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
|
+
� 73879
|
2
|
+
_ 40960
|
3
|
+
� 26019
|
4
|
+
_� 13043
|
5
|
+
� 11448
|
6
|
+
а 11447
|
7
|
+
и 10454
|
8
|
+
� 10454
|
9
|
+
е 8498
|
10
|
+
� 8498
|
11
|
+
� 8354
|
12
|
+
о 8353
|
13
|
+
т 7459
|
14
|
+
� 7459
|
15
|
+
� 7359
|
16
|
+
н 7359
|
17
|
+
н� 6078
|
18
|
+
�� 6078
|
19
|
+
� 5765
|
20
|
+
р 5460
|
21
|
+
т� 5390
|
22
|
+
�� 5390
|
23
|
+
� 5070
|
24
|
+
с 5070
|
25
|
+
�� 4637
|
26
|
+
р� 4636
|
27
|
+
�� 4209
|
28
|
+
е� 4209
|
29
|
+
� 4121
|
30
|
+
в 4119
|
31
|
+
�� 4029
|
32
|
+
а� 4029
|
33
|
+
�_ 3969
|
34
|
+
а_ 3968
|
35
|
+
о� 3839
|
36
|
+
�� 3839
|
37
|
+
и� 3688
|
38
|
+
�� 3688
|
39
|
+
� 3685
|
40
|
+
к 3685
|
41
|
+
_� 3683
|
42
|
+
и� 3582
|
43
|
+
�� 3582
|
44
|
+
� 3450
|
45
|
+
л 3450
|
46
|
+
д 3071
|
47
|
+
� 3071
|
48
|
+
�� 2942
|
49
|
+
а� 2942
|
50
|
+
�� 2907
|
51
|
+
л� 2907
|
52
|
+
в� 2905
|
53
|
+
�� 2905
|
54
|
+
�� 2813
|
55
|
+
с� 2813
|
56
|
+
к� 2793
|
57
|
+
�� 2793
|
58
|
+
�_ 2637
|
59
|
+
и_ 2637
|
60
|
+
__ 2576
|
61
|
+
п 2507
|
62
|
+
� 2507
|
63
|
+
д� 2355
|
64
|
+
�� 2355
|
65
|
+
�� 2274
|
66
|
+
о� 2274
|
67
|
+
на 2261
|
68
|
+
�а 2261
|
69
|
+
з 2176
|
70
|
+
� 2176
|
71
|
+
е_ 2116
|
72
|
+
�_ 2116
|
73
|
+
я 2001
|
74
|
+
� 2001
|
75
|
+
�� 1974
|
76
|
+
с� 1974
|
77
|
+
�_ 1964
|
78
|
+
о_ 1964
|
79
|
+
_с 1943
|
80
|
+
м 1872
|
81
|
+
� 1872
|
82
|
+
�� 1806
|
83
|
+
е� 1806
|
84
|
+
з� 1756
|
85
|
+
�� 1756
|
86
|
+
_н 1747
|
87
|
+
_н� 1660
|
88
|
+
ни 1604
|
89
|
+
�и 1604
|
90
|
+
ъ 1598
|
91
|
+
� 1598
|
92
|
+
м� 1546
|
93
|
+
�� 1546
|
94
|
+
г 1534
|
95
|
+
� 1534
|
96
|
+
ст 1463
|
97
|
+
�т 1463
|
98
|
+
, 1462
|
99
|
+
п� 1461
|
100
|
+
�� 1461
|
101
|
+
�т 1457
|
102
|
+
ат 1457
|
103
|
+
,_ 1442
|
104
|
+
_п 1435
|
105
|
+
то 1405
|
106
|
+
�о 1405
|
107
|
+
на_ 1376
|
108
|
+
�а_ 1376
|
109
|
+
ра 1372
|
110
|
+
�а 1372
|
111
|
+
�е 1359
|
112
|
+
те 1359
|
113
|
+
_и 1344
|
114
|
+
�н 1332
|
115
|
+
ан 1332
|
116
|
+
�� 1296
|
117
|
+
г� 1296
|
118
|
+
_на 1296
|
119
|
+
�а 1264
|
120
|
+
та 1264
|
121
|
+
� 1235
|
122
|
+
б 1234
|
123
|
+
�н 1178
|
124
|
+
ен 1178
|
125
|
+
� 1167
|
126
|
+
у 1165
|
127
|
+
�_ 1161
|
128
|
+
т_ 1161
|
129
|
+
ия 1149
|
130
|
+
�я 1149
|
131
|
+
ч 1105
|
132
|
+
� 1105
|
133
|
+
_в 1095
|
134
|
+
ат� 1091
|
135
|
+
�т� 1091
|
136
|
+
ит 1082
|
137
|
+
�а 1082
|
138
|
+
ва 1082
|
139
|
+
�т 1082
|
140
|
+
ре 1077
|
141
|
+
�е 1077
|
142
|
+
ч� 1059
|
143
|
+
�� 1059
|
144
|
+
_с� 1057
|
145
|
+
�� 1037
|
146
|
+
п� 1037
|
147
|
+
�н� 1034
|
148
|
+
ан� 1034
|
149
|
+
�т� 1034
|
150
|
+
ит� 1034
|
151
|
+
. 1032
|
152
|
+
�а� 1015
|
153
|
+
ра� 1015
|
154
|
+
но 1010
|
155
|
+
�о 1010
|
156
|
+
�т� 1007
|
157
|
+
ст� 1007
|
158
|
+
_о 957
|
159
|
+
�� 927
|
160
|
+
ъ� 927
|
161
|
+
ки 919
|
162
|
+
�и 919
|
163
|
+
_д 889
|
164
|
+
�е� 882
|
165
|
+
то_ 882
|
166
|
+
ре� 882
|
167
|
+
�о_ 882
|
168
|
+
�и 874
|
169
|
+
ри 874
|
170
|
+
ли 873
|
171
|
+
�и 873
|
172
|
+
�к 872
|
173
|
+
ск 872
|
174
|
+
�т 863
|
175
|
+
от 863
|
176
|
+
пр 857
|
177
|
+
�р 857
|
178
|
+
ск� 853
|
179
|
+
�к� 853
|
180
|
+
�р� 840
|
181
|
+
пр� 840
|
182
|
+
�а 832
|
183
|
+
ка 832
|
184
|
+
�� 816
|
185
|
+
н� 816
|
186
|
+
ти 802
|
187
|
+
�и 802
|
188
|
+
�д 799
|
189
|
+
ед 799
|
190
|
+
�о 778
|
191
|
+
ко 778
|
192
|
+
т� 769
|
193
|
+
�� 769
|
194
|
+
�о 767
|
195
|
+
по 767
|
196
|
+
� 756
|
197
|
+
ц 756
|
198
|
+
не 755
|
199
|
+
�е 755
|
200
|
+
�те 744
|
201
|
+
�а 736
|
202
|
+
да 736
|
203
|
+
�� 731
|
204
|
+
б� 731
|
205
|
+
_п� 730
|
206
|
+
_и_ 725
|
207
|
+
_к 720
|
208
|
+
_с� 716
|
209
|
+
_е 711
|
210
|
+
у� 706
|
211
|
+
�� 706
|
212
|
+
ц� 704
|
213
|
+
�� 704
|
214
|
+
_п� 703
|
215
|
+
�н� 698
|
216
|
+
ен� 698
|
217
|
+
�е_ 684
|
218
|
+
те_ 684
|
219
|
+
�р 683
|
220
|
+
ар 683
|
221
|
+
ов 682
|
222
|
+
�в 682
|
223
|
+
._ 676
|
224
|
+
ъ� 671
|
225
|
+
_о� 671
|
226
|
+
�� 671
|
227
|
+
й 670
|
228
|
+
� 670
|
229
|
+
_д� 670
|
230
|
+
�о 667
|
231
|
+
ро 667
|
232
|
+
ед� 659
|
233
|
+
�д� 659
|
234
|
+
в� 643
|
235
|
+
�� 643
|
236
|
+
я_ 640
|
237
|
+
�_ 640
|
238
|
+
�� 635
|
239
|
+
р� 634
|
240
|
+
к� 628
|
241
|
+
�� 628
|
242
|
+
ж 627
|
243
|
+
� 627
|
244
|
+
_пр 620
|
245
|
+
ет 617
|
246
|
+
�т 617
|
247
|
+
та_ 611
|
248
|
+
�а_ 611
|
249
|
+
ик 599
|
250
|
+
�к 599
|
251
|
+
ов� 598
|
252
|
+
�в� 598
|
253
|
+
ж� 596
|
254
|
+
�� 596
|
255
|
+
_к� 591
|
256
|
+
ни� 581
|
257
|
+
�и� 581
|
258
|
+
_и� 580
|
259
|
+
_по 568
|
260
|
+
за 565
|
261
|
+
�а 565
|
262
|
+
ия_ 562
|
263
|
+
�� 562
|
264
|
+
�я_ 562
|
265
|
+
я� 562
|
266
|
+
ве 561
|
267
|
+
�е 561
|
268
|
+
ел 559
|
269
|
+
�л 559
|
270
|
+
�т� 558
|
271
|
+
ет� 558
|
272
|
+
се 551
|
273
|
+
�е 551
|
274
|
+
�р 535
|
275
|
+
ор 535
|
276
|
+
�в 527
|
277
|
+
ав 527
|
278
|
+
ди 527
|
279
|
+
�и 527
|
280
|
+
�н 523
|
281
|
+
ин 523
|
282
|
+
�_ 523
|
283
|
+
�ки 523
|
284
|
+
в_ 521
|
285
|
+
из 518
|
286
|
+
�з 518
|
287
|
+
�е 507
|
288
|
+
ле 507
|
289
|
+
�� 506
|
290
|
+
д� 506
|
291
|
+
�о� 506
|
292
|
+
ро� 506
|
293
|
+
ни_ 501
|
294
|
+
�и_ 501
|
295
|
+
_з 500
|
296
|
+
_з� 499
|
297
|
+
�� 499
|
298
|
+
я� 499
|
299
|
+
б� 497
|
300
|
+
�� 497
|
301
|
+
�та 497
|
302
|
+
ко� 496
|
303
|
+
�о� 496
|
304
|
+
_от 496
|
305
|
+
�о 486
|
306
|
+
во 486
|
307
|
+
ци 485
|
308
|
+
�и 485
|
309
|
+
ле� 462
|
310
|
+
�е� 462
|
311
|
+
га 461
|
312
|
+
�а 461
|
313
|
+
�с 459
|
314
|
+
ос 459
|
315
|
+
�р 454
|
316
|
+
тр 454
|
317
|
+
од 448
|
318
|
+
�д 448
|
319
|
+
ол 446
|
320
|
+
�л 446
|
321
|
+
ла 446
|
322
|
+
�а 446
|
323
|
+
_р 446
|
324
|
+
на� 445
|
325
|
+
�а� 445
|
326
|
+
_т 444
|
327
|
+
�и� 440
|
328
|
+
ни� 440
|
329
|
+
�р� 437
|
330
|
+
ор� 437
|
331
|
+
�к� 435
|
332
|
+
�р 435
|
333
|
+
ер 435
|
334
|
+
ик� 435
|
335
|
+
_в_ 435
|
336
|
+
ри� 435
|
337
|
+
�и� 435
|
338
|
+
ар� 431
|
339
|
+
�р� 431
|
340
|
+
ма 428
|
341
|
+
�с 428
|
342
|
+
�а 428
|
343
|
+
ес 428
|
344
|
+
�е� 426
|
345
|
+
те� 426
|
346
|
+
�л� 424
|
347
|
+
_р� 424
|
348
|
+
ел� 424
|
349
|
+
об 424
|
350
|
+
�б 424
|
351
|
+
�в� 422
|
352
|
+
ав� 422
|
353
|
+
_за 416
|
354
|
+
тр� 415
|
355
|
+
�р� 415
|
356
|
+
�л 409
|
357
|
+
ал 409
|
358
|
+
�� 407
|
359
|
+
л� 407
|
360
|
+
_м 406
|
361
|
+
от_ 405
|
362
|
+
�т_ 405
|
363
|
+
� 404
|
364
|
+
щ 400
|
365
|
+
�а_ 399
|
366
|
+
че 399
|
367
|
+
ва_ 399
|
368
|
+
�е 399
|
369
|
+
�з 398
|
370
|
+
ез 398
|
371
|
+
�ни 398
|
372
|
+
но_ 397
|
373
|
+
�о_ 397
|
374
|
+
ви 395
|
375
|
+
�и 395
|
376
|
+
н_ 393
|
377
|
+
�_ 393
|
378
|
+
из� 392
|
379
|
+
�з� 392
|
380
|
+
ят 390
|
381
|
+
�т 390
|
382
|
+
ме 390
|
383
|
+
�е 390
|
384
|
+
_се 388
|
385
|
+
�� 387
|
386
|
+
у� 387
|
387
|
+
�е 385
|
388
|
+
ие 385
|
389
|
+
- 383
|
390
|
+
�л 374
|
391
|
+
ъл 374
|
392
|
+
�ан 372
|
393
|
+
�о� 372
|
394
|
+
по� 372
|
395
|
+
�е 368
|
396
|
+
де 368
|
397
|
+
ъл� 365
|
398
|
+
да_ 365
|
399
|
+
�а_ 365
|
400
|
+
�и� 365
|