2 # Output a system dependent table of character encoding aliases.
4 # Copyright (C) 2000-2004 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 MIME? used by which systems
34 # ASCII, ANSI_X3.4-1968 glibc solaris freebsd darwin
35 # ISO-8859-1 Y glibc aix hpux irix osf solaris freebsd darwin
36 # ISO-8859-2 Y glibc aix hpux irix osf solaris freebsd darwin
37 # ISO-8859-3 Y glibc solaris
38 # ISO-8859-4 Y osf solaris freebsd darwin
39 # ISO-8859-5 Y glibc aix hpux irix osf solaris freebsd darwin
40 # ISO-8859-6 Y glibc aix hpux solaris
41 # ISO-8859-7 Y glibc aix hpux irix osf solaris darwin
42 # ISO-8859-8 Y glibc aix hpux osf solaris
43 # ISO-8859-9 Y glibc aix hpux irix osf solaris darwin
44 # ISO-8859-13 glibc darwin
46 # ISO-8859-15 glibc aix osf solaris freebsd darwin
47 # KOI8-R Y glibc solaris freebsd darwin
48 # KOI8-U Y glibc freebsd darwin
61 # CP866 freebsd darwin dos
74 # CP1251 glibc solaris darwin woe32
81 # GB2312 Y glibc aix hpux irix solaris freebsd darwin
82 # EUC-JP Y glibc aix hpux irix osf solaris freebsd darwin
83 # EUC-KR Y glibc aix hpux irix osf solaris freebsd darwin
84 # EUC-TW glibc aix hpux irix osf solaris
85 # BIG5 Y glibc aix hpux osf solaris freebsd darwin
86 # BIG5-HKSCS glibc solaris
87 # GBK glibc aix osf solaris woe32 dos
88 # GB18030 glibc solaris
89 # SHIFT_JIS Y hpux osf solaris freebsd darwin
90 # JOHAB glibc solaris woe32
91 # TIS-620 glibc aix hpux osf solaris
103 # UTF-8 Y glibc aix hpux osf solaris darwin
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 # Linux libc5 doesn't have nl_langinfo(CODESET); therefore
126 # localcharset.c falls back to using the full locale name
127 # from the environment variables.
130 for l in af af_ZA ca ca_ES da da_DK de de_AT de_BE de_CH de_DE de_LU \
131 en en_AU en_BW en_CA en_DK en_GB en_IE en_NZ en_US en_ZA \
132 en_ZW es es_AR es_BO es_CL es_CO es_DO es_EC es_ES es_GT \
133 es_HN es_MX es_PA es_PE es_PY es_SV es_US es_UY es_VE et \
134 et_EE eu eu_ES fi fi_FI fo fo_FO fr fr_BE fr_CA fr_CH fr_FR \
135 fr_LU ga ga_IE gl gl_ES id id_ID in in_ID is is_IS it it_CH \
136 it_IT kl kl_GL nl nl_BE nl_NL no no_NO pt pt_BR pt_PT sv \
139 echo "$l.iso-8859-1 ISO-8859-1"
140 echo "$l.iso-8859-15 ISO-8859-15"
141 echo "$l.iso-8859-15@euro ISO-8859-15"
142 echo "$l@euro ISO-8859-15"
143 echo "$l.cp-437 CP437"
144 echo "$l.cp-850 CP850"
145 echo "$l.cp-1252 CP1252"
146 echo "$l.cp-1252@euro CP1252"
147 #echo "$l.atari-st ATARI-ST" # not a commonly used encoding
148 echo "$l.utf-8 UTF-8"
149 echo "$l.utf-8@euro UTF-8"
151 for l in cs cs_CZ hr hr_HR hu hu_HU pl pl_PL ro ro_RO sk sk_SK sl \
152 sl_SI sr sr_CS sr_YU; do
154 echo "$l.iso-8859-2 ISO-8859-2"
155 echo "$l.cp-852 CP852"
156 echo "$l.cp-1250 CP1250"
157 echo "$l.utf-8 UTF-8"
159 for l in mk mk_MK ru ru_RU; do
161 echo "$l.iso-8859-5 ISO-8859-5"
162 echo "$l.koi8-r KOI8-R"
163 echo "$l.cp-866 CP866"
164 echo "$l.cp-1251 CP1251"
165 echo "$l.utf-8 UTF-8"
167 for l in ar ar_SA; do
169 echo "$l.iso-8859-6 ISO-8859-6"
170 echo "$l.cp-864 CP864"
171 #echo "$l.cp-868 CP868" # not a commonly used encoding
172 echo "$l.cp-1256 CP1256"
173 echo "$l.utf-8 UTF-8"
175 for l in el el_GR gr gr_GR; do
177 echo "$l.iso-8859-7 ISO-8859-7"
178 echo "$l.cp-869 CP869"
179 echo "$l.cp-1253 CP1253"
180 echo "$l.cp-1253@euro CP1253"
181 echo "$l.utf-8 UTF-8"
182 echo "$l.utf-8@euro UTF-8"
184 for l in he he_IL iw iw_IL; do
186 echo "$l.iso-8859-8 ISO-8859-8"
187 echo "$l.cp-862 CP862"
188 echo "$l.cp-1255 CP1255"
189 echo "$l.utf-8 UTF-8"
191 for l in tr tr_TR; do
193 echo "$l.iso-8859-9 ISO-8859-9"
194 echo "$l.cp-857 CP857"
195 echo "$l.cp-1254 CP1254"
196 echo "$l.utf-8 UTF-8"
198 for l in lt lt_LT lv lv_LV; do
199 #echo "$l BALTIC" # not a commonly used encoding, wrong encoding name
200 echo "$l ISO-8859-13"
202 for l in ru_UA uk uk_UA; do
205 for l in zh zh_CN; do
206 #echo "$l GB_2312-80" # not a commonly used encoding, wrong encoding name
209 for l in ja ja_JP ja_JP.EUC; do
212 for l in ko ko_KR; do
215 for l in th th_TH; do
218 for l in fa fa_IR; do
219 #echo "$l ISIRI-3342" # a broken encoding
220 echo "$l.utf-8 UTF-8"
224 # With glibc-2.1 or newer, we don't need any canonicalization,
225 # because glibc has iconv and both glibc and libiconv support all
226 # GNU canonical names directly. Therefore, the Makefile does not
227 # need to install the alias file at all.
228 # The following applies only to glibc-2.0.x and older libcs.
229 echo "ISO_646.IRV:1983 ASCII"
232 echo "ISO8859-1 ISO-8859-1"
233 echo "ISO8859-2 ISO-8859-2"
234 echo "ISO8859-5 ISO-8859-5"
235 echo "ISO8859-6 ISO-8859-6"
236 echo "ISO8859-7 ISO-8859-7"
237 echo "ISO8859-8 ISO-8859-8"
238 echo "ISO8859-9 ISO-8859-9"
239 echo "ISO8859-15 ISO-8859-15"
242 echo "IBM-921 ISO-8859-13"
246 echo "IBM-1046 CP1046"
247 echo "IBM-1124 CP1124"
248 echo "IBM-1129 CP1129"
249 echo "IBM-1252 CP1252"
250 echo "IBM-eucCN GB2312"
251 echo "IBM-eucJP EUC-JP"
252 echo "IBM-eucKR EUC-KR"
253 echo "IBM-eucTW EUC-TW"
256 echo "TIS-620 TIS-620"
260 echo "iso88591 ISO-8859-1"
261 echo "iso88592 ISO-8859-2"
262 echo "iso88595 ISO-8859-5"
263 echo "iso88596 ISO-8859-6"
264 echo "iso88597 ISO-8859-7"
265 echo "iso88598 ISO-8859-8"
266 echo "iso88599 ISO-8859-9"
267 echo "iso885915 ISO-8859-15"
268 echo "roman8 HP-ROMAN8"
269 echo "arabic8 HP-ARABIC8"
270 echo "greek8 HP-GREEK8"
271 echo "hebrew8 HP-HEBREW8"
272 echo "turkish8 HP-TURKISH8"
273 echo "kana8 HP-KANA8"
274 echo "tis620 TIS-620"
280 #echo "ccdc ?" # what is this?
281 echo "SJIS SHIFT_JIS"
285 echo "ISO8859-1 ISO-8859-1"
286 echo "ISO8859-2 ISO-8859-2"
287 echo "ISO8859-5 ISO-8859-5"
288 echo "ISO8859-7 ISO-8859-7"
289 echo "ISO8859-9 ISO-8859-9"
296 echo "ISO8859-1 ISO-8859-1"
297 echo "ISO8859-2 ISO-8859-2"
298 echo "ISO8859-4 ISO-8859-4"
299 echo "ISO8859-5 ISO-8859-5"
300 echo "ISO8859-7 ISO-8859-7"
301 echo "ISO8859-8 ISO-8859-8"
302 echo "ISO8859-9 ISO-8859-9"
303 echo "ISO8859-15 ISO-8859-15"
306 echo "dechanyu DEC-HANYU"
307 echo "dechanzi GB2312"
308 echo "deckanji DEC-KANJI"
309 echo "deckorean EUC-KR"
315 echo "sdeckanji EUC-JP"
316 echo "SJIS SHIFT_JIS"
317 echo "TACTIS TIS-620"
322 echo "ISO8859-1 ISO-8859-1"
323 echo "ISO8859-2 ISO-8859-2"
324 echo "ISO8859-3 ISO-8859-3"
325 echo "ISO8859-4 ISO-8859-4"
326 echo "ISO8859-5 ISO-8859-5"
327 echo "ISO8859-6 ISO-8859-6"
328 echo "ISO8859-7 ISO-8859-7"
329 echo "ISO8859-8 ISO-8859-8"
330 echo "ISO8859-9 ISO-8859-9"
331 echo "ISO8859-15 ISO-8859-15"
333 echo "ansi-1251 CP1251"
335 echo "Big5-HKSCS BIG5-HKSCS"
338 echo "GB18030 GB18030"
339 echo "cns11643 EUC-TW"
341 echo "ko_KR.johap92 JOHAB"
344 echo "TIS620.2533 TIS-620"
345 #echo "sun_eu_greek ?" # what is this?
349 # FreeBSD 4.2 doesn't have nl_langinfo(CODESET); therefore
350 # localcharset.c falls back to using the full locale name
351 # from the environment variables.
352 # Likewise for OS/2. OS/2 has XFree86 just like FreeBSD. Just
353 # reuse FreeBSD's locale data for OS/2.
355 echo "US-ASCII ASCII"
356 for l in la_LN lt_LN; do
357 echo "$l.ASCII ASCII"
359 for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
360 fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT la_LN \
361 lt_LN nl_BE nl_NL no_NO pt_PT sv_SE; do
362 echo "$l.ISO_8859-1 ISO-8859-1"
363 echo "$l.DIS_8859-15 ISO-8859-15"
365 for l in cs_CZ hr_HR hu_HU la_LN lt_LN pl_PL sl_SI; do
366 echo "$l.ISO_8859-2 ISO-8859-2"
368 for l in la_LN lt_LT; do
369 echo "$l.ISO_8859-4 ISO-8859-4"
371 for l in ru_RU ru_SU; do
372 echo "$l.KOI8-R KOI8-R"
373 echo "$l.ISO_8859-5 ISO-8859-5"
374 echo "$l.CP866 CP866"
376 echo "uk_UA.KOI8-U KOI8-U"
377 echo "zh_TW.BIG5 BIG5"
378 echo "zh_TW.Big5 BIG5"
379 echo "zh_CN.EUC GB2312"
380 echo "ja_JP.EUC EUC-JP"
381 echo "ja_JP.SJIS SHIFT_JIS"
382 echo "ja_JP.Shift_JIS SHIFT_JIS"
383 echo "ko_KR.EUC EUC-KR"
387 echo "ISO8859-1 ISO-8859-1"
388 echo "ISO8859-2 ISO-8859-2"
389 echo "ISO8859-4 ISO-8859-4"
390 echo "ISO8859-5 ISO-8859-5"
391 echo "ISO8859-15 ISO-8859-15"
397 echo "SJIS SHIFT_JIS"
400 # Darwin 6.8 doesn't have nl_langinfo(CODESET); therefore
401 # localcharset.c falls back to using the full locale name
402 # from the environment variables.
404 for l in en_AU en_CA en_GB en_US la_LN; do
405 echo "$l.US-ASCII ASCII"
407 for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
408 fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT nl_BE \
409 nl_NL no_NO pt_PT sv_SE; do
411 echo "$l.ISO8859-1 ISO-8859-1"
412 echo "$l.ISO8859-15 ISO-8859-15"
415 echo "$l.ISO8859-1 ISO-8859-1"
416 echo "$l.ISO8859-15 ISO-8859-15"
418 for l in cs_CZ hr_HR hu_HU la_LN pl_PL sl_SI; do
419 echo "$l.ISO8859-2 ISO-8859-2"
421 for l in la_LN lt_LT; do
422 echo "$l.ISO8859-4 ISO-8859-4"
425 echo "$l.KOI8-R KOI8-R"
426 echo "$l.ISO8859-5 ISO-8859-5"
427 echo "$l.CP866 CP866"
430 echo "$l.CP1251 CP1251"
432 echo "uk_UA.KOI8-U KOI8-U"
433 echo "zh_TW.BIG5 BIG5"
434 echo "zh_TW.Big5 BIG5"
435 echo "zh_CN.EUC GB2312"
436 echo "ja_JP.EUC EUC-JP"
437 echo "ja_JP.SJIS SHIFT_JIS"
438 echo "ko_KR.EUC EUC-KR"
441 # Darwin 7.5 has nl_langinfo(CODESET), but it is useless:
442 # - It returns the empty string when LANG is set to a locale of the
443 # form ll_CC, although ll_CC/LC_CTYPE is a symlink to an UTF-8
445 # - The environment variables LANG, LC_CTYPE, LC_ALL are not set by
446 # the system; nl_langinfo(CODESET) returns "US-ASCII" in this case.
447 # - The documentation says:
448 # "... all code that calls BSD system routines should ensure
449 # that the const *char parameters of these routines are in UTF-8
450 # encoding. All BSD system functions expect their string
451 # parameters to be in UTF-8 encoding and nothing else."
453 # "An additional caveat is that string parameters for files,
454 # paths, and other file-system entities must be in canonical
455 # UTF-8. In a canonical UTF-8 Unicode string, all decomposable
456 # characters are decomposed ..."
457 # but this is not true: You can pass non-decomposed UTF-8 strings
458 # to file system functions, and it is the OS which will convert
459 # them to decomposed UTF-8 before accessing the file system.
460 # - The Apple Terminal application displays UTF-8 by default.
461 # - However, other applications are free to use different encodings:
462 # - xterm uses ISO-8859-1 by default.
463 # - TextEdit uses MacRoman by default.
464 # We prefer UTF-8 over decomposed UTF-8-MAC because one should
465 # minimize the use of decomposed Unicode. Unfortunately, through the
466 # Darwin file system, decomposed UTF-8 strings are leaked into user
467 # space nevertheless.
471 # BeOS has a single locale, and it has UTF-8 encoding.
475 # DJGPP 2.03 doesn't have nl_langinfo(CODESET); therefore
476 # localcharset.c falls back to using the full locale name
477 # from the environment variables.
479 echo "# The encodings given here may not all be correct."
480 echo "# If you find that the encoding given for your language and"
481 echo "# country is not the one your DOS machine actually uses, just"
482 echo "# correct it in this file, and send a mail to"
483 echo "# Juan Manuel Guerrero <st001906@hrz1.hrz.tu-darmstadt.de>"
484 echo "# and Bruno Haible <bruno@clisp.org>."
487 # ISO-8859-1 languages
490 echo "da CP865" # not CP850 ??
491 echo "da_DK CP865" # not CP850 ??
497 echo "en_AU CP850" # not CP437 ??
502 echo "en_ZA CP850" # not CP437 ??
540 echo "id CP850" # not CP437 ??
541 echo "id_ID CP850" # not CP437 ??
542 echo "is CP861" # not CP850 ??
543 echo "is_IS CP861" # not CP850 ??
551 echo "nb CP865" # not CP850 ??
552 echo "nb_NO CP865" # not CP850 ??
556 echo "nn CP865" # not CP850 ??
557 echo "nn_NO CP865" # not CP850 ??
558 echo "no CP865" # not CP850 ??
559 echo "no_NO CP865" # not CP850 ??
565 # ISO-8859-2 languages
582 echo "sr CP852" # CP852 or CP866 or CP855 ??
583 echo "sr_CS CP852" # CP852 or CP866 or CP855 ??
584 echo "sr_YU CP852" # CP852 or CP866 or CP855 ??
585 # ISO-8859-3 languages
588 # ISO-8859-5 languages
591 echo "bg CP866" # not CP855 ??
592 echo "bg_BG CP866" # not CP855 ??
593 echo "mk CP866" # not CP855 ??
594 echo "mk_MK CP866" # not CP855 ??
599 # ISO-8859-6 languages
613 # ISO-8859-7 languages
616 # ISO-8859-8 languages
619 # ISO-8859-9 languages
627 echo "zh_TW CP950" # not CP938 ??
629 echo "kr CP949" # not CP934 ??
630 echo "kr_KR CP949" # not CP934 ??