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/slovenian.lm
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 1590
|
2
2
|
e 430
|
3
3
|
a 407
|
4
4
|
o 348
|
@@ -11,390 +11,390 @@ t 175
|
|
11
11
|
j 171
|
12
12
|
v 148
|
13
13
|
k 146
|
14
|
+
e_ 139
|
14
15
|
d 137
|
15
|
-
e_ 122
|
16
16
|
z 119
|
17
17
|
y 119
|
18
|
+
a_ 118
|
18
19
|
p 117
|
19
|
-
a_ 106
|
20
20
|
m 97
|
21
|
+
o_ 97
|
22
|
+
_s 93
|
21
23
|
c 89
|
22
|
-
|
23
|
-
|
24
|
+
i_ 80
|
25
|
+
_p 79
|
24
26
|
je 78
|
25
|
-
|
27
|
+
_n 76
|
26
28
|
cy 70
|
27
|
-
|
28
|
-
_p 69
|
29
|
+
_v 62
|
29
30
|
u 61
|
30
31
|
b 60
|
31
32
|
, 58
|
32
|
-
|
33
|
+
,_ 58
|
34
|
+
_j 54
|
35
|
+
_z 53
|
33
36
|
st 53
|
34
37
|
na 53
|
35
|
-
|
38
|
+
je_ 52
|
36
39
|
ra 51
|
37
40
|
ni 50
|
38
|
-
|
39
|
-
_z 48
|
41
|
+
_je 50
|
40
42
|
g 48
|
41
|
-
je_ 47
|
42
43
|
al 46
|
44
|
+
_je_ 45
|
45
|
+
._ 45
|
43
46
|
. 45
|
44
|
-
_je 45
|
45
|
-
in 44
|
46
47
|
se 44
|
48
|
+
in 44
|
47
49
|
po 43
|
48
50
|
h 42
|
49
51
|
la 41
|
50
52
|
no 40
|
51
53
|
el 40
|
54
|
+
_k 40
|
52
55
|
ye 39
|
53
|
-
_k 38
|
54
56
|
ti 38
|
55
|
-
en 37
|
56
57
|
il 37
|
58
|
+
n_ 37
|
57
59
|
re 36
|
58
|
-
|
59
|
-
n_ 35
|
60
|
+
en 35
|
60
61
|
ne 35
|
61
|
-
|
62
|
+
_na 34
|
63
|
+
_d 34
|
62
64
|
ko 34
|
65
|
+
pr 34
|
66
|
+
va 33
|
63
67
|
ja 33
|
64
|
-
lo 33
|
65
68
|
de 33
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
ka 31
|
69
|
+
_po 33
|
70
|
+
_i 33
|
71
|
+
lo 33
|
72
|
+
_o 32
|
73
|
+
_t 32
|
72
74
|
ve 31
|
73
|
-
|
75
|
+
ka 31
|
76
|
+
_m 30
|
77
|
+
ov 30
|
74
78
|
le 30
|
75
|
-
|
79
|
+
za 29
|
76
80
|
ri 29
|
77
81
|
nj 29
|
78
|
-
|
79
|
-
an 29
|
80
|
-
aj 29
|
81
|
-
od 28
|
82
|
-
_m 28
|
82
|
+
te 28
|
83
83
|
zy 28
|
84
84
|
li 28
|
85
|
-
|
85
|
+
an 28
|
86
|
+
aj 28
|
86
87
|
_se 27
|
87
|
-
l_ 27
|
88
88
|
et 27
|
89
|
-
|
90
|
-
|
91
|
-
|
89
|
+
v_ 27
|
90
|
+
l_ 27
|
91
|
+
_pr 26
|
92
|
+
od 26
|
93
|
+
_b 26
|
94
|
+
da 25
|
92
95
|
ro 25
|
93
96
|
ek 25
|
94
|
-
|
95
|
-
_b 24
|
97
|
+
_za 24
|
96
98
|
ih 24
|
97
99
|
ed 24
|
98
|
-
yi 23
|
99
|
-
ocy 23
|
100
100
|
to 23
|
101
|
-
|
102
|
-
se_
|
101
|
+
yi 23
|
102
|
+
se_ 23
|
103
103
|
ad 22
|
104
|
-
|
105
|
-
|
106
|
-
|
107
|
-
|
108
|
-
|
104
|
+
_se_ 22
|
105
|
+
_r 22
|
106
|
+
h_ 22
|
107
|
+
oc 21
|
108
|
+
ih_ 21
|
109
|
+
ocy 21
|
109
110
|
so 21
|
110
|
-
|
111
|
+
lo_ 21
|
111
112
|
tr 20
|
112
|
-
|
113
|
-
|
114
|
-
|
113
|
+
la_ 20
|
114
|
+
ji 20
|
115
|
+
_v_ 20
|
115
116
|
em 20
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
_v_ 19
|
120
|
-
lo_ 19
|
117
|
+
ar 20
|
118
|
+
_ne 20
|
119
|
+
ob 19
|
121
120
|
ya 19
|
122
|
-
|
123
|
-
|
124
|
-
|
121
|
+
_so 19
|
122
|
+
r_ 19
|
123
|
+
es 19
|
124
|
+
ic 19
|
125
|
+
in_ 18
|
126
|
+
iz 18
|
125
127
|
er 18
|
128
|
+
cye 18
|
126
129
|
ta 18
|
127
|
-
|
128
|
-
|
129
|
-
iz 18
|
130
|
+
ak 18
|
131
|
+
_in 18
|
130
132
|
mo 18
|
131
|
-
|
132
|
-
bi 17
|
133
|
-
os 17
|
134
|
-
in_ 17
|
135
|
-
_ne 17
|
133
|
+
_in_ 18
|
136
134
|
ki 17
|
135
|
+
os 17
|
136
|
+
na_ 17
|
137
|
+
is 17
|
138
|
+
as 17
|
137
139
|
mi 17
|
138
|
-
|
140
|
+
m_ 17
|
141
|
+
az 17
|
142
|
+
bi 17
|
143
|
+
no_ 17
|
139
144
|
lj 17
|
140
145
|
sy 17
|
141
|
-
as 17
|
142
146
|
ga 17
|
143
|
-
|
147
|
+
ye_ 17
|
148
|
+
on 16
|
149
|
+
_ve 16
|
150
|
+
og 16
|
144
151
|
t_ 16
|
145
|
-
|
146
|
-
ns 16
|
152
|
+
pa 16
|
147
153
|
ec 16
|
148
|
-
|
149
|
-
|
154
|
+
ns 16
|
155
|
+
ne_ 16
|
150
156
|
ik 16
|
151
|
-
|
152
|
-
u_
|
153
|
-
|
154
|
-
|
155
|
-
or 15
|
156
|
-
m_ 15
|
157
|
+
so_ 16
|
158
|
+
u_ 16
|
159
|
+
z_ 16
|
160
|
+
pre 16
|
157
161
|
kr 15
|
158
|
-
|
162
|
+
_bi 15
|
163
|
+
or 15
|
164
|
+
ja_ 15
|
165
|
+
sa 15
|
166
|
+
ot 15
|
167
|
+
_so_ 15
|
159
168
|
ol 15
|
160
|
-
na_ 15
|
161
|
-
so_ 15
|
162
|
-
_so 15
|
163
|
-
at 15
|
164
|
-
yn 14
|
165
169
|
dn 14
|
166
|
-
|
170
|
+
yn 14
|
167
171
|
cyi 14
|
168
|
-
om 14
|
169
|
-
im 14
|
170
172
|
di 14
|
171
|
-
j_ 14
|
172
173
|
ecy 14
|
173
|
-
|
174
|
+
_pre 14
|
175
|
+
at 14
|
176
|
+
av 14
|
177
|
+
om 14
|
178
|
+
_c 14
|
174
179
|
vo 14
|
175
|
-
|
176
|
-
|
177
|
-
|
178
|
-
|
179
|
-
i, 13
|
180
|
-
ap 13
|
181
|
-
go 13
|
182
|
-
ye_ 13
|
183
|
-
z_ 13
|
184
|
-
_pre 13
|
185
|
-
ez 13
|
186
|
-
ev 13
|
187
|
-
_ve 13
|
188
|
-
me 13
|
180
|
+
j_ 14
|
181
|
+
nje 14
|
182
|
+
im 14
|
183
|
+
zye 14
|
189
184
|
ir 13
|
185
|
+
go 13
|
186
|
+
ti_ 13
|
187
|
+
ap 13
|
188
|
+
i, 13
|
190
189
|
ins 13
|
190
|
+
_ko 13
|
191
|
+
ke 13
|
192
|
+
raz 13
|
193
|
+
me 13
|
194
|
+
i,_ 13
|
195
|
+
_iz 13
|
196
|
+
_ni 12
|
197
|
+
bil 12
|
198
|
+
ova 12
|
191
199
|
_st 12
|
192
|
-
|
193
|
-
|
194
|
-
vi 12
|
195
|
-
ko_ 12
|
196
|
-
cya 12
|
197
|
-
ij 12
|
198
|
-
eg 12
|
200
|
+
da_ 12
|
201
|
+
_bil 12
|
199
202
|
sto 12
|
203
|
+
ok 12
|
200
204
|
li_ 12
|
201
|
-
|
202
|
-
i,_ 12
|
205
|
+
eg 12
|
203
206
|
do 12
|
204
|
-
|
205
|
-
|
206
|
-
|
207
|
-
|
208
|
-
|
209
|
-
|
210
|
-
|
211
|
-
da_ 11
|
212
|
-
elo 11
|
213
|
-
_ra 11
|
214
|
-
_iz 11
|
215
|
-
nst 11
|
216
|
-
_so_ 11
|
207
|
+
_na_ 12
|
208
|
+
ez 12
|
209
|
+
ko_ 12
|
210
|
+
cya 12
|
211
|
+
_da 11
|
212
|
+
_g 11
|
213
|
+
_mo 11
|
217
214
|
ga_ 11
|
218
|
-
|
219
|
-
|
215
|
+
a, 11
|
216
|
+
ev 11
|
217
|
+
a,_ 11
|
220
218
|
ala 11
|
219
|
+
_ra 11
|
220
|
+
_l 11
|
221
|
+
ni_ 11
|
221
222
|
del 11
|
222
|
-
|
223
|
-
|
223
|
+
nst 11
|
224
|
+
ilo 11
|
225
|
+
sk 11
|
226
|
+
ilo_ 11
|
224
227
|
jo 11
|
225
|
-
|
226
|
-
|
227
|
-
|
228
|
-
|
229
|
-
|
230
|
-
|
231
|
-
|
232
|
-
|
233
|
-
|
234
|
-
|
235
|
-
it 10
|
236
|
-
un 10
|
237
|
-
nston 10
|
238
|
-
ln 10
|
239
|
-
anj 10
|
228
|
+
cyn 11
|
229
|
+
_pa 11
|
230
|
+
ij 11
|
231
|
+
elo 11
|
232
|
+
vi 11
|
233
|
+
_cy 11
|
234
|
+
le_ 11
|
235
|
+
Win 10
|
236
|
+
d_ 10
|
237
|
+
_do 10
|
240
238
|
insto 10
|
241
|
-
nsto 10
|
242
239
|
ston 10
|
243
|
-
|
244
|
-
|
245
|
-
|
246
|
-
ost 10
|
247
|
-
ala_ 10
|
248
|
-
ton 10
|
249
|
-
_mo 10
|
250
|
-
_l 10
|
240
|
+
ali 10
|
241
|
+
aj_ 10
|
242
|
+
ln 10
|
251
243
|
Wins 10
|
244
|
+
Winst 10
|
245
|
+
_Wi 10
|
246
|
+
_zy 10
|
247
|
+
W 10
|
248
|
+
_W 10
|
249
|
+
cye_ 10
|
250
|
+
ton 10
|
252
251
|
inst 10
|
252
|
+
ala_ 10
|
253
|
+
_Wins 10
|
254
|
+
Wi 10
|
255
|
+
nsto 10
|
253
256
|
eti 10
|
254
|
-
|
257
|
+
anj 10
|
258
|
+
nston 10
|
255
259
|
yal 10
|
256
|
-
|
260
|
+
un 10
|
261
|
+
em_ 10
|
262
|
+
ac 10
|
263
|
+
ost 10
|
264
|
+
_Win 10
|
265
|
+
_ob 9
|
266
|
+
ce 9
|
257
267
|
br 9
|
258
|
-
|
259
|
-
|
268
|
+
ka_ 9
|
269
|
+
_ka 9
|
270
|
+
oz 9
|
271
|
+
am 9
|
260
272
|
elo_ 9
|
261
|
-
|
273
|
+
pi 9
|
262
274
|
kra 9
|
263
|
-
|
264
|
-
|
265
|
-
ilo_ 9
|
266
|
-
al_ 9
|
267
|
-
oz 9
|
275
|
+
rj 9
|
276
|
+
k_ 9
|
268
277
|
y_ 9
|
269
|
-
nic 9
|
270
|
-
le_ 9
|
271
|
-
_pa 9
|
272
278
|
acy 9
|
273
|
-
|
274
|
-
za_
|
275
|
-
|
276
|
-
|
277
|
-
|
278
|
-
|
279
|
-
|
280
|
-
|
281
|
-
|
279
|
+
al_ 9
|
280
|
+
za_ 9
|
281
|
+
_od 9
|
282
|
+
it 9
|
283
|
+
il_ 9
|
284
|
+
nic 9
|
285
|
+
icy 9
|
286
|
+
nu 9
|
287
|
+
_te 9
|
288
|
+
stv 8
|
282
289
|
vr 8
|
283
|
-
|
284
|
-
ah 8
|
290
|
+
rat 8
|
285
291
|
bo 8
|
292
|
+
a._ 8
|
293
|
+
val 8
|
286
294
|
tv 8
|
295
|
+
ki_ 8
|
296
|
+
ezy 8
|
297
|
+
o._ 8
|
287
298
|
imi 8
|
288
|
-
|
289
|
-
|
290
|
-
|
291
|
-
val 8
|
292
|
-
ali_ 8
|
293
|
-
rat 8
|
299
|
+
ah 8
|
300
|
+
po_ 8
|
301
|
+
pe 8
|
294
302
|
cy_ 8
|
295
|
-
|
296
|
-
|
297
|
-
|
303
|
+
ese 8
|
304
|
+
jen 8
|
305
|
+
_da_ 8
|
306
|
+
ze 8
|
307
|
+
a. 8
|
308
|
+
o. 8
|
298
309
|
ist 8
|
299
|
-
|
300
|
-
pe 8
|
301
|
-
kl 8
|
310
|
+
ali_ 8
|
302
311
|
ran 8
|
312
|
+
_nj 8
|
313
|
+
kl 8
|
314
|
+
ma 8
|
315
|
+
_po_ 8
|
303
316
|
O 8
|
304
|
-
|
305
|
-
|
306
|
-
kih 7
|
307
|
-
dno 7
|
308
|
-
nost 7
|
317
|
+
yil 8
|
318
|
+
_V 7
|
309
319
|
var 7
|
310
|
-
|
311
|
-
|
312
|
-
kih_ 7
|
313
|
-
pri 7
|
314
|
-
ep 7
|
315
|
-
_ko_ 7
|
316
|
-
nov 7
|
317
|
-
ci 7
|
318
|
-
_ob 7
|
319
|
-
_od 7
|
320
|
-
o,_ 7
|
321
|
-
dr 7
|
322
|
-
_kr 7
|
323
|
-
en_ 7
|
320
|
+
sed 7
|
321
|
+
tak 7
|
324
322
|
_le 7
|
323
|
+
to_ 7
|
324
|
+
_S 7
|
325
|
+
_de 7
|
326
|
+
_za_ 7
|
327
|
+
dr 7
|
325
328
|
o, 7
|
329
|
+
on_ 7
|
330
|
+
tem 7
|
331
|
+
ci 7
|
326
332
|
pa_ 7
|
327
|
-
tak 7
|
328
|
-
nih 7
|
329
|
-
e,_ 7
|
330
|
-
op 7
|
331
333
|
S 7
|
332
|
-
|
333
|
-
set 7
|
334
|
-
sti 7
|
335
|
-
_da_ 7
|
336
|
-
o._ 7
|
337
|
-
pol 7
|
338
|
-
tem 7
|
339
|
-
et_ 7
|
340
|
-
cye_ 7
|
341
|
-
_V 7
|
342
|
-
eni 7
|
334
|
+
er_ 7
|
343
335
|
I 7
|
344
|
-
|
345
|
-
|
346
|
-
|
347
|
-
nos 7
|
336
|
+
nih_ 7
|
337
|
+
el_ 7
|
338
|
+
kih_ 7
|
348
339
|
str 7
|
349
|
-
|
340
|
+
V 7
|
341
|
+
_kr 7
|
342
|
+
nov 7
|
343
|
+
o,_ 7
|
344
|
+
_ko_ 7
|
345
|
+
pol 7
|
346
|
+
ste 7
|
347
|
+
en_ 7
|
350
348
|
ju 7
|
351
|
-
|
349
|
+
yno 7
|
350
|
+
ston_ 7
|
351
|
+
set 7
|
352
|
+
ega 7
|
353
|
+
e,_ 7
|
354
|
+
e, 7
|
355
|
+
ke_ 7
|
356
|
+
dno 7
|
357
|
+
nost 7
|
358
|
+
_ne_ 7
|
359
|
+
_zye 7
|
360
|
+
nih 7
|
361
|
+
pri 7
|
362
|
+
_a 7
|
363
|
+
_pri 7
|
364
|
+
et_ 7
|
352
365
|
ji_ 7
|
353
|
-
|
354
|
-
|
355
|
-
|
356
|
-
|
357
|
-
|
358
|
-
|
366
|
+
sti 7
|
367
|
+
_ta 7
|
368
|
+
kih 7
|
369
|
+
ton_ 7
|
370
|
+
_re 7
|
371
|
+
nos 7
|
372
|
+
i. 6
|
373
|
+
nik 6
|
374
|
+
ale 6
|
375
|
+
tk 6
|
376
|
+
di_ 6
|
377
|
+
des 6
|
378
|
+
stva 6
|
359
379
|
_raz 6
|
360
|
-
ved 6
|
361
|
-
_Wins 6
|
362
|
-
vec 6
|
363
|
-
aja 6
|
364
380
|
lad 6
|
365
|
-
|
366
|
-
eka 6
|
367
|
-
or_ 6
|
368
|
-
_a 6
|
369
|
-
_Win 6
|
370
|
-
_W 6
|
371
|
-
-- 6
|
372
|
-
va_ 6
|
373
|
-
vs 6
|
374
|
-
ale 6
|
381
|
+
ov_ 6
|
375
382
|
_pol 6
|
376
|
-
dal 6
|
377
|
-
be 6
|
378
383
|
eli 6
|
379
|
-
|
380
|
-
|
381
|
-
|
382
|
-
|
383
|
-
|
384
|
-
|
385
|
-
ston_ 6
|
386
|
-
dese 6
|
387
|
-
_ta 6
|
388
|
-
_stva 6
|
389
|
-
ecye 6
|
384
|
+
nil 6
|
385
|
+
ocye_ 6
|
386
|
+
nja 6
|
387
|
+
eka 6
|
388
|
+
gov 6
|
389
|
+
mi_ 6
|
390
390
|
yno_ 6
|
391
|
-
|
392
|
-
|
393
|
-
|
394
|
-
|
391
|
+
_stva 6
|
392
|
+
mog 6
|
393
|
+
eset 6
|
394
|
+
vec 6
|
395
|
+
stvar 6
|
395
396
|
iv 6
|
396
|
-
|
397
|
-
|
398
|
-
|
399
|
-
|
400
|
-
ki_ 6
|
397
|
+
_zap 6
|
398
|
+
red 6
|
399
|
+
zap 6
|
400
|
+
ede 6
|