« back to all changes in this revision
Viewing changes to src/Utils/Encoding.vala
- browse files at revision 48.1.1
- compare with another revision
- download diff
- download tarball
- view history from revision 48.1.1
- Committer: Anthony Huben
- Date: 2014-08-28 17:41:35 UTC
- mto: This revision was merged to the branch mainline in revision 49.
- Revision ID: harp37@gmail.com-20140828174135-c21gx6wphxh1amex
Implement Encoding.
- files added:
- resources
added
removed
src/Utils/Encoding.vala
1
// -*- Mode: vala; indent-tabs-mode: nil; tab-width: 4 -*-
2
/***
3
The MIT License (MIT)
4
5
Copyright (c) 2014 Anthony Huben
6
7
Permission is hereby granted, free of charge, to any person obtaining a copy
8
of this software and associated documentation files (the "Software"), to deal
9
in the Software without restriction, including without limitation the rights
10
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
11
copies of the Software, and to permit persons to whom the Software is
12
furnished to do so, subject to the following conditions:
13
14
The above copyright notice and this permission notice shall be included in all
15
copies or substantial portions of the Software.
16
17
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
18
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
19
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
20
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
21
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
22
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
23
SOFTWARE.
24
25
-> Taken from Scratch (https://launchpad.net/scratch/)
26
***/
27
28
namespace Writer.Utils {
29
30
public enum EncodingType {
31
32
ISO_8859_1,
33
ISO_8859_2,
34
ISO_8859_3,
35
ISO_8859_4,
36
ISO_8859_5,
37
ISO_8859_6,
38
ISO_8859_7,
39
ISO_8859_8,
40
ISO_8859_9,
41
ISO_8859_10,
42
ISO_8859_13,
43
ISO_8859_14,
44
ISO_8859_15,
45
ISO_8859_16,
46
47
UTF_7,
48
UTF_16,
49
UTF_16_BE,
50
UTF_16_LE,
51
UTF_32,
52
UCS_2,
53
UCS_4,
54
55
ARMSCII_8,
56
BIG5,
57
BIG5_HKSCS,
58
CP_866,
59
60
EUC_JP,
61
EUC_JP_MS,
62
CP932,
63
EUC_KR,
64
EUC_TW,
65
66
GB18030,
67
GB2312,
68
GBK,
69
GEOSTD8,
70
71
IBM_850,
72
IBM_852,
73
IBM_855,
74
IBM_857,
75
IBM_862,
76
IBM_864,
77
78
ISO_2022_JP,
79
ISO_2022_KR,
80
ISO_IR_111,
81
JOHAB,
82
KOI8_R,
83
KOI8__R,
84
KOI8_U,
85
86
SHIFT_JIS,
87
TCVN,
88
TIS_620,
89
UHC,
90
VISCII,
91
92
WINDOWS_1250,
93
WINDOWS_1251,
94
WINDOWS_1252,
95
WINDOWS_1253,
96
WINDOWS_1254,
97
WINDOWS_1255,
98
WINDOWS_1256,
99
WINDOWS_1257,
100
WINDOWS_1258,
101
102
LAST,
103
104
UTF_8,
105
UNKNOWN
106
107
}
108
109
public struct Encoding {
110
public EncodingType type;
111
public string? encoding;
112
public string? name;
113
}
114
115
public static const Encoding[] encodings = {
116
117
{ EncodingType.ISO_8859_1,
118
"ISO-8859-1", "Western" },
119
{ EncodingType.ISO_8859_2,
120
"ISO-8859-2", "Central European" },
121
{ EncodingType.ISO_8859_3,
122
"ISO-8859-3", "South European" },
123
{ EncodingType.ISO_8859_4,
124
"ISO-8859-4", "Baltic" },
125
{ EncodingType.ISO_8859_5,
126
"ISO-8859-5", "Cyrillic" },
127
{ EncodingType.ISO_8859_6,
128
"ISO-8859-6", "Arabic" },
129
{ EncodingType.ISO_8859_7,
130
"ISO-8859-7", "Greek" },
131
{ EncodingType.ISO_8859_8,
132
"ISO-8859-8", "Hebrew Visual" },
133
{ EncodingType.ISO_8859_9,
134
"ISO-8859-9", "Turkish" },
135
{ EncodingType.ISO_8859_10,
136
"ISO-8859-10", "Nordic" },
137
{ EncodingType.ISO_8859_13,
138
"ISO-8859-13", "Baltic" },
139
{ EncodingType.ISO_8859_14,
140
"ISO-8859-14", "Celtic" },
141
{ EncodingType.ISO_8859_15,
142
"ISO-8859-15", "Western" },
143
{ EncodingType.ISO_8859_16,
144
"ISO-8859-16", "Romanian" },
145
146
{ EncodingType.UTF_7,
147
"UTF-7", "Unicode" },
148
{ EncodingType.UTF_16,
149
"UTF-16", "Unicode" },
150
{ EncodingType.UTF_16_BE,
151
"UTF-16BE", "Unicode" },
152
{ EncodingType.UTF_16_LE,
153
"UTF-16LE", "Unicode" },
154
{ EncodingType.UTF_32,
155
"UTF-32", "Unicode" },
156
{ EncodingType.UCS_2,
157
"UCS-2", "Unicode" },
158
{ EncodingType.UCS_4,
159
"UCS-4", "Unicode" },
160
161
{ EncodingType.ARMSCII_8,
162
"ARMSCII-8", "Armenian" },
163
{ EncodingType.BIG5,
164
"BIG5", "Chinese Traditional" },
165
{ EncodingType.BIG5_HKSCS,
166
"BIG5-HKSCS", "Chinese Traditional" },
167
{ EncodingType.CP_866,
168
"CP866", "Cyrillic/Russian" },
169
170
{ EncodingType.EUC_JP,
171
"EUC-JP", "Japanese" },
172
{ EncodingType.EUC_JP_MS,
173
"EUC-JP-MS", "Japanese" },
174
{ EncodingType.CP932,
175
"CP932", "Japanese" },
176
177
{ EncodingType.EUC_KR,
178
"EUC-KR", "Korean" },
179
{ EncodingType.EUC_TW,
180
"EUC-TW", "Chinese Traditional" },
181
182
{ EncodingType.GB18030,
183
"GB18030", "Chinese Simplified" },
184
{ EncodingType.GB2312,
185
"GB2312", "Chinese Simplified" },
186
{ EncodingType.GBK,
187
"GBK", "Chinese Simplified" },
188
{ EncodingType.GEOSTD8,
189
"GEORGIAN-ACADEMY", "Georgian" }, /* FIXME GEOSTD8 ? */
190
191
{ EncodingType.IBM_850,
192
"IBM850", "Western" },
193
{ EncodingType.IBM_852,
194
"IBM852", "Central European" },
195
{ EncodingType.IBM_855,
196
"IBM855", "Cyrillic" },
197
{ EncodingType.IBM_857,
198
"IBM857", "Turkish" },
199
{ EncodingType.IBM_862,
200
"IBM862", "Hebrew" },
201
{ EncodingType.IBM_864,
202
"IBM864", "Arabic" },
203
204
{ EncodingType.ISO_2022_JP,
205
"ISO-2022-JP", "Japanese" },
206
{ EncodingType.ISO_2022_KR,
207
"ISO-2022-KR", "Korean" },
208
{ EncodingType.ISO_IR_111,
209
"ISO-IR-111", "Cyrillic" },
210
{ EncodingType.JOHAB,
211
"JOHAB", "Korean" },
212
{ EncodingType.KOI8_R,
213
"KOI8R", "Cyrillic" },
214
{ EncodingType.KOI8__R,
215
"KOI8-R", "Cyrillic" },
216
{ EncodingType.KOI8_U,
217
"KOI8U", "Cyrillic/Ukrainian" },
218
219
{ EncodingType.SHIFT_JIS,
220
"SHIFT_JIS", "Japanese" },
221
{ EncodingType.TCVN,
222
"TCVN", "Vietnamese" },
223
{ EncodingType.TIS_620,
224
"TIS-620", "Thai" },
225
{ EncodingType.UHC,
226
"UHC", "Korean" },
227
{ EncodingType.VISCII,
228
"VISCII", "Vietnamese" },
229
230
{ EncodingType.WINDOWS_1250,
231
"WINDOWS-1250", "Central European" },
232
{ EncodingType.WINDOWS_1251,
233
"WINDOWS-1251", "Cyrillic" },
234
{ EncodingType.WINDOWS_1252,
235
"WINDOWS-1252", "Western" },
236
{ EncodingType.WINDOWS_1253,
237
"WINDOWS-1253", "Greek" },
238
{ EncodingType.WINDOWS_1254,
239
"WINDOWS-1254", "Turkish" },
240
{ EncodingType.WINDOWS_1255,
241
"WINDOWS-1255", "Hebrew" },
242
{ EncodingType.WINDOWS_1256,
243
"WINDOWS-1256", "Arabic" },
244
{ EncodingType.WINDOWS_1257,
245
"WINDOWS-1257", "Baltic" },
246
{ EncodingType.WINDOWS_1258,
247
"WINDOWS-1258", "Vietnamese" }
248
};
249
250
private static bool test (string text, string charset) {
251
bool valid = false;
252
253
try {
254
string convert;
255
convert = GLib.convert (text, -1, "UTF-8", charset);
256
valid = true;
257
}
258
catch (Error e) {
259
debug (e.message);
260
}
261
return valid;
262
}
263
264
public static string get_charset (string path) {
265
// Get correct encoding via chardect.py script
266
267
const string FALLBACK_CHARSET = "ISO-8859-1";
268
string script = Constants.SCRIPTDIR + "/chardetect.py";
269
string command = "python " + script + " \"" + path.replace ("\\ ", " ") + "\"";
270
string? charset = null;
271
272
try {
273
GLib.Process.spawn_command_line_sync (command, out charset);
274
} catch (SpawnError e) {
275
warning ("Could not execute \"%s\": %s", script, e.message);
276
}
277
if ( charset == null || strcmp (charset, "error") != 0) {
278
warning ("Could not automatically detect encoding, assuming %s", FALLBACK_CHARSET);
279
charset = FALLBACK_CHARSET; //TODO: prompt the user to meddle with encoding manually, until satisfied
280
} else {
281
debug ("Detected encoding of file \"%s\" to be \"%s\"", path, charset);
282
}
283
return charset;
284
}
285
286
public string? file_content_to_utf8 (File file, string content, string mode = "r" /* it means read or write */) {
287
288
string? encoding = null;
289
string? encoded_content = null;
290
291
encoding = get_charset (file.get_path ());
292
293
try {
294
InputStream @is = file.read ();
295
CharsetConverter iconverter = new CharsetConverter ("utf-8", encoding.down ());
296
ConverterInputStream @converted = new ConverterInputStream (@is, iconverter);
297
DataInputStream dis = new DataInputStream (@converted);
298
string line = dis.read_line ();
299
string str = line;
300
while ((line = dis.read_line (null)) != null) {
301
str += line + "\n";
302
}
303
encoded_content = str;
304
} catch (GLib.ConvertError ce) {
305
warning (ce.message);
306
} catch (IOError e) {
307
warning (e.message);
308
} catch (Error e) {
309
warning (e.message);
310
}
311
312
return encoded_content;
313
314
}
315
316
}
b'\\ No newline at end of file'
Loggerhead is a web-based interface for Breezy
Version: 2.0.1