X-Git-Url: https://erislabs.net/gitweb/?a=blobdiff_plain;f=lib%2Fconfig.charset;h=f4f2611c5ecbd837f86df20638b117e577e3a969;hb=8b8ff236fe4bd09b2cdbd5d26909a008d342a695;hp=6104d5fd7b2fb66fae00f6781a248ee3902cbd2e;hpb=75fa9a8a26d9eb25872cd50eede1821152fd42bd;p=gnulib.git diff --git a/lib/config.charset b/lib/config.charset index 6104d5fd7..f4f2611c5 100755 --- a/lib/config.charset +++ b/lib/config.charset @@ -1,7 +1,7 @@ #! /bin/sh # Output a system dependent table of character encoding aliases. # -# Copyright (C) 2000 Free Software Foundation, Inc. +# Copyright (C) 2000-2001 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 @@ -30,45 +30,78 @@ # 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 +# 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 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-8859-15 aix solaris -# KOI8-R glibc solaris -# KOI8-U glibc -# CP850 aix osf +# ISO-8859-15 glibc aix osf solaris freebsd +# KOI8-R glibc solaris freebsd yes +# KOI8-U glibc freebsd yes +# CP437 dos +# CP775 dos +# CP850 aix osf dos +# CP852 dos +# CP855 dos # CP856 aix -# CP921 aix +# CP857 dos +# CP861 dos +# CP862 dos +# CP864 dos +# CP865 dos +# CP866 freebsd dos +# CP869 dos +# CP874 win32 dos # CP922 aix -# CP932 aix +# CP932 aix win32 dos # CP943 aix +# CP949 osf win32 dos +# CP950 win32 dos # 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 +# CP1250 win32 +# CP1251 glibc win32 +# CP1252 aix win32 +# CP1253 win32 +# CP1254 win32 +# CP1255 win32 +# CP1256 win32 +# CP1257 win32 +# 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 +# GBK aix osf win32 dos +# GB18030 glibc +# SHIFT_JIS hpux osf solaris freebsd yes +# JOHAB glibc win32 +# TIS-620 glibc aix hpux osf solaris +# VISCII glibc yes # HP-ROMAN8 hpux # HP-ARABIC8 hpux # HP-GREEK8 hpux # HP-HEBREW8 hpux # HP-TURKISH8 hpux # HP-KANA8 hpux -# UTF-8 glibc aix hpux solaris +# DEC-KANJI osf +# DEC-HANYU osf +# UTF-8 glibc aix hpux osf solaris yes +# +# 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 @@ -80,13 +113,16 @@ 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 "$os" in linux* | *-gnu*) - # With glibc we don't need any canonicalization, because glibc - # supports all GNU canonical names directly. - echo "ANSI_X3.4-1968 ASCII" # this is a nop - echo "ISO_646.IRV:1983 ASCII" # this is a nop - echo "BALTIC ISO-8859-13" # in glibc-2.2 or newer, this is a nop + # With glibc-2.1 or newer, we don't need any canonicalization, + # because glibc has iconv and both glibc and libiconv support all + # GNU canonical names directly. Therefore, the Makefile does not + # need to install the alias file at all. + # The following applies only to glibc-2.0.x and older libcs. + echo "ISO_646.IRV:1983 ASCII" ;; aix*) echo "ISO8859-1 ISO-8859-1" @@ -99,7 +135,7 @@ case "$os" in echo "ISO8859-15 ISO-8859-15" echo "IBM-850 CP850" echo "IBM-856 CP856" - echo "IBM-921 CP921" + echo "IBM-921 ISO-8859-13" echo "IBM-922 CP922" echo "IBM-932 CP932" echo "IBM-943 CP943" @@ -107,7 +143,7 @@ case "$os" in echo "IBM-1124 CP1124" echo "IBM-1129 CP1129" echo "IBM-1252 CP1252" - echo "IBM-eucCN EUC-CN" + echo "IBM-eucCN GB2312" echo "IBM-eucJP EUC-JP" echo "IBM-eucKR EUC-KR" echo "IBM-eucTW EUC-TW" @@ -124,6 +160,7 @@ case "$os" in 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" @@ -135,9 +172,9 @@ case "$os" in echo "eucJP EUC-JP" echo "eucKR EUC-KR" echo "eucTW EUC-TW" - echo "hp15CN EUC-CN" + echo "hp15CN GB2312" #echo "ccdc ?" # what is this? - echo "SJIS SJIS" + echo "SJIS SHIFT_JIS" echo "utf8 UTF-8" ;; irix*) @@ -146,12 +183,35 @@ case "$os" in 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" @@ -166,13 +226,213 @@ case "$os" in echo "ISO8859-15 ISO-8859-15" echo "koi8-r KOI8-R" echo "BIG5 BIG5" - echo "gb2312 EUC-CN" + echo "gb2312 GB2312" echo "cns11643 EUC-TW" echo "5601 EUC-KR" echo "eucJP EUC-JP" - echo "PCK SJIS" + echo "PCK SHIFT_JIS" echo "TIS620.2533 TIS-620" #echo "sun_eu_greek ?" # what is this? echo "UTF-8 UTF-8" ;; + freebsd*) + # FreeBSD 4.2 doesn't have nl_langinfo(CODESET); therefore + # localcharset.c falls back to using the full locale name + # from the environment variables. + echo "C ASCII" + echo "US-ASCII ASCII" + for l in la_LN lt_LN; do + echo "$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" + ;; + beos*) + # BeOS has 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 " + echo "# and Bruno Haible ." + 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_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 KOI8-R" # not CP866 ?? + echo "ru_RU KOI8-R" # not CP866 ?? + # 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