summaryrefslogtreecommitdiff
path: root/lib/config.charset
blob: b1f5d41624c952eeae4d80b982989cbc301b141d (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
#! /bin/sh
# Output a system dependent table of character encoding aliases.
#
#   Copyright (C) 2000 Free Software Foundation, Inc.
#
#   This program is free software; you can redistribute it and/or modify it
#   under the terms of the GNU Library General Public License as published
#   by the Free Software Foundation; either version 2, or (at your option)
#   any later version.
#
#   This program is distributed in the hope that it will be useful,
#   but WITHOUT ANY WARRANTY; without even the implied warranty of
#   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
#   Library General Public License for more details.
#
#   You should have received a copy of the GNU Library General Public
#   License along with this program; if not, write to the Free Software
#   Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307,
#   USA.
#
# The table consists of lines of the form
#    ALIAS  CANONICAL
#
# ALIAS is the (system dependent) result of "nl_langinfo (CODESET)".
# ALIAS is compared in a case sensitive way.
#
# CANONICAL is the GNU canonical name for this character encoding.
# It must be an encoding supported by libiconv. Support by GNU libc is
# also desirable. CANONICAL is case insensitive. Usually an upper case
# MIME charset name is preferred.
# The current list of GNU canonical charset names is as follows.
#
#       name                         used by which systems         a MIME name?
#   ASCII, ANSI_X3.4-1968     glibc solaris freebsd
#   ISO-8859-1                glibc aix hpux irix osf solaris freebsd   yes
#   ISO-8859-2                glibc aix hpux irix solaris freebsd       yes
#   ISO-8859-3                glibc                                     yes
#   ISO-8859-4                solaris                                   yes
#   ISO-8859-5                glibc aix hpux irix solaris               yes
#   ISO-8859-6                glibc aix hpux solaris                    yes
#   ISO-8859-7                glibc aix hpux irix osf solaris           yes
#   ISO-8859-8                glibc aix hpux solaris                    yes
#   ISO-8859-9                glibc aix hpux irix osf solaris           yes
#   ISO-8859-13               glibc
#   ISO-8859-15               glibc aix solaris freebsd
#   KOI8-R                    glibc solaris freebsd                     yes
#   KOI8-U                    glibc                                     yes
#   CP850                     aix osf
#   CP856                     aix
#   CP866                     freebsd
#   CP874                     win32
#   CP922                     aix
#   CP932                     aix win32
#   CP943                     aix
#   CP949                     win32
#   CP950                     win32
#   CP1046                    aix
#   CP1124                    aix
#   CP1129                    aix
#   CP1250                    win32
#   CP1251                    glibc win32
#   CP1252                    aix win32
#   CP1253                    win32
#   CP1254                    win32
#   CP1255                    win32
#   CP1256                    win32
#   CP1257                    win32
#   GB2312                    glibc aix hpux irix solaris               yes
#   EUC-JP                    glibc aix hpux irix solaris               yes
#   EUC-KR                    glibc aix hpux irix solaris               yes
#   EUC-TW                    glibc aix hpux irix solaris
#   BIG5                      glibc aix hpux solaris                    yes
#   BIG5HKSCS                 glibc
#   GBK                       aix win32
#   GB18030                   glibc
#   SJIS                      hpux solaris
#   JOHAB                     glibc win32
#   TIS-620                   glibc aix hpux solaris
#   VISCII                    glibc                                     yes
#   HP-ROMAN8                 hpux
#   HP-ARABIC8                hpux
#   HP-GREEK8                 hpux
#   HP-HEBREW8                hpux
#   HP-TURKISH8               hpux
#   HP-KANA8                  hpux
#   UTF-8                     glibc aix hpux solaris                    yes
#
# Note: Names which are not marked as being a MIME name should not be used in
# Internet protocols for information interchange (mail, news, etc.).
#
# Note: ASCII and ANSI_X3.4-1968 are synonymous canonical names. Applications
# must understand both names and treat them as equivalent.
#
# The first argument passed to this file is the canonical host specification,
#    CPU_TYPE-MANUFACTURER-OPERATING_SYSTEM
# or
#    CPU_TYPE-MANUFACTURER-KERNEL-OPERATING_SYSTEM

host="$1"
os=`echo "$host" | sed -e 's/^[^-]*-[^-]*-\(.*\)$/\1/'`
echo "# This file contains a table of character encoding aliases,"
echo "# suitable for operating system '${os}'."
echo "# It was automatically generated from config.charset."
# List of references, updated during installation:
echo "# Packages using this file: "
case "$os" in
    linux* | *-gnu*)
	# With glibc-2.1 or newer, we don't need any canonicalization,
	# because glibc has iconv and both glibc and libiconv support all
	# GNU canonical names directly. Therefore, the Makefile does not
	# need to install the alias file at all.
	# The following applies only to glibc-2.0.x and older libcs.
	echo "ISO_646.IRV:1983 ASCII"
	;;
    aix*)
	echo "ISO8859-1 ISO-8859-1"
	echo "ISO8859-2 ISO-8859-2"
	echo "ISO8859-5 ISO-8859-5"
	echo "ISO8859-6 ISO-8859-6"
	echo "ISO8859-7 ISO-8859-7"
	echo "ISO8859-8 ISO-8859-8"
	echo "ISO8859-9 ISO-8859-9"
	echo "ISO8859-15 ISO-8859-15"
	echo "IBM-850 CP850"
	echo "IBM-856 CP856"
	echo "IBM-921 ISO-8859-13"
	echo "IBM-922 CP922"
	echo "IBM-932 CP932"
	echo "IBM-943 CP943"
	echo "IBM-1046 CP1046"
	echo "IBM-1124 CP1124"
	echo "IBM-1129 CP1129"
	echo "IBM-1252 CP1252"
	echo "IBM-eucCN GB2312"
	echo "IBM-eucJP EUC-JP"
	echo "IBM-eucKR EUC-KR"
	echo "IBM-eucTW EUC-TW"
	echo "big5 BIG5"
	echo "GBK GBK"
	echo "TIS-620 TIS-620"
	echo "UTF-8 UTF-8"
	;;
    hpux*)
	echo "iso88591 ISO-8859-1"
	echo "iso88592 ISO-8859-2"
	echo "iso88595 ISO-8859-5"
	echo "iso88596 ISO-8859-6"
	echo "iso88597 ISO-8859-7"
	echo "iso88598 ISO-8859-8"
	echo "iso88599 ISO-8859-9"
	echo "iso885915 ISO-8859-15"
	echo "roman8 HP-ROMAN8"
	echo "arabic8 HP-ARABIC8"
	echo "greek8 HP-GREEK8"
	echo "hebrew8 HP-HEBREW8"
	echo "turkish8 HP-TURKISH8"
	echo "kana8 HP-KANA8"
	echo "tis620 TIS-620"
	echo "big5 BIG5"
	echo "eucJP EUC-JP"
	echo "eucKR EUC-KR"
	echo "eucTW EUC-TW"
	echo "hp15CN GB2312"
	#echo "ccdc ?" # what is this?
	echo "SJIS SJIS"
	echo "utf8 UTF-8"
	;;
    irix*)
	echo "ISO8859-1 ISO-8859-1"
	echo "ISO8859-2 ISO-8859-2"
	echo "ISO8859-5 ISO-8859-5"
	echo "ISO8859-7 ISO-8859-7"
	echo "ISO8859-9 ISO-8859-9"
	echo "eucCN GB2312"
	echo "eucJP EUC-JP"
	echo "eucKR EUC-KR"
	echo "eucTW EUC-TW"
	;;
    osf*)
	echo "ISO8859-1 ISO-8859-1"
	echo "ISO8859-7 ISO-8859-7"
	echo "ISO8859-9 ISO-8859-9"
	echo "cp850 CP850"
	;;
    solaris*)
	echo "646 ASCII"
	echo "ISO8859-1 ISO-8859-1"
	echo "ISO8859-2 ISO-8859-2"
	echo "ISO8859-4 ISO-8859-4"
	echo "ISO8859-5 ISO-8859-5"
	echo "ISO8859-6 ISO-8859-6"
	echo "ISO8859-7 ISO-8859-7"
	echo "ISO8859-8 ISO-8859-8"
	echo "ISO8859-9 ISO-8859-9"
	echo "ISO8859-15 ISO-8859-15"
	echo "koi8-r KOI8-R"
	echo "BIG5 BIG5"
	echo "gb2312 GB2312"
	echo "cns11643 EUC-TW"
	echo "5601 EUC-KR"
	echo "eucJP EUC-JP"
	echo "PCK SJIS"
	echo "TIS620.2533 TIS-620"
	#echo "sun_eu_greek ?" # what is this?
	echo "UTF-8 UTF-8"
	;;
    freebsd*)
	# FreeBSD 3.3 doesn't have nl_langinfo(CODESET); therefore
	# localcharset.c falls back to using the full locale name
	# from the environment variables.
	echo "C ASCII"
	echo "US-ASCII ASCII"
	for l in lt_LN; do
	  echo "$l.ASCII ASCII"
	done
	for l in da_DK de_AT de_CH de_DE en_AU en_CA en_GB en_US es_ES \
                 fi_FI fr_BE fr_CA fr_CH fr_FR is_IS it_CH it_IT lt_LN \
                 nl_BE nl_NL no_NO pt_PT sv_SE; do
	  echo "$l.ISO_8859-1 ISO-8859-1"
	  echo "$l.DIS_8859-15 ISO-8859-15"
	done
	for l in hr_HR hu_HU lt_LN pl_PL sl_SI; do
	  echo "$l.ISO_8859-2 ISO-8859-2"
	done
	for l in ru_RU ru_SU; do
	  echo "$l.KOI8-R KOI8-R"
	  echo "$l.CP866 CP866"
	done
	;;
    beos*)
	# BeOS has a single locale, and it has UTF-8 encoding.
	echo "C UTF-8"
	;;
esac