Commit d904cc83 authored by Paul Eggert's avatar Paul Eggert
Browse files

Use Gnulib regex for lib-src

Emacs regular expressions forked from everyone else long ago.
This makes it official and should allow simplification later.
etags.c now uses the glibc regex API, falling back on a
Gnulib-supplied substitute lib/regex.c if necessary.
Emacs proper now uses its own regular expression module.
Although this patch may look dauntingly large, most of it
was generated automatically by admin/merge-gnulib
and contains an exact copy of the glibc regex source,
and the by-hand changes do not grow the Emacs source code.
* admin/merge-gnulib (GNULIB_MODULES): Add regex.
(AVOIDED_MODULES): Add btowc, langinfo, lock, mbrtowc, mbsinit,
nl_langinfo, wchar, wcrtomb, wctype-h.
* lib-src/Makefile.in (regex-emacs.o): Remove; Gnulib does it now.
(etags_deps, etags_libs): Remove regex-emacs.o.
* lib-src/etags.c: Go back to including regex.h.
(add_regex): Use unsigned char translation array,
since glibc regex requires that.
* lib/Makefile.in (not_emacs_OBJECTS, for_emacs_OBJECTS): New macros.
(libegnu_a_OBJECTS): Use them, to avoid building e-regex.o.
* lib/gnulib.mk.in, m4/gnulib-comp.m4: Regenerate.
* lib/regcomp.c, lib/regex.c, lib/regex.h, lib/regex_internal.c:
* lib/regex_internal.h, lib/regexec.c, m4/builtin-expect.m4:
* m4/eealloc.m4, m4/glibc21.m4, m4/mbstate_t.m4, m4/regex.m4:
New files, copied from Gnulib.
* src/regex-emacs.h, src/conf_post.h:
(RE_TRANSLATE_TYPE, RE_TRANSLATE, RE_TRANSLATE_P):
Move from src/conf_post.h to src/regex-emacs.h,
so that they don’t interfere with compiling lib/regex.c.
parent e5652268
......@@ -37,7 +37,7 @@ GNULIB_MODULES='
getloadavg getopt-gnu gettime gettimeofday gitlog-to-changelog
ieee754-h ignore-value intprops largefile lstat
manywarnings memrchr minmax mkostemp mktime nstrftime
pipe2 pselect pthread_sigmask putenv qcopy-acl readlink readlinkat
pipe2 pselect pthread_sigmask putenv qcopy-acl readlink readlinkat regex
sig2str socklen stat-time std-gnu11 stdalign stddef stdio
stpcpy strtoimax symlink sys_stat sys_time
tempname time time_r time_rz timegm timer-time timespec-add timespec-sub
......@@ -46,11 +46,12 @@ GNULIB_MODULES='
'
AVOIDED_MODULES='
close dup fchdir fstat
malloc-posix msvc-inval msvc-nothrow
btowc close dup fchdir fstat langinfo lock
malloc-posix mbrtowc mbsinit msvc-inval msvc-nothrow nl_langinfo
openat-die opendir raise
save-cwd select setenv sigprocmask stat stdarg stdbool
threadlib tzset unsetenv utime utime-h
wchar wcrtomb wctype-h
'
GNULIB_TOOL_FLAGS='
......
......@@ -31,6 +31,13 @@ functions 'json-serialize', 'json-insert', 'json-parse-string', and
'json-parse-buffer' are typically much faster than their Lisp
counterparts from json.el.
** The etags program now uses the C library's regular expression matcher
when possible, and a compatible regex substitute otherwise. This will
let developers maintain Emacs's own regex code without having to also
support other programs. The new configure option '--without-included-regex'
forces etags to use the C library's regex matcher even if the regex
substitute ordinarily would be used to work around compatibility problems.
** Emacs has been ported to the -fcheck-pointer-bounds option of GCC.
This causes Emacs to check bounds of some arrays addressed by its
internal pointers, which can be helpful when debugging the Emacs
......
......@@ -361,13 +361,9 @@ TAGS: etags${EXEEXT} ${tagsfiles}
../lib/libgnu.a: $(config_h)
$(MAKE) -C ../lib all
regex-emacs.o: $(srcdir)/../src/regex-emacs.c $(srcdir)/../src/regex-emacs.h $(config_h)
$(AM_V_CC)$(CC) -c $(CPP_CFLAGS) $<
etags_deps = ${srcdir}/etags.c regex-emacs.o $(NTLIB) $(config_h)
etags_deps = ${srcdir}/etags.c $(NTLIB) $(config_h)
etags_cflags = -DEMACS_NAME="\"GNU Emacs\"" -DVERSION="\"${version}\"" -o $@
etags_libs = regex-emacs.o $(NTLIB) $(LOADLIBES)
etags_libs = $(NTLIB) $(LOADLIBES)
etags${EXEEXT}: ${etags_deps}
$(AM_V_CCLD)$(CC) ${ALL_CFLAGS} $(etags_cflags) $< $(etags_libs)
......
......@@ -135,7 +135,7 @@ char pot_etags_version[] = "@(#) pot revision number is 17.38.1.4";
#endif
#include <getopt.h>
#include <regex-emacs.h>
#include <regex.h>
/* Define CTAGS to make the program "ctags" compatible with the usual one.
Leave it undefined to make the program "etags", which makes emacs-style
......@@ -6401,7 +6401,7 @@ add_regex (char *regexp_pattern, language *lang)
*patbuf = zeropattern;
if (ignore_case)
{
static char lc_trans[UCHAR_MAX + 1];
static unsigned char lc_trans[UCHAR_MAX + 1];
int i;
for (i = 0; i < UCHAR_MAX + 1; i++)
lc_trans[i] = c_tolower (i);
......
......@@ -79,9 +79,15 @@ endif
Makefile: ../config.status $(srcdir)/Makefile.in
$(MAKE) -C .. src/$@
# Object modules that need not be built for Emacs.
# Emacs does not need e-regex.o (it has its own regex-emacs.c),
# and building it would just waste time.
not_emacs_OBJECTS = regex.o
libgnu_a_OBJECTS = $(gl_LIBOBJS) \
$(patsubst %.c,%.o,$(filter %.c,$(libgnu_a_SOURCES)))
libegnu_a_OBJECTS = $(patsubst %.o,e-%.o,$(libgnu_a_OBJECTS))
for_emacs_OBJECTS = $(filter-out $(not_emacs_OBJECTS),$(libgnu_a_OBJECTS))
libegnu_a_OBJECTS = $(patsubst %.o,e-%.o,$(for_emacs_OBJECTS))
$(libegnu_a_OBJECTS) $(libgnu_a_OBJECTS): $(BUILT_SOURCES)
......
......@@ -34,13 +34,19 @@
# --no-libtool \
# --macro-prefix=gl \
# --no-vc-files \
# --avoid=btowc \
# --avoid=close \
# --avoid=dup \
# --avoid=fchdir \
# --avoid=fstat \
# --avoid=langinfo \
# --avoid=lock \
# --avoid=malloc-posix \
# --avoid=mbrtowc \
# --avoid=mbsinit \
# --avoid=msvc-inval \
# --avoid=msvc-nothrow \
# --avoid=nl_langinfo \
# --avoid=openat-die \
# --avoid=opendir \
# --avoid=raise \
......@@ -56,6 +62,9 @@
# --avoid=unsetenv \
# --avoid=utime \
# --avoid=utime-h \
# --avoid=wchar \
# --avoid=wcrtomb \
# --avoid=wctype-h \
# alloca-opt \
# binary-io \
# byteswap \
......@@ -113,6 +122,7 @@
# qcopy-acl \
# readlink \
# readlinkat \
# regex \
# sig2str \
# socklen \
# stat-time \
......@@ -216,6 +226,7 @@ GETOPT_CDEFS_H = @GETOPT_CDEFS_H@
GETOPT_H = @GETOPT_H@
GFILENOTIFY_CFLAGS = @GFILENOTIFY_CFLAGS@
GFILENOTIFY_LIBS = @GFILENOTIFY_LIBS@
GLIBC21 = @GLIBC21@
GL_COND_LIBTOOL = @GL_COND_LIBTOOL@
GL_GENERATE_ALLOCA_H = @GL_GENERATE_ALLOCA_H@
GL_GENERATE_BYTESWAP_H = @GL_GENERATE_BYTESWAP_H@
......@@ -1024,6 +1035,7 @@ gameuser = @gameuser@
gl_GNULIB_ENABLED_03e0aaad4cb89ca757653bd367a6ccb7 = @gl_GNULIB_ENABLED_03e0aaad4cb89ca757653bd367a6ccb7@
gl_GNULIB_ENABLED_2049e887c7e5308faad27b3f894bb8c9 = @gl_GNULIB_ENABLED_2049e887c7e5308faad27b3f894bb8c9@
gl_GNULIB_ENABLED_260941c0e5dc67ec9e87d1fb321c300b = @gl_GNULIB_ENABLED_260941c0e5dc67ec9e87d1fb321c300b@
gl_GNULIB_ENABLED_37f71b604aa9c54446783d80f42fe547 = @gl_GNULIB_ENABLED_37f71b604aa9c54446783d80f42fe547@
gl_GNULIB_ENABLED_5264294aa0a5557541b53c8c741f7f31 = @gl_GNULIB_ENABLED_5264294aa0a5557541b53c8c741f7f31@
gl_GNULIB_ENABLED_6099e9737f757db36c47fa9d9f02e88c = @gl_GNULIB_ENABLED_6099e9737f757db36c47fa9d9f02e88c@
gl_GNULIB_ENABLED_682e609604ccaac6be382e4ee3a4eaec = @gl_GNULIB_ENABLED_682e609604ccaac6be382e4ee3a4eaec@
......@@ -2095,6 +2107,17 @@ EXTRA_libgnu_a_SOURCES += at-func.c readlinkat.c
endif
## end gnulib module readlinkat
## begin gnulib module regex
ifeq (,$(OMIT_GNULIB_MODULE_regex))
EXTRA_DIST += regcomp.c regex.c regex.h regex_internal.c regex_internal.h regexec.c
EXTRA_libgnu_a_SOURCES += regcomp.c regex.c regex_internal.c regexec.c
endif
## end gnulib module regex
## begin gnulib module root-uid
ifeq (,$(OMIT_GNULIB_MODULE_root-uid))
......
This diff is collapsed.
/* Extended regular expression matching and search library.
Copyright (C) 2002-2018 Free Software Foundation, Inc.
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 General Public
License as published by the Free Software Foundation; either
version 3 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
General Public License for more details.
You should have received a copy of the GNU General Public
License along with the GNU C Library; if not, see
<https://www.gnu.org/licenses/>. */
#ifndef _LIBC
# include <config.h>
# if (__GNUC__ == 4 && 6 <= __GNUC_MINOR__) || 4 < __GNUC__
# pragma GCC diagnostic ignored "-Wsuggest-attribute=pure"
# endif
# if (__GNUC__ == 4 && 3 <= __GNUC_MINOR__) || 4 < __GNUC__
# pragma GCC diagnostic ignored "-Wold-style-definition"
# pragma GCC diagnostic ignored "-Wtype-limits"
# endif
#endif
/* Make sure no one compiles this code with a C++ compiler. */
#if defined __cplusplus && defined _LIBC
# error "This is C code, use a C compiler"
#endif
#ifdef _LIBC
/* We have to keep the namespace clean. */
# define regfree(preg) __regfree (preg)
# define regexec(pr, st, nm, pm, ef) __regexec (pr, st, nm, pm, ef)
# define regcomp(preg, pattern, cflags) __regcomp (preg, pattern, cflags)
# define regerror(errcode, preg, errbuf, errbuf_size) \
__regerror(errcode, preg, errbuf, errbuf_size)
# define re_set_registers(bu, re, nu, st, en) \
__re_set_registers (bu, re, nu, st, en)
# define re_match_2(bufp, string1, size1, string2, size2, pos, regs, stop) \
__re_match_2 (bufp, string1, size1, string2, size2, pos, regs, stop)
# define re_match(bufp, string, size, pos, regs) \
__re_match (bufp, string, size, pos, regs)
# define re_search(bufp, string, size, startpos, range, regs) \
__re_search (bufp, string, size, startpos, range, regs)
# define re_compile_pattern(pattern, length, bufp) \
__re_compile_pattern (pattern, length, bufp)
# define re_set_syntax(syntax) __re_set_syntax (syntax)
# define re_search_2(bufp, st1, s1, st2, s2, startpos, range, regs, stop) \
__re_search_2 (bufp, st1, s1, st2, s2, startpos, range, regs, stop)
# define re_compile_fastmap(bufp) __re_compile_fastmap (bufp)
# include "../locale/localeinfo.h"
#endif
/* On some systems, limits.h sets RE_DUP_MAX to a lower value than
GNU regex allows. Include it before <regex.h>, which correctly
#undefs RE_DUP_MAX and sets it to the right value. */
#include <limits.h>
#include <regex.h>
#include "regex_internal.h"
#include "regex_internal.c"
#include "regcomp.c"
#include "regexec.c"
/* Binary backward compatibility. */
#if _LIBC
# include <shlib-compat.h>
# if SHLIB_COMPAT (libc, GLIBC_2_0, GLIBC_2_3)
link_warning (re_max_failures, "the 're_max_failures' variable is obsolete and will go away.")
int re_max_failures = 2000;
# endif
#endif
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
This diff is collapsed.
dnl Check for __builtin_expect.
dnl Copyright 2016-2018 Free Software Foundation, Inc.
dnl This file is free software; the Free Software Foundation
dnl gives unlimited permission to copy and/or distribute it,
dnl with or without modifications, as long as this notice is preserved.
dnl Written by Paul Eggert.
AC_DEFUN([gl___BUILTIN_EXPECT],
[
AC_CACHE_CHECK([for __builtin_expect],
[gl_cv___builtin_expect],
[AC_LINK_IFELSE(
[AC_LANG_SOURCE([[
int
main (int argc, char **argv)
{
argc = __builtin_expect (argc, 100);
return argv[argc != 100][0];
}]])],
[gl_cv___builtin_expect=yes],
[AC_LINK_IFELSE(
[AC_LANG_SOURCE([[
#include <builtins.h>
int
main (int argc, char **argv)
{
argc = __builtin_expect (argc, 100);
return argv[argc != 100][0];
}]])],
[gl_cv___builtin_expect="in <builtins.h>"],
[gl_cv___builtin_expect=no])])])
if test "$gl_cv___builtin_expect" = yes; then
AC_DEFINE([HAVE___BUILTIN_EXPECT], [1])
elif test "$gl_cv___builtin_expect" = "in <builtins.h>"; then
AC_DEFINE([HAVE___BUILTIN_EXPECT], [2])
fi
AH_VERBATIM([HAVE___BUILTIN_EXPECT],
[/* Define to 1 if the compiler supports __builtin_expect,
and to 2 if <builtins.h> does. */
#undef HAVE___BUILTIN_EXPECT
#ifndef HAVE___BUILTIN_EXPECT
# define __builtin_expect(e, c) (e)
#elif HAVE___BUILTIN_EXPECT == 2
# include <builtins.h>
#endif
])
])
# eealloc.m4 serial 3
dnl Copyright (C) 2003, 2009-2018 Free Software Foundation, Inc.
dnl This file is free software; the Free Software Foundation
dnl gives unlimited permission to copy and/or distribute it,
dnl with or without modifications, as long as this notice is preserved.
AC_DEFUN([gl_EEALLOC],
[
AC_REQUIRE([gl_EEMALLOC])
AC_REQUIRE([gl_EEREALLOC])
])
AC_DEFUN([gl_EEMALLOC],
[
_AC_FUNC_MALLOC_IF(
[gl_cv_func_malloc_0_nonnull=1],
[gl_cv_func_malloc_0_nonnull=0])
AC_DEFINE_UNQUOTED([MALLOC_0_IS_NONNULL], [$gl_cv_func_malloc_0_nonnull],
[If malloc(0) is != NULL, define this to 1. Otherwise define this
to 0.])
])
AC_DEFUN([gl_EEREALLOC],
[
_AC_FUNC_REALLOC_IF(
[gl_cv_func_realloc_0_nonnull=1],
[gl_cv_func_realloc_0_nonnull=0])
AC_DEFINE_UNQUOTED([REALLOC_0_IS_NONNULL], [$gl_cv_func_realloc_0_nonnull],
[If realloc(NULL,0) is != NULL, define this to 1. Otherwise define this
to 0.])
])
# glibc21.m4 serial 5
dnl Copyright (C) 2000-2002, 2004, 2008, 2010-2018 Free Software Foundation,
dnl Inc.
dnl This file is free software; the Free Software Foundation
dnl gives unlimited permission to copy and/or distribute it,
dnl with or without modifications, as long as this notice is preserved.
# Test for the GNU C Library, version 2.1 or newer, or uClibc.
# From Bruno Haible.
AC_DEFUN([gl_GLIBC21],
[
AC_CACHE_CHECK([whether we are using the GNU C Library >= 2.1 or uClibc],
[ac_cv_gnu_library_2_1],
[AC_EGREP_CPP([Lucky],
[
#include <features.h>
#ifdef __GNU_LIBRARY__
#if (__GLIBC__ == 2 && __GLIBC_MINOR__ >= 1) || (__GLIBC__ > 2)
Lucky GNU user
#endif
#endif
#ifdef __UCLIBC__
Lucky user
#endif
],
[ac_cv_gnu_library_2_1=yes],
[ac_cv_gnu_library_2_1=no])
]
)
AC_SUBST([GLIBC21])
GLIBC21="$ac_cv_gnu_library_2_1"
]
)
This diff is collapsed.
# mbstate_t.m4 serial 13
dnl Copyright (C) 2000-2002, 2008-2018 Free Software Foundation, Inc.
dnl This file is free software; the Free Software Foundation
dnl gives unlimited permission to copy and/or distribute it,
dnl with or without modifications, as long as this notice is preserved.
# From Paul Eggert.
# BeOS 5 has <wchar.h> but does not define mbstate_t,
# so you can't declare an object of that type.
# Check for this incompatibility with Standard C.
# AC_TYPE_MBSTATE_T
# -----------------
AC_DEFUN([AC_TYPE_MBSTATE_T],
[
AC_REQUIRE([AC_USE_SYSTEM_EXTENSIONS]) dnl for HP-UX 11.11
AC_CACHE_CHECK([for mbstate_t], [ac_cv_type_mbstate_t],
[AC_COMPILE_IFELSE(
[AC_LANG_PROGRAM(
[AC_INCLUDES_DEFAULT[
/* Tru64 with Desktop Toolkit C has a bug: <stdio.h> must be included before
<wchar.h>.
BSD/OS 4.0.1 has a bug: <stddef.h>, <stdio.h> and <time.h> must be
included before <wchar.h>. */
#include <stddef.h>
#include <stdio.h>
#include <time.h>
#include <wchar.h>]],
[[mbstate_t x; return sizeof x;]])],
[ac_cv_type_mbstate_t=yes],
[ac_cv_type_mbstate_t=no])])
if test $ac_cv_type_mbstate_t = yes; then
AC_DEFINE([HAVE_MBSTATE_T], [1],
[Define to 1 if <wchar.h> declares mbstate_t.])
else
AC_DEFINE([mbstate_t], [int],
[Define to a type if <wchar.h> does not define.])
fi
])
This diff is collapsed.
......@@ -202,13 +202,6 @@ extern void _DebPrint (const char *fmt, ...);
#endif
#endif
#ifdef emacs /* Don't do this for lib-src. */
/* Tell regex-emacs.c to use a type compatible with Emacs. */
#define RE_TRANSLATE_TYPE Lisp_Object
#define RE_TRANSLATE(TBL, C) char_table_translate (TBL, C)
#define RE_TRANSLATE_P(TBL) (!EQ (TBL, make_number (0)))
#endif
/* Tell time_rz.c to use Emacs's getter and setter for TZ.
Only Emacs uses time_rz so this is OK. */
#define getenv_TZ emacs_getenv_TZ
......
This diff is collapsed.
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment