2 # Output a system dependent table of character encoding aliases.
4 # Copyright (C) 2000-2004, 2006-2008 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 MIME? used by which systems
32 # ASCII, ANSI_X3.4-1968 glibc solaris freebsd netbsd darwin
33 # ISO-8859-1 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin
34 # ISO-8859-2 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin
35 # ISO-8859-3 Y glibc solaris
36 # ISO-8859-4 Y osf solaris freebsd netbsd openbsd darwin
37 # ISO-8859-5 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin
38 # ISO-8859-6 Y glibc aix hpux solaris
39 # ISO-8859-7 Y glibc aix hpux irix osf solaris netbsd openbsd darwin
40 # ISO-8859-8 Y glibc aix hpux osf solaris
41 # ISO-8859-9 Y glibc aix hpux irix osf solaris darwin
42 # ISO-8859-13 glibc netbsd openbsd darwin
44 # ISO-8859-15 glibc aix osf solaris freebsd netbsd openbsd darwin
45 # KOI8-R Y glibc solaris freebsd netbsd openbsd darwin
46 # KOI8-U Y glibc freebsd netbsd openbsd darwin
59 # CP866 freebsd netbsd openbsd darwin dos
72 # CP1251 glibc solaris netbsd openbsd darwin woe32
79 # GB2312 Y glibc aix hpux irix solaris freebsd netbsd darwin
80 # EUC-JP Y glibc aix hpux irix osf solaris freebsd netbsd darwin
81 # EUC-KR Y glibc aix hpux irix osf solaris freebsd netbsd darwin
82 # EUC-TW glibc aix hpux irix osf solaris netbsd
83 # BIG5 Y glibc aix hpux osf solaris freebsd netbsd darwin
84 # BIG5-HKSCS glibc solaris
85 # GBK glibc aix osf solaris woe32 dos
86 # GB18030 glibc solaris netbsd
87 # SHIFT_JIS Y hpux osf solaris freebsd netbsd darwin
88 # JOHAB glibc solaris woe32
89 # TIS-620 glibc aix hpux osf solaris
101 # UTF-8 Y glibc aix hpux osf solaris netbsd darwin
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 # Linux libc5 doesn't have nl_langinfo(CODESET); therefore
124 # localcharset.c falls back to using the full locale name
125 # from the environment variables.
128 for l in af af_ZA ca ca_ES da da_DK de de_AT de_BE de_CH de_DE de_LU \
129 en en_AU en_BW en_CA en_DK en_GB en_IE en_NZ en_US en_ZA \
130 en_ZW es es_AR es_BO es_CL es_CO es_DO es_EC es_ES es_GT \
131 es_HN es_MX es_PA es_PE es_PY es_SV es_US es_UY es_VE et \
132 et_EE eu eu_ES fi fi_FI fo fo_FO fr fr_BE fr_CA fr_CH fr_FR \
133 fr_LU ga ga_IE gl gl_ES id id_ID in in_ID is is_IS it it_CH \
134 it_IT kl kl_GL nl nl_BE nl_NL no no_NO pt pt_BR pt_PT sv \
137 echo "$l.iso-8859-1 ISO-8859-1"
138 echo "$l.iso-8859-15 ISO-8859-15"
139 echo "$l.iso-8859-15@euro ISO-8859-15"
140 echo "$l@euro ISO-8859-15"
141 echo "$l.cp-437 CP437"
142 echo "$l.cp-850 CP850"
143 echo "$l.cp-1252 CP1252"
144 echo "$l.cp-1252@euro CP1252"
145 #echo "$l.atari-st ATARI-ST" # not a commonly used encoding
146 echo "$l.utf-8 UTF-8"
147 echo "$l.utf-8@euro UTF-8"
149 for l in cs cs_CZ hr hr_HR hu hu_HU pl pl_PL ro ro_RO sk sk_SK sl \
150 sl_SI sr sr_CS sr_YU; do
152 echo "$l.iso-8859-2 ISO-8859-2"
153 echo "$l.cp-852 CP852"
154 echo "$l.cp-1250 CP1250"
155 echo "$l.utf-8 UTF-8"
157 for l in mk mk_MK ru ru_RU; do
159 echo "$l.iso-8859-5 ISO-8859-5"
160 echo "$l.koi8-r KOI8-R"
161 echo "$l.cp-866 CP866"
162 echo "$l.cp-1251 CP1251"
163 echo "$l.utf-8 UTF-8"
165 for l in ar ar_SA; do
167 echo "$l.iso-8859-6 ISO-8859-6"
168 echo "$l.cp-864 CP864"
169 #echo "$l.cp-868 CP868" # not a commonly used encoding
170 echo "$l.cp-1256 CP1256"
171 echo "$l.utf-8 UTF-8"
173 for l in el el_GR gr gr_GR; do
175 echo "$l.iso-8859-7 ISO-8859-7"
176 echo "$l.cp-869 CP869"
177 echo "$l.cp-1253 CP1253"
178 echo "$l.cp-1253@euro CP1253"
179 echo "$l.utf-8 UTF-8"
180 echo "$l.utf-8@euro UTF-8"
182 for l in he he_IL iw iw_IL; do
184 echo "$l.iso-8859-8 ISO-8859-8"
185 echo "$l.cp-862 CP862"
186 echo "$l.cp-1255 CP1255"
187 echo "$l.utf-8 UTF-8"
189 for l in tr tr_TR; do
191 echo "$l.iso-8859-9 ISO-8859-9"
192 echo "$l.cp-857 CP857"
193 echo "$l.cp-1254 CP1254"
194 echo "$l.utf-8 UTF-8"
196 for l in lt lt_LT lv lv_LV; do
197 #echo "$l BALTIC" # not a commonly used encoding, wrong encoding name
198 echo "$l ISO-8859-13"
200 for l in ru_UA uk uk_UA; do
203 for l in zh zh_CN; do
204 #echo "$l GB_2312-80" # not a commonly used encoding, wrong encoding name
207 for l in ja ja_JP ja_JP.EUC; do
210 for l in ko ko_KR; do
213 for l in th th_TH; do
216 for l in fa fa_IR; do
217 #echo "$l ISIRI-3342" # a broken encoding
218 echo "$l.utf-8 UTF-8"
222 # With glibc-2.1 or newer, we don't need any canonicalization,
223 # because glibc has iconv and both glibc and libiconv support all
224 # GNU canonical names directly. Therefore, the Makefile does not
225 # need to install the alias file at all.
226 # The following applies only to glibc-2.0.x and older libcs.
227 echo "ISO_646.IRV:1983 ASCII"
230 echo "ISO8859-1 ISO-8859-1"
231 echo "ISO8859-2 ISO-8859-2"
232 echo "ISO8859-5 ISO-8859-5"
233 echo "ISO8859-6 ISO-8859-6"
234 echo "ISO8859-7 ISO-8859-7"
235 echo "ISO8859-8 ISO-8859-8"
236 echo "ISO8859-9 ISO-8859-9"
237 echo "ISO8859-15 ISO-8859-15"
240 echo "IBM-921 ISO-8859-13"
244 echo "IBM-1046 CP1046"
245 echo "IBM-1124 CP1124"
246 echo "IBM-1129 CP1129"
247 echo "IBM-1252 CP1252"
248 echo "IBM-eucCN GB2312"
249 echo "IBM-eucJP EUC-JP"
250 echo "IBM-eucKR EUC-KR"
251 echo "IBM-eucTW EUC-TW"
254 echo "TIS-620 TIS-620"
258 echo "iso88591 ISO-8859-1"
259 echo "iso88592 ISO-8859-2"
260 echo "iso88595 ISO-8859-5"
261 echo "iso88596 ISO-8859-6"
262 echo "iso88597 ISO-8859-7"
263 echo "iso88598 ISO-8859-8"
264 echo "iso88599 ISO-8859-9"
265 echo "iso885915 ISO-8859-15"
266 echo "roman8 HP-ROMAN8"
267 echo "arabic8 HP-ARABIC8"
268 echo "greek8 HP-GREEK8"
269 echo "hebrew8 HP-HEBREW8"
270 echo "turkish8 HP-TURKISH8"
271 echo "kana8 HP-KANA8"
272 echo "tis620 TIS-620"
278 #echo "ccdc ?" # what is this?
279 echo "SJIS SHIFT_JIS"
283 echo "ISO8859-1 ISO-8859-1"
284 echo "ISO8859-2 ISO-8859-2"
285 echo "ISO8859-5 ISO-8859-5"
286 echo "ISO8859-7 ISO-8859-7"
287 echo "ISO8859-9 ISO-8859-9"
294 echo "ISO8859-1 ISO-8859-1"
295 echo "ISO8859-2 ISO-8859-2"
296 echo "ISO8859-4 ISO-8859-4"
297 echo "ISO8859-5 ISO-8859-5"
298 echo "ISO8859-7 ISO-8859-7"
299 echo "ISO8859-8 ISO-8859-8"
300 echo "ISO8859-9 ISO-8859-9"
301 echo "ISO8859-15 ISO-8859-15"
304 echo "dechanyu DEC-HANYU"
305 echo "dechanzi GB2312"
306 echo "deckanji DEC-KANJI"
307 echo "deckorean EUC-KR"
313 echo "sdeckanji EUC-JP"
314 echo "SJIS SHIFT_JIS"
315 echo "TACTIS TIS-620"
320 echo "ISO8859-1 ISO-8859-1"
321 echo "ISO8859-2 ISO-8859-2"
322 echo "ISO8859-3 ISO-8859-3"
323 echo "ISO8859-4 ISO-8859-4"
324 echo "ISO8859-5 ISO-8859-5"
325 echo "ISO8859-6 ISO-8859-6"
326 echo "ISO8859-7 ISO-8859-7"
327 echo "ISO8859-8 ISO-8859-8"
328 echo "ISO8859-9 ISO-8859-9"
329 echo "ISO8859-15 ISO-8859-15"
331 echo "ansi-1251 CP1251"
333 echo "Big5-HKSCS BIG5-HKSCS"
336 echo "GB18030 GB18030"
337 echo "cns11643 EUC-TW"
339 echo "ko_KR.johap92 JOHAB"
342 echo "TIS620.2533 TIS-620"
343 #echo "sun_eu_greek ?" # what is this?
347 # FreeBSD 4.2 doesn't have nl_langinfo(CODESET); therefore
348 # localcharset.c falls back to using the full locale name
349 # from the environment variables.
350 # Likewise for OS/2. OS/2 has XFree86 just like FreeBSD. Just
351 # reuse FreeBSD's locale data for OS/2.
353 echo "US-ASCII ASCII"
354 for l in la_LN lt_LN; do
355 echo "$l.ASCII ASCII"
357 for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
358 fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT la_LN \
359 lt_LN nl_BE nl_NL no_NO pt_PT sv_SE; do
360 echo "$l.ISO_8859-1 ISO-8859-1"
361 echo "$l.DIS_8859-15 ISO-8859-15"
363 for l in cs_CZ hr_HR hu_HU la_LN lt_LN pl_PL sl_SI; do
364 echo "$l.ISO_8859-2 ISO-8859-2"
366 for l in la_LN lt_LT; do
367 echo "$l.ISO_8859-4 ISO-8859-4"
369 for l in ru_RU ru_SU; do
370 echo "$l.KOI8-R KOI8-R"
371 echo "$l.ISO_8859-5 ISO-8859-5"
372 echo "$l.CP866 CP866"
374 echo "uk_UA.KOI8-U KOI8-U"
375 echo "zh_TW.BIG5 BIG5"
376 echo "zh_TW.Big5 BIG5"
377 echo "zh_CN.EUC GB2312"
378 echo "ja_JP.EUC EUC-JP"
379 echo "ja_JP.SJIS SHIFT_JIS"
380 echo "ja_JP.Shift_JIS SHIFT_JIS"
381 echo "ko_KR.EUC EUC-KR"
385 echo "ISO8859-1 ISO-8859-1"
386 echo "ISO8859-2 ISO-8859-2"
387 echo "ISO8859-4 ISO-8859-4"
388 echo "ISO8859-5 ISO-8859-5"
389 echo "ISO8859-7 ISO-8859-7"
390 echo "ISO8859-13 ISO-8859-13"
391 echo "ISO8859-15 ISO-8859-15"
397 echo "SJIS SHIFT_JIS"
401 echo "ISO8859-1 ISO-8859-1"
402 echo "ISO8859-2 ISO-8859-2"
403 echo "ISO8859-4 ISO-8859-4"
404 echo "ISO8859-5 ISO-8859-5"
405 echo "ISO8859-7 ISO-8859-7"
406 echo "ISO8859-13 ISO-8859-13"
407 echo "ISO8859-15 ISO-8859-15"
410 # Darwin 6.8 doesn't have nl_langinfo(CODESET); therefore
411 # localcharset.c falls back to using the full locale name
412 # from the environment variables.
414 for l in en_AU en_CA en_GB en_US la_LN; do
415 echo "$l.US-ASCII ASCII"
417 for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
418 fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT nl_BE \
419 nl_NL no_NO pt_PT sv_SE; do
421 echo "$l.ISO8859-1 ISO-8859-1"
422 echo "$l.ISO8859-15 ISO-8859-15"
425 echo "$l.ISO8859-1 ISO-8859-1"
426 echo "$l.ISO8859-15 ISO-8859-15"
428 for l in cs_CZ hr_HR hu_HU la_LN pl_PL sl_SI; do
429 echo "$l.ISO8859-2 ISO-8859-2"
431 for l in la_LN lt_LT; do
432 echo "$l.ISO8859-4 ISO-8859-4"
435 echo "$l.KOI8-R KOI8-R"
436 echo "$l.ISO8859-5 ISO-8859-5"
437 echo "$l.CP866 CP866"
440 echo "$l.CP1251 CP1251"
442 echo "uk_UA.KOI8-U KOI8-U"
443 echo "zh_TW.BIG5 BIG5"
444 echo "zh_TW.Big5 BIG5"
445 echo "zh_CN.EUC GB2312"
446 echo "ja_JP.EUC EUC-JP"
447 echo "ja_JP.SJIS SHIFT_JIS"
448 echo "ko_KR.EUC EUC-KR"
451 # Darwin 7.5 has nl_langinfo(CODESET), but it is useless:
452 # - It returns the empty string when LANG is set to a locale of the
453 # form ll_CC, although ll_CC/LC_CTYPE is a symlink to an UTF-8
455 # - The environment variables LANG, LC_CTYPE, LC_ALL are not set by
456 # the system; nl_langinfo(CODESET) returns "US-ASCII" in this case.
457 # - The documentation says:
458 # "... all code that calls BSD system routines should ensure
459 # that the const *char parameters of these routines are in UTF-8
460 # encoding. All BSD system functions expect their string
461 # parameters to be in UTF-8 encoding and nothing else."
463 # "An additional caveat is that string parameters for files,
464 # paths, and other file-system entities must be in canonical
465 # UTF-8. In a canonical UTF-8 Unicode string, all decomposable
466 # characters are decomposed ..."
467 # but this is not true: You can pass non-decomposed UTF-8 strings
468 # to file system functions, and it is the OS which will convert
469 # them to decomposed UTF-8 before accessing the file system.
470 # - The Apple Terminal application displays UTF-8 by default.
471 # - However, other applications are free to use different encodings:
472 # - xterm uses ISO-8859-1 by default.
473 # - TextEdit uses MacRoman by default.
474 # We prefer UTF-8 over decomposed UTF-8-MAC because one should
475 # minimize the use of decomposed Unicode. Unfortunately, through the
476 # Darwin file system, decomposed UTF-8 strings are leaked into user
477 # space nevertheless.
481 # BeOS and Haiku have a single locale, and it has UTF-8 encoding.
485 # DJGPP 2.03 doesn't have nl_langinfo(CODESET); therefore
486 # localcharset.c falls back to using the full locale name
487 # from the environment variables.
489 echo "# The encodings given here may not all be correct."
490 echo "# If you find that the encoding given for your language and"
491 echo "# country is not the one your DOS machine actually uses, just"
492 echo "# correct it in this file, and send a mail to"
493 echo "# Juan Manuel Guerrero <juan.guerrero@gmx.de>"
494 echo "# and Bruno Haible <bruno@clisp.org>."
497 # ISO-8859-1 languages
500 echo "da CP865" # not CP850 ??
501 echo "da_DK CP865" # not CP850 ??
507 echo "en_AU CP850" # not CP437 ??
512 echo "en_ZA CP850" # not CP437 ??
550 echo "id CP850" # not CP437 ??
551 echo "id_ID CP850" # not CP437 ??
552 echo "is CP861" # not CP850 ??
553 echo "is_IS CP861" # not CP850 ??
561 echo "nb CP865" # not CP850 ??
562 echo "nb_NO CP865" # not CP850 ??
566 echo "nn CP865" # not CP850 ??
567 echo "nn_NO CP865" # not CP850 ??
568 echo "no CP865" # not CP850 ??
569 echo "no_NO CP865" # not CP850 ??
575 # ISO-8859-2 languages
592 echo "sr CP852" # CP852 or CP866 or CP855 ??
593 echo "sr_CS CP852" # CP852 or CP866 or CP855 ??
594 echo "sr_YU CP852" # CP852 or CP866 or CP855 ??
595 # ISO-8859-3 languages
598 # ISO-8859-5 languages
601 echo "bg CP866" # not CP855 ??
602 echo "bg_BG CP866" # not CP855 ??
603 echo "mk CP866" # not CP855 ??
604 echo "mk_MK CP866" # not CP855 ??
609 # ISO-8859-6 languages
623 # ISO-8859-7 languages
626 # ISO-8859-8 languages
629 # ISO-8859-9 languages
637 echo "zh_TW CP950" # not CP938 ??
639 echo "kr CP949" # not CP934 ??
640 echo "kr_KR CP949" # not CP934 ??