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
@@ -1,400 +1,400 @@
1
- _ 3692
2
- e 1020
3
- n 845
4
- a 787
5
- i 693
6
- t 684
7
- o 626
8
- s 572
9
- r 545
10
- l 453
11
- h 416
12
- d 352
13
- e_ 343
14
- g 317
15
- c 303
16
- an 270
17
- _t 254
18
- th 238
19
- u 233
20
- m 213
21
- f 206
22
- ng 201
23
- in 195
24
- s_ 194
25
- _th 193
26
- he 191
27
- _a 190
28
- d_ 188
29
- the 168
30
- n_ 166
31
- he_ 157
32
- _the 152
33
- er 146
34
- _the_ 143
35
- the_ 143
36
- w 134
37
- ,_ 132
38
- , 132
39
- is 131
40
- _o 130
41
- nd 126
42
- p 126
43
- _i 114
44
- h_ 114
45
- es 110
46
- on 105
47
- ti 102
48
- y 102
49
- v 99
50
- and 98
51
- nd_ 97
52
- en 96
53
- re 96
54
- la 93
55
- of 93
56
- t_ 93
57
- f_ 93
58
- or 92
59
- at 92
60
- _of 91
61
- of_ 89
62
- _of_ 89
63
- li 89
64
- and_ 88
65
- _s 87
66
- _an 85
67
- _l 85
68
- b 83
69
- gl 81
70
- _in 81
71
- _w 80
72
- ed 79
73
- al 78
74
- _and_ 78
75
- ngl 78
76
- _and 78
77
- _E 77
78
- E 77
79
- y_ 76
80
- . 74
81
- sh 73
82
- om 72
83
- ro 71
84
- ic 70
85
- _c 70
86
- ish 69
87
- o_ 69
88
- ri 69
89
- ._ 69
90
- te 69
91
- ma 67
92
- nt 67
93
- as 67
94
- ce 67
95
- ve 66
96
- Eng 65
97
- _Eng 65
98
- _En 65
99
- En 65
100
- _Engl 65
101
- Engl 65
102
- st 64
103
- ing 63
104
- ar 62
105
- lan 62
106
- ge 61
107
- gli 60
108
- lis 60
109
- ed_ 60
110
- ngli 60
111
- le 59
112
- Engli 59
113
- nglis 59
114
- glis 59
115
- glish 58
116
- lish 58
117
- co 58
118
- in_ 58
119
- _la 57
120
- ua 57
121
- it 56
122
- nc 55
123
- r_ 55
124
- gu 54
125
- to 54
126
- sh_ 53
127
- _b 53
128
- ish_ 53
129
- ngu 53
130
- g_ 52
131
- ngua 51
132
- gua 51
133
- _d 51
134
- ni 51
135
- es_ 51
136
- ng_ 51
137
- io 50
138
- rm 50
139
- ang 50
140
- man 50
141
- to_ 49
142
- se 49
143
- ag 49
144
- age 47
145
- _f 47
146
- l_ 47
147
- _lan 46
148
- lang 46
149
- lish_ 45
150
- ati 45
151
- angua 45
152
- _e 45
153
- nguag 45
154
- _lang 45
155
- uage 45
156
- guag 45
157
- uag 45
158
- langu 45
159
- guage 45
160
- angu 45
161
- ion 44
162
- a_ 44
163
- ur 44
164
- di 43
165
- el 43
166
- rma 42
167
- _p 42
168
- ea 42
169
- ing_ 42
170
- as_ 41
171
- _to 41
172
- _to_ 41
173
- _in_ 40
174
- th_ 40
175
- ca 40
176
- an_ 40
177
- _r 39
178
- rman 38
179
- ra 38
180
- ia 38
181
- _co 38
182
- ha 37
183
- me 37
184
- m_ 36
185
- lo 36
186
- G 36
187
- si 36
188
- _G 36
189
- ll 35
190
- de 35
191
- fr 35
192
- ec 35
193
- erm 34
194
- on_ 34
195
- ow 34
196
- s, 34
197
- er_ 34
198
- s,_ 34
199
- ly 34
200
- k 33
201
- al_ 33
202
- _fr 32
203
- tio 32
204
- nce 32
205
- tion 32
206
- _n 32
207
- ou 32
208
- Ge 31
209
- ge_ 31
210
- S 31
211
- pe 31
212
- na 31
213
- _Ge 31
214
- _re 31
215
- ent 31
216
- erman 30
217
- be 30
218
- _Ger 30
219
- Germa 30
220
- erma 30
221
- ch 30
222
- Ger 30
223
- _S 30
224
- ts 30
225
- _Germ 30
226
- Germ 30
227
- _m 29
228
- x 29
229
- ly_ 29
230
- iv 28
231
- no 28
232
- ns 28
233
- om_ 28
234
- I 27
235
- c_ 27
236
- wo 27
237
- st_ 27
238
- ce_ 27
239
- _as 27
240
- age_ 27
241
- wi 27
242
- uage_ 26
243
- ne 26
244
- ic_ 26
245
- ive 26
246
- _I 26
247
- ta 26
248
- A 25
249
- rom 25
250
- is_ 25
251
- atio 25
252
- _wo 25
253
- ct 25
254
- _wor 25
255
- we 25
256
- ani 25
257
- wor 25
258
- nic 25
259
- _A 25
260
- ation 25
261
- _a_ 25
262
- ot 24
263
- _fro 24
264
- rt 24
265
- _as_ 24
266
- enc 24
267
- fro 24
268
- from 24
269
- from_ 24
270
- ts_ 24
271
- rom_ 24
272
- _from 24
273
- pa 23
274
- _h 23
275
- nce_ 23
276
- re_ 23
277
- N 22
278
- mani 22
279
- _B 22
280
- ion_ 22
281
- ted 22
282
- _F 22
283
- ol 22
284
- _N 22
285
- ate 22
286
- ted_ 22
287
- F 22
288
- _is 22
289
- tu 22
290
- ut 22
291
- B 22
292
- _be 22
293
- manic 21
294
- _di 21
295
- anic 21
296
- ve_ 21
297
- rmani 21
298
- ie 21
299
- ry 21
300
- rd 21
301
- hi 21
302
- sp 21
303
- at_ 20
304
- se_ 20
305
- ter 20
306
- tin 20
307
- _is_ 20
308
- so 20
309
- her 20
310
- us 20
311
- ver 20
312
- fi 20
313
- ica 19
314
- com 19
315
- nic_ 19
316
- _v 19
317
- all 19
318
- ld 19
319
- su 19
320
- ges 19
321
- anic_ 18
322
- No 18
323
- anc 18
324
- _No 18
325
- ord 18
326
- if 18
327
- po 18
328
- ages 18
329
- h,_ 18
330
- _g 18
331
- ss 18
332
- tr 18
333
- h, 18
334
- ir 17
335
- rs 17
336
- tur 17
337
- ence 17
338
- _li 17
339
- uages 17
340
- rit 17
341
- cen 17
342
- ist 17
343
- mp 17
344
- con 17
345
- ch_ 17
346
- ther 17
347
- ue 17
348
- mo 17
349
- _Br 16
350
- ect 16
351
- tion_ 16
352
- orm 16
353
- _L 16
354
- _T 16
355
- L 16
356
- rn 16
357
- T 16
358
- pl 16
359
- ial 16
360
- _word 16
361
- _th_ 16
362
- am 16
363
- Br 16
364
- nt_ 16
365
- word 16
366
- O 15
367
- or_ 15
368
- ges_ 15
369
- ac 15
370
- ant 15
371
- me_ 15
372
- _Brit 15
373
- mi 15
374
- hat 15
375
- _O 15
376
- ds 15
377
- ad 15
378
- lat 15
379
- wa 15
380
- Nor 15
381
- _Nor 15
382
- land 15
383
- en_ 15
384
- op 15
385
- iti 15
386
- _Bri 15
387
- ran 15
388
- do 15
389
- _ha 15
390
- Bri 15
391
- Brit 15
392
- _no 15
393
- _wa 15
394
- ex 15
395
- ev 15
396
- _wi 15
397
- _wh 15
398
- wh 15
399
- hat_ 15
400
- pr 14
1
+ _ 18778
2
+ e 5609
3
+ t 4175
4
+ n 3756
5
+ a 3611
6
+ i 3331
7
+ o 3167
8
+ s 2888
9
+ r 2806
10
+ h 2421
11
+ e_ 2062
12
+ d 1953
13
+ l 1928
14
+ _t 1719
15
+ th 1568
16
+ c 1377
17
+ s_ 1355
18
+ he 1352
19
+ _th 1323
20
+ _a 1261
21
+ d_ 1245
22
+ the 1241
23
+ u 1130
24
+ g 1061
25
+ he_ 1060
26
+ in 1034
27
+ m 1018
28
+ f 963
29
+ an 954
30
+ n_ 868
31
+ p 815
32
+ _i 790
33
+ nd 756
34
+ w 729
35
+ re 703
36
+ t_ 678
37
+ _o 641
38
+ nd_ 636
39
+ y 630
40
+ er 625
41
+ en 624
42
+ and 608
43
+ _s 601
44
+ ng 587
45
+ on 581
46
+ b 575
47
+ y_ 525
48
+ _w 508
49
+ ar 506
50
+ ed 496
51
+ is 489
52
+ es 488
53
+ _an 476
54
+ _in 470
55
+ ed_ 469
56
+ te 463
57
+ _c 463
58
+ _e 463
59
+ or 444
60
+ ti 438
61
+ st 430
62
+ it 426
63
+ h_ 422
64
+ of 421
65
+ la 414
66
+ _of 414
67
+ f_ 414
68
+ nt 404
69
+ as 403
70
+ of_ 400
71
+ _b 398
72
+ v 390
73
+ at 385
74
+ r_ 381
75
+ ri 370
76
+ _f 369
77
+ in_ 363
78
+ al 357
79
+ _p 352
80
+ ro 323
81
+ ing 307
82
+ as_ 297
83
+ re_ 297
84
+ to 292
85
+ _m 282
86
+ co 281
87
+ g_ 279
88
+ o_ 279
89
+ de 278
90
+ ng_ 274
91
+ om 260
92
+ l_ 260
93
+ io 258
94
+ le 255
95
+ ou 254
96
+ li 250
97
+ _l 250
98
+ es_ 248
99
+ _r 246
100
+ se 245
101
+ me 244
102
+ ve 242
103
+ _en 241
104
+ ea 236
105
+ _h 236
106
+ ch 234
107
+ a_ 231
108
+ ur 227
109
+ on_ 226
110
+ is_ 223
111
+ ion 222
112
+ gl 220
113
+ ent 218
114
+ lan 216
115
+ ngl 216
116
+ eng 214
117
+ ce 214
118
+ _co 213
119
+ _to 212
120
+ er_ 211
121
+ ic 209
122
+ to_ 206
123
+ _d 203
124
+ st_ 197
125
+ _ar 196
126
+ hi 195
127
+ ha 193
128
+ _is 190
129
+ k 189
130
+ ra 188
131
+ si 188
132
+ un 180
133
+ m_ 180
134
+ nc 178
135
+ al_ 178
136
+ _a_ 176
137
+ _n 171
138
+ ns 168
139
+ tr 167
140
+ fo 167
141
+ pe 161
142
+ ll 159
143
+ _re 159
144
+ wa 158
145
+ th_ 155
146
+ ma 155
147
+ _fo 154
148
+ rt 152
149
+ na 151
150
+ ne 151
151
+ el 150
152
+ her 150
153
+ ly 150
154
+ ly_ 148
155
+ are 147
156
+ po 147
157
+ tio 145
158
+ gla 145
159
+ ere 145
160
+ no 145
161
+ ec 145
162
+ ge 144
163
+ sh 143
164
+ be 143
165
+ _as 142
166
+ mo 142
167
+ ho 141
168
+ ca 139
169
+ ol 138
170
+ _wa 136
171
+ ie 135
172
+ ch_ 135
173
+ we 132
174
+ lo 130
175
+ ta 130
176
+ ni 128
177
+ est 128
178
+ _u 126
179
+ ted 126
180
+ ot 126
181
+ pr 125
182
+ il 124
183
+ om_ 124
184
+ ts 123
185
+ _be 123
186
+ di 121
187
+ ct 121
188
+ tu 120
189
+ wh 120
190
+ x 119
191
+ pa 118
192
+ os 118
193
+ ati 117
194
+ ts_ 117
195
+ wi 117
196
+ op 116
197
+ rom 116
198
+ ate 116
199
+ ai 114
200
+ fr 114
201
+ an_ 114
202
+ _wh 113
203
+ _fr 112
204
+ _s_ 112
205
+ ow 112
206
+ nt_ 111
207
+ ish 111
208
+ or_ 110
209
+ _ha 110
210
+ su 110
211
+ for 109
212
+ ry 108
213
+ ter 108
214
+ _mo 107
215
+ ia 107
216
+ am 107
217
+ rs 106
218
+ _pr 106
219
+ us 105
220
+ _by 105
221
+ by_ 105
222
+ by 105
223
+ _wi 104
224
+ _la 103
225
+ em 102
226
+ con 102
227
+ so 102
228
+ ry_ 102
229
+ iv 100
230
+ ex 100
231
+ _g 99
232
+ et 99
233
+ was 97
234
+ me_ 96
235
+ ad 96
236
+ ut 96
237
+ ig 95
238
+ sh_ 95
239
+ le_ 95
240
+ cl 94
241
+ mi 94
242
+ _it 94
243
+ ci 93
244
+ wo 93
245
+ ul 93
246
+ ac 92
247
+ inc 92
248
+ oun 91
249
+ fro 91
250
+ ons 91
251
+ tur 91
252
+ uc 90
253
+ ver 89
254
+ ns_ 89
255
+ _pa 88
256
+ ir 88
257
+ ee 87
258
+ do 87
259
+ _ma 87
260
+ _on 86
261
+ ith 86
262
+ ce_ 86
263
+ _we 85
264
+ wit 85
265
+ lis 85
266
+ ies 85
267
+ tin 85
268
+ mp 84
269
+ du 84
270
+ at_ 84
271
+ nce 82
272
+ rl 81
273
+ all 81
274
+ ld 81
275
+ _de 81
276
+ ev 81
277
+ _no 80
278
+ id 80
279
+ _k 80
280
+ _su 80
281
+ lu 80
282
+ iti 79
283
+ te_ 79
284
+ pl 78
285
+ im 78
286
+ fi 77
287
+ en_ 77
288
+ _te 77
289
+ ov 77
290
+ _se 76
291
+ sp 76
292
+ art 74
293
+ vi 74
294
+ ss 73
295
+ par 73
296
+ gh 73
297
+ rs_ 73
298
+ rea 72
299
+ ain 72
300
+ ag 72
301
+ rit 71
302
+ man 71
303
+ gi 71
304
+ od 71
305
+ ite 71
306
+ rn 69
307
+ res 69
308
+ it_ 69
309
+ br 68
310
+ ve_ 68
311
+ whi 68
312
+ gli 68
313
+ ist 67
314
+ ntr 67
315
+ _un 67
316
+ und 67
317
+ _so 65
318
+ cen 65
319
+ _st 64
320
+ _wo 63
321
+ ove 63
322
+ ost 63
323
+ men 63
324
+ der 63
325
+ int 62
326
+ _si 62
327
+ lar 62
328
+ ty 62
329
+ ud 61
330
+ _ce 61
331
+ ki 61
332
+ pro 60
333
+ _br 60
334
+ _po 60
335
+ nti 60
336
+ eg 59
337
+ ive 59
338
+ rin 59
339
+ _pe 59
340
+ ern 59
341
+ rm 59
342
+ cou 59
343
+ ug 59
344
+ ld_ 59
345
+ ba 58
346
+ xt 58
347
+ rou 57
348
+ ort 57
349
+ _al 57
350
+ ame 57
351
+ ext 57
352
+ uri 56
353
+ ine 56
354
+ has 56
355
+ ue 56
356
+ lat 56
357
+ ect 56
358
+ _le 55
359
+ oth 55
360
+ rd 55
361
+ ers 55
362
+ sc 55
363
+ bo 55
364
+ wor 55
365
+ gr 55
366
+ kin 55
367
+ eve 54
368
+ se_ 54
369
+ clu 54
370
+ ica 54
371
+ wer 54
372
+ com 53
373
+ his 53
374
+ av 53
375
+ uch 53
376
+ ear 52
377
+ bri 52
378
+ _lo 52
379
+ ls 52
380
+ cr 52
381
+ ona 52
382
+ nal 52
383
+ eat 52
384
+ ide 51
385
+ rc 51
386
+ rie 51
387
+ tra 51
388
+ ori 51
389
+ sed 50
390
+ ga 50
391
+ _at 50
392
+ cal 50
393
+ de_ 50
394
+ rg 49
395
+ ncl 49
396
+ red 49
397
+ va 49
398
+ _ki 49
399
+ xt_ 49
400
+ ugh 49