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
|
+
_ 8148
|
2
|
+
� 2389
|
3
|
+
� 1982
|
4
|
+
� 1894
|
5
|
+
� 1872
|
6
|
+
� 1520
|
7
|
+
_� 1012
|
8
|
+
_� 815
|
9
|
+
_� 802
|
10
|
+
_� 784
|
11
|
+
_� 635
|
12
|
+
� 514
|
13
|
+
� 429
|
14
|
+
,_ 421
|
15
|
+
, 421
|
16
|
+
� 375
|
17
|
+
� 374
|
18
|
+
� 372
|
19
|
+
� 371
|
20
|
+
� 362
|
21
|
+
� 359
|
22
|
+
� 354
|
23
|
+
� 354
|
24
|
+
� 353
|
25
|
+
� 351
|
26
|
+
� 348
|
27
|
+
� 343
|
28
|
+
� 338
|
29
|
+
� 335
|
30
|
+
� 330
|
31
|
+
� 329
|
32
|
+
� 327
|
33
|
+
� 324
|
34
|
+
� 324
|
35
|
+
� 321
|
36
|
+
� 319
|
37
|
+
� 318
|
38
|
+
� 317
|
39
|
+
� 315
|
40
|
+
� 313
|
41
|
+
� 310
|
42
|
+
� 308
|
43
|
+
� 307
|
44
|
+
� 306
|
45
|
+
� 304
|
46
|
+
� 304
|
47
|
+
� 302
|
48
|
+
� 301
|
49
|
+
� 300
|
50
|
+
� 299
|
51
|
+
� 299
|
52
|
+
� 295
|
53
|
+
� 292
|
54
|
+
� 289
|
55
|
+
� 285
|
56
|
+
� 282
|
57
|
+
� 280
|
58
|
+
� 277
|
59
|
+
� 275
|
60
|
+
� 269
|
61
|
+
� 269
|
62
|
+
� 262
|
63
|
+
� 260
|
64
|
+
� 260
|
65
|
+
� 260
|
66
|
+
� 255
|
67
|
+
� 254
|
68
|
+
� 252
|
69
|
+
� 247
|
70
|
+
� 246
|
71
|
+
� 246
|
72
|
+
� 229
|
73
|
+
� 224
|
74
|
+
� 222
|
75
|
+
� 220
|
76
|
+
� 197
|
77
|
+
� 196
|
78
|
+
� 102
|
79
|
+
� 102
|
80
|
+
�_ 96
|
81
|
+
�_ 91
|
82
|
+
�_ 87
|
83
|
+
�_ 86
|
84
|
+
�_ 85
|
85
|
+
�_ 84
|
86
|
+
� 84
|
87
|
+
� 83
|
88
|
+
�_ 82
|
89
|
+
� 80
|
90
|
+
�_ 80
|
91
|
+
�_ 79
|
92
|
+
� 79
|
93
|
+
�_ 79
|
94
|
+
� 78
|
95
|
+
�_ 76
|
96
|
+
� 76
|
97
|
+
�_ 75
|
98
|
+
� 75
|
99
|
+
� 75
|
100
|
+
�_ 73
|
101
|
+
� 72
|
102
|
+
�_ 72
|
103
|
+
�_ 72
|
104
|
+
�_ 72
|
105
|
+
�_ 71
|
106
|
+
� 71
|
107
|
+
� 71
|
108
|
+
�_ 71
|
109
|
+
� 70
|
110
|
+
�_ 70
|
111
|
+
� 70
|
112
|
+
� 69
|
113
|
+
�_ 69
|
114
|
+
� 69
|
115
|
+
� 68
|
116
|
+
� 68
|
117
|
+
� 68
|
118
|
+
� 67
|
119
|
+
�_ 67
|
120
|
+
� 67
|
121
|
+
�_ 67
|
122
|
+
� 67
|
123
|
+
� 66
|
124
|
+
� 65
|
125
|
+
�_ 65
|
126
|
+
� 65
|
127
|
+
�_ 65
|
128
|
+
� 64
|
129
|
+
�_ 63
|
130
|
+
_� 63
|
131
|
+
� 62
|
132
|
+
� 62
|
133
|
+
_� 61
|
134
|
+
�_ 61
|
135
|
+
�_ 61
|
136
|
+
�_ 59
|
137
|
+
� 59
|
138
|
+
�_ 58
|
139
|
+
� 58
|
140
|
+
� 58
|
141
|
+
�_ 58
|
142
|
+
� 58
|
143
|
+
�_ 58
|
144
|
+
� 58
|
145
|
+
� 58
|
146
|
+
� 57
|
147
|
+
� 57
|
148
|
+
� 57
|
149
|
+
� 56
|
150
|
+
� 55
|
151
|
+
�_ 55
|
152
|
+
�_ 54
|
153
|
+
� 54
|
154
|
+
�_ 54
|
155
|
+
�_ 54
|
156
|
+
�_ 53
|
157
|
+
� 53
|
158
|
+
� 53
|
159
|
+
�_ 53
|
160
|
+
� 53
|
161
|
+
� 53
|
162
|
+
� 53
|
163
|
+
�_ 52
|
164
|
+
� 51
|
165
|
+
� 51
|
166
|
+
� 51
|
167
|
+
� 51
|
168
|
+
� 51
|
169
|
+
�� 51
|
170
|
+
� 51
|
171
|
+
� 50
|
172
|
+
� 50
|
173
|
+
� 50
|
174
|
+
� 50
|
175
|
+
�_ 50
|
176
|
+
� 50
|
177
|
+
� 49
|
178
|
+
� 49
|
179
|
+
� 49
|
180
|
+
�� 49
|
181
|
+
� 49
|
182
|
+
� 49
|
183
|
+
� 49
|
184
|
+
_� 49
|
185
|
+
�_ 48
|
186
|
+
� 48
|
187
|
+
� 48
|
188
|
+
�_ 48
|
189
|
+
� 48
|
190
|
+
� 48
|
191
|
+
�_ 48
|
192
|
+
� 48
|
193
|
+
�� 47
|
194
|
+
� 47
|
195
|
+
_� 46
|
196
|
+
�_ 46
|
197
|
+
� 46
|
198
|
+
� 46
|
199
|
+
�_ 46
|
200
|
+
� 45
|
201
|
+
� 45
|
202
|
+
� 45
|
203
|
+
�_ 45
|
204
|
+
� 45
|
205
|
+
�� 45
|
206
|
+
�_ 45
|
207
|
+
�_ 45
|
208
|
+
�_ 44
|
209
|
+
�_ 44
|
210
|
+
� 44
|
211
|
+
�_ 44
|
212
|
+
� 44
|
213
|
+
�� 44
|
214
|
+
_� 44
|
215
|
+
� 43
|
216
|
+
� 43
|
217
|
+
� 43
|
218
|
+
_� 43
|
219
|
+
� 43
|
220
|
+
� 43
|
221
|
+
� 42
|
222
|
+
�� 42
|
223
|
+
� 42
|
224
|
+
� 42
|
225
|
+
�_ 42
|
226
|
+
_� 42
|
227
|
+
�� 42
|
228
|
+
� 42
|
229
|
+
_� 42
|
230
|
+
� 42
|
231
|
+
_� 41
|
232
|
+
� 41
|
233
|
+
� 41
|
234
|
+
� 41
|
235
|
+
�_ 41
|
236
|
+
� 41
|
237
|
+
�_ 40
|
238
|
+
� 40
|
239
|
+
�_ 40
|
240
|
+
� 40
|
241
|
+
�� 40
|
242
|
+
� 40
|
243
|
+
�� 40
|
244
|
+
� 39
|
245
|
+
� 39
|
246
|
+
�� 39
|
247
|
+
� 39
|
248
|
+
�� 39
|
249
|
+
�� 39
|
250
|
+
� 39
|
251
|
+
� 39
|
252
|
+
� 39
|
253
|
+
� 38
|
254
|
+
� 38
|
255
|
+
� 38
|
256
|
+
_� 38
|
257
|
+
� 38
|
258
|
+
� 38
|
259
|
+
_� 38
|
260
|
+
�_ 38
|
261
|
+
� 37
|
262
|
+
�_ 37
|
263
|
+
� 37
|
264
|
+
�_ 37
|
265
|
+
� 37
|
266
|
+
� 36
|
267
|
+
� 36
|
268
|
+
� 36
|
269
|
+
� 36
|
270
|
+
_� 36
|
271
|
+
�� 36
|
272
|
+
� 36
|
273
|
+
� 36
|
274
|
+
� 36
|
275
|
+
� 36
|
276
|
+
� 36
|
277
|
+
� 36
|
278
|
+
� 35
|
279
|
+
� 35
|
280
|
+
�� 35
|
281
|
+
� 35
|
282
|
+
_� 35
|
283
|
+
� 35
|
284
|
+
� 35
|
285
|
+
�_ 34
|
286
|
+
_� 34
|
287
|
+
� 34
|
288
|
+
� 34
|
289
|
+
� 34
|
290
|
+
� 34
|
291
|
+
�� 34
|
292
|
+
_� 34
|
293
|
+
�� 34
|
294
|
+
� 33
|
295
|
+
�� 33
|
296
|
+
�_ 33
|
297
|
+
� 33
|
298
|
+
_� 33
|
299
|
+
_� 33
|
300
|
+
� 33
|
301
|
+
� 33
|
302
|
+
�� 33
|
303
|
+
�_ 33
|
304
|
+
_� 33
|
305
|
+
�� 33
|
306
|
+
�� 33
|
307
|
+
� 32
|
308
|
+
�� 32
|
309
|
+
�� 32
|
310
|
+
_� 32
|
311
|
+
�� 32
|
312
|
+
� 32
|
313
|
+
� 32
|
314
|
+
� 32
|
315
|
+
� 32
|
316
|
+
_� 32
|
317
|
+
�� 31
|
318
|
+
� 31
|
319
|
+
_� 31
|
320
|
+
�� 31
|
321
|
+
� 31
|
322
|
+
_� 31
|
323
|
+
�� 31
|
324
|
+
� 31
|
325
|
+
�� 31
|
326
|
+
� 31
|
327
|
+
�� 31
|
328
|
+
�� 31
|
329
|
+
_� 31
|
330
|
+
� 31
|
331
|
+
�� 31
|
332
|
+
� 31
|
333
|
+
� 31
|
334
|
+
�� 30
|
335
|
+
� 30
|
336
|
+
� 30
|
337
|
+
� 30
|
338
|
+
�� 30
|
339
|
+
�� 30
|
340
|
+
�� 30
|
341
|
+
_� 30
|
342
|
+
_� 30
|
343
|
+
�� 30
|
344
|
+
�� 30
|
345
|
+
�� 30
|
346
|
+
� 30
|
347
|
+
_� 30
|
348
|
+
� 30
|
349
|
+
� 29
|
350
|
+
�� 29
|
351
|
+
�� 29
|
352
|
+
�� 29
|
353
|
+
� 29
|
354
|
+
�� 29
|
355
|
+
�� 29
|
356
|
+
�� 29
|
357
|
+
�� 29
|
358
|
+
�� 29
|
359
|
+
� 29
|
360
|
+
�� 29
|
361
|
+
� 29
|
362
|
+
�� 29
|
363
|
+
�� 29
|
364
|
+
� 29
|
365
|
+
_� 29
|
366
|
+
�� 29
|
367
|
+
�� 29
|
368
|
+
�� 29
|
369
|
+
� 29
|
370
|
+
�� 29
|
371
|
+
�� 28
|
372
|
+
�� 28
|
373
|
+
_� 28
|
374
|
+
�� 28
|
375
|
+
�_ 28
|
376
|
+
�_ 28
|
377
|
+
�� 28
|
378
|
+
�� 28
|
379
|
+
�� 28
|
380
|
+
� 28
|
381
|
+
_� 28
|
382
|
+
�� 28
|
383
|
+
� 28
|
384
|
+
_� 27
|
385
|
+
_� 27
|
386
|
+
� 27
|
387
|
+
�� 27
|
388
|
+
�� 27
|
389
|
+
_� 27
|
390
|
+
�� 27
|
391
|
+
�� 27
|
392
|
+
� 27
|
393
|
+
�� 27
|
394
|
+
�� 27
|
395
|
+
� 27
|
396
|
+
� 27
|
397
|
+
� 27
|
398
|
+
� 27
|
399
|
+
� 27
|
400
|
+
_� 27
|