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
+ _ 370
2
+ � 343
3
+ � 301
4
+ � 243
5
+ � 206
6
+ � 204
7
+ � 183
8
+ � 182
9
+ � 164
10
+ � 159
11
+ � 151
12
+ � 145
13
+ � 137
14
+ � 135
15
+ � 111
16
+ � 111
17
+ � 106
18
+ � 99
19
+ � 96
20
+ � 95
21
+ � 89
22
+ � 88
23
+ � 88
24
+ � 84
25
+ � 78
26
+ � 73
27
+ � 73
28
+ �� 70
29
+ � 67
30
+ � 59
31
+ � 54
32
+ �� 54
33
+ � 53
34
+ � 52
35
+ ��� 51
36
+ � 51
37
+ �� 49
38
+ ͧ 48
39
+ �� 46
40
+ � 42
41
+ �� 38
42
+ � 37
43
+ �� 36
44
+ �� 35
45
+ � 35
46
+ � 34
47
+ �� 33
48
+ � 33
49
+ . 33
50
+ ��� 32
51
+ �� 32
52
+ ҧ 32
53
+ �� 31
54
+ �� 31
55
+ � 29
56
+ �� 29
57
+ �� 28
58
+ � 28
59
+ ��� 27
60
+ __ 27
61
+ �� 27
62
+ �� 25
63
+ �� 25
64
+ � 24
65
+ �� 24
66
+ ҡ 23
67
+ �� 23
68
+ ��� 23
69
+ Ѻ 23
70
+ _� 21
71
+ ҹ 21
72
+ � 21
73
+ � 21
74
+ �_ 21
75
+ ѧ 21
76
+ � 20
77
+ �� 20
78
+ �� 20
79
+ � 20
80
+ �� 19
81
+ �� 19
82
+ �� 19
83
+ ͡ 19
84
+ �� 19
85
+ �� 18
86
+ �� 18
87
+ � 18
88
+ �� 18
89
+ ��� 18
90
+ �� 18
91
+ � 18
92
+ � 18
93
+ �� 17
94
+ �� 17
95
+ �� 17
96
+ �� 17
97
+ � 17
98
+ ҵ 17
99
+ �Ѱ 16
100
+ Ѱ 16
101
+ �� 16
102
+ ��� 16
103
+ �ͧ 16
104
+ �_ 16
105
+ �� 16
106
+ �� 16
107
+ �� 16
108
+ ��� 16
109
+ �� 16
110
+ �� 15
111
+ � 15
112
+ �_ 15
113
+ �� 15
114
+ � 15
115
+ �� 15
116
+ �_ 15
117
+ � 15
118
+ �� 15
119
+ �ͧ 14
120
+ �� 14
121
+ �� 14
122
+ �� 14
123
+ � 14
124
+ � 14
125
+ � 14
126
+ �� 14
127
+ �� 14
128
+ ѹ 13
129
+ �� 13
130
+ � 13
131
+ �� 13
132
+ _� 13
133
+ �� 13
134
+ �� 13
135
+ �� 13
136
+ � 13
137
+ �� 13
138
+ ���� 13
139
+ ѡ 13
140
+ � 13
141
+ ¡ 13
142
+ �� 13
143
+ ��� 13
144
+ �� 13
145
+ �� 12
146
+ _� 12
147
+ �� 12
148
+ ���� 12
149
+ ��� 12
150
+ ��� 12
151
+ Ѵ 12
152
+ �� 12
153
+ ˹ 12
154
+ �ҧ 12
155
+ �� 12
156
+ ��� 12
157
+ � 12
158
+ �� 12
159
+ �� 12
160
+ �� 12
161
+ ͹ 12
162
+ �� 12
163
+ �� 12
164
+ �� 11
165
+ Թ 11
166
+ ��� 11
167
+ ��� 11
168
+ �� 11
169
+ ��� 11
170
+ з 11
171
+ � 11
172
+ �� 11
173
+ ǹ 11
174
+ �� 11
175
+ �� 11
176
+ �� 11
177
+ �� 11
178
+ �� 11
179
+ � 11
180
+ �� 11
181
+ _� 11
182
+ �� 11
183
+ �� 11
184
+ �� 10
185
+ �� 10
186
+ �� 10
187
+ � 10
188
+ �_ 10
189
+ �ҹ 10
190
+ ��� 10
191
+ Դ 10
192
+ ä 10
193
+ �� 10
194
+ �� 10
195
+ �� 10
196
+ �� 10
197
+ �� 10
198
+ ���� 10
199
+ �� 10
200
+ �� 10
201
+ ��� 10
202
+ �� 10
203
+ �� 10
204
+ �� 10
205
+ _� 10
206
+ �� 10
207
+ _� 10
208
+ ��ͧ 10
209
+ ��� 10
210
+ � 10
211
+ �Ѻ 9
212
+ ���� 9
213
+ �ҧ 9
214
+ ��� 9
215
+ �� 9
216
+ �� 9
217
+ Ҥ 9
218
+ �ѧ 9
219
+ �� 9
220
+ ��_ 9
221
+ �� 9
222
+ �� 9
223
+ �� 9
224
+ � 9
225
+ �� 9
226
+ ���_ 9
227
+ �� 9
228
+ ��� 9
229
+ ç 9
230
+ �Ѻ 9
231
+ _� 9
232
+ �� 8
233
+ �� 8
234
+ �¡ 8
235
+ ��� 8
236
+ �ҡ 8
237
+ ���� 8
238
+ �� 8
239
+ ��� 8
240
+ �� 8
241
+ �� 8
242
+ �. 8
243
+ ŧ 8
244
+ ͺ 8
245
+ �� 8
246
+ ѭ 8
247
+ �� 8
248
+ �� 8
249
+ �� 8
250
+ �� 8
251
+ �� 8
252
+ ҵ� 8
253
+ �� 8
254
+ � 8
255
+ ��� 8
256
+ �_ 8
257
+ �ҵ 8
258
+ ��� 8
259
+ �� 8
260
+ �� 8
261
+ �� 8
262
+ Ի 8
263
+ �� 8
264
+ �ҵ� 8
265
+ �� 8
266
+ _� 7
267
+ �� 7
268
+ �� 7
269
+ �� 7
270
+ ���� 7
271
+ Ѱ�� 7
272
+ �� 7
273
+ �� 7
274
+ ��� 7
275
+ _�� 7
276
+ �Ѱ�� 7
277
+ �� 7
278
+ �� 7
279
+ ��� 7
280
+ �� 7
281
+ ��� 7
282
+ �� 7
283
+ ��� 7
284
+ �Դ 7
285
+ �� 7
286
+ �� 7
287
+ �� 7
288
+ ��� 7
289
+ �� 7
290
+ � 7
291
+ �� 7
292
+ ��� 7
293
+ �� 7
294
+ ��� 7
295
+ ١ 7
296
+ ҷ 7
297
+ _� 7
298
+ � 7
299
+ Ѱ� 7
300
+ �� 7
301
+ �� 7
302
+ �� 7
303
+ ��� 7
304
+ �_ 7
305
+ �� 7
306
+ _��� 7
307
+ ��� 7
308
+ �� 7
309
+ �� 7
310
+ .� 7
311
+ �� 7
312
+ _� 7
313
+ ��� 7
314
+ ��� 7
315
+ Ѱ��� 7
316
+ _� 7
317
+ ֧ 7
318
+ ���� 7
319
+ � 7
320
+ ���� 7
321
+ ��ä 7
322
+ �ͧ 7
323
+ �Ѱ� 7
324
+ ��� 7
325
+ ��� 7
326
+ �� 7
327
+ �� 7
328
+ �� 7
329
+ �� 7
330
+ �� 7
331
+ ��� 7
332
+ ��� 7
333
+ �ä 7
334
+ �� 7
335
+ �� 7
336
+ ǡ 7
337
+ _� 7
338
+ �� 7
339
+ ��� 7
340
+ ���� 7
341
+ �� 7
342
+ �ǹ 7
343
+ ͧ� 6
344
+ �÷ 6
345
+ �� 6
346
+ ����� 6
347
+ ���� 6
348
+ �� 6
349
+ ó 6
350
+ �.�. 6
351
+ �� 6
352
+ ÷ 6
353
+ ��� 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
+ Ѳ 6
368
+ �� 6
369
+ � 6
370
+ �� 6
371
+ �Ѱ�� 6
372
+ ͧ_ 6
373
+ ��_ 6
374
+ ҡ� 6
375
+ ��� 6
376
+ Ҩ 6
377
+ �� 6
378
+ Ѱ�� 6
379
+ �� 6
380
+ �� 6
381
+ ��_ 6
382
+ ����� 6
383
+ �� 6
384
+ ��� 6
385
+ ���� 6
386
+ Ҫ 6
387
+ Ѱ��� 6
388
+ Ѳ� 6
389
+ ��.�. 6
390
+ �� 6
391
+ ��� 6
392
+ �.�.� 6
393
+ �Ѱ� 6
394
+ �� 6
395
+ �� 6
396
+ ���� 6
397
+ �� 6
398
+ �� 6
399
+ �� 6
400
+ ���� 6