scylla 0.7.0 → 0.7.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/lib/scylla/classifier.rb +3 -4
- data/lib/scylla/generator.rb +4 -7
- data/lib/scylla/lms/afrikaans.lm +280 -280
- data/lib/scylla/lms/arabic.lm +225 -225
- data/lib/scylla/lms/bulgarian.lm +208 -208
- data/lib/scylla/lms/catalan.lm +212 -212
- data/lib/scylla/lms/chinese.lm +201 -201
- data/lib/scylla/lms/danish.lm +155 -155
- data/lib/scylla/lms/english.lm +207 -207
- data/lib/scylla/lms/finnish.lm +259 -259
- data/lib/scylla/lms/french.lm +203 -203
- data/lib/scylla/lms/german.lm +280 -280
- data/lib/scylla/lms/greek.lm +276 -276
- data/lib/scylla/lms/hebrew.lm +170 -170
- data/lib/scylla/lms/hindi.lm +241 -241
- data/lib/scylla/lms/icelandic.lm +264 -264
- data/lib/scylla/lms/indonesian.lm +272 -272
- data/lib/scylla/lms/italian.lm +283 -283
- data/lib/scylla/lms/japanese.lm +105 -105
- data/lib/scylla/lms/korean.lm +400 -400
- data/lib/scylla/lms/norwegian.lm +235 -235
- data/lib/scylla/lms/polish.lm +264 -264
- data/lib/scylla/lms/portuguese.lm +269 -269
- data/lib/scylla/lms/romanian.lm +278 -278
- data/lib/scylla/lms/russian.lm +127 -127
- data/lib/scylla/lms/slovak.lm +281 -281
- data/lib/scylla/lms/slovenian.lm +276 -276
- data/lib/scylla/lms/spanish.lm +190 -190
- data/lib/scylla/lms/swedish.lm +195 -195
- data/lib/scylla/lms/tagalog.lm +282 -282
- data/lib/scylla/lms/thai.lm +257 -257
- data/lib/scylla/lms/turkish.lm +300 -300
- data/lib/scylla/lms/vietnamese.lm +277 -277
- data/lib/scylla/lms/welsh.lm +271 -271
- data/scylla.gemspec +3 -22
- data/source_texts/korean.txt +219 -134
- metadata +15 -14
- data/scylla-0.6.0.gem +0 -0
data/lib/scylla/lms/chinese.lm
CHANGED
@@ -1,14 +1,14 @@
|
|
1
|
-
_
|
1
|
+
_ 8346
|
2
2
|
� 2389
|
3
3
|
� 1982
|
4
4
|
� 1894
|
5
5
|
� 1872
|
6
6
|
� 1520
|
7
|
-
_�
|
8
|
-
_�
|
9
|
-
_�
|
10
|
-
_�
|
11
|
-
_�
|
7
|
+
_� 1037
|
8
|
+
_� 833
|
9
|
+
_� 821
|
10
|
+
_� 807
|
11
|
+
_� 648
|
12
12
|
� 514
|
13
13
|
� 429
|
14
14
|
,_ 421
|
@@ -30,8 +30,8 @@ _
|
|
30
30
|
� 330
|
31
31
|
� 329
|
32
32
|
� 327
|
33
|
-
� 324
|
34
33
|
� 324
|
34
|
+
� 324
|
35
35
|
� 321
|
36
36
|
� 319
|
37
37
|
� 318
|
@@ -57,8 +57,8 @@ _
|
|
57
57
|
� 280
|
58
58
|
� 277
|
59
59
|
� 275
|
60
|
-
� 269
|
61
60
|
� 269
|
61
|
+
� 269
|
62
62
|
� 262
|
63
63
|
� 260
|
64
64
|
� 260
|
@@ -67,334 +67,334 @@ _
|
|
67
67
|
� 254
|
68
68
|
� 252
|
69
69
|
� 247
|
70
|
-
� 246
|
71
70
|
� 246
|
71
|
+
� 246
|
72
72
|
� 229
|
73
73
|
� 224
|
74
74
|
� 222
|
75
75
|
� 220
|
76
76
|
� 197
|
77
77
|
� 196
|
78
|
-
� 102
|
79
78
|
� 102
|
80
|
-
�
|
81
|
-
�_
|
82
|
-
�_
|
83
|
-
�_
|
79
|
+
� 102
|
80
|
+
�_ 98
|
81
|
+
�_ 94
|
82
|
+
�_ 89
|
83
|
+
�_ 88
|
84
84
|
�_ 85
|
85
|
-
�_ 84
|
86
85
|
� 84
|
86
|
+
�_ 84
|
87
87
|
� 83
|
88
88
|
�_ 82
|
89
|
+
�_ 82
|
90
|
+
�_ 82
|
91
|
+
�_ 81
|
89
92
|
� 80
|
90
|
-
�_ 80
|
91
|
-
�_ 79
|
93
|
+
�_ 80
|
92
94
|
� 79
|
93
|
-
�_ 79
|
95
|
+
�_ 79
|
94
96
|
� 78
|
95
|
-
�_ 76
|
96
97
|
� 76
|
97
|
-
�_ 75
|
98
98
|
� 75
|
99
99
|
� 75
|
100
|
-
�_
|
100
|
+
�_ 74
|
101
|
+
�_ 74
|
102
|
+
�_ 73
|
103
|
+
�_ 73
|
101
104
|
� 72
|
102
|
-
�_ 72
|
103
|
-
�_ 72
|
104
|
-
�_ 72
|
105
|
-
�_ 71
|
106
|
-
� 71
|
105
|
+
�_ 72
|
106
|
+
�_ 72
|
107
|
+
�_ 72
|
107
108
|
� 71
|
108
|
-
�
|
109
|
+
� 71
|
109
110
|
� 70
|
110
|
-
�_ 70
|
111
111
|
� 70
|
112
|
+
�_ 70
|
113
|
+
�_ 70
|
114
|
+
�_ 70
|
112
115
|
� 69
|
113
|
-
�_ 69
|
114
116
|
� 69
|
115
|
-
� 68
|
116
|
-
� 68
|
117
117
|
� 68
|
118
|
+
� 68
|
119
|
+
� 68
|
120
|
+
�_ 68
|
121
|
+
� 67
|
118
122
|
� 67
|
119
|
-
�_ 67
|
120
123
|
� 67
|
121
|
-
�_ 67
|
122
|
-
� 67
|
123
124
|
� 66
|
124
125
|
� 65
|
125
|
-
�_ 65
|
126
126
|
� 65
|
127
127
|
�_ 65
|
128
|
+
_� 65
|
129
|
+
�_ 64
|
128
130
|
� 64
|
129
|
-
�_
|
130
|
-
_� 63
|
131
|
+
�_ 62
|
131
132
|
� 62
|
133
|
+
�_ 62
|
132
134
|
� 62
|
133
135
|
_� 61
|
134
|
-
�_ 61
|
135
|
-
�_
|
136
|
-
�_
|
136
|
+
�_ 61
|
137
|
+
�_ 60
|
138
|
+
�_ 60
|
139
|
+
�_ 59
|
137
140
|
� 59
|
138
|
-
�_
|
141
|
+
�_ 59
|
142
|
+
� 58
|
139
143
|
� 58
|
140
|
-
� 58
|
141
|
-
�_ 58
|
142
144
|
� 58
|
143
|
-
�
|
144
|
-
� 58
|
145
|
+
� 58
|
145
146
|
� 58
|
146
147
|
� 57
|
147
148
|
� 57
|
148
149
|
� 57
|
149
150
|
� 56
|
151
|
+
�_ 56
|
152
|
+
�_ 55
|
150
153
|
� 55
|
151
|
-
�_
|
152
|
-
�_ 54
|
154
|
+
�_ 54
|
153
155
|
� 54
|
154
156
|
�_ 54
|
155
|
-
�_ 54
|
156
|
-
�_
|
157
|
+
�_ 54
|
158
|
+
�_ 54
|
157
159
|
� 53
|
158
|
-
� 53
|
159
|
-
�_ 53
|
160
160
|
� 53
|
161
161
|
� 53
|
162
162
|
� 53
|
163
|
-
�
|
164
|
-
� 51
|
165
|
-
� 51
|
163
|
+
� 53
|
166
164
|
� 51
|
167
|
-
� 51
|
168
165
|
� 51
|
169
|
-
�� 51
|
170
166
|
� 51
|
171
|
-
�
|
172
|
-
�
|
167
|
+
� 51
|
168
|
+
� 51
|
169
|
+
�_ 51
|
170
|
+
� 51
|
171
|
+
�_ 50
|
172
|
+
�_ 50
|
173
173
|
� 50
|
174
174
|
� 50
|
175
|
-
|
175
|
+
�� 50
|
176
|
+
� 50
|
176
177
|
� 50
|
177
|
-
�
|
178
|
+
_� 50
|
179
|
+
� 50
|
178
180
|
� 49
|
181
|
+
� 49
|
179
182
|
� 49
|
180
|
-
�� 49
|
181
|
-
� 49
|
182
183
|
� 49
|
184
|
+
� 49
|
183
185
|
� 49
|
184
|
-
|
185
|
-
�
|
186
|
-
� 48
|
186
|
+
�� 48
|
187
|
+
� 48
|
188
|
+
� 48
|
187
189
|
� 48
|
190
|
+
�_ 48
|
191
|
+
� 48
|
192
|
+
�_ 48
|
188
193
|
�_ 48
|
189
|
-
� 48
|
190
194
|
� 48
|
191
195
|
�_ 48
|
192
|
-
� 48
|
193
|
-
�� 47
|
196
|
+
_� 48
|
194
197
|
� 47
|
195
|
-
_
|
196
|
-
|
197
|
-
� 46
|
198
|
+
�_ 47
|
199
|
+
�� 47
|
198
200
|
� 46
|
199
|
-
�
|
200
|
-
�
|
201
|
-
�
|
201
|
+
� 46
|
202
|
+
�_ 46
|
203
|
+
�_ 46
|
204
|
+
�_ 46
|
202
205
|
� 45
|
203
|
-
�
|
206
|
+
_� 45
|
207
|
+
� 45
|
208
|
+
� 45
|
204
209
|
� 45
|
205
|
-
|
206
|
-
�
|
207
|
-
|
208
|
-
�_ 44
|
209
|
-
�_ 44
|
210
|
+
_� 45
|
211
|
+
_� 44
|
212
|
+
�� 44
|
210
213
|
� 44
|
211
|
-
�_ 44
|
214
|
+
�_ 44
|
212
215
|
� 44
|
213
216
|
�� 44
|
214
|
-
_
|
215
|
-
� 43
|
217
|
+
�_ 43
|
216
218
|
� 43
|
217
|
-
� 43
|
218
|
-
|
219
|
+
_� 43
|
220
|
+
� 43
|
221
|
+
�_ 43
|
219
222
|
� 43
|
220
223
|
� 43
|
224
|
+
� 43
|
225
|
+
� 42
|
221
226
|
� 42
|
222
|
-
�� 42
|
223
|
-
� 42
|
224
|
-
� 42
|
225
|
-
�_ 42
|
226
227
|
_� 42
|
227
228
|
�� 42
|
228
|
-
� 42
|
229
|
-
_� 42
|
229
|
+
�_ 42
|
230
230
|
� 42
|
231
|
-
|
232
|
-
�
|
233
|
-
� 41
|
231
|
+
� 42
|
232
|
+
� 42
|
234
233
|
� 41
|
235
|
-
�_ 41
|
236
234
|
� 41
|
235
|
+
� 41
|
236
|
+
� 41
|
237
|
+
�� 41
|
238
|
+
� 40
|
239
|
+
�� 40
|
240
|
+
� 40
|
241
|
+
�_ 40
|
237
242
|
�_ 40
|
238
243
|
� 40
|
239
|
-
�_ 40
|
240
|
-
� 40
|
241
244
|
�� 40
|
242
|
-
� 40
|
243
|
-
|
245
|
+
�_ 40
|
246
|
+
� 39
|
244
247
|
� 39
|
245
248
|
� 39
|
246
249
|
�� 39
|
247
|
-
� 39
|
248
|
-
|
249
|
-
�� 39
|
250
|
+
� 39
|
251
|
+
_� 39
|
250
252
|
� 39
|
251
253
|
� 39
|
252
|
-
� 39
|
254
|
+
_� 39
|
255
|
+
�_ 39
|
253
256
|
� 38
|
254
|
-
� 38
|
255
257
|
� 38
|
256
|
-
_� 38
|
257
|
-
� 38
|
258
258
|
� 38
|
259
|
-
|
260
|
-
|
259
|
+
� 38
|
260
|
+
�� 38
|
261
|
+
�� 38
|
262
|
+
� 38
|
261
263
|
� 37
|
262
|
-
�_ 37
|
263
264
|
� 37
|
264
|
-
�_ 37
|
265
265
|
� 37
|
266
|
-
� 36
|
267
|
-
� 36
|
266
|
+
_� 36
|
268
267
|
� 36
|
269
|
-
� 36
|
270
268
|
_� 36
|
271
|
-
|
269
|
+
� 36
|
272
270
|
� 36
|
273
|
-
� 36
|
274
|
-
� 36
|
275
271
|
� 36
|
272
|
+
� 36
|
276
273
|
� 36
|
277
|
-
� 36
|
274
|
+
� 36
|
275
|
+
� 36
|
276
|
+
� 36
|
277
|
+
� 36
|
278
|
+
�� 36
|
279
|
+
� 35
|
278
280
|
� 35
|
279
281
|
� 35
|
280
|
-
|
282
|
+
�_ 35
|
283
|
+
_� 35
|
281
284
|
� 35
|
282
|
-
_� 35
|
283
|
-
� 35
|
284
285
|
� 35
|
285
|
-
|
286
|
-
_� 34
|
287
|
-
� 34
|
288
|
-
� 34
|
286
|
+
�� 34
|
289
287
|
� 34
|
290
|
-
|
288
|
+
�� 34
|
291
289
|
�� 34
|
290
|
+
_� 34
|
291
|
+
� 34
|
292
|
+
� 34
|
292
293
|
_� 34
|
293
|
-
|
294
|
-
� 33
|
295
|
-
�� 33
|
294
|
+
� 34
|
296
295
|
�_ 33
|
297
|
-
� 33
|
298
296
|
_� 33
|
299
|
-
_� 33
|
300
|
-
|
301
|
-
� 33
|
297
|
+
_� 33
|
298
|
+
�� 33
|
302
299
|
�� 33
|
300
|
+
� 33
|
303
301
|
�_ 33
|
304
|
-
_� 33
|
305
|
-
|
306
|
-
|
307
|
-
�
|
302
|
+
_� 33
|
303
|
+
_� 33
|
304
|
+
� 33
|
305
|
+
� 33
|
306
|
+
_� 33
|
307
|
+
� 33
|
308
308
|
�� 32
|
309
309
|
�� 32
|
310
|
-
_� 32
|
311
|
-
�� 32
|
312
|
-
� 32
|
313
|
-
� 32
|
314
310
|
� 32
|
315
|
-
� 32
|
316
311
|
_� 32
|
317
|
-
|
318
|
-
�
|
319
|
-
|
320
|
-
|
321
|
-
�
|
322
|
-
_� 31
|
323
|
-
�� 31
|
324
|
-
� 31
|
325
|
-
�� 31
|
326
|
-
� 31
|
312
|
+
� 32
|
313
|
+
_� 32
|
314
|
+
� 32
|
315
|
+
� 32
|
316
|
+
� 32
|
327
317
|
�� 31
|
318
|
+
�� 31
|
328
319
|
�� 31
|
329
|
-
|
320
|
+
�� 31
|
330
321
|
� 31
|
322
|
+
� 31
|
323
|
+
� 31
|
331
324
|
�� 31
|
325
|
+
_� 31
|
326
|
+
�� 31
|
327
|
+
� 31
|
328
|
+
� 31
|
329
|
+
� 31
|
330
|
+
�� 31
|
332
331
|
� 31
|
333
|
-
�
|
334
|
-
�� 30
|
332
|
+
_� 30
|
335
333
|
� 30
|
334
|
+
�� 30
|
335
|
+
_� 30
|
336
|
+
�� 30
|
337
|
+
� 30
|
338
|
+
�� 30
|
339
|
+
� 30
|
340
|
+
�� 30
|
341
|
+
_� 30
|
336
342
|
� 30
|
337
343
|
� 30
|
344
|
+
�� 30
|
338
345
|
�� 30
|
339
|
-
|
340
|
-
�� 30
|
341
|
-
_� 30
|
342
|
-
_� 30
|
346
|
+
�_ 30
|
343
347
|
�� 30
|
344
|
-
��
|
345
|
-
��
|
346
|
-
�
|
347
|
-
|
348
|
-
|
349
|
-
� 29
|
348
|
+
�� 29
|
349
|
+
�� 29
|
350
|
+
_� 29
|
351
|
+
�� 29
|
352
|
+
�� 29
|
350
353
|
�� 29
|
351
|
-
�� 29
|
354
|
+
�� 29
|
355
|
+
�� 29
|
356
|
+
� 29
|
357
|
+
�� 29
|
358
|
+
�� 29
|
359
|
+
� 29
|
360
|
+
_� 29
|
361
|
+
_� 29
|
362
|
+
�� 29
|
363
|
+
� 29
|
352
364
|
�� 29
|
365
|
+
�� 29
|
353
366
|
� 29
|
354
|
-
�� 29
|
355
|
-
�� 29
|
356
367
|
�� 29
|
357
|
-
�� 29
|
358
|
-
�� 29
|
359
368
|
� 29
|
360
|
-
�� 29
|
361
|
-
� 29
|
362
|
-
�� 29
|
363
|
-
�� 29
|
364
|
-
� 29
|
365
|
-
_� 29
|
366
|
-
�� 29
|
367
369
|
�� 29
|
368
|
-
|
369
|
-
|
370
|
-
�� 29
|
371
|
-
�� 28
|
372
|
-
�� 28
|
373
|
-
_� 28
|
370
|
+
� 29
|
371
|
+
�� 29
|
374
372
|
�� 28
|
375
|
-
�_ 28
|
376
|
-
�_ 28
|
377
|
-
�� 28
|
378
373
|
�� 28
|
379
|
-
�� 28
|
374
|
+
�� 28
|
375
|
+
�� 28
|
376
|
+
�� 28
|
380
377
|
� 28
|
381
|
-
|
382
|
-
�� 28
|
378
|
+
�� 28
|
383
379
|
� 28
|
384
|
-
|
385
|
-
|
380
|
+
�� 28
|
381
|
+
�� 28
|
382
|
+
_� 28
|
383
|
+
�� 28
|
384
|
+
�_ 28
|
385
|
+
�� 27
|
386
386
|
� 27
|
387
|
+
� 27
|
388
|
+
_� 27
|
389
|
+
_� 27
|
387
390
|
�� 27
|
388
|
-
|
389
|
-
_� 27
|
390
|
-
|
391
|
-
|
392
|
-
� 27
|
391
|
+
� 27
|
392
|
+
_� 27
|
393
|
+
_� 27
|
394
|
+
� 27
|
395
|
+
_� 27
|
396
|
+
_� 27
|
397
|
+
_� 27
|
393
398
|
�� 27
|
394
|
-
�� 27
|
395
|
-
� 27
|
396
399
|
� 27
|
397
|
-
|
398
|
-
� 27
|
399
|
-
� 27
|
400
|
-
_� 27
|
400
|
+
�� 27
|