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
data/lib/scylla/lms/danish.lm
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 14426
|
2
2
|
e 5759
|
3
3
|
r 3334
|
4
4
|
n 3061
|
@@ -13,48 +13,47 @@ g 1617
|
|
13
13
|
k 1278
|
14
14
|
m 1273
|
15
15
|
er 1209
|
16
|
-
e_
|
17
|
-
__ 1139
|
16
|
+
e_ 1202
|
18
17
|
de 1045
|
19
18
|
en 993
|
20
19
|
� 940
|
21
20
|
f 939
|
22
|
-
r_
|
21
|
+
r_ 854
|
23
22
|
v 770
|
24
|
-
t_
|
23
|
+
t_ 738
|
24
|
+
n_ 725
|
25
25
|
an 724
|
26
|
-
n_ 715
|
27
26
|
u 605
|
28
27
|
nd 598
|
29
28
|
b 585
|
30
29
|
et 574
|
31
|
-
_s
|
30
|
+
_s 562
|
32
31
|
. 546
|
32
|
+
er_ 545
|
33
33
|
re 543
|
34
|
-
er_ 541
|
35
34
|
te 540
|
35
|
+
en_ 536
|
36
36
|
st 530
|
37
|
-
|
38
|
-
|
37
|
+
g_ 523
|
38
|
+
._ 513
|
39
39
|
_o 503
|
40
|
-
_d
|
40
|
+
_d 488
|
41
41
|
, 480
|
42
|
-
,_
|
43
|
-
h 474
|
42
|
+
,_ 479
|
44
43
|
ge 474
|
44
|
+
h 474
|
45
45
|
_a 463
|
46
46
|
in 440
|
47
47
|
p 436
|
48
|
-
_f
|
48
|
+
_f 432
|
49
49
|
ar 430
|
50
50
|
og 415
|
51
51
|
or 411
|
52
52
|
ti 406
|
53
|
-
|
54
|
-
|
55
|
-
|
53
|
+
_e 406
|
54
|
+
et_ 401
|
55
|
+
_m 384
|
56
56
|
ed 381
|
57
|
-
_m 381
|
58
57
|
_i 381
|
59
58
|
sk 365
|
60
59
|
ne 365
|
@@ -62,339 +61,340 @@ le 353
|
|
62
61
|
_og 346
|
63
62
|
ke 343
|
64
63
|
el 342
|
64
|
+
d_ 338
|
65
65
|
og_ 338
|
66
66
|
� 332
|
67
67
|
ø 332
|
68
|
-
d_ 329
|
69
68
|
me 324
|
70
69
|
ng 317
|
71
|
-
_og_ 315
|
72
70
|
_de 315
|
73
|
-
|
71
|
+
_og_ 315
|
74
72
|
ig 293
|
73
|
+
å 293
|
75
74
|
� 293
|
76
75
|
_b 290
|
76
|
+
i_ 287
|
77
77
|
æ 286
|
78
78
|
� 286
|
79
|
-
|
80
|
-
de_
|
79
|
+
s_ 278
|
80
|
+
de_ 276
|
81
81
|
_h 274
|
82
|
-
s_ 273
|
83
82
|
ri 273
|
84
83
|
D 268
|
84
|
+
_D 267
|
85
85
|
nde 263
|
86
|
-
li 262
|
87
86
|
om 262
|
87
|
+
li 262
|
88
88
|
ma 259
|
89
|
+
_t 259
|
89
90
|
ve 257
|
90
91
|
y 256
|
91
92
|
_i_ 254
|
92
93
|
af 254
|
93
|
-
_t 249
|
94
94
|
at 245
|
95
95
|
il 244
|
96
|
-
es 241
|
97
96
|
and 241
|
98
|
-
|
97
|
+
es 240
|
99
98
|
al 234
|
99
|
+
be 234
|
100
100
|
is 233
|
101
|
-
fo 232
|
102
101
|
se 232
|
102
|
+
fo 232
|
103
103
|
ns 229
|
104
|
-
_D 226
|
105
104
|
la 224
|
106
105
|
on 221
|
107
106
|
rk 219
|
108
107
|
_af 217
|
109
108
|
den 216
|
110
109
|
der 214
|
111
|
-
_k
|
112
|
-
|
113
|
-
|
110
|
+
_k 213
|
111
|
+
k_ 212
|
112
|
+
_me 212
|
113
|
+
m_ 210
|
114
114
|
ing 207
|
115
115
|
_v 203
|
116
|
-
k_ 201
|
117
116
|
ra 191
|
118
117
|
f_ 188
|
119
118
|
af_ 186
|
120
|
-
|
119
|
+
l_ 186
|
120
|
+
_p 186
|
121
121
|
for 184
|
122
122
|
_af_ 180
|
123
|
-
l_ 179
|
124
123
|
ol 174
|
125
|
-
ark 172
|
126
124
|
_fo 172
|
125
|
+
ark 172
|
127
126
|
ere 172
|
128
|
-
ste 169
|
129
127
|
lan 169
|
128
|
+
ste 169
|
130
129
|
te_ 168
|
131
|
-
_l
|
130
|
+
_l 168
|
132
131
|
mar 165
|
133
132
|
ll 162
|
134
133
|
ter 161
|
135
|
-
j 159
|
136
134
|
ske 159
|
135
|
+
j 159
|
136
|
+
ke_ 157
|
137
137
|
om_ 155
|
138
|
-
ke_ 154
|
139
|
-
den_ 153
|
140
138
|
land 153
|
141
|
-
|
142
|
-
mark 153
|
139
|
+
ed_ 153
|
143
140
|
Da 153
|
144
|
-
|
141
|
+
_Da 153
|
142
|
+
mark 153
|
143
|
+
ha 153
|
144
|
+
den_ 153
|
145
|
+
_st 153
|
145
146
|
ni 151
|
146
|
-
_st 151
|
147
147
|
so 149
|
148
148
|
_for 149
|
149
149
|
Dan 148
|
150
|
+
_Dan 148
|
150
151
|
ta 148
|
151
152
|
ger 147
|
152
|
-
_er
|
153
|
+
_er 146
|
154
|
+
re_ 144
|
153
155
|
nge 144
|
154
156
|
det 143
|
155
|
-
re_ 141
|
156
157
|
ede 139
|
158
|
+
nm 138
|
157
159
|
nma 138
|
158
160
|
vi 138
|
159
|
-
|
161
|
+
nmar 137
|
160
162
|
_en 137
|
161
163
|
nmark 137
|
162
|
-
nmar 137
|
163
164
|
anma 136
|
164
|
-
_Da 136
|
165
|
-
anmar 136
|
166
165
|
anm 136
|
166
|
+
anmar 136
|
167
167
|
ev 135
|
168
168
|
rs 135
|
169
169
|
der_ 134
|
170
|
+
S 133
|
170
171
|
un 133
|
171
|
-
Danm 133
|
172
172
|
Danma 133
|
173
|
-
|
173
|
+
Danm 133
|
174
|
+
_Danm 133
|
174
175
|
ans 132
|
175
|
-
_Dan 132
|
176
176
|
da 130
|
177
177
|
med 130
|
178
178
|
io 127
|
179
179
|
ro 127
|
180
|
+
_er_ 126
|
180
181
|
til 126
|
181
182
|
ik 125
|
182
|
-
_er_ 125
|
183
183
|
som 125
|
184
|
-
rn 124
|
185
184
|
_ti 124
|
185
|
+
rn 124
|
186
|
+
å_ 123
|
186
187
|
�_ 123
|
187
188
|
ds 123
|
188
|
-
å_ 123
|
189
|
-
_u 122
|
190
189
|
em 122
|
190
|
+
_u 122
|
191
191
|
eg 121
|
192
|
-
_Danm 121
|
193
192
|
rt 120
|
194
193
|
_ha 120
|
194
|
+
_r 120
|
195
|
+
_so 120
|
195
196
|
ld 119
|
196
197
|
_med 119
|
197
|
-
_so 119
|
198
198
|
_g 118
|
199
199
|
som_ 118
|
200
|
+
_S 118
|
200
201
|
to 117
|
201
|
-
_som 116
|
202
202
|
ske_ 116
|
203
|
-
det_
|
204
|
-
|
203
|
+
det_ 116
|
204
|
+
_som 116
|
205
205
|
ar_ 114
|
206
|
+
ern 114
|
206
207
|
end 114
|
207
208
|
tr 114
|
208
|
-
ern 114
|
209
209
|
_som_ 113
|
210
210
|
ko 111
|
211
211
|
ud 111
|
212
212
|
id 111
|
213
213
|
del 110
|
214
214
|
_til 109
|
215
|
-
si 108
|
216
215
|
nsk 108
|
217
|
-
va 108
|
218
216
|
mi 108
|
219
217
|
lig 108
|
220
|
-
|
218
|
+
va 108
|
219
|
+
si 108
|
221
220
|
_be 107
|
222
|
-
|
223
|
-
|
221
|
+
ls 107
|
222
|
+
ne_ 106
|
223
|
+
_� 106
|
224
|
+
_da 105
|
224
225
|
ka 105
|
225
|
-
bl 105
|
226
226
|
ion 105
|
227
|
-
|
228
|
-
_da 105
|
227
|
+
ind 105
|
229
228
|
gs 105
|
229
|
+
bl 105
|
230
|
+
�r 105
|
231
|
+
ør 105
|
230
232
|
lle 104
|
231
|
-
|
233
|
+
med_ 104
|
234
|
+
_. 104
|
232
235
|
t� 103
|
233
|
-
_
|
234
|
-
med_ 102
|
235
|
-
ne_ 102
|
236
|
-
ag 101
|
236
|
+
_._ 103
|
237
237
|
tt 101
|
238
|
-
|
238
|
+
ag 101
|
239
239
|
_en_ 101
|
240
|
+
dt 101
|
240
241
|
c 100
|
241
242
|
r� 100
|
242
|
-
ansk 99
|
243
|
-
ie 99
|
244
243
|
nt 99
|
245
244
|
dan 99
|
245
|
+
ansk 99
|
246
|
+
ie 99
|
246
247
|
_med_ 98
|
247
248
|
or_ 97
|
248
|
-
|
249
|
-
|
250
|
-
- 95
|
249
|
+
il_ 97
|
250
|
+
_De 95
|
251
251
|
De 95
|
252
252
|
�r 95
|
253
|
-
|
254
|
-
lt 94
|
255
|
-
nin 94
|
253
|
+
ær 95
|
256
254
|
na 94
|
255
|
+
lt 94
|
257
256
|
ner 94
|
257
|
+
rne 94
|
258
258
|
ning 94
|
259
|
-
|
260
|
-
|
259
|
+
nin 94
|
260
|
+
v_ 94
|
261
|
+
til_ 93
|
261
262
|
fr 92
|
262
263
|
at_ 92
|
264
|
+
I 92
|
265
|
+
ge_ 91
|
263
266
|
op 91
|
264
267
|
ru 91
|
268
|
+
ng_ 90
|
269
|
+
a_ 90
|
265
270
|
_dan 90
|
266
|
-
|
271
|
+
_I 90
|
272
|
+
erne 89
|
267
273
|
_bl 89
|
268
274
|
rd 89
|
269
|
-
ng_ 89
|
270
|
-
v_ 89
|
271
|
-
erne 89
|
272
275
|
ige 89
|
276
|
+
_re 89
|
273
277
|
gt 88
|
274
|
-
a_ 88
|
275
278
|
inge 87
|
276
|
-
|
279
|
+
tte 87
|
277
280
|
p� 87
|
278
|
-
_den 87
|
279
281
|
kr 87
|
280
|
-
|
282
|
+
_den 87
|
283
|
+
rk_ 86
|
281
284
|
s� 86
|
282
|
-
dans 86
|
283
|
-
men 86
|
284
285
|
dansk 86
|
285
|
-
|
286
|
+
men 86
|
287
|
+
dans 86
|
288
|
+
ver 85
|
286
289
|
isk 85
|
287
|
-
es_ 85
|
288
290
|
it 85
|
289
|
-
|
290
|
-
_dans 84
|
291
|
-
_re 84
|
292
|
-
f� 84
|
291
|
+
_til_ 85
|
293
292
|
am 84
|
293
|
+
f� 84
|
294
|
+
_dans 84
|
295
|
+
es_ 84
|
294
296
|
els 84
|
295
297
|
_at 84
|
296
298
|
est 83
|
297
299
|
_n 83
|
298
300
|
_den_ 82
|
299
|
-
gen 82
|
300
301
|
ur 82
|
302
|
+
gen 82
|
303
|
+
ark_ 81
|
301
304
|
_ud 81
|
302
305
|
he 81
|
306
|
+
sk_ 81
|
303
307
|
_at_ 81
|
304
|
-
rk_ 80
|
305
308
|
ble 80
|
306
309
|
ene 80
|
307
|
-
e. 79
|
308
|
-
und 79
|
309
|
-
ande 79
|
310
|
-
od 79
|
311
310
|
ede_ 79
|
312
|
-
|
311
|
+
od 79
|
312
|
+
ande 79
|
313
313
|
sa 79
|
314
|
-
|
315
|
-
eri 78
|
314
|
+
und 79
|
316
315
|
_in 78
|
316
|
+
_la 78
|
317
317
|
nde_ 78
|
318
318
|
_fr 78
|
319
|
-
|
320
|
-
ende 77
|
319
|
+
eri 78
|
321
320
|
ov 77
|
322
|
-
|
323
|
-
|
324
|
-
|
325
|
-
|
321
|
+
ende 77
|
322
|
+
_si 77
|
323
|
+
ing_ 77
|
324
|
+
r. 76
|
326
325
|
tor 76
|
326
|
+
mark_ 76
|
327
327
|
av 75
|
328
|
-
|
329
|
-
ark_ 75
|
328
|
+
nd_ 75
|
330
329
|
lev 75
|
331
|
-
|
330
|
+
r._ 75
|
331
|
+
an_ 75
|
332
|
+
lk 75
|
332
333
|
ft 74
|
333
|
-
F 73
|
334
334
|
mm 73
|
335
335
|
us 73
|
336
336
|
på 73
|
337
|
-
|
338
|
-
|
337
|
+
e. 73
|
338
|
+
F 73
|
339
339
|
di 72
|
340
340
|
E 72
|
341
|
-
|
341
|
+
le_ 72
|
342
342
|
e,_ 72
|
343
|
-
|
344
|
-
|
345
|
-
|
346
|
-
_p� 71
|
343
|
+
rin 72
|
344
|
+
e, 72
|
345
|
+
_på 71
|
347
346
|
nske 71
|
348
347
|
_lan 71
|
349
|
-
_på 71
|
350
348
|
_der 71
|
351
|
-
|
349
|
+
_p� 71
|
350
|
+
e._ 71
|
352
351
|
get 70
|
352
|
+
st� 70
|
353
353
|
gi 70
|
354
354
|
pr 69
|
355
|
+
_,_ 69
|
355
356
|
ist 69
|
356
|
-
|
357
|
+
_, 69
|
358
|
+
_E 69
|
357
359
|
_blev 68
|
358
|
-
|
359
|
-
blev 68
|
360
|
+
ks 68
|
360
361
|
var 68
|
362
|
+
blev 68
|
363
|
+
_ble 68
|
361
364
|
_va 67
|
362
|
-
anske 67
|
363
365
|
på_ 67
|
366
|
+
anske 67
|
364
367
|
ss 67
|
365
|
-
_på_ 66
|
366
|
-
gr 66
|
367
|
-
år 66
|
368
368
|
tio 66
|
369
|
-
|
369
|
+
lse 66
|
370
|
+
år 66
|
370
371
|
tion 66
|
371
372
|
fi 66
|
372
|
-
lse 66
|
373
|
-
_land 66
|
374
373
|
�r 66
|
374
|
+
_F 66
|
375
|
+
gr 66
|
376
|
+
_land 66
|
377
|
+
_på_ 66
|
378
|
+
ati 66
|
375
379
|
ef 65
|
376
380
|
one 65
|
377
381
|
sto 65
|
378
382
|
kt 65
|
379
|
-
sen 64
|
380
383
|
else 64
|
384
|
+
sen 64
|
381
385
|
ev_ 64
|
382
|
-
|
386
|
+
ren 63
|
383
387
|
ende_ 63
|
388
|
+
A 63
|
389
|
+
ig_ 63
|
384
390
|
ring 63
|
385
|
-
ren 63
|
386
|
-
_ko 62
|
387
391
|
for_ 62
|
388
392
|
ho 62
|
389
|
-
|
390
|
-
|
391
|
-
dr 61
|
393
|
+
_ko 62
|
394
|
+
ere_ 61
|
392
395
|
rig 61
|
393
396
|
ste_ 61
|
397
|
+
dr 61
|
394
398
|
ret 60
|
395
|
-
lev_ 60
|
396
|
-
n,_ 60
|
397
|
-
_E 60
|
398
|
-
_F 60
|
399
|
-
n, 60
|
400
399
|
blev_ 60
|
400
|
+
lev_ 60
|