scylla 0.4.3 → 0.5.0

Sign up to get free protection for your applications and to get access to all the features.
Files changed (94) hide show
  1. data/Gemfile +1 -0
  2. data/Gemfile.lock +10 -0
  3. data/VERSION +1 -1
  4. data/lib/scylla/generator.rb +1 -1
  5. data/lib/scylla/lms/13375P33K.lm +156 -156
  6. data/lib/scylla/lms/arabic.lm +133 -133
  7. data/lib/scylla/lms/bulgarian.lm +122 -122
  8. data/lib/scylla/lms/catalan.lm +151 -151
  9. data/lib/scylla/lms/danish.lm +137 -137
  10. data/lib/scylla/lms/english.lm +207 -207
  11. data/lib/scylla/lms/french.lm +400 -400
  12. data/lib/scylla/lms/japanese.lm +400 -400
  13. data/lib/scylla/lms/korean.lm +233 -233
  14. data/lib/scylla/lms/norwegian.lm +398 -398
  15. data/lib/scylla/lms/spanish.lm +98 -98
  16. data/lib/scylla/lms/swedish.lm +123 -123
  17. data/lib/scylla/lms/tagalog.lm +223 -223
  18. data/lib/scylla/lms/welsh.lm +234 -234
  19. data/lib/scylla/resources.rb +10 -10
  20. data/scylla.gemspec +17 -40
  21. data/source_texts/catalan.txt +28 -28
  22. data/source_texts/danish.txt +62 -62
  23. data/source_texts/english.txt +10 -10
  24. data/source_texts/french.txt +470 -77
  25. data/source_texts/japanese.txt +453 -199
  26. data/source_texts/norwegian.txt +96 -63
  27. data/source_texts/spanish.txt +269 -269
  28. data/test/classifier_test.rb +2 -2
  29. data/test/fixtures/lms/13375p33k.lm +156 -156
  30. data/test/fixtures/lms/danish.lm +137 -137
  31. data/test/fixtures/lms/english.lm +207 -207
  32. data/test/fixtures/lms/french.lm +400 -400
  33. data/test/fixtures/lms/hindi.lm +400 -0
  34. data/test/fixtures/lms/italian.lm +400 -0
  35. data/test/fixtures/lms/japanese.lm +400 -400
  36. data/test/fixtures/lms/norwegian.lm +400 -0
  37. data/test/fixtures/lms/spanish.lm +98 -98
  38. data/test/fixtures/source_texts/danish.txt +62 -62
  39. data/test/fixtures/source_texts/english.txt +10 -10
  40. data/test/fixtures/source_texts/french.txt +470 -77
  41. data/test/fixtures/source_texts/hindi.txt +199 -0
  42. data/test/fixtures/source_texts/italian.txt +120 -0
  43. data/test/fixtures/source_texts/japanese.txt +453 -199
  44. data/test/fixtures/source_texts/norwegian.txt +190 -0
  45. data/test/fixtures/source_texts/spanish.txt +269 -269
  46. data/test/fixtures/test_languages/english +61 -0
  47. data/test/fixtures/test_languages/french +0 -0
  48. data/test/fixtures/test_languages/german +29 -0
  49. data/test/fixtures/test_languages/hindi +3 -0
  50. data/test/fixtures/test_languages/italian +6 -0
  51. data/test/fixtures/test_languages/japanese +79 -0
  52. data/test/fixtures/test_languages/norwegian +14 -0
  53. data/test/fixtures/test_languages/spanish +22 -0
  54. data/test/generator_test.rb +0 -1
  55. data/test/language_test.rb +28 -0
  56. metadata +20 -43
  57. data/lib/scylla/lms/esperanto.lm +0 -400
  58. data/lib/scylla/lms/hungarian.lm +0 -400
  59. data/lib/scylla/lms/irish.lm +0 -400
  60. data/lib/scylla/lms/kannada.lm +0 -400
  61. data/lib/scylla/lms/latin.lm +0 -400
  62. data/lib/scylla/lms/malay.lm +0 -400
  63. data/lib/scylla/lms/marathi.lm +0 -400
  64. data/lib/scylla/lms/mingo.lm +0 -400
  65. data/lib/scylla/lms/nepali.lm +0 -400
  66. data/lib/scylla/lms/quechua.lm +0 -400
  67. data/lib/scylla/lms/rumantsch.lm +0 -400
  68. data/lib/scylla/lms/sanskrit.lm +0 -400
  69. data/lib/scylla/lms/scots_gaelic.lm +0 -400
  70. data/lib/scylla/lms/serbian.lm +0 -400
  71. data/lib/scylla/lms/swahili.lm +0 -400
  72. data/lib/scylla/lms/tamil.lm +0 -400
  73. data/lib/scylla/lms/ukrainian.lm +0 -400
  74. data/lib/scylla/lms/yiddish.lm +0 -400
  75. data/source_texts/esperanto.txt +0 -199
  76. data/source_texts/hungarian.txt +0 -102
  77. data/source_texts/irish.txt +0 -209
  78. data/source_texts/kannada.txt +0 -283
  79. data/source_texts/latin.txt +0 -120
  80. data/source_texts/malay.txt +0 -108
  81. data/source_texts/marathi.txt +0 -100
  82. data/source_texts/mingo.txt +0 -146
  83. data/source_texts/nepali.txt +0 -131
  84. data/source_texts/quechua.txt +0 -108
  85. data/source_texts/rumantsch.txt +0 -110
  86. data/source_texts/sanskrit.txt +0 -135
  87. data/source_texts/scots_gaelic.txt +0 -93
  88. data/source_texts/serbian.txt +0 -121
  89. data/source_texts/swahili.txt +0 -120
  90. data/source_texts/tamil.txt +0 -167
  91. data/source_texts/ukrainian.txt +0 -214
  92. data/source_texts/yiddish-utf.txt +0 -83
  93. data/test/fixtures/lms/kannada.lm +0 -400
  94. data/test/fixtures/source_texts/kannada.txt +0 -283
@@ -1,400 +0,0 @@
1
- _ 1288
2
- � 336
3
- � 267
4
- � 222
5
- � 211
6
- � 192
7
- � 173
8
- � 150
9
- � 148
10
- � 147
11
- � 144
12
- � 125
13
- � 121
14
- � 112
15
- � 109
16
- � 106
17
- � 88
18
- � 78
19
- _� 66
20
- � 64
21
- �_ 64
22
- _� 61
23
- � 57
24
- �_ 57
25
- �_ 57
26
- � 50
27
- �_ 49
28
- � 48
29
- _� 46
30
- � 46
31
- �_ 43
32
- . 42
33
- _� 41
34
- �� 40
35
- צ 39
36
- _� 38
37
- � 37
38
- �_ 36
39
- �� 36
40
- " 35
41
- � 35
42
- � 34
43
- _� 34
44
- �� 33
45
- �� 33
46
- �� 33
47
- �_ 32
48
- �_ 31
49
- _� 30
50
- �� 30
51
- �� 30
52
- � 30
53
- �� 29
54
- � 29
55
- _� 28
56
- � 28
57
- � 27
58
- �� 27
59
- �� 27
60
- �� 27
61
- �� 26
62
- �_ 26
63
- �� 26
64
- �� 26
65
- � 26
66
- �� 26
67
- � 25
68
- �� 25
69
- �� 25
70
- �� 24
71
- _� 24
72
- _� 24
73
- �� 24
74
- �� 24
75
- � 24
76
- �� 24
77
- �� 23
78
- �� 23
79
- �� 23
80
- �� 23
81
- _�� 23
82
- _�� 23
83
- �� 22
84
- � 22
85
- � 21
86
- �� 21
87
- �� 21
88
- � 21
89
- � 20
90
- �� 20
91
- �� 20
92
- �_ 20
93
- �� 20
94
- �� 20
95
- �� 20
96
- �� 19
97
- �_ 19
98
- ��_ 19
99
- �� 19
100
- �� 18
101
- _�� 18
102
- Φ 18
103
- � 18
104
- ._ 18
105
- �� 18
106
- _� 18
107
- �� 18
108
- , 18
109
- �� 17
110
- _�_ 17
111
- �� 17
112
- � 17
113
- �� 17
114
- �� 17
115
- �� 17
116
- �� 17
117
- �� 17
118
- �_ 16
119
- Ħ 16
120
- �� 16
121
- �� 16
122
- �� 16
123
- _� 16
124
- �� 16
125
- � 16
126
- _�� 15
127
- Ц 15
128
- ��_ 15
129
- � 15
130
- ��_ 15
131
- _� 15
132
- �� 15
133
- _�� 15
134
- ��_ 14
135
- _�� 14
136
- �� 14
137
- Ҧ 14
138
- �� 14
139
- _� 14
140
- "_ 14
141
- �� 14
142
- ,_ 14
143
- �� 14
144
- _� 14
145
- ��� 14
146
- �_ 13
147
- _� 13
148
- _��_ 13
149
- ̦ 13
150
- � 13
151
- I 13
152
- æ 13
153
- ϧ 13
154
- �� 13
155
- � 13
156
- _�� 13
157
- ¦ 13
158
- �� 13
159
- � 13
160
- �� 13
161
- �� 13
162
- �� 13
163
- צ� 13
164
- _� 13
165
- �� 13
166
- �צ 13
167
- ��_ 13
168
- �� 13
169
- �� 12
170
- �� 12
171
- � 12
172
- �� 12
173
- _צ 12
174
- �� 12
175
- _��_ 12
176
- _�� 12
177
- �� 12
178
- �� 12
179
- �_ 12
180
- _�_ 12
181
- �� 12
182
- ��� 11
183
- _� 11
184
- �_ 11
185
- �� 11
186
- �_ 11
187
- �_ 11
188
- �� 11
189
- _Ц 11
190
- ��_ 11
191
- _�� 11
192
- �� 11
193
- ��_ 11
194
- Ԧ 11
195
- ��_ 11
196
- �� 11
197
- �� 11
198
- _� 11
199
- ��� 11
200
- ��_ 11
201
- ��_ 11
202
- � 11
203
- ��_ 11
204
- ���_ 11
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
- Φ_ 10
218
- � 10
219
- ���_ 10
220
- �� 10
221
- �� 10
222
- �� 10
223
- ��_ 10
224
- �� 10
225
- �� 10
226
- _��_ 9
227
- �� 9
228
- ��� 9
229
- �� 9
230
- �� 9
231
- _�� 9
232
- �� 9
233
- ˦ 9
234
- � 9
235
- �� 9
236
- ϧ_ 9
237
- � 9
238
- �� 9
239
- _�_ 9
240
- �� 9
241
- �� 9
242
- �� 9
243
- _�� 9
244
- _� 9
245
- _�� 9
246
- �� 9
247
- ��� 9
248
- �� 9
249
- �� 9
250
- _� 8
251
- _�� 8
252
- �� 8
253
- �� 8
254
- _��_ 8
255
- ��� 8
256
- _" 8
257
- �� 8
258
- �� 8
259
- �� 8
260
- _�� 8
261
- �� 8
262
- : 8
263
- �� 8
264
- ��� 8
265
- �� 8
266
- Ц� 8
267
- ��� 8
268
- �� 8
269
- _�� 8
270
- �� 7
271
- �� 7
272
- _��� 7
273
- �� 7
274
- __ 7
275
- _�� 7
276
- �� 7
277
- �� 7
278
- �� 7
279
- �� 7
280
- �� 7
281
- �� 7
282
- �� 7
283
- _Ц� 7
284
- ��_ 7
285
- ��� 7
286
- ��� 7
287
- ��_ 7
288
- �� 7
289
- �� 7
290
- �Ҧ 7
291
- �� 7
292
- �Ħ 7
293
- �� 7
294
- _�� 7
295
- ��� 7
296
- ��� 7
297
- �� 7
298
- ��� 7
299
- ��_ 7
300
- ��� 7
301
- � 7
302
- ��_ 7
303
- ��� 7
304
- ���� 6
305
- _�� 6
306
- �_ 6
307
- ��_ 6
308
- ��צ 6
309
- �� 6
310
- _Ԧ 6
311
- _צ� 6
312
- � 6
313
- ��� 6
314
- _��� 6
315
- ���_ 6
316
- �� 6
317
- ����� 6
318
- ��� 6
319
- ��� 6
320
- �� 6
321
- ��� 6
322
- ��� 6
323
- צ� 6
324
- �� 6
325
- ��� 6
326
- ��_ 6
327
- * 6
328
- �� 6
329
- _� 6
330
- �� 6
331
- �� 6
332
- ��צ 6
333
- �� 6
334
- �� 6
335
- ���צ 6
336
- �_ 6
337
- �� 6
338
- ��� 6
339
- �� 6
340
- _¦ 6
341
- _� 6
342
- ��� 6
343
- ��צ� 6
344
- ��� 6
345
- ��� 6
346
- _� 6
347
- æ_ 6
348
- �� 6
349
- ��� 6
350
- _�� 6
351
- ��� 6
352
- ���� 6
353
- �צ� 6
354
- ��� 6
355
- �_ 6
356
- Ӧ 6
357
- �� 6
358
- ��� 6
359
- �� 6
360
- _��� 6
361
- ��� 6
362
- ���� 6
363
- �� 6
364
- ��� 6
365
- ��� 6
366
- �צ� 6
367
- _�� 5
368
- �� 5
369
- ���� 5
370
- �ϧ 5
371
- _�� 5
372
- �Φ 5
373
- _�� 5
374
- ��� 5
375
- *_ 5
376
- ��� 5
377
- ���_ 5
378
- ��_ 5
379
- � 5
380
- ��� 5
381
- �Φ 5
382
- �� 5
383
- ��� 5
384
- צ� 5
385
- צ� 5
386
- _��� 5
387
- _¦� 5
388
- �� 5
389
- ��� 5
390
- ����� 5
391
- ���� 5
392
- �� 5
393
- _�� 5
394
- ��� 5
395
- ��� 5
396
- ��� 5
397
- Ħ_ 5
398
- ��� 5
399
- �� 5
400
- ���_ 5