summaryrefslogtreecommitdiff
path: root/lib/config.charset
diff options
context:
space:
mode:
authorJim Meyering <jim@meyering.net>2000-03-01 13:23:41 +0000
committerJim Meyering <jim@meyering.net>2000-03-01 13:23:41 +0000
commit8d1e103424622ea64298c8cfa1ff418770fa4193 (patch)
tree6a96b10f155017513d70ccd44cd66af18f9e0427 /lib/config.charset
parent77ec117299ea3817acd0c1a439b1f28b735f86bd (diff)
downloadcoreutils-8d1e103424622ea64298c8cfa1ff418770fa4193.tar.xz
New file from Bruno.
Diffstat (limited to 'lib/config.charset')
-rwxr-xr-xlib/config.charset178
1 files changed, 178 insertions, 0 deletions
diff --git a/lib/config.charset b/lib/config.charset
new file mode 100755
index 000000000..6104d5fd7
--- /dev/null
+++ b/lib/config.charset
@@ -0,0 +1,178 @@
+#! /bin/sh
+# Output a system dependent table of character encoding aliases.
+#
+# 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 Library 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
+# Library General Public License for more details.
+#
+# You should have received a copy of the GNU Library 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.
+#
+# 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 used by which systems
+# ASCII glibc solaris
+# ISO-8859-1 glibc aix hpux irix osf solaris
+# ISO-8859-2 glibc aix hpux irix solaris
+# ISO-8859-4 solaris
+# ISO-8859-5 glibc aix hpux irix solaris
+# ISO-8859-6 aix hpux solaris
+# ISO-8859-7 glibc aix hpux irix osf solaris
+# ISO-8859-8 glibc aix hpux solaris
+# ISO-8859-9 glibc aix hpux irix osf solaris
+# ISO-8859-13 glibc
+# ISO-8859-15 aix solaris
+# KOI8-R glibc solaris
+# KOI8-U glibc
+# CP850 aix osf
+# CP856 aix
+# CP921 aix
+# CP922 aix
+# CP932 aix
+# CP943 aix
+# CP1046 aix
+# CP1124 aix
+# CP1129 aix
+# CP1252 aix
+# EUC-CN aix hpux solaris
+# EUC-JP aix hpux solaris
+# EUC-KR aix hpux solaris
+# EUC-TW aix hpux solaris
+# BIG5 aix hpux solaris
+# GBK aix
+# SJIS hpux solaris
+# TIS-620 aix hpux solaris
+# HP-ROMAN8 hpux
+# HP-ARABIC8 hpux
+# HP-GREEK8 hpux
+# HP-HEBREW8 hpux
+# HP-TURKISH8 hpux
+# HP-KANA8 hpux
+# UTF-8 glibc aix hpux solaris
+#
+# 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."
+case "$os" in
+ linux* | *-gnu*)
+ # With glibc we don't need any canonicalization, because glibc
+ # supports all GNU canonical names directly.
+ echo "ANSI_X3.4-1968 ASCII" # this is a nop
+ echo "ISO_646.IRV:1983 ASCII" # this is a nop
+ echo "BALTIC ISO-8859-13" # in glibc-2.2 or newer, this is a nop
+ ;;
+ 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 CP921"
+ 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 EUC-CN"
+ 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 "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 EUC-CN"
+ #echo "ccdc ?" # what is this?
+ echo "SJIS SJIS"
+ 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"
+ ;;
+ osf*)
+ echo "ISO8859-1 ISO-8859-1"
+ echo "ISO8859-7 ISO-8859-7"
+ echo "ISO8859-9 ISO-8859-9"
+ echo "cp850 CP850"
+ ;;
+ solaris*)
+ 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 "ISO8859-6 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 "BIG5 BIG5"
+ echo "gb2312 EUC-CN"
+ echo "cns11643 EUC-TW"
+ echo "5601 EUC-KR"
+ echo "eucJP EUC-JP"
+ echo "PCK SJIS"
+ echo "TIS620.2533 TIS-620"
+ #echo "sun_eu_greek ?" # what is this?
+ echo "UTF-8 UTF-8"
+ ;;
+esac