern=no],
|
||||
dnl When crosscompiling, assume it is broken.
|
||||
[gl_cv_func_working_re_compile_pattern=no])])
|
||||
if test $gl_cv_func_working_re_compile_pattern = yes; then
|
||||
ac_use_included_regex=no
|
||||
fi
|
||||
|
||||
test -n "$1" || AC_MSG_ERROR([missing argument])
|
||||
m4_syscmd([test -f $1])
|
||||
m4_syscmd([test -f '$1'])
|
||||
ifelse(m4_sysval, 0,
|
||||
[
|
||||
AC_ARG_WITH(included-regex,
|
||||
[ --without-included-regex don't compile regex; this is the default on
|
||||
systems with version 2 of the GNU C library
|
||||
(use with caution on other system)],
|
||||
jm_with_regex=$withval,
|
||||
jm_with_regex=$ac_use_included_regex)
|
||||
if test "$jm_with_regex" = yes; then
|
||||
AC_LIBOBJ(regex)
|
||||
AC_ARG_WITH([included-regex],
|
||||
[ --without-included-regex don't compile regex; this is the default on
|
||||
systems with recent-enough versions of the GNU C
|
||||
Library (use with caution on other systems)],
|
||||
[gl_with_regex=$withval],
|
||||
[gl_with_regex=$ac_use_included_regex])
|
||||
if test "X$gl_with_regex" = Xyes; then
|
||||
AC_LIBOBJ([regex])
|
||||
gl_PREREQ_REGEX
|
||||
fi
|
||||
],
|
||||
@@ -107,20 +128,11 @@ AC_DEFUN([gl_INCLUDED_REGEX],
|
||||
]
|
||||
)
|
||||
|
||||
# Prerequisites of lib/regex.c.
|
||||
# Prerequisites of lib/regex.c and lib/regex_internal.c.
|
||||
AC_DEFUN([gl_PREREQ_REGEX],
|
||||
[
|
||||
dnl FIXME: Maybe provide a btowc replacement someday: Solaris 2.5.1 lacks it.
|
||||
dnl FIXME: Check for wctype and iswctype, and and add -lw if necessary
|
||||
dnl to get them.
|
||||
|
||||
dnl Persuade glibc <string.h> to declare mempcpy().
|
||||
AC_REQUIRE([AC_GNU_SOURCE])
|
||||
|
||||
AC_REQUIRE([gl_C_RESTRICT])
|
||||
AC_REQUIRE([AC_FUNC_ALLOCA])
|
||||
AC_REQUIRE([AC_HEADER_STDC])
|
||||
AC_CHECK_HEADERS_ONCE(wchar.h wctype.h)
|
||||
AC_CHECK_FUNCS_ONCE(isascii mempcpy)
|
||||
AC_CHECK_FUNCS(btowc)
|
||||
AC_REQUIRE([AM_LANGINFO_CODESET])
|
||||
AC_CHECK_HEADERS_ONCE([locale.h wchar.h wctype.h])
|
||||
AC_CHECK_FUNCS_ONCE([isblank mbrtowc mempcpy wcrtomb wcscoll])
|
||||
])
|
||||
Reference in new issue
Block a user