2 # Output a system dependent table of character encoding aliases.
4 # Copyright (C) 2000-2009 Free Software Foundation, Inc.
6 # This program is free software: you can redistribute it and/or modify
7 # it under the terms of the GNU General Public License as published by
8 # the Free Software Foundation, either version 3 of the License, or
9 # (at your option) any later version.
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
14 # GNU General Public License for more details.
16 # You should have received a copy of the GNU General Public License
17 # along with this program. If not, see <http://www.gnu.org/licenses/>.
19 # The table consists of lines of the form
22 # ALIAS is the (system dependent) result of "nl_langinfo (CODESET)".
23 # ALIAS is compared in a case sensitive way.
25 # CANONICAL is the GNU canonical name for this character encoding.
26 # It must be an encoding supported by libiconv. Support by GNU libc is
27 # also desirable. CANONICAL is case insensitive. Usually an upper case
28 # MIME charset name is preferred.
29 # The current list of GNU canonical charset names is as follows.
31 # name used by which systems a MIME name?
32 # ASCII, ANSI_X3.4-1968 glibc solaris freebsd
33 # ISO-8859-1 glibc aix hpux irix osf solaris freebsd yes
34 # ISO-8859-2 glibc aix hpux irix osf solaris freebsd yes
35 # ISO-8859-3 glibc solaris yes
36 # ISO-8859-4 osf solaris freebsd yes
37 # ISO-8859-5 glibc aix hpux irix osf solaris freebsd yes
38 # ISO-8859-6 glibc aix hpux solaris yes
39 # ISO-8859-7 glibc aix hpux irix osf solaris yes
40 # ISO-8859-8 glibc aix hpux osf solaris yes
41 # ISO-8859-9 glibc aix hpux irix osf solaris yes
44 # ISO-8859-15 glibc aix osf solaris freebsd
45 # KOI8-R glibc solaris freebsd yes
46 # KOI8-U glibc freebsd yes
72 # CP1251 glibc solaris woe32
79 # GB2312 glibc aix hpux irix solaris freebsd yes
80 # EUC-JP glibc aix hpux irix osf solaris freebsd yes
81 # EUC-KR glibc aix hpux irix osf solaris freebsd yes
82 # EUC-TW glibc aix hpux irix osf solaris
83 # BIG5 glibc aix hpux osf solaris freebsd yes
84 # BIG5-HKSCS glibc solaris
85 # GBK glibc aix osf solaris woe32 dos
86 # GB18030 glibc solaris
87 # SHIFT_JIS hpux osf solaris freebsd yes
88 # JOHAB glibc solaris woe32
89 # TIS-620 glibc aix hpux osf solaris
101 # UTF-8 glibc aix hpux osf solaris yes
103 # Note: Names which are not marked as being a MIME name should not be used in
104 # Internet protocols for information interchange (mail, news, etc.).
106 # Note: ASCII and ANSI_X3.4-1968 are synonymous canonical names. Applications
107 # must understand both names and treat them as equivalent.
109 # The first argument passed to this file is the canonical host specification,
110 # CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM
112 # CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM
115 os=`echo "$host" | sed -e 's/^[^-]*-[^-]*-\(.*\)$/\1/'`
116 echo "# This file contains a table of character encoding aliases,"
117 echo "# suitable for operating system '${os}'."
118 echo "# It was automatically generated from config.charset."
119 # List of references, updated during installation:
120 echo "# Packages using this file: "
123 # With glibc-2.1 or newer, we don't need any canonicalization,
124 # because glibc has iconv and both glibc and libiconv support all
125 # GNU canonical names directly. Therefore, the Makefile does not
126 # need to install the alias file at all.
127 # The following applies only to glibc-2.0.x and older libcs.
128 echo "ISO_646.IRV:1983 ASCII"
131 echo "ISO8859-1 ISO-8859-1"
132 echo "ISO8859-2 ISO-8859-2"
133 echo "ISO8859-5 ISO-8859-5"
134 echo "ISO8859-6 ISO-8859-6"
135 echo "ISO8859-7 ISO-8859-7"
136 echo "ISO8859-8 ISO-8859-8"
137 echo "ISO8859-9 ISO-8859-9"
138 echo "ISO8859-15 ISO-8859-15"
141 echo "IBM-921 ISO-8859-13"
145 echo "IBM-1046 CP1046"
146 echo "IBM-1124 CP1124"
147 echo "IBM-1129 CP1129"
148 echo "IBM-1252 CP1252"
149 echo "IBM-eucCN GB2312"
150 echo "IBM-eucJP EUC-JP"
151 echo "IBM-eucKR EUC-KR"
152 echo "IBM-eucTW EUC-TW"
155 echo "TIS-620 TIS-620"
159 echo "iso88591 ISO-8859-1"
160 echo "iso88592 ISO-8859-2"
161 echo "iso88595 ISO-8859-5"
162 echo "iso88596 ISO-8859-6"
163 echo "iso88597 ISO-8859-7"
164 echo "iso88598 ISO-8859-8"
165 echo "iso88599 ISO-8859-9"
166 echo "iso885915 ISO-8859-15"
167 echo "roman8 HP-ROMAN8"
168 echo "arabic8 HP-ARABIC8"
169 echo "greek8 HP-GREEK8"
170 echo "hebrew8 HP-HEBREW8"
171 echo "turkish8 HP-TURKISH8"
172 echo "kana8 HP-KANA8"
173 echo "tis620 TIS-620"
179 #echo "ccdc ?" # what is this?
180 echo "SJIS SHIFT_JIS"
184 echo "ISO8859-1 ISO-8859-1"
185 echo "ISO8859-2 ISO-8859-2"
186 echo "ISO8859-5 ISO-8859-5"
187 echo "ISO8859-7 ISO-8859-7"
188 echo "ISO8859-9 ISO-8859-9"
195 echo "ISO8859-1 ISO-8859-1"
196 echo "ISO8859-2 ISO-8859-2"
197 echo "ISO8859-4 ISO-8859-4"
198 echo "ISO8859-5 ISO-8859-5"
199 echo "ISO8859-7 ISO-8859-7"
200 echo "ISO8859-8 ISO-8859-8"
201 echo "ISO8859-9 ISO-8859-9"
202 echo "ISO8859-15 ISO-8859-15"
205 echo "dechanyu DEC-HANYU"
206 echo "dechanzi GB2312"
207 echo "deckanji DEC-KANJI"
208 echo "deckorean EUC-KR"
214 echo "sdeckanji EUC-JP"
215 echo "SJIS SHIFT_JIS"
216 echo "TACTIS TIS-620"
221 echo "ISO8859-1 ISO-8859-1"
222 echo "ISO8859-2 ISO-8859-2"
223 echo "ISO8859-3 ISO-8859-3"
224 echo "ISO8859-4 ISO-8859-4"
225 echo "ISO8859-5 ISO-8859-5"
226 echo "ISO8859-6 ISO-8859-6"
227 echo "ISO8859-7 ISO-8859-7"
228 echo "ISO8859-8 ISO-8859-8"
229 echo "ISO8859-9 ISO-8859-9"
230 echo "ISO8859-15 ISO-8859-15"
232 echo "ansi-1251 CP1251"
234 echo "Big5-HKSCS BIG5-HKSCS"
237 echo "GB18030 GB18030"
238 echo "cns11643 EUC-TW"
240 echo "ko_KR.johap92 JOHAB"
243 echo "TIS620.2533 TIS-620"
244 #echo "sun_eu_greek ?" # what is this?
248 # FreeBSD 4.2 doesn't have nl_langinfo(CODESET); therefore
249 # localcharset.c falls back to using the full locale name
250 # from the environment variables.
251 # Likewise for OS/2. OS/2 has XFree86 just like FreeBSD. Just
252 # reuse FreeBSD's locale data for OS/2.
254 echo "US-ASCII ASCII"
255 for l in la_LN lt_LN; do
256 echo "$l.ASCII ASCII"
258 for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
259 fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT la_LN \
260 lt_LN nl_BE nl_NL no_NO pt_PT sv_SE; do
261 echo "$l.ISO_8859-1 ISO-8859-1"
262 echo "$l.DIS_8859-15 ISO-8859-15"
264 for l in cs_CZ hr_HR hu_HU la_LN lt_LN pl_PL sl_SI; do
265 echo "$l.ISO_8859-2 ISO-8859-2"
267 for l in la_LN lt_LT; do
268 echo "$l.ISO_8859-4 ISO-8859-4"
270 for l in ru_RU ru_SU; do
271 echo "$l.KOI8-R KOI8-R"
272 echo "$l.ISO_8859-5 ISO-8859-5"
273 echo "$l.CP866 CP866"
275 echo "uk_UA.KOI8-U KOI8-U"
276 echo "zh_TW.BIG5 BIG5"
277 echo "zh_TW.Big5 BIG5"
278 echo "zh_CN.EUC GB2312"
279 echo "ja_JP.EUC EUC-JP"
280 echo "ja_JP.SJIS SHIFT_JIS"
281 echo "ja_JP.Shift_JIS SHIFT_JIS"
282 echo "ko_KR.EUC EUC-KR"
286 echo "ISO8859-1 ISO-8859-1"
287 echo "ISO8859-2 ISO-8859-2"
288 echo "ISO8859-4 ISO-8859-4"
289 echo "ISO8859-5 ISO-8859-5"
290 echo "ISO8859-15 ISO-8859-15"
296 echo "SJIS SHIFT_JIS"
299 # BeOS has a single locale, and it has UTF-8 encoding.
303 # DJGPP 2.03 doesn't have nl_langinfo(CODESET); therefore
304 # localcharset.c falls back to using the full locale name
305 # from the environment variables.
307 echo "# The encodings given here may not all be correct."
308 echo "# If you find that the encoding given for your language and"
309 echo "# country is not the one your DOS machine actually uses, just"
310 echo "# correct it in this file, and send a mail to"
311 echo "# Juan Manuel Guerrero <st001906@hrz1.hrz.tu-darmstadt.de>"
312 echo "# and Bruno Haible <bruno@clisp.org>."
315 # ISO-8859-1 languages
318 echo "da CP865" # not CP850 ??
319 echo "da_DK CP865" # not CP850 ??
325 echo "en_AU CP850" # not CP437 ??
330 echo "en_ZA CP850" # not CP437 ??
368 echo "id CP850" # not CP437 ??
369 echo "id_ID CP850" # not CP437 ??
370 echo "is CP861" # not CP850 ??
371 echo "is_IS CP861" # not CP850 ??
379 echo "nb CP865" # not CP850 ??
380 echo "nb_NO CP865" # not CP850 ??
384 echo "nn CP865" # not CP850 ??
385 echo "nn_NO CP865" # not CP850 ??
386 echo "no CP865" # not CP850 ??
387 echo "no_NO CP865" # not CP850 ??
393 # ISO-8859-2 languages
410 echo "sr CP852" # CP852 or CP866 or CP855 ??
411 echo "sr_YU CP852" # CP852 or CP866 or CP855 ??
412 # ISO-8859-3 languages
415 # ISO-8859-5 languages
418 echo "bg CP866" # not CP855 ??
419 echo "bg_BG CP866" # not CP855 ??
420 echo "mk CP866" # not CP855 ??
421 echo "mk_MK CP866" # not CP855 ??
426 # ISO-8859-6 languages
440 # ISO-8859-7 languages
443 # ISO-8859-8 languages
446 # ISO-8859-9 languages
454 echo "zh_TW CP950" # not CP938 ??
456 echo "kr CP949" # not CP934 ??
457 echo "kr_KR CP949" # not CP934 ??