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/bulgarian.lm
CHANGED
@@ -1,400 +1,400 @@
|
|
1
1
|
� 73868
|
2
|
-
_
|
2
|
+
_ 36956
|
3
3
|
� 26014
|
4
|
-
_�
|
4
|
+
_� 13890
|
5
5
|
� 11445
|
6
6
|
а 11444
|
7
7
|
� 10454
|
8
8
|
и 10454
|
9
|
-
� 8496
|
10
9
|
е 8496
|
10
|
+
� 8496
|
11
11
|
� 8353
|
12
12
|
о 8352
|
13
13
|
� 7456
|
14
14
|
т 7456
|
15
15
|
� 7357
|
16
16
|
н 7357
|
17
|
-
|
18
|
-
|
17
|
+
н� 6074
|
18
|
+
�� 6074
|
19
19
|
� 5764
|
20
20
|
р 5459
|
21
|
-
|
22
|
-
|
21
|
+
т� 5387
|
22
|
+
�� 5387
|
23
23
|
с 5069
|
24
24
|
� 5069
|
25
|
-
��
|
26
|
-
р�
|
27
|
-
|
28
|
-
|
25
|
+
�� 4632
|
26
|
+
р� 4631
|
27
|
+
е� 4198
|
28
|
+
�� 4198
|
29
29
|
� 4121
|
30
30
|
в 4119
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
|
35
|
-
|
36
|
-
��
|
37
|
-
|
38
|
-
и� 3693
|
39
|
-
�� 3693
|
40
|
-
� 3683
|
31
|
+
�_ 4046
|
32
|
+
а_ 4045
|
33
|
+
�� 4010
|
34
|
+
а� 4010
|
35
|
+
_� 3876
|
36
|
+
�� 3824
|
37
|
+
о� 3824
|
41
38
|
к 3683
|
39
|
+
� 3683
|
40
|
+
и� 3669
|
41
|
+
�� 3669
|
42
42
|
�� 3582
|
43
43
|
и� 3582
|
44
|
-
� 3450
|
45
44
|
л 3450
|
46
|
-
|
45
|
+
� 3450
|
47
46
|
� 3071
|
48
|
-
|
49
|
-
|
50
|
-
��
|
51
|
-
л�
|
52
|
-
��
|
53
|
-
|
54
|
-
|
55
|
-
с�
|
56
|
-
��
|
57
|
-
|
58
|
-
|
59
|
-
�_
|
60
|
-
и_
|
47
|
+
д 3071
|
48
|
+
а� 2939
|
49
|
+
�� 2939
|
50
|
+
л� 2904
|
51
|
+
�� 2904
|
52
|
+
�� 2899
|
53
|
+
в� 2899
|
54
|
+
с� 2809
|
55
|
+
�� 2809
|
56
|
+
�� 2791
|
57
|
+
к� 2791
|
58
|
+
�_ 2710
|
59
|
+
и_ 2710
|
61
60
|
п 2507
|
62
61
|
� 2507
|
63
62
|
�� 2355
|
64
63
|
д� 2355
|
65
|
-
|
66
|
-
|
67
|
-
�а 2260
|
64
|
+
о� 2272
|
65
|
+
�� 2272
|
68
66
|
на 2260
|
69
|
-
|
67
|
+
�а 2260
|
68
|
+
е_ 2226
|
69
|
+
�_ 2226
|
70
70
|
з 2176
|
71
|
-
�
|
72
|
-
|
71
|
+
� 2176
|
72
|
+
�_ 2114
|
73
|
+
о_ 2113
|
73
74
|
я 2001
|
74
75
|
� 2001
|
75
|
-
|
76
|
-
о_ 1974
|
76
|
+
_с 1974
|
77
77
|
с� 1973
|
78
78
|
�� 1973
|
79
|
-
_с 1954
|
80
|
-
м 1871
|
81
79
|
� 1871
|
80
|
+
м 1871
|
82
81
|
е� 1806
|
83
82
|
�� 1806
|
84
|
-
_н
|
85
|
-
з�
|
86
|
-
��
|
87
|
-
_н�
|
88
|
-
ни 1604
|
83
|
+
_н 1774
|
84
|
+
з� 1755
|
85
|
+
�� 1755
|
86
|
+
_н� 1687
|
89
87
|
�и 1604
|
90
|
-
|
88
|
+
ни 1604
|
91
89
|
ъ 1598
|
90
|
+
� 1598
|
92
91
|
м� 1545
|
93
92
|
�� 1545
|
94
|
-
� 1534
|
95
93
|
г 1534
|
96
|
-
|
94
|
+
� 1534
|
95
|
+
_п 1463
|
97
96
|
ст 1462
|
97
|
+
�т 1462
|
98
98
|
, 1462
|
99
|
-
�� 1461
|
100
99
|
п� 1461
|
101
|
-
|
100
|
+
�� 1461
|
101
|
+
,_ 1459
|
102
102
|
�т 1457
|
103
|
-
|
104
|
-
_п 1444
|
105
|
-
то 1405
|
103
|
+
ат 1457
|
106
104
|
�о 1405
|
107
|
-
|
108
|
-
�а_
|
109
|
-
|
105
|
+
то 1405
|
106
|
+
�а_ 1392
|
107
|
+
на_ 1392
|
110
108
|
�а 1371
|
109
|
+
ра 1371
|
111
110
|
те 1358
|
112
111
|
�е 1358
|
113
|
-
_и
|
114
|
-
�н 1332
|
112
|
+
_и 1356
|
115
113
|
ан 1332
|
116
|
-
|
117
|
-
|
114
|
+
�н 1332
|
115
|
+
_на 1305
|
118
116
|
�� 1296
|
117
|
+
г� 1296
|
119
118
|
�а 1263
|
120
119
|
та 1263
|
121
120
|
� 1235
|
122
121
|
б 1234
|
123
|
-
�н 1177
|
124
122
|
ен 1177
|
123
|
+
�н 1177
|
124
|
+
�_ 1175
|
125
|
+
т_ 1175
|
125
126
|
� 1167
|
126
|
-
�_ 1166
|
127
|
-
т_ 1166
|
128
127
|
у 1165
|
129
|
-
�я 1149
|
130
128
|
ия 1149
|
131
|
-
|
129
|
+
�я 1149
|
130
|
+
_в 1142
|
132
131
|
ч 1105
|
133
|
-
|
132
|
+
� 1105
|
134
133
|
�т� 1091
|
135
134
|
ат� 1091
|
136
|
-
�а 1082
|
137
|
-
ва 1082
|
138
135
|
ит 1082
|
136
|
+
ва 1082
|
137
|
+
�а 1082
|
139
138
|
�т 1082
|
139
|
+
_с� 1080
|
140
140
|
ре 1077
|
141
141
|
�е 1077
|
142
|
-
_с� 1065
|
143
|
-
�� 1059
|
144
142
|
ч� 1059
|
145
|
-
��
|
143
|
+
�� 1059
|
146
144
|
п� 1037
|
145
|
+
�� 1037
|
146
|
+
�н� 1034
|
147
147
|
ан� 1034
|
148
|
-
�т� 1034
|
149
148
|
ит� 1034
|
150
|
-
|
149
|
+
�т� 1034
|
151
150
|
. 1032
|
152
|
-
|
153
|
-
|
154
|
-
но 1010
|
151
|
+
�а� 1014
|
152
|
+
ра� 1014
|
155
153
|
�о 1010
|
154
|
+
но 1010
|
156
155
|
ст� 1007
|
157
156
|
�т� 1007
|
158
|
-
_
|
159
|
-
|
157
|
+
._ 982
|
158
|
+
_о 975
|
160
159
|
ъ� 927
|
160
|
+
�� 927
|
161
161
|
ки 919
|
162
162
|
�и 919
|
163
|
-
_д
|
164
|
-
|
165
|
-
|
166
|
-
�е� 882
|
163
|
+
_д 912
|
164
|
+
�о_ 893
|
165
|
+
то_ 893
|
167
166
|
ре� 882
|
168
|
-
|
167
|
+
�е� 882
|
169
168
|
ри 874
|
170
|
-
|
169
|
+
�и 874
|
171
170
|
�и 873
|
171
|
+
ли 873
|
172
172
|
�к 872
|
173
173
|
ск 872
|
174
|
-
�т
|
175
|
-
от
|
176
|
-
пр 857
|
174
|
+
�т 862
|
175
|
+
от 862
|
177
176
|
�р 857
|
178
|
-
|
177
|
+
пр 857
|
179
178
|
�к� 853
|
180
|
-
|
179
|
+
ск� 853
|
181
180
|
пр� 840
|
181
|
+
�р� 840
|
182
182
|
ка 832
|
183
183
|
�а 832
|
184
|
-
�� 815
|
185
184
|
н� 815
|
186
|
-
|
185
|
+
�� 815
|
187
186
|
�и 802
|
187
|
+
ти 802
|
188
188
|
ед 799
|
189
189
|
�д 799
|
190
190
|
ко 777
|
191
191
|
�о 777
|
192
|
-
т� 769
|
193
192
|
�� 769
|
194
|
-
|
193
|
+
т� 769
|
195
194
|
�о 767
|
196
|
-
|
195
|
+
по 767
|
197
196
|
� 756
|
197
|
+
ц 756
|
198
198
|
�е 755
|
199
199
|
не 755
|
200
200
|
�те 744
|
201
|
-
|
201
|
+
_к 742
|
202
|
+
_п� 741
|
203
|
+
�_ 738
|
204
|
+
я_ 738
|
202
205
|
да 736
|
203
206
|
�а 736
|
204
|
-
_п� 732
|
205
|
-
б� 731
|
206
207
|
�� 731
|
207
|
-
|
208
|
-
_и_
|
209
|
-
_с�
|
210
|
-
_
|
211
|
-
_
|
212
|
-
у� 706
|
208
|
+
б� 731
|
209
|
+
_и_ 727
|
210
|
+
_с� 724
|
211
|
+
_п� 720
|
212
|
+
_е 720
|
213
213
|
�� 706
|
214
|
-
|
214
|
+
у� 706
|
215
215
|
�� 704
|
216
|
-
|
217
|
-
ен�
|
218
|
-
|
219
|
-
|
220
|
-
|
221
|
-
|
216
|
+
ц� 704
|
217
|
+
ен� 697
|
218
|
+
�н� 697
|
219
|
+
�е_ 692
|
220
|
+
те_ 692
|
221
|
+
_д� 686
|
222
222
|
�в 682
|
223
|
-
�р 682
|
224
223
|
ар 682
|
224
|
+
�р 682
|
225
225
|
ов 682
|
226
|
-
_о�
|
227
|
-
_д� 675
|
226
|
+
_о� 680
|
228
227
|
�� 671
|
229
228
|
ъ� 671
|
230
|
-
� 670
|
231
229
|
й 670
|
232
|
-
|
230
|
+
� 670
|
233
231
|
ро 667
|
234
|
-
|
232
|
+
�о 667
|
233
|
+
ия_ 659
|
234
|
+
�я_ 659
|
235
235
|
ед� 659
|
236
|
+
�д� 659
|
236
237
|
в� 643
|
237
238
|
�� 643
|
239
|
+
_пр 637
|
238
240
|
�� 635
|
239
241
|
р� 634
|
240
|
-
ж 627
|
241
242
|
� 627
|
242
|
-
�� 627
|
243
243
|
к� 627
|
244
|
-
|
244
|
+
ж 627
|
245
|
+
�� 627
|
246
|
+
та_ 625
|
247
|
+
�а_ 625
|
245
248
|
�т 617
|
246
249
|
ет 617
|
247
|
-
та_ 615
|
248
|
-
�а_ 615
|
249
|
-
ия_ 607
|
250
|
-
�я_ 607
|
251
250
|
�к 599
|
252
251
|
ик 599
|
253
|
-
|
254
|
-
�в� 598
|
255
|
-
�� 596
|
252
|
+
_к� 599
|
256
253
|
ж� 596
|
257
|
-
|
258
|
-
|
254
|
+
�� 596
|
255
|
+
ов� 595
|
256
|
+
�в� 595
|
257
|
+
_и� 588
|
259
258
|
�и� 581
|
260
259
|
ни� 581
|
261
|
-
|
262
|
-
_по 569
|
263
|
-
�� 569
|
264
|
-
�а 565
|
260
|
+
_по 576
|
265
261
|
за 565
|
266
|
-
|
262
|
+
�а 565
|
267
263
|
ве 561
|
268
|
-
|
264
|
+
�е 561
|
269
265
|
�л 559
|
270
|
-
|
266
|
+
ел 559
|
271
267
|
�т� 558
|
272
|
-
|
268
|
+
ет� 558
|
273
269
|
се 551
|
270
|
+
�е 551
|
274
271
|
ор 535
|
275
272
|
�р 535
|
276
|
-
|
273
|
+
_р 531
|
274
|
+
�_ 531
|
275
|
+
в_ 529
|
276
|
+
ав 527
|
277
277
|
�в 527
|
278
278
|
�и 527
|
279
|
-
|
280
|
-
|
279
|
+
ди 527
|
280
|
+
я� 526
|
281
|
+
�� 526
|
281
282
|
�н 523
|
282
283
|
�ки 523
|
283
284
|
ин 523
|
284
|
-
в_ 523
|
285
|
-
_р 521
|
286
285
|
из 518
|
287
286
|
�з 518
|
287
|
+
ни_ 515
|
288
|
+
�и_ 515
|
289
|
+
_з 512
|
290
|
+
_з� 509
|
288
291
|
�е 507
|
289
292
|
ле 507
|
293
|
+
�� 506
|
290
294
|
д� 506
|
291
|
-
ни_ 506
|
292
|
-
�и_ 506
|
293
|
-
�о� 506
|
294
295
|
ро� 506
|
295
|
-
|
296
|
-
|
297
|
-
_
|
298
|
-
|
299
|
-
��
|
300
|
-
я� 500
|
301
|
-
_р� 498
|
296
|
+
_р� 506
|
297
|
+
�о� 506
|
298
|
+
_от 503
|
299
|
+
я� 499
|
300
|
+
�� 499
|
302
301
|
�� 497
|
303
|
-
б� 497
|
304
302
|
�та 497
|
305
|
-
|
306
|
-
|
307
|
-
|
303
|
+
б� 497
|
304
|
+
�о� 494
|
305
|
+
ко� 494
|
306
|
+
_т 490
|
308
307
|
во 486
|
308
|
+
�о 486
|
309
309
|
ци 485
|
310
310
|
�и 485
|
311
311
|
�е� 462
|
312
312
|
ле� 462
|
313
313
|
га 461
|
314
314
|
�а 461
|
315
|
-
|
316
|
-
|
317
|
-
тр 454
|
315
|
+
�с 459
|
316
|
+
ос 459
|
318
317
|
�р 454
|
318
|
+
тр 454
|
319
319
|
од 448
|
320
320
|
�д 448
|
321
|
-
|
321
|
+
�л 446
|
322
322
|
ла 446
|
323
|
-
�а 446
|
324
323
|
ол 446
|
325
|
-
|
324
|
+
�а 446
|
326
325
|
на� 445
|
327
326
|
�а� 445
|
328
|
-
ни� 443
|
329
|
-
�и� 443
|
330
327
|
_в_ 438
|
328
|
+
�и� 437
|
331
329
|
�р� 437
|
330
|
+
ни� 437
|
332
331
|
ор� 437
|
333
332
|
�р 435
|
334
|
-
|
333
|
+
ер 435
|
335
334
|
ри� 435
|
336
335
|
�к� 435
|
337
336
|
�и� 435
|
338
|
-
|
339
|
-
|
340
|
-
|
337
|
+
ик� 435
|
338
|
+
ар� 429
|
339
|
+
�р� 429
|
341
340
|
ма 428
|
342
|
-
�а 428
|
343
|
-
�с 428
|
344
341
|
ес 428
|
345
|
-
|
346
|
-
|
347
|
-
|
348
|
-
|
349
|
-
|
350
|
-
|
342
|
+
�с 428
|
343
|
+
�а 428
|
344
|
+
_м 425
|
345
|
+
те� 424
|
346
|
+
�е� 424
|
347
|
+
�л� 423
|
348
|
+
ел� 423
|
349
|
+
�б 423
|
350
|
+
об 423
|
351
351
|
ав� 422
|
352
352
|
�в� 422
|
353
|
+
но_ 420
|
354
|
+
�о_ 420
|
353
355
|
_за 419
|
354
|
-
�р� 415
|
355
356
|
тр� 415
|
356
|
-
|
357
|
-
|
358
|
-
|
359
|
-
�� 407
|
357
|
+
�р� 415
|
358
|
+
�л 409
|
359
|
+
ал 409
|
360
360
|
л� 407
|
361
|
-
|
362
|
-
�т_
|
361
|
+
�� 407
|
362
|
+
�т_ 406
|
363
|
+
ва_ 406
|
364
|
+
от_ 406
|
365
|
+
�а_ 406
|
363
366
|
� 404
|
364
|
-
|
365
|
-
но_ 402
|
366
|
-
ва_ 401
|
367
|
-
�а_ 401
|
367
|
+
_в� 402
|
368
368
|
щ 400
|
369
|
-
|
369
|
+
�_ 400
|
370
|
+
н_ 400
|
370
371
|
�е 399
|
372
|
+
че 399
|
373
|
+
�ни 398
|
371
374
|
�з 398
|
372
375
|
ез 398
|
373
|
-
�ни 398
|
374
376
|
ви 395
|
377
|
+
_г 395
|
375
378
|
�и 395
|
376
|
-
н_ 394
|
377
|
-
�_ 394
|
378
|
-
�з� 392
|
379
379
|
из� 392
|
380
|
-
|
380
|
+
�з� 392
|
381
381
|
ят 390
|
382
|
-
|
382
|
+
�т 390
|
383
383
|
ме 389
|
384
|
+
�е 389
|
384
385
|
_се 388
|
385
|
-
�� 387
|
386
386
|
у� 387
|
387
|
-
|
387
|
+
�� 387
|
388
388
|
�е 385
|
389
|
-
|
390
|
-
|
389
|
+
ие 385
|
390
|
+
ки_ 381
|
391
|
+
�и_ 381
|
391
392
|
�л 374
|
392
|
-
|
393
|
+
ъл 374
|
393
394
|
�о� 372
|
395
|
+
�ан 372
|
394
396
|
по� 372
|
395
|
-
|
396
|
-
|
397
|
+
да_ 368
|
398
|
+
�а_ 368
|
397
399
|
�е 368
|
398
400
|
де 368
|
399
|
-
да_ 367
|
400
|
-
�а_ 367
|