git-gui: Translate standard encoding names to Tcl ones
This is a essentially a copy of Paul Mackerras encoding support from gitk. I stole the code from gitk commit fd8ccbec4f0161, as Paul has already done all of the hard work setting up this translation table. Signed-off-by: Shawn O. Pearce <spearce@spearce.org>
Shawn O. Pearce committed
Jul 19, 2007 at 01:13 UTC
c4638f662c9ba5f4150ab97dbbf0e540392aad55
3 files changed
+304
-11
lib/blame.tcl
+12
-7
@@ -771,15 +771,20 @@ method _showcommit {cur_w lno} {
771
set enc [string tolower [string range $line 9 end]]
772
}
773
}
774
- set msg [encoding convertfrom $enc [read $fd]]
775
- set msg [string trim $msg]
774
+ set msg [read $fd]
775
close $fd
776
778
- set author_name [encoding convertfrom $enc $author_name]
779
- set committer_name [encoding convertfrom $enc $committer_name]
780
-
781
- set header($cmit,author) $author_name
782
- set header($cmit,committer) $committer_name
777
+ set enc [tcl_encoding $enc]
778
+ if {$enc ne {}} {
779
+ set msg [encoding convertfrom $enc $msg]
780
+ set author_name [encoding convertfrom $enc $author_name]
781
+ set committer_name [encoding convertfrom $enc $committer_name]
782
+ set header($cmit,author) $author_name
783
+ set header($cmit,committer) $committer_name
784
+ set header($cmit,summary) \
785
+ [encoding convertfrom $enc $header($cmit,summary)]
786
+ }
787
+ set msg [string trim $msg]
788
}
789
set header($cmit,message) $msg
790
}
lib/commit.tcl
+16
-4
@@ -37,9 +37,14 @@ You are currently in the middle of a merge that has not been fully completed. Y
37
set enc [string tolower [string range $line 9 end]]
38
}
39
}
40
- set msg [encoding convertfrom $enc [read $fd]]
41
- set msg [string trim $msg]
40
+ set msg [read $fd]
41
close $fd
42
+
43
+ set enc [tcl_encoding $enc]
44
+ if {$enc ne {}} {
45
+ set msg [encoding convertfrom $enc $msg]
46
+ }
47
+ set msg [string trim $msg]
48
} err]} {
49
error_popup "Error loading commit data for amend:\n\n$err"
50
return
@@ -287,11 +292,18 @@ A rescan will be automatically started now.
292
#
293
set msg_p [gitdir COMMIT_EDITMSG]
294
set msg_wt [open $msg_p w]
295
+ fconfigure $msg_wt -translation lf
296
if {[catch {set enc $repo_config(i18n.commitencoding)}]} {
297
set enc utf-8
298
}
293
- fconfigure $msg_wt -encoding binary -translation binary
294
- puts -nonewline $msg_wt [encoding convertto $enc $msg]
299
+ set use_enc [tcl_encoding $enc]
300
+ if {$use_enc ne {}} {
301
+ fconfigure $msg_wt -encoding $use_enc
302
+ } else {
303
+ puts stderr "warning: Tcl does not support encoding '$enc'."
304
+ fconfigure $msg_wt -encoding utf-8
305
+ }
306
+ puts -nonewline $msg_wt $msg
307
close $msg_wt
308
309
# -- Create the commit.
lib/encoding.tcl
new
+276
@@ -0,0 +1,276 @@
1
+# git-gui encoding support
2
+# Copyright (C) 2005 Paul Mackerras <paulus@samba.org>
3
+# (Copied from gitk, commit fd8ccbec4f0161)
4
+
5
+# This list of encoding names and aliases is distilled from
6
+# http://www.iana.org/assignments/character-sets.
7
+# Not all of them are supported by Tcl.
8
+set encoding_aliases {
9
+ { ANSI_X3.4-1968 iso-ir-6 ANSI_X3.4-1986 ISO_646.irv:1991 ASCII
10
+ ISO646-US US-ASCII us IBM367 cp367 csASCII }
11
+ { ISO-10646-UTF-1 csISO10646UTF1 }
12
+ { ISO_646.basic:1983 ref csISO646basic1983 }
13
+ { INVARIANT csINVARIANT }
14
+ { ISO_646.irv:1983 iso-ir-2 irv csISO2IntlRefVersion }
15
+ { BS_4730 iso-ir-4 ISO646-GB gb uk csISO4UnitedKingdom }
16
+ { NATS-SEFI iso-ir-8-1 csNATSSEFI }
17
+ { NATS-SEFI-ADD iso-ir-8-2 csNATSSEFIADD }
18
+ { NATS-DANO iso-ir-9-1 csNATSDANO }
19
+ { NATS-DANO-ADD iso-ir-9-2 csNATSDANOADD }
20
+ { SEN_850200_B iso-ir-10 FI ISO646-FI ISO646-SE se csISO10Swedish }
21
+ { SEN_850200_C iso-ir-11 ISO646-SE2 se2 csISO11SwedishForNames }
22
+ { KS_C_5601-1987 iso-ir-149 KS_C_5601-1989 KSC_5601 korean csKSC56011987 }
23
+ { ISO-2022-KR csISO2022KR }
24
+ { EUC-KR csEUCKR }
25
+ { ISO-2022-JP csISO2022JP }
26
+ { ISO-2022-JP-2 csISO2022JP2 }
27
+ { JIS_C6220-1969-jp JIS_C6220-1969 iso-ir-13 katakana x0201-7
28
+ csISO13JISC6220jp }
29
+ { JIS_C6220-1969-ro iso-ir-14 jp ISO646-JP csISO14JISC6220ro }
30
+ { IT iso-ir-15 ISO646-IT csISO15Italian }
31
+ { PT iso-ir-16 ISO646-PT csISO16Portuguese }
32
+ { ES iso-ir-17 ISO646-ES csISO17Spanish }
33
+ { greek7-old iso-ir-18 csISO18Greek7Old }
34
+ { latin-greek iso-ir-19 csISO19LatinGreek }
35
+ { DIN_66003 iso-ir-21 de ISO646-DE csISO21German }
36
+ { NF_Z_62-010_(1973) iso-ir-25 ISO646-FR1 csISO25French }
37
+ { Latin-greek-1 iso-ir-27 csISO27LatinGreek1 }
38
+ { ISO_5427 iso-ir-37 csISO5427Cyrillic }
39
+ { JIS_C6226-1978 iso-ir-42 csISO42JISC62261978 }
40
+ { BS_viewdata iso-ir-47 csISO47BSViewdata }
41
+ { INIS iso-ir-49 csISO49INIS }
42
+ { INIS-8 iso-ir-50 csISO50INIS8 }
43
+ { INIS-cyrillic iso-ir-51 csISO51INISCyrillic }
44
+ { ISO_5427:1981 iso-ir-54 ISO5427Cyrillic1981 }
45
+ { ISO_5428:1980 iso-ir-55 csISO5428Greek }
46
+ { GB_1988-80 iso-ir-57 cn ISO646-CN csISO57GB1988 }
47
+ { GB_2312-80 iso-ir-58 chinese csISO58GB231280 }
48
+ { NS_4551-1 iso-ir-60 ISO646-NO no csISO60DanishNorwegian
49
+ csISO60Norwegian1 }
50
+ { NS_4551-2 ISO646-NO2 iso-ir-61 no2 csISO61Norwegian2 }
51
+ { NF_Z_62-010 iso-ir-69 ISO646-FR fr csISO69French }
52
+ { videotex-suppl iso-ir-70 csISO70VideotexSupp1 }
53
+ { PT2 iso-ir-84 ISO646-PT2 csISO84Portuguese2 }
54
+ { ES2 iso-ir-85 ISO646-ES2 csISO85Spanish2 }
55
+ { MSZ_7795.3 iso-ir-86 ISO646-HU hu csISO86Hungarian }
56
+ { JIS_C6226-1983 iso-ir-87 x0208 JIS_X0208-1983 csISO87JISX0208 }
57
+ { greek7 iso-ir-88 csISO88Greek7 }
58
+ { ASMO_449 ISO_9036 arabic7 iso-ir-89 csISO89ASMO449 }
59
+ { iso-ir-90 csISO90 }
60
+ { JIS_C6229-1984-a iso-ir-91 jp-ocr-a csISO91JISC62291984a }
61
+ { JIS_C6229-1984-b iso-ir-92 ISO646-JP-OCR-B jp-ocr-b
62
+ csISO92JISC62991984b }
63
+ { JIS_C6229-1984-b-add iso-ir-93 jp-ocr-b-add csISO93JIS62291984badd }
64
+ { JIS_C6229-1984-hand iso-ir-94 jp-ocr-hand csISO94JIS62291984hand }
65
+ { JIS_C6229-1984-hand-add iso-ir-95 jp-ocr-hand-add
66
+ csISO95JIS62291984handadd }
67
+ { JIS_C6229-1984-kana iso-ir-96 csISO96JISC62291984kana }
68
+ { ISO_2033-1983 iso-ir-98 e13b csISO2033 }
69
+ { ANSI_X3.110-1983 iso-ir-99 CSA_T500-1983 NAPLPS csISO99NAPLPS }
70
+ { ISO_8859-1:1987 iso-ir-100 ISO_8859-1 ISO-8859-1 latin1 l1 IBM819
71
+ CP819 csISOLatin1 }
72
+ { ISO_8859-2:1987 iso-ir-101 ISO_8859-2 ISO-8859-2 latin2 l2 csISOLatin2 }
73
+ { T.61-7bit iso-ir-102 csISO102T617bit }
74
+ { T.61-8bit T.61 iso-ir-103 csISO103T618bit }
75
+ { ISO_8859-3:1988 iso-ir-109 ISO_8859-3 ISO-8859-3 latin3 l3 csISOLatin3 }
76
+ { ISO_8859-4:1988 iso-ir-110 ISO_8859-4 ISO-8859-4 latin4 l4 csISOLatin4 }
77
+ { ECMA-cyrillic iso-ir-111 KOI8-E csISO111ECMACyrillic }
78
+ { CSA_Z243.4-1985-1 iso-ir-121 ISO646-CA csa7-1 ca csISO121Canadian1 }
79
+ { CSA_Z243.4-1985-2 iso-ir-122 ISO646-CA2 csa7-2 csISO122Canadian2 }
80
+ { CSA_Z243.4-1985-gr iso-ir-123 csISO123CSAZ24341985gr }
81
+ { ISO_8859-6:1987 iso-ir-127 ISO_8859-6 ISO-8859-6 ECMA-114 ASMO-708
82
+ arabic csISOLatinArabic }
83
+ { ISO_8859-6-E csISO88596E ISO-8859-6-E }
84
+ { ISO_8859-6-I csISO88596I ISO-8859-6-I }
85
+ { ISO_8859-7:1987 iso-ir-126 ISO_8859-7 ISO-8859-7 ELOT_928 ECMA-118
86
+ greek greek8 csISOLatinGreek }
87
+ { T.101-G2 iso-ir-128 csISO128T101G2 }
88
+ { ISO_8859-8:1988 iso-ir-138 ISO_8859-8 ISO-8859-8 hebrew
89
+ csISOLatinHebrew }
90
+ { ISO_8859-8-E csISO88598E ISO-8859-8-E }
91
+ { ISO_8859-8-I csISO88598I ISO-8859-8-I }
92
+ { CSN_369103 iso-ir-139 csISO139CSN369103 }
93
+ { JUS_I.B1.002 iso-ir-141 ISO646-YU js yu csISO141JUSIB1002 }
94
+ { ISO_6937-2-add iso-ir-142 csISOTextComm }
95
+ { IEC_P27-1 iso-ir-143 csISO143IECP271 }
96
+ { ISO_8859-5:1988 iso-ir-144 ISO_8859-5 ISO-8859-5 cyrillic
97
+ csISOLatinCyrillic }
98
+ { JUS_I.B1.003-serb iso-ir-146 serbian csISO146Serbian }
99
+ { JUS_I.B1.003-mac macedonian iso-ir-147 csISO147Macedonian }
100
+ { ISO_8859-9:1989 iso-ir-148 ISO_8859-9 ISO-8859-9 latin5 l5 csISOLatin5 }
101
+ { greek-ccitt iso-ir-150 csISO150 csISO150GreekCCITT }
102
+ { NC_NC00-10:81 cuba iso-ir-151 ISO646-CU csISO151Cuba }
103
+ { ISO_6937-2-25 iso-ir-152 csISO6937Add }
104
+ { GOST_19768-74 ST_SEV_358-88 iso-ir-153 csISO153GOST1976874 }
105
+ { ISO_8859-supp iso-ir-154 latin1-2-5 csISO8859Supp }
106
+ { ISO_10367-box iso-ir-155 csISO10367Box }
107
+ { ISO-8859-10 iso-ir-157 l6 ISO_8859-10:1992 csISOLatin6 latin6 }
108
+ { latin-lap lap iso-ir-158 csISO158Lap }
109
+ { JIS_X0212-1990 x0212 iso-ir-159 csISO159JISX02121990 }
110
+ { DS_2089 DS2089 ISO646-DK dk csISO646Danish }
111
+ { us-dk csUSDK }
112
+ { dk-us csDKUS }
113
+ { JIS_X0201 X0201 csHalfWidthKatakana }
114
+ { KSC5636 ISO646-KR csKSC5636 }
115
+ { ISO-10646-UCS-2 csUnicode }
116
+ { ISO-10646-UCS-4 csUCS4 }
117
+ { DEC-MCS dec csDECMCS }
118
+ { hp-roman8 roman8 r8 csHPRoman8 }
119
+ { macintosh mac csMacintosh }
120
+ { IBM037 cp037 ebcdic-cp-us ebcdic-cp-ca ebcdic-cp-wt ebcdic-cp-nl
121
+ csIBM037 }
122
+ { IBM038 EBCDIC-INT cp038 csIBM038 }
123
+ { IBM273 CP273 csIBM273 }
124
+ { IBM274 EBCDIC-BE CP274 csIBM274 }
125
+ { IBM275 EBCDIC-BR cp275 csIBM275 }
126
+ { IBM277 EBCDIC-CP-DK EBCDIC-CP-NO csIBM277 }
127
+ { IBM278 CP278 ebcdic-cp-fi ebcdic-cp-se csIBM278 }
128
+ { IBM280 CP280 ebcdic-cp-it csIBM280 }
129
+ { IBM281 EBCDIC-JP-E cp281 csIBM281 }
130
+ { IBM284 CP284 ebcdic-cp-es csIBM284 }
131
+ { IBM285 CP285 ebcdic-cp-gb csIBM285 }
132
+ { IBM290 cp290 EBCDIC-JP-kana csIBM290 }
133
+ { IBM297 cp297 ebcdic-cp-fr csIBM297 }
134
+ { IBM420 cp420 ebcdic-cp-ar1 csIBM420 }
135
+ { IBM423 cp423 ebcdic-cp-gr csIBM423 }
136
+ { IBM424 cp424 ebcdic-cp-he csIBM424 }
137
+ { IBM437 cp437 437 csPC8CodePage437 }
138
+ { IBM500 CP500 ebcdic-cp-be ebcdic-cp-ch csIBM500 }
139
+ { IBM775 cp775 csPC775Baltic }
140
+ { IBM850 cp850 850 csPC850Multilingual }
141
+ { IBM851 cp851 851 csIBM851 }
142
+ { IBM852 cp852 852 csPCp852 }
143
+ { IBM855 cp855 855 csIBM855 }
144
+ { IBM857 cp857 857 csIBM857 }
145
+ { IBM860 cp860 860 csIBM860 }
146
+ { IBM861 cp861 861 cp-is csIBM861 }
147
+ { IBM862 cp862 862 csPC862LatinHebrew }
148
+ { IBM863 cp863 863 csIBM863 }
149
+ { IBM864 cp864 csIBM864 }
150
+ { IBM865 cp865 865 csIBM865 }
151
+ { IBM866 cp866 866 csIBM866 }
152
+ { IBM868 CP868 cp-ar csIBM868 }
153
+ { IBM869 cp869 869 cp-gr csIBM869 }
154
+ { IBM870 CP870 ebcdic-cp-roece ebcdic-cp-yu csIBM870 }
155
+ { IBM871 CP871 ebcdic-cp-is csIBM871 }
156
+ { IBM880 cp880 EBCDIC-Cyrillic csIBM880 }
157
+ { IBM891 cp891 csIBM891 }
158
+ { IBM903 cp903 csIBM903 }
159
+ { IBM904 cp904 904 csIBBM904 }
160
+ { IBM905 CP905 ebcdic-cp-tr csIBM905 }
161
+ { IBM918 CP918 ebcdic-cp-ar2 csIBM918 }
162
+ { IBM1026 CP1026 csIBM1026 }
163
+ { EBCDIC-AT-DE csIBMEBCDICATDE }
164
+ { EBCDIC-AT-DE-A csEBCDICATDEA }
165
+ { EBCDIC-CA-FR csEBCDICCAFR }
166
+ { EBCDIC-DK-NO csEBCDICDKNO }
167
+ { EBCDIC-DK-NO-A csEBCDICDKNOA }
168
+ { EBCDIC-FI-SE csEBCDICFISE }
169
+ { EBCDIC-FI-SE-A csEBCDICFISEA }
170
+ { EBCDIC-FR csEBCDICFR }
171
+ { EBCDIC-IT csEBCDICIT }
172
+ { EBCDIC-PT csEBCDICPT }
173
+ { EBCDIC-ES csEBCDICES }
174
+ { EBCDIC-ES-A csEBCDICESA }
175
+ { EBCDIC-ES-S csEBCDICESS }
176
+ { EBCDIC-UK csEBCDICUK }
177
+ { EBCDIC-US csEBCDICUS }
178
+ { UNKNOWN-8BIT csUnknown8BiT }
179
+ { MNEMONIC csMnemonic }
180
+ { MNEM csMnem }
181
+ { VISCII csVISCII }
182
+ { VIQR csVIQR }
183
+ { KOI8-R csKOI8R }
184
+ { IBM00858 CCSID00858 CP00858 PC-Multilingual-850+euro }
185
+ { IBM00924 CCSID00924 CP00924 ebcdic-Latin9--euro }
186
+ { IBM01140 CCSID01140 CP01140 ebcdic-us-37+euro }
187
+ { IBM01141 CCSID01141 CP01141 ebcdic-de-273+euro }
188
+ { IBM01142 CCSID01142 CP01142 ebcdic-dk-277+euro ebcdic-no-277+euro }
189
+ { IBM01143 CCSID01143 CP01143 ebcdic-fi-278+euro ebcdic-se-278+euro }
190
+ { IBM01144 CCSID01144 CP01144 ebcdic-it-280+euro }
191
+ { IBM01145 CCSID01145 CP01145 ebcdic-es-284+euro }
192
+ { IBM01146 CCSID01146 CP01146 ebcdic-gb-285+euro }
193
+ { IBM01147 CCSID01147 CP01147 ebcdic-fr-297+euro }
194
+ { IBM01148 CCSID01148 CP01148 ebcdic-international-500+euro }
195
+ { IBM01149 CCSID01149 CP01149 ebcdic-is-871+euro }
196
+ { IBM1047 IBM-1047 }
197
+ { PTCP154 csPTCP154 PT154 CP154 Cyrillic-Asian }
198
+ { Amiga-1251 Ami1251 Amiga1251 Ami-1251 }
199
+ { UNICODE-1-1 csUnicode11 }
200
+ { CESU-8 csCESU-8 }
201
+ { BOCU-1 csBOCU-1 }
202
+ { UNICODE-1-1-UTF-7 csUnicode11UTF7 }
203
+ { ISO-8859-14 iso-ir-199 ISO_8859-14:1998 ISO_8859-14 latin8 iso-celtic
204
+ l8 }
205
+ { ISO-8859-15 ISO_8859-15 Latin-9 }
206
+ { ISO-8859-16 iso-ir-226 ISO_8859-16:2001 ISO_8859-16 latin10 l10 }
207
+ { GBK CP936 MS936 windows-936 }
208
+ { JIS_Encoding csJISEncoding }
209
+ { Shift_JIS MS_Kanji csShiftJIS }
210
+ { Extended_UNIX_Code_Packed_Format_for_Japanese csEUCPkdFmtJapanese
211
+ EUC-JP }
212
+ { Extended_UNIX_Code_Fixed_Width_for_Japanese csEUCFixWidJapanese }
213
+ { ISO-10646-UCS-Basic csUnicodeASCII }
214
+ { ISO-10646-Unicode-Latin1 csUnicodeLatin1 ISO-10646 }
215
+ { ISO-Unicode-IBM-1261 csUnicodeIBM1261 }
216
+ { ISO-Unicode-IBM-1268 csUnicodeIBM1268 }
217
+ { ISO-Unicode-IBM-1276 csUnicodeIBM1276 }
218
+ { ISO-Unicode-IBM-1264 csUnicodeIBM1264 }
219
+ { ISO-Unicode-IBM-1265 csUnicodeIBM1265 }
220
+ { ISO-8859-1-Windows-3.0-Latin-1 csWindows30Latin1 }
221
+ { ISO-8859-1-Windows-3.1-Latin-1 csWindows31Latin1 }
222
+ { ISO-8859-2-Windows-Latin-2 csWindows31Latin2 }
223
+ { ISO-8859-9-Windows-Latin-5 csWindows31Latin5 }
224
+ { Adobe-Standard-Encoding csAdobeStandardEncoding }
225
+ { Ventura-US csVenturaUS }
226
+ { Ventura-International csVenturaInternational }
227
+ { PC8-Danish-Norwegian csPC8DanishNorwegian }
228
+ { PC8-Turkish csPC8Turkish }
229
+ { IBM-Symbols csIBMSymbols }
230
+ { IBM-Thai csIBMThai }
231
+ { HP-Legal csHPLegal }
232
+ { HP-Pi-font csHPPiFont }
233
+ { HP-Math8 csHPMath8 }
234
+ { Adobe-Symbol-Encoding csHPPSMath }
235
+ { HP-DeskTop csHPDesktop }
236
+ { Ventura-Math csVenturaMath }
237
+ { Microsoft-Publishing csMicrosoftPublishing }
238
+ { Windows-31J csWindows31J }
239
+ { GB2312 csGB2312 }
240
+ { Big5 csBig5 }
241
+}
242
+
243
+proc tcl_encoding {enc} {
244
+ global encoding_aliases
245
+ set names [encoding names]
246
+ set lcnames [string tolower $names]
247
+ set enc [string tolower $enc]
248
+ set i [lsearch -exact $lcnames $enc]
249
+ if {$i < 0} {
250
+ # look for "isonnn" instead of "iso-nnn" or "iso_nnn"
251
+ if {[regsub {^iso[-_]} $enc iso encx]} {
252
+ set i [lsearch -exact $lcnames $encx]
253
+ }
254
+ }
255
+ if {$i < 0} {
256
+ foreach l $encoding_aliases {
257
+ set ll [string tolower $l]
258
+ if {[lsearch -exact $ll $enc] < 0} continue
259
+ # look through the aliases for one that tcl knows about
260
+ foreach e $ll {
261
+ set i [lsearch -exact $lcnames $e]
262
+ if {$i < 0} {
263
+ if {[regsub {^iso[-_]} $e iso ex]} {
264
+ set i [lsearch -exact $lcnames $ex]
265
+ }
266
+ }
267
+ if {$i >= 0} break
268
+ }
269
+ break
270
+ }
271
+ }
272
+ if {$i >= 0} {
273
+ return [lindex $names $i]
274
+ }
275
+ return {}
276
+}