scylla 0.5.0 → 0.6.0
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +4 -2
- data/Gemfile.lock +16 -1
- data/lib/scylla/classifier.rb +1 -1
- data/lib/scylla/generator.rb +16 -4
- data/lib/scylla/lms/afrikaans.lm +232 -232
- data/lib/scylla/lms/arabic.lm +175 -175
- data/lib/scylla/lms/bulgarian.lm +225 -225
- data/lib/scylla/lms/catalan.lm +309 -309
- data/lib/scylla/lms/danish.lm +167 -167
- data/lib/scylla/lms/english.lm +398 -398
- data/lib/scylla/lms/finnish.lm +237 -237
- data/lib/scylla/lms/french.lm +148 -148
- data/lib/scylla/lms/german.lm +258 -258
- data/lib/scylla/lms/greek.lm +236 -236
- data/lib/scylla/lms/hebrew.lm +154 -154
- data/lib/scylla/lms/hindi.lm +139 -139
- data/lib/scylla/lms/icelandic.lm +239 -239
- data/lib/scylla/lms/indonesian.lm +244 -244
- data/lib/scylla/lms/italian.lm +248 -248
- data/lib/scylla/lms/japanese.lm +90 -90
- data/lib/scylla/lms/korean.lm +306 -306
- data/lib/scylla/lms/norwegian.lm +193 -193
- data/lib/scylla/lms/polish.lm +241 -241
- data/lib/scylla/lms/portuguese.lm +232 -232
- data/lib/scylla/lms/romanian.lm +246 -246
- data/lib/scylla/lms/slovak.lm +242 -242
- data/lib/scylla/lms/slovenian.lm +229 -229
- data/lib/scylla/lms/spanish.lm +164 -164
- data/lib/scylla/lms/swedish.lm +157 -157
- data/lib/scylla/lms/tagalog.lm +247 -247
- data/lib/scylla/lms/thai.lm +252 -252
- data/lib/scylla/lms/turkish.lm +285 -285
- data/lib/scylla/lms/vietnamese.lm +250 -250
- data/lib/scylla/lms/welsh.lm +248 -248
- data/lib/scylla/resources.rb +1 -9
- data/lib/scylla.rb +4 -0
- data/scylla.gemspec +2 -120
- data/source_texts/english.txt +62 -27
- data/test/classifier_test.rb +1 -3
- data/test/fixtures/lms/danish.lm +173 -173
- data/test/fixtures/lms/english.lm +220 -220
- data/test/fixtures/lms/french.lm +175 -175
- data/test/fixtures/lms/german.lm +254 -254
- data/test/fixtures/lms/hindi.lm +139 -139
- data/test/fixtures/lms/italian.lm +236 -236
- data/test/fixtures/lms/japanese.lm +88 -88
- data/test/fixtures/lms/norwegian.lm +182 -182
- data/test/fixtures/lms/spanish.lm +164 -164
- data/test/fixtures/test_languages/spanish +0 -1
- data/test/generator_test.rb +13 -0
- data/test/helper.rb +2 -0
- metadata +18 -25
- data/.document +0 -5
- data/lib/scylla/lms/13375P33K.lm +0 -400
- data/scylla-0.1.0.gem +0 -0
- data/source_texts/13375P33K.txt +0 -199
- data/test/fixtures/lms/13375p33k.lm +0 -400
- data/test/fixtures/source_texts/13375P33K.txt +0 -199
data/test/fixtures/lms/hindi.lm
CHANGED
@@ -6,364 +6,364 @@ _ 9054
|
|
6
6
|
� 5427
|
7
7
|
_� 4527
|
8
8
|
_� 4495
|
9
|
-
�� 2729
|
10
9
|
ा 2729
|
11
10
|
� 2729
|
12
|
-
|
11
|
+
�� 2729
|
13
12
|
् 2281
|
13
|
+
� 2281
|
14
14
|
�� 2281
|
15
|
+
��� 2265
|
15
16
|
�� 2265
|
16
17
|
्� 2265
|
17
|
-
��� 2265
|
18
18
|
�� 2251
|
19
|
-
��� 2251
|
20
19
|
्� 2251
|
20
|
+
��� 2251
|
21
21
|
�� 2023
|
22
22
|
ा� 2023
|
23
23
|
��� 2023
|
24
|
-
र 2005
|
25
24
|
�� 2005
|
25
|
+
र 2005
|
26
26
|
� 2005
|
27
|
-
�� 1970
|
28
|
-
ा� 1970
|
29
27
|
��� 1970
|
30
|
-
|
28
|
+
ा� 1970
|
29
|
+
�� 1970
|
31
30
|
ि 1764
|
32
31
|
� 1764
|
32
|
+
�� 1764
|
33
|
+
�� 1706
|
33
34
|
र� 1706
|
34
35
|
��� 1706
|
35
|
-
|
36
|
+
� 1665
|
36
37
|
�� 1665
|
37
38
|
क 1665
|
38
|
-
� 1665
|
39
39
|
�� 1596
|
40
40
|
त 1596
|
41
|
-
�� 1516
|
42
|
-
��� 1516
|
43
|
-
�� 1516
|
44
|
-
ि� 1516
|
45
41
|
��� 1516
|
42
|
+
�� 1516
|
46
43
|
ि� 1516
|
44
|
+
��� 1516
|
45
|
+
ि� 1516
|
46
|
+
�� 1516
|
47
47
|
� 1391
|
48
|
-
��� 1390
|
49
48
|
�� 1390
|
49
|
+
��� 1390
|
50
50
|
क� 1390
|
51
|
-
�� 1381
|
52
51
|
न 1381
|
53
|
-
��
|
54
|
-
स 1345
|
52
|
+
�� 1381
|
55
53
|
� 1345
|
56
|
-
|
57
|
-
��
|
54
|
+
स 1345
|
55
|
+
�� 1345
|
58
56
|
स� 1264
|
57
|
+
�� 1264
|
58
|
+
��� 1264
|
59
59
|
�� 1226
|
60
60
|
त� 1200
|
61
61
|
��� 1200
|
62
62
|
� 1181
|
63
63
|
े 1172
|
64
64
|
�� 1172
|
65
|
-
� 1144
|
66
65
|
व 1144
|
66
|
+
� 1144
|
67
67
|
�� 1144
|
68
|
-
व� 1083
|
69
|
-
�� 1083
|
70
68
|
��� 1083
|
69
|
+
�� 1083
|
70
|
+
व� 1083
|
71
71
|
�� 1075
|
72
|
-
��� 1065
|
73
72
|
न� 1065
|
73
|
+
��� 1065
|
74
74
|
�� 963
|
75
75
|
��� 963
|
76
76
|
र� 963
|
77
77
|
�� 920
|
78
|
-
व� 908
|
79
78
|
��� 908
|
80
79
|
�� 908
|
80
|
+
व� 908
|
81
81
|
��� 894
|
82
82
|
त� 894
|
83
|
-
म 858
|
84
|
-
�� 858
|
85
83
|
� 858
|
84
|
+
�� 858
|
85
|
+
म 858
|
86
86
|
� 853
|
87
|
-
य 836
|
88
|
-
�� 836
|
89
87
|
� 836
|
90
|
-
��
|
88
|
+
�� 836
|
89
|
+
य 836
|
91
90
|
प 829
|
91
|
+
�� 829
|
92
92
|
�� 809
|
93
93
|
�� 792
|
94
|
-
म� 792
|
95
94
|
��� 792
|
96
|
-
|
95
|
+
म� 792
|
97
96
|
स� 786
|
98
97
|
�� 786
|
98
|
+
��� 786
|
99
99
|
प� 785
|
100
100
|
��� 785
|
101
|
-
�� 752
|
102
|
-
क� 752
|
103
101
|
��� 752
|
102
|
+
क� 752
|
103
|
+
�� 752
|
104
104
|
र� 743
|
105
105
|
��� 743
|
106
106
|
�� 743
|
107
|
+
��_ 706
|
107
108
|
�_ 706
|
108
109
|
ा_ 706
|
109
|
-
��_ 706
|
110
110
|
� 705
|
111
|
-
�� 683
|
112
111
|
द 683
|
112
|
+
�� 683
|
113
113
|
�� 671
|
114
|
-
��� 663
|
115
114
|
द� 663
|
115
|
+
��� 663
|
116
|
+
ु 655
|
116
117
|
� 655
|
117
|
-
|
118
|
-
ु� 655
|
119
|
-
�� 655
|
118
|
+
��� 655
|
120
119
|
�� 655
|
120
|
+
ु� 655
|
121
|
+
ु� 655
|
121
122
|
��� 655
|
122
|
-
ु 655
|
123
|
-
��� 655
|
124
123
|
�� 655
|
125
|
-
��
|
124
|
+
�� 655
|
125
|
+
�� 649
|
126
|
+
े� 640
|
127
|
+
��� 640
|
126
128
|
क� 638
|
129
|
+
�� 638
|
127
130
|
��� 638
|
128
131
|
_स 634
|
129
132
|
_स� 634
|
130
|
-
��
|
131
|
-
य� 621
|
133
|
+
�� 626
|
132
134
|
�� 621
|
133
135
|
��� 621
|
134
|
-
|
135
|
-
|
136
|
-
|
136
|
+
य� 621
|
137
|
+
��� 617
|
138
|
+
े� 617
|
137
139
|
�� 613
|
140
|
+
��� 613
|
138
141
|
न� 613
|
139
|
-
�� 604
|
140
|
-
े� 595
|
141
|
-
��� 595
|
142
142
|
�� 568
|
143
|
-
� 568
|
144
143
|
ह 568
|
145
|
-
|
144
|
+
� 568
|
146
145
|
म� 538
|
147
146
|
��� 538
|
147
|
+
�� 538
|
148
148
|
े_ 532
|
149
|
-
��_ 532
|
150
149
|
�_ 532
|
151
|
-
��
|
150
|
+
��_ 532
|
152
151
|
ल 527
|
152
|
+
�� 527
|
153
153
|
� 527
|
154
154
|
_व� 526
|
155
155
|
_व 526
|
156
|
+
��� 524
|
156
157
|
�� 524
|
157
158
|
ह� 524
|
158
|
-
��� 524
|
159
159
|
�_ 522
|
160
160
|
� 485
|
161
|
+
��� 478
|
161
162
|
�� 478
|
162
163
|
स� 478
|
163
|
-
��� 478
|
164
|
-
�् 477
|
165
|
-
��् 477
|
166
164
|
�्� 477
|
165
|
+
��् 477
|
166
|
+
�् 477
|
167
167
|
�� 473
|
168
168
|
�र 472
|
169
169
|
��र 472
|
170
|
-
�� 462
|
171
170
|
�� 462
|
172
|
-
|
171
|
+
�� 462
|
173
172
|
_प� 461
|
174
|
-
|
173
|
+
_प 461
|
174
|
+
� 454
|
175
|
+
��� 454
|
175
176
|
श 454
|
176
177
|
�� 454
|
177
|
-
|
178
|
+
�� 454
|
178
179
|
य� 454
|
179
|
-
|
180
|
+
ी 453
|
180
181
|
�� 453
|
181
182
|
� 453
|
182
|
-
ी 453
|
183
|
-
�ि� 452
|
184
|
-
�ि 452
|
185
183
|
न� 452
|
186
|
-
��ि 452
|
187
184
|
��� 452
|
185
|
+
�ि� 452
|
186
|
+
��ि 452
|
187
|
+
�ि 452
|
188
188
|
ब 442
|
189
|
-
|
189
|
+
� 442
|
190
190
|
ब� 442
|
191
|
+
�� 442
|
191
192
|
��� 442
|
192
|
-
� 442
|
193
193
|
�� 442
|
194
|
-
�� 435
|
195
194
|
� 435
|
195
|
+
�� 435
|
196
196
|
ो 435
|
197
197
|
�� 432
|
198
|
-
ल� 432
|
199
198
|
��� 432
|
199
|
+
ल� 432
|
200
200
|
��य 427
|
201
201
|
�य 427
|
202
202
|
�र� 424
|
203
|
-
�� 424
|
204
203
|
ं 424
|
204
|
+
�� 424
|
205
205
|
��ा 413
|
206
206
|
�ा 413
|
207
|
-
ं� 412
|
208
|
-
ज 412
|
209
|
-
�� 412
|
210
207
|
� 412
|
208
|
+
�� 412
|
209
|
+
ं� 412
|
211
210
|
��� 412
|
211
|
+
ज 412
|
212
212
|
�� 407
|
213
213
|
�� 402
|
214
|
-
��� 401
|
215
214
|
ं� 401
|
216
|
-
|
215
|
+
��� 401
|
217
216
|
�र 399
|
218
|
-
|
217
|
+
��र 399
|
219
218
|
प� 397
|
219
|
+
��� 397
|
220
220
|
��_ 396
|
221
221
|
त_ 396
|
222
|
-
��� 388
|
223
222
|
प� 388
|
223
|
+
��� 388
|
224
224
|
_क� 382
|
225
225
|
_क 382
|
226
|
-
ज� 377
|
227
226
|
��� 377
|
228
227
|
�� 377
|
228
|
+
ज� 377
|
229
|
+
द� 371
|
229
230
|
�� 371
|
230
231
|
��� 371
|
231
|
-
द� 371
|
232
|
-
�क 362
|
233
232
|
��क 362
|
234
|
-
|
235
|
-
ष 361
|
233
|
+
�क 362
|
236
234
|
�� 361
|
237
|
-
|
235
|
+
ष 361
|
236
|
+
� 361
|
238
237
|
�� 354
|
239
238
|
श� 354
|
239
|
+
��� 354
|
240
240
|
�र� 349
|
241
|
+
�� 348
|
241
242
|
��� 348
|
242
243
|
ब� 348
|
243
|
-
�� 348
|
244
244
|
��� 344
|
245
|
-
�� 344
|
246
245
|
ो� 344
|
246
|
+
�� 344
|
247
247
|
�य� 343
|
248
248
|
�� 336
|
249
|
-
ध 336
|
250
249
|
� 336
|
250
|
+
ध 336
|
251
251
|
�ा_ 323
|
252
252
|
�� 322
|
253
253
|
��� 322
|
254
254
|
ो� 322
|
255
255
|
��_ 316
|
256
|
-
न_ 316
|
257
256
|
�_ 316
|
257
|
+
न_ 316
|
258
258
|
�� 315
|
259
259
|
ग 315
|
260
260
|
� 315
|
261
261
|
ल� 313
|
262
262
|
�� 313
|
263
263
|
��� 313
|
264
|
-
�� 306
|
265
264
|
��� 306
|
266
265
|
त� 306
|
266
|
+
�� 306
|
267
267
|
�� 300
|
268
|
-
�_ 299
|
269
268
|
��_ 299
|
270
269
|
र_ 299
|
271
|
-
|
270
|
+
�_ 299
|
272
271
|
� 298
|
272
|
+
�� 298
|
273
273
|
ष� 296
|
274
|
-
�� 296
|
275
274
|
��� 296
|
276
|
-
|
275
|
+
�� 296
|
277
276
|
�न 294
|
277
|
+
��न 294
|
278
278
|
द� 292
|
279
279
|
��� 292
|
280
|
-
ह� 287
|
281
|
-
�� 287
|
282
280
|
��� 287
|
283
|
-
|
281
|
+
�� 287
|
282
|
+
ह� 287
|
284
283
|
_ब� 286
|
284
|
+
_ब 286
|
285
|
+
भ� 283
|
285
286
|
�� 283
|
286
287
|
��� 283
|
287
|
-
भ� 283
|
288
288
|
भ 283
|
289
|
-
अ� 281
|
290
289
|
�� 281
|
291
|
-
��� 281
|
292
|
-
अ� 281
|
293
|
-
�� 281
|
294
290
|
�� 281
|
295
|
-
|
291
|
+
अ� 281
|
296
292
|
� 281
|
293
|
+
अ� 281
|
297
294
|
��� 281
|
298
|
-
|
295
|
+
��� 281
|
296
|
+
अ 281
|
297
|
+
�� 281
|
299
298
|
��� 277
|
300
299
|
�� 277
|
300
|
+
ध� 277
|
301
301
|
क_ 275
|
302
302
|
�_ 275
|
303
303
|
��_ 275
|
304
|
-
��र 274
|
305
304
|
�र 274
|
305
|
+
��र 274
|
306
306
|
�त 267
|
307
307
|
��त 267
|
308
|
+
ज� 266
|
308
309
|
�� 266
|
309
|
-
ी� 266
|
310
310
|
�� 266
|
311
|
-
��� 266
|
312
311
|
ी� 266
|
313
312
|
��� 266
|
314
|
-
ज� 266
|
315
313
|
�� 266
|
314
|
+
��� 266
|
316
315
|
��� 266
|
317
|
-
|
316
|
+
ी� 266
|
317
|
+
_अ� 263
|
318
318
|
ष� 263
|
319
|
+
��� 263
|
319
320
|
�� 263
|
320
321
|
_अ 263
|
321
|
-
_अ� 263
|
322
|
-
��् 261
|
323
322
|
�्� 261
|
324
323
|
�् 261
|
324
|
+
��् 261
|
325
325
|
�्� 256
|
326
|
-
��् 256
|
327
326
|
�् 256
|
327
|
+
��् 256
|
328
|
+
� 255
|
328
329
|
�� 255
|
329
330
|
च 255
|
330
|
-
� 255
|
331
|
-
ग� 254
|
332
|
-
�� 254
|
333
331
|
��� 254
|
334
|
-
|
332
|
+
ग� 254
|
335
333
|
�� 254
|
334
|
+
म� 254
|
335
|
+
�� 254
|
336
336
|
��� 254
|
337
|
-
�_ 248
|
338
337
|
ि_ 248
|
338
|
+
�_ 248
|
339
339
|
��_ 248
|
340
|
-
�ा 246
|
341
340
|
��ा 246
|
341
|
+
�ा 246
|
342
|
+
��� 245
|
342
343
|
च� 245
|
343
344
|
�� 245
|
344
|
-
|
345
|
+
ह� 237
|
345
346
|
��� 237
|
346
|
-
��त 237
|
347
347
|
�� 237
|
348
|
-
ह� 237
|
349
348
|
�त 237
|
350
|
-
|
351
|
-
�र� 233
|
349
|
+
��त 237
|
352
350
|
��� 233
|
353
351
|
श� 233
|
352
|
+
�र� 233
|
353
|
+
�� 233
|
354
354
|
ण 230
|
355
355
|
�� 230
|
356
356
|
� 230
|
357
357
|
��ा 225
|
358
358
|
�ा 225
|
359
359
|
�ा� 225
|
360
|
-
|
360
|
+
�् 220
|
361
361
|
��् 220
|
362
|
+
�ा 220
|
362
363
|
��ा 220
|
363
|
-
�् 220
|
364
364
|
�् 219
|
365
|
-
��् 219
|
366
365
|
�्� 219
|
366
|
+
��् 219
|
367
367
|
�_ 215
|
368
368
|
��_ 215
|
369
369
|
य_ 215
|
@@ -372,29 +372,29 @@ _अ
|
|
372
372
|
��ा 206
|
373
373
|
�्� 206
|
374
374
|
ग� 205
|
375
|
-
�� 205
|
376
375
|
��� 205
|
377
|
-
|
378
|
-
भ� 204
|
379
|
-
��� 204
|
380
|
-
�� 204
|
381
|
-
��ि 204
|
376
|
+
�� 205
|
382
377
|
_म 204
|
383
378
|
� 204
|
379
|
+
��� 204
|
380
|
+
�� 204
|
384
381
|
�ि 204
|
382
|
+
भ� 204
|
383
|
+
�क� 204
|
384
|
+
��ि 204
|
385
385
|
ए 204
|
386
386
|
_म� 204
|
387
|
-
�े 200
|
388
387
|
��े 200
|
388
|
+
�े 200
|
389
389
|
�त� 199
|
390
|
-
��� 198
|
391
|
-
�� 198
|
392
390
|
च� 198
|
391
|
+
�� 198
|
392
|
+
��� 198
|
393
393
|
�त_ 195
|
394
|
+
��� 194
|
394
395
|
�� 194
|
395
396
|
�� 194
|
397
|
+
आ� 194
|
396
398
|
आ� 194
|
397
|
-
�� 194
|
398
399
|
� 194
|
399
|
-
|
400
|
-
��� 194
|
400
|
+
�� 194
|