dmbcs/guile
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add more missing Gnulib files

Browse source
This commit is contained in:
Neil Jerram 2009-01-15 00:04:02 +00:00
commit 7f8e40b778
16 changed files with 2303 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

9
lib/.gitignore vendored
View file

@ -1,9 +0,0 @@
/config.charset
/localcharset.c
/localcharset.h
/mbrlen.c
/mbrtowc.c
/mbsinit.c
/ref-add.sin
/ref-del.sin
/streq.h

649
lib/config.charset Executable file
View file

@ -0,0 +1,649 @@
#! /bin/sh
# Output a system dependent table of character encoding aliases.
#
# Copyright (C) 2000-2004, 2006-2008 Free Software Foundation, Inc.
#
# This program 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, 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 Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public License along
# with this program; if not, write to the Free Software Foundation,
# Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
#
# The table consists of lines of the form
# ALIAS CANONICAL
#
# ALIAS is the (system dependent) result of "nl_langinfo (CODESET)".
# ALIAS is compared in a case sensitive way.
#
# CANONICAL is the GNU canonical name for this character encoding.
# It must be an encoding supported by libiconv. Support by GNU libc is
# also desirable. CANONICAL is case insensitive. Usually an upper case
# MIME charset name is preferred.
# The current list of GNU canonical charset names is as follows.
#
# name MIME? used by which systems
# ASCII, ANSI_X3.4-1968 glibc solaris freebsd netbsd darwin
# ISO-8859-1 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin
# ISO-8859-2 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin
# ISO-8859-3 Y glibc solaris
# ISO-8859-4 Y osf solaris freebsd netbsd openbsd darwin
# ISO-8859-5 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin
# ISO-8859-6 Y glibc aix hpux solaris
# ISO-8859-7 Y glibc aix hpux irix osf solaris netbsd openbsd darwin
# ISO-8859-8 Y glibc aix hpux osf solaris
# ISO-8859-9 Y glibc aix hpux irix osf solaris darwin
# ISO-8859-13 glibc netbsd openbsd darwin
# ISO-8859-14 glibc
# ISO-8859-15 glibc aix osf solaris freebsd netbsd openbsd darwin
# KOI8-R Y glibc solaris freebsd netbsd openbsd darwin
# KOI8-U Y glibc freebsd netbsd openbsd darwin
# KOI8-T glibc
# CP437 dos
# CP775 dos
# CP850 aix osf dos
# CP852 dos
# CP855 dos
# CP856 aix
# CP857 dos
# CP861 dos
# CP862 dos
# CP864 dos
# CP865 dos
# CP866 freebsd netbsd openbsd darwin dos
# CP869 dos
# CP874 woe32 dos
# CP922 aix
# CP932 aix woe32 dos
# CP943 aix
# CP949 osf woe32 dos
# CP950 woe32 dos
# CP1046 aix
# CP1124 aix
# CP1125 dos
# CP1129 aix
# CP1250 woe32
# CP1251 glibc solaris netbsd openbsd darwin woe32
# CP1252 aix woe32
# CP1253 woe32
# CP1254 woe32
# CP1255 glibc woe32
# CP1256 woe32
# CP1257 woe32
# GB2312 Y glibc aix hpux irix solaris freebsd netbsd darwin
# EUC-JP Y glibc aix hpux irix osf solaris freebsd netbsd darwin
# EUC-KR Y glibc aix hpux irix osf solaris freebsd netbsd darwin
# EUC-TW glibc aix hpux irix osf solaris netbsd
# BIG5 Y glibc aix hpux osf solaris freebsd netbsd darwin
# BIG5-HKSCS glibc solaris
# GBK glibc aix osf solaris woe32 dos
# GB18030 glibc solaris netbsd
# SHIFT_JIS Y hpux osf solaris freebsd netbsd darwin
# JOHAB glibc solaris woe32
# TIS-620 glibc aix hpux osf solaris
# VISCII Y glibc
# TCVN5712-1 glibc
# GEORGIAN-PS glibc
# HP-ROMAN8 hpux
# HP-ARABIC8 hpux
# HP-GREEK8 hpux
# HP-HEBREW8 hpux
# HP-TURKISH8 hpux
# HP-KANA8 hpux
# DEC-KANJI osf
# DEC-HANYU osf
# UTF-8 Y glibc aix hpux osf solaris netbsd darwin
#
# Note: Names which are not marked as being a MIME name should not be used in
# Internet protocols for information interchange (mail, news, etc.).
#
# Note: ASCII and ANSI_X3.4-1968 are synonymous canonical names. Applications
# must understand both names and treat them as equivalent.
#
# The first argument passed to this file is the canonical host specification,
# CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM
# or
# CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM
host="$1"
os=`echo "$host" | sed -e 's/^[^-]*-[^-]*-\(.*\)$/\1/'`
echo "# This file contains a table of character encoding aliases,"
echo "# suitable for operating system '${os}'."
echo "# It was automatically generated from config.charset."
# List of references, updated during installation:
echo "# Packages using this file: "
case "$os" in
linux-gnulibc1*)
# Linux libc5 doesn't have nl_langinfo(CODESET); therefore
# localcharset.c falls back to using the full locale name
# from the environment variables.
echo "C ASCII"
echo "POSIX ASCII"
for l in af af_ZA ca ca_ES da da_DK de de_AT de_BE de_CH de_DE de_LU \
en en_AU en_BW en_CA en_DK en_GB en_IE en_NZ en_US en_ZA \
en_ZW es es_AR es_BO es_CL es_CO es_DO es_EC es_ES es_GT \
es_HN es_MX es_PA es_PE es_PY es_SV es_US es_UY es_VE et \
et_EE eu eu_ES fi fi_FI fo fo_FO fr fr_BE fr_CA fr_CH fr_FR \
fr_LU ga ga_IE gl gl_ES id id_ID in in_ID is is_IS it it_CH \
it_IT kl kl_GL nl nl_BE nl_NL no no_NO pt pt_BR pt_PT sv \
sv_FI sv_SE; do
echo "$l ISO-8859-1"
echo "$l.iso-8859-1 ISO-8859-1"
echo "$l.iso-8859-15 ISO-8859-15"
echo "$l.iso-8859-15@euro ISO-8859-15"
echo "$l@euro ISO-8859-15"
echo "$l.cp-437 CP437"
echo "$l.cp-850 CP850"
echo "$l.cp-1252 CP1252"
echo "$l.cp-1252@euro CP1252"
#echo "$l.atari-st ATARI-ST" # not a commonly used encoding
echo "$l.utf-8 UTF-8"
echo "$l.utf-8@euro UTF-8"
done
for l in cs cs_CZ hr hr_HR hu hu_HU pl pl_PL ro ro_RO sk sk_SK sl \
sl_SI sr sr_CS sr_YU; do
echo "$l ISO-8859-2"
echo "$l.iso-8859-2 ISO-8859-2"
echo "$l.cp-852 CP852"
echo "$l.cp-1250 CP1250"
echo "$l.utf-8 UTF-8"
done
for l in mk mk_MK ru ru_RU; do
echo "$l ISO-8859-5"
echo "$l.iso-8859-5 ISO-8859-5"
echo "$l.koi8-r KOI8-R"
echo "$l.cp-866 CP866"
echo "$l.cp-1251 CP1251"
echo "$l.utf-8 UTF-8"
done
for l in ar ar_SA; do
echo "$l ISO-8859-6"
echo "$l.iso-8859-6 ISO-8859-6"
echo "$l.cp-864 CP864"
#echo "$l.cp-868 CP868" # not a commonly used encoding
echo "$l.cp-1256 CP1256"
echo "$l.utf-8 UTF-8"
done
for l in el el_GR gr gr_GR; do
echo "$l ISO-8859-7"
echo "$l.iso-8859-7 ISO-8859-7"
echo "$l.cp-869 CP869"
echo "$l.cp-1253 CP1253"
echo "$l.cp-1253@euro CP1253"
echo "$l.utf-8 UTF-8"
echo "$l.utf-8@euro UTF-8"
done
for l in he he_IL iw iw_IL; do
echo "$l ISO-8859-8"
echo "$l.iso-8859-8 ISO-8859-8"
echo "$l.cp-862 CP862"
echo "$l.cp-1255 CP1255"
echo "$l.utf-8 UTF-8"
done
for l in tr tr_TR; do
echo "$l ISO-8859-9"
echo "$l.iso-8859-9 ISO-8859-9"
echo "$l.cp-857 CP857"
echo "$l.cp-1254 CP1254"
echo "$l.utf-8 UTF-8"
done
for l in lt lt_LT lv lv_LV; do
#echo "$l BALTIC" # not a commonly used encoding, wrong encoding name
echo "$l ISO-8859-13"
done
for l in ru_UA uk uk_UA; do
echo "$l KOI8-U"
done
for l in zh zh_CN; do
#echo "$l GB_2312-80" # not a commonly used encoding, wrong encoding name
echo "$l GB2312"
done
for l in ja ja_JP ja_JP.EUC; do
echo "$l EUC-JP"
done
for l in ko ko_KR; do
echo "$l EUC-KR"
done
for l in th th_TH; do
echo "$l TIS-620"
done
for l in fa fa_IR; do
#echo "$l ISIRI-3342" # a broken encoding
echo "$l.utf-8 UTF-8"
done
;;
linux* | *-gnu*)
# With glibc-2.1 or newer, we don't need any canonicalization,
# because glibc has iconv and both glibc and libiconv support all
# GNU canonical names directly. Therefore, the Makefile does not
# need to install the alias file at all.
# The following applies only to glibc-2.0.x and older libcs.
echo "ISO_646.IRV:1983 ASCII"
;;
aix*)
echo "ISO8859-1 ISO-8859-1"
echo "ISO8859-2 ISO-8859-2"
echo "ISO8859-5 ISO-8859-5"
echo "ISO8859-6 ISO-8859-6"
echo "ISO8859-7 ISO-8859-7"
echo "ISO8859-8 ISO-8859-8"
echo "ISO8859-9 ISO-8859-9"
echo "ISO8859-15 ISO-8859-15"
echo "IBM-850 CP850"
echo "IBM-856 CP856"
echo "IBM-921 ISO-8859-13"
echo "IBM-922 CP922"
echo "IBM-932 CP932"
echo "IBM-943 CP943"
echo "IBM-1046 CP1046"
echo "IBM-1124 CP1124"
echo "IBM-1129 CP1129"
echo "IBM-1252 CP1252"
echo "IBM-eucCN GB2312"
echo "IBM-eucJP EUC-JP"
echo "IBM-eucKR EUC-KR"
echo "IBM-eucTW EUC-TW"
echo "big5 BIG5"
echo "GBK GBK"
echo "TIS-620 TIS-620"
echo "UTF-8 UTF-8"
;;
hpux*)
echo "iso88591 ISO-8859-1"
echo "iso88592 ISO-8859-2"
echo "iso88595 ISO-8859-5"
echo "iso88596 ISO-8859-6"
echo "iso88597 ISO-8859-7"
echo "iso88598 ISO-8859-8"
echo "iso88599 ISO-8859-9"
echo "iso885915 ISO-8859-15"
echo "roman8 HP-ROMAN8"
echo "arabic8 HP-ARABIC8"
echo "greek8 HP-GREEK8"
echo "hebrew8 HP-HEBREW8"
echo "turkish8 HP-TURKISH8"
echo "kana8 HP-KANA8"
echo "tis620 TIS-620"
echo "big5 BIG5"
echo "eucJP EUC-JP"
echo "eucKR EUC-KR"
echo "eucTW EUC-TW"
echo "hp15CN GB2312"
#echo "ccdc ?" # what is this?
echo "SJIS SHIFT_JIS"
echo "utf8 UTF-8"
;;
irix*)
echo "ISO8859-1 ISO-8859-1"
echo "ISO8859-2 ISO-8859-2"
echo "ISO8859-5 ISO-8859-5"
echo "ISO8859-7 ISO-8859-7"
echo "ISO8859-9 ISO-8859-9"
echo "eucCN GB2312"
echo "eucJP EUC-JP"
echo "eucKR EUC-KR"
echo "eucTW EUC-TW"
;;
osf*)
echo "ISO8859-1 ISO-8859-1"
echo "ISO8859-2 ISO-8859-2"
echo "ISO8859-4 ISO-8859-4"
echo "ISO8859-5 ISO-8859-5"
echo "ISO8859-7 ISO-8859-7"
echo "ISO8859-8 ISO-8859-8"
echo "ISO8859-9 ISO-8859-9"
echo "ISO8859-15 ISO-8859-15"
echo "cp850 CP850"
echo "big5 BIG5"
echo "dechanyu DEC-HANYU"
echo "dechanzi GB2312"
echo "deckanji DEC-KANJI"
echo "deckorean EUC-KR"
echo "eucJP EUC-JP"
echo "eucKR EUC-KR"
echo "eucTW EUC-TW"
echo "GBK GBK"
echo "KSC5601 CP949"
echo "sdeckanji EUC-JP"
echo "SJIS SHIFT_JIS"
echo "TACTIS TIS-620"
echo "UTF-8 UTF-8"
;;
solaris*)
echo "646 ASCII"
echo "ISO8859-1 ISO-8859-1"
echo "ISO8859-2 ISO-8859-2"
echo "ISO8859-3 ISO-8859-3"
echo "ISO8859-4 ISO-8859-4"
echo "ISO8859-5 ISO-8859-5"
echo "ISO8859-6 ISO-8859-6"
echo "ISO8859-7 ISO-8859-7"
echo "ISO8859-8 ISO-8859-8"
echo "ISO8859-9 ISO-8859-9"
echo "ISO8859-15 ISO-8859-15"
echo "koi8-r KOI8-R"
echo "ansi-1251 CP1251"
echo "BIG5 BIG5"
echo "Big5-HKSCS BIG5-HKSCS"
echo "gb2312 GB2312"
echo "GBK GBK"
echo "GB18030 GB18030"
echo "cns11643 EUC-TW"
echo "5601 EUC-KR"
echo "ko_KR.johap92 JOHAB"
echo "eucJP EUC-JP"
echo "PCK SHIFT_JIS"
echo "TIS620.2533 TIS-620"
#echo "sun_eu_greek ?" # what is this?
echo "UTF-8 UTF-8"
;;
freebsd* | os2*)
# FreeBSD 4.2 doesn't have nl_langinfo(CODESET); therefore
# localcharset.c falls back to using the full locale name
# from the environment variables.
# Likewise for OS/2. OS/2 has XFree86 just like FreeBSD. Just
# reuse FreeBSD's locale data for OS/2.
echo "C ASCII"
echo "US-ASCII ASCII"
for l in la_LN lt_LN; do
echo "$l.ASCII ASCII"
done
for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT la_LN \
lt_LN nl_BE nl_NL no_NO pt_PT sv_SE; do
echo "$l.ISO_8859-1 ISO-8859-1"
echo "$l.DIS_8859-15 ISO-8859-15"
done
for l in cs_CZ hr_HR hu_HU la_LN lt_LN pl_PL sl_SI; do
echo "$l.ISO_8859-2 ISO-8859-2"
done
for l in la_LN lt_LT; do
echo "$l.ISO_8859-4 ISO-8859-4"
done
for l in ru_RU ru_SU; do
echo "$l.KOI8-R KOI8-R"
echo "$l.ISO_8859-5 ISO-8859-5"
echo "$l.CP866 CP866"
done
echo "uk_UA.KOI8-U KOI8-U"
echo "zh_TW.BIG5 BIG5"
echo "zh_TW.Big5 BIG5"
echo "zh_CN.EUC GB2312"
echo "ja_JP.EUC EUC-JP"
echo "ja_JP.SJIS SHIFT_JIS"
echo "ja_JP.Shift_JIS SHIFT_JIS"
echo "ko_KR.EUC EUC-KR"
;;
netbsd*)
echo "646 ASCII"
echo "ISO8859-1 ISO-8859-1"
echo "ISO8859-2 ISO-8859-2"
echo "ISO8859-4 ISO-8859-4"
echo "ISO8859-5 ISO-8859-5"
echo "ISO8859-7 ISO-8859-7"
echo "ISO8859-13 ISO-8859-13"
echo "ISO8859-15 ISO-8859-15"
echo "eucCN GB2312"
echo "eucJP EUC-JP"
echo "eucKR EUC-KR"
echo "eucTW EUC-TW"
echo "BIG5 BIG5"
echo "SJIS SHIFT_JIS"
;;
openbsd*)
echo "646 ASCII"
echo "ISO8859-1 ISO-8859-1"
echo "ISO8859-2 ISO-8859-2"
echo "ISO8859-4 ISO-8859-4"
echo "ISO8859-5 ISO-8859-5"
echo "ISO8859-7 ISO-8859-7"
echo "ISO8859-13 ISO-8859-13"
echo "ISO8859-15 ISO-8859-15"
;;
darwin[56]*)
# Darwin 6.8 doesn't have nl_langinfo(CODESET); therefore
# localcharset.c falls back to using the full locale name
# from the environment variables.
echo "C ASCII"
for l in en_AU en_CA en_GB en_US la_LN; do
echo "$l.US-ASCII ASCII"
done
for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT nl_BE \
nl_NL no_NO pt_PT sv_SE; do
echo "$l ISO-8859-1"
echo "$l.ISO8859-1 ISO-8859-1"
echo "$l.ISO8859-15 ISO-8859-15"
done
for l in la_LN; do
echo "$l.ISO8859-1 ISO-8859-1"
echo "$l.ISO8859-15 ISO-8859-15"
done
for l in cs_CZ hr_HR hu_HU la_LN pl_PL sl_SI; do
echo "$l.ISO8859-2 ISO-8859-2"
done
for l in la_LN lt_LT; do
echo "$l.ISO8859-4 ISO-8859-4"
done
for l in ru_RU; do
echo "$l.KOI8-R KOI8-R"
echo "$l.ISO8859-5 ISO-8859-5"
echo "$l.CP866 CP866"
done
for l in bg_BG; do
echo "$l.CP1251 CP1251"
done
echo "uk_UA.KOI8-U KOI8-U"
echo "zh_TW.BIG5 BIG5"
echo "zh_TW.Big5 BIG5"
echo "zh_CN.EUC GB2312"
echo "ja_JP.EUC EUC-JP"
echo "ja_JP.SJIS SHIFT_JIS"
echo "ko_KR.EUC EUC-KR"
;;
darwin*)
# Darwin 7.5 has nl_langinfo(CODESET), but it is useless:
# - It returns the empty string when LANG is set to a locale of the
# form ll_CC, although ll_CC/LC_CTYPE is a symlink to an UTF-8
# LC_CTYPE file.
# - The environment variables LANG, LC_CTYPE, LC_ALL are not set by
# the system; nl_langinfo(CODESET) returns "US-ASCII" in this case.
# - The documentation says:
# "... all code that calls BSD system routines should ensure
# that the const *char parameters of these routines are in UTF-8
# encoding. All BSD system functions expect their string
# parameters to be in UTF-8 encoding and nothing else."
# It also says
# "An additional caveat is that string parameters for files,
# paths, and other file-system entities must be in canonical
# UTF-8. In a canonical UTF-8 Unicode string, all decomposable
# characters are decomposed ..."
# but this is not true: You can pass non-decomposed UTF-8 strings
# to file system functions, and it is the OS which will convert
# them to decomposed UTF-8 before accessing the file system.
# - The Apple Terminal application displays UTF-8 by default.
# - However, other applications are free to use different encodings:
# - xterm uses ISO-8859-1 by default.
# - TextEdit uses MacRoman by default.
# We prefer UTF-8 over decomposed UTF-8-MAC because one should
# minimize the use of decomposed Unicode. Unfortunately, through the
# Darwin file system, decomposed UTF-8 strings are leaked into user
# space nevertheless.
echo "* UTF-8"
;;
beos* | haiku*)
# BeOS and Haiku have a single locale, and it has UTF-8 encoding.
echo "* UTF-8"
;;
msdosdjgpp*)
# DJGPP 2.03 doesn't have nl_langinfo(CODESET); therefore
# localcharset.c falls back to using the full locale name
# from the environment variables.
echo "#"
echo "# The encodings given here may not all be correct."
echo "# If you find that the encoding given for your language and"
echo "# country is not the one your DOS machine actually uses, just"
echo "# correct it in this file, and send a mail to"
echo "# Juan Manuel Guerrero <juan.guerrero@gmx.de>"
echo "# and Bruno Haible <bruno@clisp.org>."
echo "#"
echo "C ASCII"
# ISO-8859-1 languages
echo "ca CP850"
echo "ca_ES CP850"
echo "da CP865" # not CP850 ??
echo "da_DK CP865" # not CP850 ??
echo "de CP850"
echo "de_AT CP850"
echo "de_CH CP850"
echo "de_DE CP850"
echo "en CP850"
echo "en_AU CP850" # not CP437 ??
echo "en_CA CP850"
echo "en_GB CP850"
echo "en_NZ CP437"
echo "en_US CP437"
echo "en_ZA CP850" # not CP437 ??
echo "es CP850"
echo "es_AR CP850"
echo "es_BO CP850"
echo "es_CL CP850"
echo "es_CO CP850"
echo "es_CR CP850"
echo "es_CU CP850"
echo "es_DO CP850"
echo "es_EC CP850"
echo "es_ES CP850"
echo "es_GT CP850"
echo "es_HN CP850"
echo "es_MX CP850"
echo "es_NI CP850"
echo "es_PA CP850"
echo "es_PY CP850"
echo "es_PE CP850"
echo "es_SV CP850"
echo "es_UY CP850"
echo "es_VE CP850"
echo "et CP850"
echo "et_EE CP850"
echo "eu CP850"
echo "eu_ES CP850"
echo "fi CP850"
echo "fi_FI CP850"
echo "fr CP850"
echo "fr_BE CP850"
echo "fr_CA CP850"
echo "fr_CH CP850"
echo "fr_FR CP850"
echo "ga CP850"
echo "ga_IE CP850"
echo "gd CP850"
echo "gd_GB CP850"
echo "gl CP850"
echo "gl_ES CP850"
echo "id CP850" # not CP437 ??
echo "id_ID CP850" # not CP437 ??
echo "is CP861" # not CP850 ??
echo "is_IS CP861" # not CP850 ??
echo "it CP850"
echo "it_CH CP850"
echo "it_IT CP850"
echo "lt CP775"
echo "lt_LT CP775"
echo "lv CP775"
echo "lv_LV CP775"
echo "nb CP865" # not CP850 ??
echo "nb_NO CP865" # not CP850 ??
echo "nl CP850"
echo "nl_BE CP850"
echo "nl_NL CP850"
echo "nn CP865" # not CP850 ??
echo "nn_NO CP865" # not CP850 ??
echo "no CP865" # not CP850 ??
echo "no_NO CP865" # not CP850 ??
echo "pt CP850"
echo "pt_BR CP850"
echo "pt_PT CP850"
echo "sv CP850"
echo "sv_SE CP850"
# ISO-8859-2 languages
echo "cs CP852"
echo "cs_CZ CP852"
echo "hr CP852"
echo "hr_HR CP852"
echo "hu CP852"
echo "hu_HU CP852"
echo "pl CP852"
echo "pl_PL CP852"
echo "ro CP852"
echo "ro_RO CP852"
echo "sk CP852"
echo "sk_SK CP852"
echo "sl CP852"
echo "sl_SI CP852"
echo "sq CP852"
echo "sq_AL CP852"
echo "sr CP852" # CP852 or CP866 or CP855 ??
echo "sr_CS CP852" # CP852 or CP866 or CP855 ??
echo "sr_YU CP852" # CP852 or CP866 or CP855 ??
# ISO-8859-3 languages
echo "mt CP850"
echo "mt_MT CP850"
# ISO-8859-5 languages
echo "be CP866"
echo "be_BE CP866"
echo "bg CP866" # not CP855 ??
echo "bg_BG CP866" # not CP855 ??
echo "mk CP866" # not CP855 ??
echo "mk_MK CP866" # not CP855 ??
echo "ru CP866"
echo "ru_RU CP866"
echo "uk CP1125"
echo "uk_UA CP1125"
# ISO-8859-6 languages
echo "ar CP864"
echo "ar_AE CP864"
echo "ar_DZ CP864"
echo "ar_EG CP864"
echo "ar_IQ CP864"
echo "ar_IR CP864"
echo "ar_JO CP864"
echo "ar_KW CP864"
echo "ar_MA CP864"
echo "ar_OM CP864"
echo "ar_QA CP864"
echo "ar_SA CP864"
echo "ar_SY CP864"
# ISO-8859-7 languages
echo "el CP869"
echo "el_GR CP869"
# ISO-8859-8 languages
echo "he CP862"
echo "he_IL CP862"
# ISO-8859-9 languages
echo "tr CP857"
echo "tr_TR CP857"
# Japanese
echo "ja CP932"
echo "ja_JP CP932"
# Chinese
echo "zh_CN GBK"
echo "zh_TW CP950" # not CP938 ??
# Korean
echo "kr CP949" # not CP934 ??
echo "kr_KR CP949" # not CP934 ??
# Thai
echo "th CP874"
echo "th_TH CP874"
# Other
echo "eo CP850"
echo "eo_EO CP850"
;;
esac

462
lib/localcharset.c Normal file
View file

@ -0,0 +1,462 @@
/* Determine a canonical name for the current locale's character encoding.
Copyright (C) 2000-2006, 2008 Free Software Foundation, Inc.
This program 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, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License along
with this program; if not, write to the Free Software Foundation,
Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */
/* Written by Bruno Haible <bruno@clisp.org>. */
#include <config.h>
/* Specification. */
#include "localcharset.h"
#include <stddef.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#if defined _WIN32 || defined __WIN32__
# define WIN32_NATIVE
#endif
#if defined __EMX__
/* Assume EMX program runs on OS/2, even if compiled under DOS. */
# ifndef OS2
# define OS2
# endif
#endif
#if !defined WIN32_NATIVE
# if HAVE_LANGINFO_CODESET
# include <langinfo.h>
# else
# if 0 /* see comment below */
# include <locale.h>
# endif
# endif
# ifdef __CYGWIN__
# define WIN32_LEAN_AND_MEAN
# include <windows.h>
# endif
#elif defined WIN32_NATIVE
# define WIN32_LEAN_AND_MEAN
# include <windows.h>
#endif
#if defined OS2
# define INCL_DOS
# include <os2.h>
#endif
#if ENABLE_RELOCATABLE
# include "relocatable.h"
#else
# define relocate(pathname) (pathname)
#endif
/* Get LIBDIR. */
#ifndef LIBDIR
# include "configmake.h"
#endif
#if defined _WIN32 || defined __WIN32__ || defined __CYGWIN__ || defined __EMX__ || defined __DJGPP__
/* Win32, Cygwin, OS/2, DOS */
# define ISSLASH(C) ((C) == '/' || (C) == '\\')
#endif
#ifndef DIRECTORY_SEPARATOR
# define DIRECTORY_SEPARATOR '/'
#endif
#ifndef ISSLASH
# define ISSLASH(C) ((C) == DIRECTORY_SEPARATOR)
#endif
#if HAVE_DECL_GETC_UNLOCKED
# undef getc
# define getc getc_unlocked
#endif
/* The following static variable is declared 'volatile' to avoid a
possible multithread problem in the function get_charset_aliases. If we
are running in a threaded environment, and if two threads initialize
'charset_aliases' simultaneously, both will produce the same value,
and everything will be ok if the two assignments to 'charset_aliases'
are atomic. But I don't know what will happen if the two assignments mix. */
#if __STDC__ != 1
# define volatile /* empty */
#endif
/* Pointer to the contents of the charset.alias file, if it has already been
read, else NULL. Its format is:
ALIAS_1 '\0' CANONICAL_1 '\0' ... ALIAS_n '\0' CANONICAL_n '\0' '\0' */
static const char * volatile charset_aliases;
/* Return a pointer to the contents of the charset.alias file. */
static const char *
get_charset_aliases (void)
{
const char *cp;
cp = charset_aliases;
if (cp == NULL)
{
#if !(defined VMS || defined WIN32_NATIVE || defined __CYGWIN__)
FILE *fp;
const char *dir;
const char *base = "charset.alias";
char *file_name;
/* Make it possible to override the charset.alias location. This is
necessary for running the testsuite before "make install". */
dir = getenv ("CHARSETALIASDIR");
if (dir == NULL || dir[0] == '\0')
dir = relocate (LIBDIR);
/* Concatenate dir and base into freshly allocated file_name. */
{
size_t dir_len = strlen (dir);
size_t base_len = strlen (base);
int add_slash = (dir_len > 0 && !ISSLASH (dir[dir_len - 1]));
file_name = (char *) malloc (dir_len + add_slash + base_len + 1);
if (file_name != NULL)
{
memcpy (file_name, dir, dir_len);
if (add_slash)
file_name[dir_len] = DIRECTORY_SEPARATOR;
memcpy (file_name + dir_len + add_slash, base, base_len + 1);
}
}
if (file_name == NULL || (fp = fopen (file_name, "r")) == NULL)
/* Out of memory or file not found, treat it as empty. */
cp = "";
else
{
/* Parse the file's contents. */
char *res_ptr = NULL;
size_t res_size = 0;
for (;;)
{
int c;
char buf1[50+1];
char buf2[50+1];
size_t l1, l2;
char *old_res_ptr;
c = getc (fp);
if (c == EOF)
break;
if (c == '\n' || c == ' ' || c == '\t')
continue;
if (c == '#')
{
/* Skip comment, to end of line. */
do
c = getc (fp);
while (!(c == EOF || c == '\n'));
if (c == EOF)
break;
continue;
}
ungetc (c, fp);
if (fscanf (fp, "%50s %50s", buf1, buf2) < 2)
break;
l1 = strlen (buf1);
l2 = strlen (buf2);
old_res_ptr = res_ptr;
if (res_size == 0)
{
res_size = l1 + 1 + l2 + 1;
res_ptr = (char *) malloc (res_size + 1);
}
else
{
res_size += l1 + 1 + l2 + 1;
res_ptr = (char *) realloc (res_ptr, res_size + 1);
}
if (res_ptr == NULL)
{
/* Out of memory. */
res_size = 0;
if (old_res_ptr != NULL)
free (old_res_ptr);
break;
}
strcpy (res_ptr + res_size - (l2 + 1) - (l1 + 1), buf1);
strcpy (res_ptr + res_size - (l2 + 1), buf2);
}
fclose (fp);
if (res_size == 0)
cp = "";
else
{
*(res_ptr + res_size) = '\0';
cp = res_ptr;
}
}
if (file_name != NULL)
free (file_name);
#else
# if defined VMS
/* To avoid the troubles of an extra file charset.alias_vms in the
sources of many GNU packages, simply inline the aliases here. */
/* The list of encodings is taken from the OpenVMS 7.3-1 documentation
"Compaq C Run-Time Library Reference Manual for OpenVMS systems"
section 10.7 "Handling Different Character Sets". */
cp = "ISO8859-1" "\0" "ISO-8859-1" "\0"
"ISO8859-2" "\0" "ISO-8859-2" "\0"
"ISO8859-5" "\0" "ISO-8859-5" "\0"
"ISO8859-7" "\0" "ISO-8859-7" "\0"
"ISO8859-8" "\0" "ISO-8859-8" "\0"
"ISO8859-9" "\0" "ISO-8859-9" "\0"
/* Japanese */
"eucJP" "\0" "EUC-JP" "\0"
"SJIS" "\0" "SHIFT_JIS" "\0"
"DECKANJI" "\0" "DEC-KANJI" "\0"
"SDECKANJI" "\0" "EUC-JP" "\0"
/* Chinese */
"eucTW" "\0" "EUC-TW" "\0"
"DECHANYU" "\0" "DEC-HANYU" "\0"
"DECHANZI" "\0" "GB2312" "\0"
/* Korean */
"DECKOREAN" "\0" "EUC-KR" "\0";
# endif
# if defined WIN32_NATIVE || defined __CYGWIN__
/* To avoid the troubles of installing a separate file in the same
directory as the DLL and of retrieving the DLL's directory at
runtime, simply inline the aliases here. */
cp = "CP936" "\0" "GBK" "\0"
"CP1361" "\0" "JOHAB" "\0"
"CP20127" "\0" "ASCII" "\0"
"CP20866" "\0" "KOI8-R" "\0"
"CP20936" "\0" "GB2312" "\0"
"CP21866" "\0" "KOI8-RU" "\0"
"CP28591" "\0" "ISO-8859-1" "\0"
"CP28592" "\0" "ISO-8859-2" "\0"
"CP28593" "\0" "ISO-8859-3" "\0"
"CP28594" "\0" "ISO-8859-4" "\0"
"CP28595" "\0" "ISO-8859-5" "\0"
"CP28596" "\0" "ISO-8859-6" "\0"
"CP28597" "\0" "ISO-8859-7" "\0"
"CP28598" "\0" "ISO-8859-8" "\0"
"CP28599" "\0" "ISO-8859-9" "\0"
"CP28605" "\0" "ISO-8859-15" "\0"
"CP38598" "\0" "ISO-8859-8" "\0"
"CP51932" "\0" "EUC-JP" "\0"
"CP51936" "\0" "GB2312" "\0"
"CP51949" "\0" "EUC-KR" "\0"
"CP51950" "\0" "EUC-TW" "\0"
"CP54936" "\0" "GB18030" "\0"
"CP65001" "\0" "UTF-8" "\0";
# endif
#endif
charset_aliases = cp;
}
return cp;
}
/* Determine the current locale's character encoding, and canonicalize it
into one of the canonical names listed in config.charset.
The result must not be freed; it is statically allocated.
If the canonical name cannot be determined, the result is a non-canonical
name. */
#ifdef STATIC
STATIC
#endif
const char *
locale_charset (void)
{
const char *codeset;
const char *aliases;
#if !(defined WIN32_NATIVE || defined OS2)
# if HAVE_LANGINFO_CODESET
/* Most systems support nl_langinfo (CODESET) nowadays. */
codeset = nl_langinfo (CODESET);
# ifdef __CYGWIN__
/* Cygwin 2006 does not have locales. nl_langinfo (CODESET) always
returns "US-ASCII". As long as this is not fixed, return the suffix
of the locale name from the environment variables (if present) or
the codepage as a number. */
if (codeset != NULL && strcmp (codeset, "US-ASCII") == 0)
{
const char *locale;
static char buf[2 + 10 + 1];
locale = getenv ("LC_ALL");
if (locale == NULL || locale[0] == '\0')
{
locale = getenv ("LC_CTYPE");
if (locale == NULL || locale[0] == '\0')
locale = getenv ("LANG");
}
if (locale != NULL && locale[0] != '\0')
{
/* If the locale name contains an encoding after the dot, return
it. */
const char *dot = strchr (locale, '.');
if (dot != NULL)
{
const char *modifier;
dot++;
/* Look for the possible @... trailer and remove it, if any. */
modifier = strchr (dot, '@');
if (modifier == NULL)
return dot;
if (modifier - dot < sizeof (buf))
{
memcpy (buf, dot, modifier - dot);
buf [modifier - dot] = '\0';
return buf;
}
}
}
/* Woe32 has a function returning the locale's codepage as a number. */
sprintf (buf, "CP%u", GetACP ());
codeset = buf;
}
# endif
# else
/* On old systems which lack it, use setlocale or getenv. */
const char *locale = NULL;
/* But most old systems don't have a complete set of locales. Some
(like SunOS 4 or DJGPP) have only the C locale. Therefore we don't
use setlocale here; it would return "C" when it doesn't support the
locale name the user has set. */
# if 0
locale = setlocale (LC_CTYPE, NULL);
# endif
if (locale == NULL || locale[0] == '\0')
{
locale = getenv ("LC_ALL");
if (locale == NULL || locale[0] == '\0')
{
locale = getenv ("LC_CTYPE");
if (locale == NULL || locale[0] == '\0')
locale = getenv ("LANG");
}
}
/* On some old systems, one used to set locale = "iso8859_1". On others,
you set it to "language_COUNTRY.charset". In any case, we resolve it
through the charset.alias file. */
codeset = locale;
# endif
#elif defined WIN32_NATIVE
static char buf[2 + 10 + 1];
/* Woe32 has a function returning the locale's codepage as a number. */
sprintf (buf, "CP%u", GetACP ());
codeset = buf;
#elif defined OS2
const char *locale;
static char buf[2 + 10 + 1];
ULONG cp[3];
ULONG cplen;
/* Allow user to override the codeset, as set in the operating system,
with standard language environment variables. */
locale = getenv ("LC_ALL");
if (locale == NULL || locale[0] == '\0')
{
locale = getenv ("LC_CTYPE");
if (locale == NULL || locale[0] == '\0')
locale = getenv ("LANG");
}
if (locale != NULL && locale[0] != '\0')
{
/* If the locale name contains an encoding after the dot, return it. */
const char *dot = strchr (locale, '.');
if (dot != NULL)
{
const char *modifier;
dot++;
/* Look for the possible @... trailer and remove it, if any. */
modifier = strchr (dot, '@');
if (modifier == NULL)
return dot;
if (modifier - dot < sizeof (buf))
{
memcpy (buf, dot, modifier - dot);
buf [modifier - dot] = '\0';
return buf;
}
}
/* Resolve through the charset.alias file. */
codeset = locale;
}
else
{
/* OS/2 has a function returning the locale's codepage as a number. */
if (DosQueryCp (sizeof (cp), cp, &cplen))
codeset = "";
else
{
sprintf (buf, "CP%u", cp[0]);
codeset = buf;
}
}
#endif
if (codeset == NULL)
/* The canonical name cannot be determined. */
codeset = "";
/* Resolve alias. */
for (aliases = get_charset_aliases ();
*aliases != '\0';
aliases += strlen (aliases) + 1, aliases += strlen (aliases) + 1)
if (strcmp (codeset, aliases) == 0
|| (aliases[0] == '*' && aliases[1] == '\0'))
{
codeset = aliases + strlen (aliases) + 1;
break;
}
/* Don't return an empty string. GNU libc and GNU libiconv interpret
the empty string as denoting "the locale's character encoding",
thus GNU libiconv would call this function a second time. */
if (codeset[0] == '\0')
codeset = "ASCII";
return codeset;
}

41
lib/localcharset.h Normal file
View file

@ -0,0 +1,41 @@
/* Determine a canonical name for the current locale's character encoding.
Copyright (C) 2000-2003 Free Software Foundation, Inc.
This file is part of the GNU CHARSET Library.
This program 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, 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License along
with this program; if not, write to the Free Software Foundation,
Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. */
#ifndef _LOCALCHARSET_H
#define _LOCALCHARSET_H
#ifdef __cplusplus
extern "C" {
#endif
/* Determine the current locale's character encoding, and canonicalize it
into one of the canonical names listed in config.charset.
The result must not be freed; it is statically allocated.
If the canonical name cannot be determined, the result is a non-canonical
name. */
extern const char * locale_charset (void);
#ifdef __cplusplus
}
#endif
#endif /* _LOCALCHARSET_H */

32
lib/mbrlen.c Normal file
View file

@ -0,0 +1,32 @@
/* Recognize multibyte character.
Copyright (C) 1999-2000, 2008 Free Software Foundation, Inc.
Written by Bruno Haible <bruno@clisp.org>, 2008.
This program 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 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include <wchar.h>
static mbstate_t internal_state;
size_t
mbrlen (const char *s, size_t n, mbstate_t *ps)
{
if (ps == NULL)
ps = &internal_state;
return mbrtowc (NULL, s, n, ps);
}

349
lib/mbrtowc.c Normal file
View file

@ -0,0 +1,349 @@
/* Convert multibyte character to wide character.
Copyright (C) 1999-2002, 2005-2008 Free Software Foundation, Inc.
Written by Bruno Haible <bruno@clisp.org>, 2008.
This program 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 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include <wchar.h>
#if GNULIB_defined_mbstate_t
/* Implement mbrtowc() on top of mbtowc(). */
# include <errno.h>
# include <stdlib.h>
# include "localcharset.h"
# include "streq.h"
# include "verify.h"
verify (sizeof (mbstate_t) >= 4);
static char internal_state[4];
size_t
mbrtowc (wchar_t *pwc, const char *s, size_t n, mbstate_t *ps)
{
char *pstate = (char *)ps;
if (pstate == NULL)
pstate = internal_state;
if (s == NULL)
{
pwc = NULL;
s = "";
n = 1;
}
if (n == 0)
return (size_t)(-2);
/* Here n > 0. */
{
size_t nstate = pstate[0];
char buf[4];
const char *p;
size_t m;
switch (nstate)
{
case 0:
p = s;
m = n;
break;
case 3:
buf[2] = pstate[3];
/*FALLTHROUGH*/
case 2:
buf[1] = pstate[2];
/*FALLTHROUGH*/
case 1:
buf[0] = pstate[1];
p = buf;
m = nstate;
buf[m++] = s[0];
if (n >= 2 && m < 4)
{
buf[m++] = s[1];
if (n >= 3 && m < 4)
buf[m++] = s[2];
}
break;
default:
errno = EINVAL;
return (size_t)(-1);
}
/* Here 0 < m ≤ 4. */
# if __GLIBC__
/* Work around bug <http://sourceware.org/bugzilla/show_bug.cgi?id=9674> */
mbtowc (NULL, NULL, 0);
# endif
{
int res = mbtowc (pwc, p, m);
if (res >= 0)
{
if (pwc != NULL && ((*pwc == 0) != (res == 0)))
abort ();
if (nstate >= (res > 0 ? res : 1))
abort ();
res -= nstate;
pstate[0] = 0;
return res;
}
/* mbtowc does not distinguish between invalid and incomplete multibyte
sequences. But mbrtowc needs to make this distinction.
There are two possible approaches:
- Use iconv() and its return value.
- Use built-in knowledge about the possible encodings.
Given the low quality of implementation of iconv() on the systems that
lack mbrtowc(), we use the second approach.
The possible encodings are:
- 8-bit encodings,
- EUC-JP, EUC-KR, GB2312, EUC-TW, BIG5, SJIS,
- UTF-8.
Use specialized code for each. */
if (m >= 4 || m >= MB_CUR_MAX)
goto invalid;
/* Here MB_CUR_MAX > 1 and 0 < m < 4. */
{
const char *encoding = locale_charset ();
if (STREQ (encoding, "UTF-8", 'U', 'T', 'F', '-', '8', 0, 0, 0, 0))
{
/* Cf. unistr/u8-mblen.c. */
unsigned char c = (unsigned char) p[0];
if (c >= 0xc2)
{
if (c < 0xe0)
{
if (m == 1)
goto incomplete;
}
else if (c < 0xf0)
{
if (m == 1)
goto incomplete;
if (m == 2)
{
unsigned char c2 = (unsigned char) p[1];
if ((c2 ^ 0x80) < 0x40
&& (c >= 0xe1 || c2 >= 0xa0)
&& (c != 0xed || c2 < 0xa0))
goto incomplete;
}
}
else if (c <= 0xf4)
{
if (m == 1)
goto incomplete;
else /* m == 2 || m == 3 */
{
unsigned char c2 = (unsigned char) p[1];
if ((c2 ^ 0x80) < 0x40
&& (c >= 0xf1 || c2 >= 0x90)
&& (c < 0xf4 || (c == 0xf4 && c2 < 0x90)))
{
if (m == 2)
goto incomplete;
else /* m == 3 */
{
unsigned char c3 = (unsigned char) p[2];
if ((c3 ^ 0x80) < 0x40)
goto incomplete;
}
}
}
}
}
goto invalid;
}
/* As a reference for this code, you can use the GNU libiconv
implementation. Look for uses of the RET_TOOFEW macro. */
if (STREQ (encoding, "EUC-JP", 'E', 'U', 'C', '-', 'J', 'P', 0, 0, 0))
{
if (m == 1)
{
unsigned char c = (unsigned char) p[0];
if ((c >= 0xa1 && c < 0xff) || c == 0x8e || c == 0x8f)
goto incomplete;
}
if (m == 2)
{
unsigned char c = (unsigned char) p[0];
if (c == 0x8f)
{
unsigned char c2 = (unsigned char) p[1];
if (c2 >= 0xa1 && c2 < 0xff)
goto incomplete;
}
}
goto invalid;
}
if (STREQ (encoding, "EUC-KR", 'E', 'U', 'C', '-', 'K', 'R', 0, 0, 0)
|| STREQ (encoding, "GB2312", 'G', 'B', '2', '3', '1', '2', 0, 0, 0)
|| STREQ (encoding, "BIG5", 'B', 'I', 'G', '5', 0, 0, 0, 0, 0))
{
if (m == 1)
{
unsigned char c = (unsigned char) p[0];
if (c >= 0xa1 && c < 0xff)
goto incomplete;
}
goto invalid;
}
if (STREQ (encoding, "EUC-TW", 'E', 'U', 'C', '-', 'T', 'W', 0, 0, 0))
{
if (m == 1)
{
unsigned char c = (unsigned char) p[0];
if ((c >= 0xa1 && c < 0xff) || c == 0x8e)
goto incomplete;
}
else /* m == 2 || m == 3 */
{
unsigned char c = (unsigned char) p[0];
if (c == 0x8e)
goto incomplete;
}
goto invalid;
}
if (STREQ (encoding, "SJIS", 'S', 'J', 'I', 'S', 0, 0, 0, 0, 0))
{
if (m == 1)
{
unsigned char c = (unsigned char) p[0];
if ((c >= 0x81 && c <= 0x9f) || (c >= 0xe0 && c <= 0xea)
|| (c >= 0xf0 && c <= 0xf9))
goto incomplete;
}
goto invalid;
}
/* An unknown multibyte encoding. */
goto incomplete;
}
incomplete:
{
size_t k = nstate;
/* Here 0 < k < m < 4. */
pstate[++k] = s[0];
if (k < m)
pstate[++k] = s[1];
if (k != m)
abort ();
}
pstate[0] = m;
return (size_t)(-2);
invalid:
errno = EILSEQ;
/* The conversion state is undefined, says POSIX. */
return (size_t)(-1);
}
}
}
#else
/* Override the system's mbrtowc() function. */
# undef mbrtowc
size_t
rpl_mbrtowc (wchar_t *pwc, const char *s, size_t n, mbstate_t *ps)
{
# if MBRTOWC_NULL_ARG_BUG || MBRTOWC_RETVAL_BUG
if (s == NULL)
{
pwc = NULL;
s = "";
n = 1;
}
# endif
# if MBRTOWC_RETVAL_BUG
{
static mbstate_t internal_state;
/* Override mbrtowc's internal state. We can not call mbsinit() on the
hidden internal state, but we can call it on our variable. */
if (ps == NULL)
ps = &internal_state;
if (!mbsinit (ps))
{
/* Parse the rest of the multibyte character byte for byte. */
size_t count = 0;
for (; n > 0; s++, n--)
{
wchar_t wc;
size_t ret = mbrtowc (&wc, s, 1, ps);
if (ret == (size_t)(-1))
return (size_t)(-1);
count++;
if (ret != (size_t)(-2))
{
/* The multibyte character has been completed. */
if (pwc != NULL)
*pwc = wc;
return (wc == 0 ? 0 : count);
}
}
return (size_t)(-2);
}
}
# endif
# if MBRTOWC_NUL_RETVAL_BUG
{
wchar_t wc;
size_t ret = mbrtowc (&wc, s, n, ps);
if (ret != (size_t)(-1) && ret != (size_t)(-2))
{
if (pwc != NULL)
*pwc = wc;
if (wc == 0)
ret = 0;
}
return ret;
}
# else
return mbrtowc (pwc, s, n, ps);
# endif
}
#endif

47
lib/mbsinit.c Normal file
View file

@ -0,0 +1,47 @@
/* Test for initial conversion state.
Copyright (C) 2008 Free Software Foundation, Inc.
Written by Bruno Haible <bruno@clisp.org>, 2008.
This program 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 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 Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
#include <config.h>
/* Specification. */
#include <wchar.h>
#include "verify.h"
/* Platforms that lack mbsinit() also lack mbrlen(), mbrtowc(), mbsrtowcs()
and wcrtomb(), wcsrtombs().
We assume that
- sizeof (mbstate_t) >= 4,
- only stateless encodings are supported (such as UTF-8 and EUC-JP, but
not ISO-2022 variants),
- for each encoding, the number of bytes for a wide character is <= 4.
(This maximum is attained for UTF-8, GB18030, EUC-TW.)
We define the meaning of mbstate_t as follows:
- In mb -> wc direction, mbstate_t's first byte contains the number of
buffered bytes (in the range 0..3), followed by up to 3 buffered bytes.
- In wc -> mb direction, mbstate_t contains no information. In other
words, it is always in the initial state. */
verify (sizeof (mbstate_t) >= 4);
int
mbsinit (const mbstate_t *ps)
{
const char *pstate = (const char *)ps;
return pstate[0] == 0;
}

30
lib/ref-add.sin Normal file
View file

@ -0,0 +1,30 @@
# Add this package to a list of references stored in a text file.
#
# Copyright (C) 2000 Free Software Foundation, Inc.
#
# This program 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, 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 Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public License along
# with this program; if not, write to the Free Software Foundation,
# Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
#
# Written by Bruno Haible <haible@clisp.cons.org>.
#
/^# Packages using this file: / {
s/# Packages using this file://
ta
:a
s/ @PACKAGE@ / @PACKAGE@ /
tb
s/ $/ @PACKAGE@ /
:b
s/^/# Packages using this file:/
}

25
lib/ref-del.sin Normal file
View file

@ -0,0 +1,25 @@
# Remove this package from a list of references stored in a text file.
#
# Copyright (C) 2000 Free Software Foundation, Inc.
#
# This program 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, 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 Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public License along
# with this program; if not, write to the Free Software Foundation,
# Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
#
# Written by Bruno Haible <haible@clisp.cons.org>.
#
/^# Packages using this file: / {
s/# Packages using this file://
s/ @PACKAGE@ / /
s/^/# Packages using this file:/
}

176
lib/streq.h Normal file
View file

@ -0,0 +1,176 @@
/* Optimized string comparison.
Copyright (C) 2001-2002, 2007 Free Software Foundation, Inc.
This program 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 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
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public License
along with this program. If not, see <http://www.gnu.org/licenses/>. */
/* Written by Bruno Haible <bruno@clisp.org>. */
#ifndef _GL_STREQ_H
#define _GL_STREQ_H
#include <string.h>
/* STREQ allows to optimize string comparison with a small literal string.
STREQ (s, "EUC-KR", 'E', 'U', 'C', '-', 'K', 'R', 0, 0, 0)
is semantically equivalent to
strcmp (s, "EUC-KR") == 0
just faster. */
/* Help GCC to generate good code for string comparisons with
immediate strings. */
#if defined (__GNUC__) && defined (__OPTIMIZE__)
static inline int
streq9 (const char *s1, const char *s2)
{
return strcmp (s1 + 9, s2 + 9) == 0;
}
static inline int
streq8 (const char *s1, const char *s2, char s28)
{
if (s1[8] == s28)
{
if (s28 == 0)
return 1;
else
return streq9 (s1, s2);
}
else
return 0;
}
static inline int
streq7 (const char *s1, const char *s2, char s27, char s28)
{
if (s1[7] == s27)
{
if (s27 == 0)
return 1;
else
return streq8 (s1, s2, s28);
}
else
return 0;
}
static inline int
streq6 (const char *s1, const char *s2, char s26, char s27, char s28)
{
if (s1[6] == s26)
{
if (s26 == 0)
return 1;
else
return streq7 (s1, s2, s27, s28);
}
else
return 0;
}
static inline int
streq5 (const char *s1, const char *s2, char s25, char s26, char s27, char s28)
{
if (s1[5] == s25)
{
if (s25 == 0)
return 1;
else
return streq6 (s1, s2, s26, s27, s28);
}
else
return 0;
}
static inline int
streq4 (const char *s1, const char *s2, char s24, char s25, char s26, char s27, char s28)
{
if (s1[4] == s24)
{
if (s24 == 0)
return 1;
else
return streq5 (s1, s2, s25, s26, s27, s28);
}
else
return 0;
}
static inline int
streq3 (const char *s1, const char *s2, char s23, char s24, char s25, char s26, char s27, char s28)
{
if (s1[3] == s23)
{
if (s23 == 0)
return 1;
else
return streq4 (s1, s2, s24, s25, s26, s27, s28);
}
else
return 0;
}
static inline int
streq2 (const char *s1, const char *s2, char s22, char s23, char s24, char s25, char s26, char s27, char s28)
{
if (s1[2] == s22)
{
if (s22 == 0)
return 1;
else
return streq3 (s1, s2, s23, s24, s25, s26, s27, s28);
}
else
return 0;
}
static inline int
streq1 (const char *s1, const char *s2, char s21, char s22, char s23, char s24, char s25, char s26, char s27, char s28)
{
if (s1[1] == s21)
{
if (s21 == 0)
return 1;
else
return streq2 (s1, s2, s22, s23, s24, s25, s26, s27, s28);
}
else
return 0;
}
static inline int
streq0 (const char *s1, const char *s2, char s20, char s21, char s22, char s23, char s24, char s25, char s26, char s27, char s28)
{
if (s1[0] == s20)
{
if (s20 == 0)
return 1;
else
return streq1 (s1, s2, s21, s22, s23, s24, s25, s26, s27, s28);
}
else
return 0;
}
#define STREQ(s1,s2,s20,s21,s22,s23,s24,s25,s26,s27,s28) \
streq0 (s1, s2, s20, s21, s22, s23, s24, s25, s26, s27, s28)
#else
#define STREQ(s1,s2,s20,s21,s22,s23,s24,s25,s26,s27,s28) \
(strcmp (s1, s2) == 0)
#endif
#endif /* _GL_STREQ_H */

8
m4/.gitignore vendored
View file

@ -1,8 +0,0 @@
/libtool.m4
/lt*.m4
/codeset.m4
/glibc21.m4
/gnulib-comp.m4
/locale-fr.m4
/locale-ja.m4
/locale-zh.m4

21
m4/codeset.m4 Normal file
View file

@ -0,0 +1,21 @@
# codeset.m4 serial 3 (gettext-0.18)
dnl Copyright (C) 2000-2002, 2006, 2008 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 From Bruno Haible.
AC_DEFUN([AM_LANGINFO_CODESET],
[
AC_CACHE_CHECK([for nl_langinfo and CODESET], [am_cv_langinfo_codeset],
[AC_TRY_LINK([#include <langinfo.h>],
[char* cs = nl_langinfo(CODESET); return !cs;],
[am_cv_langinfo_codeset=yes],
[am_cv_langinfo_codeset=no])
])
if test $am_cv_langinfo_codeset = yes; then
AC_DEFINE([HAVE_LANGINFO_CODESET], 1,
[Define if you have <langinfo.h> and nl_langinfo(CODESET).])
fi
])

30
m4/glibc21.m4 Normal file
View file

@ -0,0 +1,30 @@
# glibc21.m4 serial 4
dnl Copyright (C) 2000-2002, 2004, 2008 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.
# Test for the GNU C Library, version 2.1 or newer.
# From Bruno Haible.
AC_DEFUN([gl_GLIBC21],
[
AC_CACHE_CHECK([whether we are using the GNU C Library 2.1 or newer],
[ac_cv_gnu_library_2_1],
[AC_EGREP_CPP([Lucky GNU user],
[
#include <features.h>
#ifdef __GNU_LIBRARY__
#if (__GLIBC__ == 2 && __GLIBC_MINOR__ >= 1) || (__GLIBC__ > 2)
Lucky GNU user
#endif
#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"
]
)

204
m4/locale-fr.m4 Normal file
View file

@ -0,0 +1,204 @@
# locale-fr.m4 serial 9
dnl Copyright (C) 2003, 2005-2008 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 From Bruno Haible.
dnl Determine the name of a french locale with traditional encoding.
AC_DEFUN([gt_LOCALE_FR],
[
AC_REQUIRE([AC_CANONICAL_HOST])
AC_REQUIRE([AM_LANGINFO_CODESET])
AC_CACHE_CHECK([for a traditional french locale], gt_cv_locale_fr, [
macosx=
changequote(,)dnl
case "$host_os" in
darwin[56]*) ;;
darwin*) macosx=yes;;
esac
changequote([,])dnl
if test -n "$macosx"; then
# On Darwin 7 (MacOS X), the libc supports some locales in non-UTF-8
# encodings, but the kernel does not support them. The documentation
# says:
# "... all code that calls BSD system routines should ensure
# that the const *char parameters of these routines are in UTF-8
# encoding. All BSD system functions expect their string
# parameters to be in UTF-8 encoding and nothing else."
# See the comments in config.charset. Therefore we bypass the test.
gt_cv_locale_fr=none
else
AC_LANG_CONFTEST([AC_LANG_SOURCE([
changequote(,)dnl
#include <locale.h>
#include <time.h>
#if HAVE_LANGINFO_CODESET
# include <langinfo.h>
#endif
#include <stdlib.h>
#include <string.h>
struct tm t;
char buf[16];
int main () {
/* Check whether the given locale name is recognized by the system. */
if (setlocale (LC_ALL, "") == NULL) return 1;
/* Check whether nl_langinfo(CODESET) is nonempty and not "ASCII" or "646".
On MacOS X 10.3.5 (Darwin 7.5) in the fr_FR locale, nl_langinfo(CODESET)
is empty, and the behaviour of Tcl 8.4 in this locale is not useful.
On OpenBSD 4.0, when an unsupported locale is specified, setlocale()
succeeds but then nl_langinfo(CODESET) is "646". In this situation,
some unit tests fail. */
#if HAVE_LANGINFO_CODESET
{
const char *cs = nl_langinfo (CODESET);
if (cs[0] == '\0' || strcmp (cs, "ASCII") == 0 || strcmp (cs, "646") == 0)
return 1;
}
#endif
#ifdef __CYGWIN__
/* On Cygwin, avoid locale names without encoding suffix, because the
locale_charset() function relies on the encoding suffix. Note that
LC_ALL is set on the command line. */
if (strchr (getenv ("LC_ALL"), '.') == NULL) return 1;
#endif
/* Check whether in the abbreviation of the second month, the second
character (should be U+00E9: LATIN SMALL LETTER E WITH ACUTE) is only
one byte long. This excludes the UTF-8 encoding. */
t.tm_year = 1975 - 1900; t.tm_mon = 2 - 1; t.tm_mday = 4;
if (strftime (buf, sizeof (buf), "%b", &t) < 3 || buf[2] != 'v') return 1;
/* Check whether the decimal separator is a comma.
On NetBSD 3.0 in the fr_FR.ISO8859-1 locale, localeconv()->decimal_point
are nl_langinfo(RADIXCHAR) are both ".". */
if (localeconv () ->decimal_point[0] != ',') return 1;
return 0;
}
changequote([,])dnl
])])
if AC_TRY_EVAL([ac_link]) && test -s conftest$ac_exeext; then
# Setting LC_ALL is not enough. Need to set LC_TIME to empty, because
# otherwise on MacOS X 10.3.5 the LC_TIME=C from the beginning of the
# configure script would override the LC_ALL setting. Likewise for
# LC_CTYPE, which is also set at the beginning of the configure script.
# Test for the usual locale name.
if (LC_ALL=fr_FR LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_fr=fr_FR
else
# Test for the locale name with explicit encoding suffix.
if (LC_ALL=fr_FR.ISO-8859-1 LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_fr=fr_FR.ISO-8859-1
else
# Test for the AIX, OSF/1, FreeBSD, NetBSD, OpenBSD locale name.
if (LC_ALL=fr_FR.ISO8859-1 LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_fr=fr_FR.ISO8859-1
else
# Test for the HP-UX locale name.
if (LC_ALL=fr_FR.iso88591 LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_fr=fr_FR.iso88591
else
# Test for the Solaris 7 locale name.
if (LC_ALL=fr LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_fr=fr
else
# None found.
gt_cv_locale_fr=none
fi
fi
fi
fi
fi
fi
rm -fr conftest*
fi
])
LOCALE_FR=$gt_cv_locale_fr
AC_SUBST([LOCALE_FR])
])
dnl Determine the name of a french locale with UTF-8 encoding.
AC_DEFUN([gt_LOCALE_FR_UTF8],
[
AC_REQUIRE([AM_LANGINFO_CODESET])
AC_CACHE_CHECK([for a french Unicode locale], gt_cv_locale_fr_utf8, [
AC_LANG_CONFTEST([AC_LANG_SOURCE([
changequote(,)dnl
#include <locale.h>
#include <time.h>
#if HAVE_LANGINFO_CODESET
# include <langinfo.h>
#endif
#include <stdlib.h>
#include <string.h>
struct tm t;
char buf[16];
int main () {
/* On BeOS and Haiku, locales are not implemented in libc. Rather, libintl
imitates locale dependent behaviour by looking at the environment
variables, and all locales use the UTF-8 encoding. */
#if !(defined __BEOS__ || defined __HAIKU__)
/* Check whether the given locale name is recognized by the system. */
if (setlocale (LC_ALL, "") == NULL) return 1;
/* Check whether nl_langinfo(CODESET) is nonempty and not "ASCII" or "646".
On MacOS X 10.3.5 (Darwin 7.5) in the fr_FR locale, nl_langinfo(CODESET)
is empty, and the behaviour of Tcl 8.4 in this locale is not useful.
On OpenBSD 4.0, when an unsupported locale is specified, setlocale()
succeeds but then nl_langinfo(CODESET) is "646". In this situation,
some unit tests fail. */
# if HAVE_LANGINFO_CODESET
{
const char *cs = nl_langinfo (CODESET);
if (cs[0] == '\0' || strcmp (cs, "ASCII") == 0 || strcmp (cs, "646") == 0)
return 1;
}
# endif
# ifdef __CYGWIN__
/* On Cygwin, avoid locale names without encoding suffix, because the
locale_charset() function relies on the encoding suffix. Note that
LC_ALL is set on the command line. */
if (strchr (getenv ("LC_ALL"), '.') == NULL) return 1;
# endif
/* Check whether in the abbreviation of the second month, the second
character (should be U+00E9: LATIN SMALL LETTER E WITH ACUTE) is
two bytes long, with UTF-8 encoding. */
t.tm_year = 1975 - 1900; t.tm_mon = 2 - 1; t.tm_mday = 4;
if (strftime (buf, sizeof (buf), "%b", &t) < 4
|| buf[1] != (char) 0xc3 || buf[2] != (char) 0xa9 || buf[3] != 'v')
return 1;
#endif
/* Check whether the decimal separator is a comma.
On NetBSD 3.0 in the fr_FR.ISO8859-1 locale, localeconv()->decimal_point
are nl_langinfo(RADIXCHAR) are both ".". */
if (localeconv () ->decimal_point[0] != ',') return 1;
return 0;
}
changequote([,])dnl
])])
if AC_TRY_EVAL([ac_link]) && test -s conftest$ac_exeext; then
# Setting LC_ALL is not enough. Need to set LC_TIME to empty, because
# otherwise on MacOS X 10.3.5 the LC_TIME=C from the beginning of the
# configure script would override the LC_ALL setting. Likewise for
# LC_CTYPE, which is also set at the beginning of the configure script.
# Test for the usual locale name.
if (LC_ALL=fr_FR LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_fr_utf8=fr_FR
else
# Test for the locale name with explicit encoding suffix.
if (LC_ALL=fr_FR.UTF-8 LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_fr_utf8=fr_FR.UTF-8
else
# Test for the Solaris 7 locale name.
if (LC_ALL=fr.UTF-8 LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_fr_utf8=fr.UTF-8
else
# None found.
gt_cv_locale_fr_utf8=none
fi
fi
fi
fi
rm -fr conftest*
])
LOCALE_FR_UTF8=$gt_cv_locale_fr_utf8
AC_SUBST([LOCALE_FR_UTF8])
])

126
m4/locale-ja.m4 Normal file
View file

@ -0,0 +1,126 @@
# locale-ja.m4 serial 5
dnl Copyright (C) 2003, 2005-2008 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 From Bruno Haible.
dnl Determine the name of a japanese locale with EUC-JP encoding.
AC_DEFUN([gt_LOCALE_JA],
[
AC_REQUIRE([AC_CANONICAL_HOST])
AC_REQUIRE([AM_LANGINFO_CODESET])
AC_CACHE_CHECK([for a traditional japanese locale], gt_cv_locale_ja, [
macosx=
changequote(,)dnl
case "$host_os" in
darwin[56]*) ;;
darwin*) macosx=yes;;
esac
changequote([,])dnl
if test -n "$macosx"; then
# On Darwin 7 (MacOS X), the libc supports some locales in non-UTF-8
# encodings, but the kernel does not support them. The documentation
# says:
# "... all code that calls BSD system routines should ensure
# that the const *char parameters of these routines are in UTF-8
# encoding. All BSD system functions expect their string
# parameters to be in UTF-8 encoding and nothing else."
# See the comments in config.charset. Therefore we bypass the test.
gt_cv_locale_ja=none
else
AC_LANG_CONFTEST([AC_LANG_SOURCE([
changequote(,)dnl
#include <locale.h>
#include <time.h>
#if HAVE_LANGINFO_CODESET
# include <langinfo.h>
#endif
#include <stdlib.h>
#include <string.h>
struct tm t;
char buf[16];
int main ()
{
const char *p;
/* Check whether the given locale name is recognized by the system. */
if (setlocale (LC_ALL, "") == NULL) return 1;
/* Check whether nl_langinfo(CODESET) is nonempty and not "ASCII" or "646".
On MacOS X 10.3.5 (Darwin 7.5) in the fr_FR locale, nl_langinfo(CODESET)
is empty, and the behaviour of Tcl 8.4 in this locale is not useful.
On OpenBSD 4.0, when an unsupported locale is specified, setlocale()
succeeds but then nl_langinfo(CODESET) is "646". In this situation,
some unit tests fail. */
#if HAVE_LANGINFO_CODESET
{
const char *cs = nl_langinfo (CODESET);
if (cs[0] == '\0' || strcmp (cs, "ASCII") == 0 || strcmp (cs, "646") == 0)
return 1;
}
#endif
#ifdef __CYGWIN__
/* On Cygwin, avoid locale names without encoding suffix, because the
locale_charset() function relies on the encoding suffix. Note that
LC_ALL is set on the command line. */
if (strchr (getenv ("LC_ALL"), '.') == NULL) return 1;
#endif
/* Check whether MB_CUR_MAX is > 1. This excludes the dysfunctional locales
on Cygwin 1.5.x. */
if (MB_CUR_MAX == 1)
return 1;
/* Check whether in a month name, no byte in the range 0x80..0x9F occurs.
This excludes the UTF-8 encoding. */
t.tm_year = 1975 - 1900; t.tm_mon = 2 - 1; t.tm_mday = 4;
if (strftime (buf, sizeof (buf), "%B", &t) < 2) return 1;
for (p = buf; *p != '\0'; p++)
if ((unsigned char) *p >= 0x80 && (unsigned char) *p < 0xa0)
return 1;
return 0;
}
changequote([,])dnl
])])
if AC_TRY_EVAL([ac_link]) && test -s conftest$ac_exeext; then
# Setting LC_ALL is not enough. Need to set LC_TIME to empty, because
# otherwise on MacOS X 10.3.5 the LC_TIME=C from the beginning of the
# configure script would override the LC_ALL setting. Likewise for
# LC_CTYPE, which is also set at the beginning of the configure script.
# Test for the AIX locale name.
if (LC_ALL=ja_JP LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_ja=ja_JP
else
# Test for the locale name with explicit encoding suffix.
if (LC_ALL=ja_JP.EUC-JP LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_ja=ja_JP.EUC-JP
else
# Test for the HP-UX, OSF/1, NetBSD locale name.
if (LC_ALL=ja_JP.eucJP LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_ja=ja_JP.eucJP
else
# Test for the IRIX, FreeBSD locale name.
if (LC_ALL=ja_JP.EUC LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_ja=ja_JP.EUC
else
# Test for the Solaris 7 locale name.
if (LC_ALL=ja LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_ja=ja
else
# Special test for NetBSD 1.6.
if test -f /usr/share/locale/ja_JP.eucJP/LC_CTYPE; then
gt_cv_locale_ja=ja_JP.eucJP
else
# None found.
gt_cv_locale_ja=none
fi
fi
fi
fi
fi
fi
fi
rm -fr conftest*
fi
])
LOCALE_JA=$gt_cv_locale_ja
AC_SUBST([LOCALE_JA])
])

111
m4/locale-zh.m4 Normal file
View file

@ -0,0 +1,111 @@
# locale-zh.m4 serial 4
dnl Copyright (C) 2003, 2005-2008 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 From Bruno Haible.
dnl Determine the name of a chinese locale with GB18030 encoding.
AC_DEFUN([gt_LOCALE_ZH_CN],
[
AC_REQUIRE([AC_CANONICAL_HOST])
AC_REQUIRE([AM_LANGINFO_CODESET])
AC_CACHE_CHECK([for a transitional chinese locale], gt_cv_locale_zh_CN, [
macosx=
changequote(,)dnl
case "$host_os" in
darwin[56]*) ;;
darwin*) macosx=yes;;
esac
changequote([,])dnl
if test -n "$macosx"; then
# On Darwin 7 (MacOS X), the libc supports some locales in non-UTF-8
# encodings, but the kernel does not support them. The documentation
# says:
# "... all code that calls BSD system routines should ensure
# that the const *char parameters of these routines are in UTF-8
# encoding. All BSD system functions expect their string
# parameters to be in UTF-8 encoding and nothing else."
# See the comments in config.charset. Therefore we bypass the test.
gt_cv_locale_zh_CN=none
else
AC_LANG_CONFTEST([AC_LANG_SOURCE([
changequote(,)dnl
#include <locale.h>
#include <stdlib.h>
#include <time.h>
#if HAVE_LANGINFO_CODESET
# include <langinfo.h>
#endif
#include <stdlib.h>
#include <string.h>
struct tm t;
char buf[16];
int main ()
{
const char *p;
/* Check whether the given locale name is recognized by the system. */
if (setlocale (LC_ALL, "") == NULL) return 1;
/* Check whether nl_langinfo(CODESET) is nonempty and not "ASCII" or "646".
On MacOS X 10.3.5 (Darwin 7.5) in the fr_FR locale, nl_langinfo(CODESET)
is empty, and the behaviour of Tcl 8.4 in this locale is not useful.
On OpenBSD 4.0, when an unsupported locale is specified, setlocale()
succeeds but then nl_langinfo(CODESET) is "646". In this situation,
some unit tests fail. */
#if HAVE_LANGINFO_CODESET
{
const char *cs = nl_langinfo (CODESET);
if (cs[0] == '\0' || strcmp (cs, "ASCII") == 0 || strcmp (cs, "646") == 0)
return 1;
}
#endif
#ifdef __CYGWIN__
/* On Cygwin, avoid locale names without encoding suffix, because the
locale_charset() function relies on the encoding suffix. Note that
LC_ALL is set on the command line. */
if (strchr (getenv ("LC_ALL"), '.') == NULL) return 1;
#endif
/* Check whether in a month name, no byte in the range 0x80..0x9F occurs.
This excludes the UTF-8 encoding. */
t.tm_year = 1975 - 1900; t.tm_mon = 2 - 1; t.tm_mday = 4;
if (strftime (buf, sizeof (buf), "%B", &t) < 2) return 1;
for (p = buf; *p != '\0'; p++)
if ((unsigned char) *p >= 0x80 && (unsigned char) *p < 0xa0)
return 1;
/* Check whether a typical GB18030 multibyte sequence is recognized as a
single wide character. This excludes the GB2312 and GBK encodings. */
if (mblen ("\203\062\332\066", 5) != 4)
return 1;
return 0;
}
changequote([,])dnl
])])
if AC_TRY_EVAL([ac_link]) && test -s conftest$ac_exeext; then
# Setting LC_ALL is not enough. Need to set LC_TIME to empty, because
# otherwise on MacOS X 10.3.5 the LC_TIME=C from the beginning of the
# configure script would override the LC_ALL setting. Likewise for
# LC_CTYPE, which is also set at the beginning of the configure script.
# Test for the locale name without encoding suffix.
if (LC_ALL=zh_CN LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_zh_CN=zh_CN
else
# Test for the locale name with explicit encoding suffix.
if (LC_ALL=zh_CN.GB18030 LC_TIME= LC_CTYPE= ./conftest; exit) 2>/dev/null; then
gt_cv_locale_zh_CN=zh_CN.GB18030
else
# None found.
gt_cv_locale_zh_CN=none
fi
fi
else
# If there was a link error, due to mblen(), the system is so old that
# it certainly doesn't have a chinese locale.
gt_cv_locale_zh_CN=none
fi
rm -fr conftest*
fi
])
LOCALE_ZH_CN=$gt_cv_locale_zh_CN
AC_SUBST([LOCALE_ZH_CN])
])