Annotation of embedaddon/libiconv/libcharset/lib/config.charset, revision 1.1.1.2.2.1
1.1 misho 1: #! /bin/sh
2: # Output a system dependent table of character encoding aliases.
3: #
1.1.1.2 misho 4: # Copyright (C) 2000-2004, 2006-2010 Free Software Foundation, Inc.
1.1 misho 5: #
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)
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 GNU
14: # Library General Public License for more details.
15: #
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,
19: # USA.
20: #
21: # The table consists of lines of the form
22: # ALIAS CANONICAL
23: #
24: # ALIAS is the (system dependent) result of "nl_langinfo (CODESET)".
25: # ALIAS is compared in a case sensitive way.
26: #
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.
32: #
33: # name MIME? used by which systems
1.1.1.2 misho 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
1.1 misho 38: # ISO-8859-4 Y osf solaris freebsd netbsd openbsd darwin
1.1.1.2 misho 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
1.1 misho 47: # KOI8-R Y glibc solaris freebsd netbsd openbsd darwin
1.1.1.2 misho 48: # KOI8-U Y glibc freebsd netbsd openbsd darwin cygwin
1.1 misho 49: # KOI8-T glibc
50: # CP437 dos
51: # CP775 dos
52: # CP850 aix osf dos
53: # CP852 dos
54: # CP855 dos
55: # CP856 aix
56: # CP857 dos
57: # CP861 dos
58: # CP862 dos
59: # CP864 dos
60: # CP865 dos
61: # CP866 freebsd netbsd openbsd darwin dos
62: # CP869 dos
63: # CP874 woe32 dos
64: # CP922 aix
1.1.1.2 misho 65: # CP932 aix cygwin woe32 dos
1.1 misho 66: # CP943 aix
67: # CP949 osf darwin woe32 dos
68: # CP950 woe32 dos
69: # CP1046 aix
70: # CP1124 aix
71: # CP1125 dos
72: # CP1129 aix
73: # CP1131 darwin
74: # CP1250 woe32
1.1.1.2 misho 75: # CP1251 glibc solaris netbsd openbsd darwin cygwin woe32
1.1 misho 76: # CP1252 aix woe32
77: # CP1253 woe32
78: # CP1254 woe32
79: # CP1255 glibc woe32
80: # CP1256 woe32
81: # CP1257 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
1.1.1.2 misho 84: # EUC-KR Y glibc aix hpux irix osf solaris freebsd netbsd darwin cygwin
1.1 misho 85: # EUC-TW glibc aix hpux irix osf solaris netbsd
1.1.1.2 misho 86: # BIG5 Y glibc aix hpux osf solaris freebsd netbsd darwin cygwin
1.1 misho 87: # BIG5-HKSCS glibc solaris darwin
1.1.1.2 misho 88: # GBK glibc aix osf solaris darwin cygwin woe32 dos
1.1 misho 89: # GB18030 glibc solaris netbsd darwin
90: # SHIFT_JIS Y hpux osf solaris freebsd netbsd darwin
91: # JOHAB glibc solaris woe32
1.1.1.2 misho 92: # TIS-620 glibc aix hpux osf solaris cygwin
1.1 misho 93: # VISCII Y glibc
94: # TCVN5712-1 glibc
95: # ARMSCII-8 glibc darwin
1.1.1.2 misho 96: # GEORGIAN-PS glibc cygwin
1.1 misho 97: # PT154 glibc
98: # HP-ROMAN8 hpux
99: # HP-ARABIC8 hpux
100: # HP-GREEK8 hpux
101: # HP-HEBREW8 hpux
102: # HP-TURKISH8 hpux
103: # HP-KANA8 hpux
104: # DEC-KANJI osf
105: # DEC-HANYU osf
1.1.1.2 misho 106: # UTF-8 Y glibc aix hpux osf solaris netbsd darwin cygwin
1.1 misho 107: #
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.).
110: #
111: # Note: ASCII and ANSI_X3.4-1968 are synonymous canonical names. Applications
112: # must understand both names and treat them as equivalent.
113: #
114: # The first argument passed to this file is the canonical host specification,
115: # CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM
116: # or
117: # CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM
118:
119: host="$1"
120: os=`echo "$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: "
126: case "$os" in
1.1.1.2 misho 127: linux-gnulibc1*)
128: # Linux libc5 doesn't have nl_langinfo(CODESET); therefore
129: # localcharset.c falls back to using the full locale name
130: # from the environment variables.
131: echo "C ASCII"
132: echo "POSIX ASCII"
133: for l in af af_ZA ca ca_ES da da_DK de de_AT de_BE de_CH de_DE de_LU \
134: en en_AU en_BW en_CA en_DK en_GB en_IE en_NZ en_US en_ZA \
135: en_ZW es es_AR es_BO es_CL es_CO es_DO es_EC es_ES es_GT \
136: es_HN es_MX es_PA es_PE es_PY es_SV es_US es_UY es_VE et \
137: et_EE eu eu_ES fi fi_FI fo fo_FO fr fr_BE fr_CA fr_CH fr_FR \
138: fr_LU ga ga_IE gl gl_ES id id_ID in in_ID is is_IS it it_CH \
139: it_IT kl kl_GL nl nl_BE nl_NL no no_NO pt pt_BR pt_PT sv \
140: sv_FI sv_SE; do
141: echo "$l ISO-8859-1"
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 "$l.utf-8@euro UTF-8"
153: done
154: for l in cs cs_CZ hr hr_HR hu hu_HU pl pl_PL ro ro_RO sk sk_SK sl \
155: sl_SI sr sr_CS sr_YU; do
156: echo "$l ISO-8859-2"
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"
161: done
162: for l in mk mk_MK ru ru_RU; do
163: echo "$l ISO-8859-5"
164: echo "$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"
169: done
170: for l in ar ar_SA; do
171: echo "$l ISO-8859-6"
172: echo "$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"
177: done
178: for l in el el_GR gr gr_GR; do
179: echo "$l ISO-8859-7"
180: echo "$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 "$l.utf-8@euro UTF-8"
186: done
187: for l in he he_IL iw iw_IL; do
188: echo "$l ISO-8859-8"
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"
193: done
194: for l in tr tr_TR; do
195: echo "$l ISO-8859-9"
196: echo "$l.iso-8859-9 ISO-8859-9"
197: echo "$l.cp-857 CP857"
198: echo "$l.cp-1254 CP1254"
199: echo "$l.utf-8 UTF-8"
200: done
201: for l in lt lt_LT lv lv_LV; do
202: #echo "$l BALTIC" # not a commonly used encoding, wrong encoding name
203: echo "$l ISO-8859-13"
204: done
205: for l in ru_UA uk uk_UA; do
206: echo "$l KOI8-U"
207: done
208: for l in zh zh_CN; do
209: #echo "$l GB_2312-80" # not a commonly used encoding, wrong encoding name
210: echo "$l GB2312"
211: done
212: for l in ja ja_JP ja_JP.EUC; do
213: echo "$l EUC-JP"
214: done
215: for l in ko ko_KR; do
216: echo "$l EUC-KR"
217: done
218: for l in th th_TH; do
219: echo "$l TIS-620"
220: done
221: for l in fa fa_IR; do
222: #echo "$l ISIRI-3342" # a broken encoding
223: echo "$l.utf-8 UTF-8"
224: done
225: ;;
226: linux* | *-gnu*)
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"
233: ;;
234: aix*)
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"
243: echo "IBM-850 CP850"
244: echo "IBM-856 CP856"
245: echo "IBM-921 ISO-8859-13"
246: echo "IBM-922 CP922"
247: echo "IBM-932 CP932"
248: echo "IBM-943 CP943"
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"
257: echo "big5 BIG5"
258: echo "GBK GBK"
259: echo "TIS-620 TIS-620"
260: echo "UTF-8 UTF-8"
261: ;;
262: hpux*)
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"
278: echo "big5 BIG5"
279: echo "eucJP EUC-JP"
280: echo "eucKR EUC-KR"
281: echo "eucTW EUC-TW"
282: echo "hp15CN GB2312"
283: #echo "ccdc ?" # what is this?
284: echo "SJIS SHIFT_JIS"
285: echo "utf8 UTF-8"
286: ;;
287: irix*)
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"
293: echo "eucCN GB2312"
294: echo "eucJP EUC-JP"
295: echo "eucKR EUC-KR"
296: echo "eucTW EUC-TW"
297: ;;
298: osf*)
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"
307: echo "cp850 CP850"
308: echo "big5 BIG5"
309: echo "dechanyu DEC-HANYU"
310: echo "dechanzi GB2312"
311: echo "deckanji DEC-KANJI"
312: echo "deckorean EUC-KR"
313: echo "eucJP EUC-JP"
314: echo "eucKR EUC-KR"
315: echo "eucTW EUC-TW"
316: echo "GBK GBK"
317: echo "KSC5601 CP949"
318: echo "sdeckanji EUC-JP"
319: echo "SJIS SHIFT_JIS"
320: echo "TACTIS TIS-620"
321: echo "UTF-8 UTF-8"
322: ;;
323: solaris*)
324: echo "646 ASCII"
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"
335: echo "koi8-r KOI8-R"
336: echo "ansi-1251 CP1251"
337: echo "BIG5 BIG5"
338: echo "Big5-HKSCS BIG5-HKSCS"
339: echo "gb2312 GB2312"
340: echo "GBK GBK"
341: echo "GB18030 GB18030"
342: echo "cns11643 EUC-TW"
343: echo "5601 EUC-KR"
344: echo "ko_KR.johap92 JOHAB"
345: echo "eucJP EUC-JP"
346: echo "PCK SHIFT_JIS"
347: echo "TIS620.2533 TIS-620"
348: #echo "sun_eu_greek ?" # what is this?
349: echo "UTF-8 UTF-8"
350: ;;
1.1.1.2.2.1! misho 351: freebsd4.[0-5]* | os2*)
1.1.1.2 misho 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.
357: echo "C ASCII"
358: echo "US-ASCII ASCII"
359: for l in la_LN lt_LN; do
360: echo "$l.ASCII ASCII"
361: done
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"
367: done
368: for l in cs_CZ hr_HR hu_HU la_LN lt_LN pl_PL sl_SI; do
369: echo "$l.ISO_8859-2 ISO-8859-2"
370: done
371: for l in la_LN lt_LT; do
372: echo "$l.ISO_8859-4 ISO-8859-4"
373: done
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"
378: done
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"
387: ;;
1.1.1.2.2.1! misho 388: freebsd*)
! 389: echo "US-ASCII ASCII"
! 390: echo "ISO8859-1 ISO-8859-1"
! 391: echo "ISO_8859-1 ISO-8859-1"
! 392: echo "ISO8859-2 ISO-8859-2"
! 393: echo "ISO_8859-2 ISO-8859-2"
! 394: echo "ISO8859-4 ISO-8859-4"
! 395: echo "ISO_8859-4 ISO-8859-4"
! 396: echo "ISO8859-5 ISO-8859-5"
! 397: echo "ISO_8859-5 ISO-8859-5"
! 398: echo "ISO8859-7 ISO-8859-7"
! 399: echo "ISO_8859-7 ISO-8859-7"
! 400: echo "ISO8859-9 ISO-8859-9"
! 401: echo "ISO_8859-9 ISO-8859-9"
! 402: echo "ISO8859-13 ISO-8859-13"
! 403: echo "ISO_8859-13 ISO-8859-13"
! 404: echo "ISO8859-15 ISO-8859-15"
! 405: echo "ISO_8859-15 ISO-8859-15"
! 406: echo "eucCN GB2312"
! 407: echo "eucJP EUC-JP"
! 408: echo "eucKR EUC-KR"
! 409: echo "Big5 BIG5"
! 410: echo "Big5HKSCS BIG5-HKSCS"
! 411: echo "SJIS SHIFT_JIS"
! 412: ;;
1.1.1.2 misho 413: netbsd*)
414: echo "646 ASCII"
415: echo "ISO8859-1 ISO-8859-1"
416: echo "ISO8859-2 ISO-8859-2"
417: echo "ISO8859-4 ISO-8859-4"
418: echo "ISO8859-5 ISO-8859-5"
419: echo "ISO8859-7 ISO-8859-7"
420: echo "ISO8859-13 ISO-8859-13"
421: echo "ISO8859-15 ISO-8859-15"
422: echo "eucCN GB2312"
423: echo "eucJP EUC-JP"
424: echo "eucKR EUC-KR"
425: echo "eucTW EUC-TW"
426: echo "BIG5 BIG5"
427: echo "SJIS SHIFT_JIS"
428: ;;
429: openbsd*)
430: echo "646 ASCII"
431: echo "ISO8859-1 ISO-8859-1"
432: echo "ISO8859-2 ISO-8859-2"
433: echo "ISO8859-4 ISO-8859-4"
434: echo "ISO8859-5 ISO-8859-5"
435: echo "ISO8859-7 ISO-8859-7"
436: echo "ISO8859-13 ISO-8859-13"
437: echo "ISO8859-15 ISO-8859-15"
438: ;;
439: darwin[56]*)
440: # Darwin 6.8 doesn't have nl_langinfo(CODESET); therefore
441: # localcharset.c falls back to using the full locale name
442: # from the environment variables.
443: echo "C ASCII"
444: for l in en_AU en_CA en_GB en_US la_LN; do
445: echo "$l.US-ASCII ASCII"
446: done
447: for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
448: fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT nl_BE \
449: nl_NL no_NO pt_PT sv_SE; do
450: echo "$l ISO-8859-1"
451: echo "$l.ISO8859-1 ISO-8859-1"
452: echo "$l.ISO8859-15 ISO-8859-15"
453: done
454: for l in la_LN; do
455: echo "$l.ISO8859-1 ISO-8859-1"
456: echo "$l.ISO8859-15 ISO-8859-15"
457: done
458: for l in cs_CZ hr_HR hu_HU la_LN pl_PL sl_SI; do
459: echo "$l.ISO8859-2 ISO-8859-2"
460: done
461: for l in la_LN lt_LT; do
462: echo "$l.ISO8859-4 ISO-8859-4"
463: done
464: for l in ru_RU; do
465: echo "$l.KOI8-R KOI8-R"
466: echo "$l.ISO8859-5 ISO-8859-5"
467: echo "$l.CP866 CP866"
468: done
469: for l in bg_BG; do
470: echo "$l.CP1251 CP1251"
471: done
472: echo "uk_UA.KOI8-U KOI8-U"
473: echo "zh_TW.BIG5 BIG5"
474: echo "zh_TW.Big5 BIG5"
475: echo "zh_CN.EUC GB2312"
476: echo "ja_JP.EUC EUC-JP"
477: echo "ja_JP.SJIS SHIFT_JIS"
478: echo "ko_KR.EUC EUC-KR"
479: ;;
480: darwin*)
481: # Darwin 7.5 has nl_langinfo(CODESET), but sometimes its value is
482: # useless:
483: # - It returns the empty string when LANG is set to a locale of the
484: # form ll_CC, although ll_CC/LC_CTYPE is a symlink to an UTF-8
485: # LC_CTYPE file.
486: # - The environment variables LANG, LC_CTYPE, LC_ALL are not set by
487: # the system; nl_langinfo(CODESET) returns "US-ASCII" in this case.
488: # - The documentation says:
489: # "... all code that calls BSD system routines should ensure
490: # that the const *char parameters of these routines are in UTF-8
491: # encoding. All BSD system functions expect their string
492: # parameters to be in UTF-8 encoding and nothing else."
493: # It also says
494: # "An additional caveat is that string parameters for files,
495: # paths, and other file-system entities must be in canonical
496: # UTF-8. In a canonical UTF-8 Unicode string, all decomposable
497: # characters are decomposed ..."
498: # but this is not true: You can pass non-decomposed UTF-8 strings
499: # to file system functions, and it is the OS which will convert
500: # them to decomposed UTF-8 before accessing the file system.
501: # - The Apple Terminal application displays UTF-8 by default.
502: # - However, other applications are free to use different encodings:
503: # - xterm uses ISO-8859-1 by default.
504: # - TextEdit uses MacRoman by default.
505: # We prefer UTF-8 over decomposed UTF-8-MAC because one should
506: # minimize the use of decomposed Unicode. Unfortunately, through the
507: # Darwin file system, decomposed UTF-8 strings are leaked into user
508: # space nevertheless.
509: # Then there are also the locales with encodings other than US-ASCII
510: # and UTF-8. These locales can be occasionally useful to users (e.g.
511: # when grepping through ISO-8859-1 encoded text files), when all their
512: # file names are in US-ASCII.
513: echo "ISO8859-1 ISO-8859-1"
514: echo "ISO8859-2 ISO-8859-2"
515: echo "ISO8859-4 ISO-8859-4"
516: echo "ISO8859-5 ISO-8859-5"
517: echo "ISO8859-7 ISO-8859-7"
518: echo "ISO8859-9 ISO-8859-9"
519: echo "ISO8859-13 ISO-8859-13"
520: echo "ISO8859-15 ISO-8859-15"
521: echo "KOI8-R KOI8-R"
522: echo "KOI8-U KOI8-U"
523: echo "CP866 CP866"
524: echo "CP949 CP949"
525: echo "CP1131 CP1131"
526: echo "CP1251 CP1251"
527: echo "eucCN GB2312"
528: echo "GB2312 GB2312"
529: echo "eucJP EUC-JP"
530: echo "eucKR EUC-KR"
531: echo "Big5 BIG5"
532: echo "Big5HKSCS BIG5-HKSCS"
533: echo "GBK GBK"
534: echo "GB18030 GB18030"
535: echo "SJIS SHIFT_JIS"
536: echo "ARMSCII-8 ARMSCII-8"
537: echo "PT154 PT154"
538: #echo "ISCII-DEV ?"
539: echo "* UTF-8"
540: ;;
541: beos* | haiku*)
542: # BeOS and Haiku have a single locale, and it has UTF-8 encoding.
543: echo "* UTF-8"
544: ;;
545: msdosdjgpp*)
546: # DJGPP 2.03 doesn't have nl_langinfo(CODESET); therefore
547: # localcharset.c falls back to using the full locale name
548: # from the environment variables.
549: echo "#"
550: echo "# The encodings given here may not all be correct."
551: echo "# If you find that the encoding given for your language and"
552: echo "# country is not the one your DOS machine actually uses, just"
553: echo "# correct it in this file, and send a mail to"
554: echo "# Juan Manuel Guerrero <juan.guerrero@gmx.de>"
555: echo "# and Bruno Haible <bruno@clisp.org>."
556: echo "#"
557: echo "C ASCII"
558: # ISO-8859-1 languages
559: echo "ca CP850"
560: echo "ca_ES CP850"
561: echo "da CP865" # not CP850 ??
562: echo "da_DK CP865" # not CP850 ??
563: echo "de CP850"
564: echo "de_AT CP850"
565: echo "de_CH CP850"
566: echo "de_DE CP850"
567: echo "en CP850"
568: echo "en_AU CP850" # not CP437 ??
569: echo "en_CA CP850"
570: echo "en_GB CP850"
571: echo "en_NZ CP437"
572: echo "en_US CP437"
573: echo "en_ZA CP850" # not CP437 ??
574: echo "es CP850"
575: echo "es_AR CP850"
576: echo "es_BO CP850"
577: echo "es_CL CP850"
578: echo "es_CO CP850"
579: echo "es_CR CP850"
580: echo "es_CU CP850"
581: echo "es_DO CP850"
582: echo "es_EC CP850"
583: echo "es_ES CP850"
584: echo "es_GT CP850"
585: echo "es_HN CP850"
586: echo "es_MX CP850"
587: echo "es_NI CP850"
588: echo "es_PA CP850"
589: echo "es_PY CP850"
590: echo "es_PE CP850"
591: echo "es_SV CP850"
592: echo "es_UY CP850"
593: echo "es_VE CP850"
594: echo "et CP850"
595: echo "et_EE CP850"
596: echo "eu CP850"
597: echo "eu_ES CP850"
598: echo "fi CP850"
599: echo "fi_FI CP850"
600: echo "fr CP850"
601: echo "fr_BE CP850"
602: echo "fr_CA CP850"
603: echo "fr_CH CP850"
604: echo "fr_FR CP850"
605: echo "ga CP850"
606: echo "ga_IE CP850"
607: echo "gd CP850"
608: echo "gd_GB CP850"
609: echo "gl CP850"
610: echo "gl_ES CP850"
611: echo "id CP850" # not CP437 ??
612: echo "id_ID CP850" # not CP437 ??
613: echo "is CP861" # not CP850 ??
614: echo "is_IS CP861" # not CP850 ??
615: echo "it CP850"
616: echo "it_CH CP850"
617: echo "it_IT CP850"
618: echo "lt CP775"
619: echo "lt_LT CP775"
620: echo "lv CP775"
621: echo "lv_LV CP775"
622: echo "nb CP865" # not CP850 ??
623: echo "nb_NO CP865" # not CP850 ??
624: echo "nl CP850"
625: echo "nl_BE CP850"
626: echo "nl_NL CP850"
627: echo "nn CP865" # not CP850 ??
628: echo "nn_NO CP865" # not CP850 ??
629: echo "no CP865" # not CP850 ??
630: echo "no_NO CP865" # not CP850 ??
631: echo "pt CP850"
632: echo "pt_BR CP850"
633: echo "pt_PT CP850"
634: echo "sv CP850"
635: echo "sv_SE CP850"
636: # ISO-8859-2 languages
637: echo "cs CP852"
638: echo "cs_CZ CP852"
639: echo "hr CP852"
640: echo "hr_HR CP852"
641: echo "hu CP852"
642: echo "hu_HU CP852"
643: echo "pl CP852"
644: echo "pl_PL CP852"
645: echo "ro CP852"
646: echo "ro_RO CP852"
647: echo "sk CP852"
648: echo "sk_SK CP852"
649: echo "sl CP852"
650: echo "sl_SI CP852"
651: echo "sq CP852"
652: echo "sq_AL CP852"
653: echo "sr CP852" # CP852 or CP866 or CP855 ??
654: echo "sr_CS CP852" # CP852 or CP866 or CP855 ??
655: echo "sr_YU CP852" # CP852 or CP866 or CP855 ??
656: # ISO-8859-3 languages
657: echo "mt CP850"
658: echo "mt_MT CP850"
659: # ISO-8859-5 languages
660: echo "be CP866"
661: echo "be_BE CP866"
662: echo "bg CP866" # not CP855 ??
663: echo "bg_BG CP866" # not CP855 ??
664: echo "mk CP866" # not CP855 ??
665: echo "mk_MK CP866" # not CP855 ??
666: echo "ru CP866"
667: echo "ru_RU CP866"
668: echo "uk CP1125"
669: echo "uk_UA CP1125"
670: # ISO-8859-6 languages
671: echo "ar CP864"
672: echo "ar_AE CP864"
673: echo "ar_DZ CP864"
674: echo "ar_EG CP864"
675: echo "ar_IQ CP864"
676: echo "ar_IR CP864"
677: echo "ar_JO CP864"
678: echo "ar_KW CP864"
679: echo "ar_MA CP864"
680: echo "ar_OM CP864"
681: echo "ar_QA CP864"
682: echo "ar_SA CP864"
683: echo "ar_SY CP864"
684: # ISO-8859-7 languages
685: echo "el CP869"
686: echo "el_GR CP869"
687: # ISO-8859-8 languages
688: echo "he CP862"
689: echo "he_IL CP862"
690: # ISO-8859-9 languages
691: echo "tr CP857"
692: echo "tr_TR CP857"
693: # Japanese
694: echo "ja CP932"
695: echo "ja_JP CP932"
696: # Chinese
697: echo "zh_CN GBK"
698: echo "zh_TW CP950" # not CP938 ??
699: # Korean
700: echo "kr CP949" # not CP934 ??
701: echo "kr_KR CP949" # not CP934 ??
702: # Thai
703: echo "th CP874"
704: echo "th_TH CP874"
705: # Other
706: echo "eo CP850"
707: echo "eo_EO CP850"
708: ;;
1.1 misho 709: esac
FreeBSD-CVSweb <freebsd-cvsweb@FreeBSD.org>
![[BACK]](/icons/cvsweb/back.gif){kind=icon}
Return to config.charset CVS log ![[TXT]](/icons/cvsweb/text.gif){kind=icon}
![[DIR]](/icons/cvsweb/dir.gif){kind=icon}
Up to [ELWIX - Embedded LightWeight unIX -] / embedaddon / libiconv / libcharset / lib