scylla 0.1.0 → 0.2.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (80) hide show
  1. data/Gemfile +0 -1
  2. data/Gemfile.lock +0 -10
  3. data/README.rdoc +22 -0
  4. data/VERSION +1 -1
  5. data/bin/scylla +13 -0
  6. data/lib/scylla/classifier.rb +2 -2
  7. data/lib/scylla/generator.rb +1 -1
  8. data/lib/scylla/lms/13375P33K.lm +400 -0
  9. data/lib/scylla/lms/afrikaans.lm +400 -0
  10. data/lib/scylla/lms/arabic.lm +400 -0
  11. data/lib/scylla/lms/bulgarian.lm +400 -0
  12. data/lib/scylla/lms/catalan.lm +400 -0
  13. data/lib/scylla/lms/chinese.lm +400 -0
  14. data/lib/scylla/lms/danish.lm +400 -0
  15. data/lib/scylla/lms/english.lm +400 -0
  16. data/lib/scylla/lms/esperanto.lm +400 -0
  17. data/lib/scylla/lms/finnish.lm +400 -0
  18. data/lib/scylla/lms/french.lm +400 -0
  19. data/lib/scylla/lms/german.lm +400 -0
  20. data/lib/scylla/lms/greek-iso8859-7.lm +400 -0
  21. data/lib/scylla/lms/hebrew.lm +400 -0
  22. data/lib/scylla/lms/hindi.lm +400 -0
  23. data/lib/scylla/lms/hungarian.lm +400 -0
  24. data/lib/scylla/lms/icelandic.lm +400 -0
  25. data/lib/scylla/lms/indonesian.lm +400 -0
  26. data/lib/scylla/lms/irish.lm +400 -0
  27. data/lib/scylla/lms/italian.lm +400 -0
  28. data/lib/scylla/lms/japanese.lm +400 -0
  29. data/lib/scylla/lms/kannada.lm +400 -0
  30. data/lib/scylla/lms/korean.lm +400 -0
  31. data/lib/scylla/lms/latin.lm +400 -0
  32. data/lib/scylla/lms/malay.lm +400 -0
  33. data/lib/scylla/lms/marathi.lm +400 -0
  34. data/lib/scylla/lms/mingo.lm +400 -0
  35. data/lib/scylla/lms/nepali.lm +400 -0
  36. data/lib/scylla/lms/norwegian.lm +400 -0
  37. data/lib/scylla/lms/polish.lm +400 -0
  38. data/lib/scylla/lms/portuguese.lm +400 -0
  39. data/lib/scylla/lms/quechua.lm +400 -0
  40. data/lib/scylla/lms/romanian.lm +400 -0
  41. data/lib/scylla/lms/rumantsch.lm +400 -0
  42. data/lib/scylla/lms/russian.lm +400 -0
  43. data/lib/scylla/lms/sanskrit.lm +400 -0
  44. data/lib/scylla/lms/scots_gaelic.lm +400 -0
  45. data/lib/scylla/lms/serbian-ascii.lm +400 -0
  46. data/lib/scylla/lms/slovak-ascii.lm +400 -0
  47. data/lib/scylla/lms/slovenian-ascii.lm +400 -0
  48. data/lib/scylla/lms/spanish.lm +400 -0
  49. data/lib/scylla/lms/swahili.lm +400 -0
  50. data/lib/scylla/lms/swedish.lm +400 -0
  51. data/lib/scylla/lms/tagalog.lm +400 -0
  52. data/lib/scylla/lms/tamil.lm +400 -0
  53. data/lib/scylla/lms/thai.lm +400 -0
  54. data/lib/scylla/lms/turkish.lm +400 -0
  55. data/lib/scylla/lms/ukrainian-koi8_u.lm +400 -0
  56. data/lib/scylla/lms/vietnamese.lm +400 -0
  57. data/lib/scylla/lms/welsh.lm +400 -0
  58. data/lib/scylla/lms/yiddish-utf.lm +400 -0
  59. data/lib/scylla/loader.rb +8 -1
  60. data/scylla-0.1.0.gem +0 -0
  61. data/scylla.gemspec +69 -3
  62. data/source_texts/kannada.txt +283 -0
  63. data/test/classifier_test.rb +7 -0
  64. data/test/fixtures/lms/13375p33k.lm +400 -0
  65. data/test/fixtures/lms/danish.lm +400 -0
  66. data/test/fixtures/lms/english.lm +400 -0
  67. data/test/fixtures/lms/french.lm +400 -0
  68. data/test/fixtures/lms/german.lm +400 -0
  69. data/test/fixtures/lms/japanese.lm +400 -0
  70. data/test/fixtures/lms/kannada.lm +400 -0
  71. data/test/fixtures/lms/spanish.lm +400 -0
  72. data/test/fixtures/source_texts/13375P33K.txt +199 -0
  73. data/test/fixtures/source_texts/japanese.txt +199 -0
  74. data/test/fixtures/source_texts/kannada.txt +283 -0
  75. data/test/generator_test.rb +10 -7
  76. data/test/helper.rb +5 -6
  77. data/test/loader_test.rb +1 -0
  78. data/test/scylla_test.rb +1 -0
  79. metadata +78 -14
  80. data/source_texts/armenian.txt +0 -86
@@ -0,0 +1,400 @@
1
+ _ 1278
2
+ � 290
3
+ � 184
4
+ � 181
5
+ � 163
6
+ � 163
7
+ � 158
8
+ � 129
9
+ � 101
10
+ � 100
11
+ � 99
12
+ � 90
13
+ � 89
14
+ __ 86
15
+ � 78
16
+ _� 77
17
+ � 75
18
+ � 74
19
+ � 73
20
+ � 73
21
+ � 71
22
+ � 69
23
+ �� 66
24
+ �� 65
25
+ � 62
26
+ � 55
27
+ � 54
28
+ � 54
29
+ � 53
30
+ � 52
31
+ � 50
32
+ � 49
33
+ � 49
34
+ � 48
35
+ _� 48
36
+ � 46
37
+ � 45
38
+ . 44
39
+ � 40
40
+ � 39
41
+ ��. 39
42
+ � 39
43
+ �. 39
44
+ � 39
45
+ � 37
46
+ �� 36
47
+ � 35
48
+ � 35
49
+ �� 34
50
+ _� 34
51
+ � 34
52
+ � 33
53
+ �_ 32
54
+ � 32
55
+ _� 31
56
+ �_ 31
57
+ � 31
58
+ �� 29
59
+ �� 29
60
+ ��_ 29
61
+ � 29
62
+ ��_ 29
63
+ �_ 29
64
+ _� 27
65
+ _� 27
66
+ _� 27
67
+ �� 27
68
+ �� 26
69
+ � 26
70
+ �� 25
71
+ �� 25
72
+ _� 25
73
+ _� 25
74
+ �� 25
75
+ _� 25
76
+ �_ 24
77
+ �_ 24
78
+ �_ 24
79
+ �� 23
80
+ � 23
81
+ _� 23
82
+ ��_ 23
83
+ �� 23
84
+ ��_ 23
85
+ �� 23
86
+ � 23
87
+ �� 22
88
+ � 22
89
+ � 22
90
+ �� 22
91
+ �� 22
92
+ �_ 22
93
+ �� 22
94
+ ��_ 21
95
+ _� 21
96
+ �� 21
97
+ �� 21
98
+ _� 21
99
+ � 20
100
+ ��_ 20
101
+ �_ 20
102
+ ��_ 20
103
+ _� 20
104
+ �� 19
105
+ � 19
106
+ � 19
107
+ ._ 19
108
+ _�� 19
109
+ ִ 18
110
+ _�� 18
111
+ ��_ 18
112
+ �� 18
113
+ �_ 18
114
+ �_ 18
115
+ �_ 18
116
+ � 18
117
+ � 18
118
+ �� 18
119
+ � 18
120
+ ��_ 18
121
+ _� 17
122
+ � 17
123
+ �� 17
124
+ �_ 17
125
+ �ִ 17
126
+ " 16
127
+ �� 16
128
+ � 16
129
+ �� 16
130
+ �� 16
131
+ �� 16
132
+ �� 15
133
+ �� 15
134
+ � 15
135
+ � 15
136
+ ��_ 15
137
+ , 15
138
+ �._ 15
139
+ _� 15
140
+ ��._ 15
141
+ ' 15
142
+ �� 14
143
+ _�� 14
144
+ �� 14
145
+ ��� 14
146
+ � 14
147
+ �� 14
148
+ _�ִ 14
149
+ �� 14
150
+ �� 14
151
+ �� 14
152
+ � 14
153
+ � 14
154
+ �� 14
155
+ �� 14
156
+ ִ� 13
157
+ �ִ� 13
158
+ ߴ 13
159
+ ȸ 13
160
+ �� 13
161
+ � 13
162
+ �� 13
163
+ �� 13
164
+ �� 13
165
+ �� 13
166
+ �_ 13
167
+ � 12
168
+ � 12
169
+ �� 12
170
+ � 12
171
+ �ߴ� 12
172
+ ,_ 12
173
+ � 12
174
+ � 12
175
+ �ߴ 12
176
+ �_ 12
177
+ ߴ� 12
178
+ ��_ 11
179
+ ��� 11
180
+ ��� 11
181
+ _�� 11
182
+ �� 11
183
+ �ߴ�. 11
184
+ ��_ 11
185
+ ߴ�. 11
186
+ �� 11
187
+ _� 11
188
+ _� 11
189
+ _�� 11
190
+ �� 11
191
+ �� 11
192
+ ���� 11
193
+ _�� 11
194
+ �� 11
195
+ �� 11
196
+ �� 10
197
+ _�ִ� 10
198
+ ��� 10
199
+ � 10
200
+ �� 10
201
+ �� 10
202
+ �� 10
203
+ � 10
204
+ õ 10
205
+ �� 10
206
+ ��� 10
207
+ �_ 10
208
+ �_ 10
209
+ ���� 10
210
+ _�� 10
211
+ �� 10
212
+ � 10
213
+ � 10
214
+ �� 10
215
+ �� 10
216
+ �� 10
217
+ �� 10
218
+ ϰ 9
219
+ �� 9
220
+ ����_ 9
221
+ � 9
222
+ _� 9
223
+ _�� 9
224
+ � 9
225
+ �� 9
226
+ ���_ 9
227
+ �� 9
228
+ �� 9
229
+ � 9
230
+ �� 9
231
+ �� 9
232
+ �� 9
233
+ �� 8
234
+ �_ 8
235
+ ���_ 8
236
+ �� 8
237
+ �_ 8
238
+ ����_ 8
239
+ � 8
240
+ � 8
241
+ �� 8
242
+ ġ 8
243
+ �� 8
244
+ �� 8
245
+ ��_ 8
246
+ �� 8
247
+ �� 8
248
+ �� 8
249
+ �� 8
250
+ ��� 8
251
+ �_ 8
252
+ �� 8
253
+ �_ 8
254
+ �� 8
255
+ �� 8
256
+ � 8
257
+ �� 8
258
+ �_ 8
259
+ �ϰ 8
260
+ �� 8
261
+ �� 8
262
+ _' 8
263
+ � 8
264
+ � 8
265
+ � 8
266
+ ��� 8
267
+ �� 7
268
+ �� 7
269
+ ���� 7
270
+ �� 7
271
+ ��� 7
272
+ �� 7
273
+ Ʈ 7
274
+ _�� 7
275
+ Ӵ� 7
276
+ �Ӵ 7
277
+ �Ӵ 7
278
+ � 7
279
+ _��_ 7
280
+ �Ӵ� 7
281
+ �� 7
282
+ �_ 7
283
+ ��Ӵ 7
284
+ ��_ 7
285
+ ��_ 7
286
+ ��� 7
287
+ �� 7
288
+ ��_ 7
289
+ ��_ 7
290
+ �� 7
291
+ � 7
292
+ ( 7
293
+ ü 7
294
+ ����_ 7
295
+ _�� 7
296
+ �� 7
297
+ �� 7
298
+ �ִ�. 7
299
+ �� 7
300
+ ��� 7
301
+ �� 7
302
+ _�� 7
303
+ _�� 7
304
+ �� 7
305
+ ��� 7
306
+ Ӵ 7
307
+ �Ӵ� 7
308
+ _�� 7
309
+ ) 7
310
+ _��� 7
311
+ ִ�. 7
312
+ �� 7
313
+ ���_ 7
314
+ �� 7
315
+ � 6
316
+ _" 6
317
+ �Բ 6
318
+ �� 6
319
+ �� 6
320
+ _� 6
321
+ �� 6
322
+ �� 6
323
+ �_ 6
324
+ �� 6
325
+ �� 6
326
+ _�� 6
327
+ ��_ 6
328
+ �Բ�_ 6
329
+ �� 6
330
+ �� 6
331
+ �� 6
332
+ _�� 6
333
+ � 6
334
+ _�� 6
335
+ �� 6
336
+ �� 6
337
+ _�� 6
338
+ ��� 6
339
+ Բ� 6
340
+ ��_ 6
341
+ ��� 6
342
+ ȯ 6
343
+ �� 6
344
+ _�� 6
345
+ Բ�_ 6
346
+ _��� 6
347
+ �� 6
348
+ ̴ 6
349
+ ��� 6
350
+ .� 6
351
+ ��_ 6
352
+ �� 6
353
+ �Բ� 6
354
+ > 6
355
+ �� 6
356
+ _�� 6
357
+ _��� 6
358
+ �_ 6
359
+ �_ 6
360
+ ̵ 6
361
+ �� 6
362
+ �.� 6
363
+ �� 6
364
+ ��_ 6
365
+ �� 6
366
+ � 6
367
+ �� 6
368
+ �_ 6
369
+ �� 6
370
+ _��_ 6
371
+ �� 6
372
+ �� 6
373
+ < 6
374
+ �̴ 6
375
+ �� 6
376
+ �� 6
377
+ _õ 6
378
+ Բ 6
379
+ _�� 6
380
+ _� 6
381
+ ��.� 6
382
+ �� 6
383
+ � 6
384
+ Ÿ 6
385
+ �� 5
386
+ �� 5
387
+ �̴�. 5
388
+ �� 5
389
+ �� 5
390
+ ���� 5
391
+ ־ 5
392
+ �� 5
393
+ �� 5
394
+ ��ߴ 5
395
+ �� 5
396
+ �� 5
397
+ �� 5
398
+ ��� 5
399
+ �� 5
400
+ �� 5