scylla 0.8.0 → 0.8.29
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +4 -0
- data/Gemfile.lock +9 -1
- data/lib/scylla/generator.rb +46 -13
- data/lib/scylla/lms/afrikaans.lm +400 -400
- data/lib/scylla/lms/arabic.lm +400 -400
- data/lib/scylla/lms/bulgarian.lm +400 -400
- data/lib/scylla/lms/catalan.lm +399 -399
- data/lib/scylla/lms/chinese.lm +400 -400
- data/lib/scylla/lms/czech.lm +400 -0
- data/lib/scylla/lms/danish.lm +396 -396
- data/lib/scylla/lms/dutch.lm +400 -0
- data/lib/scylla/lms/english.lm +400 -400
- data/lib/scylla/lms/finnish.lm +400 -400
- data/lib/scylla/lms/french.lm +398 -398
- data/lib/scylla/lms/german.lm +400 -400
- data/lib/scylla/lms/greek.lm +400 -400
- data/lib/scylla/lms/hebrew.lm +399 -399
- data/lib/scylla/lms/hindi.lm +400 -400
- data/lib/scylla/lms/icelandic.lm +399 -399
- data/lib/scylla/lms/indonesian.lm +400 -400
- data/lib/scylla/lms/italian.lm +400 -400
- data/lib/scylla/lms/japanese.lm +399 -399
- data/lib/scylla/lms/kannada.lm +400 -0
- data/lib/scylla/lms/korean.lm +400 -400
- data/lib/scylla/lms/marathi.lm +400 -0
- data/lib/scylla/lms/norwegian.lm +400 -400
- data/lib/scylla/lms/persian.lm +400 -0
- data/lib/scylla/lms/polish.lm +400 -400
- data/lib/scylla/lms/portuguese.lm +400 -400
- data/lib/scylla/lms/romanian.lm +400 -400
- data/lib/scylla/lms/russian.lm +400 -400
- data/lib/scylla/lms/slovak.lm +400 -400
- data/lib/scylla/lms/slovenian.lm +387 -387
- data/lib/scylla/lms/spanish.lm +400 -400
- data/lib/scylla/lms/swedish.lm +399 -399
- data/lib/scylla/lms/tagalog.lm +400 -400
- data/lib/scylla/lms/thai.lm +400 -400
- data/lib/scylla/lms/turkish.lm +400 -400
- data/lib/scylla/lms/vietnamese.lm +400 -400
- data/lib/scylla/lms/welsh.lm +398 -398
- data/lib/scylla/resources.rb +43 -33
- data/lib/scylla/string.rb +2 -2
- data/lib/scylla.rb +0 -4
- data/pkg/scylla-0.5.0.gem +0 -0
- data/scylla.gemspec +1 -1
- data/source_texts/afrikaans.txt +330 -81
- data/source_texts/arabic.txt +590 -448
- data/source_texts/bulgarian.txt +588 -821
- data/source_texts/catalan.txt +435 -413
- data/source_texts/chinese.txt +526 -100
- data/source_texts/czech.txt +237 -0
- data/source_texts/danish.txt +233 -184
- data/source_texts/dutch.txt +503 -0
- data/source_texts/english.txt +673 -70
- data/source_texts/finnish.txt +939 -71
- data/source_texts/french.txt +879 -465
- data/source_texts/german.txt +1236 -137
- data/source_texts/greek.txt +488 -139
- data/source_texts/hebrew.txt +539 -100
- data/source_texts/hindi.txt +254 -100
- data/source_texts/icelandic.txt +301 -90
- data/source_texts/indonesian.txt +509 -93
- data/source_texts/italian.txt +1066 -120
- data/source_texts/japanese.txt +1217 -450
- data/source_texts/kannada.txt +340 -0
- data/source_texts/korean.txt +343 -219
- data/source_texts/marathi.txt +237 -0
- data/source_texts/norwegian.txt +555 -190
- data/source_texts/persian.txt +886 -0
- data/source_texts/polish.txt +1013 -90
- data/source_texts/portuguese.txt +690 -88
- data/source_texts/romanian.txt +436 -103
- data/source_texts/russian.txt +1029 -100
- data/source_texts/slovak.txt +575 -102
- data/source_texts/slovenian.txt +353 -99
- data/source_texts/spanish.txt +858 -675
- data/source_texts/swedish.txt +558 -488
- data/source_texts/tagalog.txt +391 -100
- data/source_texts/thai.txt +286 -60
- data/source_texts/turkish.txt +635 -87
- data/source_texts/vietnamese.txt +300 -92
- data/source_texts/welsh.txt +288 -104
- data/test/fixtures/lms/danish.lm +314 -314
- data/test/fixtures/lms/english.lm +301 -301
- data/test/fixtures/lms/french.lm +326 -326
- data/test/fixtures/lms/german.lm +331 -331
- data/test/fixtures/lms/hindi.lm +191 -191
- data/test/fixtures/lms/italian.lm +299 -299
- data/test/fixtures/lms/japanese.lm +103 -103
- data/test/fixtures/lms/norwegian.lm +309 -309
- data/test/fixtures/lms/spanish.lm +331 -331
- data/test/generator_test.rb +2 -2
- metadata +14 -3
data/test/fixtures/lms/hindi.lm
CHANGED
@@ -1,400 +1,400 @@
|
|
1
1
|
� 28567
|
2
2
|
� 24888
|
3
3
|
� 23140
|
4
|
-
_
|
4
|
+
_ 9858
|
5
5
|
� 5565
|
6
6
|
� 5427
|
7
|
-
_�
|
8
|
-
_�
|
9
|
-
ा 2729
|
7
|
+
_� 4929
|
8
|
+
_� 4897
|
10
9
|
�� 2729
|
10
|
+
ा 2729
|
11
11
|
� 2729
|
12
|
+
� 2281
|
12
13
|
् 2281
|
13
14
|
�� 2281
|
14
|
-
� 2281
|
15
|
-
्� 2265
|
16
15
|
��� 2265
|
16
|
+
्� 2265
|
17
17
|
�� 2265
|
18
|
-
�� 2251
|
19
|
-
्� 2251
|
20
18
|
��� 2251
|
19
|
+
�� 2251
|
21
20
|
र 2005
|
22
|
-
|
23
|
-
��� 2005
|
21
|
+
ा� 2005
|
24
22
|
�� 2005
|
25
23
|
� 2005
|
26
|
-
|
27
|
-
��
|
28
|
-
ा� 1952
|
24
|
+
��� 2005
|
25
|
+
�� 2005
|
29
26
|
��� 1952
|
27
|
+
�� 1952
|
30
28
|
� 1764
|
31
|
-
ि 1764
|
32
29
|
�� 1764
|
33
|
-
|
30
|
+
ि 1764
|
34
31
|
र� 1701
|
35
32
|
��� 1701
|
33
|
+
�� 1701
|
36
34
|
क 1665
|
37
35
|
� 1665
|
38
36
|
�� 1665
|
39
37
|
�� 1596
|
40
38
|
त 1596
|
41
|
-
ि� 1511
|
42
|
-
��� 1511
|
43
39
|
ि� 1511
|
44
|
-
�� 1511
|
45
|
-
�� 1511
|
46
40
|
��� 1511
|
41
|
+
�� 1511
|
42
|
+
��� 1511
|
43
|
+
�� 1511
|
47
44
|
� 1391
|
48
|
-
��� 1384
|
49
45
|
क� 1384
|
46
|
+
��� 1384
|
50
47
|
�� 1384
|
51
|
-
�� 1381
|
52
48
|
न 1381
|
53
|
-
|
54
|
-
�� 1345
|
49
|
+
�� 1381
|
55
50
|
� 1345
|
51
|
+
�� 1345
|
52
|
+
स 1345
|
56
53
|
��� 1263
|
57
54
|
�� 1263
|
58
55
|
स� 1263
|
59
56
|
�� 1216
|
60
|
-
��� 1196
|
61
57
|
त� 1196
|
58
|
+
��� 1196
|
62
59
|
� 1181
|
63
|
-
े 1172
|
64
60
|
�� 1172
|
65
|
-
|
61
|
+
े 1172
|
66
62
|
�� 1144
|
63
|
+
� 1144
|
67
64
|
व 1144
|
68
|
-
��� 1082
|
69
65
|
व� 1082
|
70
66
|
�� 1082
|
67
|
+
��� 1082
|
71
68
|
�� 1072
|
72
69
|
न� 1062
|
73
70
|
��� 1062
|
74
|
-
�� 958
|
75
71
|
��� 958
|
76
|
-
|
72
|
+
�� 958
|
77
73
|
�� 910
|
78
|
-
व� 907
|
79
74
|
�� 907
|
80
75
|
��� 907
|
81
76
|
��� 890
|
82
|
-
त� 890
|
83
77
|
� 858
|
84
78
|
म 858
|
85
79
|
�� 858
|
86
80
|
� 853
|
81
|
+
य 836
|
87
82
|
� 836
|
88
83
|
�� 836
|
89
|
-
य 836
|
90
|
-
�� 829
|
91
84
|
प 829
|
85
|
+
�� 829
|
86
|
+
�_ 813
|
92
87
|
�� 809
|
88
|
+
�� 789
|
93
89
|
��� 789
|
94
90
|
म� 789
|
95
|
-
|
96
|
-
��� 785
|
91
|
+
��� 785
|
97
92
|
प� 785
|
93
|
+
��� 785
|
98
94
|
�� 785
|
99
|
-
��� 785
|
100
|
-
स� 785
|
101
95
|
��� 746
|
102
|
-
क� 746
|
103
96
|
�� 746
|
104
97
|
�� 743
|
105
|
-
र� 743
|
106
98
|
��� 743
|
107
|
-
�_ 724
|
108
99
|
��_ 724
|
100
|
+
�_ 724
|
109
101
|
ा_ 724
|
110
102
|
� 705
|
111
|
-
�� 683
|
112
103
|
द 683
|
104
|
+
�� 683
|
105
|
+
_स 674
|
113
106
|
�� 670
|
114
107
|
द� 662
|
115
108
|
��� 662
|
116
|
-
ु� 655
|
117
|
-
ु� 655
|
118
109
|
ु 655
|
110
|
+
��� 655
|
111
|
+
�� 655
|
119
112
|
�� 655
|
113
|
+
ु� 655
|
120
114
|
� 655
|
121
115
|
��� 655
|
122
|
-
��� 655
|
123
116
|
�� 655
|
124
|
-
�� 655
|
125
|
-
_स� 653
|
126
|
-
_स 653
|
127
117
|
��� 638
|
128
|
-
क� 638
|
129
118
|
�� 638
|
119
|
+
�� 617
|
130
120
|
��� 617
|
131
121
|
य� 617
|
132
|
-
�� 617
|
133
122
|
�� 613
|
134
|
-
�� 610
|
135
|
-
न� 610
|
136
123
|
��� 610
|
137
|
-
|
124
|
+
�� 610
|
138
125
|
े� 604
|
126
|
+
��� 604
|
139
127
|
�� 590
|
140
128
|
��� 581
|
141
|
-
|
142
|
-
ह 568
|
129
|
+
_व 573
|
143
130
|
े_ 568
|
144
|
-
��
|
131
|
+
�� 568
|
132
|
+
ह 568
|
145
133
|
� 568
|
134
|
+
��_ 568
|
146
135
|
�_ 568
|
147
|
-
�� 568
|
148
|
-
_व� 556
|
149
|
-
_व 556
|
150
|
-
म� 535
|
151
136
|
�� 535
|
152
137
|
��� 535
|
153
|
-
�_ 532
|
154
|
-
ल 527
|
155
|
-
� 527
|
156
138
|
�� 527
|
157
|
-
|
139
|
+
� 527
|
140
|
+
ल 527
|
158
141
|
�� 524
|
159
142
|
ह� 524
|
143
|
+
��� 524
|
144
|
+
_प 491
|
160
145
|
� 485
|
161
146
|
�� 478
|
162
147
|
��� 478
|
163
|
-
स� 478
|
164
|
-
��् 477
|
165
148
|
�् 477
|
166
|
-
�्� 477
|
167
149
|
�� 473
|
168
|
-
��र 472
|
169
150
|
�र 472
|
170
|
-
_प� 466
|
171
|
-
_प 466
|
172
151
|
�� 462
|
173
152
|
�� 462
|
174
|
-
श 454
|
175
153
|
� 454
|
154
|
+
श 454
|
176
155
|
�� 454
|
177
156
|
�� 453
|
178
|
-
� 453
|
179
157
|
ी 453
|
180
|
-
|
181
|
-
�ि� 452
|
182
|
-
न� 452
|
158
|
+
� 453
|
183
159
|
�ि 452
|
184
|
-
|
185
|
-
��� 450
|
186
|
-
य� 450
|
160
|
+
��� 452
|
187
161
|
�� 450
|
162
|
+
��� 450
|
188
163
|
� 442
|
164
|
+
�� 442
|
189
165
|
��� 442
|
166
|
+
ब 442
|
190
167
|
ब� 442
|
191
|
-
�� 442
|
192
168
|
�� 442
|
193
|
-
ब 442
|
194
169
|
� 435
|
195
170
|
ो 435
|
196
171
|
�� 435
|
197
|
-
��� 431
|
198
172
|
�� 431
|
199
173
|
ल� 431
|
174
|
+
��� 431
|
200
175
|
�य 427
|
201
|
-
��य 427
|
202
176
|
ं 424
|
203
|
-
�र� 424
|
204
177
|
�� 424
|
205
178
|
�ा 413
|
206
|
-
��ा 413
|
207
|
-
��� 412
|
208
|
-
� 412
|
209
179
|
ज 412
|
210
|
-
|
180
|
+
��� 412
|
211
181
|
�� 412
|
182
|
+
ं� 412
|
183
|
+
� 412
|
212
184
|
�� 407
|
213
185
|
�� 402
|
214
|
-
ं� 401
|
215
186
|
��� 401
|
216
187
|
त_ 400
|
217
188
|
��_ 400
|
218
|
-
��र 399
|
219
189
|
�र 399
|
220
|
-
प� 397
|
221
190
|
��� 397
|
222
|
-
प� 388
|
223
191
|
��� 388
|
224
|
-
_क� 385
|
225
192
|
_क 385
|
226
|
-
�� 377
|
227
|
-
��� 377
|
228
193
|
ज� 377
|
229
|
-
|
230
|
-
|
194
|
+
��� 377
|
195
|
+
�� 377
|
231
196
|
��� 371
|
232
|
-
|
197
|
+
�� 371
|
233
198
|
�� 361
|
234
|
-
|
235
|
-
��क 361
|
199
|
+
ष 361
|
236
200
|
� 361
|
237
|
-
|
201
|
+
�क 361
|
238
202
|
�� 351
|
239
203
|
श� 351
|
240
|
-
|
241
|
-
�र� 348
|
242
|
-
�� 348
|
204
|
+
��� 351
|
243
205
|
��� 348
|
244
|
-
|
245
|
-
��� 337
|
206
|
+
�� 348
|
246
207
|
�� 337
|
247
208
|
ो� 337
|
209
|
+
��� 337
|
248
210
|
�� 336
|
249
|
-
�ा_ 336
|
250
211
|
ध 336
|
251
212
|
� 336
|
252
|
-
न_ 319
|
253
213
|
��_ 319
|
214
|
+
न_ 319
|
254
215
|
�_ 319
|
255
|
-
�� 315
|
256
|
-
�� 315
|
257
|
-
ो� 315
|
258
216
|
ग 315
|
259
217
|
��� 315
|
218
|
+
�� 315
|
219
|
+
�� 315
|
260
220
|
� 315
|
261
|
-
��� 312
|
262
|
-
ल� 312
|
263
221
|
�� 312
|
222
|
+
��� 312
|
264
223
|
��� 306
|
265
224
|
�� 306
|
266
|
-
त� 306
|
267
|
-
��_ 304
|
268
225
|
र_ 304
|
226
|
+
��_ 304
|
269
227
|
�_ 304
|
270
228
|
�� 299
|
271
|
-
�� 298
|
272
229
|
� 298
|
273
|
-
|
274
|
-
�� 293
|
230
|
+
�� 298
|
275
231
|
�न 293
|
276
|
-
��न 293
|
277
232
|
ष� 293
|
278
|
-
|
233
|
+
�� 293
|
234
|
+
��� 293
|
279
235
|
��� 291
|
280
|
-
|
281
|
-
_ब� 291
|
236
|
+
_ब 291
|
282
237
|
�� 287
|
283
238
|
��� 287
|
284
|
-
|
285
|
-
�� 283
|
239
|
+
भ 283
|
286
240
|
भ� 283
|
241
|
+
�� 283
|
287
242
|
��� 283
|
288
|
-
भ 283
|
289
|
-
��� 281
|
290
|
-
� 281
|
291
|
-
��� 281
|
292
243
|
�_ 281
|
293
|
-
|
294
|
-
क_ 281
|
244
|
+
�_ 281
|
295
245
|
��_ 281
|
296
|
-
|
297
|
-
�� 281
|
298
|
-
�� 281
|
299
|
-
अ� 281
|
300
|
-
अ 281
|
246
|
+
क_ 281
|
301
247
|
��� 276
|
302
|
-
�� 276
|
303
248
|
ध� 276
|
249
|
+
�� 276
|
304
250
|
�र 274
|
305
|
-
|
306
|
-
_अ 268
|
307
|
-
_अ� 268
|
308
|
-
��त 267
|
251
|
+
_�_ 268
|
309
252
|
�त 267
|
310
253
|
��� 266
|
311
254
|
�� 266
|
312
|
-
ज� 266
|
313
|
-
��् 261
|
314
|
-
��� 261
|
315
|
-
ी� 261
|
316
|
-
��� 261
|
317
255
|
ी� 261
|
318
256
|
�� 261
|
319
257
|
�् 261
|
258
|
+
��� 261
|
259
|
+
��� 261
|
320
260
|
�� 261
|
321
|
-
�्� 261
|
322
|
-
�� 260
|
323
|
-
ष� 260
|
324
261
|
��� 260
|
262
|
+
�� 260
|
325
263
|
�् 256
|
326
|
-
�्� 256
|
327
|
-
��् 256
|
328
264
|
� 255
|
329
|
-
च 255
|
330
265
|
�� 255
|
331
|
-
|
332
|
-
��� 254
|
266
|
+
च 255
|
333
267
|
�� 254
|
268
|
+
��� 254
|
269
|
+
�_ 253
|
334
270
|
��_ 253
|
335
|
-
ि_ 253
|
336
271
|
��� 253
|
337
|
-
|
272
|
+
ि_ 253
|
338
273
|
ग� 253
|
339
|
-
|
340
|
-
��ा 246
|
274
|
+
�� 253
|
341
275
|
�ा 246
|
276
|
+
च� 245
|
342
277
|
�� 245
|
343
278
|
��� 245
|
344
|
-
च� 245
|
345
|
-
ह� 237
|
346
|
-
��त 237
|
347
|
-
�त 237
|
348
279
|
�� 237
|
280
|
+
�त 237
|
349
281
|
��� 237
|
350
|
-
श� 233
|
351
|
-
�र� 233
|
352
282
|
�� 233
|
353
283
|
��� 233
|
354
284
|
ण 230
|
285
|
+
_म 230
|
355
286
|
�� 230
|
356
287
|
� 230
|
357
|
-
��ा 225
|
358
288
|
�ा 225
|
359
|
-
�ा� 225
|
360
|
-
��ा 220
|
361
|
-
�ा 220
|
362
|
-
��् 220
|
363
289
|
�् 220
|
364
|
-
|
365
|
-
य_ 219
|
290
|
+
�ा 220
|
366
291
|
�् 219
|
367
|
-
�_ 219
|
368
292
|
��_ 219
|
369
|
-
|
293
|
+
य_ 219
|
294
|
+
�_ 219
|
370
295
|
�� 211
|
371
|
-
_म� 210
|
372
|
-
_म 210
|
373
296
|
�ा 206
|
374
|
-
|
375
|
-
|
376
|
-
��� 204
|
377
|
-
ग� 204
|
297
|
+
� 204
|
298
|
+
�ि 204
|
378
299
|
�� 204
|
379
|
-
भ� 204
|
380
|
-
ए 204
|
381
300
|
��� 204
|
382
|
-
�ि 204
|
383
301
|
�� 204
|
384
|
-
|
385
|
-
|
386
|
-
��े 200
|
302
|
+
ए 204
|
303
|
+
��� 204
|
387
304
|
�े 200
|
388
|
-
�क� 199
|
389
|
-
�त� 199
|
390
|
-
�� 198
|
391
305
|
��� 198
|
392
|
-
|
393
|
-
�त_ 198
|
306
|
+
�� 198
|
394
307
|
_ह 197
|
395
|
-
_
|
396
|
-
|
308
|
+
_न 196
|
309
|
+
�� 194
|
310
|
+
��� 194
|
397
311
|
आ� 194
|
398
|
-
|
312
|
+
� 194
|
313
|
+
��� 194
|
314
|
+
�� 194
|
399
315
|
�� 194
|
400
|
-
|
316
|
+
आ 194
|
317
|
+
� 193
|
318
|
+
उ� 193
|
319
|
+
��� 193
|
320
|
+
�� 193
|
321
|
+
उ 193
|
322
|
+
�� 193
|
323
|
+
�� 193
|
324
|
+
��� 193
|
325
|
+
��_ 192
|
326
|
+
�_ 192
|
327
|
+
ी_ 192
|
328
|
+
_द 192
|
329
|
+
�ि 186
|
330
|
+
�व 184
|
331
|
+
�ष 183
|
332
|
+
�� 180
|
333
|
+
��� 180
|
334
|
+
_उ 176
|
335
|
+
��� 175
|
336
|
+
�ा 175
|
337
|
+
�� 175
|
338
|
+
ख 173
|
339
|
+
� 173
|
340
|
+
��� 173
|
341
|
+
�� 173
|
342
|
+
ख� 173
|
343
|
+
�� 173
|
344
|
+
_ज 171
|
345
|
+
�� 167
|
346
|
+
�ा 167
|
347
|
+
��� 167
|
348
|
+
�ा 160
|
349
|
+
�� 155
|
350
|
+
��� 155
|
351
|
+
ए� 155
|
352
|
+
�_ 154
|
353
|
+
ण_ 154
|
354
|
+
��_ 154
|
355
|
+
। 152
|
356
|
+
�� 152
|
357
|
+
�ा 152
|
358
|
+
��� 150
|
359
|
+
�� 150
|
360
|
+
�क 146
|
361
|
+
�द 144
|
362
|
+
�् 143
|
363
|
+
�त 139
|
364
|
+
�े 139
|
365
|
+
�� 138
|
366
|
+
थ 138
|
367
|
+
�् 137
|
368
|
+
� 133
|
369
|
+
ट 133
|
370
|
+
�� 133
|
371
|
+
।_ 132
|
372
|
+
�त 132
|
373
|
+
��_ 132
|
374
|
+
�म 131
|
375
|
+
�ि 128
|
376
|
+
�ं 128
|
377
|
+
�� 127
|
378
|
+
��� 127
|
379
|
+
��� 127
|
380
|
+
थ� 127
|
381
|
+
�म 127
|
382
|
+
�� 127
|
383
|
+
_ल 125
|
384
|
+
�र 122
|
385
|
+
�् 122
|
386
|
+
_भ 121
|
387
|
+
�� 119
|
388
|
+
_आ 119
|
389
|
+
�ो 119
|
390
|
+
��� 119
|
391
|
+
�� 118
|
392
|
+
��� 118
|
393
|
+
�श 118
|
394
|
+
ट� 117
|
395
|
+
�� 117
|
396
|
+
��� 117
|
397
|
+
�े 115
|
398
|
+
�ा 112
|
399
|
+
��� 111
|
400
|
+
�� 111
|