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
|
+
� 44428
|
2
|
+
� 33131
|
3
|
+
� 31240
|
4
|
+
� 14531
|
5
|
+
� 13188
|
6
|
+
_ 12544
|
7
|
+
் 7272
|
8
|
+
� 7272
|
9
|
+
�� 7272
|
10
|
+
�� 5073
|
11
|
+
்� 5073
|
12
|
+
��� 5073
|
13
|
+
��� 5073
|
14
|
+
்� 5073
|
15
|
+
�� 5073
|
16
|
+
_� 4880
|
17
|
+
_� 4880
|
18
|
+
� 3855
|
19
|
+
�� 3855
|
20
|
+
க 3855
|
21
|
+
�� 3598
|
22
|
+
க� 3598
|
23
|
+
��� 3598
|
24
|
+
�� 3518
|
25
|
+
� 3518
|
26
|
+
ி 3518
|
27
|
+
�� 3248
|
28
|
+
ி� 3248
|
29
|
+
��� 3248
|
30
|
+
ி� 3248
|
31
|
+
��� 3248
|
32
|
+
�� 3248
|
33
|
+
ு 3027
|
34
|
+
� 3027
|
35
|
+
�� 3027
|
36
|
+
� 2754
|
37
|
+
த 2754
|
38
|
+
�� 2754
|
39
|
+
�� 2602
|
40
|
+
த� 2602
|
41
|
+
��� 2602
|
42
|
+
�� 2395
|
43
|
+
� 2395
|
44
|
+
ப 2395
|
45
|
+
ப� 2388
|
46
|
+
��� 2388
|
47
|
+
�� 2388
|
48
|
+
��� 2074
|
49
|
+
�� 2074
|
50
|
+
�� 2074
|
51
|
+
��� 2074
|
52
|
+
ு� 2074
|
53
|
+
ு� 2074
|
54
|
+
� 2009
|
55
|
+
�� 2009
|
56
|
+
ட 2009
|
57
|
+
�� 1919
|
58
|
+
்_ 1919
|
59
|
+
��_ 1919
|
60
|
+
��� 1919
|
61
|
+
ட� 1919
|
62
|
+
�_ 1919
|
63
|
+
க� 1903
|
64
|
+
��� 1903
|
65
|
+
�� 1903
|
66
|
+
�� 1891
|
67
|
+
ம 1891
|
68
|
+
�� 1887
|
69
|
+
ம� 1887
|
70
|
+
��� 1887
|
71
|
+
�� 1695
|
72
|
+
க� 1695
|
73
|
+
��� 1695
|
74
|
+
ர 1564
|
75
|
+
�� 1564
|
76
|
+
� 1564
|
77
|
+
��� 1540
|
78
|
+
�� 1540
|
79
|
+
ர� 1540
|
80
|
+
�� 1531
|
81
|
+
ா 1531
|
82
|
+
� 1531
|
83
|
+
� 1475
|
84
|
+
�� 1475
|
85
|
+
வ 1475
|
86
|
+
வ� 1470
|
87
|
+
�� 1470
|
88
|
+
��� 1470
|
89
|
+
ம� 1405
|
90
|
+
��� 1405
|
91
|
+
�� 1405
|
92
|
+
�� 1400
|
93
|
+
��� 1400
|
94
|
+
த� 1400
|
95
|
+
��க 1382
|
96
|
+
�க 1382
|
97
|
+
�� 1371
|
98
|
+
ா� 1371
|
99
|
+
�� 1371
|
100
|
+
��� 1371
|
101
|
+
��� 1371
|
102
|
+
ா� 1371
|
103
|
+
ய 1343
|
104
|
+
�� 1343
|
105
|
+
��� 1335
|
106
|
+
ப� 1335
|
107
|
+
�� 1335
|
108
|
+
�க� 1329
|
109
|
+
� 1249
|
110
|
+
�� 1241
|
111
|
+
ை 1241
|
112
|
+
�� 1239
|
113
|
+
ற 1239
|
114
|
+
� 1239
|
115
|
+
�� 1237
|
116
|
+
� 1237
|
117
|
+
ல 1237
|
118
|
+
�� 1202
|
119
|
+
��� 1202
|
120
|
+
த� 1202
|
121
|
+
��� 1197
|
122
|
+
� 1197
|
123
|
+
ற� 1197
|
124
|
+
�� 1197
|
125
|
+
�� 1197
|
126
|
+
ன 1197
|
127
|
+
ய� 1196
|
128
|
+
��� 1196
|
129
|
+
�� 1196
|
130
|
+
�� 1177
|
131
|
+
��� 1177
|
132
|
+
ல� 1177
|
133
|
+
ள 1143
|
134
|
+
� 1143
|
135
|
+
�� 1143
|
136
|
+
��� 1097
|
137
|
+
ட� 1097
|
138
|
+
�� 1097
|
139
|
+
��� 1091
|
140
|
+
வ� 1091
|
141
|
+
�� 1091
|
142
|
+
��� 1087
|
143
|
+
�� 1087
|
144
|
+
ள� 1087
|
145
|
+
ப� 1053
|
146
|
+
�� 1053
|
147
|
+
��� 1053
|
148
|
+
ர� 1042
|
149
|
+
�� 1042
|
150
|
+
��� 1042
|
151
|
+
��� 1020
|
152
|
+
�� 1020
|
153
|
+
ன� 1020
|
154
|
+
�் 929
|
155
|
+
��் 929
|
156
|
+
�ப 921
|
157
|
+
��ப 921
|
158
|
+
�ப� 916
|
159
|
+
��� 890
|
160
|
+
ய� 890
|
161
|
+
�� 890
|
162
|
+
��் 876
|
163
|
+
�் 876
|
164
|
+
ல� 863
|
165
|
+
�� 863
|
166
|
+
��� 863
|
167
|
+
�்� 860
|
168
|
+
__ 836
|
169
|
+
��� 822
|
170
|
+
�� 822
|
171
|
+
ட� 822
|
172
|
+
��த 816
|
173
|
+
�த 816
|
174
|
+
�� 810
|
175
|
+
�� 810
|
176
|
+
��� 803
|
177
|
+
ை� 803
|
178
|
+
ை� 803
|
179
|
+
��� 803
|
180
|
+
� 763
|
181
|
+
ச 763
|
182
|
+
�� 763
|
183
|
+
�� 750
|
184
|
+
ச� 750
|
185
|
+
��� 750
|
186
|
+
ற� 749
|
187
|
+
ன� 749
|
188
|
+
��� 749
|
189
|
+
�� 749
|
190
|
+
��� 749
|
191
|
+
�� 749
|
192
|
+
��் 736
|
193
|
+
�் 736
|
194
|
+
ு_ 701
|
195
|
+
�_ 701
|
196
|
+
��_ 701
|
197
|
+
�த� 697
|
198
|
+
�்� 694
|
199
|
+
�் 652
|
200
|
+
��் 652
|
201
|
+
�்_ 646
|
202
|
+
�ட 645
|
203
|
+
��ட 645
|
204
|
+
��் 630
|
205
|
+
�் 630
|
206
|
+
�� 627
|
207
|
+
� 627
|
208
|
+
�� 627
|
209
|
+
�ு 625
|
210
|
+
��ு 625
|
211
|
+
��� 622
|
212
|
+
�� 622
|
213
|
+
ள� 622
|
214
|
+
� 619
|
215
|
+
��ய 609
|
216
|
+
�ய 609
|
217
|
+
�ள� 584
|
218
|
+
�ள 584
|
219
|
+
��ள 584
|
220
|
+
_ப 574
|
221
|
+
_ப� 574
|
222
|
+
�ம 568
|
223
|
+
��ம 568
|
224
|
+
�ட� 568
|
225
|
+
�ம� 567
|
226
|
+
�� 562
|
227
|
+
�� 562
|
228
|
+
_க� 558
|
229
|
+
_க 558
|
230
|
+
��� 556
|
231
|
+
�� 556
|
232
|
+
ந 556
|
233
|
+
ந� 556
|
234
|
+
�� 556
|
235
|
+
� 556
|
236
|
+
��ி 549
|
237
|
+
�ி 549
|
238
|
+
_வ� 546
|
239
|
+
_வ 546
|
240
|
+
��் 536
|
241
|
+
�் 536
|
242
|
+
�ய� 529
|
243
|
+
��ி 525
|
244
|
+
�ி 525
|
245
|
+
�ி� 524
|
246
|
+
�் 515
|
247
|
+
��் 515
|
248
|
+
��க 507
|
249
|
+
�க 507
|
250
|
+
�ி 503
|
251
|
+
�க� 503
|
252
|
+
��ி 503
|
253
|
+
��் 500
|
254
|
+
�் 500
|
255
|
+
��� 498
|
256
|
+
ர� 498
|
257
|
+
�� 498
|
258
|
+
_ம 497
|
259
|
+
_ம� 497
|
260
|
+
�ி� 496
|
261
|
+
�ி� 493
|
262
|
+
�்� 488
|
263
|
+
ம� 482
|
264
|
+
�� 482
|
265
|
+
��� 482
|
266
|
+
�ு 474
|
267
|
+
��ு 474
|
268
|
+
��� 465
|
269
|
+
�்� 465
|
270
|
+
�� 465
|
271
|
+
ள� 465
|
272
|
+
ற� 448
|
273
|
+
��� 448
|
274
|
+
�� 448
|
275
|
+
��ி 434
|
276
|
+
�ி 434
|
277
|
+
�ற 424
|
278
|
+
��ற 424
|
279
|
+
� 421
|
280
|
+
��� 421
|
281
|
+
அ� 421
|
282
|
+
அ� 421
|
283
|
+
�� 421
|
284
|
+
�� 421
|
285
|
+
��� 421
|
286
|
+
�� 421
|
287
|
+
அ 421
|
288
|
+
��ல 416
|
289
|
+
�ல 416
|
290
|
+
_அ 412
|
291
|
+
_அ� 412
|
292
|
+
� 411
|
293
|
+
ண 411
|
294
|
+
�� 411
|
295
|
+
�்_ 407
|
296
|
+
ண� 406
|
297
|
+
�� 406
|
298
|
+
��� 406
|
299
|
+
. 403
|
300
|
+
��ு 403
|
301
|
+
�ு 403
|
302
|
+
�ா 402
|
303
|
+
��ா 402
|
304
|
+
�ி� 393
|
305
|
+
�ற� 387
|
306
|
+
��க 387
|
307
|
+
�க 387
|
308
|
+
�_ 386
|
309
|
+
ை_ 385
|
310
|
+
��_ 385
|
311
|
+
�க� 383
|
312
|
+
�ு� 383
|
313
|
+
��் 382
|
314
|
+
�் 382
|
315
|
+
�ல� 381
|
316
|
+
வ� 379
|
317
|
+
��� 379
|
318
|
+
�� 379
|
319
|
+
��� 378
|
320
|
+
ச� 378
|
321
|
+
�� 378
|
322
|
+
ச� 372
|
323
|
+
��� 372
|
324
|
+
�� 372
|
325
|
+
_ச 368
|
326
|
+
_ச� 368
|
327
|
+
�்� 365
|
328
|
+
��� 362
|
329
|
+
�� 362
|
330
|
+
�ய 362
|
331
|
+
ெ 362
|
332
|
+
ெ� 362
|
333
|
+
��� 362
|
334
|
+
��ய 362
|
335
|
+
ெ� 362
|
336
|
+
��ப 361
|
337
|
+
��் 361
|
338
|
+
�ப 361
|
339
|
+
�் 361
|
340
|
+
�ப� 361
|
341
|
+
�்� 360
|
342
|
+
��� 359
|
343
|
+
�� 359
|
344
|
+
ந� 359
|
345
|
+
��ு 357
|
346
|
+
�ு 357
|
347
|
+
_த� 347
|
348
|
+
_த 347
|
349
|
+
�்� 340
|
350
|
+
��ன 329
|
351
|
+
�ன 329
|
352
|
+
�ன� 328
|
353
|
+
�� 318
|
354
|
+
�� 318
|
355
|
+
� 318
|
356
|
+
�ட 315
|
357
|
+
��ட 315
|
358
|
+
ல� 314
|
359
|
+
�� 314
|
360
|
+
��� 314
|
361
|
+
ே 312
|
362
|
+
�� 312
|
363
|
+
�ட� 312
|
364
|
+
._ 308
|
365
|
+
ொ� 307
|
366
|
+
��� 307
|
367
|
+
இ 307
|
368
|
+
��� 307
|
369
|
+
��� 307
|
370
|
+
�� 307
|
371
|
+
இ� 307
|
372
|
+
இ� 307
|
373
|
+
�� 307
|
374
|
+
ொ 307
|
375
|
+
��� 307
|
376
|
+
ொ� 307
|
377
|
+
�� 306
|
378
|
+
��� 306
|
379
|
+
ய� 306
|
380
|
+
�ய� 303
|
381
|
+
��� 301
|
382
|
+
ண� 301
|
383
|
+
�� 301
|
384
|
+
�ு 300
|
385
|
+
��ு 300
|
386
|
+
� 292
|
387
|
+
ீ 290
|
388
|
+
�� 290
|
389
|
+
_இ 288
|
390
|
+
_இ� 288
|
391
|
+
ீ� 284
|
392
|
+
��� 284
|
393
|
+
�� 284
|
394
|
+
ீ� 284
|
395
|
+
��� 284
|
396
|
+
�� 284
|
397
|
+
�த 283
|
398
|
+
��த 283
|
399
|
+
��க 283
|
400
|
+
�க 283
|