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/icelandic.lm
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 1490
|
2
2
|
a 336
|
3
3
|
r 312
|
4
4
|
n 283
|
@@ -13,388 +13,388 @@ g 157
|
|
13
13
|
k 143
|
14
14
|
m 135
|
15
15
|
f 132
|
16
|
-
r_
|
17
|
-
�_
|
16
|
+
r_ 110
|
17
|
+
�_ 79
|
18
18
|
v 74
|
19
19
|
ar 73
|
20
20
|
� 71
|
21
|
+
_s 70
|
21
22
|
o 70
|
22
|
-
_s 65
|
23
|
-
� 63
|
24
23
|
a� 63
|
24
|
+
� 63
|
25
25
|
j 62
|
26
|
-
|
26
|
+
a_ 60
|
27
|
+
m_ 60
|
27
28
|
� 55
|
29
|
+
_f 55
|
28
30
|
in 55
|
29
|
-
|
30
|
-
_e
|
31
|
-
|
31
|
+
i_ 54
|
32
|
+
_e 53
|
33
|
+
n_ 53
|
34
|
+
u_ 52
|
35
|
+
_a 51
|
32
36
|
um 48
|
33
37
|
ur 48
|
34
|
-
_a 47
|
35
38
|
h 47
|
36
|
-
|
37
|
-
d 46
|
39
|
+
_� 46
|
38
40
|
. 46
|
39
|
-
|
40
|
-
_
|
41
|
-
|
41
|
+
d 46
|
42
|
+
a�_ 45
|
43
|
+
._ 45
|
44
|
+
g_ 45
|
42
45
|
st 44
|
43
|
-
i_ 44
|
44
46
|
b 44
|
45
47
|
er 44
|
46
|
-
u_ 43
|
47
|
-
� 43
|
48
48
|
� 43
|
49
|
-
|
49
|
+
� 43
|
50
|
+
�_ 42
|
50
51
|
nn 42
|
51
|
-
|
52
|
+
_�_ 41
|
52
53
|
ei 40
|
53
|
-
|
54
|
-
|
55
|
-
i� 38
|
54
|
+
_v 40
|
55
|
+
nu 40
|
56
56
|
� 38
|
57
|
+
i� 38
|
57
58
|
y 37
|
59
|
+
um_ 37
|
60
|
+
_h 37
|
58
61
|
ir 36
|
59
|
-
�
|
62
|
+
_a� 36
|
60
63
|
an 36
|
61
|
-
|
62
|
-
|
64
|
+
_� 36
|
65
|
+
_o 36
|
66
|
+
�_ 36
|
67
|
+
_� 36
|
63
68
|
ve 35
|
69
|
+
p 35
|
64
70
|
og 34
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
og_ 33
|
71
|
+
ur_ 34
|
72
|
+
_og_ 33
|
73
|
+
_og 33
|
69
74
|
un 33
|
70
|
-
|
71
|
-
|
72
|
-
|
75
|
+
og_ 33
|
76
|
+
_m 32
|
77
|
+
ar_ 31
|
73
78
|
ta 30
|
74
|
-
|
75
|
-
_m 29
|
76
|
-
na 29
|
77
|
-
_og 29
|
79
|
+
_a�_ 30
|
78
80
|
�u 29
|
81
|
+
na 29
|
79
82
|
en 29
|
80
|
-
ti 28
|
81
|
-
lu 28
|
82
83
|
ri 28
|
84
|
+
ti 28
|
83
85
|
la 28
|
84
|
-
|
85
|
-
|
86
|
+
lu 28
|
87
|
+
_�_ 26
|
88
|
+
_ve 26
|
86
89
|
� 26
|
87
|
-
�i 25
|
88
|
-
._ 25
|
89
|
-
_a�_ 25
|
90
90
|
t_ 25
|
91
|
-
|
92
|
-
|
93
|
-
_b 24
|
91
|
+
_b 25
|
92
|
+
�i 25
|
94
93
|
nd 24
|
95
|
-
|
94
|
+
ja 24
|
96
95
|
ng 24
|
97
|
-
r� 23
|
98
96
|
ki 23
|
97
|
+
r� 23
|
98
|
+
_u 23
|
99
99
|
kk 23
|
100
|
+
ra 23
|
100
101
|
ir_ 22
|
101
102
|
i�_ 22
|
102
103
|
sl 21
|
103
|
-
|
104
|
+
_g 21
|
104
105
|
ef 21
|
105
|
-
tu 20
|
106
106
|
em 20
|
107
|
-
|
108
|
-
_u 20
|
107
|
+
tu 20
|
109
108
|
_t 20
|
110
|
-
|
109
|
+
ku 20
|
111
110
|
inn 19
|
111
|
+
_l 19
|
112
112
|
se 19
|
113
113
|
sk 19
|
114
|
+
il 19
|
114
115
|
ga 18
|
116
|
+
ver 18
|
115
117
|
� 18
|
116
|
-
_g 18
|
117
118
|
�a 18
|
118
|
-
_l 18
|
119
119
|
_n 18
|
120
|
-
ver 18
|
121
|
-
ni 17
|
122
120
|
af 17
|
121
|
+
ni 17
|
122
|
+
_er 17
|
123
123
|
ek 17
|
124
|
+
nn_ 17
|
125
|
+
sem 16
|
124
126
|
eg 16
|
125
|
-
|
127
|
+
_se 16
|
126
128
|
num 16
|
127
|
-
|
128
|
-
ka 15
|
129
|
-
gu 15
|
129
|
+
_ver 16
|
130
130
|
gi 15
|
131
|
-
|
132
|
-
_er 15
|
131
|
+
gu 15
|
133
132
|
em_ 15
|
134
|
-
|
135
|
-
da 15
|
133
|
+
ag 15
|
136
134
|
es 15
|
137
|
-
|
135
|
+
mi 15
|
136
|
+
,_ 15
|
137
|
+
_sem_ 15
|
138
138
|
, 15
|
139
|
+
ka 15
|
140
|
+
da 15
|
141
|
+
_sem 15
|
139
142
|
sem_ 15
|
140
|
-
�k 14
|
141
|
-
nar 14
|
142
143
|
b� 14
|
143
|
-
|
144
|
+
am 14
|
144
145
|
l� 14
|
146
|
+
nar 14
|
145
147
|
�e 14
|
146
|
-
|
147
|
-
|
148
|
+
�k 14
|
149
|
+
yr 14
|
150
|
+
�i_ 14
|
151
|
+
s_ 14
|
152
|
+
_�e 14
|
148
153
|
�ur 14
|
149
154
|
j� 14
|
150
|
-
|
151
|
-
|
152
|
-
|
153
|
-
is 13
|
155
|
+
rf 14
|
156
|
+
al 13
|
157
|
+
�g 13
|
154
158
|
S 13
|
155
|
-
|
156
|
-
|
157
|
-
ge 13
|
158
|
-
_�e 13
|
159
|
+
tt 13
|
160
|
+
fl 13
|
159
161
|
li 13
|
162
|
+
ki_ 13
|
163
|
+
ne 13
|
160
164
|
l_ 13
|
165
|
+
ge 13
|
166
|
+
vi 13
|
161
167
|
ll 13
|
162
|
-
tt 13
|
163
|
-
u� 13
|
164
|
-
al 13
|
165
|
-
�g 13
|
166
|
-
ne 13
|
167
|
-
fl 13
|
168
|
-
_sem_ 13
|
169
168
|
re 13
|
170
|
-
|
169
|
+
u� 13
|
170
|
+
ey 12
|
171
171
|
ekk 12
|
172
|
+
he 12
|
173
|
+
num_ 12
|
174
|
+
te 12
|
172
175
|
�k 12
|
176
|
+
ha 12
|
177
|
+
is 12
|
173
178
|
fr 12
|
174
|
-
ru 12
|
175
|
-
me 12
|
176
|
-
ey 12
|
177
|
-
he 12
|
178
179
|
_k 12
|
179
|
-
|
180
|
-
inu 12
|
181
|
-
te 12
|
182
|
-
fyrir 11
|
180
|
+
me 12
|
183
181
|
slu 11
|
184
|
-
|
185
|
-
|
186
|
-
fyr 11
|
187
|
-
di 11
|
188
|
-
us 11
|
182
|
+
yrir 11
|
183
|
+
ru 11
|
189
184
|
fyri 11
|
190
|
-
|
191
|
-
|
192
|
-
rir 11
|
185
|
+
us 11
|
186
|
+
fyr 11
|
193
187
|
_ha 11
|
188
|
+
inu 11
|
189
|
+
rir 11
|
190
|
+
_he 11
|
194
191
|
ju 11
|
195
|
-
fy 11
|
196
|
-
yrir 11
|
197
|
-
rs 11
|
198
192
|
er� 11
|
199
|
-
|
200
|
-
|
201
|
-
|
202
|
-
|
203
|
-
|
204
|
-
|
205
|
-
kj 10
|
206
|
-
_�a 10
|
207
|
-
il_ 10
|
208
|
-
arf 10
|
209
|
-
_ekki 10
|
210
|
-
ekki 10
|
211
|
-
et 10
|
212
|
-
le 10
|
213
|
-
ko 10
|
214
|
-
fj 10
|
215
|
-
_ekk 10
|
216
|
-
�i_ 10
|
217
|
-
rn 10
|
193
|
+
fy 11
|
194
|
+
yri 11
|
195
|
+
fyrir 11
|
196
|
+
_S 11
|
197
|
+
di 11
|
198
|
+
ma 11
|
218
199
|
_ek 10
|
219
|
-
_he 10
|
220
200
|
f_ 10
|
221
|
-
|
201
|
+
rn 10
|
202
|
+
_�a 10
|
203
|
+
et 10
|
222
204
|
si 10
|
205
|
+
arf 10
|
206
|
+
�s 10
|
207
|
+
il_ 10
|
208
|
+
ko 10
|
209
|
+
_ekki 10
|
210
|
+
_mi 10
|
211
|
+
ekki_ 10
|
223
212
|
_st 10
|
213
|
+
ns 10
|
214
|
+
or 10
|
224
215
|
r�u 10
|
225
|
-
|
216
|
+
_ekk 10
|
217
|
+
fj 10
|
218
|
+
kki 10
|
219
|
+
�a 10
|
220
|
+
kj 10
|
221
|
+
le 10
|
222
|
+
kki_ 10
|
223
|
+
ekki 10
|
224
|
+
fu 10
|
225
|
+
pp 10
|
226
|
+
til_ 9
|
227
|
+
_til_ 9
|
228
|
+
_fyr 9
|
229
|
+
_um_ 9
|
230
|
+
nar_ 9
|
231
|
+
nni 9
|
226
232
|
gn 9
|
227
|
-
K 9
|
228
|
-
sa 9
|
229
|
-
kki_ 9
|
230
|
-
v� 9
|
231
233
|
er_ 9
|
232
|
-
|
233
|
-
_ti 9
|
234
|
-
_til_ 9
|
234
|
+
kur 9
|
235
235
|
til 9
|
236
|
+
_um 9
|
237
|
+
_fy 9
|
236
238
|
� 9
|
239
|
+
rs 9
|
237
240
|
_er_ 9
|
241
|
+
_me 9
|
238
242
|
_til 9
|
243
|
+
ann 9
|
244
|
+
sa 9
|
245
|
+
lu_ 9
|
246
|
+
v� 9
|
247
|
+
_ge 9
|
248
|
+
ta_ 9
|
249
|
+
_sk 9
|
250
|
+
_fyri 9
|
239
251
|
av 9
|
240
252
|
f� 9
|
241
|
-
|
242
|
-
|
243
|
-
|
244
|
-
|
245
|
-
|
246
|
-
|
253
|
+
K 9
|
254
|
+
ru_ 9
|
255
|
+
_ti 9
|
256
|
+
_en 8
|
257
|
+
_ei 8
|
258
|
+
va 8
|
259
|
+
st_ 8
|
260
|
+
l�g 8
|
261
|
+
�u_ 8
|
262
|
+
ngi 8
|
263
|
+
hef 8
|
264
|
+
_hef 8
|
265
|
+
an_ 8
|
266
|
+
�ur_ 8
|
267
|
+
�r 8
|
247
268
|
e� 8
|
248
|
-
|
249
|
-
|
250
|
-
|
251
|
-
|
252
|
-
|
269
|
+
�n 8
|
270
|
+
du 8
|
271
|
+
stu 8
|
272
|
+
_af 8
|
273
|
+
_H 8
|
253
274
|
H 8
|
275
|
+
_G 8
|
276
|
+
_fr 8
|
254
277
|
�t 8
|
255
278
|
ut 8
|
256
|
-
|
279
|
+
u�u 8
|
280
|
+
fe 8
|
281
|
+
ss 8
|
282
|
+
�a_ 8
|
283
|
+
_b� 8
|
284
|
+
nes 8
|
285
|
+
kt 8
|
257
286
|
_vi 8
|
258
|
-
|
287
|
+
G 8
|
288
|
+
a�i 8
|
259
289
|
ing 8
|
260
|
-
stu 8
|
261
290
|
ik 8
|
262
|
-
_sk 8
|
263
|
-
�r 8
|
264
|
-
�n 8
|
265
|
-
an_ 8
|
266
|
-
_S 8
|
267
|
-
u�u 8
|
268
|
-
l�g 8
|
269
|
-
st_ 8
|
270
|
-
_en 8
|
271
291
|
fa 8
|
272
|
-
nda 8
|
273
292
|
it 8
|
274
|
-
|
275
|
-
ss 8
|
276
|
-
_me 8
|
277
|
-
va 8
|
278
|
-
_ei 8
|
279
|
-
nes 8
|
293
|
+
un_ 8
|
280
294
|
gr 8
|
281
|
-
|
282
|
-
|
283
|
-
|
284
|
-
|
285
|
-
|
286
|
-
|
295
|
+
nda 8
|
296
|
+
tu_ 8
|
297
|
+
_en_ 7
|
298
|
+
eru 7
|
299
|
+
_f�k 7
|
300
|
+
_eru 7
|
301
|
+
as 7
|
287
302
|
r. 7
|
288
|
-
|
289
|
-
|
303
|
+
er�ur 7
|
304
|
+
ei� 7
|
305
|
+
�kk 7
|
306
|
+
rl 7
|
307
|
+
rt 7
|
308
|
+
ig 7
|
309
|
+
gre 7
|
290
310
|
ein 7
|
311
|
+
ram 7
|
312
|
+
_K 7
|
313
|
+
br 7
|
314
|
+
B 7
|
315
|
+
eru_ 7
|
316
|
+
_f� 7
|
291
317
|
v�k 7
|
292
|
-
|
293
|
-
|
294
|
-
|
295
|
-
_H 7
|
296
|
-
�kk 7
|
318
|
+
rk 7
|
319
|
+
fi 7
|
320
|
+
av� 7
|
297
321
|
_f�kk 7
|
322
|
+
ja_ 7
|
323
|
+
und 7
|
298
324
|
�t 7
|
299
|
-
ust 7
|
300
325
|
ga_ 7
|
301
|
-
|
302
|
-
|
303
|
-
|
304
|
-
|
326
|
+
inni 7
|
327
|
+
lj 7
|
328
|
+
yrir_ 7
|
329
|
+
gl 7
|
305
330
|
rir_ 7
|
306
|
-
_b� 7
|
307
|
-
B 7
|
308
|
-
_G 7
|
309
|
-
as 7
|
310
|
-
kun 7
|
311
|
-
er�ur 7
|
312
|
-
_fr 7
|
313
|
-
�� 7
|
314
|
-
er�u 7
|
315
331
|
_fj 7
|
316
|
-
|
317
|
-
|
318
|
-
|
319
|
-
|
320
|
-
|
321
|
-
|
322
|
-
|
323
|
-
|
324
|
-
|
332
|
+
el 7
|
333
|
+
jar 7
|
334
|
+
er�u 7
|
335
|
+
�� 7
|
336
|
+
fn 7
|
337
|
+
f�kk 7
|
338
|
+
eng 7
|
339
|
+
av�k 7
|
340
|
+
en_ 7
|
325
341
|
m. 7
|
342
|
+
_B 7
|
343
|
+
_eru_ 7
|
344
|
+
r�ur 7
|
326
345
|
f�k 7
|
327
|
-
|
328
|
-
|
346
|
+
_un 7
|
347
|
+
k_ 7
|
348
|
+
na_ 7
|
349
|
+
kun 7
|
350
|
+
ri� 7
|
351
|
+
�ar 7
|
352
|
+
r._ 7
|
353
|
+
ust 7
|
354
|
+
_� 7
|
329
355
|
ld 7
|
330
356
|
�l 7
|
331
|
-
|
332
|
-
|
333
|
-
|
334
|
-
|
335
|
-
|
336
|
-
|
337
|
-
|
338
|
-
|
339
|
-
|
340
|
-
|
341
|
-
|
342
|
-
|
343
|
-
�r_ 6
|
344
|
-
upp 6
|
345
|
-
�kur 6
|
357
|
+
um._ 6
|
358
|
+
nu� 6
|
359
|
+
ann_ 6
|
360
|
+
�l 6
|
361
|
+
i�s 6
|
362
|
+
_�t 6
|
363
|
+
ug 6
|
364
|
+
ra_ 6
|
365
|
+
nna 6
|
366
|
+
_upp 6
|
367
|
+
ys 6
|
368
|
+
j� 6
|
346
369
|
R 6
|
370
|
+
s� 6
|
371
|
+
nga 6
|
372
|
+
yk 6
|
373
|
+
gar 6
|
347
374
|
stu_ 6
|
348
|
-
sko 6
|
349
|
-
rst 6
|
350
|
-
av�ku 6
|
351
|
-
_K 6
|
352
|
-
ka� 6
|
353
375
|
tar 6
|
354
|
-
|
355
|
-
|
356
|
-
tr 6
|
357
|
-
nga 6
|
358
|
-
_B 6
|
359
|
-
dur 6
|
360
|
-
_ge 6
|
361
|
-
fur 6
|
362
|
-
rg 6
|
363
|
-
_up 6
|
364
|
-
j� 6
|
365
|
-
v�ku 6
|
376
|
+
av�ku 6
|
377
|
+
dur_ 6
|
366
378
|
fra 6
|
379
|
+
�n 6
|
380
|
+
tir 6
|
381
|
+
�_ 6
|
367
382
|
and 6
|
368
|
-
dag 6
|
369
|
-
_ef 6
|
370
|
-
_upp 6
|
371
|
-
nna 6
|
372
|
-
s� 6
|
373
|
-
yk 6
|
374
|
-
tir_ 6
|
375
383
|
lg 6
|
376
|
-
|
384
|
+
sko 6
|
385
|
+
up 6
|
377
386
|
enn 6
|
387
|
+
_ef 6
|
378
388
|
kja 6
|
379
|
-
|
380
|
-
|
381
|
-
|
382
|
-
|
383
|
-
up 6
|
389
|
+
li� 6
|
390
|
+
fur_ 6
|
391
|
+
dur 6
|
392
|
+
inn_ 6
|
384
393
|
tarf 6
|
385
|
-
|
386
|
-
�_ 6
|
387
|
-
ra_ 6
|
388
|
-
�ku 6
|
389
|
-
ug 6
|
390
|
-
�n 6
|
391
|
-
eir 6
|
394
|
+
upp 6
|
392
395
|
eit 6
|
393
|
-
|
394
|
-
|
395
|
-
|
396
|
-
|
397
|
-
|
398
|
-
k_ 6
|
399
|
-
li� 6
|
400
|
-
ann_ 6
|
396
|
+
eir 6
|
397
|
+
f� 6
|
398
|
+
dag 6
|
399
|
+
_Re 6
|
400
|
+
tr 6
|