summaryrefslogtreecommitdiffstats
path: root/intl/config.charset
diff options
context:
space:
mode:
Diffstat (limited to 'intl/config.charset')
-rwxr-xr-xintl/config.charset285
1 files changed, 213 insertions, 72 deletions
diff --git a/intl/config.charset b/intl/config.charset
index 32becece9..43d45fb75 100755
--- a/intl/config.charset
+++ b/intl/config.charset
@@ -1,7 +1,7 @@
#! /bin/sh
# Output a system dependent table of character encoding aliases.
#
-# Copyright (C) 2000-2003 Free Software Foundation, Inc.
+# Copyright (C) 2000-2004 Free Software Foundation, Inc.
#
# This program is free software; you can redistribute it and/or modify it
# under the terms of the GNU Library General Public License as published
@@ -30,77 +30,77 @@
# MIME charset name is preferred.
# The current list of GNU canonical charset names is as follows.
#
-# name used by which systems a MIME name?
-# ASCII, ANSI_X3.4-1968 glibc solaris freebsd
-# ISO-8859-1 glibc aix hpux irix osf solaris freebsd yes
-# ISO-8859-2 glibc aix hpux irix osf solaris freebsd yes
-# ISO-8859-3 glibc solaris yes
-# ISO-8859-4 osf solaris freebsd yes
-# ISO-8859-5 glibc aix hpux irix osf solaris freebsd yes
-# ISO-8859-6 glibc aix hpux solaris yes
-# ISO-8859-7 glibc aix hpux irix osf solaris yes
-# ISO-8859-8 glibc aix hpux osf solaris yes
-# ISO-8859-9 glibc aix hpux irix osf solaris yes
-# ISO-8859-13 glibc
-# ISO-8859-14 glibc
-# ISO-8859-15 glibc aix osf solaris freebsd
-# KOI8-R glibc solaris freebsd yes
-# KOI8-U glibc freebsd yes
-# 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 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 woe32
-# CP1252 aix woe32
-# CP1253 woe32
-# CP1254 woe32
-# CP1255 glibc woe32
-# CP1256 woe32
-# CP1257 woe32
-# GB2312 glibc aix hpux irix solaris freebsd yes
-# EUC-JP glibc aix hpux irix osf solaris freebsd yes
-# EUC-KR glibc aix hpux irix osf solaris freebsd yes
-# EUC-TW glibc aix hpux irix osf solaris
-# BIG5 glibc aix hpux osf solaris freebsd yes
-# BIG5-HKSCS glibc solaris
-# GBK glibc aix osf solaris woe32 dos
-# GB18030 glibc solaris
-# SHIFT_JIS hpux osf solaris freebsd yes
-# JOHAB glibc solaris woe32
-# TIS-620 glibc aix hpux osf solaris
-# VISCII glibc yes
-# 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 glibc aix hpux osf solaris yes
+# name MIME? used by which systems
+# ASCII, ANSI_X3.4-1968 glibc solaris freebsd darwin
+# ISO-8859-1 Y glibc aix hpux irix osf solaris freebsd darwin
+# ISO-8859-2 Y glibc aix hpux irix osf solaris freebsd darwin
+# ISO-8859-3 Y glibc solaris
+# ISO-8859-4 Y osf solaris freebsd darwin
+# ISO-8859-5 Y glibc aix hpux irix osf solaris freebsd darwin
+# ISO-8859-6 Y glibc aix hpux solaris
+# ISO-8859-7 Y glibc aix hpux irix osf solaris
+# ISO-8859-8 Y glibc aix hpux osf solaris
+# ISO-8859-9 Y glibc aix hpux irix osf solaris
+# ISO-8859-13 glibc
+# ISO-8859-14 glibc
+# ISO-8859-15 glibc aix osf solaris freebsd
+# KOI8-R Y glibc solaris freebsd darwin
+# KOI8-U Y glibc freebsd 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 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 darwin woe32
+# CP1252 aix woe32
+# CP1253 woe32
+# CP1254 woe32
+# CP1255 glibc woe32
+# CP1256 woe32
+# CP1257 woe32
+# GB2312 Y glibc aix hpux irix solaris freebsd darwin
+# EUC-JP Y glibc aix hpux irix osf solaris freebsd darwin
+# EUC-KR Y glibc aix hpux irix osf solaris freebsd darwin
+# EUC-TW glibc aix hpux irix osf solaris
+# BIG5 Y glibc aix hpux osf solaris freebsd darwin
+# BIG5-HKSCS glibc solaris
+# GBK glibc aix osf solaris woe32 dos
+# GB18030 glibc solaris
+# SHIFT_JIS Y hpux osf solaris freebsd 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
#
# Note: Names which are not marked as being a MIME name should not be used in
# Internet protocols for information interchange (mail, news, etc.).
@@ -121,6 +121,105 @@ 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 "$l.utf-8 UTF-8"
+ done
+ ;;
linux* | *-gnu*)
# With glibc-2.1 or newer, we don't need any canonicalization,
# because glibc has iconv and both glibc and libiconv support all
@@ -297,6 +396,47 @@ case "$os" in
echo "BIG5 BIG5"
echo "SJIS SHIFT_JIS"
;;
+ darwin*)
+ # 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"
+ ;;
beos*)
# BeOS has a single locale, and it has UTF-8 encoding.
echo "* UTF-8"
@@ -410,6 +550,7 @@ case "$os" in
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"
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-30 04:40:31 +0100