2002-02-27 03:06:03 +08:00
|
|
|
|
/* Extended regular expression matching and search library.
|
2003-02-21 09:52:32 +08:00
|
|
|
|
Copyright (C) 2002, 2003 Free Software Foundation, Inc.
|
2002-02-27 03:06:03 +08:00
|
|
|
|
This file is part of the GNU C Library.
|
|
|
|
|
Contributed by Isamu Hasegawa <isamu@yamato.ibm.com>.
|
|
|
|
|
|
|
|
|
|
The GNU C Library is free software; you can redistribute it and/or
|
|
|
|
|
modify it under the terms of the GNU Lesser General Public
|
|
|
|
|
License as published by the Free Software Foundation; either
|
|
|
|
|
version 2.1 of the License, or (at your option) any later version.
|
|
|
|
|
|
|
|
|
|
The GNU C Library 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
|
|
|
|
|
Lesser General Public License for more details.
|
|
|
|
|
|
|
|
|
|
You should have received a copy of the GNU Lesser General Public
|
|
|
|
|
License along with the GNU C Library; if not, write to the Free
|
|
|
|
|
Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
|
|
|
|
|
02111-1307 USA. */
|
|
|
|
|
|
|
|
|
|
#ifndef _REGEX_INTERNAL_H
|
|
|
|
|
#define _REGEX_INTERNAL_H 1
|
|
|
|
|
|
2003-02-21 09:52:32 +08:00
|
|
|
|
#ifdef HAVE_CONFIG_H
|
|
|
|
|
#include "config.h"
|
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#include <assert.h>
|
|
|
|
|
#include <ctype.h>
|
|
|
|
|
#include <limits.h>
|
|
|
|
|
#include <stdio.h>
|
|
|
|
|
#include <stdlib.h>
|
|
|
|
|
#include <string.h>
|
|
|
|
|
|
|
|
|
|
#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 */
|
|
|
|
|
|
|
|
|
|
/* 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 || defined _LIBC
|
|
|
|
|
# include <libintl.h>
|
|
|
|
|
# ifdef _LIBC
|
|
|
|
|
# undef gettext
|
|
|
|
|
# define gettext(msgid) \
|
|
|
|
|
INTUSE(__dcgettext) (INTUSE(_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
|
|
|
|
|
|
2003-02-23 17:58:08 +08:00
|
|
|
|
#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
|
2003-02-21 09:52:32 +08:00
|
|
|
|
#endif
|
|
|
|
|
|
|
|
|
|
#if __GNUC__ >= 3
|
|
|
|
|
# define BE(expr, val) __builtin_expect (expr, val)
|
|
|
|
|
#else
|
|
|
|
|
# define BE(expr, val) (expr)
|
|
|
|
|
# define inline
|
|
|
|
|
#endif
|
|
|
|
|
|
2002-02-27 03:06:03 +08:00
|
|
|
|
/* 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'
|
2002-11-13 12:00:16 +08:00
|
|
|
|
#define WIDE_NEWLINE_CHAR L'\n'
|
2002-02-27 03:06:03 +08:00
|
|
|
|
|
|
|
|
|
/* Rename to standard API for using out of glibc. */
|
|
|
|
|
#ifndef _LIBC
|
|
|
|
|
# define __wctype wctype
|
|
|
|
|
# define __iswctype iswctype
|
|
|
|
|
# define __btowc btowc
|
2003-02-21 09:52:32 +08:00
|
|
|
|
# define __mempcpy mempcpy
|
|
|
|
|
# define __wcrtomb wcrtomb
|
2002-04-27 04:52:02 +08:00
|
|
|
|
# define attribute_hidden
|
|
|
|
|
#endif /* not _LIBC */
|
2002-02-27 03:06:03 +08:00
|
|
|
|
|
2003-09-23 13:33:43 +08:00
|
|
|
|
#ifdef __GNUC__
|
|
|
|
|
# define __attribute __attribute__
|
|
|
|
|
#else
|
|
|
|
|
# define __attribute
|
|
|
|
|
#endif
|
|
|
|
|
|
2002-03-13 16:59:47 +08:00
|
|
|
|
extern const char __re_error_msgid[] attribute_hidden;
|
|
|
|
|
extern const size_t __re_error_msgid_idx[] attribute_hidden;
|
2002-02-27 03:06:03 +08:00
|
|
|
|
|
|
|
|
|
/* 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;
|
|
|
|
|
|
|
|
|
|
#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);
|
|
|
|
|
|
|
|
|
|
#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 DUMMY_CONSTRAINT 0x0100
|
|
|
|
|
|
|
|
|
|
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,
|
|
|
|
|
LINE_FIRST = PREV_NEWLINE_CONSTRAINT,
|
|
|
|
|
LINE_LAST = NEXT_NEWLINE_CONSTRAINT,
|
|
|
|
|
BUF_FIRST = PREV_BEGBUF_CONSTRAINT,
|
|
|
|
|
BUF_LAST = NEXT_ENDBUF_CONSTRAINT,
|
|
|
|
|
WORD_DELIM = DUMMY_CONSTRAINT
|
|
|
|
|
} re_context_type;
|
|
|
|
|
|
|
|
|
|
typedef struct
|
|
|
|
|
{
|
|
|
|
|
int alloc;
|
|
|
|
|
int nelem;
|
|
|
|
|
int *elems;
|
|
|
|
|
} re_node_set;
|
|
|
|
|
|
|
|
|
|
typedef enum
|
|
|
|
|
{
|
|
|
|
|
NON_TYPE = 0,
|
|
|
|
|
|
2003-11-19 07:40:59 +08:00
|
|
|
|
/* 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 */
|
|
|
|
|
|
|
|
|
|
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,
|
|
|
|
|
OP_DUP_PLUS = EPSILON_BIT | 4,
|
|
|
|
|
OP_DUP_QUESTION = EPSILON_BIT | 5,
|
|
|
|
|
ANCHOR = EPSILON_BIT | 6,
|
|
|
|
|
|
|
|
|
|
/* Tree type, these are used only by tree. */
|
|
|
|
|
CONCAT = 16,
|
|
|
|
|
|
2002-02-27 03:06:03 +08:00
|
|
|
|
/* Token type, these are used only by token. */
|
2003-11-19 07:40:59 +08:00
|
|
|
|
OP_OPEN_BRACKET = 17,
|
2002-02-27 03:06:03 +08:00
|
|
|
|
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,
|
2003-09-23 13:43:03 +08:00
|
|
|
|
OP_SPACE,
|
|
|
|
|
OP_NOTSPACE,
|
2003-11-19 07:40:59 +08:00
|
|
|
|
BACK_SLASH
|
2002-02-27 03:06:03 +08:00
|
|
|
|
|
|
|
|
|
} re_token_type_t;
|
|
|
|
|
|
2002-05-24 16:49:00 +08:00
|
|
|
|
#ifdef RE_ENABLE_I18N
|
2002-02-27 03:06:03 +08:00
|
|
|
|
typedef struct
|
|
|
|
|
{
|
|
|
|
|
/* Multibyte characters. */
|
|
|
|
|
wchar_t *mbchars;
|
|
|
|
|
|
|
|
|
|
/* Collating symbols. */
|
2002-05-24 16:49:00 +08:00
|
|
|
|
# ifdef _LIBC
|
2002-02-27 03:06:03 +08:00
|
|
|
|
int32_t *coll_syms;
|
2002-05-24 16:49:00 +08:00
|
|
|
|
# endif
|
2002-02-27 03:06:03 +08:00
|
|
|
|
|
|
|
|
|
/* Equivalence classes. */
|
2002-05-24 16:49:00 +08:00
|
|
|
|
# ifdef _LIBC
|
2002-02-27 03:06:03 +08:00
|
|
|
|
int32_t *equiv_classes;
|
2002-05-24 16:49:00 +08:00
|
|
|
|
# endif
|
2002-02-27 03:06:03 +08:00
|
|
|
|
|
|
|
|
|
/* Range expressions. */
|
2002-05-24 16:49:00 +08:00
|
|
|
|
# ifdef _LIBC
|
2002-02-27 03:06:03 +08:00
|
|
|
|
uint32_t *range_starts;
|
|
|
|
|
uint32_t *range_ends;
|
2002-05-24 16:49:00 +08:00
|
|
|
|
# else /* not _LIBC */
|
2002-04-27 04:52:02 +08:00
|
|
|
|
wchar_t *range_starts;
|
|
|
|
|
wchar_t *range_ends;
|
2002-05-24 16:49:00 +08:00
|
|
|
|
# endif /* not _LIBC */
|
2002-02-27 03:06:03 +08:00
|
|
|
|
|
|
|
|
|
/* Character classes. */
|
|
|
|
|
wctype_t *char_classes;
|
2002-07-11 07:09:16 +08:00
|
|
|
|
|
|
|
|
|
/* 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. */
|
2002-02-27 03:06:03 +08:00
|
|
|
|
int nchar_classes;
|
|
|
|
|
} re_charset_t;
|
2002-05-24 16:49:00 +08:00
|
|
|
|
#endif /* RE_ENABLE_I18N */
|
2002-02-27 03:06:03 +08:00
|
|
|
|
|
|
|
|
|
typedef struct
|
|
|
|
|
{
|
|
|
|
|
union
|
|
|
|
|
{
|
|
|
|
|
unsigned char c; /* for CHARACTER */
|
|
|
|
|
re_bitset_ptr_t sbcset; /* for SIMPLE_BRACKET */
|
2002-05-24 16:49:00 +08:00
|
|
|
|
#ifdef RE_ENABLE_I18N
|
2002-02-27 03:06:03 +08:00
|
|
|
|
re_charset_t *mbcset; /* for COMPLEX_BRACKET */
|
2002-05-24 16:49:00 +08:00
|
|
|
|
#endif /* RE_ENABLE_I18N */
|
2002-02-27 03:06:03 +08:00
|
|
|
|
int idx; /* for BACK_REF */
|
|
|
|
|
re_context_type ctx_type; /* for ANCHOR */
|
|
|
|
|
} opr;
|
2002-07-11 07:09:16 +08:00
|
|
|
|
#if __GNUC__ >= 2
|
|
|
|
|
re_token_type_t type : 8;
|
|
|
|
|
#else
|
|
|
|
|
re_token_type_t type;
|
|
|
|
|
#endif
|
2002-02-27 03:06:03 +08:00
|
|
|
|
unsigned int constraint : 10; /* context constraint */
|
|
|
|
|
unsigned int duplicated : 1;
|
|
|
|
|
#ifdef RE_ENABLE_I18N
|
|
|
|
|
unsigned int mb_partial : 1;
|
|
|
|
|
#endif
|
|
|
|
|
} re_token_t;
|
|
|
|
|
|
2003-11-19 07:40:59 +08:00
|
|
|
|
#define IS_EPSILON_NODE(type) ((type) & EPSILON_BIT)
|
2002-02-27 03:06:03 +08:00
|
|
|
|
#define ACCEPT_MB_NODE(type) \
|
2003-11-19 07:40:59 +08:00
|
|
|
|
((type) >= OP_PERIOD && (type) <= OP_UTF8_PERIOD)
|
2002-02-27 03:06:03 +08:00
|
|
|
|
|
|
|
|
|
struct re_string_t
|
|
|
|
|
{
|
2002-04-25 05:54:53 +08:00
|
|
|
|
/* Indicate the raw buffer which is the original string passed as an
|
|
|
|
|
argument of regexec(), re_search(), etc.. */
|
2002-09-11 02:40:35 +08:00
|
|
|
|
const unsigned char *raw_mbs;
|
2002-02-27 03:06:03 +08:00
|
|
|
|
/* Store the multibyte string. In case of "case insensitive mode" like
|
2002-04-25 05:54:53 +08:00
|
|
|
|
REG_ICASE, upper cases of the string are stored, otherwise MBS points
|
|
|
|
|
the same address that RAW_MBS points. */
|
2002-09-11 02:40:35 +08:00
|
|
|
|
unsigned char *mbs;
|
2002-02-27 03:06:03 +08:00
|
|
|
|
/* Store the case sensitive multibyte string. In case of
|
|
|
|
|
"case insensitive mode", the original string are stored,
|
|
|
|
|
otherwise MBS_CASE points the same address that MBS points. */
|
2002-09-11 02:40:35 +08:00
|
|
|
|
unsigned char *mbs_case;
|
2002-02-27 03:06:03 +08:00
|
|
|
|
#ifdef RE_ENABLE_I18N
|
|
|
|
|
/* Store the wide character string which is corresponding to MBS. */
|
2002-05-24 16:49:00 +08:00
|
|
|
|
wint_t *wcs;
|
2002-04-25 05:54:53 +08:00
|
|
|
|
mbstate_t cur_state;
|
2002-02-27 03:06:03 +08:00
|
|
|
|
#endif
|
2002-07-11 07:09:16 +08:00
|
|
|
|
/* Index in RAW_MBS. Each character mbs[i] corresponds to
|
|
|
|
|
raw_mbs[raw_mbs_idx + i]. */
|
|
|
|
|
int raw_mbs_idx;
|
2002-04-25 05:54:53 +08:00
|
|
|
|
/* The length of the valid characters in the buffers. */
|
|
|
|
|
int valid_len;
|
|
|
|
|
/* The length of the buffers MBS, MBS_CASE, and WCS. */
|
|
|
|
|
int bufs_len;
|
|
|
|
|
/* The index in MBS, which is updated by re_string_fetch_byte. */
|
|
|
|
|
int cur_idx;
|
|
|
|
|
/* This is length_of_RAW_MBS - RAW_MBS_IDX. */
|
|
|
|
|
int len;
|
2002-07-27 16:20:17 +08:00
|
|
|
|
/* 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 stop;
|
|
|
|
|
|
2002-04-25 05:54:53 +08:00
|
|
|
|
/* 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. */
|
|
|
|
|
RE_TRANSLATE_TYPE trans;
|
|
|
|
|
/* 1 if REG_ICASE. */
|
|
|
|
|
unsigned int icase : 1;
|
Update.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* io/ftw.c (NFTW_NEW_NAME, NFTW_OLD_NAME): Add prototypes.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/tst-regex.c (umemlen): New variable.
(test_expr): Add expectedicase argument. Test case insensitive
searches as well as backwards searches (case sensitive and
insensitive) too.
(run_test): Add icase argument. Use it to compute regcomp flags.
(run_test_backwards): New function.
(main): Cast read to size_t to avoid warning. Set umemlen.
Add expectedicase arguments to test_expr.
* posix/regex_internal.c (re_string_reconstruct): If is_utf8,
find previous character by walking back instead of converting
all chars from beginning.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/regex_internal.h (struct re_string_t): Add is_utf8
and mb_cur_max fields.
(struct re_dfa_t): Likewise. Reorder fields to make structure
smaller on 64-bit arches.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments.
(re_string_char_size_at, re_string_wchar_at): Use pstr->mb_cur_max
instead of MB_CUR_MAX.
* posix/regcomp.c (re_compile_fastmap_iter): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
(re_compile_internal): Pass new arguments to re_string_construct.
(init_dfa): Initialize mb_cur_max and is_utf8 fields.
(peek_token, peek_token_bracket): Use input->mb_cur_max instead
of MB_CUR_MAX.
(parse_expression, parse_bracket_exp, parse_charclass_op): Use
dfa->mb_cur_max instead of MB_CUR_MAX.
* posix/regex_internal.c (re_string_construct_common): Add
mb_cur_max and is_utf8 arguments. Initialize fields with them.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments, pass them to re_string_construct_common.
Use mb_cur_max instead of MB_CUR_MAX.
(re_string_realloc_buffers): Use pstr->mb_cur_max instead of
MB_CUR_MAX.
(re_string_reconstruct): Likewise.
(re_string_context_at): Use input->mb_cur_max instead of
MB_CUR_MAX.
(create_ci_newstate, create_cd_newstate): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
* posix/regexec.c (re_search_internal): Likewise.
Pass new arguments to re_string_allocate.
(check_matching, transit_state_sb): Use dfa->mb_cur_max instead of
MB_CUR_MAX.
(extend_buffers): Use pstr->mb_cur_max instead of MB_CUR_MAX.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/Makefile (tests): Add bug-regex19.
(bug-regex19-ENV): Add LOCPATH.
* posix/bug-regex19.c: New test.
2003-11-13 01:47:46 +08:00
|
|
|
|
unsigned int is_utf8 : 1;
|
2003-11-16 15:14:28 +08:00
|
|
|
|
unsigned int map_notascii : 1;
|
Update.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* io/ftw.c (NFTW_NEW_NAME, NFTW_OLD_NAME): Add prototypes.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/tst-regex.c (umemlen): New variable.
(test_expr): Add expectedicase argument. Test case insensitive
searches as well as backwards searches (case sensitive and
insensitive) too.
(run_test): Add icase argument. Use it to compute regcomp flags.
(run_test_backwards): New function.
(main): Cast read to size_t to avoid warning. Set umemlen.
Add expectedicase arguments to test_expr.
* posix/regex_internal.c (re_string_reconstruct): If is_utf8,
find previous character by walking back instead of converting
all chars from beginning.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/regex_internal.h (struct re_string_t): Add is_utf8
and mb_cur_max fields.
(struct re_dfa_t): Likewise. Reorder fields to make structure
smaller on 64-bit arches.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments.
(re_string_char_size_at, re_string_wchar_at): Use pstr->mb_cur_max
instead of MB_CUR_MAX.
* posix/regcomp.c (re_compile_fastmap_iter): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
(re_compile_internal): Pass new arguments to re_string_construct.
(init_dfa): Initialize mb_cur_max and is_utf8 fields.
(peek_token, peek_token_bracket): Use input->mb_cur_max instead
of MB_CUR_MAX.
(parse_expression, parse_bracket_exp, parse_charclass_op): Use
dfa->mb_cur_max instead of MB_CUR_MAX.
* posix/regex_internal.c (re_string_construct_common): Add
mb_cur_max and is_utf8 arguments. Initialize fields with them.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments, pass them to re_string_construct_common.
Use mb_cur_max instead of MB_CUR_MAX.
(re_string_realloc_buffers): Use pstr->mb_cur_max instead of
MB_CUR_MAX.
(re_string_reconstruct): Likewise.
(re_string_context_at): Use input->mb_cur_max instead of
MB_CUR_MAX.
(create_ci_newstate, create_cd_newstate): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
* posix/regexec.c (re_search_internal): Likewise.
Pass new arguments to re_string_allocate.
(check_matching, transit_state_sb): Use dfa->mb_cur_max instead of
MB_CUR_MAX.
(extend_buffers): Use pstr->mb_cur_max instead of MB_CUR_MAX.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/Makefile (tests): Add bug-regex19.
(bug-regex19-ENV): Add LOCPATH.
* posix/bug-regex19.c: New test.
2003-11-13 01:47:46 +08:00
|
|
|
|
int mb_cur_max;
|
2002-02-27 03:06:03 +08:00
|
|
|
|
};
|
|
|
|
|
typedef struct re_string_t re_string_t;
|
2002-04-25 05:54:53 +08:00
|
|
|
|
/* In case of REG_ICASE, we allocate the buffer dynamically for mbs. */
|
|
|
|
|
#define MBS_ALLOCATED(pstr) (pstr->icase)
|
|
|
|
|
/* In case that we need translation, we allocate the buffer dynamically
|
|
|
|
|
for mbs_case. Note that mbs == mbs_case if not REG_ICASE. */
|
|
|
|
|
#define MBS_CASE_ALLOCATED(pstr) (pstr->trans != NULL)
|
|
|
|
|
|
2002-02-27 03:06:03 +08:00
|
|
|
|
|
2003-11-16 15:14:28 +08:00
|
|
|
|
struct re_dfa_t;
|
|
|
|
|
typedef struct re_dfa_t re_dfa_t;
|
2003-11-13 03:09:20 +08:00
|
|
|
|
#ifndef RE_NO_INTERNAL_PROTOTYPES
|
2002-09-05 18:28:51 +08:00
|
|
|
|
static reg_errcode_t re_string_allocate (re_string_t *pstr, const char *str,
|
2002-11-07 04:36:47 +08:00
|
|
|
|
int len, int init_len,
|
Update.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* io/ftw.c (NFTW_NEW_NAME, NFTW_OLD_NAME): Add prototypes.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/tst-regex.c (umemlen): New variable.
(test_expr): Add expectedicase argument. Test case insensitive
searches as well as backwards searches (case sensitive and
insensitive) too.
(run_test): Add icase argument. Use it to compute regcomp flags.
(run_test_backwards): New function.
(main): Cast read to size_t to avoid warning. Set umemlen.
Add expectedicase arguments to test_expr.
* posix/regex_internal.c (re_string_reconstruct): If is_utf8,
find previous character by walking back instead of converting
all chars from beginning.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/regex_internal.h (struct re_string_t): Add is_utf8
and mb_cur_max fields.
(struct re_dfa_t): Likewise. Reorder fields to make structure
smaller on 64-bit arches.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments.
(re_string_char_size_at, re_string_wchar_at): Use pstr->mb_cur_max
instead of MB_CUR_MAX.
* posix/regcomp.c (re_compile_fastmap_iter): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
(re_compile_internal): Pass new arguments to re_string_construct.
(init_dfa): Initialize mb_cur_max and is_utf8 fields.
(peek_token, peek_token_bracket): Use input->mb_cur_max instead
of MB_CUR_MAX.
(parse_expression, parse_bracket_exp, parse_charclass_op): Use
dfa->mb_cur_max instead of MB_CUR_MAX.
* posix/regex_internal.c (re_string_construct_common): Add
mb_cur_max and is_utf8 arguments. Initialize fields with them.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments, pass them to re_string_construct_common.
Use mb_cur_max instead of MB_CUR_MAX.
(re_string_realloc_buffers): Use pstr->mb_cur_max instead of
MB_CUR_MAX.
(re_string_reconstruct): Likewise.
(re_string_context_at): Use input->mb_cur_max instead of
MB_CUR_MAX.
(create_ci_newstate, create_cd_newstate): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
* posix/regexec.c (re_search_internal): Likewise.
Pass new arguments to re_string_allocate.
(check_matching, transit_state_sb): Use dfa->mb_cur_max instead of
MB_CUR_MAX.
(extend_buffers): Use pstr->mb_cur_max instead of MB_CUR_MAX.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/Makefile (tests): Add bug-regex19.
(bug-regex19-ENV): Add LOCPATH.
* posix/bug-regex19.c: New test.
2003-11-13 01:47:46 +08:00
|
|
|
|
RE_TRANSLATE_TYPE trans, int icase,
|
2003-11-16 15:14:28 +08:00
|
|
|
|
const re_dfa_t *dfa);
|
2002-09-05 18:28:51 +08:00
|
|
|
|
static reg_errcode_t re_string_construct (re_string_t *pstr, const char *str,
|
2002-11-07 04:36:47 +08:00
|
|
|
|
int len, RE_TRANSLATE_TYPE trans,
|
2003-11-16 15:14:28 +08:00
|
|
|
|
int icase, const re_dfa_t *dfa);
|
2002-04-25 05:54:53 +08:00
|
|
|
|
static reg_errcode_t re_string_reconstruct (re_string_t *pstr, int idx,
|
2002-11-07 04:36:47 +08:00
|
|
|
|
int eflags, int newline);
|
2002-04-25 05:54:53 +08:00
|
|
|
|
static reg_errcode_t re_string_realloc_buffers (re_string_t *pstr,
|
2002-11-07 04:36:47 +08:00
|
|
|
|
int new_buf_len);
|
2003-11-16 15:14:28 +08:00
|
|
|
|
# ifdef RE_ENABLE_I18N
|
2002-04-25 05:54:53 +08:00
|
|
|
|
static void build_wcs_buffer (re_string_t *pstr);
|
|
|
|
|
static void build_wcs_upper_buffer (re_string_t *pstr);
|
2003-11-16 15:14:28 +08:00
|
|
|
|
# endif /* RE_ENABLE_I18N */
|
2002-04-25 05:54:53 +08:00
|
|
|
|
static void build_upper_buffer (re_string_t *pstr);
|
|
|
|
|
static void re_string_translate_buffer (re_string_t *pstr);
|
2002-02-27 03:06:03 +08:00
|
|
|
|
static void re_string_destruct (re_string_t *pstr);
|
2003-11-16 15:14:28 +08:00
|
|
|
|
# ifdef RE_ENABLE_I18N
|
2002-02-27 03:06:03 +08:00
|
|
|
|
static int re_string_elem_size_at (const re_string_t *pstr, int idx);
|
|
|
|
|
static inline int re_string_char_size_at (const re_string_t *pstr, int idx);
|
|
|
|
|
static inline wint_t re_string_wchar_at (const re_string_t *pstr, int idx);
|
2003-11-16 15:14:28 +08:00
|
|
|
|
# endif /* RE_ENABLE_I18N */
|
2002-02-27 03:06:03 +08:00
|
|
|
|
static unsigned int re_string_context_at (const re_string_t *input, int idx,
|
|
|
|
|
int eflags, int newline_anchor);
|
2003-11-13 03:09:20 +08:00
|
|
|
|
#endif
|
2002-02-27 03:06:03 +08:00
|
|
|
|
#define re_string_peek_byte(pstr, offset) \
|
|
|
|
|
((pstr)->mbs[(pstr)->cur_idx + offset])
|
|
|
|
|
#define re_string_peek_byte_case(pstr, offset) \
|
|
|
|
|
((pstr)->mbs_case[(pstr)->cur_idx + offset])
|
|
|
|
|
#define re_string_fetch_byte(pstr) \
|
|
|
|
|
((pstr)->mbs[(pstr)->cur_idx++])
|
|
|
|
|
#define re_string_fetch_byte_case(pstr) \
|
|
|
|
|
((pstr)->mbs_case[(pstr)->cur_idx++])
|
|
|
|
|
#define re_string_first_byte(pstr, idx) \
|
2003-11-19 16:43:18 +08:00
|
|
|
|
((idx) == (pstr)->valid_len || (pstr)->wcs[idx] != WEOF)
|
2002-02-27 03:06:03 +08:00
|
|
|
|
#define re_string_is_single_byte_char(pstr, idx) \
|
2003-11-19 16:43:18 +08:00
|
|
|
|
((pstr)->wcs[idx] != WEOF && ((pstr)->valid_len == (idx) \
|
2002-11-07 04:36:47 +08:00
|
|
|
|
|| (pstr)->wcs[(idx) + 1] != WEOF))
|
2002-07-27 16:20:17 +08:00
|
|
|
|
#define re_string_eoi(pstr) ((pstr)->stop <= (pstr)->cur_idx)
|
2002-02-27 03:06:03 +08:00
|
|
|
|
#define re_string_cur_idx(pstr) ((pstr)->cur_idx)
|
|
|
|
|
#define re_string_get_buffer(pstr) ((pstr)->mbs)
|
|
|
|
|
#define re_string_length(pstr) ((pstr)->len)
|
2002-04-25 05:54:53 +08:00
|
|
|
|
#define re_string_byte_at(pstr,idx) ((pstr)->mbs[idx])
|
2002-02-27 03:06:03 +08:00
|
|
|
|
#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;
|
|
|
|
|
|
|
|
|
|
/* `node_idx' is the index in dfa->nodes, if `type' == 0.
|
|
|
|
|
Otherwise `type' indicate the type of this node. */
|
|
|
|
|
re_token_type_t type;
|
|
|
|
|
int node_idx;
|
|
|
|
|
|
|
|
|
|
int first;
|
|
|
|
|
int next;
|
|
|
|
|
re_node_set eclosure;
|
|
|
|
|
};
|
|
|
|
|
typedef struct bin_tree_t bin_tree_t;
|
|
|
|
|
|
Update.
2003-11-19 Jakub Jelinek <jakub@redhat.com>
* posix/regexec.c (extend_buffers): Don't allocate
twice as big state_log as needed. Don't modify pstr->valid_len
for mb_cur_max == 1 !icase !trans.
* posix/regcomp.c (free_bin_tree): Removed.
(create_tree): Add dfa argument. Don't call re_malloc for
each tree, instead allocate from str_tree_storage.
(re_dfa_add_tree_node): New function.
(free_dfa_content): Handle freeing if dfa->nodes == NULL
or dfa->state_table == NULL.
(re_compile_internal): Call free_dfa_content if init_dfa
fails. Call free_workarea_compile, re_string_destruct
and free_dfa_content for most of the other failure paths.
(init_dfa): Initialize str_tree_storage_idx.
Don't clear any fields on allocation failure.
(free_workarea_compile): Free str_tree_storage chunks
instead of free_bin_tree (dfa->str_tree).
(parse): Call re_dfa_add_tree_node instead of re_dfa_add_node
followed by create_tree. Add dfa argument to remaining
create_tree calls. Remove new_idx variable. Remove calls
to free_bin_tree.
(parse_reg_exp, parse_branch, parse_expression, parse_sub_exp,
parse_dup_op, parse_bracket_exp, build_charclass_op): Likewise.
(duplicate_tree): Remove calls to free_bin_tree, add dfa
argument to create_tree.
* posix/regex_internal.h (BIN_TREE_STORAGE_SIZE): Define.
(bin_tree_storage_t): New type.
(re_dfa_t): Add str_tree_storage and str_tree_storage_idx
fields.
* posix/Makefile (tests): Add bug-regex21.
(generated): Add bug-regex21-mem, bug-regex21.mtrace,
tst-rxspencer-mem and tst-rxspencer.mtrace.
(tests): Depend on $(objpfx)bug-regex21-mem
and $(objpfx)tst-rxspencer-mem.
(bug-regex21-ENV, tst-rxspencer-ENV): Set.
($(objpfx)bug-regex21-mem, $(objpfx)tst-rxspencer-mem): New.
* posix/tst-rxspencer.c (main): Add call to mtrace.
Free line at the end.
* posix/bug-regex21.c: New test.
* posix/regexec.c (get_subexp): After calling get_subexp_sub
2003-11-20 03:37:31 +08:00
|
|
|
|
#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;
|
2002-02-27 03:06:03 +08:00
|
|
|
|
|
|
|
|
|
#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)
|
2002-11-13 12:00:16 +08:00
|
|
|
|
#define IS_WIDE_WORD_CHAR(ch) (iswalnum (ch) || (ch) == L'_')
|
|
|
|
|
#define IS_WIDE_NEWLINE(ch) ((ch) == WIDE_NEWLINE_CHAR)
|
2002-02-27 03:06:03 +08:00
|
|
|
|
|
|
|
|
|
#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 *entrance_nodes;
|
|
|
|
|
struct re_dfastate_t **trtable;
|
|
|
|
|
struct re_dfastate_t **trtable_search;
|
|
|
|
|
/* If this state is a special state.
|
|
|
|
|
A state is a special state if the state is the halt state, or
|
|
|
|
|
a anchor. */
|
|
|
|
|
unsigned int context : 2;
|
|
|
|
|
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;
|
|
|
|
|
|
|
|
|
|
typedef struct
|
|
|
|
|
{
|
|
|
|
|
/* start <= node < end */
|
|
|
|
|
int start;
|
|
|
|
|
int end;
|
|
|
|
|
} re_subexp_t;
|
|
|
|
|
|
|
|
|
|
struct re_state_table_entry
|
|
|
|
|
{
|
|
|
|
|
int num;
|
|
|
|
|
int alloc;
|
2002-03-12 10:04:08 +08:00
|
|
|
|
re_dfastate_t **array;
|
2002-02-27 03:06:03 +08:00
|
|
|
|
};
|
|
|
|
|
|
2002-11-28 07:00:16 +08:00
|
|
|
|
/* 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;
|
|
|
|
|
|
2002-04-25 05:54:53 +08:00
|
|
|
|
struct re_backref_cache_entry
|
|
|
|
|
{
|
|
|
|
|
int node;
|
2002-09-28 13:28:44 +08:00
|
|
|
|
int str_idx;
|
|
|
|
|
int subexp_from;
|
|
|
|
|
int subexp_to;
|
2002-04-25 05:54:53 +08:00
|
|
|
|
int flag;
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
typedef struct
|
|
|
|
|
{
|
|
|
|
|
/* EFLAGS of the argument of regexec. */
|
|
|
|
|
int eflags;
|
|
|
|
|
/* Where the matching ends. */
|
|
|
|
|
int match_last;
|
2002-10-01 06:01:05 +08:00
|
|
|
|
int last_node;
|
2002-04-25 05:54:53 +08:00
|
|
|
|
/* The string object corresponding to the input string. */
|
|
|
|
|
re_string_t *input;
|
|
|
|
|
/* 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;
|
2002-09-28 13:28:44 +08:00
|
|
|
|
int max_mb_elem_len;
|
2002-11-28 07:00:16 +08:00
|
|
|
|
int nsub_tops;
|
|
|
|
|
int asub_tops;
|
|
|
|
|
re_sub_match_top_t **sub_tops;
|
2002-04-25 05:54:53 +08:00
|
|
|
|
} re_match_context_t;
|
|
|
|
|
|
2002-09-28 13:28:44 +08:00
|
|
|
|
typedef struct
|
|
|
|
|
{
|
|
|
|
|
int cur_bkref;
|
|
|
|
|
int cls_subexp_idx;
|
|
|
|
|
|
|
|
|
|
re_dfastate_t **sifted_states;
|
|
|
|
|
re_dfastate_t **limited_states;
|
|
|
|
|
|
|
|
|
|
re_node_set limits;
|
|
|
|
|
|
|
|
|
|
int last_node;
|
|
|
|
|
int last_str_idx;
|
|
|
|
|
int check_subexp;
|
|
|
|
|
} re_sift_context_t;
|
|
|
|
|
|
2002-10-01 06:01:05 +08:00
|
|
|
|
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;
|
|
|
|
|
};
|
|
|
|
|
|
2002-02-27 03:06:03 +08:00
|
|
|
|
struct re_dfa_t
|
|
|
|
|
{
|
|
|
|
|
re_bitset_ptr_t word_char;
|
|
|
|
|
re_subexp_t *subexps;
|
|
|
|
|
re_token_t *nodes;
|
|
|
|
|
int nodes_alloc;
|
|
|
|
|
int nodes_len;
|
|
|
|
|
int *nexts;
|
2002-12-17 18:58:04 +08:00
|
|
|
|
int *org_indices;
|
2002-02-27 03:06:03 +08:00
|
|
|
|
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;
|
Update.
2003-11-19 Jakub Jelinek <jakub@redhat.com>
* posix/regexec.c (extend_buffers): Don't allocate
twice as big state_log as needed. Don't modify pstr->valid_len
for mb_cur_max == 1 !icase !trans.
* posix/regcomp.c (free_bin_tree): Removed.
(create_tree): Add dfa argument. Don't call re_malloc for
each tree, instead allocate from str_tree_storage.
(re_dfa_add_tree_node): New function.
(free_dfa_content): Handle freeing if dfa->nodes == NULL
or dfa->state_table == NULL.
(re_compile_internal): Call free_dfa_content if init_dfa
fails. Call free_workarea_compile, re_string_destruct
and free_dfa_content for most of the other failure paths.
(init_dfa): Initialize str_tree_storage_idx.
Don't clear any fields on allocation failure.
(free_workarea_compile): Free str_tree_storage chunks
instead of free_bin_tree (dfa->str_tree).
(parse): Call re_dfa_add_tree_node instead of re_dfa_add_node
followed by create_tree. Add dfa argument to remaining
create_tree calls. Remove new_idx variable. Remove calls
to free_bin_tree.
(parse_reg_exp, parse_branch, parse_expression, parse_sub_exp,
parse_dup_op, parse_bracket_exp, build_charclass_op): Likewise.
(duplicate_tree): Remove calls to free_bin_tree, add dfa
argument to create_tree.
* posix/regex_internal.h (BIN_TREE_STORAGE_SIZE): Define.
(bin_tree_storage_t): New type.
(re_dfa_t): Add str_tree_storage and str_tree_storage_idx
fields.
* posix/Makefile (tests): Add bug-regex21.
(generated): Add bug-regex21-mem, bug-regex21.mtrace,
tst-rxspencer-mem and tst-rxspencer.mtrace.
(tests): Depend on $(objpfx)bug-regex21-mem
and $(objpfx)tst-rxspencer-mem.
(bug-regex21-ENV, tst-rxspencer-ENV): Set.
($(objpfx)bug-regex21-mem, $(objpfx)tst-rxspencer-mem): New.
* posix/tst-rxspencer.c (main): Add call to mtrace.
Free line at the end.
* posix/bug-regex21.c: New test.
* posix/regexec.c (get_subexp): After calling get_subexp_sub
2003-11-20 03:37:31 +08:00
|
|
|
|
bin_tree_t *str_tree;
|
|
|
|
|
bin_tree_storage_t *str_tree_storage;
|
|
|
|
|
int str_tree_storage_idx;
|
Update.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* io/ftw.c (NFTW_NEW_NAME, NFTW_OLD_NAME): Add prototypes.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/tst-regex.c (umemlen): New variable.
(test_expr): Add expectedicase argument. Test case insensitive
searches as well as backwards searches (case sensitive and
insensitive) too.
(run_test): Add icase argument. Use it to compute regcomp flags.
(run_test_backwards): New function.
(main): Cast read to size_t to avoid warning. Set umemlen.
Add expectedicase arguments to test_expr.
* posix/regex_internal.c (re_string_reconstruct): If is_utf8,
find previous character by walking back instead of converting
all chars from beginning.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/regex_internal.h (struct re_string_t): Add is_utf8
and mb_cur_max fields.
(struct re_dfa_t): Likewise. Reorder fields to make structure
smaller on 64-bit arches.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments.
(re_string_char_size_at, re_string_wchar_at): Use pstr->mb_cur_max
instead of MB_CUR_MAX.
* posix/regcomp.c (re_compile_fastmap_iter): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
(re_compile_internal): Pass new arguments to re_string_construct.
(init_dfa): Initialize mb_cur_max and is_utf8 fields.
(peek_token, peek_token_bracket): Use input->mb_cur_max instead
of MB_CUR_MAX.
(parse_expression, parse_bracket_exp, parse_charclass_op): Use
dfa->mb_cur_max instead of MB_CUR_MAX.
* posix/regex_internal.c (re_string_construct_common): Add
mb_cur_max and is_utf8 arguments. Initialize fields with them.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments, pass them to re_string_construct_common.
Use mb_cur_max instead of MB_CUR_MAX.
(re_string_realloc_buffers): Use pstr->mb_cur_max instead of
MB_CUR_MAX.
(re_string_reconstruct): Likewise.
(re_string_context_at): Use input->mb_cur_max instead of
MB_CUR_MAX.
(create_ci_newstate, create_cd_newstate): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
* posix/regexec.c (re_search_internal): Likewise.
Pass new arguments to re_string_allocate.
(check_matching, transit_state_sb): Use dfa->mb_cur_max instead of
MB_CUR_MAX.
(extend_buffers): Use pstr->mb_cur_max instead of MB_CUR_MAX.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/Makefile (tests): Add bug-regex19.
(bug-regex19-ENV): Add LOCPATH.
* posix/bug-regex19.c: New test.
2003-11-13 01:47:46 +08:00
|
|
|
|
|
|
|
|
|
/* number of subexpressions `re_nsub' is in regex_t. */
|
|
|
|
|
int subexps_alloc;
|
|
|
|
|
unsigned int state_hash_mask;
|
2002-02-27 03:06:03 +08:00
|
|
|
|
int states_alloc;
|
|
|
|
|
int init_node;
|
|
|
|
|
int nbackref; /* The number of backreference in this dfa. */
|
2002-11-28 07:00:16 +08:00
|
|
|
|
/* Bitmap expressing which backreference is used. */
|
|
|
|
|
unsigned int used_bkref_map;
|
2002-09-28 13:28:44 +08:00
|
|
|
|
unsigned int has_plural_match : 1;
|
2002-11-28 07:00:16 +08:00
|
|
|
|
/* If this dfa has "multibyte node", which is a backreference or
|
|
|
|
|
a node which can accept multibyte character or multi character
|
|
|
|
|
collating element. */
|
2002-02-27 03:06:03 +08:00
|
|
|
|
unsigned int has_mb_node : 1;
|
Update.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* io/ftw.c (NFTW_NEW_NAME, NFTW_OLD_NAME): Add prototypes.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/tst-regex.c (umemlen): New variable.
(test_expr): Add expectedicase argument. Test case insensitive
searches as well as backwards searches (case sensitive and
insensitive) too.
(run_test): Add icase argument. Use it to compute regcomp flags.
(run_test_backwards): New function.
(main): Cast read to size_t to avoid warning. Set umemlen.
Add expectedicase arguments to test_expr.
* posix/regex_internal.c (re_string_reconstruct): If is_utf8,
find previous character by walking back instead of converting
all chars from beginning.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/regex_internal.h (struct re_string_t): Add is_utf8
and mb_cur_max fields.
(struct re_dfa_t): Likewise. Reorder fields to make structure
smaller on 64-bit arches.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments.
(re_string_char_size_at, re_string_wchar_at): Use pstr->mb_cur_max
instead of MB_CUR_MAX.
* posix/regcomp.c (re_compile_fastmap_iter): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
(re_compile_internal): Pass new arguments to re_string_construct.
(init_dfa): Initialize mb_cur_max and is_utf8 fields.
(peek_token, peek_token_bracket): Use input->mb_cur_max instead
of MB_CUR_MAX.
(parse_expression, parse_bracket_exp, parse_charclass_op): Use
dfa->mb_cur_max instead of MB_CUR_MAX.
* posix/regex_internal.c (re_string_construct_common): Add
mb_cur_max and is_utf8 arguments. Initialize fields with them.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments, pass them to re_string_construct_common.
Use mb_cur_max instead of MB_CUR_MAX.
(re_string_realloc_buffers): Use pstr->mb_cur_max instead of
MB_CUR_MAX.
(re_string_reconstruct): Likewise.
(re_string_context_at): Use input->mb_cur_max instead of
MB_CUR_MAX.
(create_ci_newstate, create_cd_newstate): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
* posix/regexec.c (re_search_internal): Likewise.
Pass new arguments to re_string_allocate.
(check_matching, transit_state_sb): Use dfa->mb_cur_max instead of
MB_CUR_MAX.
(extend_buffers): Use pstr->mb_cur_max instead of MB_CUR_MAX.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/Makefile (tests): Add bug-regex19.
(bug-regex19-ENV): Add LOCPATH.
* posix/bug-regex19.c: New test.
2003-11-13 01:47:46 +08:00
|
|
|
|
unsigned int is_utf8 : 1;
|
2003-11-16 15:14:28 +08:00
|
|
|
|
unsigned int map_notascii : 1;
|
Update.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* io/ftw.c (NFTW_NEW_NAME, NFTW_OLD_NAME): Add prototypes.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/tst-regex.c (umemlen): New variable.
(test_expr): Add expectedicase argument. Test case insensitive
searches as well as backwards searches (case sensitive and
insensitive) too.
(run_test): Add icase argument. Use it to compute regcomp flags.
(run_test_backwards): New function.
(main): Cast read to size_t to avoid warning. Set umemlen.
Add expectedicase arguments to test_expr.
* posix/regex_internal.c (re_string_reconstruct): If is_utf8,
find previous character by walking back instead of converting
all chars from beginning.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/regex_internal.h (struct re_string_t): Add is_utf8
and mb_cur_max fields.
(struct re_dfa_t): Likewise. Reorder fields to make structure
smaller on 64-bit arches.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments.
(re_string_char_size_at, re_string_wchar_at): Use pstr->mb_cur_max
instead of MB_CUR_MAX.
* posix/regcomp.c (re_compile_fastmap_iter): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
(re_compile_internal): Pass new arguments to re_string_construct.
(init_dfa): Initialize mb_cur_max and is_utf8 fields.
(peek_token, peek_token_bracket): Use input->mb_cur_max instead
of MB_CUR_MAX.
(parse_expression, parse_bracket_exp, parse_charclass_op): Use
dfa->mb_cur_max instead of MB_CUR_MAX.
* posix/regex_internal.c (re_string_construct_common): Add
mb_cur_max and is_utf8 arguments. Initialize fields with them.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments, pass them to re_string_construct_common.
Use mb_cur_max instead of MB_CUR_MAX.
(re_string_realloc_buffers): Use pstr->mb_cur_max instead of
MB_CUR_MAX.
(re_string_reconstruct): Likewise.
(re_string_context_at): Use input->mb_cur_max instead of
MB_CUR_MAX.
(create_ci_newstate, create_cd_newstate): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
* posix/regexec.c (re_search_internal): Likewise.
Pass new arguments to re_string_allocate.
(check_matching, transit_state_sb): Use dfa->mb_cur_max instead of
MB_CUR_MAX.
(extend_buffers): Use pstr->mb_cur_max instead of MB_CUR_MAX.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/Makefile (tests): Add bug-regex19.
(bug-regex19-ENV): Add LOCPATH.
* posix/bug-regex19.c: New test.
2003-11-13 01:47:46 +08:00
|
|
|
|
int mb_cur_max;
|
Update.
2003-11-19 Jakub Jelinek <jakub@redhat.com>
* posix/regexec.c (extend_buffers): Don't allocate
twice as big state_log as needed. Don't modify pstr->valid_len
for mb_cur_max == 1 !icase !trans.
* posix/regcomp.c (free_bin_tree): Removed.
(create_tree): Add dfa argument. Don't call re_malloc for
each tree, instead allocate from str_tree_storage.
(re_dfa_add_tree_node): New function.
(free_dfa_content): Handle freeing if dfa->nodes == NULL
or dfa->state_table == NULL.
(re_compile_internal): Call free_dfa_content if init_dfa
fails. Call free_workarea_compile, re_string_destruct
and free_dfa_content for most of the other failure paths.
(init_dfa): Initialize str_tree_storage_idx.
Don't clear any fields on allocation failure.
(free_workarea_compile): Free str_tree_storage chunks
instead of free_bin_tree (dfa->str_tree).
(parse): Call re_dfa_add_tree_node instead of re_dfa_add_node
followed by create_tree. Add dfa argument to remaining
create_tree calls. Remove new_idx variable. Remove calls
to free_bin_tree.
(parse_reg_exp, parse_branch, parse_expression, parse_sub_exp,
parse_dup_op, parse_bracket_exp, build_charclass_op): Likewise.
(duplicate_tree): Remove calls to free_bin_tree, add dfa
argument to create_tree.
* posix/regex_internal.h (BIN_TREE_STORAGE_SIZE): Define.
(bin_tree_storage_t): New type.
(re_dfa_t): Add str_tree_storage and str_tree_storage_idx
fields.
* posix/Makefile (tests): Add bug-regex21.
(generated): Add bug-regex21-mem, bug-regex21.mtrace,
tst-rxspencer-mem and tst-rxspencer.mtrace.
(tests): Depend on $(objpfx)bug-regex21-mem
and $(objpfx)tst-rxspencer-mem.
(bug-regex21-ENV, tst-rxspencer-ENV): Set.
($(objpfx)bug-regex21-mem, $(objpfx)tst-rxspencer-mem): New.
* posix/tst-rxspencer.c (main): Add call to mtrace.
Free line at the end.
* posix/bug-regex21.c: New test.
* posix/regexec.c (get_subexp): After calling get_subexp_sub
2003-11-20 03:37:31 +08:00
|
|
|
|
#ifdef DEBUG
|
|
|
|
|
char* re_str;
|
|
|
|
|
#endif
|
2002-02-27 03:06:03 +08:00
|
|
|
|
};
|
|
|
|
|
|
2003-11-13 03:09:20 +08:00
|
|
|
|
#ifndef RE_NO_INTERNAL_PROTOTYPES
|
2002-02-27 03:06:03 +08:00
|
|
|
|
static reg_errcode_t re_node_set_alloc (re_node_set *set, int size);
|
|
|
|
|
static reg_errcode_t re_node_set_init_1 (re_node_set *set, int elem);
|
|
|
|
|
static reg_errcode_t re_node_set_init_2 (re_node_set *set, int elem1,
|
2002-11-07 04:36:47 +08:00
|
|
|
|
int elem2);
|
2002-02-27 03:06:03 +08:00
|
|
|
|
#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,
|
2002-11-07 04:36:47 +08:00
|
|
|
|
const re_node_set *src);
|
2002-02-27 03:06:03 +08:00
|
|
|
|
static reg_errcode_t re_node_set_add_intersect (re_node_set *dest,
|
2002-11-07 04:36:47 +08:00
|
|
|
|
const re_node_set *src1,
|
|
|
|
|
const re_node_set *src2);
|
2002-02-27 03:06:03 +08:00
|
|
|
|
static reg_errcode_t re_node_set_init_union (re_node_set *dest,
|
2002-11-07 04:36:47 +08:00
|
|
|
|
const re_node_set *src1,
|
|
|
|
|
const re_node_set *src2);
|
2002-02-27 03:06:03 +08:00
|
|
|
|
static reg_errcode_t re_node_set_merge (re_node_set *dest,
|
2002-11-07 04:36:47 +08:00
|
|
|
|
const re_node_set *src);
|
2002-02-27 03:06:03 +08:00
|
|
|
|
static int re_node_set_insert (re_node_set *set, int elem);
|
|
|
|
|
static int re_node_set_compare (const re_node_set *set1,
|
2002-11-07 04:36:47 +08:00
|
|
|
|
const re_node_set *set2);
|
2002-02-27 03:06:03 +08:00
|
|
|
|
static int re_node_set_contains (const re_node_set *set, int elem);
|
|
|
|
|
static void re_node_set_remove_at (re_node_set *set, int idx);
|
2002-10-12 16:34:26 +08:00
|
|
|
|
#define re_node_set_remove(set,id) \
|
|
|
|
|
(re_node_set_remove_at (set, re_node_set_contains (set, id) - 1))
|
2002-02-27 03:06:03 +08:00
|
|
|
|
#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, int mode);
|
2002-02-28 15:43:13 +08:00
|
|
|
|
static re_dfastate_t *re_acquire_state (reg_errcode_t *err, re_dfa_t *dfa,
|
2002-11-07 04:36:47 +08:00
|
|
|
|
const re_node_set *nodes);
|
2002-02-28 15:43:13 +08:00
|
|
|
|
static re_dfastate_t *re_acquire_state_context (reg_errcode_t *err,
|
2002-11-07 04:36:47 +08:00
|
|
|
|
re_dfa_t *dfa,
|
|
|
|
|
const re_node_set *nodes,
|
|
|
|
|
unsigned int context);
|
|
|
|
|
static void free_state (re_dfastate_t *state);
|
2003-11-13 03:09:20 +08:00
|
|
|
|
#endif
|
2002-02-27 03:06:03 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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;
|
2002-09-11 02:40:35 +08:00
|
|
|
|
unsigned char *name;
|
2002-02-27 03:06:03 +08:00
|
|
|
|
wchar_t wch;
|
|
|
|
|
} opr;
|
|
|
|
|
} bracket_elem_t;
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
/* Inline functions for bitset operation. */
|
|
|
|
|
static inline void
|
|
|
|
|
bitset_not (set)
|
|
|
|
|
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 (dest, src)
|
|
|
|
|
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 (dest, src)
|
|
|
|
|
bitset dest;
|
|
|
|
|
const bitset src;
|
|
|
|
|
{
|
|
|
|
|
int i;
|
|
|
|
|
for (i = 0; i < BITSET_UINTS; ++i)
|
|
|
|
|
dest[i] |= ~src[i];
|
|
|
|
|
}
|
|
|
|
|
|
2003-11-13 03:09:20 +08:00
|
|
|
|
#if defined RE_ENABLE_I18N && !defined RE_NO_INTERNAL_PROTOTYPES
|
2002-02-27 03:06:03 +08:00
|
|
|
|
/* Inline functions for re_string. */
|
|
|
|
|
static inline int
|
|
|
|
|
re_string_char_size_at (pstr, idx)
|
|
|
|
|
const re_string_t *pstr;
|
|
|
|
|
int idx;
|
|
|
|
|
{
|
|
|
|
|
int byte_idx;
|
Update.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* io/ftw.c (NFTW_NEW_NAME, NFTW_OLD_NAME): Add prototypes.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/tst-regex.c (umemlen): New variable.
(test_expr): Add expectedicase argument. Test case insensitive
searches as well as backwards searches (case sensitive and
insensitive) too.
(run_test): Add icase argument. Use it to compute regcomp flags.
(run_test_backwards): New function.
(main): Cast read to size_t to avoid warning. Set umemlen.
Add expectedicase arguments to test_expr.
* posix/regex_internal.c (re_string_reconstruct): If is_utf8,
find previous character by walking back instead of converting
all chars from beginning.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/regex_internal.h (struct re_string_t): Add is_utf8
and mb_cur_max fields.
(struct re_dfa_t): Likewise. Reorder fields to make structure
smaller on 64-bit arches.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments.
(re_string_char_size_at, re_string_wchar_at): Use pstr->mb_cur_max
instead of MB_CUR_MAX.
* posix/regcomp.c (re_compile_fastmap_iter): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
(re_compile_internal): Pass new arguments to re_string_construct.
(init_dfa): Initialize mb_cur_max and is_utf8 fields.
(peek_token, peek_token_bracket): Use input->mb_cur_max instead
of MB_CUR_MAX.
(parse_expression, parse_bracket_exp, parse_charclass_op): Use
dfa->mb_cur_max instead of MB_CUR_MAX.
* posix/regex_internal.c (re_string_construct_common): Add
mb_cur_max and is_utf8 arguments. Initialize fields with them.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments, pass them to re_string_construct_common.
Use mb_cur_max instead of MB_CUR_MAX.
(re_string_realloc_buffers): Use pstr->mb_cur_max instead of
MB_CUR_MAX.
(re_string_reconstruct): Likewise.
(re_string_context_at): Use input->mb_cur_max instead of
MB_CUR_MAX.
(create_ci_newstate, create_cd_newstate): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
* posix/regexec.c (re_search_internal): Likewise.
Pass new arguments to re_string_allocate.
(check_matching, transit_state_sb): Use dfa->mb_cur_max instead of
MB_CUR_MAX.
(extend_buffers): Use pstr->mb_cur_max instead of MB_CUR_MAX.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/Makefile (tests): Add bug-regex19.
(bug-regex19-ENV): Add LOCPATH.
* posix/bug-regex19.c: New test.
2003-11-13 01:47:46 +08:00
|
|
|
|
if (pstr->mb_cur_max == 1)
|
2002-02-27 03:06:03 +08:00
|
|
|
|
return 1;
|
2003-11-11 14:58:52 +08:00
|
|
|
|
for (byte_idx = 1; idx + byte_idx < pstr->valid_len; ++byte_idx)
|
2002-02-27 03:06:03 +08:00
|
|
|
|
if (pstr->wcs[idx + byte_idx] != WEOF)
|
|
|
|
|
break;
|
|
|
|
|
return byte_idx;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static inline wint_t
|
|
|
|
|
re_string_wchar_at (pstr, idx)
|
|
|
|
|
const re_string_t *pstr;
|
|
|
|
|
int idx;
|
|
|
|
|
{
|
Update.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* io/ftw.c (NFTW_NEW_NAME, NFTW_OLD_NAME): Add prototypes.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/tst-regex.c (umemlen): New variable.
(test_expr): Add expectedicase argument. Test case insensitive
searches as well as backwards searches (case sensitive and
insensitive) too.
(run_test): Add icase argument. Use it to compute regcomp flags.
(run_test_backwards): New function.
(main): Cast read to size_t to avoid warning. Set umemlen.
Add expectedicase arguments to test_expr.
* posix/regex_internal.c (re_string_reconstruct): If is_utf8,
find previous character by walking back instead of converting
all chars from beginning.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/regex_internal.h (struct re_string_t): Add is_utf8
and mb_cur_max fields.
(struct re_dfa_t): Likewise. Reorder fields to make structure
smaller on 64-bit arches.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments.
(re_string_char_size_at, re_string_wchar_at): Use pstr->mb_cur_max
instead of MB_CUR_MAX.
* posix/regcomp.c (re_compile_fastmap_iter): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
(re_compile_internal): Pass new arguments to re_string_construct.
(init_dfa): Initialize mb_cur_max and is_utf8 fields.
(peek_token, peek_token_bracket): Use input->mb_cur_max instead
of MB_CUR_MAX.
(parse_expression, parse_bracket_exp, parse_charclass_op): Use
dfa->mb_cur_max instead of MB_CUR_MAX.
* posix/regex_internal.c (re_string_construct_common): Add
mb_cur_max and is_utf8 arguments. Initialize fields with them.
(re_string_allocate, re_string_construct): Add mb_cur_max and
is_utf8 arguments, pass them to re_string_construct_common.
Use mb_cur_max instead of MB_CUR_MAX.
(re_string_realloc_buffers): Use pstr->mb_cur_max instead of
MB_CUR_MAX.
(re_string_reconstruct): Likewise.
(re_string_context_at): Use input->mb_cur_max instead of
MB_CUR_MAX.
(create_ci_newstate, create_cd_newstate): Use dfa->mb_cur_max
instead of MB_CUR_MAX.
* posix/regexec.c (re_search_internal): Likewise.
Pass new arguments to re_string_allocate.
(check_matching, transit_state_sb): Use dfa->mb_cur_max instead of
MB_CUR_MAX.
(extend_buffers): Use pstr->mb_cur_max instead of MB_CUR_MAX.
2003-11-12 Jakub Jelinek <jakub@redhat.com>
* posix/Makefile (tests): Add bug-regex19.
(bug-regex19-ENV): Add LOCPATH.
* posix/bug-regex19.c: New test.
2003-11-13 01:47:46 +08:00
|
|
|
|
if (pstr->mb_cur_max == 1)
|
2002-02-27 03:06:03 +08:00
|
|
|
|
return (wint_t) pstr->mbs[idx];
|
|
|
|
|
return (wint_t) pstr->wcs[idx];
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
static int
|
|
|
|
|
re_string_elem_size_at (pstr, idx)
|
|
|
|
|
const re_string_t *pstr;
|
|
|
|
|
int idx;
|
|
|
|
|
{
|
|
|
|
|
#ifdef _LIBC
|
2002-09-11 02:40:35 +08:00
|
|
|
|
const unsigned char *p, *extra;
|
2002-02-27 03:06:03 +08:00
|
|
|
|
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);
|
2002-09-11 02:40:35 +08:00
|
|
|
|
extra = (const unsigned char *)
|
2002-11-07 04:36:47 +08:00
|
|
|
|
_NL_CURRENT (LC_COLLATE, _NL_COLLATE_EXTRAMB);
|
2002-02-27 03:06:03 +08:00
|
|
|
|
indirect = (const int32_t *) _NL_CURRENT (LC_COLLATE,
|
|
|
|
|
_NL_COLLATE_INDIRECTMB);
|
|
|
|
|
p = pstr->mbs + idx;
|
2002-09-11 02:40:35 +08:00
|
|
|
|
tmp = findidx (&p);
|
2002-09-05 18:28:51 +08:00
|
|
|
|
return p - pstr->mbs - idx;
|
2002-02-27 03:06:03 +08:00
|
|
|
|
}
|
|
|
|
|
else
|
|
|
|
|
#endif /* _LIBC */
|
|
|
|
|
return 1;
|
|
|
|
|
}
|
|
|
|
|
#endif /* RE_ENABLE_I18N */
|
|
|
|
|
|
|
|
|
|
#endif /* _REGEX_INTERNAL_H */
|