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
|
# KDE Config file
#
# This file defines where to find conversion maps for specific encodings.
# The directory below gives the dir where the posix charmaps are located.
#
[general]
i18ndir=/usr/share/i18n/charmaps
# defines some different names for codecs that are built into Qt.
[builtin]
iso-ir-111=koi8-r
koi8-ru=koi8-u
koi8r=koi8-r
koi8u=koi8-u
koi unified=koi8-r
us-ascii=iso 8859-1
usascii=iso 8859-1
x-utf-8=utf8
x-utf-7=utf7
ucs2=utf16
iso10646-1=ISO-10646-UCS-2
gbk-0=gbk
gb2312=gbk
gb2312.1980-0=gbk
euc-kr=euckr
x-euc-kr=euckr
euc-jp=eucjp
x-euc-jp=eucjp
jisx0201.1976-0=eucjp
jisx0208.1983-0=eucjp
jisx0208.1990-0=eucjp
jisx0208.1997-0=eucjp
jisx0212.1990-0=eucjp
jisx0213.2000-1=eucjp
jisx0213.2000-2=eucjp
shift_jis=sjis
shift-jis=sjis
x-sjis=sjis
iso-2022-jp=jis7
windows1250=cp 1250
windows1251=cp 1251
windows1252=cp 1252
windows1253=cp 1253
windows1254=cp 1254
windows1255=cp 1255
windows1256=cp 1256
windows1257=cp 1257
windows-1250=cp 1250
windows-1251=cp 1251
windows-1252=cp 1252
windows-1253=cp 1253
windows-1254=cp 1254
windows-1255=cp 1255
windows-1256=cp 1256
windows-1257=cp 1257
x-windows-1250=cp 1250
x-windows-1251=cp 1251
x-windows-1252=cp 1252
x-windows-1253=cp 1253
x-windows-1254=cp 1254
x-windows-1255=cp 1255
x-windows-1256=cp 1256
x-windows-1257=cp 1257
cp-1250=cp 1250
cp-1251=cp 1251
cp-1252=cp 1252
cp-1253=cp 1253
cp-1254=cp 1254
cp-1255=cp 1255
cp-1256=cp 1256
cp-1257=cp 1257
x-cp-1250=cp 1250
x-cp-1251=cp 1251
x-cp-1252=cp 1252
x-cp-1253=cp 1253
x-cp-1254=cp 1254
x-cp-1255=cp 1255
x-cp-1256=cp 1256
x-cp-1257=cp 1257
tis620=iso 8859-11
tis-620=iso 8859-11
windows-874=iso 8859-11
windows874=iso 8859-11
x-windows-874=iso 8859-11
cp874=iso 8859-11
cp-874=iso 8859-11
x-cp-874=iso 8859-11
ksc5601.1987-0=euckr
ks_c_5601-1987=euckr
iso-8859-1=iso 8859-1
iso-8859-2=iso 8859-2
iso-8859-3=iso 8859-3
iso-8859-4=iso 8859-4
iso-8859-5=iso 8859-5
iso-8859-6=iso 8859-6
iso-8859-7=iso 8859-7
iso-8859-8=iso 8859-8
iso-8859-9=iso 8859-9
iso-8859-10=iso 8859-10
iso-8859-11=iso 8859-11
iso-8859-12=iso 8859-12
iso-8859-13=iso 8859-13
iso-8859-14=iso 8859-14
iso-8859-15=iso 8859-15
tscii=tscii
paratype-154=pt 154
pt-154=pt 154
# some different names for the encodings defined in the charmaps files.
# even though the charmap file names are all uppercase, the names are all lowercase here.
[aliases]
cp852=ibm852
# some last resort hints in case the charmap file couldn't be found. This gives at least a partial conversion
# and helps making things readable.
#the name used as input here is already converted to the more canonical name as defined in the [aliases] group.
[conversionHints]
cp1250=iso-8859-2
koi8-r=iso-8859-5
koi8-u=koi8-r
# this list gives the charsets that can be used to display a file given in a certain encoding.
# the list should be in order of preference
# left side is the name returned by the codec used, right side the name of the charset as
# used in kcharsets.cpp
# 'unicode' will always be chosen as last resort, so it only needs to be added to the list,
# if it should get a higher priority
[charsetsForEncoding]
koi8-r=koi8-r,cp 1251,koi8-u,iso-8859-5
koi8-u=koi8-u,cp 1251,iso-8859-5,koi8-r
iso 8859-1=iso8859-1,iso8859-15
iso 8859-2=iso8859-2,unicode,iso8859-1
iso 8859-3=iso8859-3,unicode,iso8859-1
iso 8859-4=iso8859-4,unicode,iso8859-1
iso 8859-5=iso8859-5,koi8-u,koi8-r
iso 8859-6=unicode,iso8859-6
iso 8859-7=iso8859-7
iso 8859-8=iso8859-8,unicode
iso 8859-8-i=iso8859-8
iso 8859-9=iso8859-9,unicode,iso8859-1
iso 8859-11=iso8859-11
iso 8859-13=iso8859-13,unicode,iso8859-1
iso 8859-15=iso8859-15,unicode,iso8859-1
utf8=unicode,iso8859-1
utf16=unicode,iso8859-1
ISO-10646-UCS-2=unicode,iso8859-1
cp 1250=iso8859-2
cp 1251=cp 1251,koi8-u,koi8-r,iso8859-5
cp 1252=iso8859-1
cp 1253=iso8859-7
cp 1254=iso8859-9
cp 1255=iso8859-8
cp 1256=unicode,iso8859-6
cp 1257=iso8859-13
ibm852=unicode,iso-8859-2
tis620=iso8859-11,unicode
eucjp=eucjp,unicode,iso8859-1
sjis=eucjp,unicode,iso8859-1
jis7=eucjp,unicode,iso8859-1
big5=big5,unicode,iso8859-1
gbk=gb2312.1980-0,gbk-0,unicode,iso8859-1
gb2312=gb2312.1980-0,unicode,iso8859-1
euckr=euckr,unicode,iso8859-1
tscii=tscii
pt 154=pt 154,cp 1251,koi8-u,koi8-r,iso8859-5
[LanguageForEncoding]
# keep this in sync with the stuff in kcharsets.cpp
# 0 other
# 1 Arabic
# 2 Baltic
# 3 Central European
# 4 Chinese Simplified
# 5 Chinese Traditional
# 6 Cyrillic
# 7 Greek
# 8 Hebrew
# 9 Japanese
# 10 Korean
# 11 Thai
# 12 Turkish
# 13 Western European
# 14 Tamil
# 15 Unicode
iso 8859-1=13
iso 8859-15=13
cp 1252=13
iso 8859-2=3
iso 8859-3=3
iso 8859-4=2
iso 8859-13=2
cp 1250=3
cp 1254=12
cp 1257=2
ibm852=3
koi8-r=6
iso 8859-5=6
cp 1251=6
koi8-u=6
pt 154=6
big5=5
gbk=4
gb2312=4
euckr=10
sjis=9
jis7=9
eucjp=9
iso 8859-7=7
cp 1253=7
iso 8859-6=1
cp 1256=1
iso 8859-8=8
iso 8859-8-i=8
cp 1255=8
iso 8859-9=12
tis620=11
iso 8859-11=11
utf8=15
utf16=15
utf7=15
ucs2=15
|
