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/thai.lm
CHANGED
@@ -1,39 +1,39 @@
|
|
1
1
|
_ 370
|
2
2
|
� 343
|
3
3
|
� 301
|
4
|
-
�
|
4
|
+
� 236
|
5
5
|
� 206
|
6
6
|
� 204
|
7
7
|
� 183
|
8
|
-
�
|
9
|
-
� 164
|
8
|
+
� 173
|
10
9
|
� 159
|
10
|
+
� 156
|
11
11
|
� 151
|
12
|
+
� 146
|
12
13
|
� 145
|
13
|
-
�
|
14
|
-
�
|
15
|
-
� 111
|
14
|
+
� 136
|
15
|
+
� 112
|
16
16
|
� 111
|
17
|
-
�
|
18
|
-
�
|
19
|
-
� 96
|
17
|
+
� 104
|
18
|
+
� 98
|
20
19
|
� 95
|
20
|
+
� 92
|
21
21
|
� 89
|
22
|
-
� 88
|
23
22
|
� 88
|
24
|
-
�
|
25
|
-
�
|
23
|
+
� 86
|
24
|
+
� 85
|
26
25
|
� 73
|
26
|
+
� 73
|
27
27
|
� 73
|
28
28
|
�� 70
|
29
|
-
�
|
29
|
+
� 66
|
30
30
|
� 59
|
31
|
+
� 56
|
31
32
|
� 54
|
32
33
|
�� 54
|
33
34
|
� 53
|
34
|
-
� 52
|
35
35
|
��� 51
|
36
|
-
�
|
36
|
+
� 50
|
37
37
|
�� 49
|
38
38
|
ͧ 48
|
39
39
|
�� 46
|
@@ -44,357 +44,357 @@ _ 370
|
|
44
44
|
�� 35
|
45
45
|
� 35
|
46
46
|
� 34
|
47
|
-
|
48
|
-
� 33
|
47
|
+
� 34
|
49
48
|
. 33
|
50
|
-
|
49
|
+
�� 33
|
51
50
|
�� 32
|
51
|
+
��� 32
|
52
52
|
ҧ 32
|
53
53
|
�� 31
|
54
54
|
�� 31
|
55
55
|
� 29
|
56
56
|
�� 29
|
57
|
-
|
57
|
+
__ 28
|
58
58
|
� 28
|
59
|
+
�� 28
|
59
60
|
��� 27
|
60
|
-
__ 27
|
61
61
|
�� 27
|
62
62
|
�� 25
|
63
63
|
�� 25
|
64
|
-
� 24
|
65
64
|
�� 24
|
66
|
-
|
65
|
+
� 24
|
67
66
|
�� 23
|
68
|
-
��� 23
|
69
67
|
Ѻ 23
|
70
|
-
|
68
|
+
ҡ 23
|
69
|
+
��� 23
|
70
|
+
� 22
|
71
|
+
_� 22
|
72
|
+
ѧ 21
|
73
|
+
�_ 21
|
71
74
|
ҹ 21
|
72
75
|
� 21
|
73
|
-
� 21
|
74
|
-
�_ 21
|
75
|
-
ѧ 21
|
76
76
|
� 20
|
77
77
|
�� 20
|
78
|
-
�� 20
|
79
78
|
� 20
|
79
|
+
�� 20
|
80
80
|
�� 19
|
81
|
-
�� 19
|
82
|
-
�� 19
|
83
81
|
͡ 19
|
82
|
+
�� 19
|
84
83
|
�� 19
|
85
|
-
��
|
86
|
-
�� 18
|
87
|
-
� 18
|
84
|
+
�� 19
|
88
85
|
�� 18
|
86
|
+
�� 18
|
89
87
|
��� 18
|
90
|
-
|
88
|
+
� 18
|
89
|
+
�� 18
|
91
90
|
� 18
|
92
91
|
� 18
|
92
|
+
�� 18
|
93
|
+
�� 17
|
93
94
|
�� 17
|
94
|
-
|
95
|
+
ҵ 17
|
95
96
|
�� 17
|
96
|
-
�� 17
|
97
|
+
�� 17
|
97
98
|
� 17
|
98
|
-
ҵ 17
|
99
99
|
�Ѱ 16
|
100
|
-
|
101
|
-
�� 16
|
100
|
+
�� 16
|
102
101
|
��� 16
|
103
|
-
�ͧ 16
|
104
102
|
�_ 16
|
105
103
|
�� 16
|
106
|
-
�� 16
|
107
|
-
�� 16
|
108
104
|
��� 16
|
105
|
+
�ͧ 16
|
106
|
+
Ѱ 16
|
107
|
+
�� 16
|
108
|
+
�� 16
|
109
109
|
�� 16
|
110
|
-
|
111
|
-
� 15
|
112
|
-
�_ 15
|
110
|
+
�_ 15
|
113
111
|
�� 15
|
114
|
-
� 15
|
112
|
+
�_ 15
|
113
|
+
�� 15
|
115
114
|
�� 15
|
116
|
-
�_ 15
|
117
|
-
� 15
|
118
115
|
�� 15
|
116
|
+
� 15
|
117
|
+
� 15
|
119
118
|
�ͧ 14
|
120
|
-
�� 14
|
121
119
|
�� 14
|
122
|
-
�� 14
|
123
|
-
� 14
|
124
120
|
� 14
|
125
|
-
� 14
|
126
|
-
�� 14
|
127
121
|
�� 14
|
128
|
-
|
129
|
-
��
|
130
|
-
�
|
131
|
-
��
|
132
|
-
|
122
|
+
� 14
|
123
|
+
�� 14
|
124
|
+
� 14
|
125
|
+
�� 14
|
126
|
+
� 14
|
127
|
+
�� 13
|
133
128
|
�� 13
|
134
|
-
|
129
|
+
_� 13
|
135
130
|
�� 13
|
136
|
-
� 13
|
137
131
|
�� 13
|
138
|
-
���� 13
|
139
132
|
ѡ 13
|
133
|
+
�� 13
|
134
|
+
� 13
|
135
|
+
���� 13
|
140
136
|
� 13
|
141
|
-
¡ 13
|
142
137
|
�� 13
|
138
|
+
¡ 13
|
139
|
+
�� 13
|
140
|
+
� 13
|
143
141
|
��� 13
|
142
|
+
ѹ 13
|
144
143
|
�� 13
|
145
|
-
��
|
146
|
-
|
147
|
-
�� 12
|
148
|
-
���� 12
|
149
|
-
��� 12
|
144
|
+
�� 13
|
145
|
+
�� 12
|
150
146
|
��� 12
|
147
|
+
�� 12
|
148
|
+
���� 12
|
149
|
+
_� 12
|
150
|
+
12
|
151
|
+
�� 12
|
151
152
|
Ѵ 12
|
152
|
-
�� 12
|
153
153
|
˹ 12
|
154
|
-
|
155
|
-
�� 12
|
154
|
+
�� 12
|
155
|
+
�� 12
|
156
156
|
��� 12
|
157
|
+
�� 12
|
158
|
+
��� 12
|
157
159
|
� 12
|
158
|
-
�� 12
|
159
160
|
�� 12
|
160
|
-
�� 12
|
161
|
-
|
162
|
-
�� 12
|
163
|
-
�� 12
|
161
|
+
�� 12
|
162
|
+
�ҧ 12
|
163
|
+
�� 12
|
164
164
|
�� 11
|
165
|
-
Թ 11
|
166
165
|
��� 11
|
167
|
-
|
168
|
-
�� 11
|
169
|
-
|
166
|
+
�� 11
|
167
|
+
�� 11
|
168
|
+
_� 11
|
169
|
+
_� 11
|
170
170
|
з 11
|
171
|
-
� 11
|
172
|
-
�� 11
|
173
171
|
ǹ 11
|
174
|
-
|
172
|
+
Դ 11
|
173
|
+
Թ 11
|
175
174
|
�� 11
|
176
|
-
�� 11
|
177
|
-
�� 11
|
178
175
|
�� 11
|
176
|
+
�� 11
|
177
|
+
��� 11
|
178
|
+
�� 11
|
179
|
+
�� 11
|
179
180
|
� 11
|
181
|
+
��� 11
|
182
|
+
� 11
|
183
|
+
�� 11
|
180
184
|
�� 11
|
181
|
-
_� 11
|
182
|
-
�� 11
|
183
185
|
�� 11
|
184
186
|
�� 10
|
185
|
-
|
186
|
-
�� 10
|
187
|
-
� 10
|
188
|
-
�_ 10
|
189
|
-
�ҹ 10
|
190
|
-
��� 10
|
191
|
-
Դ 10
|
192
|
-
ä 10
|
187
|
+
_� 10
|
188
|
+
�� 10
|
193
189
|
�� 10
|
190
|
+
�� 10
|
191
|
+
��� 10
|
194
192
|
�� 10
|
195
|
-
|
193
|
+
ä 10
|
194
|
+
��ͧ 10
|
195
|
+
�� 10
|
196
196
|
�� 10
|
197
|
-
�� 10
|
197
|
+
�� 10
|
198
198
|
���� 10
|
199
|
+
� 10
|
199
200
|
�� 10
|
200
|
-
|
201
|
-
��� 10
|
201
|
+
�_ 10
|
202
202
|
�� 10
|
203
|
+
�ҹ 10
|
204
|
+
� 10
|
203
205
|
�� 10
|
204
|
-
�� 10
|
205
|
-
_� 10
|
206
|
-
�� 10
|
207
|
-
_� 10
|
208
|
-
��ͧ 10
|
209
206
|
��� 10
|
210
|
-
|
207
|
+
��� 10
|
208
|
+
�� 10
|
209
|
+
�_ 9
|
210
|
+
�Ѻ 9
|
211
|
+
�� 9
|
212
|
+
�� 9
|
211
213
|
�Ѻ 9
|
212
|
-
���� 9
|
213
|
-
�ҧ 9
|
214
|
-
��� 9
|
215
|
-
�� 9
|
216
|
-
�� 9
|
217
214
|
Ҥ 9
|
215
|
+
�� 9
|
218
216
|
�ѧ 9
|
219
|
-
|
217
|
+
ç 9
|
220
218
|
��_ 9
|
221
|
-
|
222
|
-
|
219
|
+
�ҧ 9
|
220
|
+
_� 9
|
223
221
|
�� 9
|
224
|
-
� 9
|
225
|
-
�� 9
|
226
222
|
���_ 9
|
227
|
-
�� 9
|
223
|
+
�� 9
|
224
|
+
���� 9
|
225
|
+
�� 9
|
226
|
+
�� 9
|
228
227
|
��� 9
|
229
|
-
|
230
|
-
|
231
|
-
|
232
|
-
�� 8
|
233
|
-
�� 8
|
234
|
-
�¡ 8
|
235
|
-
��� 8
|
236
|
-
�ҡ 8
|
237
|
-
���� 8
|
228
|
+
��� 9
|
229
|
+
� 9
|
230
|
+
�� 9
|
238
231
|
�� 8
|
239
|
-
��� 8
|
240
232
|
�� 8
|
241
|
-
�� 8
|
233
|
+
�� 8
|
234
|
+
�� 8
|
242
235
|
�. 8
|
236
|
+
�� 8
|
237
|
+
�� 8
|
238
|
+
�� 8
|
239
|
+
�¡ 8
|
240
|
+
��� 8
|
241
|
+
�_ 8
|
242
|
+
�ҵ 8
|
243
243
|
ŧ 8
|
244
|
-
ͺ 8
|
245
244
|
�� 8
|
246
245
|
ѭ 8
|
247
|
-
|
248
|
-
�� 8
|
246
|
+
�ҡ 8
|
249
247
|
�� 8
|
250
248
|
�� 8
|
251
|
-
�� 8
|
252
249
|
ҵ� 8
|
253
|
-
|
254
|
-
|
255
|
-
��� 8
|
256
|
-
�_ 8
|
257
|
-
�ҵ 8
|
258
|
-
��� 8
|
250
|
+
Ի 8
|
251
|
+
���� 8
|
259
252
|
�� 8
|
260
|
-
|
253
|
+
�ҵ� 8
|
254
|
+
��� 8
|
255
|
+
� 8
|
256
|
+
��� 8
|
261
257
|
�� 8
|
262
|
-
|
258
|
+
�� 8
|
263
259
|
�� 8
|
264
|
-
|
265
|
-
�� 8
|
266
|
-
|
267
|
-
�� 7
|
268
|
-
�� 7
|
269
|
-
|
270
|
-
|
271
|
-
|
260
|
+
Ǻ 8
|
261
|
+
�� 8
|
262
|
+
ͺ 8
|
263
|
+
�� 7
|
264
|
+
�� 7
|
265
|
+
��� 7
|
266
|
+
��� 7
|
267
|
+
��� 7
|
268
|
+
��� 7
|
269
|
+
_� 7
|
270
|
+
��� 7
|
271
|
+
�ä 7
|
272
272
|
�� 7
|
273
|
+
_� 7
|
274
|
+
�� 7
|
273
275
|
�� 7
|
274
|
-
|
275
|
-
|
276
|
-
�Ѱ�� 7
|
277
|
-
�� 7
|
276
|
+
_� 7
|
277
|
+
� 7
|
278
278
|
�� 7
|
279
|
-
|
280
|
-
|
281
|
-
|
282
|
-
�� 7
|
283
|
-
��� 7
|
284
|
-
�Դ 7
|
285
|
-
�� 7
|
286
|
-
�� 7
|
287
|
-
�� 7
|
288
|
-
��� 7
|
289
|
-
�� 7
|
290
|
-
� 7
|
279
|
+
� 7
|
280
|
+
_� 7
|
281
|
+
�� 7
|
291
282
|
�� 7
|
292
|
-
|
293
|
-
|
294
|
-
��� 7
|
295
|
-
١ 7
|
283
|
+
� 7
|
284
|
+
��� 7
|
296
285
|
ҷ 7
|
297
|
-
|
298
|
-
|
299
|
-
|
300
|
-
|
286
|
+
��� 7
|
287
|
+
�� 7
|
288
|
+
�� 7
|
289
|
+
Ѱ��� 7
|
290
|
+
��� 7
|
291
|
+
��� 7
|
292
|
+
���� 7
|
293
|
+
�� 7
|
294
|
+
��� 7
|
295
|
+
ǡ 7
|
296
|
+
�� 7
|
297
|
+
�� 7
|
298
|
+
���� 7
|
299
|
+
Ѱ�� 7
|
300
|
+
֧ 7
|
301
301
|
�� 7
|
302
|
-
|
303
|
-
��� 7
|
304
|
-
�_ 7
|
305
|
-
�� 7
|
306
|
-
_��� 7
|
302
|
+
�Ѱ�� 7
|
307
303
|
��� 7
|
304
|
+
�� 7
|
308
305
|
�� 7
|
309
|
-
�� 7
|
306
|
+
�� 7
|
307
|
+
��� 7
|
308
|
+
���� 7
|
309
|
+
�� 7
|
310
310
|
.� 7
|
311
|
-
�� 7
|
312
|
-
_� 7
|
313
|
-
��� 7
|
314
|
-
��� 7
|
315
|
-
Ѱ��� 7
|
316
|
-
_� 7
|
317
|
-
֧ 7
|
318
|
-
���� 7
|
319
|
-
� 7
|
320
|
-
���� 7
|
321
311
|
��ä 7
|
322
|
-
|
323
|
-
|
324
|
-
|
325
|
-
��� 7
|
312
|
+
�� 7
|
313
|
+
_�� 7
|
314
|
+
�� 7
|
326
315
|
�� 7
|
316
|
+
��� 7
|
317
|
+
�Դ 7
|
318
|
+
Ѱ� 7
|
327
319
|
�� 7
|
328
|
-
�� 7
|
329
|
-
|
330
|
-
|
331
|
-
|
332
|
-
|
333
|
-
�ä 7
|
334
|
-
�� 7
|
320
|
+
�� 7
|
321
|
+
��� 7
|
322
|
+
��� 7
|
323
|
+
�ͧ 7
|
324
|
+
�� 7
|
335
325
|
�� 7
|
336
|
-
|
337
|
-
|
326
|
+
�� 7
|
327
|
+
�� 7
|
328
|
+
�Ѱ� 7
|
329
|
+
�� 7
|
338
330
|
�� 7
|
339
|
-
|
340
|
-
|
341
|
-
|
331
|
+
١ 7
|
332
|
+
_� 7
|
333
|
+
��� 7
|
334
|
+
�� 7
|
335
|
+
�� 7
|
336
|
+
_��� 7
|
337
|
+
���� 7
|
338
|
+
�� 7
|
342
339
|
�ǹ 7
|
343
|
-
|
344
|
-
|
345
|
-
�� 6
|
346
|
-
|
347
|
-
���� 6
|
348
|
-
�� 6
|
349
|
-
ó 6
|
350
|
-
�.�. 6
|
351
|
-
�� 6
|
352
|
-
÷ 6
|
353
|
-
��� 6
|
340
|
+
�.� 6
|
341
|
+
�� 6
|
342
|
+
�� 6
|
343
|
+
_� 6
|
354
344
|
�� 6
|
355
|
-
|
356
|
-
�� 6
|
357
|
-
|
358
|
-
|
359
|
-
|
360
|
-
|
361
|
-
|
345
|
+
�. 6
|
346
|
+
_�� 6
|
347
|
+
��� 6
|
348
|
+
��� 6
|
349
|
+
�� 6
|
350
|
+
Ѱy� 6
|
351
|
+
÷ 6
|
352
|
+
��� 6
|
353
|
+
y��� 6
|
354
|
+
Ѱy�� 6
|
355
|
+
��� 6
|
362
356
|
��� 6
|
363
|
-
|
364
|
-
�_ 6
|
365
|
-
���ͧ 6
|
366
|
-
�� 6
|
357
|
+
�� 6
|
367
358
|
Ѳ 6
|
368
|
-
�� 6
|
369
|
-
� 6
|
370
|
-
�� 6
|
371
|
-
�Ѱ�� 6
|
372
|
-
ͧ_ 6
|
373
|
-
��_ 6
|
374
|
-
ҡ� 6
|
375
|
-
��� 6
|
376
|
-
Ҩ 6
|
377
|
-
�� 6
|
378
|
-
Ѱ�� 6
|
379
|
-
�� 6
|
380
|
-
�� 6
|
381
|
-
��_ 6
|
382
359
|
����� 6
|
383
|
-
|
384
|
-
|
385
|
-
|
386
|
-
|
387
|
-
|
388
|
-
|
389
|
-
|
390
|
-
�� 6
|
360
|
+
�÷ 6
|
361
|
+
��ǹ 6
|
362
|
+
���ͧ 6
|
363
|
+
�� 6
|
364
|
+
.� 6
|
365
|
+
ӹ 6
|
366
|
+
��� 6
|
367
|
+
�� 6
|
368
|
+
ͧ_ 6
|
391
369
|
��� 6
|
370
|
+
ҡ� 6
|
371
|
+
y�� 6
|
392
372
|
�.�.� 6
|
393
|
-
|
394
|
-
|
395
|
-
|
396
|
-
|
397
|
-
|
373
|
+
ҡ�� 6
|
374
|
+
�Ѱy� 6
|
375
|
+
�_ 6
|
376
|
+
�� 6
|
377
|
+
��� 6
|
378
|
+
�_ 6
|
379
|
+
y 6
|
380
|
+
ó 6
|
398
381
|
�� 6
|
399
|
-
�� 6
|
382
|
+
_�� 6
|
383
|
+
�Ѵ 6
|
384
|
+
�Ѱy 6
|
385
|
+
�� 6
|
386
|
+
�� 6
|
387
|
+
�. 6
|
388
|
+
�� 6
|
400
389
|
���� 6
|
390
|
+
����� 6
|
391
|
+
��. 6
|
392
|
+
��÷ 6
|
393
|
+
�� 6
|
394
|
+
�� 6
|
395
|
+
��� 6
|
396
|
+
�� 6
|
397
|
+
�Դ 6
|
398
|
+
.�.� 6
|
399
|
+
�� 6
|
400
|
+
�� 6
|