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
- _ 1490
2
- a 336
3
- r 312
4
- n 283
5
- i 254
6
- u 245
7
- e 242
8
- s 194
9
- t 176
10
- 175
11
- l 166
12
- g 157
13
- k 143
14
- m 135
15
- f 132
16
- r_ 110
17
- �_ 79
18
- v 74
19
- ar 73
20
- 71
21
- _s 70
22
- o 70
23
- a63
24
- 63
25
- j 62
26
- a_ 60
27
- m_ 60
28
- 55
29
- _f 55
30
- in 55
31
- i_ 54
32
- _e 53
33
- n_ 53
34
- u_ 52
35
- _a 51
36
- um 48
37
- ur 48
38
- h 47
39
- _� 46
40
- . 46
41
- d 46
42
- a�_ 45
43
- ._ 45
44
- g_ 45
45
- st 44
46
- b 44
47
- er 44
48
- 43
49
- 43
50
- �_ 42
51
- nn 42
52
- _�_ 41
53
- ei 40
54
- _v 40
55
- nu 40
56
- 38
57
- i38
58
- y 37
59
- um_ 37
60
- _h 37
61
- ir 36
62
- _a36
63
- an 36
64
- _� 36
65
- _o 36
66
- _ 36
67
- _� 36
68
- ve 35
69
- p 35
70
- og 34
71
- ur_ 34
72
- _og_ 33
73
- _og 33
74
- un 33
75
- og_ 33
76
- _m 32
77
- ar_ 31
78
- ta 30
79
- _a�_ 30
80
- �u 29
81
- na 29
82
- en 29
83
- ri 28
84
- ti 28
85
- la 28
86
- lu 28
87
- _�_ 26
88
- _ve 26
89
- 26
90
- t_ 25
91
- _b 25
92
- �i 25
93
- nd 24
94
- ja 24
95
- ng 24
96
- ki 23
97
- r� 23
98
- _u 23
99
- kk 23
100
- ra 23
101
- ir_ 22
102
- i�_ 22
103
- sl 21
104
- _g 21
105
- ef 21
106
- em 20
107
- tu 20
108
- _t 20
109
- ku 20
110
- inn 19
111
- _l 19
112
- se 19
113
- sk 19
114
- il 19
115
- ga 18
116
- ver 18
117
- 18
118
- �a 18
119
- _n 18
120
- af 17
121
- ni 17
122
- _er 17
1
+ _ 3270
2
+ 1142
3
+ r 775
4
+ a 756
5
+ n 717
6
+ i 641
7
+ s 544
8
+ e 517
9
+ l 417
10
+ t 401
11
+ u 389
12
+ _� 355
13
+ 327
14
+ ð 327
15
+ g 310
16
+ m 304
17
+ r_ 304
18
+ f 255
19
+ k 233
20
+ d 217
21
+ á 191
22
+ o 191
23
+ 191
24
+ _s 185
25
+ í 176
26
+ ð_ 176
27
+ �_ 176
28
+ 176
29
+ v 175
30
+ ar 162
31
+ _e 158
32
+ i_ 153
33
+ nd 152
34
+ in 147
35
+ an 145
36
+ a_ 145
37
+ h 137
38
+ st 129
39
+ m_ 129
40
+ er 123
41
+ 122
42
+ þ 122
43
+ _á 113
44
+ 110
45
+ g_ 107
46
+ j 107
47
+ 107
48
+ _h 106
49
+ n_ 104
50
+ ar_ 104
51
+ r� 101
52
+ la 99
53
+ um 99
54
+ _f 92
55
+ _v 90
56
+ ö 89
57
+ a89
58
+ u_ 89
59
+ i� 89
60
+ 89
61
+ ir 88
62
+ 88
63
+ 88
64
+ 88
65
+ ó 88
66
+ j87
67
+ nn 86
68
+ um_ 86
69
+ and 86
70
+ _o 85
71
+ _a 84
72
+ t_ 84
73
+ og 83
74
+ á_ 83
75
+ �_ 83
76
+ en 82
77
+ di 82
78
+ og_ 82
79
+ _og 82
80
+ ri 82
81
+ ti 79
82
+ ei 78
83
+ sl 74
84
+ ur 74
85
+ _er 74
86
+ ir_ 72
87
+ na 71
88
+ ndi 70
89
+ ng 70
90
+ lan 70
91
+ b 65
92
+ le 65
93
+ ta 64
94
+ 64
95
+ æ 64
96
+ ur_ 63
97
+ _t 60
98
+ y 59
99
+ s_ 59
100
+ _n 58
101
+ ga 57
102
+ un 57
103
+ ve 56
104
+ ís 56
105
+ �sl 56
106
+ �s 56
107
+ _l 55
108
+ _u 55
109
+ _m 52
110
+ í_ 51
111
+ �_ 51
112
+ p 50
113
+ il 49
114
+ se 49
115
+ or 49
116
+ af 48
117
+ ki 48
118
+ 48
119
+ ra 48
120
+ sk 48
121
+ ing 47
122
+ ni 46
123
+ er_ 46
124
+ al 45
125
+ ru 45
126
+ l_ 44
127
+ is 44
128
+ nu 44
129
+ _k 44
130
+ va 44
131
+ ár 43
132
+ �r 43
133
+ sla 43
134
+ � 40
135
+ ns 40
136
+ s� 40
137
+ me 40
138
+ ú 40
139
+ ha 39
140
+ ða 38
141
+ rn 38
142
+ _r 38
143
+ ri� 38
144
+ �a 38
145
+ ði 37
146
+ _a� 37
147
+ di_ 37
148
+ eg 37
149
+ �i 37
150
+ am 37
151
+ d_ 37
152
+ _va 37
153
+ _st 37
154
+ gu 36
155
+ _se 36
156
+ inn 35
157
+ lu 35
158
+ st_ 35
159
+ l� 35
160
+ ld 35
161
+ ef 34
162
+ þa 34
163
+ �a 34
164
+ v� 34
165
+ _s� 34
166
+ em 33
167
+ tt 33
168
+ da 33
169
+ ru_ 32
170
+ il_ 32
171
+ rs 32
172
+ var 32
173
+ he 32
174
+ _g 31
175
+ _en 31
176
+ _ha 31
177
+ t� 30
178
+ til 30
179
+ n� 30
180
+ sa 30
181
+ fl 30
182
+ rð 30
183
+ �u 30
184
+ ðu 30
185
+ �r 30
186
+ ór 30
187
+ et 29
188
+ sem 29
189
+ _r� 29
190
+ ein 29
191
+ em_ 29
192
+ �e 29
193
+ _ti 29
194
+ tj 29
195
+ þe 29
196
+ ku 28
197
+ �ri 28
198
+ ver 28
199
+ ka 28
200
+ ma 27
201
+ tu 27
202
+ h� 27
203
+ gi 27
204
+ tj� 27
205
+ eru 27
206
+ gar 27
207
+ _b 27
208
+ re 27
209
+ stj 26
210
+ na_ 26
211
+ _me 26
212
+ _um 26
213
+ �rn 26
214
+ ns_ 25
215
+ _n� 25
216
+ vi 25
217
+ �l 25
218
+ öl 25
219
+ jö 25
220
+ e� 25
221
+ eð 25
222
+ _he 25
223
+ ta_ 24
224
+ end 24
225
+ nn_ 24
226
+ rí 24
227
+ f� 24
228
+ kk 24
229
+ � 24
230
+ und 24
231
+ len 24
232
+ en_ 24
233
+ ko 24
234
+ nd_ 24
235
+ ti_ 24
236
+ m� 24
237
+ _la 24
238
+ ý 24
239
+ fa 23
240
+ _ve 23
241
+ ík 23
242
+ f_ 23
243
+ �k 23
244
+ ds 23
245
+ nar 23
246
+ nds 23
247
+ fn 23
248
+ ag 22
249
+ _sa 22
250
+ nga 22
251
+ sam 22
252
+ sv 22
253
+ rá 22
254
+ _h� 22
255
+ ins 22
256
+ ll 22
257
+ ann 22
258
+ fr 21
259
+ �i_ 21
260
+ si 21
261
+ _d 21
262
+ li 21
263
+ fu 21
264
+ é 21
265
+ � 21
266
+ no 20
267
+ me� 20
268
+ ega 20
269
+ ss 20
270
+ _no 20
271
+ �ki 20
272
+ mi 20
273
+ _af 20
274
+ í� 19
275
+ kis 19
276
+ rl 19
277
+ rr 19
278
+ fi 19
279
+ num 19
280
+ �� 19
281
+ dir 19
282
+ b� 19
283
+ þ� 18
284
+ haf 18
285
+ �� 18
286
+ nna 18
287
+ �� 18
288
+ �a� 18
289
+ ó� 18
290
+ _un 18
291
+ yr 18
292
+ sta 18
293
+ _sk 18
294
+ ey 18
295
+ �ð 18
296
+ fy 17
297
+ _vi 17
298
+ fo 17
299
+ �j 17
300
+ k_ 17
301
+ ut 17
302
+ _fo 17
303
+ þj 17
123
304
  ek 17
124
- nn_ 17
125
- sem 16
126
- eg 16
127
- _se 16
128
- num 16
129
- _ver 16
130
- gi 15
131
- gu 15
132
- em_ 15
133
- ag 15
134
- es 15
135
- mi 15
136
- ,_ 15
137
- _sem_ 15
138
- , 15
139
- ka 15
140
- da 15
141
- _sem 15
142
- sem_ 15
143
- b� 14
144
- am 14
145
- l� 14
146
- nar 14
147
- �e 14
148
- �k 14
149
- yr 14
150
- �i_ 14
151
- s_ 14
152
- _�e 14
153
- ur 14
154
- j� 14
155
- rf 14
156
- al 13
157
- �g 13
158
- S 13
159
- tt 13
160
- fl 13
161
- li 13
162
- ki_ 13
163
- ne 13
164
- l_ 13
165
- ge 13
166
- vi 13
167
- ll 13
168
- re 13
169
- u� 13
170
- ey 12
171
- ekk 12
172
- he 12
173
- num_ 12
174
- te 12
175
- �k 12
176
- ha 12
177
- is 12
178
- fr 12
179
- _k 12
180
- me 12
181
- slu 11
182
- yrir 11
183
- ru 11
184
- fyri 11
185
- us 11
186
- fyr 11
187
- _ha 11
188
- inu 11
189
- rir 11
190
- _he 11
191
- ju 11
192
- er� 11
193
- fy 11
194
- yri 11
195
- fyrir 11
196
- _S 11
197
- di 11
198
- ma 11
199
- _ek 10
200
- f_ 10
201
- rn 10
202
- _�a 10
203
- et 10
204
- si 10
205
- arf 10
206
- �s 10
207
- il_ 10
208
- ko 10
209
- _ekki 10
210
- _mi 10
211
- ekki_ 10
212
- _st 10
213
- ns 10
214
- or 10
215
- r�u 10
216
- _ekk 10
217
- fj 10
218
- kki 10
219
- �a 10
220
- kj 10
221
- le 10
222
- kki_ 10
223
- ekki 10
224
- fu 10
225
- pp 10
226
- til_ 9
227
- _til_ 9
228
- _fyr 9
229
- _um_ 9
230
- nar_ 9
231
- nni 9
232
- gn 9
233
- er_ 9
234
- kur 9
235
- til 9
236
- _um 9
237
- _fy 9
238
- � 9
239
- rs 9
240
- _er_ 9
241
- _me 9
242
- _til 9
243
- ann 9
244
- sa 9
245
- lu_ 9
246
- v� 9
247
- _ge 9
248
- ta_ 9
249
- _sk 9
250
- _fyri 9
251
- av 9
252
- f� 9
253
- K 9
254
- ru_ 9
255
- _ti 9
256
- _en 8
257
- _ei 8
258
- va 8
259
- st_ 8
260
- l�g 8
261
- �u_ 8
262
- ngi 8
263
- hef 8
264
- _hef 8
265
- an_ 8
266
- �ur_ 8
267
- �r 8
268
- e� 8
269
- �n 8
270
- du 8
271
- stu 8
272
- _af 8
273
- _H 8
274
- H 8
275
- _G 8
276
- _fr 8
277
- �t 8
278
- ut 8
279
- u�u 8
280
- fe 8
281
- ss 8
282
- �a_ 8
283
- _b� 8
284
- nes 8
285
- kt 8
286
- _vi 8
287
- G 8
288
- a�i 8
289
- ing 8
290
- ik 8
291
- fa 8
292
- it 8
293
- un_ 8
294
- gr 8
295
- nda 8
296
- tu_ 8
297
- _en_ 7
298
- eru 7
299
- _f�k 7
300
- _eru 7
301
- as 7
302
- r. 7
303
- er�ur 7
304
- ei� 7
305
- �kk 7
306
- rl 7
307
- rt 7
308
- ig 7
309
- gre 7
310
- ein 7
311
- ram 7
312
- _K 7
313
- br 7
314
- B 7
315
- eru_ 7
316
- _f� 7
317
- v�k 7
318
- rk 7
319
- fi 7
320
- av� 7
321
- _f�kk 7
322
- ja_ 7
323
- und 7
324
- �t 7
325
- ga_ 7
326
- inni 7
327
- lj 7
328
- yrir_ 7
329
- gl 7
330
- rir_ 7
331
- _fj 7
332
- el 7
333
- jar 7
334
- er�u 7
335
- �� 7
336
- fn 7
337
- f�kk 7
338
- eng 7
339
- av�k 7
340
- en_ 7
341
- m. 7
342
- _B 7
343
- _eru_ 7
344
- r�ur 7
345
- f�k 7
346
- _un 7
347
- k_ 7
348
- na_ 7
349
- kun 7
350
- ri� 7
351
- �ar 7
352
- r._ 7
353
- ust 7
354
- _� 7
355
- ld 7
356
- �l 7
357
- um._ 6
358
- nu� 6
359
- ann_ 6
360
- �l 6
361
- i�s 6
362
- _�t 6
363
- ug 6
364
- ra_ 6
365
- nna 6
366
- _upp 6
367
- ys 6
368
- j� 6
369
- R 6
370
- s� 6
371
- nga 6
372
- yk 6
373
- gar 6
374
- stu_ 6
375
- tar 6
376
- av�ku 6
377
- dur_ 6
378
- fra 6
379
- �n 6
380
- tir 6
381
- �_ 6
382
- and 6
383
- lg 6
384
- sko 6
385
- up 6
386
- enn 6
387
- _ef 6
388
- kja 6
389
- li� 6
390
- fur_ 6
391
- dur 6
392
- inn_ 6
393
- tarf 6
394
- upp 6
395
- eit 6
396
- eir 6
397
- f� 6
398
- dag 6
399
- _Re 6
400
- tr 6
305
+ for 17
306
+ din 17
307
+ �j� 17
308
+ af_ 17
309
+ _l� 17
310
+ es 17
311
+ vi� 17
312
+ _ef 17
313
+ ör 16
314
+ _fy 16
315
+ du 16
316
+ _i 16
317
+ fj� 16
318
+ �r 16
319
+ ra_ 16
320
+ fj 16
321
+ nin 16
322
+ ál 16
323
+ el 16
324
+ sin 16
325
+ kv 16
326
+ ge 16
327
+ ga_ 16
328
+ it 16
329
+ ön 16
330
+ _fr 16
331
+ au 16
332
+ �n 16
333
+ enn 16
334
+ l 16
335
+ ja 15
336
+ ngu 15
337
+ 15
338
+ _ei 15
339
+ �ð 15
340
+ ok 15
341
+ tir 15
342
+ leg 15
343
+ fyr 15
344
+ _ge 15
345
+ nni 15
346
+ _al 15
347
+ all 15
348
+ set 15
349
+ _sv 15
350
+ tt_ 14
351
+ fur 14
352
+ _ko 14
353
+ ms 14
354
+ gur 14
355
+ �� 14
356
+ nor 14
357
+ lut 14
358
+ ni_ 14
359
+ in_ 14
360
+ efn 14
361
+ nda 14
362
+ �ð 14
363
+ vo 14
364
+ ki_ 14
365
+ �ar 14
366
+ á� 14
367
+ þi 13
368
+ ski 13
369
+ sle 13
370
+ st� 13
371
+ 13
372
+ kr 13
373
+ hl 13
374
+ gs 13
375
+ �i 13
376
+ ær 13
377
+ er� 13
378
+ ls 13
379
+ as 13
380
+ �r 13
381
+ fa_ 13
382
+ hi 13
383
+ rir 13
384
+ bo 13
385
+ dan 13
386
+ �in 13
387
+ 13
388
+ fle 13
389
+ 13
390
+ kv� 12
391
+ ors 12
392
+ �ð 12
393
+ æ� 12
394
+ �m 12
395
+ ist 12
396
+ �� 12
397
+ rt 12
398
+ ðs 12
399
+ æm 12
400
+ rei 12