2 # Output a system dependent table of character encoding aliases.
4 # Copyright (C) 2000-2001 Free Software Foundation, Inc.
6 # This program is free software; you can redistribute it and/or modify it
7 # under the terms of the GNU Library General Public License as published
8 # by the Free Software Foundation; either version 2, or (at your option)
11 # This program is distributed in the hope that it will be useful,
12 # but WITHOUT ANY WARRANTY; without even the implied warranty of
13 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
14 # Library General Public License for more details.
16 # You should have received a copy of the GNU Library General Public
17 # License along with this program; if not, write to the Free Software
18 # Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
21 # The table consists of lines of the form
24 # ALIAS is the (system dependent) result of "nl_langinfo (CODESET)".
25 # ALIAS is compared in a case sensitive way.
27 # CANONICAL is the GNU canonical name for this character encoding.
28 # It must be an encoding supported by libiconv. Support by GNU libc is
29 # also desirable. CANONICAL is case insensitive. Usually an upper case
30 # MIME charset name is preferred.
31 # The current list of GNU canonical charset names is as follows.
33 # name used by which systems a MIME name?
34 # ASCII, ANSI_X3.4-1968 glibc solaris freebsd
35 # ISO-8859-1 glibc aix hpux irix osf solaris freebsd yes
36 # ISO-8859-2 glibc aix hpux irix osf solaris freebsd yes
37 # ISO-8859-3 glibc yes
38 # ISO-8859-4 osf solaris freebsd yes
39 # ISO-8859-5 glibc aix hpux irix osf solaris freebsd yes
40 # ISO-8859-6 glibc aix hpux solaris yes
41 # ISO-8859-7 glibc aix hpux irix osf solaris yes
42 # ISO-8859-8 glibc aix hpux osf solaris yes
43 # ISO-8859-9 glibc aix hpux irix osf solaris yes
45 # ISO-8859-15 glibc aix osf solaris freebsd
46 # KOI8-R glibc solaris freebsd yes
47 # KOI8-U glibc freebsd yes
78 # GB2312 glibc aix hpux irix solaris freebsd yes
79 # EUC-JP glibc aix hpux irix osf solaris freebsd yes
80 # EUC-KR glibc aix hpux irix osf solaris freebsd yes
81 # EUC-TW glibc aix hpux irix osf solaris
82 # BIG5 glibc aix hpux osf solaris freebsd yes
84 # GBK aix osf win32 dos
86 # SJIS hpux osf solaris freebsd
88 # TIS-620 glibc aix hpux osf solaris
98 # UTF-8 glibc aix hpux osf solaris yes
100 # Note: Names which are not marked as being a MIME name should not be used in
101 # Internet protocols for information interchange (mail, news, etc.).
103 # Note: ASCII and ANSI_X3.4-1968 are synonymous canonical names. Applications
104 # must understand both names and treat them as equivalent.
106 # The first argument passed to this file is the canonical host specification,
107 # CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM
109 # CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM
112 os
=`echo "$host" | sed -e 's/^[^-]*-[^-]*-\(.*\)$/\1/'`
113 echo "# This file contains a table of character encoding aliases,"
114 echo "# suitable for operating system '${os}'."
115 echo "# It was automatically generated from config.charset."
116 # List of references, updated during installation:
117 echo "# Packages using this file: "
120 # With glibc-2.1 or newer, we don't need any canonicalization,
121 # because glibc has iconv and both glibc and libiconv support all
122 # GNU canonical names directly. Therefore, the Makefile does not
123 # need to install the alias file at all.
124 # The following applies only to glibc-2.0.x and older libcs.
125 echo "ISO_646.IRV:1983 ASCII"
128 echo "ISO8859-1 ISO-8859-1"
129 echo "ISO8859-2 ISO-8859-2"
130 echo "ISO8859-5 ISO-8859-5"
131 echo "ISO8859-6 ISO-8859-6"
132 echo "ISO8859-7 ISO-8859-7"
133 echo "ISO8859-8 ISO-8859-8"
134 echo "ISO8859-9 ISO-8859-9"
135 echo "ISO8859-15 ISO-8859-15"
138 echo "IBM-921 ISO-8859-13"
142 echo "IBM-1046 CP1046"
143 echo "IBM-1124 CP1124"
144 echo "IBM-1129 CP1129"
145 echo "IBM-1252 CP1252"
146 echo "IBM-eucCN GB2312"
147 echo "IBM-eucJP EUC-JP"
148 echo "IBM-eucKR EUC-KR"
149 echo "IBM-eucTW EUC-TW"
152 echo "TIS-620 TIS-620"
156 echo "iso88591 ISO-8859-1"
157 echo "iso88592 ISO-8859-2"
158 echo "iso88595 ISO-8859-5"
159 echo "iso88596 ISO-8859-6"
160 echo "iso88597 ISO-8859-7"
161 echo "iso88598 ISO-8859-8"
162 echo "iso88599 ISO-8859-9"
163 echo "iso885915 ISO-8859-15"
164 echo "roman8 HP-ROMAN8"
165 echo "arabic8 HP-ARABIC8"
166 echo "greek8 HP-GREEK8"
167 echo "hebrew8 HP-HEBREW8"
168 echo "turkish8 HP-TURKISH8"
169 echo "kana8 HP-KANA8"
170 echo "tis620 TIS-620"
176 #echo "ccdc ?" # what is this?
181 echo "ISO8859-1 ISO-8859-1"
182 echo "ISO8859-2 ISO-8859-2"
183 echo "ISO8859-5 ISO-8859-5"
184 echo "ISO8859-7 ISO-8859-7"
185 echo "ISO8859-9 ISO-8859-9"
192 echo "ISO8859-1 ISO-8859-1"
193 echo "ISO8859-2 ISO-8859-2"
194 echo "ISO8859-4 ISO-8859-4"
195 echo "ISO8859-5 ISO-8859-5"
196 echo "ISO8859-7 ISO-8859-7"
197 echo "ISO8859-8 ISO-8859-8"
198 echo "ISO8859-9 ISO-8859-9"
199 echo "ISO8859-15 ISO-8859-15"
202 echo "dechanyu DEC-HANYU"
203 echo "dechanzi GB2312"
204 echo "deckanji DEC-KANJI"
205 echo "deckorean EUC-KR"
211 echo "sdeckanji EUC-JP"
213 echo "TACTIS TIS-620"
218 echo "ISO8859-1 ISO-8859-1"
219 echo "ISO8859-2 ISO-8859-2"
220 echo "ISO8859-4 ISO-8859-4"
221 echo "ISO8859-5 ISO-8859-5"
222 echo "ISO8859-6 ISO-8859-6"
223 echo "ISO8859-7 ISO-8859-7"
224 echo "ISO8859-8 ISO-8859-8"
225 echo "ISO8859-9 ISO-8859-9"
226 echo "ISO8859-15 ISO-8859-15"
230 echo "cns11643 EUC-TW"
234 echo "TIS620.2533 TIS-620"
235 #echo "sun_eu_greek ?" # what is this?
239 # FreeBSD 4.2 doesn't have nl_langinfo(CODESET); therefore
240 # localcharset.c falls back to using the full locale name
241 # from the environment variables.
243 echo "US-ASCII ASCII"
244 for l
in la_LN lt_LN
; do
245 echo "$l.ASCII ASCII"
247 for l
in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
248 fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT la_LN \
249 lt_LN nl_BE nl_NL no_NO pt_PT sv_SE
; do
250 echo "$l.ISO_8859-1 ISO-8859-1"
251 echo "$l.DIS_8859-15 ISO-8859-15"
253 for l
in cs_CZ hr_HR hu_HU la_LN lt_LN pl_PL sl_SI
; do
254 echo "$l.ISO_8859-2 ISO-8859-2"
256 for l
in la_LN lt_LT
; do
257 echo "$l.ISO_8859-4 ISO-8859-4"
259 for l
in ru_RU ru_SU
; do
260 echo "$l.KOI8-R KOI8-R"
261 echo "$l.ISO_8859-5 ISO-8859-5"
262 echo "$l.CP866 CP866"
264 echo "uk_UA.KOI8-U KOI8-U"
265 echo "zh_TW.BIG5 BIG5"
266 echo "zh_TW.Big5 BIG5"
267 echo "zh_CN.EUC GB2312"
268 echo "ja_JP.EUC EUC-JP"
269 echo "ja_JP.SJIS SJIS"
270 echo "ja_JP.Shift_JIS SJIS"
271 echo "ko_KR.EUC EUC-KR"
274 # BeOS has a single locale, and it has UTF-8 encoding.
278 # DJGPP 2.03 doesn't have nl_langinfo(CODESET); therefore
279 # localcharset.c falls back to using the full locale name
280 # from the environment variables.
282 echo "# The encodings given here may not all be correct."
283 echo "# If you find that the encoding given for your language and"
284 echo "# country is not the one your DOS machine actually uses, just"
285 echo "# correct it in this file, and send a mail to"
286 echo "# Juan Manuel Guerrero <st001906@hrz1.hrz.tu-darmstadt.de>"
287 echo "# and Bruno Haible <haible@clisp.cons.org>."
290 # ISO-8859-1 languages
293 echo "da CP865" # not CP850 ??
294 echo "da_DK CP865" # not CP850 ??
300 echo "en_AU CP850" # not CP437 ??
305 echo "en_ZA CP850" # not CP437 ??
343 echo "id CP850" # not CP437 ??
344 echo "id_ID CP850" # not CP437 ??
345 echo "is CP861" # not CP850 ??
346 echo "is_IS CP861" # not CP850 ??
354 echo "nb CP865" # not CP850 ??
355 echo "nb_NO CP865" # not CP850 ??
359 echo "nn CP865" # not CP850 ??
360 echo "nn_NO CP865" # not CP850 ??
361 echo "no CP865" # not CP850 ??
362 echo "no_NO CP865" # not CP850 ??
368 # ISO-8859-2 languages
385 echo "sr CP852" # CP852 or CP866 or CP855 ??
386 echo "sr_YU CP852" # CP852 or CP866 or CP855 ??
387 # ISO-8859-3 languages
390 # ISO-8859-5 languages
393 echo "bg CP866" # not CP855 ??
394 echo "bg_BG CP866" # not CP855 ??
395 echo "mk CP866" # not CP855 ??
396 echo "mk_MK CP866" # not CP855 ??
397 echo "ru KOI8-R" # not CP866 ??
398 echo "ru_RU KOI8-R" # not CP866 ??
399 # ISO-8859-6 languages
413 # ISO-8859-7 languages
416 # ISO-8859-8 languages
419 # ISO-8859-9 languages
427 echo "zh_TW CP950" # not CP938 ??
429 echo "kr CP949" # not CP934 ??
430 echo "kr_KR CP949" # not CP934 ??