rpm/grep
SHA256
1
0
Fork 0
forked from pool/grep
Code Pull Requests Activity

OBS-URL: https://build.opensuse.org/package/show/openSUSE:Factory/grep?expand=0&rev=8

Browse Source
This commit is contained in:
OBS User unknown 2008-05-29 13:20:52 +00:00 committed by Git OBS Bridge
parent f30f3390a6
commit 5b8d935d00
3 changed files with 514 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

518
grep-i18n-speedup.diff
View File

@ -1,24 +1,498 @@
--- lib/Makefile.am
+++ lib/Makefile.am
@@ -9,12 +9,12 @@ INCLUDES = -I.. -I$(srcdir) -I../intl
DEFS = -DLIBDIR=\"$(libdir)\" @DEFS@
libgreputils_a_SOURCES = \
- closeout.c error.c exclude.c hard-locale.c \
+ closeout.c error.c exclude.c hard-locale.c mbchar.c \
isdir.c obstack.c quotearg.c savedir.c xmalloc.c xstrtol.c xstrtoumax.c
libgreputils_a_LIBADD = @LIBOBJS@ @ALLOCA@
noinst_HEADERS = \
- closeout.h error.h exclude.h fnmatch.h getopt.h \
+ closeout.h error.h exclude.h fnmatch.h getopt.h mbchar.h \
hard-locale.h obstack.h quotearg.h savedir.h xalloc.h xstrtol.h
EXTRA_DIST = strtol.c malloc.c realloc.c
--- lib/mbchar.c
+++ lib/mbchar.c
@@ -0,0 +1,35 @@
+/* Copyright (C) 2001, 2006 Free Software Foundation, Inc.
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3 of the License, 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, see <http://www.gnu.org/licenses/>. */
+
+
+#include <config.h>
+
+#include <limits.h>
+
+#include "mbchar.h"
+
+#if IS_BASIC_ASCII
+
+/* Bit table of characters in the ISO C "basic character set". */
+const unsigned int is_basic_table [UCHAR_MAX / 32 + 1] =
+{
+ 0x00001a00, /* '\t' '\v' '\f' */
+ 0xffffffef, /* ' '...'#' '%'...'?' */
+ 0xfffffffe, /* 'A'...'Z' '[' '\\' ']' '^' '_' */
+ 0x7ffffffe /* 'a'...'z' '{' '|' '}' '~' */
+ /* The remaining bits are 0. */
+};
+
+#endif /* IS_BASIC_ASCII */
--- lib/mbchar.h
+++ lib/mbchar.h
@@ -0,0 +1,350 @@
+/* Multibyte character data type.
+ Copyright (C) 2001, 2005-2007 Free Software Foundation, Inc.
+
+ This program is free software: you can redistribute it and/or modify
+ it under the terms of the GNU General Public License as published by
+ the Free Software Foundation; either version 3 of the License, 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, see <http://www.gnu.org/licenses/>. */
+
+/* Written by Bruno Haible <bruno@clisp.org>. */
+
+/* A multibyte character is a short subsequence of a char* string,
+ representing a single wide character.
+
+ We use multibyte characters instead of wide characters because of
+ the following goals:
+ 1) correct multibyte handling, i.e. operate according to the LC_CTYPE
+ locale,
+ 2) ease of maintenance, i.e. the maintainer needs not know all details
+ of the ISO C 99 standard,
+ 3) don't fail grossly if the input is not in the encoding set by the
+ locale, because often different encodings are in use in the same
+ countries (ISO-8859-1/UTF-8, EUC-JP/Shift_JIS, ...),
+ 4) fast in the case of ASCII characters,
+ 5) portability, i.e. don't make unportable assumptions about wchar_t.
+
+ Multibyte characters are only accessed through the mb* macros.
+
+ mb_ptr (mbc)
+ return a pointer to the beginning of the multibyte sequence.
+
+ mb_len (mbc)
+ returns the number of bytes occupied by the multibyte sequence.
+ Always > 0.
+
+ mb_iseq (mbc, sc)
+ returns true if mbc is the standard ASCII character sc.
+
+ mb_isnul (mbc)
+ returns true if mbc is the nul character.
+
+ mb_cmp (mbc1, mbc2)
+ returns a positive, zero, or negative value depending on whether mbc1
+ sorts after, same or before mbc2.
+
+ mb_casecmp (mbc1, mbc2)
+ returns a positive, zero, or negative value depending on whether mbc1
+ sorts after, same or before mbc2, modulo upper/lowercase conversion.
+
+ mb_equal (mbc1, mbc2)
+ returns true if mbc1 and mbc2 are equal.
+
+ mb_caseequal (mbc1, mbc2)
+ returns true if mbc1 and mbc2 are equal modulo upper/lowercase conversion.
+
+ mb_isalnum (mbc)
+ returns true if mbc is alphanumeric.
+
+ mb_isalpha (mbc)
+ returns true if mbc is alphabetic.
+
+ mb_isascii(mbc)
+ returns true if mbc is plain ASCII.
+
+ mb_isblank (mbc)
+ returns true if mbc is a blank.
+
+ mb_iscntrl (mbc)
+ returns true if mbc is a control character.
+
+ mb_isdigit (mbc)
+ returns true if mbc is a decimal digit.
+
+ mb_isgraph (mbc)
+ returns true if mbc is a graphic character.
+
+ mb_islower (mbc)
+ returns true if mbc is lowercase.
+
+ mb_isprint (mbc)
+ returns true if mbc is a printable character.
+
+ mb_ispunct (mbc)
+ returns true if mbc is a punctuation character.
+
+ mb_isspace (mbc)
+ returns true if mbc is a space character.
+
+ mb_isupper (mbc)
+ returns true if mbc is uppercase.
+
+ mb_isxdigit (mbc)
+ returns true if mbc is a hexadecimal digit.
+
+ mb_width (mbc)
+ returns the number of columns on the output device occupied by mbc.
+ Always >= 0.
+
+ mb_putc (mbc, stream)
+ outputs mbc on stream, a byte oriented FILE stream opened for output.
+
+ mb_setascii (&mbc, sc)
+ assigns the standard ASCII character sc to mbc.
+
+ mb_copy (&destmbc, &srcmbc)
+ copies srcmbc to destmbc.
+
+ Here are the function prototypes of the macros.
+
+ extern const char * mb_ptr (const mbchar_t mbc);
+ extern size_t mb_len (const mbchar_t mbc);
+ extern bool mb_iseq (const mbchar_t mbc, char sc);
+ extern bool mb_isnul (const mbchar_t mbc);
+ extern int mb_cmp (const mbchar_t mbc1, const mbchar_t mbc2);
+ extern int mb_casecmp (const mbchar_t mbc1, const mbchar_t mbc2);
+ extern bool mb_equal (const mbchar_t mbc1, const mbchar_t mbc2);
+ extern bool mb_caseequal (const mbchar_t mbc1, const mbchar_t mbc2);
+ extern bool mb_isalnum (const mbchar_t mbc);
+ extern bool mb_isalpha (const mbchar_t mbc);
+ extern bool mb_isascii (const mbchar_t mbc);
+ extern bool mb_isblank (const mbchar_t mbc);
+ extern bool mb_iscntrl (const mbchar_t mbc);
+ extern bool mb_isdigit (const mbchar_t mbc);
+ extern bool mb_isgraph (const mbchar_t mbc);
+ extern bool mb_islower (const mbchar_t mbc);
+ extern bool mb_isprint (const mbchar_t mbc);
+ extern bool mb_ispunct (const mbchar_t mbc);
+ extern bool mb_isspace (const mbchar_t mbc);
+ extern bool mb_isupper (const mbchar_t mbc);
+ extern bool mb_isxdigit (const mbchar_t mbc);
+ extern int mb_width (const mbchar_t mbc);
+ extern void mb_putc (const mbchar_t mbc, FILE *stream);
+ extern void mb_setascii (mbchar_t *new, char sc);
+ extern void mb_copy (mbchar_t *new, const mbchar_t *old);
+ */
+
+#ifndef _MBCHAR_H
+#define _MBCHAR_H 1
+
+#include <stdbool.h>
+#include <string.h>
+
+/* Tru64 with Desktop Toolkit C has a bug: <stdio.h> must be included before
+ <wchar.h>.
+ BSD/OS 4.1 has a bug: <stdio.h> and <time.h> must be included before
+ <wchar.h>. */
+#include <stdio.h>
+#include <time.h>
+#include <wchar.h>
+#include <wctype.h>
+
+#define MBCHAR_BUF_SIZE 24
+
+struct mbchar
+{
+ const char *ptr; /* pointer to current character */
+ size_t bytes; /* number of bytes of current character, > 0 */
+ bool wc_valid; /* true if wc is a valid wide character */
+ wchar_t wc; /* if wc_valid: the current character */
+ char buf[MBCHAR_BUF_SIZE]; /* room for the bytes, used for file input only */
+};
+
+/* EOF (not a real character) is represented with bytes = 0 and
+ wc_valid = false. */
+
+typedef struct mbchar mbchar_t;
+
+/* Access the current character. */
+#define mb_ptr(mbc) ((mbc).ptr)
+#define mb_len(mbc) ((mbc).bytes)
+
+/* Comparison of characters. */
+#define mb_iseq(mbc, sc) ((mbc).wc_valid && (mbc).wc == (sc))
+#define mb_isnul(mbc) ((mbc).wc_valid && (mbc).wc == 0)
+#define mb_cmp(mbc1, mbc2) \
+ ((mbc1).wc_valid \
+ ? ((mbc2).wc_valid \
+ ? (int) (mbc1).wc - (int) (mbc2).wc \
+ : -1) \
+ : ((mbc2).wc_valid \
+ ? 1 \
+ : (mbc1).bytes == (mbc2).bytes \
+ ? memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) \
+ : (mbc1).bytes < (mbc2).bytes \
+ ? (memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) > 0 ? 1 : -1) \
+ : (memcmp ((mbc1).ptr, (mbc2).ptr, (mbc2).bytes) >= 0 ? 1 : -1)))
+#define mb_casecmp(mbc1, mbc2) \
+ ((mbc1).wc_valid \
+ ? ((mbc2).wc_valid \
+ ? (int) towlower ((mbc1).wc) - (int) towlower ((mbc2).wc) \
+ : -1) \
+ : ((mbc2).wc_valid \
+ ? 1 \
+ : (mbc1).bytes == (mbc2).bytes \
+ ? memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) \
+ : (mbc1).bytes < (mbc2).bytes \
+ ? (memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) > 0 ? 1 : -1) \
+ : (memcmp ((mbc1).ptr, (mbc2).ptr, (mbc2).bytes) >= 0 ? 1 : -1)))
+#define mb_equal(mbc1, mbc2) \
+ ((mbc1).wc_valid && (mbc2).wc_valid \
+ ? (mbc1).wc == (mbc2).wc \
+ : (mbc1).bytes == (mbc2).bytes \
+ && memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) == 0)
+#define mb_caseequal(mbc1, mbc2) \
+ ((mbc1).wc_valid && (mbc2).wc_valid \
+ ? towlower ((mbc1).wc) == towlower ((mbc2).wc) \
+ : (mbc1).bytes == (mbc2).bytes \
+ && memcmp ((mbc1).ptr, (mbc2).ptr, (mbc1).bytes) == 0)
+
+/* <ctype.h>, <wctype.h> classification. */
+#define mb_isascii(mbc) \
+ ((mbc).wc_valid && (mbc).wc >= 0 && (mbc).wc <= 127)
+#define mb_isalnum(mbc) ((mbc).wc_valid && iswalnum ((mbc).wc))
+#define mb_isalpha(mbc) ((mbc).wc_valid && iswalpha ((mbc).wc))
+#define mb_isblank(mbc) ((mbc).wc_valid && iswblank ((mbc).wc))
+#define mb_iscntrl(mbc) ((mbc).wc_valid && iswcntrl ((mbc).wc))
+#define mb_isdigit(mbc) ((mbc).wc_valid && iswdigit ((mbc).wc))
+#define mb_isgraph(mbc) ((mbc).wc_valid && iswgraph ((mbc).wc))
+#define mb_islower(mbc) ((mbc).wc_valid && iswlower ((mbc).wc))
+#define mb_isprint(mbc) ((mbc).wc_valid && iswprint ((mbc).wc))
+#define mb_ispunct(mbc) ((mbc).wc_valid && iswpunct ((mbc).wc))
+#define mb_isspace(mbc) ((mbc).wc_valid && iswspace ((mbc).wc))
+#define mb_isupper(mbc) ((mbc).wc_valid && iswupper ((mbc).wc))
+#define mb_isxdigit(mbc) ((mbc).wc_valid && iswxdigit ((mbc).wc))
+
+/* Extra <wchar.h> function. */
+
+/* Unprintable characters appear as a small box of width 1. */
+#define MB_UNPRINTABLE_WIDTH 1
+
+static inline int
+mb_width_aux (wint_t wc)
+{
+ int w = wcwidth (wc);
+ /* For unprintable characters, arbitrarily return 0 for control characters
+ and MB_UNPRINTABLE_WIDTH otherwise. */
+ return (w >= 0 ? w : iswcntrl (wc) ? 0 : MB_UNPRINTABLE_WIDTH);
+}
+
+#define mb_width(mbc) \
+ ((mbc).wc_valid ? mb_width_aux ((mbc).wc) : MB_UNPRINTABLE_WIDTH)
+
+/* Output. */
+#define mb_putc(mbc, stream) fwrite ((mbc).ptr, 1, (mbc).bytes, (stream))
+
+/* Assignment. */
+#define mb_setascii(mbc, sc) \
+ ((mbc)->ptr = (mbc)->buf, (mbc)->bytes = 1, (mbc)->wc_valid = 1, \
+ (mbc)->wc = (mbc)->buf[0] = (sc))
+
+/* Copying a character. */
+static inline void
+mb_copy (mbchar_t *new_mbc, const mbchar_t *old_mbc)
+{
+ if (old_mbc->ptr == &old_mbc->buf[0])
+ {
+ memcpy (&new_mbc->buf[0], &old_mbc->buf[0], old_mbc->bytes);
+ new_mbc->ptr = &new_mbc->buf[0];
+ }
+ else
+ new_mbc->ptr = old_mbc->ptr;
+ new_mbc->bytes = old_mbc->bytes;
+ if ((new_mbc->wc_valid = old_mbc->wc_valid))
+ new_mbc->wc = old_mbc->wc;
+}
+
+
+/* is_basic(c) tests whether the single-byte character c is in the
+ ISO C "basic character set".
+ This is a convenience function, and is in this file only to share code
+ between mbiter_multi.h and mbfile_multi.h. */
+#if (' ' == 32) && ('!' == 33) && ('"' == 34) && ('#' == 35) \
+ && ('%' == 37) && ('&' == 38) && ('\'' == 39) && ('(' == 40) \
+ && (')' == 41) && ('*' == 42) && ('+' == 43) && (',' == 44) \
+ && ('-' == 45) && ('.' == 46) && ('/' == 47) && ('0' == 48) \
+ && ('1' == 49) && ('2' == 50) && ('3' == 51) && ('4' == 52) \
+ && ('5' == 53) && ('6' == 54) && ('7' == 55) && ('8' == 56) \
+ && ('9' == 57) && (':' == 58) && (';' == 59) && ('<' == 60) \
+ && ('=' == 61) && ('>' == 62) && ('?' == 63) && ('A' == 65) \
+ && ('B' == 66) && ('C' == 67) && ('D' == 68) && ('E' == 69) \
+ && ('F' == 70) && ('G' == 71) && ('H' == 72) && ('I' == 73) \
+ && ('J' == 74) && ('K' == 75) && ('L' == 76) && ('M' == 77) \
+ && ('N' == 78) && ('O' == 79) && ('P' == 80) && ('Q' == 81) \
+ && ('R' == 82) && ('S' == 83) && ('T' == 84) && ('U' == 85) \
+ && ('V' == 86) && ('W' == 87) && ('X' == 88) && ('Y' == 89) \
+ && ('Z' == 90) && ('[' == 91) && ('\\' == 92) && (']' == 93) \
+ && ('^' == 94) && ('_' == 95) && ('a' == 97) && ('b' == 98) \
+ && ('c' == 99) && ('d' == 100) && ('e' == 101) && ('f' == 102) \
+ && ('g' == 103) && ('h' == 104) && ('i' == 105) && ('j' == 106) \
+ && ('k' == 107) && ('l' == 108) && ('m' == 109) && ('n' == 110) \
+ && ('o' == 111) && ('p' == 112) && ('q' == 113) && ('r' == 114) \
+ && ('s' == 115) && ('t' == 116) && ('u' == 117) && ('v' == 118) \
+ && ('w' == 119) && ('x' == 120) && ('y' == 121) && ('z' == 122) \
+ && ('{' == 123) && ('|' == 124) && ('}' == 125) && ('~' == 126)
+/* The character set is ISO-646, not EBCDIC. */
+# define IS_BASIC_ASCII 1
+
+extern const unsigned int is_basic_table[];
+
+static inline bool
+is_basic (char c)
+{
+ return (is_basic_table [(unsigned char) c >> 5] >> ((unsigned char) c & 31))
+ & 1;
+}
+
+#else
+
+static inline bool
+is_basic (char c)
+{
+ switch (c)
+ {
+ case '\t': case '\v': case '\f':
+ case ' ': case '!': case '"': case '#': case '%':
+ case '&': case '\'': case '(': case ')': case '*':
+ case '+': case ',': case '-': case '.': case '/':
+ case '0': case '1': case '2': case '3': case '4':
+ case '5': case '6': case '7': case '8': case '9':
+ case ':': case ';': case '<': case '=': case '>':
+ case '?':
+ case 'A': case 'B': case 'C': case 'D': case 'E':
+ case 'F': case 'G': case 'H': case 'I': case 'J':
+ case 'K': case 'L': case 'M': case 'N': case 'O':
+ case 'P': case 'Q': case 'R': case 'S': case 'T':
+ case 'U': case 'V': case 'W': case 'X': case 'Y':
+ case 'Z':
+ case '[': case '\\': case ']': case '^': case '_':
+ case 'a': case 'b': case 'c': case 'd': case 'e':
+ case 'f': case 'g': case 'h': case 'i': case 'j':
+ case 'k': case 'l': case 'm': case 'n': case 'o':
+ case 'p': case 'q': case 'r': case 's': case 't':
+ case 'u': case 'v': case 'w': case 'x': case 'y':
+ case 'z': case '{': case '|': case '}': case '~':
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+#endif
+
+#endif /* _MBCHAR_H */
--- src/search.c --- src/search.c
+++ src/search.c +++ src/search.c
@@ -140,7 +140,7 @@ kwsmusts (void) @@ -43,6 +43,7 @@
#ifdef HAVE_LIBPCRE
# include <pcre.h>
#endif
+#include "mbchar.h"
#define NCHAR (UCHAR_MAX + 1)
@@ -140,40 +141,62 @@ kwsmusts (void)
are not single byte character nor the first byte of a multibyte are not single byte character nor the first byte of a multibyte
character. Caller must free the array. */ character. Caller must free the array. */
static char* static char*
-check_multibyte_string(char const *buf, size_t size) -check_multibyte_string(char const *buf, size_t size)
+check_multibyte_string(char const *buf, size_t size, int case_convert) +check_multibyte_string(char const *buf, size_t size, int case_convert)
{ {
char *mb_properties = xmalloc(size); - char *mb_properties = xmalloc(size);
+ char *mb_properties = NULL;
mbstate_t cur_state; mbstate_t cur_state;
@@ -161,7 +161,7 @@ check_multibyte_string(char const *buf, wchar_t wc;
We treat it as a single byte character. */ int i;
+ int in_shift = 0;
memset(&cur_state, 0, sizeof(mbstate_t));
- memset(mb_properties, 0, sizeof(char)*size);
for (i = 0; i < size ;)
{
size_t mbclen;
- mbclen = mbrtowc(&wc, buf + i, size - i, &cur_state);
- if (mbclen == (size_t) -1 || mbclen == (size_t) -2 || mbclen == 0)
+ if (!in_shift && is_basic (buf[i]))
{
- /* An invalid sequence, or a truncated multibyte character.
- We treat it as a single byte character. */
mbclen = 1; mbclen = 1;
+ wc = buf[i];
+ if (case_convert && iswupper ((wint_t)wc))
+ wc = towlower ((wint_t) wc);
+ }
+ else
+ {
+ in_shift = true;
+ mbclen = mbrtowc(&wc, buf + i, size - i, &cur_state);
+
+ if (mbclen == (size_t) -1 || mbclen == (size_t) -2 || mbclen == 0)
+ {
+ /* An invalid sequence, or a truncated multibyte character.
+ We treat it as a single byte character. */
+ mbclen = 1;
+ }
+ else if (case_convert)
+ {
+ if (iswupper((wint_t)wc))
+ {
+ wc = towlower((wint_t)wc);
+ wcrtomb(buf + i, wc, &cur_state);
+ }
+ }
+ if (mbsinit (&cur_state))
+ in_shift = false;
} }
- else if (match_icase) - else if (match_icase)
+ else if (case_convert) + if (mbclen != 1)
{ {
if (iswupper((wint_t)wc)) - if (iswupper((wint_t)wc))
+ if (!mb_properties)
{ {
@@ -327,9 +327,8 @@ EXECUTE_FCT(EGexecute) - wc = towlower((wint_t)wc);
- wcrtomb(buf + i, wc, &cur_state);
+ mb_properties = xcalloc (1, size);
+ memset (mb_properties, 1, i);
}
+ mb_properties[i] = mbclen;
}
- mb_properties[i] = mbclen;
i += mbclen;
}
- return mb_properties;
+ return mb_properties ? mb_properties : (char *) -1;
}
#endif /* MBS_SUPPORT */
@@ -311,9 +334,8 @@ EXECUTE_FCT(EGexecute)
if (start_ptr) if (start_ptr)
start_ptr = case_buf + (start_ptr - buf); start_ptr = case_buf + (start_ptr - buf);
buf = case_buf; buf = case_buf;
@ -29,7 +503,7 @@
} }
#endif /* MBS_SUPPORT */ #endif /* MBS_SUPPORT */
@@ -352,8 +352,13 @@ EXECUTE_FCT(EGexecute) @@ -336,8 +358,14 @@ EXECUTE_FCT(EGexecute)
end = memchr(beg, eol, buflim - beg); end = memchr(beg, eol, buflim - beg);
end++; end++;
#ifdef MBS_SUPPORT #ifdef MBS_SUPPORT
@ -39,13 +513,23 @@
+ { + {
+ if (!mb_properties) + if (!mb_properties)
+ mb_properties = check_multibyte_string (buf, size, 0); + mb_properties = check_multibyte_string (buf, size, 0);
+ if (mb_properties[beg - buf] == 0) + if (mb_properties != (char *) -1
+ && mb_properties[beg - buf] == 0)
+ continue; + continue;
+ } + }
#endif #endif
while (beg > buf && beg[-1] != eol) while (beg > buf && beg[-1] != eol)
--beg; --beg;
@@ -543,8 +548,8 @@ EXECUTE_FCT(Fexecute) @@ -478,7 +506,7 @@ EXECUTE_FCT(EGexecute)
{
if (match_icase)
free((char*)buf);
- if (mb_properties)
+ if (mb_properties != (char *) -1)
free(mb_properties);
}
#endif /* MBS_SUPPORT */
@@ -527,8 +555,8 @@ EXECUTE_FCT(Fexecute)
if (start_ptr) if (start_ptr)
start_ptr = case_buf + (start_ptr - buf); start_ptr = case_buf + (start_ptr - buf);
buf = case_buf; buf = case_buf;
@ -55,7 +539,7 @@
} }
#endif /* MBS_SUPPORT */ #endif /* MBS_SUPPORT */
@@ -554,8 +559,13 @@ EXECUTE_FCT(Fexecute) @@ -538,8 +566,14 @@ EXECUTE_FCT(Fexecute)
if (offset == (size_t) -1) if (offset == (size_t) -1)
goto failure; goto failure;
#ifdef MBS_SUPPORT #ifdef MBS_SUPPORT
@ -65,9 +549,19 @@
+ { + {
+ if (!mb_properties) + if (!mb_properties)
+ mb_properties = check_multibyte_string(buf, size, 0); + mb_properties = check_multibyte_string(buf, size, 0);
+ if (mb_properties[offset+beg-buf] == 0) + if (mb_properties != (char *) -1
+ && mb_properties[offset+beg-buf] == 0)
+ continue; /* It is a part of multibyte character. */ + continue; /* It is a part of multibyte character. */
+ } + }
#endif /* MBS_SUPPORT */ #endif /* MBS_SUPPORT */
beg += offset; beg += offset;
len = kwsmatch.size[0]; len = kwsmatch.size[0];
@@ -595,7 +629,7 @@ EXECUTE_FCT(Fexecute)
{
if (match_icase)
free((char*)buf);
- if (mb_properties)
+ if (mb_properties != (char *) -1)
free(mb_properties);
}
#endif /* MBS_SUPPORT */

5
grep.changes
View File

@ -1,3 +1,8 @@
-------------------------------------------------------------------
Tue May 27 18:45:20 CEST 2008 - schwab@suse.de
- Some speadups.
------------------------------------------------------------------- -------------------------------------------------------------------
Mon Feb 11 17:45:07 CET 2008 - schwab@suse.de Mon Feb 11 17:45:07 CET 2008 - schwab@suse.de

4
grep.spec
View File

@ -20,7 +20,7 @@ Provides: base:/usr/bin/grep
AutoReqProv: on AutoReqProv: on
PreReq: %{install_info_prereq} PreReq: %{install_info_prereq}
Version: 2.5.2 Version: 2.5.2
Release: 50 Release: 69
Summary: Print lines matching a pattern Summary: Print lines matching a pattern
Source: grep-%{version}.tar.bz2 Source: grep-%{version}.tar.bz2
Patch: grep-%{version}.diff Patch: grep-%{version}.diff
@ -95,6 +95,8 @@ ln -sf ../../bin/grep $RPM_BUILD_ROOT/usr/bin/grep
%doc %{_infodir}/*.gz %doc %{_infodir}/*.gz
%changelog %changelog
* Tue May 27 2008 schwab@suse.de
- Some speadups.
* Mon Feb 11 2008 schwab@suse.de * Mon Feb 11 2008 schwab@suse.de
- Fix another icase bug. - Fix another icase bug.
* Wed Nov 28 2007 schwab@suse.de * Wed Nov 28 2007 schwab@suse.de