scylla 0.4.3 → 0.5.0
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +1 -0
- data/Gemfile.lock +10 -0
- data/VERSION +1 -1
- data/lib/scylla/generator.rb +1 -1
- data/lib/scylla/lms/13375P33K.lm +156 -156
- data/lib/scylla/lms/arabic.lm +133 -133
- data/lib/scylla/lms/bulgarian.lm +122 -122
- data/lib/scylla/lms/catalan.lm +151 -151
- data/lib/scylla/lms/danish.lm +137 -137
- data/lib/scylla/lms/english.lm +207 -207
- data/lib/scylla/lms/french.lm +400 -400
- data/lib/scylla/lms/japanese.lm +400 -400
- data/lib/scylla/lms/korean.lm +233 -233
- data/lib/scylla/lms/norwegian.lm +398 -398
- data/lib/scylla/lms/spanish.lm +98 -98
- data/lib/scylla/lms/swedish.lm +123 -123
- data/lib/scylla/lms/tagalog.lm +223 -223
- data/lib/scylla/lms/welsh.lm +234 -234
- data/lib/scylla/resources.rb +10 -10
- data/scylla.gemspec +17 -40
- data/source_texts/catalan.txt +28 -28
- data/source_texts/danish.txt +62 -62
- data/source_texts/english.txt +10 -10
- data/source_texts/french.txt +470 -77
- data/source_texts/japanese.txt +453 -199
- data/source_texts/norwegian.txt +96 -63
- data/source_texts/spanish.txt +269 -269
- data/test/classifier_test.rb +2 -2
- data/test/fixtures/lms/13375p33k.lm +156 -156
- data/test/fixtures/lms/danish.lm +137 -137
- data/test/fixtures/lms/english.lm +207 -207
- data/test/fixtures/lms/french.lm +400 -400
- data/test/fixtures/lms/hindi.lm +400 -0
- data/test/fixtures/lms/italian.lm +400 -0
- data/test/fixtures/lms/japanese.lm +400 -400
- data/test/fixtures/lms/norwegian.lm +400 -0
- data/test/fixtures/lms/spanish.lm +98 -98
- data/test/fixtures/source_texts/danish.txt +62 -62
- data/test/fixtures/source_texts/english.txt +10 -10
- data/test/fixtures/source_texts/french.txt +470 -77
- data/test/fixtures/source_texts/hindi.txt +199 -0
- data/test/fixtures/source_texts/italian.txt +120 -0
- data/test/fixtures/source_texts/japanese.txt +453 -199
- data/test/fixtures/source_texts/norwegian.txt +190 -0
- data/test/fixtures/source_texts/spanish.txt +269 -269
- data/test/fixtures/test_languages/english +61 -0
- data/test/fixtures/test_languages/french +0 -0
- data/test/fixtures/test_languages/german +29 -0
- data/test/fixtures/test_languages/hindi +3 -0
- data/test/fixtures/test_languages/italian +6 -0
- data/test/fixtures/test_languages/japanese +79 -0
- data/test/fixtures/test_languages/norwegian +14 -0
- data/test/fixtures/test_languages/spanish +22 -0
- data/test/generator_test.rb +0 -1
- data/test/language_test.rb +28 -0
- metadata +20 -43
- data/lib/scylla/lms/esperanto.lm +0 -400
- data/lib/scylla/lms/hungarian.lm +0 -400
- data/lib/scylla/lms/irish.lm +0 -400
- data/lib/scylla/lms/kannada.lm +0 -400
- data/lib/scylla/lms/latin.lm +0 -400
- data/lib/scylla/lms/malay.lm +0 -400
- data/lib/scylla/lms/marathi.lm +0 -400
- data/lib/scylla/lms/mingo.lm +0 -400
- data/lib/scylla/lms/nepali.lm +0 -400
- data/lib/scylla/lms/quechua.lm +0 -400
- data/lib/scylla/lms/rumantsch.lm +0 -400
- data/lib/scylla/lms/sanskrit.lm +0 -400
- data/lib/scylla/lms/scots_gaelic.lm +0 -400
- data/lib/scylla/lms/serbian.lm +0 -400
- data/lib/scylla/lms/swahili.lm +0 -400
- data/lib/scylla/lms/tamil.lm +0 -400
- data/lib/scylla/lms/ukrainian.lm +0 -400
- data/lib/scylla/lms/yiddish.lm +0 -400
- data/source_texts/esperanto.txt +0 -199
- data/source_texts/hungarian.txt +0 -102
- data/source_texts/irish.txt +0 -209
- data/source_texts/kannada.txt +0 -283
- data/source_texts/latin.txt +0 -120
- data/source_texts/malay.txt +0 -108
- data/source_texts/marathi.txt +0 -100
- data/source_texts/mingo.txt +0 -146
- data/source_texts/nepali.txt +0 -131
- data/source_texts/quechua.txt +0 -108
- data/source_texts/rumantsch.txt +0 -110
- data/source_texts/sanskrit.txt +0 -135
- data/source_texts/scots_gaelic.txt +0 -93
- data/source_texts/serbian.txt +0 -121
- data/source_texts/swahili.txt +0 -120
- data/source_texts/tamil.txt +0 -167
- data/source_texts/ukrainian.txt +0 -214
- data/source_texts/yiddish-utf.txt +0 -83
- data/test/fixtures/lms/kannada.lm +0 -400
- data/test/fixtures/source_texts/kannada.txt +0 -283
data/lib/scylla/lms/korean.lm
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 1282
|
2
2
|
� 290
|
3
3
|
� 184
|
4
4
|
� 181
|
@@ -11,7 +11,7 @@ _ 1278
|
|
11
11
|
� 99
|
12
12
|
� 90
|
13
13
|
� 89
|
14
|
-
__
|
14
|
+
__ 87
|
15
15
|
� 78
|
16
16
|
_� 77
|
17
17
|
� 75
|
@@ -24,377 +24,377 @@ _
|
|
24
24
|
�� 65
|
25
25
|
� 62
|
26
26
|
� 55
|
27
|
-
� 54
|
28
27
|
� 54
|
28
|
+
� 54
|
29
29
|
� 53
|
30
30
|
� 52
|
31
31
|
� 50
|
32
|
-
� 49
|
33
32
|
� 49
|
34
|
-
�
|
33
|
+
� 49
|
35
34
|
_� 48
|
35
|
+
� 48
|
36
36
|
� 46
|
37
37
|
� 45
|
38
38
|
. 44
|
39
39
|
� 40
|
40
|
-
� 39
|
41
|
-
��. 39
|
42
40
|
� 39
|
43
41
|
�. 39
|
44
42
|
� 39
|
43
|
+
� 39
|
44
|
+
��. 39
|
45
45
|
� 37
|
46
46
|
�� 36
|
47
|
-
� 35
|
48
47
|
� 35
|
49
|
-
|
50
|
-
_� 34
|
48
|
+
� 35
|
51
49
|
� 34
|
50
|
+
_� 34
|
51
|
+
�� 34
|
52
52
|
� 33
|
53
53
|
�_ 32
|
54
54
|
� 32
|
55
|
-
_�
|
55
|
+
_� 32
|
56
56
|
�_ 31
|
57
57
|
� 31
|
58
|
+
��_ 29
|
58
59
|
�� 29
|
60
|
+
�_ 29
|
59
61
|
�� 29
|
60
|
-
��_ 29
|
61
62
|
� 29
|
62
|
-
��_ 29
|
63
|
-
�_ 29
|
64
|
-
_� 27
|
63
|
+
��_ 29
|
65
64
|
_� 27
|
66
|
-
_� 27
|
67
65
|
�� 27
|
68
|
-
|
66
|
+
_� 27
|
67
|
+
_� 27
|
69
68
|
� 26
|
70
|
-
��
|
71
|
-
�� 25
|
72
|
-
_� 25
|
73
|
-
_� 25
|
69
|
+
�� 26
|
74
70
|
�� 25
|
75
71
|
_� 25
|
76
|
-
�
|
72
|
+
_� 25
|
73
|
+
_� 25
|
74
|
+
�� 25
|
75
|
+
�� 25
|
77
76
|
�_ 24
|
78
77
|
�_ 24
|
79
|
-
|
80
|
-
� 23
|
81
|
-
_� 23
|
78
|
+
�_ 24
|
82
79
|
��_ 23
|
83
|
-
�� 23
|
84
80
|
��_ 23
|
85
81
|
�� 23
|
82
|
+
�� 23
|
86
83
|
� 23
|
84
|
+
�� 23
|
85
|
+
� 23
|
86
|
+
_� 23
|
87
87
|
�� 22
|
88
|
-
� 22
|
89
|
-
� 22
|
90
88
|
�� 22
|
91
|
-
�� 22
|
92
89
|
�_ 22
|
90
|
+
� 22
|
91
|
+
� 22
|
92
|
+
�� 22
|
93
93
|
�� 22
|
94
|
+
_� 21
|
94
95
|
��_ 21
|
95
96
|
_� 21
|
96
|
-
�� 21
|
97
97
|
�� 21
|
98
|
-
|
99
|
-
� 20
|
100
|
-
��_ 20
|
98
|
+
�� 21
|
99
|
+
_� 20
|
101
100
|
�_ 20
|
101
|
+
� 20
|
102
102
|
��_ 20
|
103
|
-
_
|
103
|
+
��_ 20
|
104
|
+
� 19
|
105
|
+
_�� 19
|
104
106
|
�� 19
|
105
107
|
� 19
|
106
|
-
� 19
|
107
108
|
._ 19
|
108
|
-
_�� 19
|
109
109
|
ִ 18
|
110
|
-
_�� 18
|
111
|
-
��_ 18
|
112
|
-
�� 18
|
113
110
|
�_ 18
|
114
|
-
�_ 18
|
115
|
-
�_ 18
|
116
|
-
� 18
|
117
111
|
� 18
|
112
|
+
��_ 18
|
118
113
|
�� 18
|
114
|
+
�_ 18
|
115
|
+
��_ 18
|
116
|
+
� 18
|
119
117
|
� 18
|
120
|
-
��
|
121
|
-
_
|
122
|
-
�
|
123
|
-
�� 17
|
118
|
+
�� 18
|
119
|
+
_�� 18
|
120
|
+
�_ 18
|
124
121
|
�_ 17
|
122
|
+
� 17
|
125
123
|
�ִ 17
|
124
|
+
�� 17
|
125
|
+
_� 17
|
126
|
+
�� 16
|
126
127
|
" 16
|
127
128
|
�� 16
|
128
|
-
� 16
|
129
129
|
�� 16
|
130
130
|
�� 16
|
131
|
-
|
131
|
+
� 16
|
132
|
+
_� 15
|
133
|
+
, 15
|
134
|
+
��_ 15
|
135
|
+
' 15
|
132
136
|
�� 15
|
133
|
-
�� 15
|
134
|
-
� 15
|
135
137
|
� 15
|
136
|
-
��
|
137
|
-
, 15
|
138
|
-
�._ 15
|
139
|
-
_� 15
|
138
|
+
�� 15
|
140
139
|
��._ 15
|
141
|
-
|
140
|
+
�._ 15
|
141
|
+
� 15
|
142
|
+
�� 14
|
143
|
+
�� 14
|
144
|
+
� 14
|
142
145
|
�� 14
|
143
|
-
|
144
|
-
�� 14
|
145
|
-
��� 14
|
146
|
-
� 14
|
146
|
+
�� 14
|
147
|
+
�� 14
|
147
148
|
�� 14
|
149
|
+
��� 14
|
148
150
|
_�ִ 14
|
149
|
-
�� 14
|
150
|
-
�� 14
|
151
|
-
�� 14
|
152
151
|
� 14
|
153
|
-
|
154
|
-
�� 14
|
155
|
-
�� 14
|
156
|
-
|
157
|
-
�ִ� 13
|
158
|
-
ߴ 13
|
159
|
-
ȸ 13
|
160
|
-
�� 13
|
152
|
+
�� 14
|
153
|
+
�� 14
|
154
|
+
_�� 14
|
155
|
+
� 14
|
161
156
|
� 13
|
157
|
+
ȸ 13
|
162
158
|
�� 13
|
163
|
-
�� 13
|
164
159
|
�� 13
|
160
|
+
�� 13
|
161
|
+
�ִ� 13
|
162
|
+
ߴ 13
|
163
|
+
ִ� 13
|
164
|
+
�� 13
|
165
165
|
�� 13
|
166
166
|
�_ 13
|
167
|
-
� 12
|
168
167
|
� 12
|
169
|
-
|
170
|
-
� 12
|
171
|
-
�ߴ� 12
|
168
|
+
� 12
|
172
169
|
,_ 12
|
170
|
+
� 12
|
173
171
|
� 12
|
172
|
+
�ߴ� 12
|
173
|
+
�_ 12
|
174
174
|
� 12
|
175
175
|
�ߴ 12
|
176
|
-
�_ 12
|
177
176
|
ߴ� 12
|
178
|
-
��
|
179
|
-
|
180
|
-
��� 11
|
181
|
-
_�� 11
|
182
|
-
�� 11
|
183
|
-
�ߴ�. 11
|
184
|
-
��_ 11
|
185
|
-
ߴ�. 11
|
186
|
-
�� 11
|
187
|
-
_� 11
|
177
|
+
�� 12
|
178
|
+
�� 11
|
188
179
|
_� 11
|
189
|
-
_�� 11
|
190
180
|
�� 11
|
181
|
+
�� 11
|
182
|
+
�ߴ�. 11
|
183
|
+
_�� 11
|
184
|
+
��_ 11
|
185
|
+
��_ 11
|
186
|
+
��� 11
|
187
|
+
�� 11
|
191
188
|
�� 11
|
189
|
+
_� 11
|
192
190
|
���� 11
|
191
|
+
�� 11
|
193
192
|
_�� 11
|
194
|
-
|
195
|
-
|
196
|
-
��
|
193
|
+
�_ 11
|
194
|
+
ߴ�. 11
|
195
|
+
_�� 11
|
196
|
+
��� 11
|
197
197
|
_�ִ� 10
|
198
|
-
��� 10
|
199
|
-
� 10
|
200
|
-
�� 10
|
201
|
-
�� 10
|
202
|
-
�� 10
|
203
198
|
� 10
|
199
|
+
��� 10
|
204
200
|
õ 10
|
205
|
-
�� 10
|
201
|
+
�� 10
|
202
|
+
� 10
|
203
|
+
� 10
|
206
204
|
��� 10
|
207
|
-
|
208
|
-
�
|
209
|
-
|
210
|
-
_�� 10
|
205
|
+
�� 10
|
206
|
+
� 10
|
207
|
+
�� 10
|
211
208
|
�� 10
|
212
|
-
� 10
|
213
|
-
� 10
|
214
|
-
�� 10
|
215
209
|
�� 10
|
216
|
-
�� 10
|
210
|
+
_�� 10
|
211
|
+
�� 10
|
212
|
+
�_ 10
|
213
|
+
���� 10
|
214
|
+
�� 10
|
217
215
|
�� 10
|
218
|
-
|
219
|
-
��
|
220
|
-
����_ 9
|
221
|
-
� 9
|
222
|
-
_� 9
|
216
|
+
�� 10
|
217
|
+
�� 10
|
223
218
|
_�� 9
|
224
|
-
� 9
|
225
|
-
|
219
|
+
� 9
|
220
|
+
����_ 9
|
226
221
|
���_ 9
|
227
|
-
�� 9
|
228
|
-
�� 9
|
229
|
-
� 9
|
230
222
|
�� 9
|
231
|
-
|
223
|
+
_� 9
|
232
224
|
�� 9
|
233
|
-
|
225
|
+
ϰ 9
|
226
|
+
� 9
|
227
|
+
�� 9
|
228
|
+
�� 9
|
229
|
+
�� 9
|
230
|
+
�� 9
|
231
|
+
�� 9
|
232
|
+
� 9
|
234
233
|
�_ 8
|
235
|
-
���_ 8
|
236
234
|
�� 8
|
237
|
-
|
238
|
-
|
239
|
-
� 8
|
235
|
+
���_ 8
|
236
|
+
� 8
|
240
237
|
� 8
|
241
|
-
�� 8
|
242
|
-
ġ 8
|
243
|
-
�� 8
|
244
238
|
�� 8
|
239
|
+
�� 8
|
240
|
+
� 8
|
241
|
+
��� 8
|
242
|
+
�� 8
|
243
|
+
� 8
|
245
244
|
��_ 8
|
246
|
-
�� 8
|
245
|
+
�� 8
|
247
246
|
�� 8
|
248
|
-
|
249
|
-
|
247
|
+
�_ 8
|
248
|
+
� 8
|
249
|
+
�� 8
|
250
|
+
�� 8
|
251
|
+
�_ 8
|
252
|
+
�� 8
|
253
|
+
ġ 8
|
250
254
|
��� 8
|
251
|
-
�_ 8
|
252
|
-
�� 8
|
253
255
|
�_ 8
|
254
|
-
�� 8
|
256
|
+
�� 8
|
255
257
|
�� 8
|
256
|
-
|
257
|
-
�� 8
|
258
|
-
�_ 8
|
258
|
+
�� 8
|
259
259
|
�ϰ 8
|
260
|
-
|
260
|
+
�_ 8
|
261
|
+
����_ 8
|
261
262
|
�� 8
|
262
|
-
_
|
263
|
+
_�� 8
|
264
|
+
�� 8
|
265
|
+
�� 8
|
263
266
|
� 8
|
264
|
-
|
265
|
-
� 8
|
266
|
-
��� 8
|
267
|
-
�� 7
|
268
|
-
�� 7
|
267
|
+
_' 8
|
269
268
|
���� 7
|
270
|
-
�� 7
|
269
|
+
_�� 7
|
271
270
|
��� 7
|
271
|
+
�Ӵ 7
|
272
|
+
��_ 7
|
272
273
|
�� 7
|
273
|
-
|
274
|
-
_�� 7
|
275
|
-
Ӵ� 7
|
274
|
+
��� 7
|
276
275
|
�Ӵ 7
|
277
|
-
|
278
|
-
� 7
|
276
|
+
����_ 7
|
279
277
|
_��_ 7
|
280
|
-
|
281
|
-
�� 7
|
278
|
+
�� 7
|
282
279
|
�_ 7
|
283
|
-
|
284
|
-
��_ 7
|
285
|
-
��_ 7
|
286
|
-
��� 7
|
287
|
-
�� 7
|
288
|
-
��_ 7
|
280
|
+
��� 7
|
289
281
|
��_ 7
|
290
|
-
�� 7
|
282
|
+
�� 7
|
291
283
|
� 7
|
292
|
-
( 7
|
293
|
-
ü 7
|
294
|
-
����_ 7
|
295
|
-
_�� 7
|
296
|
-
�� 7
|
297
|
-
�� 7
|
298
|
-
�ִ�. 7
|
299
|
-
�� 7
|
300
|
-
��� 7
|
301
284
|
�� 7
|
285
|
+
�Ӵ� 7
|
286
|
+
��_ 7
|
287
|
+
��Ӵ 7
|
302
288
|
_�� 7
|
303
|
-
|
304
|
-
�� 7
|
289
|
+
�� 7
|
290
|
+
�� 7
|
305
291
|
��� 7
|
292
|
+
� 7
|
293
|
+
�� 7
|
294
|
+
�� 7
|
295
|
+
ü 7
|
296
|
+
�� 7
|
297
|
+
��_ 7
|
298
|
+
( 7
|
299
|
+
_�� 7
|
300
|
+
�� 7
|
306
301
|
Ӵ 7
|
302
|
+
�� 7
|
303
|
+
Ӵ� 7
|
304
|
+
Ʈ 7
|
305
|
+
_�� 7
|
307
306
|
�Ӵ� 7
|
308
|
-
|
309
|
-
) 7
|
307
|
+
�ִ�. 7
|
310
308
|
_��� 7
|
311
|
-
|
309
|
+
�� 7
|
312
310
|
�� 7
|
313
311
|
���_ 7
|
314
|
-
|
315
|
-
|
316
|
-
|
317
|
-
|
312
|
+
) 7
|
313
|
+
ִ�. 7
|
314
|
+
�� 7
|
315
|
+
��� 6
|
316
|
+
_�� 6
|
317
|
+
ȯ 6
|
318
318
|
�� 6
|
319
|
+
�Բ 6
|
319
320
|
�� 6
|
320
|
-
_� 6
|
321
|
-
�� 6
|
322
|
-
�� 6
|
323
321
|
�_ 6
|
324
|
-
|
325
|
-
�� 6
|
326
|
-
_�� 6
|
327
|
-
��_ 6
|
322
|
+
Բ� 6
|
323
|
+
�� 6
|
328
324
|
�Բ�_ 6
|
329
|
-
�� 6
|
330
|
-
|
331
|
-
|
332
|
-
|
333
|
-
|
325
|
+
�� 6
|
326
|
+
.� 6
|
327
|
+
_� 6
|
328
|
+
�� 6
|
329
|
+
��_ 6
|
330
|
+
_� 6
|
331
|
+
�� 6
|
334
332
|
_�� 6
|
333
|
+
�� 6
|
334
|
+
_��� 6
|
335
|
+
��_ 6
|
336
|
+
Ÿ 6
|
337
|
+
Բ 6
|
335
338
|
�� 6
|
336
|
-
�� 6
|
339
|
+
�� 6
|
340
|
+
� 6
|
341
|
+
�� 6
|
342
|
+
�� 6
|
343
|
+
_õ 6
|
344
|
+
�� 6
|
345
|
+
�� 6
|
346
|
+
_�� 6
|
347
|
+
_��� 6
|
348
|
+
�� 6
|
349
|
+
_" 6
|
337
350
|
_�� 6
|
338
|
-
��� 6
|
339
|
-
Բ� 6
|
340
|
-
��_ 6
|
341
351
|
��� 6
|
342
|
-
|
343
|
-
�� 6
|
344
|
-
|
345
|
-
Բ�_ 6
|
346
|
-
_��� 6
|
347
|
-
�� 6
|
352
|
+
��� 6
|
353
|
+
�� 6
|
354
|
+
�� 6
|
348
355
|
̴ 6
|
349
|
-
��� 6
|
350
|
-
.� 6
|
351
|
-
��_ 6
|
352
|
-
�� 6
|
353
|
-
�Բ� 6
|
354
356
|
> 6
|
355
|
-
|
356
|
-
_�� 6
|
357
|
-
_��� 6
|
357
|
+
Բ�_ 6
|
358
358
|
�_ 6
|
359
|
-
|
360
|
-
̵ 6
|
359
|
+
�� 6
|
361
360
|
�� 6
|
361
|
+
�� 6
|
362
|
+
�Բ� 6
|
362
363
|
�.� 6
|
363
|
-
�� 6
|
364
|
-
��_ 6
|
364
|
+
�� 6
|
365
365
|
�� 6
|
366
|
+
_�� 6
|
367
|
+
� 6
|
366
368
|
� 6
|
367
|
-
|
368
|
-
�_ 6
|
369
|
-
�� 6
|
370
|
-
_��_ 6
|
371
|
-
�� 6
|
372
|
-
�� 6
|
373
|
-
< 6
|
369
|
+
̵ 6
|
374
370
|
�̴ 6
|
375
|
-
|
376
|
-
�� 6
|
377
|
-
|
378
|
-
|
371
|
+
�_ 6
|
372
|
+
_�� 6
|
373
|
+
�� 6
|
374
|
+
�� 6
|
379
375
|
_�� 6
|
380
|
-
_
|
376
|
+
��_ 6
|
377
|
+
��_ 6
|
378
|
+
�� 6
|
379
|
+
_��_ 6
|
381
380
|
��.� 6
|
382
|
-
|
381
|
+
< 6
|
383
382
|
� 6
|
384
|
-
|
385
|
-
|
386
|
-
�� 5
|
387
|
-
�̴�. 5
|
388
|
-
�� 5
|
389
|
-
�� 5
|
390
|
-
���� 5
|
383
|
+
�� 6
|
384
|
+
�_ 6
|
391
385
|
־ 5
|
392
|
-
�� 5
|
393
|
-
�� 5
|
394
|
-
|
395
|
-
�� 5
|
386
|
+
��_ 5
|
387
|
+
�� 5
|
388
|
+
��� 5
|
389
|
+
�� 5
|
390
|
+
��ߴ� 5
|
396
391
|
�� 5
|
392
|
+
_�� 5
|
393
|
+
�� 5
|
394
|
+
�� 5
|
395
|
+
��_ 5
|
397
396
|
�� 5
|
398
|
-
|
399
|
-
|
400
|
-
|
397
|
+
��ߴ 5
|
398
|
+
�_ 5
|
399
|
+
�ѱ 5
|
400
|
+
�� 5
|