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
- _ 8664
2
- o 2534
3
- i 2204
4
- a 2154
5
- e 2086
6
- t 1488
7
- n 1469
8
- r 1262
9
- o_ 1097
10
- l 974
11
- s 937
12
- k 880
13
- m 777
14
- u 677
15
- p 676
16
- d 558
17
- a_ 556
18
- v 516
19
- . 514
20
- , 475
21
- ,_ 475
22
- ._ 415
23
- g 379
24
- i_ 365
25
- f 327
26
- e_ 323
27
- _a 322
28
- _p 311
29
- _s 296
30
- _i 295
31
- ti 294
32
- b 291
33
- an 291
34
- j 281
35
- c 274
36
- ta 272
37
- _k 271
38
- nt 270
39
- _t 268
40
- _n 266
41
- en 262
42
- to 254
43
- ek 249
44
- on 249
45
- al 248
46
- _e 245
47
- ri 237
48
- te 236
49
- ro 235
50
- _d 228
51
- er 218
52
- _m 218
53
- re 217
54
- li 213
55
- in 210
56
- ra 208
57
- z 207
58
- no 204
59
- st 201
60
- ia 199
61
- h 191
62
- lo 189
63
- _f 183
64
- tr 179
65
- io 172
66
- to_ 172
67
- vo 172
68
- at 172
69
- _o 171
70
- po 168
71
- me 163
72
- om 162
73
- or 161
74
- ko 158
75
- de 156
76
- � 151
77
- ŭ 151
78
- � 151
79
- _v 150
80
- o. 148
81
- ne 148
82
- pr 146
83
- ci 139
84
- a� 138
85
- aŭ 138
86
- ma 137
87
- la 136
88
- n_ 135
89
- iv 134
90
- il 130
91
- it 130
92
- et 128
93
- _h 126
94
- mo 123
95
- es 120
96
- em 120
97
- _ne 119
98
- is 119
99
- ol 118
100
- o, 116
101
- o,_ 116
102
- o._ 116
103
- s_ 115
104
- ar 115
105
- mi 115
106
- el 113
107
- ni 112
108
- ant 112
109
- pe 111
110
- _r 108
111
- ie 107
112
- no_ 106
113
- ig 105
114
- le 105
115
- do 105
116
- vi 101
117
- ro_ 99
118
- _pr 99
119
- un 97
120
- _de 96
121
- gi 96
122
- ta_ 96
123
- l_ 95
124
- _l 95
125
- tiv 93
126
- va 92
127
- ka 92
128
- su 92
129
- ks 92
130
- os 91
131
- am 90
132
- se 90
133
- si 89
134
- r_ 89
135
- na 88
136
- ono 87
137
- ki 87
138
- _ek 85
139
- pl 84
140
- _se 80
141
- rt 79
142
- ter 79
143
- _al 78
144
- _su 78
145
- ati 78
146
- j_ 77
147
- lo_ 77
148
- nd 77
149
- _po 77
150
- fi 76
151
- pa 75
152
- _an 75
153
- _ti 74
154
- nta 74
155
- sa 74
156
- ent 74
157
- _b 74
158
- _u 73
159
- eks 73
160
- nu 73
161
- _g 72
162
- ik 72
163
- ns 71
164
- _tr 71
165
- kr 71
166
- fr 71
167
- m_ 70
168
- _j 70
169
- di 70
170
- ec 70
171
- ga 70
172
- _ki 70
173
- t_ 69
174
- ng 69
175
- ost 69
176
- a, 67
177
- a,_ 67
178
- sk 66
179
- ia_ 66
180
- do_ 65
181
- so 65
182
- io_ 65
183
- _re 65
184
- per 65
185
- ok 65
186
- _ko 64
187
- ku 64
188
- nte 64
189
- _c 64
190
- _in 64
191
- nk 63
192
- ta� 62
193
- taŭ 62
194
- en_ 62
195
- fa 62
196
- mp 61
197
- ed 61
198
- anta 60
199
- az 60
200
- k_ 60
201
- v_ 60
202
- ve 60
203
- _ma 59
204
- u_ 59
205
- du 58
206
- ort 58
207
- kt 58
208
- mo_ 58
209
- vo_ 57
210
- d_ 57
211
- ili 57
212
- zo 57
213
- _vi 57
214
- ali 57
215
- je 57
216
- igi 57
217
- ur 57
218
- era 56
219
- _du 55
220
- ativ 55
221
- da 55
222
- id 55
223
- _fr 54
224
- S 54
225
- _mi 54
226
- ub 54
227
- fo 54
228
- ic 54
229
- sp 54
230
- nto 53
231
- _ali 53
232
- ho 53
233
- fra 53
234
- ad 53
235
- sub 52
236
- a. 52
237
- pre 52
238
- nom 52
239
- uo 52
240
- ke 52
241
- oj 51
242
- i,_ 51
243
- i, 51
244
- im 51
245
- iva 51
246
- mal 51
247
- ivo 51
248
- sta 51
249
- kri 51
250
- um 50
251
- i. 50
252
- vor 50
253
- vort 50
254
- I 50
255
- post 49
256
- ez 49
257
- tro 49
258
- ko_ 49
259
- eko 49
260
- pos 49
261
- _sub 48
262
- ono_ 48
263
- ir 48
264
- go 48
265
- bi 48
266
- he 48
267
- _pl 47
268
- ul 47
269
- lt 47
270
- bl 47
271
- tivo 47
272
- ri_ 46
273
- _vo 46
274
- � 46
275
- fin 46
276
- re_ 46
277
- lu 46
278
- _te 46
279
- ze 46
280
- _mal 46
281
- alo 45
282
- _nu 45
283
- nti 44
284
- str 44
285
- pro 44
286
- tu 44
287
- i._ 44
288
- kv 44
289
- eni 44
290
- ej 43
291
- ma_ 43
292
- ep 43
293
- _fra 43
294
- _he 42
295
- gi_ 42
296
- _pe 42
297
- ntaŭ 42
298
- vol 42
299
- raz 42
300
- nta� 42
301
- anta� 42
302
- _me 41
303
- fraz 41
304
- skri 41
305
- skr 41
306
- a� 41
307
- rto 41
308
- nst 40
309
- _eks 40
310
- tra 40
311
- _fo 40
312
- bo 40
313
- tiva 40
314
- ra_ 40
315
- ot 40
316
- ivo_ 40
317
- _ant 40
318
- ren 40
319
- _ci 40
320
- ib 40
321
- tivo_ 40
322
- a._ 39
323
- omo 39
324
- ce 39
325
- int 39
326
- ita 38
327
- cio 38
328
- zo_ 38
329
- _vol 38
330
- jo 38
331
- _si 38
332
- _ho 38
333
- _I 38
334
- lon 38
335
- e,_ 38
336
- ba 38
337
- _pa 38
338
- e, 38
339
- ha 38
340
- men 38
341
- ilo 37
342
- _fa 37
343
- iu 37
344
- zi 37
345
- kom 37
346
- met 37
347
- tre 37
348
- us 37
349
- op 36
350
- eb 36
351
- ĵ 36
352
- _mo 36
353
- � 36
354
- la_ 36
355
- nen 36
356
- li_ 36
357
- A 36
358
- _S 36
359
- aĵ 36
360
- ici 36
361
- ano 36
362
- ru 35
363
- e. 35
364
- _nen 35
365
- kon 35
366
- ka_ 35
367
- ' 35
368
- ome 35
369
- K 35
370
- go_ 35
371
- up 35
372
- _ku 35
373
- _so 35
374
- lio 35
375
- ip 35
376
- ag 35
377
- ado 35
378
- emp 35
379
- va_ 35
380
- eg 35
381
- iva_ 35
382
- ans 35
383
- ion 34
384
- _ve 34
385
- _ha 34
386
- _sa 34
387
- sa_ 33
388
- rib 33
389
- as 33
390
- _pos 33
391
- _fraz 33
392
- _post 33
393
- ov 33
394
- orto 33
395
- _no 33
396
- P 33
397
- tem 33
398
- vorto 33
399
- _on 33
400
- skrib 33