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
- _ 1566
2
- a 856
3
- n 460
4
- i 336
5
- g 302
6
- ng 210
7
- g_ 192
8
- t 183
9
- ng_ 180
10
- a_ 177
11
- o 173
12
- k 155
13
- an 154
14
- s 150
15
- _n 147
16
- l 147
17
- m 131
18
- y 105
19
- p 105
20
- u 103
21
- na 101
22
- ang 98
23
- ang_ 89
24
- . 85
25
- _a 83
26
- la 80
27
- in 79
28
- r 77
29
- ._ 74
30
- ka 72
31
- b 72
32
- _na 70
33
- _m 70
34
- _s 69
35
- sa 67
36
- ak 67
37
- pa 65
38
- ma 64
39
- h 63
40
- al 57
41
- d 57
42
- _p 56
43
- at 54
44
- ag 52
45
- t_ 49
46
- o_ 49
47
- ta 49
48
- _k 48
49
- n_ 47
50
- _ng 46
51
- _sa 45
52
- ni 45
53
- sa_ 43
54
- _pa 42
55
- ya 42
56
- ay 41
57
- it 40
58
- on 39
59
- e 39
60
- _sa_ 38
61
- y_ 38
62
- _ng_ 37
63
- ga 37
64
- il 36
65
- iy 36
66
- _ma 35
67
- ala 35
68
- w 35
69
- i_ 35
70
- na_ 34
71
- _t 33
72
- am 32
73
- _an 32
74
- , 31
75
- ,_ 31
76
- _ni 31
77
- ra 31
78
- _i 31
79
- ba 30
80
- _ka 30
81
- _ang_ 30
82
- _l 30
83
- _ang 30
84
- ar 29
85
- _na_ 29
86
- iya 29
87
- ha 27
88
- aka 27
89
- ong 27
90
- is 27
91
- li 27
92
- hi 27
93
- ko 26
94
- as 26
95
- ong_ 26
96
- s_ 25
97
- ri 25
98
- to 25
99
- ap 25
100
- gi 24
101
- an_ 24
102
- ay_ 24
103
- lan 24
104
- ah 24
105
- un 24
106
- o. 23
107
- ata 23
108
- di 23
109
- ing 23
110
- si 23
111
- um 23
112
- wa 23
113
- o._ 22
114
- ki 22
115
- ti 22
116
- ya_ 21
117
- _d 21
118
- niy 21
119
- at_ 21
120
- niya 21
121
- _niya 21
122
- _niy 21
123
- ab 21
124
- mo 21
125
- a._ 20
126
- a. 20
127
- N 20
128
- _mo 19
129
- yo 19
130
- ila 19
131
- aw 19
132
- iya_ 18
133
- _b 18
134
- ot 18
135
- ig 18
136
- _ak 18
137
- A 18
138
- lang 18
139
- nag 17
140
- in_ 17
141
- _A 17
142
- ing_ 17
143
- tu 17
144
- ama 16
145
- nga 16
146
- ali 16
147
- _si 16
148
- ina 16
149
- P 16
150
- _at 16
151
- aki 16
152
- ara 16
153
- _N 16
154
- _at_ 15
155
- _h 15
156
- lang_ 15
157
- ga_ 15
158
- nd 14
159
- ai 14
160
- bi 14
161
- _la 14
162
- da 14
163
- _P 14
164
- ib 14
165
- _r 14
166
- ito 13
167
- hin 13
168
- ako 13
169
- la_ 13
170
- lo 13
171
- ro 13
172
- ik 13
173
- aa 13
174
- ahi 12
175
- S 12
176
- rin 12
177
- a, 12
178
- _Na 12
179
- ul 12
180
- K 12
181
- _is 12
182
- Na 12
183
- _ta 12
184
- mag 12
185
- _K 12
186
- _tu 12
187
- _y 12
188
- a,_ 12
189
- _S 12
190
- _y_ 11
191
- ot_ 11
192
- lu 11
193
- pan 11
194
- _di 11
195
- gk 11
196
- ilan 11
197
- niya_ 11
198
- mi 11
199
- k_ 11
200
- go 11
201
- _ri 11
202
- man 11
203
- ung 11
204
- kin 11
205
- M 11
206
- _M 11
207
- _mag 11
208
- apa 11
209
- Ma 10
210
- _Ka 10
211
- _Ma 10
212
- it_ 10
213
- _mga 10
214
- is_ 10
215
- _mga_ 10
216
- mg 10
217
- ari 10
218
- akin 10
219
- _mg 10
220
- l_ 10
221
- yon 10
222
- mo_ 10
223
- asa 10
224
- .. 10
225
- pa_ 10
226
- agk 10
227
- to_ 10
228
- mga_ 10
229
- pi 10
230
- _mo_ 10
231
- _nag 10
232
- yan 10
233
- ir 10
234
- uma 10
235
- su 10
236
- wala 10
237
- wal 10
238
- mga 10
239
- ilang 10
240
- nak 10
241
- mu 10
242
- I 10
243
- Ka 10
244
- di_ 10
245
- awa 10
246
- _akin 9
247
- n, 9
248
- alan 9
249
- _ba 9
250
- An 9
251
- agka 9
252
- _I 9
253
- _An 9
254
- isa 9
255
- no 9
256
- pu 9
257
- n,_ 9
258
- n. 9
259
- n._ 9
260
- gka 9
261
- aba 9
262
- ini 9
263
- _aki 9
264
- as_ 9
265
- _lu 9
266
- nan 9
267
- pag 9
268
- _isa 9
269
- e_ 8
270
- yang_ 8
271
- _ako 8
272
- abi 8
273
- iti 8
274
- Pa 8
275
- ayo 8
276
- _wa 8
277
- _wal 8
278
- naka 8
279
- b_ 8
280
- aman 8
281
- _pag 8
282
- tay 8
283
- mat 8
284
- si_ 8
285
- aking 8
286
- ili 8
287
- ka_ 8
288
- alang 8
289
- aha 8
290
- _pa_ 8
291
- dib 8
292
- umi 8
293
- t. 8
294
- tan 8
295
- yang 8
296
- san 8
297
- _Pa 8
298
- p_ 8
299
- aga 8
300
- igi 8
301
- king 8
302
- _w 8
303
- _wala 8
304
- _iyo 7
305
- gin 7
306
- er 7
307
- _ko 7
308
- _ay 7
309
- _pu 7
310
- pak 7
311
- o,_ 7
312
- tum 7
313
- _ha 7
314
- tak 7
315
- ko_ 7
316
- _rin 7
317
- ito_ 7
318
- king_ 7
319
- ail 7
320
- iyo 7
321
- o, 7
322
- _iy 7
323
- _ku 7
324
- ala_ 7
325
- _nak 7
326
- ob 7
327
- tang 7
328
- tat 7
329
- d_ 7
330
- ra_ 7
331
- ut 7
332
- _tum 7
333
- B 7
334
- oo 7
335
- _B 7
336
- ram 7
337
- _hi 7
338
- tin 7
339
- lis 7
340
- ku 7
341
- kan 7
342
- ban 7
343
- bo 7
344
- _si_ 7
345
- mata 7
346
- kat 7
347
- ip 7
348
- sang 6
349
- ha_ 6
350
- gan 6
351
- ngi 6
352
- isan 6
353
- una 6
354
- os 6
355
- _naka 6
356
- nt 6
357
- mba 6
358
- man_ 6
359
- walan 6
360
- st 6
361
- agi 6
362
- _ay_ 6
363
- Sa 6
364
- isang 6
365
- ita 6
366
- nang 6
367
- _kun 6
368
- bang_ 6
369
- tata 6
370
- _siy 6
371
- _siya 6
372
- kaka 6
373
- par 6
374
- ig_ 6
375
- nit 6
376
- ago 6
377
- siy 6
378
- _par 6
379
- _mu 6
380
- kun 6
381
- ung_ 6
382
- ana 6
383
- mb 6
384
- c 6
385
- sang_ 6
386
- bang 6
387
- kak 6
388
- tang_ 6
389
- im 6
390
- ula 6
391
- _nga 6
392
- kah 6
393
- _isan 6
394
- ak_ 6
395
- t._ 6
396
- up 6
397
- anga 6
398
- ap_ 6
399
- on_ 6
400
- lis_ 6
1
+ _ 6178
2
+ a 3506
3
+ n 2158
4
+ g 1432
5
+ i 1276
6
+ ng 952
7
+ an 885
8
+ g_ 854
9
+ o 847
10
+ s 845
11
+ ng_ 814
12
+ t 773
13
+ a_ 750
14
+ l 728
15
+ p 683
16
+ m 591
17
+ _n 517
18
+ u 515
19
+ ang 507
20
+ k 473
21
+ _a 448
22
+ y 411
23
+ na 411
24
+ e 409
25
+ r 398
26
+ sa 367
27
+ _p 361
28
+ n_ 336
29
+ in 332
30
+ _m 330
31
+ _s 328
32
+ at 309
33
+ la 295
34
+ ka 295
35
+ b 294
36
+ ga 285
37
+ pa 279
38
+ o_ 269
39
+ h 263
40
+ d 260
41
+ al 251
42
+ sa_ 247
43
+ _ng 239
44
+ on 235
45
+ ma 230
46
+ _sa 227
47
+ _na 215
48
+ t_ 197
49
+ _an 196
50
+ pi 194
51
+ an_ 194
52
+ ta 192
53
+ _pa 192
54
+ ag 189
55
+ ay 189
56
+ _k 186
57
+ li 171
58
+ as 159
59
+ ga_ 158
60
+ il 158
61
+ mga 151
62
+ mg 151
63
+ _mg 151
64
+ y_ 148
65
+ _ka 143
66
+ at_ 142
67
+ ul 138
68
+ _i 129
69
+ ba 129
70
+ na_ 128
71
+ ala 127
72
+ ti 127
73
+ s_ 126
74
+ it 125
75
+ is 121
76
+ no 121
77
+ ay_ 121
78
+ _ma 120
79
+ ina 119
80
+ _at 118
81
+ _b 115
82
+ ya 115
83
+ ha 115
84
+ ra 114
85
+ am 110
86
+ _t 109
87
+ pin 106
88
+ ar 105
89
+ un 105
90
+ ong 103
91
+ yo 101
92
+ ah 101
93
+ w 100
94
+ si 98
95
+ ip 97
96
+ on_ 95
97
+ ak 90
98
+ hi 90
99
+ ap 88
100
+ ili 87
101
+ _pi 86
102
+ lo 82
103
+ _d 82
104
+ ipi 81
105
+ ni 80
106
+ lip 80
107
+ pan 79
108
+ ik 79
109
+ _ay 79
110
+ i_ 78
111
+ c 78
112
+ ata 76
113
+ to 74
114
+ st 73
115
+ yon 72
116
+ tu 71
117
+ ula 70
118
+ ama 70
119
+ _h 69
120
+ mi 69
121
+ gan 68
122
+ ing 68
123
+ _ba 67
124
+ l_ 67
125
+ as_ 67
126
+ ab 67
127
+ re 66
128
+ ri 66
129
+ ns 64
130
+ pag 64
131
+ lan 63
132
+ ko 62
133
+ aha 62
134
+ er 62
135
+ san 61
136
+ pil 61
137
+ pu 60
138
+ iy 60
139
+ _e 60
140
+ _r 59
141
+ _o 58
142
+ di 58
143
+ _l 57
144
+ e_ 57
145
+ ara 56
146
+ nas 56
147
+ en 55
148
+ no_ 55
149
+ da 55
150
+ aka 55
151
+ mu 55
152
+ sy 55
153
+ d_ 54
154
+ ban 54
155
+ po 54
156
+ ad 53
157
+ la_ 53
158
+ es 52
159
+ nga 52
160
+ wa 51
161
+ _si 50
162
+ ila 49
163
+ ika 49
164
+ lu 48
165
+ aw 48
166
+ aa 48
167
+ or 48
168
+ yan 48
169
+ bu 47
170
+ al_ 46
171
+ ans 46
172
+ um 46
173
+ ati 45
174
+ te 45
175
+ asa 44
176
+ nsa 44
177
+ op 44
178
+ ig 44
179
+ nd 44
180
+ nt 44
181
+ _is 43
182
+ oo 42
183
+ ro 42
184
+ pul 42
185
+ bi 42
186
+ gk 42
187
+ nan 42
188
+ ino 41
189
+ han 41
190
+ kas 40
191
+ _ta 40
192
+ tan 40
193
+ ana 40
194
+ apa 40
195
+ kan 40
196
+ to_ 39
197
+ kal 39
198
+ pam 39
199
+ _re 39
200
+ ya_ 38
201
+ ito 38
202
+ _o_ 37
203
+ nag 36
204
+ man 36
205
+ kat 36
206
+ aga 36
207
+ gu 35
208
+ in_ 35
209
+ su 35
210
+ _g 35
211
+ ali 35
212
+ _no 34
213
+ isa 34
214
+ gi 33
215
+ awa 33
216
+ ku 33
217
+ oon 33
218
+ syo 33
219
+ _ha 33
220
+ os 33
221
+ ran 32
222
+ aan 32
223
+ do 32
224
+ aya 32
225
+ hal 31
226
+ p_ 31
227
+ nak 31
228
+ ub 31
229
+ _di 31
230
+ gka 31
231
+ om 30
232
+ _po 30
233
+ ulo 30
234
+ _u 30
235
+ wi 30
236
+ r_ 30
237
+ im 30
238
+ f 30
239
+ ung 29
240
+ ol 29
241
+ aba 29
242
+ _w 29
243
+ _c 29
244
+ tin 28
245
+ tag 28
246
+ mul 28
247
+ _mu 28
248
+ ngg 28
249
+ hiy 28
250
+ gg 28
251
+ mah 28
252
+ ur 28
253
+ iyo 28
254
+ it_ 27
255
+ ra_ 27
256
+ ehi 27
257
+ uk 27
258
+ nu 27
259
+ ist 27
260
+ eh 27
261
+ iya 27
262
+ ne 27
263
+ noo 27
264
+ bo 26
265
+ mat 26
266
+ se 26
267
+ sta 26
268
+ _es 26
269
+ mal 25
270
+ _da 25
271
+ may 25
272
+ ahi 25
273
+ ka_ 25
274
+ nat 25
275
+ reh 25
276
+ lo_ 25
277
+ _it 25
278
+ ita 25
279
+ de 25
280
+ ta_ 24
281
+ ag_ 24
282
+ me 24
283
+ ny 24
284
+ gga 24
285
+ ye 24
286
+ so 24
287
+ ib 23
288
+ uma 23
289
+ hin 23
290
+ _la 23
291
+ ki 23
292
+ k_ 23
293
+ agk 23
294
+ sti 23
295
+ v 23
296
+ ent 23
297
+ ani 23
298
+ _bi 23
299
+ lit 22
300
+ una 22
301
+ atu 22
302
+ go 22
303
+ nah 22
304
+ _ti 21
305
+ _tu 21
306
+ os_ 21
307
+ ek 21
308
+ ut 21
309
+ _su 21
310
+ min 21
311
+ us 21
312
+ tr 21
313
+ laa 20
314
+ rin 20
315
+ ca 20
316
+ mb 20
317
+ _ni 20
318
+ ad_ 20
319
+ he 20
320
+ est 20
321
+ asy 20
322
+ ngu 20
323
+ lak 20
324
+ gs 20
325
+ et 19
326
+ omi 19
327
+ din 19
328
+ kar 19
329
+ ngk 19
330
+ kap 19
331
+ du 19
332
+ kon 19
333
+ lat 19
334
+ _mi 19
335
+ gd 19
336
+ nap 19
337
+ te_ 19
338
+ nit 19
339
+ od 19
340
+ sya 18
341
+ _bu 18
342
+ lin 18
343
+ gp 18
344
+ tul 18
345
+ opu 18
346
+ gl 18
347
+ ir 18
348
+ ro_ 18
349
+ bin 18
350
+ ia 18
351
+ gr 18
352
+ ii 18
353
+ pop 18
354
+ ao 18
355
+ nom 18
356
+ kab 18
357
+ sin 18
358
+ yo_ 18
359
+ mo 18
360
+ ai 18
361
+ ry 18
362
+ wan 18
363
+ em 18
364
+ isy 18
365
+ pat 18
366
+ ari 17
367
+ ua 17
368
+ ini 17
369
+ pe 17
370
+ lal 17
371
+ ags 17
372
+ _wi 17
373
+ agp 17
374
+ ob 17
375
+ ok 17
376
+ lay 17
377
+ gal 17
378
+ ulu 17
379
+ wik 17
380
+ any 17
381
+ law 16
382
+ gay 16
383
+ lon 16
384
+ ind 16
385
+ uan 16
386
+ ado 16
387
+ up 16
388
+ tal 16
389
+ uo 16
390
+ iko 16
391
+ tat 16
392
+ _se 16
393
+ alo 16
394
+ agi 16
395
+ par 16
396
+ _ko 16
397
+ _hi 16
398
+ ura 16
399
+ apu 16
400
+ nya 16