scylla 0.5.0 → 0.6.0
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +4 -2
- data/Gemfile.lock +16 -1
- data/lib/scylla/classifier.rb +1 -1
- data/lib/scylla/generator.rb +16 -4
- data/lib/scylla/lms/afrikaans.lm +232 -232
- data/lib/scylla/lms/arabic.lm +175 -175
- data/lib/scylla/lms/bulgarian.lm +225 -225
- data/lib/scylla/lms/catalan.lm +309 -309
- data/lib/scylla/lms/danish.lm +167 -167
- data/lib/scylla/lms/english.lm +398 -398
- data/lib/scylla/lms/finnish.lm +237 -237
- data/lib/scylla/lms/french.lm +148 -148
- data/lib/scylla/lms/german.lm +258 -258
- data/lib/scylla/lms/greek.lm +236 -236
- data/lib/scylla/lms/hebrew.lm +154 -154
- data/lib/scylla/lms/hindi.lm +139 -139
- data/lib/scylla/lms/icelandic.lm +239 -239
- data/lib/scylla/lms/indonesian.lm +244 -244
- data/lib/scylla/lms/italian.lm +248 -248
- data/lib/scylla/lms/japanese.lm +90 -90
- data/lib/scylla/lms/korean.lm +306 -306
- data/lib/scylla/lms/norwegian.lm +193 -193
- data/lib/scylla/lms/polish.lm +241 -241
- data/lib/scylla/lms/portuguese.lm +232 -232
- data/lib/scylla/lms/romanian.lm +246 -246
- data/lib/scylla/lms/slovak.lm +242 -242
- data/lib/scylla/lms/slovenian.lm +229 -229
- data/lib/scylla/lms/spanish.lm +164 -164
- data/lib/scylla/lms/swedish.lm +157 -157
- data/lib/scylla/lms/tagalog.lm +247 -247
- data/lib/scylla/lms/thai.lm +252 -252
- data/lib/scylla/lms/turkish.lm +285 -285
- data/lib/scylla/lms/vietnamese.lm +250 -250
- data/lib/scylla/lms/welsh.lm +248 -248
- data/lib/scylla/resources.rb +1 -9
- data/lib/scylla.rb +4 -0
- data/scylla.gemspec +2 -120
- data/source_texts/english.txt +62 -27
- data/test/classifier_test.rb +1 -3
- data/test/fixtures/lms/danish.lm +173 -173
- data/test/fixtures/lms/english.lm +220 -220
- data/test/fixtures/lms/french.lm +175 -175
- data/test/fixtures/lms/german.lm +254 -254
- data/test/fixtures/lms/hindi.lm +139 -139
- data/test/fixtures/lms/italian.lm +236 -236
- data/test/fixtures/lms/japanese.lm +88 -88
- data/test/fixtures/lms/norwegian.lm +182 -182
- data/test/fixtures/lms/spanish.lm +164 -164
- data/test/fixtures/test_languages/spanish +0 -1
- data/test/generator_test.rb +13 -0
- data/test/helper.rb +2 -0
- metadata +18 -25
- data/.document +0 -5
- data/lib/scylla/lms/13375P33K.lm +0 -400
- data/scylla-0.1.0.gem +0 -0
- data/source_texts/13375P33K.txt +0 -199
- data/test/fixtures/lms/13375p33k.lm +0 -400
- data/test/fixtures/source_texts/13375P33K.txt +0 -199
data/lib/scylla/lms/greek.lm
CHANGED
@@ -20,31 +20,30 @@ _
|
|
20
20
|
� 90
|
21
21
|
� 82
|
22
22
|
� 75
|
23
|
+
�_ 74
|
23
24
|
�� 74
|
24
|
-
�_ 73
|
25
25
|
. 73
|
26
26
|
_� 71
|
27
|
-
�_
|
27
|
+
�_ 70
|
28
28
|
�_ 69
|
29
|
+
�_ 65
|
29
30
|
�_ 65
|
30
|
-
�_ 64
|
31
31
|
, 58
|
32
32
|
� 56
|
33
33
|
� 56
|
34
|
-
" 55
|
35
34
|
_� 54
|
36
35
|
�_ 53
|
37
36
|
,_ 53
|
38
|
-
�_
|
39
|
-
_� 51
|
37
|
+
�_ 52
|
40
38
|
�� 51
|
41
|
-
��
|
39
|
+
�� 51
|
40
|
+
_� 51
|
42
41
|
� 50
|
43
42
|
_� 48
|
44
43
|
- 48
|
45
44
|
_�� 48
|
46
|
-
._ 47
|
47
45
|
_� 47
|
46
|
+
._ 47
|
48
47
|
�� 46
|
49
48
|
��_ 44
|
50
49
|
�� 43
|
@@ -59,342 +58,343 @@ _
|
|
59
58
|
_�� 36
|
60
59
|
�� 35
|
61
60
|
�� 35
|
62
|
-
_�
|
63
|
-
�_
|
61
|
+
_� 34
|
62
|
+
�_ 33
|
64
63
|
� 32
|
65
64
|
� 31
|
66
65
|
�� 31
|
67
|
-
� 30
|
68
66
|
_��� 30
|
67
|
+
� 30
|
69
68
|
�� 29
|
70
69
|
�� 29
|
71
70
|
�� 28
|
72
71
|
� 28
|
73
72
|
�� 27
|
74
73
|
_� 27
|
75
|
-
�� 26
|
76
74
|
��_ 26
|
75
|
+
�� 26
|
76
|
+
�_ 25
|
77
|
+
��_ 24
|
77
78
|
�� 24
|
78
79
|
�� 24
|
79
80
|
�� 24
|
80
|
-
��_ 24
|
81
|
-
�_ 24
|
82
|
-
��_ 23
|
83
|
-
��_ 23
|
84
|
-
���_ 23
|
85
81
|
�� 23
|
82
|
+
���_ 23
|
83
|
+
��_ 23
|
86
84
|
�� 23
|
87
|
-
��
|
88
|
-
�� 22
|
89
|
-
� 22
|
85
|
+
��_ 23
|
90
86
|
� 22
|
91
87
|
_�� 22
|
92
|
-
|
93
|
-
|
94
|
-
��
|
88
|
+
� 22
|
89
|
+
�� 22
|
90
|
+
�� 22
|
95
91
|
_�� 21
|
92
|
+
�� 21
|
96
93
|
_�� 21
|
94
|
+
�� 21
|
95
|
+
_� 21
|
97
96
|
�� 20
|
98
|
-
��� 20
|
99
|
-
�� 20
|
100
97
|
�� 20
|
98
|
+
�� 20
|
99
|
+
��� 20
|
100
|
+
�� 19
|
101
101
|
�� 19
|
102
|
-
�� 19
|
103
102
|
� 19
|
104
103
|
�� 19
|
105
|
-
�� 19
|
104
|
+
�� 19
|
106
105
|
_��� 18
|
107
|
-
|
108
|
-
��
|
106
|
+
� 18
|
107
|
+
�� 18
|
109
108
|
��� 18
|
109
|
+
_� 18
|
110
|
+
�_ 18
|
110
111
|
�� 18
|
111
|
-
�� 18
|
112
|
+
��_ 18
|
112
113
|
_�� 18
|
113
|
-
|
114
|
-
_
|
115
|
-
�_ 17
|
114
|
+
�� 18
|
115
|
+
���_ 17
|
116
116
|
�� 17
|
117
|
+
�. 17
|
118
|
+
�� 17
|
117
119
|
�� 17
|
118
|
-
_" 17
|
119
120
|
_���_ 17
|
120
|
-
�� 17
|
121
|
-
���_ 17
|
122
121
|
��� 17
|
123
|
-
�� 16
|
124
|
-
�� 16
|
125
|
-
�_ 16
|
126
122
|
�� 16
|
123
|
+
�_ 16
|
124
|
+
�� 16
|
125
|
+
�� 16
|
127
126
|
�� 16
|
128
|
-
|
129
|
-
�� 15
|
130
|
-
_
|
127
|
+
_��_ 15
|
128
|
+
�� 15
|
129
|
+
_� 15
|
131
130
|
�� 15
|
132
|
-
|
131
|
+
_���_ 15
|
133
132
|
�� 15
|
133
|
+
�� 15
|
134
|
+
��_ 15
|
135
|
+
���_ 15
|
136
|
+
_�_ 15
|
134
137
|
�� 15
|
135
|
-
_��_ 15
|
136
138
|
�� 15
|
137
|
-
|
138
|
-
|
139
|
-
�� 15
|
140
|
-
_� 15
|
141
|
-
�� 14
|
142
|
-
_� 14
|
143
|
-
�� 14
|
144
|
-
_�� 14
|
145
|
-
�. 14
|
146
|
-
��� 14
|
139
|
+
�� 15
|
140
|
+
���_ 14
|
147
141
|
�� 14
|
142
|
+
��� 14
|
143
|
+
_�� 14
|
144
|
+
��_ 14
|
145
|
+
_� 14
|
148
146
|
_�� 14
|
149
147
|
�� 14
|
150
|
-
��� 14
|
148
|
+
��� 14
|
149
|
+
�� 14
|
150
|
+
�� 14
|
151
151
|
�� 14
|
152
|
-
|
153
|
-
��_ 14
|
152
|
+
�_ 13
|
154
153
|
_��� 13
|
155
|
-
�� 13
|
156
|
-
�� 13
|
157
|
-
�� 13
|
158
|
-
�� 13
|
159
|
-
��_ 13
|
160
154
|
�� 13
|
155
|
+
��_ 13
|
156
|
+
�� 13
|
157
|
+
�. 13
|
161
158
|
��_ 13
|
162
|
-
|
163
|
-
|
159
|
+
_�� 13
|
160
|
+
�� 13
|
161
|
+
�� 13
|
162
|
+
�� 13
|
164
163
|
���_ 12
|
165
|
-
�� 12
|
166
|
-
�� 12
|
167
164
|
�� 12
|
165
|
+
��� 12
|
166
|
+
�� 12
|
168
167
|
��_ 12
|
169
|
-
��� 12
|
168
|
+
_���_ 12
|
169
|
+
�� 12
|
170
|
+
��_ 12
|
170
171
|
�� 12
|
171
|
-
��� 12
|
172
|
-
��_ 12
|
173
|
-
��� 12
|
172
|
+
��� 12
|
174
173
|
_��� 12
|
175
174
|
�� 12
|
176
|
-
�� 12
|
177
|
-
|
178
|
-
��_ 12
|
179
|
-
�� 11
|
180
|
-
��� 11
|
181
|
-
�� 11
|
182
|
-
". 11
|
175
|
+
�� 12
|
176
|
+
��� 12
|
177
|
+
��_ 12
|
178
|
+
�� 11
|
183
179
|
�� 11
|
184
|
-
��� 11
|
180
|
+
��� 11
|
181
|
+
�� 11
|
185
182
|
�� 11
|
186
|
-
�� 11
|
187
|
-
�� 11
|
188
183
|
� 11
|
184
|
+
��� 11
|
189
185
|
�� 11
|
190
|
-
|
191
|
-
|
192
|
-
�� 10
|
193
|
-
��� 10
|
186
|
+
�� 11
|
187
|
+
�� 11
|
194
188
|
_�� 10
|
195
189
|
�� 10
|
196
|
-
��_ 10
|
197
190
|
�� 10
|
198
|
-
_��_ 10
|
199
|
-
��� 10
|
200
191
|
��� 10
|
192
|
+
_��� 10
|
201
193
|
_�� 10
|
202
|
-
�� 10
|
203
|
-
|
204
|
-
|
205
|
-
_��� 10
|
194
|
+
�� 10
|
195
|
+
� 10
|
196
|
+
��� 10
|
197
|
+
_��� 10
|
206
198
|
�� 10
|
207
199
|
��� 10
|
208
|
-
|
209
|
-
|
200
|
+
��� 10
|
201
|
+
�� 10
|
202
|
+
_��_ 10
|
203
|
+
_��� 10
|
204
|
+
_� 10
|
205
|
+
�� 10
|
206
|
+
�� 10
|
207
|
+
_��� 10
|
208
|
+
_�� 10
|
209
|
+
�� 10
|
210
|
+
�� 10
|
210
211
|
_���_ 10
|
211
|
-
��� 10
|
212
|
-
� 10
|
213
212
|
�� 10
|
214
|
-
|
215
|
-
|
213
|
+
���� 10
|
214
|
+
��� 10
|
216
215
|
_���� 10
|
217
|
-
|
218
|
-
�� 10
|
219
|
-
|
220
|
-
_
|
221
|
-
�� 10
|
222
|
-
��� 9
|
223
|
-
��� 9
|
224
|
-
� 9
|
225
|
-
�._ 9
|
226
|
-
�� 9
|
227
|
-
�� 9
|
228
|
-
� 9
|
216
|
+
�� 10
|
217
|
+
��_ 10
|
218
|
+
_� 10
|
219
|
+
���_ 9
|
229
220
|
_�� 9
|
230
|
-
|
231
|
-
��� 9
|
221
|
+
�� 9
|
232
222
|
���_ 9
|
233
|
-
� 9
|
234
|
-
��_ 9
|
235
|
-
��� 9
|
236
|
-
��_ 9
|
237
|
-
�� 9
|
238
223
|
�_ 9
|
239
|
-
|
240
|
-
|
241
|
-
��� 9
|
242
|
-
���_ 9
|
243
|
-
�� 9
|
244
|
-
���� 9
|
224
|
+
�� 9
|
225
|
+
�� 9
|
226
|
+
��� 9
|
245
227
|
_���_ 9
|
246
|
-
�� 9
|
247
228
|
�� 9
|
248
|
-
|
229
|
+
�� 9
|
249
230
|
��� 9
|
250
|
-
|
231
|
+
_��� 9
|
232
|
+
��_ 9
|
233
|
+
�� 9
|
234
|
+
���_ 9
|
235
|
+
�._ 9
|
236
|
+
��� 9
|
237
|
+
��� 9
|
238
|
+
�� 9
|
239
|
+
��� 9
|
240
|
+
��� 9
|
241
|
+
� 9
|
251
242
|
�� 9
|
243
|
+
�- 9
|
244
|
+
���� 9
|
252
245
|
_�� 9
|
253
|
-
|
254
|
-
�� 9
|
255
|
-
�� 9
|
246
|
+
��_ 9
|
256
247
|
���� 9
|
248
|
+
_�� 9
|
249
|
+
�� 9
|
250
|
+
_� 9
|
251
|
+
� 9
|
252
|
+
� 9
|
253
|
+
_� 8
|
254
|
+
��� 8
|
255
|
+
_�� 8
|
256
|
+
�. 8
|
257
|
+
�, 8
|
258
|
+
���_ 8
|
259
|
+
�, 8
|
257
260
|
�� 8
|
258
|
-
|
259
|
-
���� 8
|
261
|
+
���� 8
|
260
262
|
_�� 8
|
261
|
-
��� 8
|
262
|
-
|
263
|
-
�� 8
|
264
|
-
�. 8
|
263
|
+
��� 8
|
264
|
+
���� 8
|
265
265
|
_���� 8
|
266
|
-
����� 8
|
267
|
-
��_ 8
|
268
|
-
_���� 8
|
269
|
-
_� 8
|
270
|
-
_� 8
|
271
|
-
��� 8
|
272
|
-
��� 8
|
273
|
-
���� 8
|
274
|
-
_��� 8
|
275
|
-
_�� 8
|
276
|
-
�� 8
|
277
|
-
�� 8
|
278
|
-
���� 8
|
279
266
|
�� 8
|
280
|
-
���_ 8
|
281
267
|
�� 8
|
268
|
+
�,_ 8
|
269
|
+
_��� 8
|
270
|
+
�._ 8
|
271
|
+
_�� 8
|
272
|
+
���� 8
|
273
|
+
_� 8
|
274
|
+
�. 8
|
275
|
+
��_ 8
|
276
|
+
�� 8
|
277
|
+
��� 8
|
282
278
|
��_ 8
|
283
|
-
�- 8
|
284
|
-
��� 8
|
285
|
-
���� 8
|
286
279
|
����� 8
|
280
|
+
�� 8
|
281
|
+
_���� 8
|
282
|
+
��� 8
|
287
283
|
�� 8
|
288
|
-
��� 8
|
289
|
-
|
290
|
-
|
291
|
-
|
292
|
-
|
293
|
-
|
284
|
+
��� 8
|
285
|
+
����� 8
|
286
|
+
����� 8
|
287
|
+
���� 8
|
288
|
+
�� 8
|
289
|
+
_� 8
|
290
|
+
��_ 8
|
291
|
+
�� 8
|
292
|
+
_�� 7
|
293
|
+
�� 7
|
294
294
|
�� 7
|
295
|
-
|
295
|
+
����� 7
|
296
|
+
-� 7
|
297
|
+
���_ 7
|
298
|
+
��_ 7
|
296
299
|
��_ 7
|
297
|
-
|
298
|
-
|
299
|
-
�� 7
|
300
|
-
��_ 7
|
301
|
-
�� 7
|
300
|
+
��� 7
|
301
|
+
_���� 7
|
302
|
+
�� 7
|
302
303
|
���� 7
|
304
|
+
����_ 7
|
303
305
|
�� 7
|
304
|
-
_
|
305
|
-
|
306
|
-
���_ 7
|
307
|
-
����� 7
|
308
|
-
��� 7
|
306
|
+
_� 7
|
307
|
+
�_ 7
|
309
308
|
��� 7
|
310
|
-
|
311
|
-
|
312
|
-
����_ 7
|
313
|
-
�� 7
|
309
|
+
��� 7
|
310
|
+
�� 7
|
314
311
|
_��� 7
|
315
|
-
|
312
|
+
�� 7
|
313
|
+
_��_ 7
|
316
314
|
�� 7
|
317
|
-
|
315
|
+
��� 7
|
316
|
+
_���_ 7
|
317
|
+
�� 7
|
318
|
+
����� 7
|
319
|
+
�� 7
|
318
320
|
���� 7
|
321
|
+
�� 7
|
322
|
+
��� 7
|
323
|
+
_� 7
|
319
324
|
�- 7
|
320
|
-
_
|
325
|
+
�,_ 7
|
326
|
+
��_ 7
|
321
327
|
_��� 7
|
322
|
-
|
323
|
-
|
324
|
-
|
325
|
-
|
326
|
-
|
327
|
-
��� 7
|
328
|
-
����_ 6
|
329
|
-
�. 6
|
330
|
-
�� 6
|
331
|
-
_���_ 6
|
328
|
+
��, 7
|
329
|
+
_��� 7
|
330
|
+
��,_ 7
|
331
|
+
_�� 6
|
332
|
+
��_ 6
|
332
333
|
�� 6
|
334
|
+
��� 6
|
335
|
+
���_ 6
|
333
336
|
���_ 6
|
337
|
+
��_ 6
|
338
|
+
�,_ 6
|
334
339
|
_� 6
|
335
|
-
|
340
|
+
��� 6
|
341
|
+
�� 6
|
342
|
+
�� 6
|
343
|
+
�� 6
|
344
|
+
�� 6
|
345
|
+
�, 6
|
346
|
+
��_ 6
|
347
|
+
�� 6
|
348
|
+
��� 6
|
349
|
+
�� 6
|
350
|
+
_��� 6
|
351
|
+
���� 6
|
352
|
+
�� 6
|
353
|
+
���� 6
|
354
|
+
��� 6
|
336
355
|
_��_ 6
|
356
|
+
�� 6
|
357
|
+
_�� 6
|
358
|
+
�� 6
|
359
|
+
�� 6
|
360
|
+
�� 6
|
337
361
|
_��� 6
|
362
|
+
_��� 6
|
338
363
|
_�� 6
|
339
|
-
�� 6
|
340
|
-
���_ 6
|
341
|
-
_�� 6
|
342
|
-
�� 6
|
343
|
-
���_ 6
|
344
|
-
_��� 6
|
345
|
-
�,_ 6
|
346
|
-
��_ 6
|
347
|
-
�� 6
|
364
|
+
�� 6
|
348
365
|
��_ 6
|
349
366
|
�� 6
|
350
|
-
|
351
|
-
|
352
|
-
�� 6
|
367
|
+
��� 6
|
368
|
+
_�._ 6
|
353
369
|
��. 6
|
370
|
+
��� 6
|
354
371
|
�._ 6
|
355
|
-
�� 6
|
356
|
-
�� 6
|
357
|
-
��� 6
|
358
|
-
�� 6
|
359
|
-
���� 6
|
372
|
+
�� 6
|
360
373
|
�� 6
|
361
|
-
���� 6
|
362
|
-
��� 6
|
363
|
-
��� 6
|
364
|
-
; 6
|
365
|
-
�� 6
|
366
|
-
��� 6
|
367
|
-
�,_ 6
|
368
|
-
_� 6
|
369
|
-
��_ 6
|
370
|
-
���_ 6
|
371
|
-
��� 6
|
372
|
-
_��� 6
|
373
|
-
��_ 6
|
374
|
-
�._ 6
|
375
|
-
�� 6
|
376
374
|
����_ 6
|
375
|
+
�� 6
|
376
|
+
�� 6
|
377
|
+
_�. 6
|
378
|
+
��� 6
|
377
379
|
��� 6
|
380
|
+
�� 6
|
378
381
|
_�� 6
|
379
382
|
�� 6
|
380
|
-
�� 6
|
381
|
-
_�._ 6
|
382
|
-
�� 6
|
383
|
-
�� 6
|
384
|
-
�� 6
|
385
|
-
�, 6
|
386
|
-
�, 6
|
387
|
-
�� 6
|
388
|
-
��� 6
|
389
|
-
�� 6
|
390
383
|
_� 6
|
391
|
-
|
384
|
+
�, 6
|
385
|
+
�� 6
|
386
|
+
����_ 6
|
387
|
+
���_ 6
|
388
|
+
_���_ 6
|
392
389
|
_�� 6
|
393
|
-
�� 6
|
394
|
-
�" 6
|
395
|
-
�� 6
|
396
|
-
��_ 6
|
397
|
-
_�. 6
|
390
|
+
��_ 6
|
398
391
|
��� 6
|
399
|
-
|
400
|
-
|
392
|
+
�._ 6
|
393
|
+
�� 6
|
394
|
+
�. 6
|
395
|
+
��_ 6
|
396
|
+
�� 6
|
397
|
+
���_ 6
|
398
|
+
�� 6
|
399
|
+
��� 5
|
400
|
+
���_ 5
|