diff options
Diffstat (limited to 'intl/config.charset')
| -rwxr-xr-x | intl/config.charset | 1132 |
1 files changed, 588 insertions, 544 deletions
diff --git a/intl/config.charset b/intl/config.charset index e8c258b3..b9dccbb9 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) 2000-2004, 2006 Free Software Foundation, Inc. +# Copyright (C) 2000-2004, 2006-2010 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 @@ -31,21 +31,21 @@ # 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 darwin -# ISO-8859-2 Y glibc aix hpux irix osf solaris freebsd netbsd darwin -# ISO-8859-3 Y glibc solaris -# ISO-8859-4 Y osf solaris freebsd netbsd darwin -# ISO-8859-5 Y glibc aix hpux irix osf solaris freebsd netbsd darwin -# ISO-8859-6 Y glibc aix hpux solaris -# ISO-8859-7 Y glibc aix hpux irix osf solaris netbsd 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 darwin -# ISO-8859-14 glibc -# ISO-8859-15 glibc aix osf solaris freebsd darwin -# KOI8-R Y glibc solaris freebsd netbsd darwin -# KOI8-U Y glibc freebsd netbsd darwin +# ASCII, ANSI_X3.4-1968 glibc solaris freebsd netbsd darwin cygwin +# ISO-8859-1 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin cygwin +# ISO-8859-2 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin cygwin +# ISO-8859-3 Y glibc solaris cygwin +# ISO-8859-4 Y osf solaris freebsd netbsd openbsd darwin +# ISO-8859-5 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin cygwin +# ISO-8859-6 Y glibc aix hpux solaris cygwin +# ISO-8859-7 Y glibc aix hpux irix osf solaris netbsd openbsd darwin cygwin +# ISO-8859-8 Y glibc aix hpux osf solaris cygwin +# ISO-8859-9 Y glibc aix hpux irix osf solaris darwin cygwin +# ISO-8859-13 glibc netbsd openbsd darwin cygwin +# ISO-8859-14 glibc cygwin +# ISO-8859-15 glibc aix osf solaris freebsd netbsd openbsd darwin cygwin +# KOI8-R Y glibc solaris freebsd netbsd openbsd darwin +# KOI8-U Y glibc freebsd netbsd openbsd darwin cygwin # KOI8-T glibc # CP437 dos # CP775 dos @@ -58,20 +58,21 @@ # CP862 dos # CP864 dos # CP865 dos -# CP866 freebsd netbsd darwin dos +# CP866 freebsd netbsd openbsd darwin dos # CP869 dos # CP874 woe32 dos # CP922 aix -# CP932 aix woe32 dos +# CP932 aix cygwin woe32 dos # CP943 aix -# CP949 osf woe32 dos +# CP949 osf darwin woe32 dos # CP950 woe32 dos # CP1046 aix # CP1124 aix # CP1125 dos # CP1129 aix +# CP1131 darwin # CP1250 woe32 -# CP1251 glibc solaris netbsd darwin woe32 +# CP1251 glibc solaris netbsd openbsd darwin cygwin woe32 # CP1252 aix woe32 # CP1253 woe32 # CP1254 woe32 @@ -80,18 +81,20 @@ # 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-KR Y glibc aix hpux irix osf solaris freebsd netbsd darwin cygwin # 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 +# BIG5 Y glibc aix hpux osf solaris freebsd netbsd darwin cygwin +# BIG5-HKSCS glibc solaris darwin +# GBK glibc aix osf solaris darwin cygwin 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 +# TIS-620 glibc aix hpux osf solaris cygwin # VISCII Y glibc # TCVN5712-1 glibc -# GEORGIAN-PS glibc +# ARMSCII-8 glibc darwin +# GEORGIAN-PS glibc cygwin +# PT154 glibc # HP-ROMAN8 hpux # HP-ARABIC8 hpux # HP-GREEK8 hpux @@ -100,7 +103,7 @@ # HP-KANA8 hpux # DEC-KANJI osf # DEC-HANYU osf -# UTF-8 Y glibc aix hpux osf solaris netbsd darwin +# UTF-8 Y glibc aix hpux osf solaris netbsd darwin cygwin # # Note: Names which are not marked as being a MIME name should not be used in # Internet protocols for information interchange (mail, news, etc.). @@ -121,520 +124,561 @@ 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 "$l.CP866 CP866" - done - echo "uk_UA.KOI8-U KOI8-U" - echo "zh_TW.BIG5 BIG5" - echo "zh_TW.Big5 BIG5" - echo "zh_CN.EUC GB2312" - echo "ja_JP.EUC EUC-JP" - echo "ja_JP.SJIS SHIFT_JIS" - echo "ja_JP.Shift_JIS SHIFT_JIS" - echo "ko_KR.EUC EUC-KR" - ;; - netbsd*) - echo "646 ASCII" - echo "ISO8859-1 ISO-8859-1" - echo "ISO8859-2 ISO-8859-2" - echo "ISO8859-4 ISO-8859-4" - echo "ISO8859-5 ISO-8859-5" - echo "ISO8859-7 ISO-8859-7" - echo "ISO8859-13 ISO-8859-13" - echo "ISO8859-15 ISO-8859-15" - echo "eucCN GB2312" - echo "eucJP EUC-JP" - echo "eucKR EUC-KR" - echo "eucTW EUC-TW" - echo "BIG5 BIG5" - echo "SJIS SHIFT_JIS" - ;; - darwin[56]*) - # Darwin 6.8 doesn't have nl_langinfo(CODESET); therefore - # localcharset.c falls back to using the full locale name - # from the environment variables. - echo "C ASCII" - for l in en_AU en_CA en_GB en_US la_LN; do - echo "$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*) - # 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 <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" - ;; + 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 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*) + # 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 |