2 # Output a system dependent table of character encoding aliases.
4 # Copyright (C) 2000-2004, 2006-2010 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., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301,
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 netbsd darwin cygwin
35 # ISO-8859-1 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin cygwin
36 # ISO-8859-2 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin cygwin
37 # ISO-8859-3 Y glibc solaris cygwin
38 # ISO-8859-4 Y osf solaris freebsd netbsd openbsd darwin
39 # ISO-8859-5 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin cygwin
40 # ISO-8859-6 Y glibc aix hpux solaris cygwin
41 # ISO-8859-7 Y glibc aix hpux irix osf solaris netbsd openbsd darwin cygwin
42 # ISO-8859-8 Y glibc aix hpux osf solaris cygwin
43 # ISO-8859-9 Y glibc aix hpux irix osf solaris darwin cygwin
44 # ISO-8859-13 glibc netbsd openbsd darwin cygwin
45 # ISO-8859-14 glibc cygwin
46 # ISO-8859-15 glibc aix osf solaris freebsd netbsd openbsd darwin cygwin
47 # KOI8-R Y glibc solaris freebsd netbsd openbsd darwin
48 # KOI8-U Y glibc freebsd netbsd openbsd darwin cygwin
61 # CP866 freebsd netbsd openbsd darwin dos
65 # CP932 aix cygwin woe32 dos
67 # CP949 osf darwin woe32 dos
75 # CP1251 glibc solaris netbsd openbsd darwin cygwin woe32
82 # GB2312 Y glibc aix hpux irix solaris freebsd netbsd darwin
83 # EUC-JP Y glibc aix hpux irix osf solaris freebsd netbsd darwin
84 # EUC-KR Y glibc aix hpux irix osf solaris freebsd netbsd darwin cygwin
85 # EUC-TW glibc aix hpux irix osf solaris netbsd
86 # BIG5 Y glibc aix hpux osf solaris freebsd netbsd darwin cygwin
87 # BIG5-HKSCS glibc solaris darwin
88 # GBK glibc aix osf solaris darwin cygwin woe32 dos
89 # GB18030 glibc solaris netbsd darwin
90 # SHIFT_JIS Y hpux osf solaris freebsd netbsd darwin
91 # JOHAB glibc solaris woe32
92 # TIS-620 glibc aix hpux osf solaris cygwin
95 # ARMSCII-8 glibc darwin
96 # GEORGIAN-PS glibc cygwin
106 # UTF-8 Y glibc aix hpux osf solaris netbsd darwin cygwin
108 # Note: Names which are not marked as being a MIME name should not be used in
109 # Internet protocols for information interchange (mail, news, etc.).
111 # Note: ASCII and ANSI_X3.4-1968 are synonymous canonical names. Applications
112 # must understand both names and treat them as equivalent.
114 # The first argument passed to this file is the canonical host specification,
115 # CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM
117 # CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM
120 os=`echo "$host" | sed -e 's/^[^-]*-[^-]*-\(.*\)$/\1/'`
121 echo "# This file contains a table of character encoding aliases,"
122 echo "# suitable for operating system '${os}'."
123 echo "# It was automatically generated from config.charset."
124 # List of references, updated during installation:
125 echo "# Packages using this file: "
128 # Linux libc5 doesn't have nl_langinfo(CODESET); therefore
129 # localcharset.c falls back to using the full locale name
130 # from the environment variables.
133 for l in af af_ZA ca ca_ES da da_DK de de_AT de_BE de_CH de_DE de_LU \
134 en en_AU en_BW en_CA en_DK en_GB en_IE en_NZ en_US en_ZA \
135 en_ZW es es_AR es_BO es_CL es_CO es_DO es_EC es_ES es_GT \
136 es_HN es_MX es_PA es_PE es_PY es_SV es_US es_UY es_VE et \
137 et_EE eu eu_ES fi fi_FI fo fo_FO fr fr_BE fr_CA fr_CH fr_FR \
138 fr_LU ga ga_IE gl gl_ES id id_ID in in_ID is is_IS it it_CH \
139 it_IT kl kl_GL nl nl_BE nl_NL no no_NO pt pt_BR pt_PT sv \
142 echo "$l.iso-8859-1 ISO-8859-1"
143 echo "$l.iso-8859-15 ISO-8859-15"
144 echo "$l.iso-8859-15@euro ISO-8859-15"
145 echo "$l@euro ISO-8859-15"
146 echo "$l.cp-437 CP437"
147 echo "$l.cp-850 CP850"
148 echo "$l.cp-1252 CP1252"
149 echo "$l.cp-1252@euro CP1252"
150 #echo "$l.atari-st ATARI-ST" # not a commonly used encoding
151 echo "$l.utf-8 UTF-8"
152 echo "$l.utf-8@euro UTF-8"
154 for l in cs cs_CZ hr hr_HR hu hu_HU pl pl_PL ro ro_RO sk sk_SK sl \
155 sl_SI sr sr_CS sr_YU; do
157 echo "$l.iso-8859-2 ISO-8859-2"
158 echo "$l.cp-852 CP852"
159 echo "$l.cp-1250 CP1250"
160 echo "$l.utf-8 UTF-8"
162 for l in mk mk_MK ru ru_RU; do
164 echo "$l.iso-8859-5 ISO-8859-5"
165 echo "$l.koi8-r KOI8-R"
166 echo "$l.cp-866 CP866"
167 echo "$l.cp-1251 CP1251"
168 echo "$l.utf-8 UTF-8"
170 for l in ar ar_SA; do
172 echo "$l.iso-8859-6 ISO-8859-6"
173 echo "$l.cp-864 CP864"
174 #echo "$l.cp-868 CP868" # not a commonly used encoding
175 echo "$l.cp-1256 CP1256"
176 echo "$l.utf-8 UTF-8"
178 for l in el el_GR gr gr_GR; do
180 echo "$l.iso-8859-7 ISO-8859-7"
181 echo "$l.cp-869 CP869"
182 echo "$l.cp-1253 CP1253"
183 echo "$l.cp-1253@euro CP1253"
184 echo "$l.utf-8 UTF-8"
185 echo "$l.utf-8@euro UTF-8"
187 for l in he he_IL iw iw_IL; do
189 echo "$l.iso-8859-8 ISO-8859-8"
190 echo "$l.cp-862 CP862"
191 echo "$l.cp-1255 CP1255"
192 echo "$l.utf-8 UTF-8"
194 for l in tr tr_TR; do
196 echo "$l.iso-8859-9 ISO-8859-9"
197 echo "$l.cp-857 CP857"
198 echo "$l.cp-1254 CP1254"
199 echo "$l.utf-8 UTF-8"
201 for l in lt lt_LT lv lv_LV; do
202 #echo "$l BALTIC" # not a commonly used encoding, wrong encoding name
203 echo "$l ISO-8859-13"
205 for l in ru_UA uk uk_UA; do
208 for l in zh zh_CN; do
209 #echo "$l GB_2312-80" # not a commonly used encoding, wrong encoding name
212 for l in ja ja_JP ja_JP.EUC; do
215 for l in ko ko_KR; do
218 for l in th th_TH; do
221 for l in fa fa_IR; do
222 #echo "$l ISIRI-3342" # a broken encoding
223 echo "$l.utf-8 UTF-8"
227 # With glibc-2.1 or newer, we don't need any canonicalization,
228 # because glibc has iconv and both glibc and libiconv support all
229 # GNU canonical names directly. Therefore, the Makefile does not
230 # need to install the alias file at all.
231 # The following applies only to glibc-2.0.x and older libcs.
232 echo "ISO_646.IRV:1983 ASCII"
235 echo "ISO8859-1 ISO-8859-1"
236 echo "ISO8859-2 ISO-8859-2"
237 echo "ISO8859-5 ISO-8859-5"
238 echo "ISO8859-6 ISO-8859-6"
239 echo "ISO8859-7 ISO-8859-7"
240 echo "ISO8859-8 ISO-8859-8"
241 echo "ISO8859-9 ISO-8859-9"
242 echo "ISO8859-15 ISO-8859-15"
245 echo "IBM-921 ISO-8859-13"
249 echo "IBM-1046 CP1046"
250 echo "IBM-1124 CP1124"
251 echo "IBM-1129 CP1129"
252 echo "IBM-1252 CP1252"
253 echo "IBM-eucCN GB2312"
254 echo "IBM-eucJP EUC-JP"
255 echo "IBM-eucKR EUC-KR"
256 echo "IBM-eucTW EUC-TW"
259 echo "TIS-620 TIS-620"
263 echo "iso88591 ISO-8859-1"
264 echo "iso88592 ISO-8859-2"
265 echo "iso88595 ISO-8859-5"
266 echo "iso88596 ISO-8859-6"
267 echo "iso88597 ISO-8859-7"
268 echo "iso88598 ISO-8859-8"
269 echo "iso88599 ISO-8859-9"
270 echo "iso885915 ISO-8859-15"
271 echo "roman8 HP-ROMAN8"
272 echo "arabic8 HP-ARABIC8"
273 echo "greek8 HP-GREEK8"
274 echo "hebrew8 HP-HEBREW8"
275 echo "turkish8 HP-TURKISH8"
276 echo "kana8 HP-KANA8"
277 echo "tis620 TIS-620"
283 #echo "ccdc ?" # what is this?
284 echo "SJIS SHIFT_JIS"
288 echo "ISO8859-1 ISO-8859-1"
289 echo "ISO8859-2 ISO-8859-2"
290 echo "ISO8859-5 ISO-8859-5"
291 echo "ISO8859-7 ISO-8859-7"
292 echo "ISO8859-9 ISO-8859-9"
299 echo "ISO8859-1 ISO-8859-1"
300 echo "ISO8859-2 ISO-8859-2"
301 echo "ISO8859-4 ISO-8859-4"
302 echo "ISO8859-5 ISO-8859-5"
303 echo "ISO8859-7 ISO-8859-7"
304 echo "ISO8859-8 ISO-8859-8"
305 echo "ISO8859-9 ISO-8859-9"
306 echo "ISO8859-15 ISO-8859-15"
309 echo "dechanyu DEC-HANYU"
310 echo "dechanzi GB2312"
311 echo "deckanji DEC-KANJI"
312 echo "deckorean EUC-KR"
318 echo "sdeckanji EUC-JP"
319 echo "SJIS SHIFT_JIS"
320 echo "TACTIS TIS-620"
325 echo "ISO8859-1 ISO-8859-1"
326 echo "ISO8859-2 ISO-8859-2"
327 echo "ISO8859-3 ISO-8859-3"
328 echo "ISO8859-4 ISO-8859-4"
329 echo "ISO8859-5 ISO-8859-5"
330 echo "ISO8859-6 ISO-8859-6"
331 echo "ISO8859-7 ISO-8859-7"
332 echo "ISO8859-8 ISO-8859-8"
333 echo "ISO8859-9 ISO-8859-9"
334 echo "ISO8859-15 ISO-8859-15"
336 echo "ansi-1251 CP1251"
338 echo "Big5-HKSCS BIG5-HKSCS"
341 echo "GB18030 GB18030"
342 echo "cns11643 EUC-TW"
344 echo "ko_KR.johap92 JOHAB"
347 echo "TIS620.2533 TIS-620"
348 #echo "sun_eu_greek ?" # what is this?
352 # FreeBSD 4.2 doesn't have nl_langinfo(CODESET); therefore
353 # localcharset.c falls back to using the full locale name
354 # from the environment variables.
355 # Likewise for OS/2. OS/2 has XFree86 just like FreeBSD. Just
356 # reuse FreeBSD's locale data for OS/2.
358 echo "US-ASCII ASCII"
359 for l in la_LN lt_LN; do
360 echo "$l.ASCII ASCII"
362 for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
363 fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT la_LN \
364 lt_LN nl_BE nl_NL no_NO pt_PT sv_SE; do
365 echo "$l.ISO_8859-1 ISO-8859-1"
366 echo "$l.DIS_8859-15 ISO-8859-15"
368 for l in cs_CZ hr_HR hu_HU la_LN lt_LN pl_PL sl_SI; do
369 echo "$l.ISO_8859-2 ISO-8859-2"
371 for l in la_LN lt_LT; do
372 echo "$l.ISO_8859-4 ISO-8859-4"
374 for l in ru_RU ru_SU; do
375 echo "$l.KOI8-R KOI8-R"
376 echo "$l.ISO_8859-5 ISO-8859-5"
377 echo "$l.CP866 CP866"
379 echo "uk_UA.KOI8-U KOI8-U"
380 echo "zh_TW.BIG5 BIG5"
381 echo "zh_TW.Big5 BIG5"
382 echo "zh_CN.EUC GB2312"
383 echo "ja_JP.EUC EUC-JP"
384 echo "ja_JP.SJIS SHIFT_JIS"
385 echo "ja_JP.Shift_JIS SHIFT_JIS"
386 echo "ko_KR.EUC EUC-KR"
390 echo "ISO8859-1 ISO-8859-1"
391 echo "ISO8859-2 ISO-8859-2"
392 echo "ISO8859-4 ISO-8859-4"
393 echo "ISO8859-5 ISO-8859-5"
394 echo "ISO8859-7 ISO-8859-7"
395 echo "ISO8859-13 ISO-8859-13"
396 echo "ISO8859-15 ISO-8859-15"
402 echo "SJIS SHIFT_JIS"
406 echo "ISO8859-1 ISO-8859-1"
407 echo "ISO8859-2 ISO-8859-2"
408 echo "ISO8859-4 ISO-8859-4"
409 echo "ISO8859-5 ISO-8859-5"
410 echo "ISO8859-7 ISO-8859-7"
411 echo "ISO8859-13 ISO-8859-13"
412 echo "ISO8859-15 ISO-8859-15"
415 # Darwin 6.8 doesn't have nl_langinfo(CODESET); therefore
416 # localcharset.c falls back to using the full locale name
417 # from the environment variables.
419 for l in en_AU en_CA en_GB en_US la_LN; do
420 echo "$l.US-ASCII ASCII"
422 for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
423 fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT nl_BE \
424 nl_NL no_NO pt_PT sv_SE; do
426 echo "$l.ISO8859-1 ISO-8859-1"
427 echo "$l.ISO8859-15 ISO-8859-15"
430 echo "$l.ISO8859-1 ISO-8859-1"
431 echo "$l.ISO8859-15 ISO-8859-15"
433 for l in cs_CZ hr_HR hu_HU la_LN pl_PL sl_SI; do
434 echo "$l.ISO8859-2 ISO-8859-2"
436 for l in la_LN lt_LT; do
437 echo "$l.ISO8859-4 ISO-8859-4"
440 echo "$l.KOI8-R KOI8-R"
441 echo "$l.ISO8859-5 ISO-8859-5"
442 echo "$l.CP866 CP866"
445 echo "$l.CP1251 CP1251"
447 echo "uk_UA.KOI8-U KOI8-U"
448 echo "zh_TW.BIG5 BIG5"
449 echo "zh_TW.Big5 BIG5"
450 echo "zh_CN.EUC GB2312"
451 echo "ja_JP.EUC EUC-JP"
452 echo "ja_JP.SJIS SHIFT_JIS"
453 echo "ko_KR.EUC EUC-KR"
456 # Darwin 7.5 has nl_langinfo(CODESET), but sometimes its value is
458 # - It returns the empty string when LANG is set to a locale of the
459 # form ll_CC, although ll_CC/LC_CTYPE is a symlink to an UTF-8
461 # - The environment variables LANG, LC_CTYPE, LC_ALL are not set by
462 # the system; nl_langinfo(CODESET) returns "US-ASCII" in this case.
463 # - The documentation says:
464 # "... all code that calls BSD system routines should ensure
465 # that the const *char parameters of these routines are in UTF-8
466 # encoding. All BSD system functions expect their string
467 # parameters to be in UTF-8 encoding and nothing else."
469 # "An additional caveat is that string parameters for files,
470 # paths, and other file-system entities must be in canonical
471 # UTF-8. In a canonical UTF-8 Unicode string, all decomposable
472 # characters are decomposed ..."
473 # but this is not true: You can pass non-decomposed UTF-8 strings
474 # to file system functions, and it is the OS which will convert
475 # them to decomposed UTF-8 before accessing the file system.
476 # - The Apple Terminal application displays UTF-8 by default.
477 # - However, other applications are free to use different encodings:
478 # - xterm uses ISO-8859-1 by default.
479 # - TextEdit uses MacRoman by default.
480 # We prefer UTF-8 over decomposed UTF-8-MAC because one should
481 # minimize the use of decomposed Unicode. Unfortunately, through the
482 # Darwin file system, decomposed UTF-8 strings are leaked into user
483 # space nevertheless.
484 # Then there are also the locales with encodings other than US-ASCII
485 # and UTF-8. These locales can be occasionally useful to users (e.g.
486 # when grepping through ISO-8859-1 encoded text files), when all their
487 # file names are in US-ASCII.
488 echo "ISO8859-1 ISO-8859-1"
489 echo "ISO8859-2 ISO-8859-2"
490 echo "ISO8859-4 ISO-8859-4"
491 echo "ISO8859-5 ISO-8859-5"
492 echo "ISO8859-7 ISO-8859-7"
493 echo "ISO8859-9 ISO-8859-9"
494 echo "ISO8859-13 ISO-8859-13"
495 echo "ISO8859-15 ISO-8859-15"
507 echo "Big5HKSCS BIG5-HKSCS"
509 echo "GB18030 GB18030"
510 echo "SJIS SHIFT_JIS"
511 echo "ARMSCII-8 ARMSCII-8"
517 # BeOS and Haiku have a single locale, and it has UTF-8 encoding.
521 # DJGPP 2.03 doesn't have nl_langinfo(CODESET); therefore
522 # localcharset.c falls back to using the full locale name
523 # from the environment variables.
525 echo "# The encodings given here may not all be correct."
526 echo "# If you find that the encoding given for your language and"
527 echo "# country is not the one your DOS machine actually uses, just"
528 echo "# correct it in this file, and send a mail to"
529 echo "# Juan Manuel Guerrero <juan.guerrero@gmx.de>"
530 echo "# and Bruno Haible <bruno@clisp.org>."
533 # ISO-8859-1 languages
536 echo "da CP865" # not CP850 ??
537 echo "da_DK CP865" # not CP850 ??
543 echo "en_AU CP850" # not CP437 ??
548 echo "en_ZA CP850" # not CP437 ??
586 echo "id CP850" # not CP437 ??
587 echo "id_ID CP850" # not CP437 ??
588 echo "is CP861" # not CP850 ??
589 echo "is_IS CP861" # not CP850 ??
597 echo "nb CP865" # not CP850 ??
598 echo "nb_NO CP865" # not CP850 ??
602 echo "nn CP865" # not CP850 ??
603 echo "nn_NO CP865" # not CP850 ??
604 echo "no CP865" # not CP850 ??
605 echo "no_NO CP865" # not CP850 ??
611 # ISO-8859-2 languages
628 echo "sr CP852" # CP852 or CP866 or CP855 ??
629 echo "sr_CS CP852" # CP852 or CP866 or CP855 ??
630 echo "sr_YU CP852" # CP852 or CP866 or CP855 ??
631 # ISO-8859-3 languages
634 # ISO-8859-5 languages
637 echo "bg CP866" # not CP855 ??
638 echo "bg_BG CP866" # not CP855 ??
639 echo "mk CP866" # not CP855 ??
640 echo "mk_MK CP866" # not CP855 ??
645 # ISO-8859-6 languages
659 # ISO-8859-7 languages
662 # ISO-8859-8 languages
665 # ISO-8859-9 languages
673 echo "zh_TW CP950" # not CP938 ??
675 echo "kr CP949" # not CP934 ??
676 echo "kr_KR CP949" # not CP934 ??