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
+ _ 1360
2
+ i 470
3
+ a 439
4
+ e 316
5
+ n 276
6
+ & 256
7
+ ; 256
8
+ l 244
9
+ r 239
10
+ k 175
11
+ s 172
12
+ &i; 166
13
+ &i 166
14
+ i; 166
15
+ d 148
16
+ t 119
17
+ y 113
18
+ m 110
19
+ __ 107
20
+ u 105
21
+ n_ 101
22
+ o 97
23
+ b 90
24
+ ar 75
25
+ g 73
26
+ la 73
27
+ e_ 71
28
+ an 66
29
+ � 65
30
+ a_ 65
31
+ &s 60
32
+ s; 60
33
+ &s; 60
34
+ in 59
35
+ _b 56
36
+ i_ 56
37
+ _, 54
38
+ , 54
39
+ ra 54
40
+ le 52
41
+ il 49
42
+ ;_ 49
43
+ er 48
44
+ da 48
45
+ ,_ 47
46
+ _,_ 47
47
+ &i;n 44
48
+ i;n 44
49
+ ;n 44
50
+ z 44
51
+ &i;_ 43
52
+ i;_ 43
53
+ _y 43
54
+ k_ 42
55
+ _k 41
56
+ de 40
57
+ en 40
58
+ ' 40
59
+ nd 40
60
+ . 39
61
+ _. 39
62
+ p 39
63
+ lar 37
64
+ ka 36
65
+ ;& 36
66
+ r_ 35
67
+ ya 34
68
+ ri 34
69
+ c 33
70
+ v 33
71
+ _d 31
72
+ _i 31
73
+ ak 30
74
+ ma 30
75
+ g; 30
76
+ &g; 30
77
+ � 30
78
+ &g 30
79
+ bi 30
80
+ ara 29
81
+ ol 29
82
+ ;l 29
83
+ _t 28
84
+ ler 28
85
+ _a 28
86
+ ki 28
87
+ in_ 28
88
+ eri 27
89
+ h 27
90
+ re 27
91
+ ir 27
92
+ si 26
93
+ ek 26
94
+ _s 25
95
+ a& 24
96
+ li 24
97
+ me 23
98
+ u_ 23
99
+ ni 23
100
+ ba 23
101
+ an_ 22
102
+ _g 22
103
+ leri 22
104
+ di 22
105
+ r& 22
106
+ te 22
107
+ on 22
108
+ _o 22
109
+ nda 22
110
+ i& 22
111
+ al 21
112
+ en_ 21
113
+ s&i; 21
114
+ s&i 21
115
+ s& 21
116
+ ve 21
117
+ f 21
118
+ � 21
119
+ at 20
120
+ da_ 20
121
+ n&i; 20
122
+ n&i 20
123
+ n& 20
124
+ et 20
125
+ ay 20
126
+ _bi 20
127
+ un 20
128
+ i&s; 19
129
+ ile 19
130
+ _v 19
131
+ es 19
132
+ i&s 19
133
+ bu 19
134
+ r&i 18
135
+ d&i 18
136
+ &i;l 18
137
+ i;& 18
138
+ &i;& 18
139
+ i;l 18
140
+ r&i; 18
141
+ ;&i; 18
142
+ ;&i 18
143
+ d& 18
144
+ d&i; 18
145
+ ar& 17
146
+ l&i 17
147
+ ;i 17
148
+ l&i; 17
149
+ mi 17
150
+ _ya 17
151
+ nu 17
152
+ l& 17
153
+ l_ 17
154
+ _ol 17
155
+ ;k 16
156
+ _ve 16
157
+ pa 16
158
+ se 16
159
+ ola 16
160
+ _ka 16
161
+ ye 16
162
+ or 16
163
+ is 16
164
+ as 15
165
+ ;nda 15
166
+ _ba 15
167
+ &i;nd 15
168
+ de_ 15
169
+ ke 15
170
+ na 15
171
+ ;nd 15
172
+ el 15
173
+ az 15
174
+ ed 15
175
+ ge 15
176
+ ta 15
177
+ nl 15
178
+ i;nd 15
179
+ am 15
180
+ ad 15
181
+ ar&i 15
182
+ ar&i; 15
183
+ i;nda 15
184
+ ve_ 14
185
+ as&i 14
186
+ ko 14
187
+ erin 14
188
+ as&i; 14
189
+ ._ 14
190
+ as& 14
191
+ _._ 14
192
+ ik 14
193
+ rl 14
194
+ rin 14
195
+ ;n& 13
196
+ i;n& 13
197
+ _ve_ 13
198
+ lar&i 13
199
+ t&i; 13
200
+ ;n&i; 13
201
+ rk 13
202
+ ;n_ 13
203
+ _m 13
204
+ lar& 13
205
+ t& 13
206
+ t&i 13
207
+ y� 13
208
+ dan 13
209
+ i;n_ 13
210
+ sa 13
211
+ yo 13
212
+ _' 13
213
+ esi 13
214
+ a&s 13
215
+ em 13
216
+ iy 13
217
+ a&s; 13
218
+ &i;n_ 13
219
+ i;n&i 13
220
+ ki_ 13
221
+ ;n&i 13
222
+ &i;n& 13
223
+ ap 13
224
+ ne 13
225
+ ld 13
226
+ &g;&i 12
227
+ ha 12
228
+ _ko 12
229
+ y&i 12
230
+ g;&i 12
231
+ lerin 12
232
+ g;&i; 12
233
+ y&i; 12
234
+ _h 12
235
+ y& 12
236
+ ur 12
237
+ ti 12
238
+ &g;& 12
239
+ im 12
240
+ g;& 12
241
+ lara 12
242
+ ar_ 12
243
+ lm 12
244
+ to 12
245
+ _p 12
246
+ anl 12
247
+ _bu 12
248
+ bir 11
249
+ i;&s 11
250
+ a&g 11
251
+ tl 11
252
+ ek_ 11
253
+ ini 11
254
+ ;&s 11
255
+ _� 11
256
+ ir_ 11
257
+ rak 11
258
+ a&g; 11
259
+ _ola 11
260
+ ;&s; 11
261
+ kan 11
262
+ _e 11
263
+ i;&s; 11
264
+ ;r 11
265
+ t� 11
266
+ &i;&s 11
267
+ iz 10
268
+ &i;r 10
269
+ bil 10
270
+ _& 10
271
+ af 10
272
+ &s;i 10
273
+ _&s 10
274
+ ru 10
275
+ _� 10
276
+ nin 10
277
+ ;m 10
278
+ �k 10
279
+ r&i;n 10
280
+ ce 10
281
+ _&s; 10
282
+ &i;k 10
283
+ nde 10
284
+ i;k 10
285
+ lan 10
286
+ i;r 10
287
+ s;i 10
288
+ _ge 10
289
+ �r 10
290
+ dan_ 10
291
+ _y� 9
292
+ za 9
293
+ _bir_ 9
294
+ sin 9
295
+ ec 9
296
+ ak_ 9
297
+ ada 9
298
+ rd 9
299
+ _bir 9
300
+ bir_ 9
301
+ lk 9
302
+ kon 9
303
+ ba& 9
304
+ _sa 9
305
+ s&i;n 9
306
+ &s;l 9
307
+ ;la 9
308
+ _il 9
309
+ ala 9
310
+ si_ 9
311
+ s;l 9
312
+ nda_ 9
313
+ ra_ 9
314
+ iler 9
315
+ ul 9
316
+ olar 9
317
+ su 9
318
+ inin 8
319
+ on_ 8
320
+ _pa 8
321
+ �e 8
322
+ _y&i; 8
323
+ nla 8
324
+ esi_ 8
325
+ s&i;_ 8
326
+ _f 8
327
+ bu_ 8
328
+ e� 8
329
+ ci 8
330
+ ind 8
331
+ eni 8
332
+ ama 8
333
+ _te 8
334
+ lu 8
335
+ rla 8
336
+ y&i;l 8
337
+ edi 8
338
+ ba&s 8
339
+ eki 8
340
+ nin_ 8
341
+ iye 8
342
+ ab 8
343
+ _ha 8
344
+ _kon 8
345
+ ece 8
346
+ lma 8
347
+ ;&i;n 8
348
+ onu 8
349
+ _y&i 8
350
+ um 8
351
+ _y& 8
352
+ arak 8
353
+ ba&s; 8
354
+ ;i& 7
355
+ _ba& 7
356
+ mesi 7
357
+ aya 7
358
+ i;k_ 7
359
+ &g;i 7
360
+ m_ 7
361
+ d&i;_ 7
362
+ g;i 7
363
+ ;a 7
364
+ &i;k_ 7
365
+ �n 7
366
+ ;&g;& 7
367
+ lir 7
368
+ olara 7
369
+ ;&g 7
370
+ i;&g; 7
371
+ ;i&s; 7
372
+ t�r 7
373
+ ndan 7
374
+ ri_ 7
375
+ n&i;n 7
376
+ eri_ 7
377
+ _l 7
378
+ mes 7
379
+ and 7
380
+ _bin_ 7
381
+ un_ 7
382
+ lar_ 7
383
+ cu 7
384
+ &i;&g 7
385
+ _bin 7
386
+ d&i;& 7
387
+ dil 7
388
+ anla 7
389
+ �rk 7
390
+ ;k_ 7
391
+ bin_ 7
392
+ ;i&s 7
393
+ _r 7
394
+ _li 7
395
+ _da 7
396
+ _de 7
397
+ _to 7
398
+ unu 7
399
+ di_ 7
400
+ t�rk 7