scylla 0.1.0 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +0 -1
- data/Gemfile.lock +0 -10
- data/README.rdoc +22 -0
- data/VERSION +1 -1
- data/bin/scylla +13 -0
- data/lib/scylla/classifier.rb +2 -2
- data/lib/scylla/generator.rb +1 -1
- data/lib/scylla/lms/13375P33K.lm +400 -0
- data/lib/scylla/lms/afrikaans.lm +400 -0
- data/lib/scylla/lms/arabic.lm +400 -0
- data/lib/scylla/lms/bulgarian.lm +400 -0
- data/lib/scylla/lms/catalan.lm +400 -0
- data/lib/scylla/lms/chinese.lm +400 -0
- data/lib/scylla/lms/danish.lm +400 -0
- data/lib/scylla/lms/english.lm +400 -0
- data/lib/scylla/lms/esperanto.lm +400 -0
- data/lib/scylla/lms/finnish.lm +400 -0
- data/lib/scylla/lms/french.lm +400 -0
- data/lib/scylla/lms/german.lm +400 -0
- data/lib/scylla/lms/greek-iso8859-7.lm +400 -0
- data/lib/scylla/lms/hebrew.lm +400 -0
- data/lib/scylla/lms/hindi.lm +400 -0
- data/lib/scylla/lms/hungarian.lm +400 -0
- data/lib/scylla/lms/icelandic.lm +400 -0
- data/lib/scylla/lms/indonesian.lm +400 -0
- data/lib/scylla/lms/irish.lm +400 -0
- data/lib/scylla/lms/italian.lm +400 -0
- data/lib/scylla/lms/japanese.lm +400 -0
- data/lib/scylla/lms/kannada.lm +400 -0
- data/lib/scylla/lms/korean.lm +400 -0
- data/lib/scylla/lms/latin.lm +400 -0
- data/lib/scylla/lms/malay.lm +400 -0
- data/lib/scylla/lms/marathi.lm +400 -0
- data/lib/scylla/lms/mingo.lm +400 -0
- data/lib/scylla/lms/nepali.lm +400 -0
- data/lib/scylla/lms/norwegian.lm +400 -0
- data/lib/scylla/lms/polish.lm +400 -0
- data/lib/scylla/lms/portuguese.lm +400 -0
- data/lib/scylla/lms/quechua.lm +400 -0
- data/lib/scylla/lms/romanian.lm +400 -0
- data/lib/scylla/lms/rumantsch.lm +400 -0
- data/lib/scylla/lms/russian.lm +400 -0
- data/lib/scylla/lms/sanskrit.lm +400 -0
- data/lib/scylla/lms/scots_gaelic.lm +400 -0
- data/lib/scylla/lms/serbian-ascii.lm +400 -0
- data/lib/scylla/lms/slovak-ascii.lm +400 -0
- data/lib/scylla/lms/slovenian-ascii.lm +400 -0
- data/lib/scylla/lms/spanish.lm +400 -0
- data/lib/scylla/lms/swahili.lm +400 -0
- data/lib/scylla/lms/swedish.lm +400 -0
- data/lib/scylla/lms/tagalog.lm +400 -0
- data/lib/scylla/lms/tamil.lm +400 -0
- data/lib/scylla/lms/thai.lm +400 -0
- data/lib/scylla/lms/turkish.lm +400 -0
- data/lib/scylla/lms/ukrainian-koi8_u.lm +400 -0
- data/lib/scylla/lms/vietnamese.lm +400 -0
- data/lib/scylla/lms/welsh.lm +400 -0
- data/lib/scylla/lms/yiddish-utf.lm +400 -0
- data/lib/scylla/loader.rb +8 -1
- data/scylla-0.1.0.gem +0 -0
- data/scylla.gemspec +69 -3
- data/source_texts/kannada.txt +283 -0
- data/test/classifier_test.rb +7 -0
- data/test/fixtures/lms/13375p33k.lm +400 -0
- data/test/fixtures/lms/danish.lm +400 -0
- data/test/fixtures/lms/english.lm +400 -0
- data/test/fixtures/lms/french.lm +400 -0
- data/test/fixtures/lms/german.lm +400 -0
- data/test/fixtures/lms/japanese.lm +400 -0
- data/test/fixtures/lms/kannada.lm +400 -0
- data/test/fixtures/lms/spanish.lm +400 -0
- data/test/fixtures/source_texts/13375P33K.txt +199 -0
- data/test/fixtures/source_texts/japanese.txt +199 -0
- data/test/fixtures/source_texts/kannada.txt +283 -0
- data/test/generator_test.rb +10 -7
- data/test/helper.rb +5 -6
- data/test/loader_test.rb +1 -0
- data/test/scylla_test.rb +1 -0
- metadata +78 -14
- data/source_texts/armenian.txt +0 -86
@@ -0,0 +1,400 @@
|
|
1
|
+
� 21655
|
2
|
+
� 17227
|
3
|
+
� 16413
|
4
|
+
_ 5882
|
5
|
+
� 5693
|
6
|
+
� 5242
|
7
|
+
_� 2814
|
8
|
+
_� 2711
|
9
|
+
� 2049
|
10
|
+
್ 2046
|
11
|
+
�� 2046
|
12
|
+
�� 1941
|
13
|
+
�� 1941
|
14
|
+
್� 1939
|
15
|
+
��� 1939
|
16
|
+
್� 1939
|
17
|
+
��� 1939
|
18
|
+
�� 1450
|
19
|
+
� 1450
|
20
|
+
ಿ 1450
|
21
|
+
� 1382
|
22
|
+
�� 1376
|
23
|
+
ರ 1376
|
24
|
+
�� 1265
|
25
|
+
�� 1265
|
26
|
+
� 1265
|
27
|
+
ಾ 1265
|
28
|
+
ರ� 1265
|
29
|
+
��� 1265
|
30
|
+
ಾ� 1226
|
31
|
+
��� 1226
|
32
|
+
�� 1226
|
33
|
+
��� 1225
|
34
|
+
�� 1225
|
35
|
+
ಾ� 1225
|
36
|
+
� 1213
|
37
|
+
�� 1213
|
38
|
+
ು 1213
|
39
|
+
� 1119
|
40
|
+
� 1095
|
41
|
+
ಿ� 1070
|
42
|
+
��� 1070
|
43
|
+
�� 1070
|
44
|
+
��� 1067
|
45
|
+
ಿ� 1067
|
46
|
+
�� 1067
|
47
|
+
ದ 1062
|
48
|
+
�� 1062
|
49
|
+
ನ 1052
|
50
|
+
�� 1052
|
51
|
+
�� 995
|
52
|
+
ನ� 968
|
53
|
+
��� 968
|
54
|
+
�� 906
|
55
|
+
ತ 906
|
56
|
+
� 906
|
57
|
+
� 879
|
58
|
+
�� 852
|
59
|
+
ತ� 852
|
60
|
+
��� 852
|
61
|
+
� 832
|
62
|
+
�� 832
|
63
|
+
ಕ 832
|
64
|
+
�� 827
|
65
|
+
�� 812
|
66
|
+
ಲ 812
|
67
|
+
ೆ 804
|
68
|
+
�� 804
|
69
|
+
� 796
|
70
|
+
ಗ 796
|
71
|
+
�� 796
|
72
|
+
��� 791
|
73
|
+
ದ� 791
|
74
|
+
�� 778
|
75
|
+
��� 777
|
76
|
+
ಲ� 777
|
77
|
+
�� 763
|
78
|
+
ಗ� 763
|
79
|
+
��� 763
|
80
|
+
ಕ� 762
|
81
|
+
�� 762
|
82
|
+
��� 762
|
83
|
+
ರ� 705
|
84
|
+
��� 705
|
85
|
+
�� 705
|
86
|
+
ವ 690
|
87
|
+
� 690
|
88
|
+
�� 690
|
89
|
+
� 690
|
90
|
+
� 654
|
91
|
+
ಯ 647
|
92
|
+
�� 647
|
93
|
+
��� 630
|
94
|
+
ವ� 630
|
95
|
+
�� 630
|
96
|
+
� 618
|
97
|
+
ಸ 618
|
98
|
+
�� 618
|
99
|
+
��� 610
|
100
|
+
�� 610
|
101
|
+
ಸ� 610
|
102
|
+
�� 604
|
103
|
+
�� 604
|
104
|
+
ರ� 560
|
105
|
+
��� 560
|
106
|
+
�� 560
|
107
|
+
� 558
|
108
|
+
��_ 536
|
109
|
+
�_ 536
|
110
|
+
ು_ 536
|
111
|
+
�� 529
|
112
|
+
�� 528
|
113
|
+
ಮ 528
|
114
|
+
�� 520
|
115
|
+
�� 518
|
116
|
+
�� 514
|
117
|
+
�� 511
|
118
|
+
ಮ� 508
|
119
|
+
��� 508
|
120
|
+
�� 500
|
121
|
+
ಯ� 500
|
122
|
+
��� 500
|
123
|
+
ಂ 500
|
124
|
+
��� 495
|
125
|
+
�� 495
|
126
|
+
ಗ� 495
|
127
|
+
��� 488
|
128
|
+
ನ� 488
|
129
|
+
��� 487
|
130
|
+
�� 487
|
131
|
+
ು� 487
|
132
|
+
��� 485
|
133
|
+
��� 485
|
134
|
+
ಂ� 485
|
135
|
+
ಂ� 485
|
136
|
+
�� 481
|
137
|
+
ು� 480
|
138
|
+
��� 480
|
139
|
+
�� 480
|
140
|
+
ನ� 480
|
141
|
+
��� 480
|
142
|
+
��� 471
|
143
|
+
ತ� 471
|
144
|
+
�� 471
|
145
|
+
ಳ 451
|
146
|
+
�� 451
|
147
|
+
ೆ� 449
|
148
|
+
��� 449
|
149
|
+
�� 447
|
150
|
+
� 444
|
151
|
+
ೆ� 440
|
152
|
+
��� 440
|
153
|
+
ವ� 437
|
154
|
+
�� 437
|
155
|
+
��� 437
|
156
|
+
ದ� 435
|
157
|
+
��� 435
|
158
|
+
�� 425
|
159
|
+
��� 425
|
160
|
+
ಕ� 425
|
161
|
+
�� 419
|
162
|
+
ಪ 419
|
163
|
+
�� 415
|
164
|
+
��� 403
|
165
|
+
ಪ� 403
|
166
|
+
ಲ� 401
|
167
|
+
��� 401
|
168
|
+
�� 401
|
169
|
+
�� 396
|
170
|
+
ಯ� 394
|
171
|
+
ಳ� 394
|
172
|
+
�� 394
|
173
|
+
��� 394
|
174
|
+
��� 394
|
175
|
+
��� 381
|
176
|
+
ತ� 381
|
177
|
+
�� 381
|
178
|
+
�� 380
|
179
|
+
�� 377
|
180
|
+
ಲ� 376
|
181
|
+
��� 376
|
182
|
+
��� 356
|
183
|
+
ದ� 356
|
184
|
+
��� 338
|
185
|
+
�� 338
|
186
|
+
ಸ� 338
|
187
|
+
ಕ� 337
|
188
|
+
��� 337
|
189
|
+
�� 337
|
190
|
+
ಮ� 332
|
191
|
+
��� 332
|
192
|
+
�� 332
|
193
|
+
��ನ 307
|
194
|
+
�ನ 307
|
195
|
+
� 302
|
196
|
+
�� 302
|
197
|
+
ಡ 302
|
198
|
+
. 301
|
199
|
+
�ನ� 299
|
200
|
+
ಿ_ 296
|
201
|
+
��_ 296
|
202
|
+
�_ 296
|
203
|
+
� 284
|
204
|
+
�ರ 281
|
205
|
+
�್ 281
|
206
|
+
��್ 281
|
207
|
+
��ರ 281
|
208
|
+
�್� 277
|
209
|
+
�_ 276
|
210
|
+
_ಕ 276
|
211
|
+
_ಕ� 275
|
212
|
+
�್ 272
|
213
|
+
�� 272
|
214
|
+
ಸ� 272
|
215
|
+
��� 272
|
216
|
+
��್ 272
|
217
|
+
�ಳ 271
|
218
|
+
��ಳ 271
|
219
|
+
ಗ� 268
|
220
|
+
��� 268
|
221
|
+
�� 268
|
222
|
+
�ರ� 267
|
223
|
+
�್� 267
|
224
|
+
_ಸ 264
|
225
|
+
��_ 263
|
226
|
+
ದ_ 263
|
227
|
+
_ಸ� 262
|
228
|
+
� 262
|
229
|
+
�� 261
|
230
|
+
, 257
|
231
|
+
ಬ 256
|
232
|
+
�� 256
|
233
|
+
��್ 254
|
234
|
+
�್ 254
|
235
|
+
� 249
|
236
|
+
�� 249
|
237
|
+
ಟ 249
|
238
|
+
ಬ� 247
|
239
|
+
��� 247
|
240
|
+
��ಿ 241
|
241
|
+
�ಿ 241
|
242
|
+
�� 240
|
243
|
+
�ತ 240
|
244
|
+
��ತ 240
|
245
|
+
ಟ� 239
|
246
|
+
�� 239
|
247
|
+
�� 239
|
248
|
+
��� 239
|
249
|
+
,_ 238
|
250
|
+
�್� 237
|
251
|
+
� 236
|
252
|
+
ಹ 236
|
253
|
+
_ಮ 236
|
254
|
+
�� 236
|
255
|
+
_ಮ� 235
|
256
|
+
�ತ� 233
|
257
|
+
�� 228
|
258
|
+
��� 228
|
259
|
+
�ಳ� 228
|
260
|
+
ಹ� 228
|
261
|
+
�� 226
|
262
|
+
��� 226
|
263
|
+
ಡ� 226
|
264
|
+
��್ 224
|
265
|
+
�್ 224
|
266
|
+
ಷ 223
|
267
|
+
�� 223
|
268
|
+
� 223
|
269
|
+
��ಲ 222
|
270
|
+
�ಲ 222
|
271
|
+
�ಲ� 213
|
272
|
+
�� 212
|
273
|
+
ಪ� 211
|
274
|
+
��� 211
|
275
|
+
� 209
|
276
|
+
��ಯ 207
|
277
|
+
�ಯ 207
|
278
|
+
� 206
|
279
|
+
ಜ 206
|
280
|
+
�� 206
|
281
|
+
�� 204
|
282
|
+
�ು 204
|
283
|
+
ಷ� 204
|
284
|
+
��� 204
|
285
|
+
��ು 204
|
286
|
+
�� 203
|
287
|
+
��� 201
|
288
|
+
�� 201
|
289
|
+
�_ 201
|
290
|
+
ಜ� 201
|
291
|
+
ಳ� 198
|
292
|
+
�� 198
|
293
|
+
��� 198
|
294
|
+
ೆ_ 198
|
295
|
+
��_ 198
|
296
|
+
�್� 197
|
297
|
+
��� 196
|
298
|
+
�� 196
|
299
|
+
ಳ� 196
|
300
|
+
�� 195
|
301
|
+
ವ� 193
|
302
|
+
�� 193
|
303
|
+
��� 193
|
304
|
+
��� 192
|
305
|
+
ಪ� 192
|
306
|
+
�ಾ 187
|
307
|
+
��ಾ 187
|
308
|
+
� 186
|
309
|
+
�� 186
|
310
|
+
� 184
|
311
|
+
ಅ 184
|
312
|
+
�� 184
|
313
|
+
ಭ 183
|
314
|
+
�ಾ� 183
|
315
|
+
�� 183
|
316
|
+
��� 179
|
317
|
+
ಭ� 179
|
318
|
+
�� 178
|
319
|
+
ಅ� 178
|
320
|
+
��� 178
|
321
|
+
ಅ� 178
|
322
|
+
��� 178
|
323
|
+
�� 178
|
324
|
+
ೇ 177
|
325
|
+
�� 177
|
326
|
+
�� 176
|
327
|
+
ಮ� 176
|
328
|
+
ಣ 176
|
329
|
+
� 176
|
330
|
+
��� 176
|
331
|
+
�� 176
|
332
|
+
ಶ 176
|
333
|
+
� 176
|
334
|
+
��ದ 175
|
335
|
+
�ದ 175
|
336
|
+
_ಪ 172
|
337
|
+
._ 171
|
338
|
+
_ಪ� 171
|
339
|
+
�ಯ� 166
|
340
|
+
�� 163
|
341
|
+
_ಅ 163
|
342
|
+
ಶ� 163
|
343
|
+
��� 163
|
344
|
+
��� 160
|
345
|
+
��� 160
|
346
|
+
ೇ� 160
|
347
|
+
ೇ� 160
|
348
|
+
��್ 158
|
349
|
+
�್ 158
|
350
|
+
_ಅ� 158
|
351
|
+
�� 157
|
352
|
+
�ಯ 156
|
353
|
+
��ಯ 156
|
354
|
+
�� 154
|
355
|
+
ೂ 154
|
356
|
+
�� 153
|
357
|
+
�್� 152
|
358
|
+
�� 151
|
359
|
+
�ರ 150
|
360
|
+
��ರ 150
|
361
|
+
ಭ� 149
|
362
|
+
ಬ� 149
|
363
|
+
��� 149
|
364
|
+
��� 149
|
365
|
+
�� 148
|
366
|
+
� 148
|
367
|
+
ಚ 148
|
368
|
+
�� 147
|
369
|
+
ಣ� 147
|
370
|
+
��� 147
|
371
|
+
��್ 145
|
372
|
+
�್ 145
|
373
|
+
��� 143
|
374
|
+
ಚ� 143
|
375
|
+
�� 143
|
376
|
+
�ರ� 143
|
377
|
+
�ಿ_ 143
|
378
|
+
��� 142
|
379
|
+
�� 142
|
380
|
+
ಟ� 142
|
381
|
+
_ವ 141
|
382
|
+
��ಗ 140
|
383
|
+
�ಗ 140
|
384
|
+
_ಬ 140
|
385
|
+
�_ 139
|
386
|
+
_ವ� 139
|
387
|
+
�್ 138
|
388
|
+
�್� 138
|
389
|
+
_ಬ� 138
|
390
|
+
��್ 138
|
391
|
+
_ಹ 137
|
392
|
+
��� 135
|
393
|
+
�ಗ� 135
|
394
|
+
ಡ� 135
|
395
|
+
�� 135
|
396
|
+
_ಹ� 135
|
397
|
+
��ು 134
|
398
|
+
�ು 134
|
399
|
+
ಯ_ 133
|
400
|
+
��_ 133
|