#! /bin/sh
# Output a system dependent table of character encoding aliases.
#
-# Copyright (C) 2000-2003 Free Software Foundation, Inc.
+# Copyright (C) 2000-2004, 2006-2009 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
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, write to the Free Software Foundation,
-# Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+# Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
#
# The table consists of lines of the form
# ALIAS CANONICAL
# 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 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 darwin woe32 dos
+# CP950 woe32 dos
+# CP1046 aix
+# CP1124 aix
+# CP1125 dos
+# CP1129 aix
+# CP1131 darwin
+# 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 darwin
+# GBK glibc aix osf solaris darwin woe32 dos
+# GB18030 glibc solaris netbsd darwin
+# 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
+# ARMSCII-8 glibc darwin
+# GEORGIAN-PS glibc
+# PT154 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.).
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 "BIG5 BIG5"
echo "SJIS SHIFT_JIS"
;;
- beos*)
- # BeOS has a single locale, and it has UTF-8 encoding.
+ 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 sometimes its value 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.
+ # Then there are also the locales with encodings other than US-ASCII
+ # and UTF-8. These locales can be occasionally useful to users (e.g.
+ # when grepping through ISO-8859-1 encoded text files), when all their
+ # file names are in US-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 "ISO8859-9 ISO-8859-9"
+ echo "ISO8859-13 ISO-8859-13"
+ echo "ISO8859-15 ISO-8859-15"
+ echo "KOI8-R KOI8-R"
+ echo "KOI8-U KOI8-U"
+ echo "CP866 CP866"
+ echo "CP949 CP949"
+ echo "CP1131 CP1131"
+ echo "CP1251 CP1251"
+ echo "eucCN GB2312"
+ echo "GB2312 GB2312"
+ echo "eucJP EUC-JP"
+ echo "eucKR EUC-KR"
+ echo "Big5 BIG5"
+ echo "Big5HKSCS BIG5-HKSCS"
+ echo "GBK GBK"
+ echo "GB18030 GB18030"
+ echo "SJIS SHIFT_JIS"
+ echo "ARMSCII-8 ARMSCII-8"
+ echo "PT154 PT154"
+ #echo "ISCII-DEV ?"
+ echo "* UTF-8"
+ ;;
+ beos* | haiku*)
+ # BeOS and Haiku have a single locale, and it has UTF-8 encoding.
echo "* UTF-8"
;;
msdosdjgpp*)
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 <st001906@hrz1.hrz.tu-darmstadt.de>"
+ echo "# Juan Manuel Guerrero <juan.guerrero@gmx.de>"
echo "# and Bruno Haible <bruno@clisp.org>."
echo "#"
echo "C ASCII"