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
|
+
� 15665
|
2
|
+
_ 8378
|
3
|
+
� 7040
|
4
|
+
_� 3171
|
5
|
+
� 2622
|
6
|
+
о 2622
|
7
|
+
е 1879
|
8
|
+
� 1879
|
9
|
+
а 1680
|
10
|
+
� 1680
|
11
|
+
� 1658
|
12
|
+
т 1658
|
13
|
+
� 1503
|
14
|
+
н 1503
|
15
|
+
и 1424
|
16
|
+
� 1424
|
17
|
+
�� 1372
|
18
|
+
о� 1372
|
19
|
+
н� 1113
|
20
|
+
�� 1113
|
21
|
+
� 1043
|
22
|
+
р 1043
|
23
|
+
_� 1018
|
24
|
+
с 997
|
25
|
+
� 997
|
26
|
+
а� 978
|
27
|
+
�� 978
|
28
|
+
�� 918
|
29
|
+
т� 918
|
30
|
+
р� 890
|
31
|
+
�� 890
|
32
|
+
� 865
|
33
|
+
в 865
|
34
|
+
е� 827
|
35
|
+
�� 827
|
36
|
+
� 760
|
37
|
+
л 759
|
38
|
+
� 730
|
39
|
+
м 730
|
40
|
+
� 695
|
41
|
+
к 695
|
42
|
+
д 686
|
43
|
+
� 686
|
44
|
+
п 655
|
45
|
+
� 655
|
46
|
+
в� 610
|
47
|
+
�� 610
|
48
|
+
�� 607
|
49
|
+
о� 607
|
50
|
+
� 603
|
51
|
+
у 603
|
52
|
+
�� 583
|
53
|
+
и� 583
|
54
|
+
� 571
|
55
|
+
ы 571
|
56
|
+
�� 558
|
57
|
+
и� 558
|
58
|
+
. 524
|
59
|
+
�� 505
|
60
|
+
д� 505
|
61
|
+
�� 503
|
62
|
+
е� 503
|
63
|
+
_п 500
|
64
|
+
�� 494
|
65
|
+
с� 494
|
66
|
+
ь 488
|
67
|
+
� 488
|
68
|
+
�� 486
|
69
|
+
т� 486
|
70
|
+
б 472
|
71
|
+
� 472
|
72
|
+
�_ 460
|
73
|
+
о_ 460
|
74
|
+
с� 457
|
75
|
+
�� 457
|
76
|
+
�� 442
|
77
|
+
к� 442
|
78
|
+
�_ 432
|
79
|
+
е_ 432
|
80
|
+
, 430
|
81
|
+
,_ 430
|
82
|
+
_н 428
|
83
|
+
._ 425
|
84
|
+
�� 422
|
85
|
+
л� 422
|
86
|
+
а� 388
|
87
|
+
�� 388
|
88
|
+
� 388
|
89
|
+
г 388
|
90
|
+
з 384
|
91
|
+
� 384
|
92
|
+
ч 376
|
93
|
+
� 376
|
94
|
+
_н� 368
|
95
|
+
�� 359
|
96
|
+
п� 359
|
97
|
+
_о 351
|
98
|
+
�� 336
|
99
|
+
м� 336
|
100
|
+
_в 329
|
101
|
+
� 325
|
102
|
+
я 325
|
103
|
+
ра 306
|
104
|
+
�а 306
|
105
|
+
�т 301
|
106
|
+
ст 301
|
107
|
+
�� 298
|
108
|
+
н� 298
|
109
|
+
ч� 298
|
110
|
+
�� 298
|
111
|
+
�� 296
|
112
|
+
п� 296
|
113
|
+
�� 295
|
114
|
+
но 295
|
115
|
+
�о 295
|
116
|
+
л� 295
|
117
|
+
з� 294
|
118
|
+
�� 294
|
119
|
+
_п� 280
|
120
|
+
_т 274
|
121
|
+
ни 268
|
122
|
+
�и 268
|
123
|
+
�� 259
|
124
|
+
г� 259
|
125
|
+
а_ 256
|
126
|
+
�_ 256
|
127
|
+
ра� 254
|
128
|
+
�а� 254
|
129
|
+
�� 253
|
130
|
+
б� 253
|
131
|
+
пр� 245
|
132
|
+
пр 245
|
133
|
+
�р 245
|
134
|
+
�р� 245
|
135
|
+
�_ 244
|
136
|
+
ы_ 244
|
137
|
+
� 240
|
138
|
+
х 240
|
139
|
+
�_ 236
|
140
|
+
ь_ 236
|
141
|
+
у� 234
|
142
|
+
ов 234
|
143
|
+
�в 234
|
144
|
+
�о 234
|
145
|
+
по 234
|
146
|
+
�� 234
|
147
|
+
й 233
|
148
|
+
� 233
|
149
|
+
то 232
|
150
|
+
�о 232
|
151
|
+
и_ 229
|
152
|
+
�_ 229
|
153
|
+
�о 227
|
154
|
+
ро 227
|
155
|
+
�ь 226
|
156
|
+
ст� 226
|
157
|
+
ть 226
|
158
|
+
�т� 226
|
159
|
+
от 222
|
160
|
+
�т 222
|
161
|
+
_п� 220
|
162
|
+
_по 219
|
163
|
+
_о� 219
|
164
|
+
_с 217
|
165
|
+
�_ 216
|
166
|
+
м_ 216
|
167
|
+
на 215
|
168
|
+
�� 215
|
169
|
+
те 215
|
170
|
+
�а 215
|
171
|
+
�е 215
|
172
|
+
в� 215
|
173
|
+
� 213
|
174
|
+
ю 213
|
175
|
+
у� 211
|
176
|
+
�� 211
|
177
|
+
не 210
|
178
|
+
�е 210
|
179
|
+
_пр 207
|
180
|
+
_д 206
|
181
|
+
�_ 200
|
182
|
+
т_ 200
|
183
|
+
_к 199
|
184
|
+
_т� 199
|
185
|
+
�н 197
|
186
|
+
ен 197
|
187
|
+
_д� 197
|
188
|
+
_б 191
|
189
|
+
_в� 189
|
190
|
+
ш 185
|
191
|
+
� 185
|
192
|
+
�г 183
|
193
|
+
ог 183
|
194
|
+
�о 183
|
195
|
+
ко 183
|
196
|
+
та 180
|
197
|
+
во 180
|
198
|
+
�о 180
|
199
|
+
�а 180
|
200
|
+
_р 176
|
201
|
+
б� 175
|
202
|
+
�� 175
|
203
|
+
ит 174
|
204
|
+
�т 174
|
205
|
+
ы� 168
|
206
|
+
�� 168
|
207
|
+
ет 167
|
208
|
+
�т 167
|
209
|
+
� 166
|
210
|
+
ж 166
|
211
|
+
ко� 165
|
212
|
+
�о� 165
|
213
|
+
�ь_ 164
|
214
|
+
ть_ 164
|
215
|
+
_с� 161
|
216
|
+
�� 160
|
217
|
+
ш� 160
|
218
|
+
�н 158
|
219
|
+
он 158
|
220
|
+
�н� 157
|
221
|
+
�в� 157
|
222
|
+
ов� 157
|
223
|
+
ен� 157
|
224
|
+
го 157
|
225
|
+
�о 157
|
226
|
+
ж� 156
|
227
|
+
я_ 156
|
228
|
+
�о� 156
|
229
|
+
�_ 156
|
230
|
+
ро� 156
|
231
|
+
�� 156
|
232
|
+
_не 153
|
233
|
+
_м 153
|
234
|
+
�а 150
|
235
|
+
ва 150
|
236
|
+
_р� 149
|
237
|
+
�е 148
|
238
|
+
ре 148
|
239
|
+
к� 148
|
240
|
+
�� 148
|
241
|
+
ри 146
|
242
|
+
�и 146
|
243
|
+
�и 144
|
244
|
+
ли 144
|
245
|
+
�т 141
|
246
|
+
�� 141
|
247
|
+
�е 141
|
248
|
+
р� 141
|
249
|
+
ве 141
|
250
|
+
ат 141
|
251
|
+
�л 140
|
252
|
+
�е 140
|
253
|
+
_в� 140
|
254
|
+
че 140
|
255
|
+
ол 140
|
256
|
+
ка 137
|
257
|
+
�а 137
|
258
|
+
�е 135
|
259
|
+
_к� 135
|
260
|
+
де 135
|
261
|
+
у_ 133
|
262
|
+
�д 133
|
263
|
+
од 133
|
264
|
+
�_ 133
|
265
|
+
от� 132
|
266
|
+
�т� 132
|
267
|
+
_о� 132
|
268
|
+
�о 130
|
269
|
+
бо 130
|
270
|
+
аз 129
|
271
|
+
�з 129
|
272
|
+
_ра 128
|
273
|
+
�м 128
|
274
|
+
ом 128
|
275
|
+
ль 127
|
276
|
+
�ь 127
|
277
|
+
_на 126
|
278
|
+
�е� 125
|
279
|
+
�н 125
|
280
|
+
ан 125
|
281
|
+
ре� 125
|
282
|
+
но_ 124
|
283
|
+
_и 124
|
284
|
+
�о_ 124
|
285
|
+
за 122
|
286
|
+
й_ 122
|
287
|
+
�а 122
|
288
|
+
�_ 122
|
289
|
+
ан� 121
|
290
|
+
х_ 121
|
291
|
+
�_ 121
|
292
|
+
�н� 121
|
293
|
+
�и� 120
|
294
|
+
ни� 120
|
295
|
+
�ро 120
|
296
|
+
ос 119
|
297
|
+
�с 119
|
298
|
+
ам 117
|
299
|
+
�м 117
|
300
|
+
д� 117
|
301
|
+
�� 117
|
302
|
+
�б 116
|
303
|
+
об 116
|
304
|
+
�а� 114
|
305
|
+
та� 114
|
306
|
+
�� 114
|
307
|
+
�м 114
|
308
|
+
ем 114
|
309
|
+
м� 114
|
310
|
+
ал 113
|
311
|
+
_м� 113
|
312
|
+
�р 113
|
313
|
+
�л 113
|
314
|
+
ор 113
|
315
|
+
ер 112
|
316
|
+
�р 112
|
317
|
+
_з� 112
|
318
|
+
_з 112
|
319
|
+
бы 110
|
320
|
+
ес 110
|
321
|
+
�с 110
|
322
|
+
�ы 110
|
323
|
+
�к 109
|
324
|
+
ак 109
|
325
|
+
�� 107
|
326
|
+
ь� 107
|
327
|
+
_у 107
|
328
|
+
ю� 106
|
329
|
+
ь� 106
|
330
|
+
�� 106
|
331
|
+
�� 106
|
332
|
+
тр 105
|
333
|
+
�о� 105
|
334
|
+
до 105
|
335
|
+
�о 105
|
336
|
+
�р 105
|
337
|
+
по� 105
|
338
|
+
�в 104
|
339
|
+
ск 104
|
340
|
+
�к 104
|
341
|
+
�. 104
|
342
|
+
тв 104
|
343
|
+
о. 104
|
344
|
+
ед 103
|
345
|
+
�д 103
|
346
|
+
аб 100
|
347
|
+
�б 100
|
348
|
+
� 100
|
349
|
+
�ы 99
|
350
|
+
.� 99
|
351
|
+
ны 99
|
352
|
+
�о� 99
|
353
|
+
ти 99
|
354
|
+
то� 99
|
355
|
+
�и 99
|
356
|
+
_б� 98
|
357
|
+
�о� 98
|
358
|
+
_за 98
|
359
|
+
но� 98
|
360
|
+
ел 97
|
361
|
+
�е 97
|
362
|
+
ме 97
|
363
|
+
�л 97
|
364
|
+
�и� 95
|
365
|
+
ни� 95
|
366
|
+
_во 95
|
367
|
+
�в� 95
|
368
|
+
тв� 95
|
369
|
+
ог� 94
|
370
|
+
�г� 94
|
371
|
+
ат� 94
|
372
|
+
�з� 94
|
373
|
+
�т� 94
|
374
|
+
аз� 94
|
375
|
+
�ы 93
|
376
|
+
_б� 93
|
377
|
+
вы 93
|
378
|
+
�тв 93
|
379
|
+
на� 92
|
380
|
+
�а� 92
|
381
|
+
�� 91
|
382
|
+
ы� 91
|
383
|
+
ит� 90
|
384
|
+
�м 90
|
385
|
+
те� 90
|
386
|
+
�т� 90
|
387
|
+
�е� 90
|
388
|
+
че� 90
|
389
|
+
�е� 90
|
390
|
+
им 90
|
391
|
+
_он 89
|
392
|
+
к_ 88
|
393
|
+
�н 88
|
394
|
+
�_ 88
|
395
|
+
ин 88
|
396
|
+
их 87
|
397
|
+
�го 87
|
398
|
+
�х 87
|
399
|
+
�к� 86
|
400
|
+
тр� 86
|