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
@@ -10,391 +10,391 @@ _t 134
|
|
10
10
|
a 123
|
11
11
|
_n 117
|
12
12
|
u 113
|
13
|
-
_c
|
13
|
+
_c 108
|
14
14
|
nh 105
|
15
|
-
|
16
|
-
|
15
|
+
ng_ 103
|
16
|
+
g_ 103
|
17
17
|
i_ 101
|
18
|
-
n_
|
18
|
+
n_ 100
|
19
19
|
� 92
|
20
20
|
m 74
|
21
21
|
o 70
|
22
22
|
r 65
|
23
|
-
� 64
|
24
23
|
. 64
|
25
|
-
�
|
24
|
+
� 64
|
26
25
|
l 63
|
26
|
+
� 63
|
27
27
|
_� 59
|
28
28
|
th 57
|
29
|
-
c_
|
29
|
+
c_ 56
|
30
|
+
h_ 53
|
30
31
|
_th 53
|
31
|
-
h_ 52
|
32
32
|
s 51
|
33
33
|
_nh 50
|
34
|
-
t_
|
35
|
-
, 47
|
34
|
+
t_ 49
|
36
35
|
y 47
|
36
|
+
, 47
|
37
37
|
_l 46
|
38
38
|
� 45
|
39
39
|
_s 45
|
40
|
-
a_
|
41
|
-
nh_
|
40
|
+
a_ 45
|
41
|
+
nh_ 44
|
42
42
|
ch 42
|
43
|
+
u_ 42
|
43
44
|
,_ 41
|
45
|
+
_h 39
|
44
46
|
k 39
|
45
|
-
_h 38
|
46
47
|
._ 38
|
47
|
-
u_ 37
|
48
|
-
hi 37
|
49
48
|
o_ 37
|
49
|
+
hi 37
|
50
50
|
v 37
|
51
51
|
_k 36
|
52
|
+
�_ 36
|
52
53
|
_v 35
|
53
54
|
T 35
|
54
|
-
�_ 35
|
55
55
|
kh 34
|
56
56
|
_m 34
|
57
57
|
� 34
|
58
|
-
|
58
|
+
__ 33
|
59
59
|
_kh 33
|
60
|
+
� 33
|
60
61
|
p 32
|
61
62
|
� 31
|
62
|
-
b 31
|
63
63
|
_ch 31
|
64
|
-
|
65
|
-
� 30
|
64
|
+
b 31
|
66
65
|
_b 30
|
66
|
+
� 30
|
67
67
|
d 30
|
68
|
+
� 30
|
69
|
+
y_ 29
|
68
70
|
_ng 29
|
69
|
-
__ 29
|
70
|
-
y_ 28
|
71
|
-
N 27
|
72
71
|
tr 27
|
73
|
-
|
74
|
-
l� 26
|
72
|
+
N 27
|
75
73
|
e 26
|
74
|
+
l� 26
|
76
75
|
_d 26
|
77
|
-
|
76
|
+
_T 26
|
78
77
|
_g 25
|
78
|
+
m_ 25
|
79
79
|
� 25
|
80
80
|
� 24
|
81
|
-
_tr 24
|
82
81
|
_l� 24
|
83
82
|
� 24
|
84
83
|
� 24
|
84
|
+
_tr 24
|
85
|
+
� 23
|
85
86
|
� 23
|
86
87
|
an 23
|
87
|
-
�
|
88
|
+
�n 22
|
88
89
|
�_ 22
|
89
90
|
�n 22
|
90
91
|
C 22
|
91
|
-
�n 22
|
92
92
|
ܩ 21
|
93
|
-
� 21
|
94
93
|
ph 21
|
95
|
-
|
96
|
-
|
97
|
-
|
94
|
+
_p 21
|
95
|
+
� 21
|
96
|
+
_ph 21
|
98
97
|
H 20
|
98
|
+
c�a 20
|
99
99
|
h� 20
|
100
|
-
_ph 20
|
101
100
|
� 20
|
101
|
+
�a 20
|
102
|
+
l�_ 20
|
102
103
|
c� 20
|
104
|
+
_c�a 19
|
103
105
|
�i 19
|
104
|
-
|
105
|
-
|
106
|
-
ho 18
|
107
|
-
�c 18
|
108
|
-
� 18
|
109
|
-
c�a_ 18
|
106
|
+
_c� 19
|
107
|
+
_l�_ 18
|
110
108
|
�a_ 18
|
111
|
-
_c� 18
|
112
109
|
ha 18
|
113
|
-
�
|
114
|
-
|
115
|
-
|
110
|
+
�c 18
|
111
|
+
c�a_ 18
|
112
|
+
ho 18
|
113
|
+
� 18
|
114
|
+
_c�a_ 17
|
116
115
|
c� 17
|
117
116
|
gi 17
|
118
|
-
|
117
|
+
�ng 17
|
119
118
|
�n 17
|
119
|
+
_r 17
|
120
|
+
c�_ 17
|
121
|
+
in 16
|
120
122
|
_c� 16
|
123
|
+
� 16
|
124
|
+
� 16
|
121
125
|
� 16
|
122
|
-
|
126
|
+
_C 16
|
123
127
|
�i_ 16
|
124
|
-
|
125
|
-
� 16
|
126
|
-
_c�a_ 16
|
127
|
-
� 16
|
128
|
-
" 15
|
129
|
-
i� 15
|
128
|
+
_c�_ 16
|
130
129
|
i� 15
|
131
|
-
_gi 15
|
132
|
-
nhi 15
|
133
|
-
q 15
|
134
|
-
uy 15
|
135
130
|
h� 15
|
136
131
|
qu 15
|
132
|
+
�ng_ 15
|
133
|
+
� 15
|
134
|
+
q 15
|
135
|
+
nhi 15
|
137
136
|
h� 15
|
137
|
+
_gi 15
|
138
|
+
i� 15
|
138
139
|
g� 15
|
139
|
-
|
140
|
-
�
|
141
|
-
�
|
140
|
+
uy 15
|
141
|
+
�n 14
|
142
|
+
�t 14
|
143
|
+
.. 14
|
144
|
+
�n_ 14
|
145
|
+
h� 14
|
146
|
+
_nhi 14
|
142
147
|
ra 14
|
143
148
|
� 14
|
144
|
-
�n 14
|
145
149
|
� 14
|
146
|
-
|
147
|
-
h� 14
|
148
|
-
.. 14
|
149
|
-
�t 14
|
150
|
+
�i 13
|
150
151
|
gܩi 13
|
152
|
+
ܩi_ 13
|
153
|
+
�u 13
|
151
154
|
�nh 13
|
155
|
+
� 13
|
156
|
+
v� 13
|
152
157
|
ܩi 13
|
153
|
-
�
|
154
|
-
ܩi_ 13
|
158
|
+
�n 13
|
159
|
+
gܩi_ 13
|
155
160
|
_qu 13
|
161
|
+
_H 13
|
162
|
+
gܩ 13
|
156
163
|
�t_ 13
|
164
|
+
_N 13
|
165
|
+
�i_ 13
|
157
166
|
_q 13
|
158
|
-
�n 13
|
159
|
-
gܩ 13
|
160
|
-
� 13
|
161
|
-
v� 13
|
162
|
-
gܩi_ 13
|
163
|
-
�i 13
|
164
167
|
� 13
|
165
|
-
�
|
166
|
-
�
|
167
|
-
_v� 12
|
168
|
+
h�ng 12
|
169
|
+
hi�u 12
|
168
170
|
h�n 12
|
169
|
-
|
171
|
+
�u_ 12
|
170
172
|
� 12
|
171
|
-
|
173
|
+
_v� 12
|
174
|
+
on 12
|
172
175
|
i�u 12
|
173
|
-
hi�u 12
|
174
|
-
�u_ 12
|
175
|
-
hi� 12
|
176
176
|
inh 12
|
177
|
-
|
177
|
+
hi� 12
|
178
|
+
_c� 11
|
178
179
|
x 11
|
179
|
-
|
180
|
-
|
181
|
-
kh� 11
|
182
|
-
kh�n 11
|
183
|
-
nhi�u 11
|
180
|
+
�n_ 11
|
181
|
+
� 11
|
184
182
|
kh�ng 11
|
185
|
-
�n 11
|
186
183
|
c� 11
|
187
|
-
�
|
188
|
-
�t 11
|
189
|
-
ay 11
|
190
|
-
� 11
|
191
|
-
�o 11
|
184
|
+
�c_ 11
|
192
185
|
sa 11
|
193
|
-
�
|
194
|
-
|
186
|
+
hi�u_ 11
|
187
|
+
ܮ 11
|
188
|
+
�o 11
|
189
|
+
� 11
|
195
190
|
m� 11
|
196
|
-
_c� 11
|
197
191
|
_sa 11
|
198
|
-
|
192
|
+
nhi� 11
|
193
|
+
�n 11
|
194
|
+
nhi�u 11
|
195
|
+
kh� 11
|
196
|
+
kh�n 11
|
197
|
+
_m� 11
|
198
|
+
ay 11
|
199
|
+
�t 11
|
199
200
|
i�u_ 11
|
200
|
-
� 11
|
201
|
-
_H 11
|
202
|
-
�c_ 10
|
203
|
-
� 10
|
204
|
-
�nh_ 10
|
205
|
-
�n 10
|
206
|
-
i� 10
|
207
|
-
�o_ 10
|
208
|
-
_kh�n 10
|
209
|
-
_m�t_ 10
|
210
|
-
ng� 10
|
201
|
+
�_ 11
|
211
202
|
�n 10
|
212
203
|
ngܩi 10
|
213
|
-
|
214
|
-
|
215
|
-
�
|
216
|
-
|
204
|
+
ng� 10
|
205
|
+
�t_ 10
|
206
|
+
�nh_ 10
|
207
|
+
_m�t 10
|
208
|
+
_x 10
|
209
|
+
ܮc 10
|
217
210
|
m�t 10
|
218
|
-
ngܩ 10
|
219
211
|
h�ng_ 10
|
212
|
+
�n 10
|
213
|
+
� 10
|
214
|
+
h� 10
|
215
|
+
�c 10
|
216
|
+
inh_ 10
|
217
|
+
m�t_ 10
|
218
|
+
�t 10
|
219
|
+
� 10
|
220
|
+
�n 10
|
221
|
+
_m�t_ 10
|
222
|
+
_ng� 10
|
220
223
|
�� 10
|
224
|
+
i� 10
|
225
|
+
_nhi� 10
|
221
226
|
�ng 10
|
222
|
-
|
223
|
-
|
224
|
-
m�t_ 10
|
225
|
-
� 10
|
227
|
+
V 10
|
228
|
+
�o_ 10
|
226
229
|
�ܮc 10
|
227
|
-
_nhi� 10
|
228
|
-
ܮc 10
|
229
|
-
�n 10
|
230
|
-
_m�t 10
|
231
230
|
_kh� 10
|
232
|
-
|
233
|
-
|
234
|
-
|
235
|
-
|
236
|
-
|
231
|
+
ngܩ 10
|
232
|
+
�ܮ 10
|
233
|
+
_kh�n 10
|
234
|
+
_ngܩ 10
|
235
|
+
_�� 9
|
236
|
+
�ng_ 9
|
237
|
+
th� 9
|
237
238
|
nh� 9
|
239
|
+
n� 9
|
240
|
+
�_ 9
|
238
241
|
�_ 9
|
239
|
-
|
242
|
+
�ܮc_ 9
|
243
|
+
L 9
|
244
|
+
_V 9
|
240
245
|
ti 9
|
246
|
+
�c_ 9
|
241
247
|
_�ܮc 9
|
242
|
-
|
243
|
-
�_ 9
|
244
|
-
inh_ 9
|
248
|
+
�n 9
|
245
249
|
ch_ 9
|
250
|
+
ܮc_ 9
|
251
|
+
_c�c 9
|
252
|
+
S 9
|
253
|
+
�t_ 9
|
254
|
+
ho_ 9
|
255
|
+
A 9
|
256
|
+
_th� 9
|
257
|
+
h�n 9
|
246
258
|
_�ܮ 9
|
247
|
-
�ng_ 9
|
248
|
-
�n 9
|
249
|
-
L 9
|
250
|
-
f 9
|
251
|
-
ra_ 9
|
252
|
-
n� 9
|
253
|
-
_V 9
|
254
259
|
an_ 9
|
255
|
-
� 9
|
256
|
-
_�� 9
|
257
|
-
th� 9
|
258
|
-
ܮc_ 9
|
259
260
|
� 9
|
260
|
-
|
261
|
-
_n� 9
|
262
|
-
h�n 9
|
263
|
-
�c_ 9
|
264
|
-
ay_ 9
|
265
|
-
A 9
|
261
|
+
ra_ 9
|
266
262
|
c�c 9
|
267
|
-
|
263
|
+
_n� 9
|
268
264
|
_nh� 9
|
269
|
-
|
270
|
-
|
271
|
-
|
272
|
-
|
273
|
-
�c 8
|
274
|
-
_s� 8
|
275
|
-
ong_ 8
|
276
|
-
_th�_ 8
|
277
|
-
ro 8
|
278
|
-
ron 8
|
279
|
-
h� 8
|
280
|
-
h�_ 8
|
281
|
-
rong 8
|
282
|
-
p_ 8
|
283
|
-
�� 8
|
284
|
-
�ng_ 8
|
265
|
+
ay_ 9
|
266
|
+
f 9
|
267
|
+
� 9
|
268
|
+
� 9
|
285
269
|
ܧ 8
|
286
|
-
|
270
|
+
�y 8
|
271
|
+
��_ 8
|
287
272
|
au 8
|
288
|
-
|
289
|
-
�
|
290
|
-
ܩn 8
|
273
|
+
h�_ 8
|
274
|
+
�c 8
|
291
275
|
�u 8
|
276
|
+
ro 8
|
277
|
+
�n_ 8
|
278
|
+
cho 8
|
292
279
|
h� 8
|
293
|
-
|
294
|
-
|
280
|
+
M 8
|
281
|
+
�� 8
|
282
|
+
ong_ 8
|
283
|
+
h�_ 8
|
284
|
+
�ng_ 8
|
285
|
+
�_ 8
|
286
|
+
_s� 8
|
287
|
+
�nh 8
|
288
|
+
�n 8
|
295
289
|
G 8
|
290
|
+
�_ 8
|
291
|
+
ܩng 8
|
292
|
+
h� 8
|
296
293
|
ܩng_ 8
|
297
|
-
�
|
294
|
+
�_ 8
|
295
|
+
s� 8
|
298
296
|
�c_ 8
|
299
|
-
|
297
|
+
ܩn 8
|
298
|
+
_th�_ 8
|
299
|
+
p_ 8
|
300
|
+
Th 8
|
301
|
+
ong 8
|
302
|
+
rong_ 8
|
303
|
+
ron 8
|
304
|
+
hu 8
|
305
|
+
un 8
|
300
306
|
_ti 8
|
307
|
+
_cho 8
|
308
|
+
rong 8
|
301
309
|
ta 8
|
302
|
-
ܩng 8
|
303
|
-
hu 8
|
304
|
-
�nh 8
|
305
|
-
M 8
|
306
|
-
�y 8
|
307
|
-
Th 8
|
308
|
-
h�_ 8
|
309
|
-
�_ 8
|
310
|
-
cho 8
|
311
|
-
�n_ 8
|
312
310
|
�ng 8
|
313
|
-
|
314
|
-
� 7
|
315
|
-
� 7
|
316
|
-
�n_ 7
|
317
|
-
ao_ 7
|
318
|
-
�ch 7
|
319
|
-
� 7
|
320
|
-
�nh_ 7
|
321
|
-
ar 7
|
311
|
+
th�_ 8
|
312
|
+
nh�_ 7
|
313
|
+
�n 7
|
322
314
|
� 7
|
315
|
+
�n 7
|
316
|
+
� 7
|
323
317
|
i� 7
|
324
|
-
hay 7
|
325
|
-
ao 7
|
326
|
-
�t_ 7
|
327
318
|
�ch_ 7
|
328
|
-
|
329
|
-
|
330
|
-
_nh�_ 7
|
331
|
-
_Th 7
|
332
|
-
nh�_ 7
|
333
|
-
kh� 7
|
319
|
+
re 7
|
320
|
+
� 7
|
334
321
|
_�� 7
|
335
|
-
|
322
|
+
_nh�_ 7
|
336
323
|
vi 7
|
337
|
-
|
324
|
+
anh 7
|
325
|
+
� 7
|
326
|
+
�n_ 7
|
327
|
+
kh� 7
|
328
|
+
ao_ 7
|
329
|
+
_vi 7
|
338
330
|
�n 7
|
339
|
-
� 7
|
331
|
+
�u_ 7
|
332
|
+
_cho_ 7
|
333
|
+
hay 7
|
334
|
+
� 7
|
340
335
|
ai_ 7
|
341
|
-
|
342
|
-
|
336
|
+
... 7
|
337
|
+
�i 7
|
343
338
|
Ng 7
|
344
|
-
|
345
|
-
|
339
|
+
_��_ 7
|
340
|
+
� 7
|
341
|
+
� 7
|
346
342
|
_kh� 7
|
347
|
-
|
348
|
-
|
349
|
-
_cho_ 7
|
350
|
-
� 7
|
351
|
-
�i 7
|
352
|
-
... 7
|
353
|
-
_vi 7
|
343
|
+
ao 7
|
344
|
+
_Th 7
|
354
345
|
ai 7
|
355
|
-
|
356
|
-
|
346
|
+
_L 7
|
347
|
+
ua 7
|
348
|
+
�ch 7
|
349
|
+
cho_ 7
|
350
|
+
ar 7
|
351
|
+
�nh_ 7
|
352
|
+
_Ng 7
|
353
|
+
�y_ 7
|
354
|
+
l� 7
|
357
355
|
l�i 6
|
358
|
-
|
359
|
-
|
360
|
-
|
361
|
-
|
362
|
-
_
|
363
|
-
|
364
|
-
_th� 6
|
356
|
+
�i 6
|
357
|
+
�� 6
|
358
|
+
_M 6
|
359
|
+
_ljn 6
|
360
|
+
�_ 6
|
361
|
+
hay_ 6
|
365
362
|
��ng 6
|
366
|
-
_ra 6
|
367
|
-
Nj_ 6
|
368
|
-
trong 6
|
369
|
-
ngu 6
|
370
|
-
h� 6
|
371
|
-
_Nj 6
|
372
|
-
�u_ 6
|
373
|
-
Tr 6
|
374
363
|
_ljn_ 6
|
375
|
-
|
376
|
-
|
377
|
-
�
|
378
|
-
d� 6
|
379
|
-
r�t 6
|
364
|
+
v�_ 6
|
365
|
+
_th� 6
|
366
|
+
r� 6
|
380
367
|
� 6
|
381
|
-
|
382
|
-
Nj 6
|
368
|
+
s� 6
|
383
369
|
lj 6
|
384
|
-
|
385
|
-
|
386
|
-
h�
|
387
|
-
|
388
|
-
�i_ 6
|
389
|
-
� 6
|
390
|
-
_Nj_ 6
|
370
|
+
_r� 6
|
371
|
+
hi� 6
|
372
|
+
h� 6
|
373
|
+
_r�t_ 6
|
391
374
|
_s� 6
|
392
|
-
|
393
|
-
|
375
|
+
� 6
|
376
|
+
� 6
|
377
|
+
_� 6
|
378
|
+
h� 6
|
379
|
+
r�t_ 6
|
380
|
+
�ng 6
|
381
|
+
d� 6
|
394
382
|
_r�t 6
|
395
|
-
|
396
|
-
|
397
|
-
|
383
|
+
�i_ 6
|
384
|
+
i�t 6
|
385
|
+
_S 6
|
386
|
+
i�n 6
|
387
|
+
�n 6
|
388
|
+
Tr 6
|
389
|
+
_l� 6
|
390
|
+
ung 6
|
391
|
+
l�i_ 6
|
392
|
+
tron 6
|
393
|
+
�_ 6
|
394
|
+
th� 6
|
395
|
+
tro 6
|
398
396
|
gu 6
|
399
|
-
ljn 6
|
400
397
|
ia 6
|
398
|
+
_Nj_ 6
|
399
|
+
Nj_ 6
|
400
|
+
r�t 6
|