diff options
Diffstat (limited to 'gl/config.charset')
-rwxr-xr-x | gl/config.charset | 649 |
1 files changed, 649 insertions, 0 deletions
diff --git a/gl/config.charset b/gl/config.charset new file mode 100755 index 0000000..c233788 --- /dev/null +++ b/gl/config.charset | |||
@@ -0,0 +1,649 @@ | |||
1 | #! /bin/sh | ||
2 | # Output a system dependent table of character encoding aliases. | ||
3 | # | ||
4 | # Copyright (C) 2000-2004, 2006-2007 Free Software Foundation, Inc. | ||
5 | # | ||
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, or (at your option) | ||
9 | # any later version. | ||
10 | # | ||
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. | ||
15 | # | ||
16 | # You should have received a copy of the GNU General Public License along | ||
17 | # with this program; if not, write to the Free Software Foundation, | ||
18 | # Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA. | ||
19 | # | ||
20 | # The table consists of lines of the form | ||
21 | # ALIAS CANONICAL | ||
22 | # | ||
23 | # ALIAS is the (system dependent) result of "nl_langinfo (CODESET)". | ||
24 | # ALIAS is compared in a case sensitive way. | ||
25 | # | ||
26 | # CANONICAL is the GNU canonical name for this character encoding. | ||
27 | # It must be an encoding supported by libiconv. Support by GNU libc is | ||
28 | # also desirable. CANONICAL is case insensitive. Usually an upper case | ||
29 | # MIME charset name is preferred. | ||
30 | # The current list of GNU canonical charset names is as follows. | ||
31 | # | ||
32 | # name MIME? used by which systems | ||
33 | # ASCII, ANSI_X3.4-1968 glibc solaris freebsd netbsd darwin | ||
34 | # ISO-8859-1 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin | ||
35 | # ISO-8859-2 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin | ||
36 | # ISO-8859-3 Y glibc solaris | ||
37 | # ISO-8859-4 Y osf solaris freebsd netbsd openbsd darwin | ||
38 | # ISO-8859-5 Y glibc aix hpux irix osf solaris freebsd netbsd openbsd darwin | ||
39 | # ISO-8859-6 Y glibc aix hpux solaris | ||
40 | # ISO-8859-7 Y glibc aix hpux irix osf solaris netbsd openbsd darwin | ||
41 | # ISO-8859-8 Y glibc aix hpux osf solaris | ||
42 | # ISO-8859-9 Y glibc aix hpux irix osf solaris darwin | ||
43 | # ISO-8859-13 glibc netbsd openbsd darwin | ||
44 | # ISO-8859-14 glibc | ||
45 | # ISO-8859-15 glibc aix osf solaris freebsd netbsd openbsd darwin | ||
46 | # KOI8-R Y glibc solaris freebsd netbsd openbsd darwin | ||
47 | # KOI8-U Y glibc freebsd netbsd openbsd darwin | ||
48 | # KOI8-T glibc | ||
49 | # CP437 dos | ||
50 | # CP775 dos | ||
51 | # CP850 aix osf dos | ||
52 | # CP852 dos | ||
53 | # CP855 dos | ||
54 | # CP856 aix | ||
55 | # CP857 dos | ||
56 | # CP861 dos | ||
57 | # CP862 dos | ||
58 | # CP864 dos | ||
59 | # CP865 dos | ||
60 | # CP866 freebsd netbsd openbsd darwin dos | ||
61 | # CP869 dos | ||
62 | # CP874 woe32 dos | ||
63 | # CP922 aix | ||
64 | # CP932 aix woe32 dos | ||
65 | # CP943 aix | ||
66 | # CP949 osf woe32 dos | ||
67 | # CP950 woe32 dos | ||
68 | # CP1046 aix | ||
69 | # CP1124 aix | ||
70 | # CP1125 dos | ||
71 | # CP1129 aix | ||
72 | # CP1250 woe32 | ||
73 | # CP1251 glibc solaris netbsd openbsd darwin woe32 | ||
74 | # CP1252 aix woe32 | ||
75 | # CP1253 woe32 | ||
76 | # CP1254 woe32 | ||
77 | # CP1255 glibc woe32 | ||
78 | # CP1256 woe32 | ||
79 | # CP1257 woe32 | ||
80 | # GB2312 Y glibc aix hpux irix solaris freebsd netbsd darwin | ||
81 | # EUC-JP Y glibc aix hpux irix osf solaris freebsd netbsd darwin | ||
82 | # EUC-KR Y glibc aix hpux irix osf solaris freebsd netbsd darwin | ||
83 | # EUC-TW glibc aix hpux irix osf solaris netbsd | ||
84 | # BIG5 Y glibc aix hpux osf solaris freebsd netbsd darwin | ||
85 | # BIG5-HKSCS glibc solaris | ||
86 | # GBK glibc aix osf solaris woe32 dos | ||
87 | # GB18030 glibc solaris netbsd | ||
88 | # SHIFT_JIS Y hpux osf solaris freebsd netbsd darwin | ||
89 | # JOHAB glibc solaris woe32 | ||
90 | # TIS-620 glibc aix hpux osf solaris | ||
91 | # VISCII Y glibc | ||
92 | # TCVN5712-1 glibc | ||
93 | # GEORGIAN-PS glibc | ||
94 | # HP-ROMAN8 hpux | ||
95 | # HP-ARABIC8 hpux | ||
96 | # HP-GREEK8 hpux | ||
97 | # HP-HEBREW8 hpux | ||
98 | # HP-TURKISH8 hpux | ||
99 | # HP-KANA8 hpux | ||
100 | # DEC-KANJI osf | ||
101 | # DEC-HANYU osf | ||
102 | # UTF-8 Y glibc aix hpux osf solaris netbsd darwin | ||
103 | # | ||
104 | # Note: Names which are not marked as being a MIME name should not be used in | ||
105 | # Internet protocols for information interchange (mail, news, etc.). | ||
106 | # | ||
107 | # Note: ASCII and ANSI_X3.4-1968 are synonymous canonical names. Applications | ||
108 | # must understand both names and treat them as equivalent. | ||
109 | # | ||
110 | # The first argument passed to this file is the canonical host specification, | ||
111 | # CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM | ||
112 | # or | ||
113 | # CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM | ||
114 | |||
115 | host="$1" | ||
116 | os=`echo "$host" | sed -e 's/^[^-]*-[^-]*-\(.*\)$/\1/'` | ||
117 | echo "# This file contains a table of character encoding aliases," | ||
118 | echo "# suitable for operating system '${os}'." | ||
119 | echo "# It was automatically generated from config.charset." | ||
120 | # List of references, updated during installation: | ||
121 | echo "# Packages using this file: " | ||
122 | case "$os" in | ||
123 | linux-gnulibc1*) | ||
124 | # Linux libc5 doesn't have nl_langinfo(CODESET); therefore | ||
125 | # localcharset.c falls back to using the full locale name | ||
126 | # from the environment variables. | ||
127 | echo "C ASCII" | ||
128 | echo "POSIX ASCII" | ||
129 | for l in af af_ZA ca ca_ES da da_DK de de_AT de_BE de_CH de_DE de_LU \ | ||
130 | en en_AU en_BW en_CA en_DK en_GB en_IE en_NZ en_US en_ZA \ | ||
131 | en_ZW es es_AR es_BO es_CL es_CO es_DO es_EC es_ES es_GT \ | ||
132 | es_HN es_MX es_PA es_PE es_PY es_SV es_US es_UY es_VE et \ | ||
133 | et_EE eu eu_ES fi fi_FI fo fo_FO fr fr_BE fr_CA fr_CH fr_FR \ | ||
134 | fr_LU ga ga_IE gl gl_ES id id_ID in in_ID is is_IS it it_CH \ | ||
135 | it_IT kl kl_GL nl nl_BE nl_NL no no_NO pt pt_BR pt_PT sv \ | ||
136 | sv_FI sv_SE; do | ||
137 | echo "$l ISO-8859-1" | ||
138 | echo "$l.iso-8859-1 ISO-8859-1" | ||
139 | echo "$l.iso-8859-15 ISO-8859-15" | ||
140 | echo "$l.iso-8859-15@euro ISO-8859-15" | ||
141 | echo "$l@euro ISO-8859-15" | ||
142 | echo "$l.cp-437 CP437" | ||
143 | echo "$l.cp-850 CP850" | ||
144 | echo "$l.cp-1252 CP1252" | ||
145 | echo "$l.cp-1252@euro CP1252" | ||
146 | #echo "$l.atari-st ATARI-ST" # not a commonly used encoding | ||
147 | echo "$l.utf-8 UTF-8" | ||
148 | echo "$l.utf-8@euro UTF-8" | ||
149 | done | ||
150 | for l in cs cs_CZ hr hr_HR hu hu_HU pl pl_PL ro ro_RO sk sk_SK sl \ | ||
151 | sl_SI sr sr_CS sr_YU; do | ||
152 | echo "$l ISO-8859-2" | ||
153 | echo "$l.iso-8859-2 ISO-8859-2" | ||
154 | echo "$l.cp-852 CP852" | ||
155 | echo "$l.cp-1250 CP1250" | ||
156 | echo "$l.utf-8 UTF-8" | ||
157 | done | ||
158 | for l in mk mk_MK ru ru_RU; do | ||
159 | echo "$l ISO-8859-5" | ||
160 | echo "$l.iso-8859-5 ISO-8859-5" | ||
161 | echo "$l.koi8-r KOI8-R" | ||
162 | echo "$l.cp-866 CP866" | ||
163 | echo "$l.cp-1251 CP1251" | ||
164 | echo "$l.utf-8 UTF-8" | ||
165 | done | ||
166 | for l in ar ar_SA; do | ||
167 | echo "$l ISO-8859-6" | ||
168 | echo "$l.iso-8859-6 ISO-8859-6" | ||
169 | echo "$l.cp-864 CP864" | ||
170 | #echo "$l.cp-868 CP868" # not a commonly used encoding | ||
171 | echo "$l.cp-1256 CP1256" | ||
172 | echo "$l.utf-8 UTF-8" | ||
173 | done | ||
174 | for l in el el_GR gr gr_GR; do | ||
175 | echo "$l ISO-8859-7" | ||
176 | echo "$l.iso-8859-7 ISO-8859-7" | ||
177 | echo "$l.cp-869 CP869" | ||
178 | echo "$l.cp-1253 CP1253" | ||
179 | echo "$l.cp-1253@euro CP1253" | ||
180 | echo "$l.utf-8 UTF-8" | ||
181 | echo "$l.utf-8@euro UTF-8" | ||
182 | done | ||
183 | for l in he he_IL iw iw_IL; do | ||
184 | echo "$l ISO-8859-8" | ||
185 | echo "$l.iso-8859-8 ISO-8859-8" | ||
186 | echo "$l.cp-862 CP862" | ||
187 | echo "$l.cp-1255 CP1255" | ||
188 | echo "$l.utf-8 UTF-8" | ||
189 | done | ||
190 | for l in tr tr_TR; do | ||
191 | echo "$l ISO-8859-9" | ||
192 | echo "$l.iso-8859-9 ISO-8859-9" | ||
193 | echo "$l.cp-857 CP857" | ||
194 | echo "$l.cp-1254 CP1254" | ||
195 | echo "$l.utf-8 UTF-8" | ||
196 | done | ||
197 | for l in lt lt_LT lv lv_LV; do | ||
198 | #echo "$l BALTIC" # not a commonly used encoding, wrong encoding name | ||
199 | echo "$l ISO-8859-13" | ||
200 | done | ||
201 | for l in ru_UA uk uk_UA; do | ||
202 | echo "$l KOI8-U" | ||
203 | done | ||
204 | for l in zh zh_CN; do | ||
205 | #echo "$l GB_2312-80" # not a commonly used encoding, wrong encoding name | ||
206 | echo "$l GB2312" | ||
207 | done | ||
208 | for l in ja ja_JP ja_JP.EUC; do | ||
209 | echo "$l EUC-JP" | ||
210 | done | ||
211 | for l in ko ko_KR; do | ||
212 | echo "$l EUC-KR" | ||
213 | done | ||
214 | for l in th th_TH; do | ||
215 | echo "$l TIS-620" | ||
216 | done | ||
217 | for l in fa fa_IR; do | ||
218 | #echo "$l ISIRI-3342" # a broken encoding | ||
219 | echo "$l.utf-8 UTF-8" | ||
220 | done | ||
221 | ;; | ||
222 | linux* | *-gnu*) | ||
223 | # With glibc-2.1 or newer, we don't need any canonicalization, | ||
224 | # because glibc has iconv and both glibc and libiconv support all | ||
225 | # GNU canonical names directly. Therefore, the Makefile does not | ||
226 | # need to install the alias file at all. | ||
227 | # The following applies only to glibc-2.0.x and older libcs. | ||
228 | echo "ISO_646.IRV:1983 ASCII" | ||
229 | ;; | ||
230 | aix*) | ||
231 | echo "ISO8859-1 ISO-8859-1" | ||
232 | echo "ISO8859-2 ISO-8859-2" | ||
233 | echo "ISO8859-5 ISO-8859-5" | ||
234 | echo "ISO8859-6 ISO-8859-6" | ||
235 | echo "ISO8859-7 ISO-8859-7" | ||
236 | echo "ISO8859-8 ISO-8859-8" | ||
237 | echo "ISO8859-9 ISO-8859-9" | ||
238 | echo "ISO8859-15 ISO-8859-15" | ||
239 | echo "IBM-850 CP850" | ||
240 | echo "IBM-856 CP856" | ||
241 | echo "IBM-921 ISO-8859-13" | ||
242 | echo "IBM-922 CP922" | ||
243 | echo "IBM-932 CP932" | ||
244 | echo "IBM-943 CP943" | ||
245 | echo "IBM-1046 CP1046" | ||
246 | echo "IBM-1124 CP1124" | ||
247 | echo "IBM-1129 CP1129" | ||
248 | echo "IBM-1252 CP1252" | ||
249 | echo "IBM-eucCN GB2312" | ||
250 | echo "IBM-eucJP EUC-JP" | ||
251 | echo "IBM-eucKR EUC-KR" | ||
252 | echo "IBM-eucTW EUC-TW" | ||
253 | echo "big5 BIG5" | ||
254 | echo "GBK GBK" | ||
255 | echo "TIS-620 TIS-620" | ||
256 | echo "UTF-8 UTF-8" | ||
257 | ;; | ||
258 | hpux*) | ||
259 | echo "iso88591 ISO-8859-1" | ||
260 | echo "iso88592 ISO-8859-2" | ||
261 | echo "iso88595 ISO-8859-5" | ||
262 | echo "iso88596 ISO-8859-6" | ||
263 | echo "iso88597 ISO-8859-7" | ||
264 | echo "iso88598 ISO-8859-8" | ||
265 | echo "iso88599 ISO-8859-9" | ||
266 | echo "iso885915 ISO-8859-15" | ||
267 | echo "roman8 HP-ROMAN8" | ||
268 | echo "arabic8 HP-ARABIC8" | ||
269 | echo "greek8 HP-GREEK8" | ||
270 | echo "hebrew8 HP-HEBREW8" | ||
271 | echo "turkish8 HP-TURKISH8" | ||
272 | echo "kana8 HP-KANA8" | ||
273 | echo "tis620 TIS-620" | ||
274 | echo "big5 BIG5" | ||
275 | echo "eucJP EUC-JP" | ||
276 | echo "eucKR EUC-KR" | ||
277 | echo "eucTW EUC-TW" | ||
278 | echo "hp15CN GB2312" | ||
279 | #echo "ccdc ?" # what is this? | ||
280 | echo "SJIS SHIFT_JIS" | ||
281 | echo "utf8 UTF-8" | ||
282 | ;; | ||
283 | irix*) | ||
284 | echo "ISO8859-1 ISO-8859-1" | ||
285 | echo "ISO8859-2 ISO-8859-2" | ||
286 | echo "ISO8859-5 ISO-8859-5" | ||
287 | echo "ISO8859-7 ISO-8859-7" | ||
288 | echo "ISO8859-9 ISO-8859-9" | ||
289 | echo "eucCN GB2312" | ||
290 | echo "eucJP EUC-JP" | ||
291 | echo "eucKR EUC-KR" | ||
292 | echo "eucTW EUC-TW" | ||
293 | ;; | ||
294 | osf*) | ||
295 | echo "ISO8859-1 ISO-8859-1" | ||
296 | echo "ISO8859-2 ISO-8859-2" | ||
297 | echo "ISO8859-4 ISO-8859-4" | ||
298 | echo "ISO8859-5 ISO-8859-5" | ||
299 | echo "ISO8859-7 ISO-8859-7" | ||
300 | echo "ISO8859-8 ISO-8859-8" | ||
301 | echo "ISO8859-9 ISO-8859-9" | ||
302 | echo "ISO8859-15 ISO-8859-15" | ||
303 | echo "cp850 CP850" | ||
304 | echo "big5 BIG5" | ||
305 | echo "dechanyu DEC-HANYU" | ||
306 | echo "dechanzi GB2312" | ||
307 | echo "deckanji DEC-KANJI" | ||
308 | echo "deckorean EUC-KR" | ||
309 | echo "eucJP EUC-JP" | ||
310 | echo "eucKR EUC-KR" | ||
311 | echo "eucTW EUC-TW" | ||
312 | echo "GBK GBK" | ||
313 | echo "KSC5601 CP949" | ||
314 | echo "sdeckanji EUC-JP" | ||
315 | echo "SJIS SHIFT_JIS" | ||
316 | echo "TACTIS TIS-620" | ||
317 | echo "UTF-8 UTF-8" | ||
318 | ;; | ||
319 | solaris*) | ||
320 | echo "646 ASCII" | ||
321 | echo "ISO8859-1 ISO-8859-1" | ||
322 | echo "ISO8859-2 ISO-8859-2" | ||
323 | echo "ISO8859-3 ISO-8859-3" | ||
324 | echo "ISO8859-4 ISO-8859-4" | ||
325 | echo "ISO8859-5 ISO-8859-5" | ||
326 | echo "ISO8859-6 ISO-8859-6" | ||
327 | echo "ISO8859-7 ISO-8859-7" | ||
328 | echo "ISO8859-8 ISO-8859-8" | ||
329 | echo "ISO8859-9 ISO-8859-9" | ||
330 | echo "ISO8859-15 ISO-8859-15" | ||
331 | echo "koi8-r KOI8-R" | ||
332 | echo "ansi-1251 CP1251" | ||
333 | echo "BIG5 BIG5" | ||
334 | echo "Big5-HKSCS BIG5-HKSCS" | ||
335 | echo "gb2312 GB2312" | ||
336 | echo "GBK GBK" | ||
337 | echo "GB18030 GB18030" | ||
338 | echo "cns11643 EUC-TW" | ||
339 | echo "5601 EUC-KR" | ||
340 | echo "ko_KR.johap92 JOHAB" | ||
341 | echo "eucJP EUC-JP" | ||
342 | echo "PCK SHIFT_JIS" | ||
343 | echo "TIS620.2533 TIS-620" | ||
344 | #echo "sun_eu_greek ?" # what is this? | ||
345 | echo "UTF-8 UTF-8" | ||
346 | ;; | ||
347 | freebsd* | os2*) | ||
348 | # FreeBSD 4.2 doesn't have nl_langinfo(CODESET); therefore | ||
349 | # localcharset.c falls back to using the full locale name | ||
350 | # from the environment variables. | ||
351 | # Likewise for OS/2. OS/2 has XFree86 just like FreeBSD. Just | ||
352 | # reuse FreeBSD's locale data for OS/2. | ||
353 | echo "C ASCII" | ||
354 | echo "US-ASCII ASCII" | ||
355 | for l in la_LN lt_LN; do | ||
356 | echo "$l.ASCII ASCII" | ||
357 | done | ||
358 | for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \ | ||
359 | fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT la_LN \ | ||
360 | lt_LN nl_BE nl_NL no_NO pt_PT sv_SE; do | ||
361 | echo "$l.ISO_8859-1 ISO-8859-1" | ||
362 | echo "$l.DIS_8859-15 ISO-8859-15" | ||
363 | done | ||
364 | for l in cs_CZ hr_HR hu_HU la_LN lt_LN pl_PL sl_SI; do | ||
365 | echo "$l.ISO_8859-2 ISO-8859-2" | ||
366 | done | ||
367 | for l in la_LN lt_LT; do | ||
368 | echo "$l.ISO_8859-4 ISO-8859-4" | ||
369 | done | ||
370 | for l in ru_RU ru_SU; do | ||
371 | echo "$l.KOI8-R KOI8-R" | ||
372 | echo "$l.ISO_8859-5 ISO-8859-5" | ||
373 | echo "$l.CP866 CP866" | ||
374 | done | ||
375 | echo "uk_UA.KOI8-U KOI8-U" | ||
376 | echo "zh_TW.BIG5 BIG5" | ||
377 | echo "zh_TW.Big5 BIG5" | ||
378 | echo "zh_CN.EUC GB2312" | ||
379 | echo "ja_JP.EUC EUC-JP" | ||
380 | echo "ja_JP.SJIS SHIFT_JIS" | ||
381 | echo "ja_JP.Shift_JIS SHIFT_JIS" | ||
382 | echo "ko_KR.EUC EUC-KR" | ||
383 | ;; | ||
384 | netbsd*) | ||
385 | echo "646 ASCII" | ||
386 | echo "ISO8859-1 ISO-8859-1" | ||
387 | echo "ISO8859-2 ISO-8859-2" | ||
388 | echo "ISO8859-4 ISO-8859-4" | ||
389 | echo "ISO8859-5 ISO-8859-5" | ||
390 | echo "ISO8859-7 ISO-8859-7" | ||
391 | echo "ISO8859-13 ISO-8859-13" | ||
392 | echo "ISO8859-15 ISO-8859-15" | ||
393 | echo "eucCN GB2312" | ||
394 | echo "eucJP EUC-JP" | ||
395 | echo "eucKR EUC-KR" | ||
396 | echo "eucTW EUC-TW" | ||
397 | echo "BIG5 BIG5" | ||
398 | echo "SJIS SHIFT_JIS" | ||
399 | ;; | ||
400 | openbsd*) | ||
401 | echo "646 ASCII" | ||
402 | echo "ISO8859-1 ISO-8859-1" | ||
403 | echo "ISO8859-2 ISO-8859-2" | ||
404 | echo "ISO8859-4 ISO-8859-4" | ||
405 | echo "ISO8859-5 ISO-8859-5" | ||
406 | echo "ISO8859-7 ISO-8859-7" | ||
407 | echo "ISO8859-13 ISO-8859-13" | ||
408 | echo "ISO8859-15 ISO-8859-15" | ||
409 | ;; | ||
410 | darwin[56]*) | ||
411 | # Darwin 6.8 doesn't have nl_langinfo(CODESET); therefore | ||
412 | # localcharset.c falls back to using the full locale name | ||
413 | # from the environment variables. | ||
414 | echo "C ASCII" | ||
415 | for l in en_AU en_CA en_GB en_US la_LN; do | ||
416 | echo "$l.US-ASCII ASCII" | ||
417 | done | ||
418 | for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \ | ||
419 | fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT nl_BE \ | ||
420 | nl_NL no_NO pt_PT sv_SE; do | ||
421 | echo "$l ISO-8859-1" | ||
422 | echo "$l.ISO8859-1 ISO-8859-1" | ||
423 | echo "$l.ISO8859-15 ISO-8859-15" | ||
424 | done | ||
425 | for l in la_LN; do | ||
426 | echo "$l.ISO8859-1 ISO-8859-1" | ||
427 | echo "$l.ISO8859-15 ISO-8859-15" | ||
428 | done | ||
429 | for l in cs_CZ hr_HR hu_HU la_LN pl_PL sl_SI; do | ||
430 | echo "$l.ISO8859-2 ISO-8859-2" | ||
431 | done | ||
432 | for l in la_LN lt_LT; do | ||
433 | echo "$l.ISO8859-4 ISO-8859-4" | ||
434 | done | ||
435 | for l in ru_RU; do | ||
436 | echo "$l.KOI8-R KOI8-R" | ||
437 | echo "$l.ISO8859-5 ISO-8859-5" | ||
438 | echo "$l.CP866 CP866" | ||
439 | done | ||
440 | for l in bg_BG; do | ||
441 | echo "$l.CP1251 CP1251" | ||
442 | done | ||
443 | echo "uk_UA.KOI8-U KOI8-U" | ||
444 | echo "zh_TW.BIG5 BIG5" | ||
445 | echo "zh_TW.Big5 BIG5" | ||
446 | echo "zh_CN.EUC GB2312" | ||
447 | echo "ja_JP.EUC EUC-JP" | ||
448 | echo "ja_JP.SJIS SHIFT_JIS" | ||
449 | echo "ko_KR.EUC EUC-KR" | ||
450 | ;; | ||
451 | darwin*) | ||
452 | # Darwin 7.5 has nl_langinfo(CODESET), but it is useless: | ||
453 | # - It returns the empty string when LANG is set to a locale of the | ||
454 | # form ll_CC, although ll_CC/LC_CTYPE is a symlink to an UTF-8 | ||
455 | # LC_CTYPE file. | ||
456 | # - The environment variables LANG, LC_CTYPE, LC_ALL are not set by | ||
457 | # the system; nl_langinfo(CODESET) returns "US-ASCII" in this case. | ||
458 | # - The documentation says: | ||
459 | # "... all code that calls BSD system routines should ensure | ||
460 | # that the const *char parameters of these routines are in UTF-8 | ||
461 | # encoding. All BSD system functions expect their string | ||
462 | # parameters to be in UTF-8 encoding and nothing else." | ||
463 | # It also says | ||
464 | # "An additional caveat is that string parameters for files, | ||
465 | # paths, and other file-system entities must be in canonical | ||
466 | # UTF-8. In a canonical UTF-8 Unicode string, all decomposable | ||
467 | # characters are decomposed ..." | ||
468 | # but this is not true: You can pass non-decomposed UTF-8 strings | ||
469 | # to file system functions, and it is the OS which will convert | ||
470 | # them to decomposed UTF-8 before accessing the file system. | ||
471 | # - The Apple Terminal application displays UTF-8 by default. | ||
472 | # - However, other applications are free to use different encodings: | ||
473 | # - xterm uses ISO-8859-1 by default. | ||
474 | # - TextEdit uses MacRoman by default. | ||
475 | # We prefer UTF-8 over decomposed UTF-8-MAC because one should | ||
476 | # minimize the use of decomposed Unicode. Unfortunately, through the | ||
477 | # Darwin file system, decomposed UTF-8 strings are leaked into user | ||
478 | # space nevertheless. | ||
479 | echo "* UTF-8" | ||
480 | ;; | ||
481 | beos*) | ||
482 | # BeOS has a single locale, and it has UTF-8 encoding. | ||
483 | echo "* UTF-8" | ||
484 | ;; | ||
485 | msdosdjgpp*) | ||
486 | # DJGPP 2.03 doesn't have nl_langinfo(CODESET); therefore | ||
487 | # localcharset.c falls back to using the full locale name | ||
488 | # from the environment variables. | ||
489 | echo "#" | ||
490 | echo "# The encodings given here may not all be correct." | ||
491 | echo "# If you find that the encoding given for your language and" | ||
492 | echo "# country is not the one your DOS machine actually uses, just" | ||
493 | echo "# correct it in this file, and send a mail to" | ||
494 | echo "# Juan Manuel Guerrero <juan.guerrero@gmx.de>" | ||
495 | echo "# and Bruno Haible <bruno@clisp.org>." | ||
496 | echo "#" | ||
497 | echo "C ASCII" | ||
498 | # ISO-8859-1 languages | ||
499 | echo "ca CP850" | ||
500 | echo "ca_ES CP850" | ||
501 | echo "da CP865" # not CP850 ?? | ||
502 | echo "da_DK CP865" # not CP850 ?? | ||
503 | echo "de CP850" | ||
504 | echo "de_AT CP850" | ||
505 | echo "de_CH CP850" | ||
506 | echo "de_DE CP850" | ||
507 | echo "en CP850" | ||
508 | echo "en_AU CP850" # not CP437 ?? | ||
509 | echo "en_CA CP850" | ||
510 | echo "en_GB CP850" | ||
511 | echo "en_NZ CP437" | ||
512 | echo "en_US CP437" | ||
513 | echo "en_ZA CP850" # not CP437 ?? | ||
514 | echo "es CP850" | ||
515 | echo "es_AR CP850" | ||
516 | echo "es_BO CP850" | ||
517 | echo "es_CL CP850" | ||
518 | echo "es_CO CP850" | ||
519 | echo "es_CR CP850" | ||
520 | echo "es_CU CP850" | ||
521 | echo "es_DO CP850" | ||
522 | echo "es_EC CP850" | ||
523 | echo "es_ES CP850" | ||
524 | echo "es_GT CP850" | ||
525 | echo "es_HN CP850" | ||
526 | echo "es_MX CP850" | ||
527 | echo "es_NI CP850" | ||
528 | echo "es_PA CP850" | ||
529 | echo "es_PY CP850" | ||
530 | echo "es_PE CP850" | ||
531 | echo "es_SV CP850" | ||
532 | echo "es_UY CP850" | ||
533 | echo "es_VE CP850" | ||
534 | echo "et CP850" | ||
535 | echo "et_EE CP850" | ||
536 | echo "eu CP850" | ||
537 | echo "eu_ES CP850" | ||
538 | echo "fi CP850" | ||
539 | echo "fi_FI CP850" | ||
540 | echo "fr CP850" | ||
541 | echo "fr_BE CP850" | ||
542 | echo "fr_CA CP850" | ||
543 | echo "fr_CH CP850" | ||
544 | echo "fr_FR CP850" | ||
545 | echo "ga CP850" | ||
546 | echo "ga_IE CP850" | ||
547 | echo "gd CP850" | ||
548 | echo "gd_GB CP850" | ||
549 | echo "gl CP850" | ||
550 | echo "gl_ES CP850" | ||
551 | echo "id CP850" # not CP437 ?? | ||
552 | echo "id_ID CP850" # not CP437 ?? | ||
553 | echo "is CP861" # not CP850 ?? | ||
554 | echo "is_IS CP861" # not CP850 ?? | ||
555 | echo "it CP850" | ||
556 | echo "it_CH CP850" | ||
557 | echo "it_IT CP850" | ||
558 | echo "lt CP775" | ||
559 | echo "lt_LT CP775" | ||
560 | echo "lv CP775" | ||
561 | echo "lv_LV CP775" | ||
562 | echo "nb CP865" # not CP850 ?? | ||
563 | echo "nb_NO CP865" # not CP850 ?? | ||
564 | echo "nl CP850" | ||
565 | echo "nl_BE CP850" | ||
566 | echo "nl_NL CP850" | ||
567 | echo "nn CP865" # not CP850 ?? | ||
568 | echo "nn_NO CP865" # not CP850 ?? | ||
569 | echo "no CP865" # not CP850 ?? | ||
570 | echo "no_NO CP865" # not CP850 ?? | ||
571 | echo "pt CP850" | ||
572 | echo "pt_BR CP850" | ||
573 | echo "pt_PT CP850" | ||
574 | echo "sv CP850" | ||
575 | echo "sv_SE CP850" | ||
576 | # ISO-8859-2 languages | ||
577 | echo "cs CP852" | ||
578 | echo "cs_CZ CP852" | ||
579 | echo "hr CP852" | ||
580 | echo "hr_HR CP852" | ||
581 | echo "hu CP852" | ||
582 | echo "hu_HU CP852" | ||
583 | echo "pl CP852" | ||
584 | echo "pl_PL CP852" | ||
585 | echo "ro CP852" | ||
586 | echo "ro_RO CP852" | ||
587 | echo "sk CP852" | ||
588 | echo "sk_SK CP852" | ||
589 | echo "sl CP852" | ||
590 | echo "sl_SI CP852" | ||
591 | echo "sq CP852" | ||
592 | echo "sq_AL CP852" | ||
593 | echo "sr CP852" # CP852 or CP866 or CP855 ?? | ||
594 | echo "sr_CS CP852" # CP852 or CP866 or CP855 ?? | ||
595 | echo "sr_YU CP852" # CP852 or CP866 or CP855 ?? | ||
596 | # ISO-8859-3 languages | ||
597 | echo "mt CP850" | ||
598 | echo "mt_MT CP850" | ||
599 | # ISO-8859-5 languages | ||
600 | echo "be CP866" | ||
601 | echo "be_BE CP866" | ||
602 | echo "bg CP866" # not CP855 ?? | ||
603 | echo "bg_BG CP866" # not CP855 ?? | ||
604 | echo "mk CP866" # not CP855 ?? | ||
605 | echo "mk_MK CP866" # not CP855 ?? | ||
606 | echo "ru CP866" | ||
607 | echo "ru_RU CP866" | ||
608 | echo "uk CP1125" | ||
609 | echo "uk_UA CP1125" | ||
610 | # ISO-8859-6 languages | ||
611 | echo "ar CP864" | ||
612 | echo "ar_AE CP864" | ||
613 | echo "ar_DZ CP864" | ||
614 | echo "ar_EG CP864" | ||
615 | echo "ar_IQ CP864" | ||
616 | echo "ar_IR CP864" | ||
617 | echo "ar_JO CP864" | ||
618 | echo "ar_KW CP864" | ||
619 | echo "ar_MA CP864" | ||
620 | echo "ar_OM CP864" | ||
621 | echo "ar_QA CP864" | ||
622 | echo "ar_SA CP864" | ||
623 | echo "ar_SY CP864" | ||
624 | # ISO-8859-7 languages | ||
625 | echo "el CP869" | ||
626 | echo "el_GR CP869" | ||
627 | # ISO-8859-8 languages | ||
628 | echo "he CP862" | ||
629 | echo "he_IL CP862" | ||
630 | # ISO-8859-9 languages | ||
631 | echo "tr CP857" | ||
632 | echo "tr_TR CP857" | ||
633 | # Japanese | ||
634 | echo "ja CP932" | ||
635 | echo "ja_JP CP932" | ||
636 | # Chinese | ||
637 | echo "zh_CN GBK" | ||
638 | echo "zh_TW CP950" # not CP938 ?? | ||
639 | # Korean | ||
640 | echo "kr CP949" # not CP934 ?? | ||
641 | echo "kr_KR CP949" # not CP934 ?? | ||
642 | # Thai | ||
643 | echo "th CP874" | ||
644 | echo "th_TH CP874" | ||
645 | # Other | ||
646 | echo "eo CP850" | ||
647 | echo "eo_EO CP850" | ||
648 | ;; | ||
649 | esac | ||