2 # Output a system dependent table of character encoding aliases.
4 # Copyright (C) 2000-2003 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 solaris 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
46 # ISO-8859-15 glibc aix osf solaris freebsd
47 # KOI8-R glibc solaris freebsd yes
48 # KOI8-U glibc freebsd yes
74 # CP1251 glibc solaris woe32
81 # GB2312 glibc aix hpux irix solaris freebsd yes
82 # EUC-JP glibc aix hpux irix osf solaris freebsd yes
83 # EUC-KR glibc aix hpux irix osf solaris freebsd yes
84 # EUC-TW glibc aix hpux irix osf solaris
85 # BIG5 glibc aix hpux osf solaris freebsd yes
86 # BIG5-HKSCS glibc solaris
87 # GBK glibc aix osf solaris woe32 dos
88 # GB18030 glibc solaris
89 # SHIFT_JIS hpux osf solaris freebsd yes
90 # JOHAB glibc solaris woe32
91 # TIS-620 glibc aix hpux osf solaris
103 # UTF-8 glibc aix hpux osf solaris yes
105 # Note: Names which are not marked as being a MIME name should not be used in
106 # Internet protocols for information interchange (mail, news, etc.).
108 # Note: ASCII and ANSI_X3.4-1968 are synonymous canonical names. Applications
109 # must understand both names and treat them as equivalent.
111 # The first argument passed to this file is the canonical host specification,
112 # CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM
114 # CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM
117 os
=`echo "$host" | sed -e 's/^[^-]*-[^-]*-\(.*\)$/\1/'`
118 echo "# This file contains a table of character encoding aliases,"
119 echo "# suitable for operating system '${os}'."
120 echo "# It was automatically generated from config.charset."
121 # List of references, updated during installation:
122 echo "# Packages using this file: "
125 # With glibc-2.1 or newer, we don't need any canonicalization,
126 # because glibc has iconv and both glibc and libiconv support all
127 # GNU canonical names directly. Therefore, the Makefile does not
128 # need to install the alias file at all.
129 # The following applies only to glibc-2.0.x and older libcs.
130 echo "ISO_646.IRV:1983 ASCII"
133 echo "ISO8859-1 ISO-8859-1"
134 echo "ISO8859-2 ISO-8859-2"
135 echo "ISO8859-5 ISO-8859-5"
136 echo "ISO8859-6 ISO-8859-6"
137 echo "ISO8859-7 ISO-8859-7"
138 echo "ISO8859-8 ISO-8859-8"
139 echo "ISO8859-9 ISO-8859-9"
140 echo "ISO8859-15 ISO-8859-15"
143 echo "IBM-921 ISO-8859-13"
147 echo "IBM-1046 CP1046"
148 echo "IBM-1124 CP1124"
149 echo "IBM-1129 CP1129"
150 echo "IBM-1252 CP1252"
151 echo "IBM-eucCN GB2312"
152 echo "IBM-eucJP EUC-JP"
153 echo "IBM-eucKR EUC-KR"
154 echo "IBM-eucTW EUC-TW"
157 echo "TIS-620 TIS-620"
161 echo "iso88591 ISO-8859-1"
162 echo "iso88592 ISO-8859-2"
163 echo "iso88595 ISO-8859-5"
164 echo "iso88596 ISO-8859-6"
165 echo "iso88597 ISO-8859-7"
166 echo "iso88598 ISO-8859-8"
167 echo "iso88599 ISO-8859-9"
168 echo "iso885915 ISO-8859-15"
169 echo "roman8 HP-ROMAN8"
170 echo "arabic8 HP-ARABIC8"
171 echo "greek8 HP-GREEK8"
172 echo "hebrew8 HP-HEBREW8"
173 echo "turkish8 HP-TURKISH8"
174 echo "kana8 HP-KANA8"
175 echo "tis620 TIS-620"
181 #echo "ccdc ?" # what is this?
182 echo "SJIS SHIFT_JIS"
186 echo "ISO8859-1 ISO-8859-1"
187 echo "ISO8859-2 ISO-8859-2"
188 echo "ISO8859-5 ISO-8859-5"
189 echo "ISO8859-7 ISO-8859-7"
190 echo "ISO8859-9 ISO-8859-9"
197 echo "ISO8859-1 ISO-8859-1"
198 echo "ISO8859-2 ISO-8859-2"
199 echo "ISO8859-4 ISO-8859-4"
200 echo "ISO8859-5 ISO-8859-5"
201 echo "ISO8859-7 ISO-8859-7"
202 echo "ISO8859-8 ISO-8859-8"
203 echo "ISO8859-9 ISO-8859-9"
204 echo "ISO8859-15 ISO-8859-15"
207 echo "dechanyu DEC-HANYU"
208 echo "dechanzi GB2312"
209 echo "deckanji DEC-KANJI"
210 echo "deckorean EUC-KR"
216 echo "sdeckanji EUC-JP"
217 echo "SJIS SHIFT_JIS"
218 echo "TACTIS TIS-620"
223 echo "ISO8859-1 ISO-8859-1"
224 echo "ISO8859-2 ISO-8859-2"
225 echo "ISO8859-3 ISO-8859-3"
226 echo "ISO8859-4 ISO-8859-4"
227 echo "ISO8859-5 ISO-8859-5"
228 echo "ISO8859-6 ISO-8859-6"
229 echo "ISO8859-7 ISO-8859-7"
230 echo "ISO8859-8 ISO-8859-8"
231 echo "ISO8859-9 ISO-8859-9"
232 echo "ISO8859-15 ISO-8859-15"
234 echo "ansi-1251 CP1251"
236 echo "Big5-HKSCS BIG5-HKSCS"
239 echo "GB18030 GB18030"
240 echo "cns11643 EUC-TW"
242 echo "ko_KR.johap92 JOHAB"
245 echo "TIS620.2533 TIS-620"
246 #echo "sun_eu_greek ?" # what is this?
250 # FreeBSD 4.2 doesn't have nl_langinfo(CODESET); therefore
251 # localcharset.c falls back to using the full locale name
252 # from the environment variables.
253 # Likewise for OS/2. OS/2 has XFree86 just like FreeBSD. Just
254 # reuse FreeBSD's locale data for OS/2.
256 echo "US-ASCII ASCII"
257 for l
in la_LN lt_LN
; do
258 echo "$l.ASCII ASCII"
260 for l
in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
261 fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT la_LN \
262 lt_LN nl_BE nl_NL no_NO pt_PT sv_SE
; do
263 echo "$l.ISO_8859-1 ISO-8859-1"
264 echo "$l.DIS_8859-15 ISO-8859-15"
266 for l
in cs_CZ hr_HR hu_HU la_LN lt_LN pl_PL sl_SI
; do
267 echo "$l.ISO_8859-2 ISO-8859-2"
269 for l
in la_LN lt_LT
; do
270 echo "$l.ISO_8859-4 ISO-8859-4"
272 for l
in ru_RU ru_SU
; do
273 echo "$l.KOI8-R KOI8-R"
274 echo "$l.ISO_8859-5 ISO-8859-5"
275 echo "$l.CP866 CP866"
277 echo "uk_UA.KOI8-U KOI8-U"
278 echo "zh_TW.BIG5 BIG5"
279 echo "zh_TW.Big5 BIG5"
280 echo "zh_CN.EUC GB2312"
281 echo "ja_JP.EUC EUC-JP"
282 echo "ja_JP.SJIS SHIFT_JIS"
283 echo "ja_JP.Shift_JIS SHIFT_JIS"
284 echo "ko_KR.EUC EUC-KR"
288 echo "ISO8859-1 ISO-8859-1"
289 echo "ISO8859-2 ISO-8859-2"
290 echo "ISO8859-4 ISO-8859-4"
291 echo "ISO8859-5 ISO-8859-5"
292 echo "ISO8859-15 ISO-8859-15"
298 echo "SJIS SHIFT_JIS"
301 # BeOS has a single locale, and it has UTF-8 encoding.
305 # DJGPP 2.03 doesn't have nl_langinfo(CODESET); therefore
306 # localcharset.c falls back to using the full locale name
307 # from the environment variables.
309 echo "# The encodings given here may not all be correct."
310 echo "# If you find that the encoding given for your language and"
311 echo "# country is not the one your DOS machine actually uses, just"
312 echo "# correct it in this file, and send a mail to"
313 echo "# Juan Manuel Guerrero <st001906@hrz1.hrz.tu-darmstadt.de>"
314 echo "# and Bruno Haible <bruno@clisp.org>."
317 # ISO-8859-1 languages
320 echo "da CP865" # not CP850 ??
321 echo "da_DK CP865" # not CP850 ??
327 echo "en_AU CP850" # not CP437 ??
332 echo "en_ZA CP850" # not CP437 ??
370 echo "id CP850" # not CP437 ??
371 echo "id_ID CP850" # not CP437 ??
372 echo "is CP861" # not CP850 ??
373 echo "is_IS CP861" # not CP850 ??
381 echo "nb CP865" # not CP850 ??
382 echo "nb_NO CP865" # not CP850 ??
386 echo "nn CP865" # not CP850 ??
387 echo "nn_NO CP865" # not CP850 ??
388 echo "no CP865" # not CP850 ??
389 echo "no_NO CP865" # not CP850 ??
395 # ISO-8859-2 languages
412 echo "sr CP852" # CP852 or CP866 or CP855 ??
413 echo "sr_YU CP852" # CP852 or CP866 or CP855 ??
414 # ISO-8859-3 languages
417 # ISO-8859-5 languages
420 echo "bg CP866" # not CP855 ??
421 echo "bg_BG CP866" # not CP855 ??
422 echo "mk CP866" # not CP855 ??
423 echo "mk_MK CP866" # not CP855 ??
428 # ISO-8859-6 languages
442 # ISO-8859-7 languages
445 # ISO-8859-8 languages
448 # ISO-8859-9 languages
456 echo "zh_TW CP950" # not CP938 ??
458 echo "kr CP949" # not CP934 ??
459 echo "kr_KR CP949" # not CP934 ??