SHA256
1
0
forked from pool/grep

Accepting request 43849 from Base:System

Copy from Base:System/grep based on submit request 43849 from user jsmeix

OBS-URL: https://build.opensuse.org/request/show/43849
OBS-URL: https://build.opensuse.org/package/show/openSUSE:Factory/grep?expand=0&rev=18
This commit is contained in:
OBS User autobuild 2010-07-23 15:17:36 +00:00 committed by Git OBS Bridge
parent 2a0a7cfe60
commit 5e7a038201
10 changed files with 30 additions and 947 deletions

View File

@ -1,20 +0,0 @@
Index: src/dfa.c
===================================================================
--- src/dfa.c.orig
+++ src/dfa.c
@@ -1339,7 +1339,14 @@ copytoks (int tindex, int ntokens)
int i;
for (i = 0; i < ntokens; ++i)
- addtok(dfa->tokens[tindex + i]);
+ {
+ addtok(dfa->tokens[tindex + i]);
+#ifdef MBS_SUPPORT
+ /* Update index into multibyte csets. */
+ if (MB_CUR_MAX > 1 && dfa->tokens[tindex + i] == MBCSET)
+ dfa->multibyte_prop[dfa->tindex - 1] = dfa->multibyte_prop[tindex + i];
+#endif
+ }
}
static void

View File

@ -1,39 +0,0 @@
Index: Makefile.am
===================================================================
--- Makefile.am.orig
+++ Makefile.am
@@ -22,21 +22,7 @@ SUBDIRS = intl po lib doc src tests m4 v
EXTRA_DIST = TODO README README-alpha
-# We should be able to just define `ACLOCAL_AMFLAGS = --acdir=m4',
-# but this runs afoul of a bug in automake 1.
-# The following hack works around this bug by creating acinclude.m4 manually.
-ACLOCAL_AMFLAGS =
-M4DIR = $(srcdir)/m4
-ACINCLUDE_INPUTS = $(M4DIR)/decl.m4 $(M4DIR)/djgpp.m4 $(M4DIR)/dosfile.m4 \
- $(M4DIR)/envsep.m4 $(M4DIR)/error.m4 $(M4DIR)/gettext.m4 $(M4DIR)/glibc.m4 \
- $(M4DIR)/header.m4 $(M4DIR)/init.m4 $(M4DIR)/install.m4 \
- $(M4DIR)/inttypes_h.m4 $(M4DIR)/isc-posix.m4 $(M4DIR)/largefile.m4 \
- $(M4DIR)/lcmessage.m4 $(M4DIR)/malloc.m4 $(M4DIR)/mbstate_t.m4 \
- $(M4DIR)/missing.m4 $(M4DIR)/progtest.m4 $(M4DIR)/realloc.m4 \
- $(M4DIR)/regex.m4 $(M4DIR)/sanity.m4 $(M4DIR)/strerror_r.m4 \
- $(M4DIR)/uintmax_t.m4 $(M4DIR)/ulonglong.m4 $(M4DIR)/xstrtoumax.m4
-$(srcdir)/acinclude.m4 : $(ACINCLUDE_INPUTS)
- cat $(ACINCLUDE_INPUTS) >$(srcdir)/acinclude.m4
+ACLOCAL_AMFLAGS = -I m4
# make cvs-clean blatantly stolen from KDE CVS ;)
cvs-clean:
Index: lib/Makefile.am
===================================================================
--- lib/Makefile.am.orig
+++ lib/Makefile.am
@@ -30,6 +30,6 @@ libgreputils_a_SOURCES = \
libgreputils_a_LIBADD = @LIBOBJS@ @ALLOCA@
noinst_HEADERS = \
closeout.h error.h exclude.h fnmatch.h getopt.h \
- hard-locale.h obstack.h quotearg.h regex.h savedir.h xalloc.h xstrtol.h
+ hard-locale.h obstack.h quotearg.h savedir.h xalloc.h xstrtol.h
EXTRA_DIST = strtol.c malloc.c realloc.c

View File

@ -1,3 +0,0 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0abec64e01458fbd032e33351d8071602a959529ea796965e98338ee83a40020
size 723181

3
grep-2.6.3.tar.bz2 Normal file
View File

@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d319e79d5b1b3f9331da1db281949f7bc02e385abbf984764f2bb26783005c78
size 1021770

View File

@ -1,33 +0,0 @@
Index: grep-2.5.4/src/search.c
===================================================================
--- grep-2.5.4.orig/src/search.c
+++ grep-2.5.4/src/search.c
@@ -34,6 +34,8 @@
#include "system.h"
#include "grep.h"
#ifndef FGREP_PROGRAM
+#include <stdio.h>
+#define __USE_GNU
# include <regex.h>
# include "dfa.h"
#endif
@@ -45,6 +47,7 @@
#endif
#include "mbchar.h"
+
#define NCHAR (UCHAR_MAX + 1)
/* For -w, we also consider _ to be word constituent. */
Index: grep-2.5.4/src/dfa.c
===================================================================
--- grep-2.5.4.orig/src/dfa.c
+++ grep-2.5.4/src/dfa.c
@@ -120,6 +120,7 @@ extern void free();
# include <wctype.h>
#endif
+#define __USE_GNU
#include "regex.h"
#include "dfa.h"
#include "hard-locale.h"

View File

@ -1,662 +0,0 @@
Index: lib/Makefile.am
===================================================================
--- lib/Makefile.am.orig
+++ lib/Makefile.am
@@ -24,12 +24,12 @@ 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
Index: lib/mbchar.c
===================================================================
--- /dev/null
+++ 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 */
Index: lib/mbchar.h
===================================================================
--- /dev/null
+++ 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 */
Index: src/dfa.c
===================================================================
--- src/dfa.c.orig
+++ src/dfa.c
@@ -123,6 +123,7 @@ extern void free();
#include "regex.h"
#include "dfa.h"
#include "hard-locale.h"
+#include "mbchar.h"
/* HPUX, define those as macros in sys/param.h */
#ifdef setbit
@@ -379,6 +380,7 @@ static int hard_LC_COLLATE; /* Nonzero i
#ifdef MBS_SUPPORT
/* These variables are used only if (MB_CUR_MAX > 1). */
static mbstate_t mbs; /* Mbstate for mbrlen(). */
+static bool cur_mb_in_shift;
static int cur_mb_len; /* Byte length of the current scanning
multibyte character. */
static int cur_mb_index; /* Byte index of the current scanning multibyte
@@ -427,7 +429,14 @@ update_mb_len_index (char const *p, int
next character is a multibyte character or not. */
if (! cur_mb_index)
{
- cur_mb_len = mbrlen(p, len, &mbs);
+ if (!cur_mb_in_shift && is_basic (*p))
+ cur_mb_len = 1;
+ else
+ {
+ cur_mb_len = mbrlen(p, len, &mbs);
+ if (!mbsinit (&mbs))
+ cur_mb_in_shift = true;
+ }
if (cur_mb_len > 1)
/* It is a multibyte character.
cur_mb_len was already set by mbrlen(). */
@@ -473,12 +482,22 @@ fetch_wc (char const *eoferr)
return WEOF;
}
- cur_mb_len = mbrtowc(&wc, lexptr, lexleft, &mbs);
- if (cur_mb_len <= 0)
- {
+ if (!cur_mb_in_shift && is_basic (*lexptr))
+ {
cur_mb_len = 1;
wc = *lexptr;
}
+ else
+ {
+ cur_mb_len = mbrtowc(&wc, lexptr, lexleft, &mbs);
+ if (!mbsinit (&mbs))
+ cur_mb_in_shift = true;
+ if (cur_mb_len <= 0)
+ {
+ cur_mb_len = 1;
+ wc = *lexptr;
+ }
+ }
lexptr += cur_mb_len;
lexleft -= cur_mb_len;
return wc;
@@ -1430,6 +1449,7 @@ dfaparse (char const *s, size_t len, str
{
cur_mb_index = 0;
cur_mb_len = 0;
+ cur_mb_in_shift = false;
memset(&mbs, 0, sizeof(mbstate_t));
}
#endif /* MBS_SUPPORT */
@@ -2838,6 +2858,7 @@ dfaexec (struct dfa *d, char const *begi
if (MB_CUR_MAX > 1)
{
int remain_bytes, i;
+ bool in_shift = false;
buf_begin = (unsigned char const *) begin;
buf_end = end;
@@ -2850,9 +2871,16 @@ dfaexec (struct dfa *d, char const *begi
{
if (remain_bytes == 0)
{
- remain_bytes
- = mbrtowc(inputwcs + i, begin + i,
- end - (unsigned char const *)begin - i + 1, &mbs);
+ if (!in_shift && is_basic (begin[i]))
+ remain_bytes = 1;
+ else
+ {
+ remain_bytes
+ = mbrtowc(inputwcs + i, begin + i,
+ end - (unsigned char const *)begin - i + 1, &mbs);
+ if (!mbsinit (&mbs))
+ in_shift = true;
+ }
if (remain_bytes <= 1)
{
remain_bytes = 0;
Index: src/search.c
===================================================================
--- src/search.c.orig
+++ src/search.c
@@ -43,6 +43,7 @@
#ifdef HAVE_LIBPCRE
# include <pcre.h>
#endif
+#include "mbchar.h"
#define NCHAR (UCHAR_MAX + 1)
@@ -140,40 +141,59 @@ kwsmusts (void)
are not single byte character nor the first byte of a multibyte
character. Caller must free the array. */
static char*
-check_multibyte_string(char const *buf, size_t size)
+check_multibyte_string(char const *buf, size_t size, int case_convert)
{
- char *mb_properties = xmalloc(size);
+ char *mb_properties = NULL;
mbstate_t cur_state;
wchar_t wc;
int i;
+ bool in_shift = false;
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;
+ wc = buf[i];
+ if (case_convert && iswupper ((wint_t)wc))
+ {
+ wc = towlower((wint_t)wc);
+ wcrtomb(buf + i, wc, &cur_state);
+ }
}
- else if (match_icase)
+ else
{
- if (iswupper((wint_t)wc))
+ mbclen = mbrtowc(&wc, buf + i, size - i, &cur_state);
+ if (!mbsinit (&cur_state))
+ in_shift = true;
+
+ 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 && iswupper((wint_t)wc))
{
wc = towlower((wint_t)wc);
wcrtomb(buf + i, wc, &cur_state);
}
}
- mb_properties[i] = mbclen;
+ if (mbclen != 1 && !mb_properties)
+ {
+ mb_properties = xcalloc (1, size);
+ memset (mb_properties, 1, i);
+ }
+ if (mb_properties)
+ mb_properties[i] = mbclen;
i += mbclen;
}
- return mb_properties;
+ return mb_properties ? mb_properties : (char *) -1;
}
#endif /* MBS_SUPPORT */
@@ -311,9 +331,8 @@ EXECUTE_FCT(EGexecute)
if (start_ptr)
start_ptr = case_buf + (start_ptr - buf);
buf = case_buf;
+ mb_properties = check_multibyte_string(buf, size, 1);
}
- if (kwset)
- mb_properties = check_multibyte_string(buf, size);
}
#endif /* MBS_SUPPORT */
@@ -335,10 +354,6 @@ EXECUTE_FCT(EGexecute)
run it through DFA. */
end = memchr(beg, eol, buflim - beg);
end++;
-#ifdef MBS_SUPPORT
- if (MB_CUR_MAX > 1 && mb_properties[beg - buf] == 0)
- continue;
-#endif
while (beg > buf && beg[-1] != eol)
--beg;
if (kwsm.index < kwset_exact_matches)
@@ -478,7 +493,7 @@ 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 +542,8 @@ EXECUTE_FCT(Fexecute)
if (start_ptr)
start_ptr = case_buf + (start_ptr - buf);
buf = case_buf;
+ mb_properties = check_multibyte_string(buf, size, 1);
}
- mb_properties = check_multibyte_string(buf, size);
}
#endif /* MBS_SUPPORT */
@@ -538,8 +553,14 @@ EXECUTE_FCT(Fexecute)
if (offset == (size_t) -1)
goto failure;
#ifdef MBS_SUPPORT
- if (MB_CUR_MAX > 1 && mb_properties[offset+beg-buf] == 0)
- continue; /* It is a part of multibyte character. */
+ if (MB_CUR_MAX > 1)
+ {
+ if (!mb_properties)
+ mb_properties = check_multibyte_string(buf, size, 0);
+ if (mb_properties != (char *) -1
+ && mb_properties[offset+beg-buf] == 0)
+ continue; /* It is a part of multibyte character. */
+ }
#endif /* MBS_SUPPORT */
beg += offset;
len = kwsmatch.size[0];
@@ -594,7 +615,7 @@ EXECUTE_FCT(Fexecute)
{
if (match_icase)
free((char*)buf);
- if (mb_properties)
+ if (mb_properties != (char *) -1)
free(mb_properties);
}
#endif /* MBS_SUPPORT */

View File

@ -1,3 +1,24 @@
-------------------------------------------------------------------
Thu Jul 22 15:45:31 CEST 2010 - jsmeix@suse.de
- Forwarded the below "upgrade to grep-2.6.3" to openSUSE:Factory.
This is also a reset to full compliance with upstream.
All our own patches and "speedups" were dropped in the below
"upgrade to grep-2.6.3" because they had bad side effects
like bnc#618455 (SLES11-SP1) and bug#616037 (SLES9-SP4)
which do not happen with an upstream compliant grep
(regardless of an old version 2.5.1 or the new 2.6.3).
- On Fri Apr 9 16:43:45 CEST 2010 duwe@suse.de did a version
upgrade to grep-2.6.3, which brings among various compile fixes
vast improvements for UTF-8 / multibyte handling.
Fixes bnc#255977 (SLES10-SP2) and bnc#415228 (SLES9-SP3).
-------------------------------------------------------------------
Mon Jun 28 06:38:35 UTC 2010 - jengelh@medozas.de
- use %_smp_mflags
-------------------------------------------------------------------
Thu Jun 11 21:46:26 CEST 2009 - coolo@novell.com

123
grep.spec
View File

@ -1,7 +1,7 @@
#
# spec file for package grep (Version 2.5.4)
# spec file for package grep (Version 2.6.3)
#
# Copyright (c) 2009 SUSE LINUX Products GmbH, Nuernberg, Germany.
# Copyright (c) 2010 SUSE LINUX Products GmbH, Nuernberg, Germany.
#
# All modifications and additions to the file contributed by third parties
# remain the property of their copyright owners, unless otherwise agreed
@ -20,21 +20,15 @@
Name: grep
BuildRequires: pcre-devel
Url: http://www.gnu.org/software/grep/
License: GPL v2 or later
License: GPLv3
Group: Productivity/Text/Utilities
Provides: base:/usr/bin/grep
AutoReqProv: on
PreReq: %{install_info_prereq}
Version: 2.5.4
Release: 3
Version: 2.6.3
Release: 1
Summary: Print lines matching a pattern
Source: grep-%{version}.tar.bz2
Patch: grep-%{version}.diff
Patch1: pcre-static.patch
Patch2: grep-2.5.1a-mbcset.diff
Patch3: icase.diff
Patch4: grep-i18n-speedup.diff
Patch5: grep-glibc210.diff
BuildRoot: %{_tmppath}/%{name}-%{version}-build
%description
@ -54,19 +48,11 @@ Authors:
%prep
%setup -q
%patch
%patch1
%patch2
%patch3
%patch4
%patch5 -p1
rm -f lib/regex.h
rm -f m4/header.m4 m4/install.m4 m4/isc-posix.m4 m4/largefile.m4 m4/missing.m4 m4/sanity.m4
%build
AUTOPOINT=true autoreconf --force --install
%configure --bindir=/bin --without-included-regex
%{__make} %{?jobs:-j%jobs}
%{__make} %{?_smp_mflags}
%check
make check VERBOSE=1
@ -94,100 +80,3 @@ ln -sf ../../bin/grep $RPM_BUILD_ROOT/usr/bin/grep
%doc %{_infodir}/*.gz
%changelog
* Thu Jun 11 2009 coolo@novell.com
- rediff to avoid fuzz
- fix build with glibc 2.10
* Thu Jun 04 2009 crrodriguez@suse.de
- link pcre library dynamically
* Wed Feb 11 2009 schwab@suse.de
- Update to grep 2.5.4.
* This is a bugfix release. No new features.
* Thu Aug 14 2008 schwab@suse.de
- More speedups.
* Tue Jun 03 2008 schwab@suse.de
- Fix last change.
* Tue May 27 2008 schwab@suse.de
- Some speedups.
* Mon Feb 11 2008 schwab@suse.de
- Fix another icase bug.
* Wed Nov 28 2007 schwab@suse.de
- General cleanup.
* Wed Sep 12 2007 schwab@suse.de
- Allocate MB properties lazily.
* Tue May 15 2007 schwab@suse.de
- Fix some icase bugs.
* Mon May 07 2007 schwab@suse.de
- Try to get something sensible out of CVS.
* Thu Mar 22 2007 schwab@suse.de
- Add a variant of the mbcache patch.
* Mon Jul 17 2006 schwab@suse.de
- Fix matching in unsafe encodings [#192390].
* Sun Jun 11 2006 schwab@suse.de
- Fix crash with -P '\xa'.
* Wed Mar 15 2006 schwab@suse.de
- Don't block on opening a pipe when devices are supposed to be skipped
[#149660].
* Wed Feb 08 2006 schwab@suse.de
- Fix dfa generation of interval expressions [#148453].
* Wed Jan 25 2006 mls@suse.de
- converted neededforbuild to BuildRequires
* Fri Jan 20 2006 agruen@suse.de
- Fix a formatting error in the man page.
* Sat Mar 12 2005 schwab@suse.de
- Fix word matching.
* Mon Nov 22 2004 schwab@suse.de
- Update to grep 2.5.1a.
* Wed Oct 20 2004 ro@suse.de
- locale rename: no -> nb
* Thu Sep 23 2004 schwab@suse.de
- Better fix for last change [#45689].
* Wed Mar 17 2004 schwab@suse.de
- Fix dangling pointer [#36172].
* Wed Mar 03 2004 schwab@suse.de
- Update from CVS.
* Thu Feb 19 2004 kukuk@suse.de
- Cleanup neededforbuild
* Tue Feb 10 2004 schwab@suse.de
- Fix configure test for strerror [#34231].
* Sat Jan 10 2004 adrian@suse.de
- add %%defattr
- let rpm strip
* Fri Jul 25 2003 schwab@suse.de
- Fix parsing of bracket expressions.
* Mon Jul 21 2003 schwab@suse.de
- Fix use of pointer after free.
* Fri Jun 20 2003 ro@suse.de
- build with current gettext
* Wed Apr 30 2003 schwab@suse.de
- Add i18n speedup patch from Takashi.
* Thu Apr 24 2003 ro@suse.de
- fix install_info --delete call and move from preun to postun
* Mon Apr 07 2003 schwab@suse.de
- Only delete info entries when removing last version.
* Wed Feb 12 2003 schwab@suse.de
- Disable huge backref test for now.
* Thu Feb 06 2003 schwab@suse.de
- Use %%install_info.
* Mon Nov 18 2002 schwab@suse.de
- Add AM_GNU_GETTEXT_VERSION.
* Thu Aug 15 2002 schwab@suse.de
- Add i18n patches.
* Wed Apr 03 2002 schwab@suse.de
- Link -lpcre statically.
* Wed Apr 03 2002 schwab@suse.de
- Update to grep 2.5.1.
* Includes support for Perl regexps.
* Wed Apr 03 2002 ro@suse.de
- build with current autoconf/automake
* Tue Feb 05 2002 schwab@suse.de
- Don't replace autoconf macros from gettext.
* Mon Jan 28 2002 schwab@suse.de
- Add i18n patch.
* Tue Sep 04 2001 schwab@suse.de
- Update to grep 2.4.2:
- New option --binary-files
- Final newline silently provided.
* Thu Mar 22 2001 ro@suse.de
- added split-aliases as provides
* Wed Mar 07 2001 schwab@suse.de
- Split from base.

View File

@ -1,60 +0,0 @@
Index: src/grep.c
===================================================================
--- src/grep.c.orig
+++ src/grep.c
@@ -789,28 +789,10 @@ print_line_middle (const char *beg, cons
size_t match_offset;
const char *cur = beg;
const char *mid = NULL;
- char *buf; /* XXX */
- const char *ibeg; /* XXX */
-
- if (match_icase) /* XXX - None of the -i stuff should be here. */
- {
- int i = lim - beg;
-
- ibeg = buf = (char *) xmalloc(i);
- /* This can't possibly be correct with UTF-8,
- but it's equivalent to what was there so far. */
- while (--i >= 0)
- buf[i] = tolower(beg[i]);
- }
- else
- {
- buf = NULL;
- ibeg = beg;
- }
while ( lim > cur
- && ((match_offset = execute(ibeg, lim - beg, &match_size,
- ibeg + (cur - beg))) != (size_t) -1))
+ && ((match_offset = execute(beg, lim - beg, &match_size,
+ beg + (cur - beg))) != (size_t) -1))
{
char const *b = beg + match_offset;
@@ -854,9 +836,6 @@ print_line_middle (const char *beg, cons
cur = b + match_size;
}
- if (buf)
- free(buf); /* XXX */
-
if (only_matching)
cur = lim;
else if (mid)
Index: src/search.c
===================================================================
--- src/search.c.orig
+++ src/search.c
@@ -193,10 +193,8 @@ GEAcompile (char const *pattern, size_t
size_t total = size;
char const *motif = pattern;
-#if 0
if (match_icase)
syntax_bits |= RE_ICASE;
-#endif
re_set_syntax (syntax_bits);
dfasyntax (syntax_bits, match_icase, eolbyte);

View File

@ -1,13 +0,0 @@
Index: configure.ac
===================================================================
--- configure.ac.orig
+++ configure.ac
@@ -157,7 +157,7 @@ if test x"$testpcre" = x"yes"; then
CPPFLAGS="$CPPFLAGS `pcre-config --cflags`"
LIBS="$LIBS `pcre-config --libs`"
fi
- AC_CHECK_LIB(pcre, pcre_exec)
+ AC_SEARCH_LIBS(pcre_exec, pcre, [AC_DEFINE(HAVE_LIBPCRE, 1, [Define to 1 if you have the `pcre' library (-lpcre).])])
fi
AC_CONFIG_FILES([Makefile