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
+ _ 926
2
+ a 376
3
+ h 237
4
+ i 215
5
+ n 185
6
+ r 117
7
+ e 116
8
+ d 115
9
+ _a 87
10
+ __ 84
11
+ g 81
12
+ s 80
13
+ l 79
14
+ c 76
15
+ an 72
16
+ u 70
17
+ ai 67
18
+ n_ 66
19
+ t 63
20
+ h_ 59
21
+ o 58
22
+ ch 56
23
+ dh 55
24
+ ha 54
25
+ ea 53
26
+ a_ 48
27
+ b 43
28
+ id 41
29
+ m 41
30
+ na 39
31
+ ir 38
32
+ � 35
33
+ nn 34
34
+ ac 33
35
+ ach 31
36
+ idh 31
37
+ r_ 31
38
+ an_ 31
39
+ ad 31
40
+ s_ 26
41
+ he 26
42
+ in 25
43
+ _an 25
44
+ dh_ 24
45
+ _b 24
46
+ th 24
47
+ bh 24
48
+ ig 24
49
+ - 23
50
+ _c 23
51
+ d_ 23
52
+ T 23
53
+ gh 23
54
+ il 22
55
+ ei 22
56
+ gu 22
57
+ ean 21
58
+ ann 21
59
+ , 20
60
+ . 20
61
+ ir_ 20
62
+ air 19
63
+ ? 19
64
+ nn_ 19
65
+ ar 19
66
+ �i 19
67
+ _T 18
68
+ _t 18
69
+ ag 18
70
+ is 18
71
+ la 17
72
+ ha_ 17
73
+ as 17
74
+ _g 17
75
+ C 17
76
+ cha 16
77
+ _n 16
78
+ G 16
79
+ ui 16
80
+ _ai 16
81
+ _na 16
82
+ g_ 16
83
+ oi 15
84
+ adh 15
85
+ am 15
86
+ ._ 15
87
+ aid 15
88
+ hai 15
89
+ gus 15
90
+ us 15
91
+ f 15
92
+ _s 14
93
+ ,_ 14
94
+ _r 14
95
+ air_ 14
96
+ Th 14
97
+ eac 14
98
+ da 14
99
+ le 13
100
+ ig_ 13
101
+ us_ 13
102
+ idh_ 13
103
+ hea 13
104
+ gus_ 13
105
+ e_ 13
106
+ _ch 13
107
+ ann_ 13
108
+ on 13
109
+ a? 13
110
+ _a? 13
111
+ _C 13
112
+ ri 13
113
+ hu 12
114
+ each 12
115
+ agus 12
116
+ rd 12
117
+ agu 12
118
+ ch_ 12
119
+ hl 12
120
+ hi 12
121
+ aidh 12
122
+ _na_ 11
123
+ _an_ 11
124
+ na_ 11
125
+ _e 11
126
+ chd 11
127
+ _f 11
128
+ �id 11
129
+ ao 11
130
+ aig 11
131
+ hd 11
132
+ _d 11
133
+ �idh 11
134
+ ma 11
135
+ it 10
136
+ achd 10
137
+ _ag 10
138
+ _agu 10
139
+ al 10
140
+ te 10
141
+ sa 10
142
+ _agus 10
143
+ _air 10
144
+ l_ 10
145
+ E 10
146
+ ne 10
147
+ B 10
148
+ _ann 10
149
+ ith 10
150
+ _G 10
151
+ ach_ 10
152
+ _bh 10
153
+ _a_ 10
154
+ Tha 10
155
+ Tha_ 10
156
+ agus_ 10
157
+ _Th 10
158
+ ra 9
159
+ � 9
160
+ ad_ 9
161
+ acha 9
162
+ G�idh 9
163
+ li 9
164
+ inn 9
165
+ ua 9
166
+ ta 9
167
+ aidh_ 9
168
+ G�id 9
169
+ m_ 9
170
+ se 9
171
+ G� 9
172
+ lea 9
173
+ adh_ 9
174
+ ga 9
175
+ mh 9
176
+ G�i 9
177
+ _ann_ 9
178
+ h- 9
179
+ chai 8
180
+ ho 8
181
+ ?_ 8
182
+ lig 8
183
+ hli 8
184
+ _gu 8
185
+ ia 8
186
+ sg 8
187
+ �r 8
188
+ Ch 8
189
+ re 8
190
+ am_ 8
191
+ dhe 8
192
+ dhl 8
193
+ haid 8
194
+ � 8
195
+ lt 8
196
+ ain 8
197
+ ba 8
198
+ _air_ 8
199
+ eil 8
200
+ hei 8
201
+ bh_ 7
202
+ A 7
203
+ _G� 7
204
+ idhli 7
205
+ D 7
206
+ ana 7
207
+ _i 7
208
+ dhlig 7
209
+ � 7
210
+ h. 7
211
+ _Tha_ 7
212
+ idhe 7
213
+ _a?_ 7
214
+ a?_ 7
215
+ u_ 7
216
+ idhl 7
217
+ _Tha 7
218
+ _se 7
219
+ _G�i 7
220
+ dhli 7
221
+ hui 7
222
+ �idhl 7
223
+ _B 7
224
+ hlig 7
225
+ _G�id 7
226
+ igh 7
227
+ _th 7
228
+ I 7
229
+ fh 7
230
+ h� 6
231
+ agh 6
232
+ p 6
233
+ ona 6
234
+ han 6
235
+ on_ 6
236
+ gh_ 6
237
+ haidh 6
238
+ Ei 6
239
+ _E 6
240
+ ada 6
241
+ ic 6
242
+ lig_ 6
243
+ tr 6
244
+ ilt 6
245
+ nan 6
246
+ aoi 6
247
+ nam 6
248
+ _Ch 6
249
+ _I 6
250
+ tha 6
251
+ _dh 6
252
+ th_ 6
253
+ hlig_ 6
254
+ de 6
255
+ ' 6
256
+ ile 6
257
+ chaid 6
258
+ oin 6
259
+ nea 6
260
+ un 6
261
+ o_ 6
262
+ ean_ 6
263
+ ich 5
264
+ hd_ 5
265
+ in_ 5
266
+ _A 5
267
+ _D 5
268
+ _am 5
269
+ _h- 5
270
+ nach 5
271
+ ain_ 5
272
+ eacha 5
273
+ F 5
274
+ S 5
275
+ _tr 5
276
+ bhe 5
277
+ eann 5
278
+ gha 5
279
+ ilea 5
280
+ ll 5
281
+ iad_ 5
282
+ _fa 5
283
+ hean 5
284
+ eal 5
285
+ _Ta 5
286
+ _ba 5
287
+ Ta 5
288
+ is_ 5
289
+ ithe 5
290
+ ob 5
291
+ N 5
292
+ ine 5
293
+ _h 5
294
+ nac 5
295
+ _aig 5
296
+ idhea 5
297
+ aoine 5
298
+ eo 5
299
+ t_ 5
300
+ rd_ 5
301
+ h._ 5
302
+ had 5
303
+ eir 5
304
+ neach 5
305
+ han_ 5
306
+ ur 5
307
+ iad 5
308
+ ead 5
309
+ im 5
310
+ neac 5
311
+ dhea 5
312
+ _bar 5
313
+ io 5
314
+ eu 5
315
+ rt 5
316
+ at 5
317
+ aig_ 5
318
+ oine 5
319
+ � 5
320
+ the 5
321
+ bar 5
322
+ _ri 5
323
+ chu 5
324
+ fa 5
325
+ aoin 5
326
+ chd_ 5
327
+ sm 4
328
+ b� 4
329
+ thea 4
330
+ uid 4
331
+ nai 4
332
+ lean 4
333
+ ro 4
334
+ dac 4
335
+ _gh 4
336
+ sga 4
337
+ il_ 4
338
+ un_ 4
339
+ fha 4
340
+ _� 4
341
+ hadh 4
342
+ _iad 4
343
+ achd_ 4
344
+ uir 4
345
+ ilean 4
346
+ du 4
347
+ nt 4
348
+ n, 4
349
+ irt 4
350
+ eis 4
351
+ ru 4
352
+ obh 4
353
+ sma 4
354
+ idea 4
355
+ r- 4
356
+ sea 4
357
+ ab 4
358
+ ide 4
359
+ ais 4
360
+ oinea 4
361
+ cl 4
362
+ chadh 4
363
+ ni 4
364
+ _F 4
365
+ me 4
366
+ asg 4
367
+ _aig_ 4
368
+ gu_ 4
369
+ ith_ 4
370
+ Cha 4
371
+ n- 4
372
+ ar_ 4
373
+ e� 4
374
+ �rd 4
375
+ eachd 4
376
+ dach 4
377
+ hith 4
378
+ ail 4
379
+ r� 4
380
+ ug 4
381
+ chi 4
382
+ _l 4
383
+ as_ 4
384
+ �n 4
385
+ Bh 4
386
+ heil 4
387
+ ithea 4
388
+ _ia 4
389
+ aigh 4
390
+ hit 4
391
+ _chi 4
392
+ tha_ 4
393
+ �na 4
394
+ huir 4
395
+ _chu 4
396
+ P 4
397
+ _P 4
398
+ nan_ 4
399
+ _bho 4
400
+ bho 4