scylla 0.8.0 → 0.8.29

Sign up to get free protection for your applications and to get access to all the features.
Files changed (93) hide show
  1. data/Gemfile +4 -0
  2. data/Gemfile.lock +9 -1
  3. data/lib/scylla/generator.rb +46 -13
  4. data/lib/scylla/lms/afrikaans.lm +400 -400
  5. data/lib/scylla/lms/arabic.lm +400 -400
  6. data/lib/scylla/lms/bulgarian.lm +400 -400
  7. data/lib/scylla/lms/catalan.lm +399 -399
  8. data/lib/scylla/lms/chinese.lm +400 -400
  9. data/lib/scylla/lms/czech.lm +400 -0
  10. data/lib/scylla/lms/danish.lm +396 -396
  11. data/lib/scylla/lms/dutch.lm +400 -0
  12. data/lib/scylla/lms/english.lm +400 -400
  13. data/lib/scylla/lms/finnish.lm +400 -400
  14. data/lib/scylla/lms/french.lm +398 -398
  15. data/lib/scylla/lms/german.lm +400 -400
  16. data/lib/scylla/lms/greek.lm +400 -400
  17. data/lib/scylla/lms/hebrew.lm +399 -399
  18. data/lib/scylla/lms/hindi.lm +400 -400
  19. data/lib/scylla/lms/icelandic.lm +399 -399
  20. data/lib/scylla/lms/indonesian.lm +400 -400
  21. data/lib/scylla/lms/italian.lm +400 -400
  22. data/lib/scylla/lms/japanese.lm +399 -399
  23. data/lib/scylla/lms/kannada.lm +400 -0
  24. data/lib/scylla/lms/korean.lm +400 -400
  25. data/lib/scylla/lms/marathi.lm +400 -0
  26. data/lib/scylla/lms/norwegian.lm +400 -400
  27. data/lib/scylla/lms/persian.lm +400 -0
  28. data/lib/scylla/lms/polish.lm +400 -400
  29. data/lib/scylla/lms/portuguese.lm +400 -400
  30. data/lib/scylla/lms/romanian.lm +400 -400
  31. data/lib/scylla/lms/russian.lm +400 -400
  32. data/lib/scylla/lms/slovak.lm +400 -400
  33. data/lib/scylla/lms/slovenian.lm +387 -387
  34. data/lib/scylla/lms/spanish.lm +400 -400
  35. data/lib/scylla/lms/swedish.lm +399 -399
  36. data/lib/scylla/lms/tagalog.lm +400 -400
  37. data/lib/scylla/lms/thai.lm +400 -400
  38. data/lib/scylla/lms/turkish.lm +400 -400
  39. data/lib/scylla/lms/vietnamese.lm +400 -400
  40. data/lib/scylla/lms/welsh.lm +398 -398
  41. data/lib/scylla/resources.rb +43 -33
  42. data/lib/scylla/string.rb +2 -2
  43. data/lib/scylla.rb +0 -4
  44. data/pkg/scylla-0.5.0.gem +0 -0
  45. data/scylla.gemspec +1 -1
  46. data/source_texts/afrikaans.txt +330 -81
  47. data/source_texts/arabic.txt +590 -448
  48. data/source_texts/bulgarian.txt +588 -821
  49. data/source_texts/catalan.txt +435 -413
  50. data/source_texts/chinese.txt +526 -100
  51. data/source_texts/czech.txt +237 -0
  52. data/source_texts/danish.txt +233 -184
  53. data/source_texts/dutch.txt +503 -0
  54. data/source_texts/english.txt +673 -70
  55. data/source_texts/finnish.txt +939 -71
  56. data/source_texts/french.txt +879 -465
  57. data/source_texts/german.txt +1236 -137
  58. data/source_texts/greek.txt +488 -139
  59. data/source_texts/hebrew.txt +539 -100
  60. data/source_texts/hindi.txt +254 -100
  61. data/source_texts/icelandic.txt +301 -90
  62. data/source_texts/indonesian.txt +509 -93
  63. data/source_texts/italian.txt +1066 -120
  64. data/source_texts/japanese.txt +1217 -450
  65. data/source_texts/kannada.txt +340 -0
  66. data/source_texts/korean.txt +343 -219
  67. data/source_texts/marathi.txt +237 -0
  68. data/source_texts/norwegian.txt +555 -190
  69. data/source_texts/persian.txt +886 -0
  70. data/source_texts/polish.txt +1013 -90
  71. data/source_texts/portuguese.txt +690 -88
  72. data/source_texts/romanian.txt +436 -103
  73. data/source_texts/russian.txt +1029 -100
  74. data/source_texts/slovak.txt +575 -102
  75. data/source_texts/slovenian.txt +353 -99
  76. data/source_texts/spanish.txt +858 -675
  77. data/source_texts/swedish.txt +558 -488
  78. data/source_texts/tagalog.txt +391 -100
  79. data/source_texts/thai.txt +286 -60
  80. data/source_texts/turkish.txt +635 -87
  81. data/source_texts/vietnamese.txt +300 -92
  82. data/source_texts/welsh.txt +288 -104
  83. data/test/fixtures/lms/danish.lm +314 -314
  84. data/test/fixtures/lms/english.lm +301 -301
  85. data/test/fixtures/lms/french.lm +326 -326
  86. data/test/fixtures/lms/german.lm +331 -331
  87. data/test/fixtures/lms/hindi.lm +191 -191
  88. data/test/fixtures/lms/italian.lm +299 -299
  89. data/test/fixtures/lms/japanese.lm +103 -103
  90. data/test/fixtures/lms/norwegian.lm +309 -309
  91. data/test/fixtures/lms/spanish.lm +331 -331
  92. data/test/generator_test.rb +2 -2
  93. metadata +14 -3
@@ -0,0 +1,400 @@
1
+ _ 5514
2
+ o 1351
3
+ e 1215
4
+ � 1119
5
+ n 1108
6
+ a 1022
7
+ s 894
8
+ t 790
9
+ l 788
10
+ v 770
11
+ i 714
12
+ k 665
13
+ r 538
14
+ d 528
15
+ p 474
16
+ m 473
17
+ � 470
18
+ � 460
19
+ � 423
20
+ u 392
21
+ c 392
22
+ í 374
23
+ � 374
24
+ a_ 368
25
+ á 363
26
+ z 358
27
+ y 337
28
+ n� 323
29
+ _p 314
30
+ _s 310
31
+ h 291
32
+ _v 275
33
+ _n 260
34
+ b 259
35
+ o_ 255
36
+ st 254
37
+ � 240
38
+ ě 237
39
+ e_ 217
40
+ j 217
41
+ ov 209
42
+ en 206
43
+ í_ 202
44
+ �_ 202
45
+ é 184
46
+ � 184
47
+ � 177
48
+ č 177
49
+ sk 177
50
+ i_ 175
51
+ po 167
52
+ ko 165
53
+ ý 162
54
+ _z 162
55
+ � 162
56
+ u_ 161
57
+ ro 160
58
+ na 159
59
+ ní 158
60
+ y_ 157
61
+ _a 153
62
+ _o 150
63
+ lo 145
64
+ � 144
65
+ ř 144
66
+ k� 142
67
+ li 141
68
+ m_ 138
69
+ v_ 138
70
+ _d 134
71
+ _k 132
72
+ os 125
73
+ _po 124
74
+ od 124
75
+ ž 123
76
+ � 123
77
+ v� 122
78
+ ch 121
79
+ sl 116
80
+ é_ 116
81
+ �_ 116
82
+ la 116
83
+ ve 115
84
+ _b 115
85
+ al 115
86
+ pr 115
87
+ t� 112
88
+ te 111
89
+ _a_ 111
90
+ le 111
91
+ l_ 109
92
+ _v_ 109
93
+ _r 108
94
+ š 107
95
+ n� 106
96
+ em 105
97
+ es 103
98
+ na_ 103
99
+ by 102
100
+ ně 101
101
+ _t 99
102
+ _pr 98
103
+ no 96
104
+ _� 96
105
+ _j 95
106
+ _č 95
107
+ če 90
108
+ ho 90
109
+ ce 90
110
+ �e 90
111
+ ra 89
112
+ do 86
113
+ ti 86
114
+ va 86
115
+ ni 86
116
+ _na 85
117
+ ch_ 84
118
+ h_ 84
119
+ ná 84
120
+ �_ 83
121
+ ou 83
122
+ _by 82
123
+ yl 82
124
+ ze 82
125
+ ě_ 82
126
+ byl 82
127
+ de 81
128
+ an 80
129
+ ta 78
130
+ �e 77
131
+ ře 77
132
+ ic 76
133
+ ké 76
134
+ _m 76
135
+ ed 75
136
+ lov 74
137
+ se 73
138
+ _st 73
139
+ p� 73
140
+ ne 72
141
+ ů 72
142
+ � 72
143
+ to 71
144
+ slo 70
145
+ ak 70
146
+ sk� 70
147
+ př 69
148
+ ven 68
149
+ je 68
150
+ sko 67
151
+ ck 67
152
+ ol 66
153
+ dn 65
154
+ ns 65
155
+ t_ 65
156
+ _p� 65
157
+ �t 64
158
+ is 64
159
+ ove 64
160
+ _n� 63
161
+ k_ 63
162
+ vo 63
163
+ ce_ 63
164
+ re 63
165
+ vá 62
166
+ r� 62
167
+ il 62
168
+ _se 62
169
+ el 62
170
+ nsk 61
171
+ za 61
172
+ la_ 61
173
+ _do 61
174
+ st� 61
175
+ in 60
176
+ ob 60
177
+ esk 60
178
+ �es 59
179
+ at 59
180
+ ens 59
181
+ se_ 57
182
+ ci 57
183
+ em_ 56
184
+ át 56
185
+ �n 55
186
+ ka 55
187
+ �_ 55
188
+ ý_ 55
189
+ �l 54
190
+ n_ 54
191
+ it 54
192
+ lo_ 54
193
+ _ne 53
194
+ osl 52
195
+ _za 52
196
+ ho_ 52
197
+ ný 52
198
+ m� 52
199
+ ost 51
200
+ _ro 51
201
+ án 51
202
+ tn 51
203
+ pro 50
204
+ me 50
205
+ on 50
206
+ ck� 50
207
+ ik 49
208
+ _od 49
209
+ ec 49
210
+ l� 48
211
+ ej 48
212
+ ick 48
213
+ ova 48
214
+ ad 47
215
+ ou_ 47
216
+ o� 47
217
+ tá 47
218
+ ov� 47
219
+ er 47
220
+ ž_ 47
221
+ �_ 47
222
+ ýc 47
223
+ �c 47
224
+ sta 47
225
+ li_ 46
226
+ ký 46
227
+ �ch 46
228
+ kos 45
229
+ kt 44
230
+ ja 44
231
+ vy 44
232
+ ku 43
233
+ ím 43
234
+ �m 43
235
+ mu 43
236
+ �_ 42
237
+ mi 42
238
+ ky 42
239
+ oc 42
240
+ ál 42
241
+ _re 41
242
+ et 41
243
+ ot 41
244
+ s_ 41
245
+ e� 40
246
+ av 40
247
+ pol 39
248
+ _ja 39
249
+ om 39
250
+ or 39
251
+ ky_ 38
252
+ ist 38
253
+ tic 37
254
+ en� 37
255
+ ez 37
256
+ ok 37
257
+ so 37
258
+ á_ 37
259
+ v� 37
260
+ ac 37
261
+ _je 37
262
+ tr 37
263
+ rá 37
264
+ �t 36
265
+ � 36
266
+ � 36
267
+ ko_ 36
268
+ ět 36
269
+ vi 36
270
+ _n� 36
271
+ vě 36
272
+ t� 36
273
+ � 36
274
+ ln 36
275
+ vn 36
276
+ �_ 35
277
+ ev 35
278
+ _vy 35
279
+ _ob 35
280
+ ů_ 35
281
+ �ho 34
282
+ �h 34
283
+ nov 34
284
+ nt 34
285
+ tí 34
286
+ _l 34
287
+ éh 34
288
+ ým 34
289
+ ka_ 34
290
+ �m 34
291
+ kon 34
292
+ tu 34
293
+ _u 34
294
+ ú 33
295
+ m� 33
296
+ val 33
297
+ � 33
298
+ id 33
299
+ d� 33
300
+ da 33
301
+ ep 33
302
+ _i 33
303
+ ci_ 33
304
+ _� 32
305
+ f 32
306
+ _ú 32
307
+ mí 32
308
+ mě 32
309
+ z� 32
310
+ odn 32
311
+ sp 32
312
+ oj 32
313
+ _� 32
314
+ _h 32
315
+ zn 31
316
+ _v� 31
317
+ up 31
318
+ d_ 31
319
+ vý 31
320
+ ter 31
321
+ �n� 31
322
+ �m_ 30
323
+ iv 30
324
+ íc 30
325
+ lá 30
326
+ pu 30
327
+ yl_ 30
328
+ mo 30
329
+ �c 30
330
+ rod 30
331
+ sti 30
332
+ al_ 30
333
+ hl 30
334
+ kte 29
335
+ op 29
336
+ er� 29
337
+ _kt 29
338
+ _s_ 29
339
+ ár 29
340
+ az 29
341
+ ěm 29
342
+ nu 29
343
+ ož 29
344
+ �m 29
345
+ �r 29
346
+ ar 29
347
+ am 29
348
+ ji 29
349
+ oz 28
350
+ zem 28
351
+ vn� 28
352
+ _ve 28
353
+ a� 28
354
+ né 28
355
+ bo 28
356
+ �ro 28
357
+ ny 28
358
+ ny_ 27
359
+ �í 27
360
+ as 27
361
+ �� 27
362
+ _sl 27
363
+ ř� 27
364
+ dy 27
365
+ tn� 26
366
+ z_ 26
367
+ vl 26
368
+ g 26
369
+ _z� 26
370
+ kr 26
371
+ _so 26
372
+ ech 26
373
+ mi_ 25
374
+ roc 25
375
+ ali 25
376
+ ku_ 25
377
+ ma 25
378
+ spo 25
379
+ tv 25
380
+ ly 25
381
+ dn� 25
382
+ _ko 25
383
+ �v 25
384
+ to_ 25
385
+ oli 25
386
+ nos 25
387
+ r_ 25
388
+ ži 25
389
+ �i 25
390
+ sa 25
391
+ ly_ 25
392
+ vat 24
393
+ _k_ 24
394
+ jak 24
395
+ tel 24
396
+ oce 24
397
+ zi 24
398
+ š� 24
399
+ čn 24
400
+ c� 24