scylla 0.7.0 → 0.7.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/lib/scylla/classifier.rb +3 -4
- data/lib/scylla/generator.rb +4 -7
- data/lib/scylla/lms/afrikaans.lm +280 -280
- data/lib/scylla/lms/arabic.lm +225 -225
- data/lib/scylla/lms/bulgarian.lm +208 -208
- data/lib/scylla/lms/catalan.lm +212 -212
- data/lib/scylla/lms/chinese.lm +201 -201
- data/lib/scylla/lms/danish.lm +155 -155
- data/lib/scylla/lms/english.lm +207 -207
- data/lib/scylla/lms/finnish.lm +259 -259
- data/lib/scylla/lms/french.lm +203 -203
- data/lib/scylla/lms/german.lm +280 -280
- data/lib/scylla/lms/greek.lm +276 -276
- data/lib/scylla/lms/hebrew.lm +170 -170
- data/lib/scylla/lms/hindi.lm +241 -241
- data/lib/scylla/lms/icelandic.lm +264 -264
- data/lib/scylla/lms/indonesian.lm +272 -272
- data/lib/scylla/lms/italian.lm +283 -283
- data/lib/scylla/lms/japanese.lm +105 -105
- data/lib/scylla/lms/korean.lm +400 -400
- data/lib/scylla/lms/norwegian.lm +235 -235
- data/lib/scylla/lms/polish.lm +264 -264
- data/lib/scylla/lms/portuguese.lm +269 -269
- data/lib/scylla/lms/romanian.lm +278 -278
- data/lib/scylla/lms/russian.lm +127 -127
- data/lib/scylla/lms/slovak.lm +281 -281
- data/lib/scylla/lms/slovenian.lm +276 -276
- data/lib/scylla/lms/spanish.lm +190 -190
- data/lib/scylla/lms/swedish.lm +195 -195
- data/lib/scylla/lms/tagalog.lm +282 -282
- data/lib/scylla/lms/thai.lm +257 -257
- data/lib/scylla/lms/turkish.lm +300 -300
- data/lib/scylla/lms/vietnamese.lm +277 -277
- data/lib/scylla/lms/welsh.lm +271 -271
- data/scylla.gemspec +3 -22
- data/source_texts/korean.txt +219 -134
- metadata +15 -14
- data/scylla-0.6.0.gem +0 -0
data/lib/scylla/lms/russian.lm
CHANGED
@@ -1,30 +1,30 @@
|
|
1
1
|
� 15665
|
2
|
-
_
|
2
|
+
_ 8576
|
3
3
|
� 7040
|
4
|
-
_�
|
5
|
-
� 2622
|
4
|
+
_� 3270
|
6
5
|
о 2622
|
7
|
-
|
6
|
+
� 2622
|
8
7
|
� 1879
|
8
|
+
е 1879
|
9
9
|
а 1680
|
10
10
|
� 1680
|
11
|
-
� 1658
|
12
11
|
т 1658
|
13
|
-
�
|
12
|
+
� 1658
|
14
13
|
н 1503
|
15
|
-
|
14
|
+
� 1503
|
16
15
|
� 1424
|
16
|
+
и 1424
|
17
17
|
�� 1372
|
18
18
|
о� 1372
|
19
|
-
н� 1113
|
20
19
|
�� 1113
|
20
|
+
н� 1113
|
21
21
|
� 1043
|
22
22
|
р 1043
|
23
23
|
_� 1018
|
24
|
-
с 997
|
25
24
|
� 997
|
26
|
-
|
25
|
+
с 997
|
27
26
|
�� 978
|
27
|
+
а� 978
|
28
28
|
�� 918
|
29
29
|
т� 918
|
30
30
|
р� 890
|
@@ -35,10 +35,10 @@ _
|
|
35
35
|
�� 827
|
36
36
|
� 760
|
37
37
|
л 759
|
38
|
-
� 730
|
39
38
|
м 730
|
40
|
-
�
|
39
|
+
� 730
|
41
40
|
к 695
|
41
|
+
� 695
|
42
42
|
д 686
|
43
43
|
� 686
|
44
44
|
п 655
|
@@ -53,9 +53,10 @@ _
|
|
53
53
|
и� 583
|
54
54
|
� 571
|
55
55
|
ы 571
|
56
|
-
�� 558
|
57
56
|
и� 558
|
57
|
+
�� 558
|
58
58
|
. 524
|
59
|
+
._ 524
|
59
60
|
�� 505
|
60
61
|
д� 505
|
61
62
|
�� 503
|
@@ -69,23 +70,22 @@ _п 500
|
|
69
70
|
т� 486
|
70
71
|
б 472
|
71
72
|
� 472
|
72
|
-
�_ 460
|
73
73
|
о_ 460
|
74
|
+
�_ 460
|
74
75
|
с� 457
|
75
76
|
�� 457
|
76
77
|
�� 442
|
77
78
|
к� 442
|
78
|
-
�_ 432
|
79
79
|
е_ 432
|
80
|
-
|
80
|
+
�_ 432
|
81
81
|
,_ 430
|
82
|
+
, 430
|
82
83
|
_н 428
|
83
|
-
._ 425
|
84
|
-
�� 422
|
85
84
|
л� 422
|
85
|
+
�� 422
|
86
86
|
а� 388
|
87
|
-
�� 388
|
88
87
|
� 388
|
88
|
+
�� 388
|
89
89
|
г 388
|
90
90
|
з 384
|
91
91
|
� 384
|
@@ -95,25 +95,25 @@ _н
|
|
95
95
|
�� 359
|
96
96
|
п� 359
|
97
97
|
_о 351
|
98
|
-
�� 336
|
99
98
|
м� 336
|
99
|
+
�� 336
|
100
100
|
_в 329
|
101
|
-
� 325
|
102
101
|
я 325
|
103
|
-
|
102
|
+
� 325
|
104
103
|
�а 306
|
104
|
+
ра 306
|
105
105
|
�т 301
|
106
106
|
ст 301
|
107
|
-
�� 298
|
107
|
+
�� 298
|
108
108
|
н� 298
|
109
|
+
�� 298
|
109
110
|
ч� 298
|
110
|
-
�� 298
|
111
|
-
�� 296
|
112
111
|
п� 296
|
112
|
+
�� 296
|
113
113
|
�� 295
|
114
|
-
но 295
|
115
|
-
�о 295
|
116
114
|
л� 295
|
115
|
+
�о 295
|
116
|
+
но 295
|
117
117
|
з� 294
|
118
118
|
�� 294
|
119
119
|
_п� 280
|
@@ -122,92 +122,92 @@ _т 274
|
|
122
122
|
�и 268
|
123
123
|
�� 259
|
124
124
|
г� 259
|
125
|
-
а_ 256
|
126
125
|
�_ 256
|
127
|
-
|
126
|
+
а_ 256
|
128
127
|
�а� 254
|
128
|
+
ра� 254
|
129
129
|
�� 253
|
130
130
|
б� 253
|
131
|
-
пр� 245
|
132
|
-
пр 245
|
133
131
|
�р 245
|
132
|
+
пр 245
|
134
133
|
�р� 245
|
134
|
+
пр� 245
|
135
135
|
�_ 244
|
136
136
|
ы_ 244
|
137
137
|
� 240
|
138
138
|
х 240
|
139
|
-
�_ 236
|
140
139
|
ь_ 236
|
140
|
+
�_ 236
|
141
141
|
у� 234
|
142
142
|
ов 234
|
143
|
-
|
143
|
+
�� 234
|
144
144
|
�о 234
|
145
145
|
по 234
|
146
|
-
|
147
|
-
й 233
|
146
|
+
�в 234
|
148
147
|
� 233
|
148
|
+
й 233
|
149
149
|
то 232
|
150
150
|
�о 232
|
151
151
|
и_ 229
|
152
152
|
�_ 229
|
153
|
-
�о 227
|
154
153
|
ро 227
|
155
|
-
|
154
|
+
�о 227
|
156
155
|
ст� 226
|
157
|
-
|
156
|
+
�ь 226
|
158
157
|
�т� 226
|
158
|
+
ть 226
|
159
159
|
от 222
|
160
160
|
�т 222
|
161
161
|
_п� 220
|
162
162
|
_по 219
|
163
163
|
_о� 219
|
164
164
|
_с 217
|
165
|
-
�_ 216
|
166
165
|
м_ 216
|
167
|
-
|
166
|
+
�_ 216
|
168
167
|
�� 215
|
169
|
-
те 215
|
170
168
|
�а 215
|
171
|
-
|
169
|
+
те 215
|
172
170
|
в� 215
|
173
|
-
|
171
|
+
на 215
|
172
|
+
�е 215
|
174
173
|
ю 213
|
175
|
-
|
174
|
+
� 213
|
176
175
|
�� 211
|
177
|
-
|
176
|
+
у� 211
|
178
177
|
�е 210
|
178
|
+
не 210
|
179
179
|
_пр 207
|
180
180
|
_д 206
|
181
|
-
�_ 200
|
182
181
|
т_ 200
|
183
|
-
_
|
182
|
+
�_ 200
|
184
183
|
_т� 199
|
184
|
+
_к 199
|
185
185
|
�н 197
|
186
|
-
ен 197
|
187
186
|
_д� 197
|
187
|
+
ен 197
|
188
188
|
_б 191
|
189
189
|
_в� 189
|
190
|
-
ш 185
|
191
190
|
� 185
|
192
|
-
|
193
|
-
ог 183
|
191
|
+
ш 185
|
194
192
|
�о 183
|
195
193
|
ко 183
|
194
|
+
�г 183
|
195
|
+
ог 183
|
196
|
+
�а 180
|
196
197
|
та 180
|
197
198
|
во 180
|
198
199
|
�о 180
|
199
|
-
�а 180
|
200
200
|
_р 176
|
201
201
|
б� 175
|
202
202
|
�� 175
|
203
|
-
ит 174
|
204
203
|
�т 174
|
204
|
+
ит 174
|
205
205
|
ы� 168
|
206
206
|
�� 168
|
207
207
|
ет 167
|
208
208
|
�т 167
|
209
|
-
� 166
|
210
209
|
ж 166
|
210
|
+
� 166
|
211
211
|
ко� 165
|
212
212
|
�о� 165
|
213
213
|
�ь_ 164
|
@@ -215,186 +215,186 @@ _р 176
|
|
215
215
|
_с� 161
|
216
216
|
�� 160
|
217
217
|
ш� 160
|
218
|
-
�н 158
|
219
218
|
он 158
|
220
|
-
|
219
|
+
�н 158
|
221
220
|
�в� 157
|
222
|
-
ов� 157
|
223
|
-
ен� 157
|
224
221
|
го 157
|
222
|
+
�н� 157
|
225
223
|
�о 157
|
226
|
-
|
227
|
-
|
228
|
-
�о� 156
|
229
|
-
�_ 156
|
224
|
+
ен� 157
|
225
|
+
ов� 157
|
230
226
|
ро� 156
|
227
|
+
�_ 156
|
228
|
+
�о� 156
|
231
229
|
�� 156
|
230
|
+
ж� 156
|
231
|
+
я_ 156
|
232
232
|
_не 153
|
233
233
|
_м 153
|
234
|
-
�а 150
|
235
234
|
ва 150
|
235
|
+
�а 150
|
236
236
|
_р� 149
|
237
|
+
�� 148
|
237
238
|
�е 148
|
238
239
|
ре 148
|
239
240
|
к� 148
|
240
|
-
�� 148
|
241
241
|
ри 146
|
242
242
|
�и 146
|
243
|
-
�и 144
|
244
243
|
ли 144
|
244
|
+
�и 144
|
245
|
+
ат 141
|
246
|
+
ве 141
|
245
247
|
�т 141
|
246
|
-
�� 141
|
247
248
|
�е 141
|
249
|
+
�� 141
|
248
250
|
р� 141
|
249
|
-
ве 141
|
250
|
-
ат 141
|
251
251
|
�л 140
|
252
|
-
|
252
|
+
ол 140
|
253
253
|
_в� 140
|
254
254
|
че 140
|
255
|
-
|
256
|
-
ка 137
|
255
|
+
�е 140
|
257
256
|
�а 137
|
258
|
-
|
257
|
+
ка 137
|
259
258
|
_к� 135
|
260
259
|
де 135
|
261
|
-
|
260
|
+
�е 135
|
262
261
|
�д 133
|
263
262
|
од 133
|
263
|
+
у_ 133
|
264
264
|
�_ 133
|
265
|
+
_о� 132
|
265
266
|
от� 132
|
266
267
|
�т� 132
|
267
|
-
_о� 132
|
268
268
|
�о 130
|
269
269
|
бо 130
|
270
270
|
аз 129
|
271
271
|
�з 129
|
272
|
-
_ра 128
|
273
272
|
�м 128
|
273
|
+
_ра 128
|
274
274
|
ом 128
|
275
275
|
ль 127
|
276
276
|
�ь 127
|
277
277
|
_на 126
|
278
278
|
�е� 125
|
279
|
-
�н 125
|
280
279
|
ан 125
|
280
|
+
�н 125
|
281
281
|
ре� 125
|
282
|
-
но_ 124
|
283
282
|
_и 124
|
283
|
+
но_ 124
|
284
284
|
�о_ 124
|
285
|
-
за 122
|
286
|
-
й_ 122
|
287
285
|
�а 122
|
286
|
+
за 122
|
288
287
|
�_ 122
|
288
|
+
й_ 122
|
289
|
+
�н� 121
|
290
|
+
�_ 121
|
289
291
|
ан� 121
|
290
292
|
х_ 121
|
291
|
-
�_ 121
|
292
|
-
�н� 121
|
293
293
|
�и� 120
|
294
294
|
ни� 120
|
295
295
|
�ро 120
|
296
|
-
ос 119
|
297
296
|
�с 119
|
298
|
-
|
297
|
+
ос 119
|
299
298
|
�м 117
|
300
299
|
д� 117
|
301
300
|
�� 117
|
302
|
-
|
301
|
+
ам 117
|
303
302
|
об 116
|
303
|
+
�б 116
|
304
|
+
�� 114
|
304
305
|
�а� 114
|
305
306
|
та� 114
|
306
|
-
�� 114
|
307
|
-
�м 114
|
308
|
-
ем 114
|
309
307
|
м� 114
|
308
|
+
ем 114
|
309
|
+
�м 114
|
310
|
+
ор 113
|
311
|
+
�л 113
|
310
312
|
ал 113
|
311
|
-
_м� 113
|
312
313
|
�р 113
|
313
|
-
|
314
|
-
ор 113
|
315
|
-
ер 112
|
314
|
+
_м� 113
|
316
315
|
�р 112
|
316
|
+
ер 112
|
317
317
|
_з� 112
|
318
318
|
_з 112
|
319
319
|
бы 110
|
320
320
|
ес 110
|
321
|
-
�с 110
|
322
321
|
�ы 110
|
323
|
-
|
322
|
+
�с 110
|
324
323
|
ак 109
|
325
|
-
|
326
|
-
ь� 107
|
324
|
+
�к 109
|
327
325
|
_у 107
|
326
|
+
ь� 107
|
327
|
+
�� 107
|
328
328
|
ю� 106
|
329
|
+
�� 106
|
329
330
|
ь� 106
|
330
331
|
�� 106
|
331
|
-
|
332
|
+
по� 105
|
333
|
+
�р 105
|
334
|
+
до 105
|
332
335
|
тр 105
|
333
336
|
�о� 105
|
334
|
-
до 105
|
335
337
|
�о 105
|
336
|
-
|
337
|
-
|
338
|
-
�в 104
|
339
|
-
ск 104
|
338
|
+
о._ 104
|
339
|
+
о. 104
|
340
340
|
�к 104
|
341
|
-
�. 104
|
342
341
|
тв 104
|
343
|
-
|
344
|
-
|
342
|
+
ск 104
|
343
|
+
�. 104
|
344
|
+
�._ 104
|
345
|
+
�в 104
|
345
346
|
�д 103
|
346
|
-
|
347
|
+
ед 103
|
347
348
|
�б 100
|
348
349
|
� 100
|
349
|
-
|
350
|
-
|
350
|
+
аб 100
|
351
|
+
�и 99
|
351
352
|
ны 99
|
352
|
-
�о� 99
|
353
353
|
ти 99
|
354
|
+
�о� 99
|
354
355
|
то� 99
|
355
|
-
|
356
|
+
�ы 99
|
357
|
+
но� 98
|
356
358
|
_б� 98
|
357
|
-
�о� 98
|
358
359
|
_за 98
|
359
|
-
|
360
|
-
ел 97
|
361
|
-
�е 97
|
360
|
+
�о� 98
|
362
361
|
ме 97
|
363
362
|
�л 97
|
364
|
-
|
363
|
+
ел 97
|
364
|
+
�е 97
|
365
365
|
ни� 95
|
366
|
+
тв� 95
|
366
367
|
_во 95
|
368
|
+
�и� 95
|
367
369
|
�в� 95
|
368
|
-
тв� 95
|
369
|
-
ог� 94
|
370
|
-
�г� 94
|
371
370
|
ат� 94
|
372
371
|
�з� 94
|
372
|
+
ог� 94
|
373
|
+
�г� 94
|
373
374
|
�т� 94
|
374
375
|
аз� 94
|
376
|
+
вы 93
|
375
377
|
�ы 93
|
376
378
|
_б� 93
|
377
|
-
вы 93
|
378
379
|
�тв 93
|
379
380
|
на� 92
|
380
381
|
�а� 92
|
381
|
-
�� 91
|
382
382
|
ы� 91
|
383
|
-
|
384
|
-
|
383
|
+
�� 91
|
384
|
+
им 90
|
385
385
|
те� 90
|
386
386
|
�т� 90
|
387
387
|
�е� 90
|
388
|
-
|
388
|
+
�м 90
|
389
389
|
�е� 90
|
390
|
-
|
390
|
+
че� 90
|
391
|
+
ит� 90
|
391
392
|
_он 89
|
392
|
-
к_ 88
|
393
393
|
�н 88
|
394
|
+
к_ 88
|
394
395
|
�_ 88
|
395
396
|
ин 88
|
396
397
|
их 87
|
397
|
-
�го 87
|
398
398
|
�х 87
|
399
|
-
|
400
|
-
|
399
|
+
�го 87
|
400
|
+
�а� 86
|