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
- _ 2622
2
- e 773
3
- t 520
4
- i 515
5
- a 507
6
- o 495
7
- s 453
8
- n 422
9
- r 391
10
- u 337
11
- l 264
12
- m 234
13
- d 226
14
- e_ 213
15
- c 198
16
- h 188
17
- p 178
18
- s_ 153
19
- re 134
20
- _a 127
21
- _t 127
22
- t_ 127
23
- in 123
24
- m_ 105
1
+ _ 2598
2
+ e 779
3
+ i 547
4
+ t 538
5
+ a 512
6
+ o 496
7
+ s 459
8
+ n 427
9
+ r 397
10
+ u 339
11
+ l 290
12
+ m 241
13
+ e_ 229
14
+ d 228
15
+ c 213
16
+ h 192
17
+ p 184
18
+ s_ 171
19
+ t_ 150
20
+ _t 144
21
+ re 135
22
+ _a 132
23
+ in 128
24
+ m_ 119
25
+ _i 114
26
+ f 104
25
27
  or 103
26
- f 99
27
- b 91
28
- n_ 89
29
- _o 87
30
- g 87
31
- th 84
32
- d_ 84
28
+ b 102
29
+ th 97
30
+ n_ 93
31
+ g 90
32
+ d_ 90
33
+ _o 88
34
+ _e 84
33
35
  er 83
34
- _i 82
36
+ _th 83
35
37
  he 81
36
38
  y 80
39
+ at 79
37
40
  an 79
38
- _e 78
39
- at 78
40
- ,_ 75
41
- , 75
42
- _s 73
43
- on 73
41
+ _s 78
42
+ on 74
43
+ te 74
44
44
  es 72
45
- te 72
46
- _th 70
45
+ _p 70
46
+ r_ 69
47
47
  is 69
48
- _p 65
49
- . 64
50
- v 63
48
+ se 66
49
+ o_ 66
50
+ v 65
51
+ it 64
52
+ w 63
53
+ the 63
51
54
  um 63
52
- o_ 63
53
- se 62
54
- r_ 62
55
- w 60
56
- en 60
55
+ en 62
56
+ _the 61
57
+ _c 59
57
58
  ti 59
58
- it 58
59
+ _b 58
59
60
  nd 58
60
- _d 56
61
- ._ 55
62
- as 52
63
- the 52
61
+ _d 58
62
+ _l 57
63
+ a_ 53
64
+ um_ 52
64
65
  ur 52
66
+ as 52
67
+ y_ 52
68
+ lo 51
65
69
  nt 51
66
- a_ 50
67
- _the 50
68
70
  su 50
69
- _c 49
70
- y_ 49
71
- q 48
71
+ re_ 49
72
+ qu 49
73
+ q 49
72
74
  he_ 48
73
- qu 48
74
- _w 47
75
- um_ 47
76
- _b 47
75
+ _w 48
77
76
  us 46
78
- le 45
77
+ the_ 46
78
+ le 46
79
+ em 45
80
+ f_ 45
79
81
  of 44
80
- em 44
81
82
  si 43
83
+ _m 43
82
84
  ta 43
83
- re_ 43
84
- ed 42
85
- f_ 42
86
85
  ore 42
86
+ k 42
87
87
  _of 42
88
- to 41
89
- k 41
90
- li 40
91
- et 40
88
+ _in 42
89
+ ed 42
90
+ to 42
91
+ li 42
92
+ et 41
93
+ in_ 41
94
+ _r 41
95
+ lor 40
92
96
  ng 40
93
- the_ 39
94
- ea 39
95
97
  of_ 39
96
- _the_ 39
97
98
  is_ 39
98
- _of_ 39
99
+ ea 39
100
+ _h 39
99
101
  and 39
100
- in_ 38
101
- ol 38
102
+ _of_ 39
102
103
  st 38
103
- _m 37
104
- _in 37
104
+ la 38
105
+ ed_ 38
106
+ _f 38
107
+ ol 38
105
108
  de 37
109
+ es_ 36
106
110
  _an 36
107
111
  io 35
108
- _h 35
109
- _r 35
110
- ri 34
111
- ve 34
112
- la 34
112
+ ri 35
113
+ _n 35
113
114
  ar 34
114
- ed_ 34
115
+ ve 34
116
+ co 33
117
+ ing 33
118
+ ra 33
115
119
  ou 33
116
- _f 33
117
120
  ce 33
118
- ing 33
119
- _I 32
121
+ g_ 32
120
122
  ec 32
121
- I 32
122
- lo 32
123
+ ng_ 32
124
+ l_ 32
125
+ nd_ 32
126
+ al 32
127
+ em_ 32
123
128
  ro 32
124
- _l 31
125
- nd_ 31
126
- ng_ 31
127
- g_ 31
128
- em_ 30
129
- el 30
130
- es_ 30
131
- _n 30
132
- ha 30
133
- co 30
134
- ing_ 30
135
- al 30
136
- to_ 30
129
+ to_ 31
130
+ ut 31
131
+ ip 31
132
+ ing_ 31
133
+ _to 31
134
+ ha 31
135
+ no 31
136
+ ne 30
137
137
  ni 30
138
- _to 30
139
- no 29
138
+ el 30
139
+ _u 30
140
+ ci 29
141
+ pa 29
140
142
  di 29
143
+ lore 29
144
+ it_ 29
141
145
  om 29
142
- ra 29
143
- ut 29
144
- am 28
145
- ct 28
146
- _u 28
147
- l_ 28
148
- ne 28
146
+ _v 29
149
147
  ic 28
148
+ _re 28
149
+ ma 28
150
+ ns 28
151
+ and_ 28
152
+ ct 28
153
+ am 28
150
154
  ai 28
151
- _v 27
152
- ion 27
153
- ns 27
155
+ on_ 27
156
+ _to_ 27
154
157
  _and 27
155
- and_ 27
156
- _and_ 27
157
- _re 27
158
- ll 27
159
158
  rem 27
160
- do 26
159
+ ion 27
160
+ do 27
161
+ ll 27
162
+ _lo 27
161
163
  _a_ 26
162
- _to_ 26
164
+ _qu 26
165
+ _co 26
166
+ _q 26
163
167
  sum 26
164
- L 26
165
- _L 26
166
168
  ia 26
169
+ sum_ 25
170
+ _pa 25
171
+ ips 25
172
+ il 25
167
173
  ru 25
168
- _qu 25
169
174
  ps 25
170
- _q 25
171
- pa 25
172
175
  tio 25
173
- ci 25
174
- il 25
175
- un 24
176
- x 24
177
- on_ 24
178
- ui 24
176
+ et_ 25
177
+ x 25
178
+ pl 24
179
179
  ati 24
180
180
  me 24
181
- ss 23
182
- _co 23
183
- orem 23
184
- psu 23
185
- psum 23
186
- _in_ 23
187
- pl 23
181
+ _in_ 24
182
+ ui 24
183
+ un 24
188
184
  rem_ 23
185
+ tr 23
189
186
  hi 23
190
- tion 23
191
187
  or_ 23
192
- ure 22
193
- mo 22
194
- _do 22
195
- se_ 22
196
- ma 22
197
- orem_ 22
198
- tr 22
188
+ _ips 23
189
+ h_ 23
190
+ _ip 23
191
+ ut_ 23
192
+ ex 23
193
+ psum 23
194
+ i_ 23
195
+ at_ 23
196
+ se_ 23
197
+ ss 23
198
+ ipsu 23
199
+ tion 23
200
+ psu 23
201
+ orem 23
202
+ _do 23
203
+ ac 22
199
204
  id 22
205
+ us_ 22
200
206
  im 22
201
- sum_ 22
202
- _pa 22
203
- ac 21
204
- it_ 21
207
+ mo 22
208
+ ure 22
205
209
  nc 21
206
- lor 21
210
+ nt_ 21
211
+ _ma 21
212
+ ur_ 21
213
+ ons 20
214
+ _lor 20
215
+ qui 20
216
+ ge 20
207
217
  _si 20
208
- at_ 20
209
- psum_ 20
210
- i_ 20
211
- ut_ 20
218
+ _no 20
212
219
  tu 20
213
- ge 20
214
- ex 20
215
- ons 19
216
220
  pt 19
217
- Lo 19
218
- Lorem 19
219
- _Lore 19
220
221
  er_ 19
221
- _Lo 19
222
- _Lor 19
223
- Lore 19
224
- qui 19
225
- us_ 19
226
- et_ 19
227
- Lor 19
228
- ab 18
229
- ect 18
222
+ bu 19
230
223
  ain 18
231
- _no 18
232
- be 18
233
- ho 18
234
- as_ 18
235
224
  pe 18
236
- T 18
225
+ ho 18
226
+ ect 18
227
+ _et 18
228
+ ca 18
237
229
  _de 18
238
- ple 17
239
- Ipsu 17
230
+ ab 18
231
+ as_ 18
232
+ be 18
233
+ ple 18
234
+ du 17
235
+ _it 17
236
+ _is 17
237
+ rum_ 17
238
+ _wh 17
239
+ rs 17
240
+ _be 17
240
241
  sa 17
241
- _Ips 17
242
+ _qui 17
242
243
  up 17
243
- bl 17
244
- _T 17
244
+ eas 17
245
245
  vo 17
246
- Ips 17
247
- _et 17
248
- rum 17
249
- _Ip 17
250
- _wh 17
251
- ca 17
252
- _be 17
253
- _Ipsu 17
254
- Ipsum 17
255
- rs 17
246
+ ch 17
256
247
  wh 17
257
248
  pr 17
258
- Ip 17
259
- h_ 17
260
- _is 17
261
- eas 17
262
- ate 16
249
+ am_ 17
250
+ rum 17
251
+ ure_ 17
252
+ bl 17
253
+ _ex 17
254
+ ag 16
263
255
  ep 16
264
- au 16
265
- _ma 16
266
256
  tur 16
257
+ na 16
258
+ ua 16
267
259
  po 16
268
- rum_ 16
269
- cu 16
270
- ch 16
271
- du 16
260
+ bo 16
261
+ ere 16
262
+ lu 16
272
263
  ul 16
264
+ _et_ 16
265
+ con 16
266
+ cu 16
273
267
  olo 16
274
- lu 16
275
- ua 16
276
- ag 16
277
- nt_ 16
278
- _qui 16
279
- ere 16
280
- bu 16
281
- ent 16
268
+ ate 16
269
+ _con 16
282
270
  lea 16
283
- leas 15
271
+ ent 16
272
+ au 16
284
273
  _dol 15
285
- C 15
286
- _dolo 15
287
- dol 15
288
- _is_ 15
274
+ leas 15
289
275
  ter 15
276
+ _pl 15
277
+ olor 15
290
278
  os 15
291
- na 15
292
- _ex 15
293
- _et_ 15
279
+ dolo 15
280
+ _is_ 15
281
+ dol 15
294
282
  tat 15
295
- olor 15
296
- dolor 15
297
- s, 15
298
- s,_ 15
299
283
  ver 15
300
- dolo 15
301
- sur 14
284
+ _se 15
285
+ en_ 14
286
+ _la 14
302
287
  te_ 14
303
- ke 14
304
- ure_ 14
305
288
  so 14
306
- t,_ 14
307
- _con 14
308
- wi 14
309
- _pl 14
310
- t, 14
311
- con 14
289
+ _ple 14
290
+ _g 14
291
+ int 14
312
292
  qua 14
293
+ _ha 14
294
+ wi 14
295
+ sur 14
296
+ plea 14
297
+ ke 14
313
298
  ue 14
314
- ur_ 14
315
- en_ 14
316
- ip 14
299
+ _it_ 13
317
300
  vol 13
318
- _by_ 13
319
- atio 13
320
- ation 13
321
- _plea 13
322
- _ha 13
323
- olu 13
324
- plea 13
325
- sure 13
301
+ _by 13
302
+ ain_ 13
303
+ ir 13
326
304
  _ve 13
327
- _ple 13
305
+ sure 13
306
+ by 13
307
+ res 13
308
+ _al 13
328
309
  her 13
310
+ fi 13
311
+ olu 13
312
+ le_ 13
313
+ _te 13
314
+ ion_ 13
315
+ atio 13
316
+ od 13
329
317
  _mo 13
330
- res 13
331
318
  upt 13
332
- pleas 13
333
319
  by_ 13
334
- od 13
335
- _by 13
336
- by 13
337
- ir 13
338
- Th 13
339
- _Th 13
340
- _volu 12
341
- easu 12
342
- _wi 12
343
- easur 12
344
- _vol 12
345
- ae 12
346
- _fr 12
320
+ _by_ 13
347
321
  olup 12
348
- mp 12
349
- volu 12
322
+ _pr 12
350
323
  sin 12
351
- bo 12
352
- oo 12
353
- olupt 12
354
- am_ 12
324
+ pta 12
355
325
  unt 12
356
- lupta 12
357
- ly 12
358
- asu 12
326
+ lup 12
359
327
  fr 12
328
+ _vo 12
360
329
  lupt 12
361
- pta 12
362
- upta 12
363
- asur 12
364
- leasu 12
365
- ly_ 12
366
- nte 12
367
- age 12
368
- _pr 12
330
+ asu 12
369
331
  da 12
370
- asure 12
371
- lup 12
372
332
  est 12
373
- _vo 12
374
- volup 12
333
+ easu 12
334
+ cc 12
335
+ nte 12
336
+ age 12
337
+ upta 12
338
+ _vol 12
339
+ volu 12
340
+ _li 12
341
+ ore_ 12
342
+ ly 12
343
+ _wi 12
344
+ mp 12
345
+ ae 12
346
+ ly_ 12
347
+ _fr 12
348
+ asur 12
349
+ oo 12
350
+ tur_ 11
351
+ nce 11
352
+ k_ 11
353
+ pain 11
375
354
  fo 11
376
- _y 11
377
- tion_ 11
378
- eq 11
379
- _it 11
380
- cons 11
381
- equ 11
382
- _us 11
383
- cc 11
384
- ib 11
385
- _pain 11
386
- ain_ 11
387
- _te 11
388
- _g 11
389
- B 11
390
- The 11
391
- _se 11
355
+ _on 11
392
356
  oru 11
393
- _The 11
357
+ ib 11
358
+ oi 11
394
359
  pai 11
395
- nce 11
360
+ _us 11
361
+ equ 11
362
+ _y 11
363
+ eq 11
364
+ _pai 11
396
365
  yo 11
397
- _B 11
398
- ion_ 11
366
+ here 11
367
+ tem 11
368
+ orum 11
369
+ cons 11
399
370
  tin 11
400
- ore_ 11
371
+ ini 10
372
+ use 10
373
+ _es 10
374
+ st_ 10
375
+ lat 10
376
+ pu 10
377
+ atu 10
378
+ ll_ 10
379
+ ass 10
380
+ ome 10
381
+ ns_ 10
382
+ ess 10
383
+ que 10
384
+ rat 10
385
+ _tr 10
386
+ ill 10
387
+ ble 10
388
+ rom 10
389
+ _he 10
390
+ _or 10
391
+ res_ 10
392
+ ere_ 10
393
+ rd 10
394
+ ev 10
395
+ ce_ 10
396
+ _su 10
397
+ _so 10
398
+ ibu 10
399
+ om_ 10
400
+ for 10