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
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 2068
|
2
2
|
n 418
|
3
3
|
h 330
|
4
4
|
i 203
|
@@ -6,395 +6,395 @@ t 202
|
|
6
6
|
c 191
|
7
7
|
g 183
|
8
8
|
ng 147
|
9
|
-
_t
|
9
|
+
_t 141
|
10
10
|
a 123
|
11
|
-
_n
|
11
|
+
_n 120
|
12
|
+
_c 114
|
12
13
|
u 113
|
13
|
-
|
14
|
+
g_ 109
|
15
|
+
ng_ 109
|
16
|
+
n_ 107
|
14
17
|
nh 105
|
15
|
-
|
16
|
-
g_ 103
|
17
|
-
i_ 101
|
18
|
-
n_ 100
|
18
|
+
i_ 103
|
19
19
|
� 92
|
20
20
|
m 74
|
21
21
|
o 70
|
22
22
|
r 65
|
23
|
-
. 64
|
24
23
|
� 64
|
24
|
+
. 64
|
25
|
+
_� 63
|
25
26
|
l 63
|
26
27
|
� 63
|
27
|
-
|
28
|
+
c_ 59
|
28
29
|
th 57
|
29
|
-
|
30
|
-
h_
|
31
|
-
|
30
|
+
_th 57
|
31
|
+
h_ 55
|
32
|
+
t_ 52
|
33
|
+
_nh 51
|
32
34
|
s 51
|
33
|
-
|
34
|
-
|
35
|
-
y 47
|
35
|
+
_l 50
|
36
|
+
._ 49
|
36
37
|
, 47
|
37
|
-
|
38
|
+
_s 47
|
39
|
+
y 47
|
40
|
+
,_ 47
|
41
|
+
a_ 47
|
42
|
+
nh_ 46
|
38
43
|
� 45
|
39
|
-
|
40
|
-
|
41
|
-
nh_ 44
|
44
|
+
u_ 45
|
45
|
+
_h 42
|
42
46
|
ch 42
|
43
|
-
|
44
|
-
,_ 41
|
45
|
-
_h 39
|
47
|
+
o_ 39
|
46
48
|
k 39
|
47
|
-
|
48
|
-
|
49
|
-
|
49
|
+
_m 39
|
50
|
+
�_ 38
|
51
|
+
_v 37
|
50
52
|
v 37
|
51
|
-
|
52
|
-
|
53
|
-
_v 35
|
53
|
+
hi 37
|
54
|
+
_k 37
|
54
55
|
T 35
|
55
|
-
|
56
|
-
_m 34
|
56
|
+
_kh 34
|
57
57
|
� 34
|
58
|
-
|
59
|
-
|
58
|
+
kh 34
|
59
|
+
_ch 33
|
60
60
|
� 33
|
61
|
+
_T 33
|
61
62
|
p 32
|
62
63
|
� 31
|
63
|
-
_ch 31
|
64
64
|
b 31
|
65
|
-
_b
|
66
|
-
� 30
|
67
|
-
d 30
|
65
|
+
_b 31
|
68
66
|
� 30
|
69
|
-
|
67
|
+
d 30
|
68
|
+
y_ 30
|
69
|
+
� 30
|
70
70
|
_ng 29
|
71
|
-
|
71
|
+
_g 29
|
72
|
+
m_ 28
|
73
|
+
_d 28
|
72
74
|
N 27
|
75
|
+
tr 27
|
73
76
|
e 26
|
74
77
|
l� 26
|
75
|
-
|
76
|
-
_T 26
|
77
|
-
_g 25
|
78
|
-
m_ 25
|
78
|
+
_l� 26
|
79
79
|
� 25
|
80
|
-
|
81
|
-
_l� 24
|
80
|
+
_tr 25
|
82
81
|
� 24
|
83
82
|
� 24
|
84
|
-
|
83
|
+
� 24
|
84
|
+
an 23
|
85
85
|
� 23
|
86
86
|
� 23
|
87
|
-
|
88
|
-
�n 22
|
87
|
+
C 22
|
89
88
|
�_ 22
|
90
89
|
�n 22
|
91
|
-
|
90
|
+
�n 22
|
91
|
+
� 21
|
92
92
|
ܩ 21
|
93
|
-
ph 21
|
94
93
|
_p 21
|
95
|
-
|
94
|
+
ph 21
|
96
95
|
_ph 21
|
97
|
-
|
98
|
-
c�a 20
|
96
|
+
_C 20
|
99
97
|
h� 20
|
98
|
+
_l�_ 20
|
99
|
+
H 20
|
100
|
+
_c�a 20
|
100
101
|
� 20
|
101
102
|
�a 20
|
102
103
|
l�_ 20
|
103
104
|
c� 20
|
104
|
-
_c�
|
105
|
+
_c� 20
|
106
|
+
c�a 20
|
105
107
|
�i 19
|
106
|
-
|
107
|
-
|
108
|
-
�a_
|
109
|
-
ha 18
|
110
|
-
�c 18
|
111
|
-
c�a_ 18
|
108
|
+
�a_ 19
|
109
|
+
c�a_ 19
|
110
|
+
_c�a_ 19
|
112
111
|
ho 18
|
113
112
|
� 18
|
114
|
-
|
113
|
+
_r 18
|
114
|
+
�c 18
|
115
|
+
ha 18
|
116
|
+
�n 17
|
117
|
+
_gi 17
|
118
|
+
_c�_ 17
|
115
119
|
c� 17
|
116
120
|
gi 17
|
117
|
-
�
|
118
|
-
�
|
119
|
-
_r 17
|
121
|
+
�ng_ 17
|
122
|
+
_c� 17
|
120
123
|
c�_ 17
|
121
|
-
|
122
|
-
|
124
|
+
�i_ 17
|
125
|
+
�ng 17
|
123
126
|
� 16
|
127
|
+
_N 16
|
128
|
+
in 16
|
124
129
|
� 16
|
125
130
|
� 16
|
126
|
-
|
127
|
-
�i_ 16
|
128
|
-
_c�_ 16
|
131
|
+
� 15
|
129
132
|
i� 15
|
130
|
-
h� 15
|
131
133
|
qu 15
|
132
|
-
|
133
|
-
� 15
|
134
|
-
q 15
|
135
|
-
nhi 15
|
136
|
-
h� 15
|
137
|
-
_gi 15
|
134
|
+
uy 15
|
138
135
|
i� 15
|
136
|
+
nhi 15
|
137
|
+
h� 15
|
138
|
+
q 15
|
139
|
+
�n_ 15
|
139
140
|
g� 15
|
140
|
-
|
141
|
-
|
142
|
-
�
|
141
|
+
_q 15
|
142
|
+
_qu 15
|
143
|
+
h� 15
|
144
|
+
_nhi 15
|
145
|
+
ra 14
|
143
146
|
.. 14
|
144
|
-
�
|
147
|
+
�n 14
|
145
148
|
h� 14
|
146
|
-
_nhi 14
|
147
|
-
ra 14
|
148
|
-
� 14
|
149
149
|
� 14
|
150
|
-
�
|
151
|
-
|
152
|
-
|
150
|
+
�t 14
|
151
|
+
� 14
|
152
|
+
� 13
|
153
153
|
�u 13
|
154
|
-
�nh 13
|
155
154
|
� 13
|
156
|
-
|
157
|
-
|
158
|
-
�n 13
|
159
|
-
gܩi_ 13
|
160
|
-
_qu 13
|
161
|
-
_H 13
|
155
|
+
�i 13
|
156
|
+
�nh 13
|
162
157
|
gܩ 13
|
158
|
+
�u_ 13
|
159
|
+
gܩi 13
|
160
|
+
v� 13
|
163
161
|
�t_ 13
|
164
|
-
|
162
|
+
gܩi_ 13
|
163
|
+
�n 13
|
164
|
+
ܩi_ 13
|
165
|
+
_v� 13
|
165
166
|
�i_ 13
|
166
|
-
|
167
|
-
|
168
|
-
|
167
|
+
ܩi 13
|
168
|
+
_H 13
|
169
|
+
�n_ 13
|
170
|
+
hi� 12
|
171
|
+
inh 12
|
172
|
+
hi�u_ 12
|
173
|
+
on 12
|
174
|
+
�_ 12
|
175
|
+
i�u_ 12
|
169
176
|
hi�u 12
|
170
|
-
h�n 12
|
171
|
-
�u_ 12
|
172
177
|
� 12
|
173
|
-
|
174
|
-
|
178
|
+
h�ng 12
|
179
|
+
h�ng_ 12
|
175
180
|
i�u 12
|
176
|
-
|
177
|
-
|
178
|
-
|
179
|
-
x 11
|
180
|
-
�n_ 11
|
181
|
-
� 11
|
182
|
-
kh�ng 11
|
183
|
-
c� 11
|
184
|
-
�c_ 11
|
181
|
+
h�n 12
|
182
|
+
�_ 12
|
183
|
+
� 11
|
185
184
|
sa 11
|
186
|
-
|
185
|
+
kh� 11
|
186
|
+
kh�ng 11
|
187
187
|
ܮ 11
|
188
|
-
�
|
189
|
-
� 11
|
190
|
-
m� 11
|
191
|
-
_sa 11
|
188
|
+
_m� 11
|
189
|
+
_nhi� 11
|
192
190
|
nhi� 11
|
193
191
|
�n 11
|
194
|
-
|
195
|
-
kh� 11
|
192
|
+
�t_ 11
|
196
193
|
kh�n 11
|
197
|
-
_m� 11
|
198
|
-
ay 11
|
199
194
|
�t 11
|
200
|
-
|
201
|
-
�
|
202
|
-
�
|
203
|
-
|
204
|
-
|
195
|
+
c� 11
|
196
|
+
nhi�u 11
|
197
|
+
_c� 11
|
198
|
+
�o 11
|
199
|
+
x 11
|
200
|
+
inh_ 11
|
201
|
+
�c_ 11
|
202
|
+
_sa 11
|
203
|
+
_kh� 11
|
204
|
+
m� 11
|
205
|
+
_kh�n 11
|
206
|
+
� 11
|
207
|
+
ay 11
|
208
|
+
_m�t_ 10
|
209
|
+
�n 10
|
210
|
+
�c 10
|
211
|
+
_ng� 10
|
212
|
+
ho_ 10
|
213
|
+
h� 10
|
214
|
+
_m�t 10
|
215
|
+
�ng 10
|
205
216
|
�t_ 10
|
217
|
+
�t 10
|
218
|
+
ngܩi 10
|
206
219
|
�nh_ 10
|
207
|
-
_m�t 10
|
208
|
-
_x 10
|
209
|
-
ܮc 10
|
210
|
-
m�t 10
|
211
|
-
h�ng_ 10
|
212
|
-
�n 10
|
213
220
|
� 10
|
214
|
-
|
215
|
-
|
216
|
-
inh_ 10
|
217
|
-
m�t_ 10
|
218
|
-
�t 10
|
219
|
-
� 10
|
220
|
-
�n 10
|
221
|
-
_m�t_ 10
|
222
|
-
_ng� 10
|
221
|
+
_V 10
|
222
|
+
_�� 10
|
223
223
|
�� 10
|
224
224
|
i� 10
|
225
|
-
|
226
|
-
�ng 10
|
225
|
+
�n 10
|
227
226
|
V 10
|
227
|
+
_x 10
|
228
228
|
�o_ 10
|
229
|
-
�ܮc 10
|
230
|
-
|
229
|
+
_�ܮc 10
|
230
|
+
ay_ 10
|
231
|
+
�n 10
|
232
|
+
m�t 10
|
233
|
+
ng� 10
|
234
|
+
_�ܮ 10
|
235
|
+
� 10
|
236
|
+
m�t_ 10
|
231
237
|
ngܩ 10
|
238
|
+
�ܮc 10
|
239
|
+
ܮc 10
|
232
240
|
�ܮ 10
|
233
|
-
_kh�n 10
|
234
241
|
_ngܩ 10
|
235
|
-
_�� 9
|
236
|
-
�ng_ 9
|
237
|
-
th� 9
|
238
|
-
nh� 9
|
239
|
-
n� 9
|
240
|
-
�_ 9
|
241
|
-
�_ 9
|
242
|
-
�ܮc_ 9
|
243
|
-
L 9
|
244
|
-
_V 9
|
245
|
-
ti 9
|
246
|
-
�c_ 9
|
247
|
-
_�ܮc 9
|
248
|
-
�n 9
|
249
|
-
ch_ 9
|
250
|
-
ܮc_ 9
|
251
242
|
_c�c 9
|
243
|
+
ch_ 9
|
244
|
+
ti 9
|
245
|
+
_n� 9
|
246
|
+
f 9
|
252
247
|
S 9
|
253
|
-
�
|
254
|
-
|
255
|
-
|
256
|
-
|
248
|
+
� 9
|
249
|
+
�ܮc_ 9
|
250
|
+
p_ 9
|
251
|
+
ܮc_ 9
|
257
252
|
h�n 9
|
258
|
-
_
|
253
|
+
th�_ 9
|
254
|
+
_th� 9
|
255
|
+
_th�_ 9
|
256
|
+
A 9
|
257
|
+
�n 9
|
259
258
|
an_ 9
|
260
|
-
� 9
|
261
|
-
|
259
|
+
h�_ 9
|
260
|
+
�c_ 9
|
262
261
|
c�c 9
|
263
|
-
_n� 9
|
264
|
-
_nh� 9
|
265
|
-
ay_ 9
|
266
|
-
f 9
|
267
|
-
� 9
|
268
262
|
� 9
|
269
|
-
|
270
|
-
|
271
|
-
|
272
|
-
|
273
|
-
|
274
|
-
�
|
263
|
+
nh� 9
|
264
|
+
ra_ 9
|
265
|
+
n� 9
|
266
|
+
�ng_ 9
|
267
|
+
�_ 9
|
268
|
+
_nh� 9
|
269
|
+
� 9
|
270
|
+
L 9
|
271
|
+
th� 9
|
272
|
+
�ng 8
|
275
273
|
�u 8
|
276
|
-
|
277
|
-
�n_ 8
|
278
|
-
cho 8
|
279
|
-
h� 8
|
274
|
+
ܩng 8
|
280
275
|
M 8
|
281
|
-
�� 8
|
282
|
-
ong_ 8
|
283
|
-
h�_ 8
|
284
276
|
�ng_ 8
|
285
|
-
�_ 8
|
286
|
-
_s� 8
|
287
|
-
�nh 8
|
288
|
-
�n 8
|
289
277
|
G 8
|
278
|
+
_L 8
|
279
|
+
ܩng_ 8
|
280
|
+
hu 8
|
281
|
+
ong_ 8
|
282
|
+
�nh 8
|
283
|
+
_S 8
|
284
|
+
_��_ 8
|
290
285
|
�_ 8
|
291
|
-
|
286
|
+
cho 8
|
287
|
+
ta 8
|
288
|
+
ro 8
|
289
|
+
_s� 8
|
290
|
+
ron 8
|
291
|
+
cho_ 8
|
292
|
+
au 8
|
293
|
+
_cho_ 8
|
294
|
+
�c 8
|
292
295
|
h� 8
|
293
|
-
|
294
|
-
|
296
|
+
�y 8
|
297
|
+
Th 8
|
298
|
+
_cho 8
|
299
|
+
_�� 8
|
295
300
|
s� 8
|
301
|
+
��_ 8
|
302
|
+
_ti 8
|
303
|
+
rong 8
|
304
|
+
�� 8
|
305
|
+
�n_ 8
|
306
|
+
ong 8
|
307
|
+
ܧ 8
|
308
|
+
un 8
|
296
309
|
�c_ 8
|
310
|
+
h�_ 8
|
311
|
+
h� 8
|
297
312
|
ܩn 8
|
298
|
-
|
299
|
-
p_ 8
|
300
|
-
Th 8
|
301
|
-
ong 8
|
313
|
+
�_ 8
|
302
314
|
rong_ 8
|
303
|
-
|
304
|
-
|
305
|
-
|
306
|
-
|
307
|
-
|
308
|
-
|
309
|
-
|
310
|
-
|
311
|
-
|
315
|
+
�n 8
|
316
|
+
�_ 8
|
317
|
+
_Th 8
|
318
|
+
kh� 7
|
319
|
+
�i 7
|
320
|
+
_v�_ 7
|
321
|
+
vi 7
|
322
|
+
_ra 7
|
323
|
+
�u_ 7
|
324
|
+
_kh� 7
|
325
|
+
_� 7
|
312
326
|
nh�_ 7
|
313
|
-
|
314
|
-
� 7
|
327
|
+
.._ 7
|
315
328
|
�n 7
|
316
|
-
� 7
|
317
|
-
i� 7
|
318
|
-
�ch_ 7
|
319
|
-
re 7
|
320
|
-
� 7
|
321
|
-
_�� 7
|
329
|
+
l� 7
|
322
330
|
_nh�_ 7
|
323
|
-
|
331
|
+
� 7
|
332
|
+
_Ng 7
|
333
|
+
i� 7
|
334
|
+
� 7
|
324
335
|
anh 7
|
325
|
-
� 7
|
326
|
-
�n_ 7
|
327
|
-
kh� 7
|
328
|
-
ao_ 7
|
329
|
-
_vi 7
|
330
|
-
�n 7
|
331
|
-
�u_ 7
|
332
|
-
_cho_ 7
|
333
|
-
hay 7
|
334
|
-
� 7
|
335
|
-
ai_ 7
|
336
|
-
... 7
|
337
|
-
�i 7
|
338
|
-
Ng 7
|
339
|
-
_��_ 7
|
336
|
+
_l� 7
|
340
337
|
� 7
|
338
|
+
... 7
|
341
339
|
� 7
|
342
|
-
|
340
|
+
ai_ 7
|
341
|
+
v�_ 7
|
343
342
|
ao 7
|
344
|
-
|
345
|
-
ai 7
|
346
|
-
_L 7
|
343
|
+
�y_ 7
|
347
344
|
ua 7
|
345
|
+
_vi 7
|
346
|
+
� 7
|
347
|
+
hay_ 7
|
348
|
+
ai 7
|
348
349
|
�ch 7
|
349
|
-
|
350
|
-
|
350
|
+
�n 7
|
351
|
+
�n 7
|
351
352
|
�nh_ 7
|
352
|
-
|
353
|
-
�
|
354
|
-
|
355
|
-
|
356
|
-
�
|
357
|
-
|
353
|
+
..._ 7
|
354
|
+
� 7
|
355
|
+
re 7
|
356
|
+
hay 7
|
357
|
+
�n_ 7
|
358
|
+
Ng 7
|
359
|
+
� 7
|
360
|
+
�ch_ 7
|
361
|
+
ao_ 7
|
362
|
+
ar 7
|
363
|
+
_ra_ 7
|
364
|
+
�n_ 6
|
365
|
+
l�i_ 6
|
366
|
+
s�_ 6
|
367
|
+
d�n 6
|
368
|
+
tron 6
|
369
|
+
h�nh 6
|
370
|
+
r�t 6
|
371
|
+
s�_ 6
|
372
|
+
_l�i 6
|
358
373
|
_M 6
|
374
|
+
i�n 6
|
359
375
|
_ljn 6
|
360
|
-
�
|
361
|
-
|
362
|
-
��ng 6
|
363
|
-
_ljn_ 6
|
364
|
-
v�_ 6
|
365
|
-
_th� 6
|
366
|
-
r� 6
|
367
|
-
� 6
|
368
|
-
s� 6
|
369
|
-
lj 6
|
370
|
-
_r� 6
|
376
|
+
�i_ 6
|
377
|
+
�i 6
|
371
378
|
hi� 6
|
372
|
-
|
379
|
+
Nj_ 6
|
380
|
+
trong 6
|
373
381
|
_r�t_ 6
|
382
|
+
al 6
|
383
|
+
_ta 6
|
384
|
+
� 6
|
385
|
+
ung 6
|
386
|
+
h� 6
|
387
|
+
_s�_ 6
|
388
|
+
_lj 6
|
389
|
+
_Nj 6
|
374
390
|
_s� 6
|
375
|
-
|
376
|
-
|
377
|
-
|
378
|
-
h� 6
|
379
|
-
|
380
|
-
�ng 6
|
381
|
-
d� 6
|
391
|
+
_ljn_ 6
|
392
|
+
��n 6
|
393
|
+
ljn 6
|
394
|
+
h� 6
|
395
|
+
tro 6
|
382
396
|
_r�t 6
|
383
|
-
|
384
|
-
|
385
|
-
_S 6
|
386
|
-
i�n 6
|
387
|
-
�n 6
|
397
|
+
_Tr 6
|
398
|
+
_tron 6
|
388
399
|
Tr 6
|
389
|
-
|
390
|
-
ung 6
|
391
|
-
l�i_ 6
|
392
|
-
tron 6
|
393
|
-
�_ 6
|
394
|
-
th� 6
|
395
|
-
tro 6
|
396
|
-
gu 6
|
397
|
-
ia 6
|
398
|
-
_Nj_ 6
|
399
|
-
Nj_ 6
|
400
|
-
r�t 6
|
400
|
+
h�nh_ 6
|