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/slovak.lm
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 1388
|
2
2
|
a 370
|
3
3
|
o 334
|
4
4
|
e 307
|
@@ -10,391 +10,391 @@ t 164
|
|
10
10
|
s 161
|
11
11
|
k 150
|
12
12
|
l 150
|
13
|
-
__ 147
|
14
13
|
c 142
|
15
14
|
u 130
|
16
15
|
p 127
|
17
16
|
d 123
|
17
|
+
a_ 108
|
18
18
|
y 106
|
19
|
-
a_ 99
|
20
19
|
h 91
|
21
20
|
m 88
|
22
21
|
z 79
|
22
|
+
e_ 73
|
23
23
|
na 69
|
24
|
-
|
24
|
+
_p 68
|
25
25
|
. 62
|
26
|
-
|
27
|
-
|
26
|
+
._ 61
|
27
|
+
ov 61
|
28
|
+
_v 60
|
28
29
|
j 59
|
29
|
-
_s
|
30
|
+
_s 55
|
30
31
|
ro 53
|
31
32
|
po 52
|
32
|
-
|
33
|
+
i_ 51
|
34
|
+
o_ 50
|
33
35
|
b 49
|
34
36
|
, 46
|
35
37
|
ch 46
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
en
|
41
|
-
u_ 42
|
42
|
-
i_ 42
|
43
|
-
_n 41
|
38
|
+
_n 46
|
39
|
+
,_ 46
|
40
|
+
v_ 44
|
41
|
+
u_ 43
|
42
|
+
en 41
|
44
43
|
ne 41
|
44
|
+
_z 40
|
45
45
|
re 40
|
46
|
-
|
47
|
-
|
46
|
+
y_ 39
|
47
|
+
_a 39
|
48
|
+
h_ 38
|
48
49
|
la 38
|
50
|
+
_na 37
|
51
|
+
an 37
|
49
52
|
st 37
|
50
|
-
_a 36
|
51
|
-
y_ 34
|
52
53
|
vy 33
|
53
|
-
|
54
|
-
h_ 32
|
55
|
-
pr 31
|
54
|
+
ch_ 33
|
56
55
|
ie 31
|
56
|
+
_o 31
|
57
57
|
od 31
|
58
|
+
pr 31
|
58
59
|
ko 30
|
59
|
-
|
60
|
+
_po 29
|
60
61
|
ci 29
|
61
|
-
er
|
62
|
+
er 28
|
63
|
+
_t 28
|
64
|
+
_k 28
|
62
65
|
ti 28
|
63
|
-
al 27
|
64
|
-
_o 27
|
65
66
|
sk 27
|
66
|
-
|
67
|
-
|
68
|
-
na_
|
69
|
-
_po 26
|
67
|
+
_pr 27
|
68
|
+
al 27
|
69
|
+
na_ 27
|
70
70
|
ni 26
|
71
|
+
ed 26
|
72
|
+
ve 26
|
71
73
|
or 26
|
72
|
-
|
74
|
+
_v_ 26
|
73
75
|
yc 25
|
74
|
-
|
75
|
-
ny 25
|
76
|
-
_pr 25
|
76
|
+
ak 25
|
77
77
|
va 25
|
78
78
|
mi 25
|
79
|
-
|
80
|
-
to 24
|
81
|
-
ra 24
|
82
|
-
_k 24
|
83
|
-
in 24
|
79
|
+
ny 25
|
84
80
|
ych 24
|
85
|
-
|
81
|
+
_m 24
|
86
82
|
ho 24
|
87
|
-
|
88
|
-
|
83
|
+
ac 24
|
84
|
+
le 24
|
85
|
+
to 24
|
86
|
+
ra 24
|
89
87
|
tr 23
|
90
|
-
|
91
|
-
|
92
|
-
|
93
|
-
|
88
|
+
ad 23
|
89
|
+
in 23
|
90
|
+
_r 23
|
91
|
+
il 22
|
92
|
+
li 22
|
94
93
|
ka 22
|
95
94
|
no 22
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
_,
|
100
|
-
|
101
|
-
ok 20
|
102
|
-
ych_ 20
|
95
|
+
si 22
|
96
|
+
ych_ 22
|
97
|
+
ce 22
|
98
|
+
_, 21
|
99
|
+
_,_ 21
|
103
100
|
sa 20
|
101
|
+
it 20
|
102
|
+
ok 20
|
103
|
+
_na_ 20
|
104
|
+
om 20
|
104
105
|
te 20
|
105
|
-
_, 20
|
106
106
|
os 20
|
107
|
-
|
108
|
-
ta 19
|
109
|
-
da 19
|
107
|
+
ia 19
|
110
108
|
ku 19
|
109
|
+
da 19
|
110
|
+
ta 19
|
111
111
|
do 19
|
112
|
-
|
112
|
+
_a_ 18
|
113
113
|
za 18
|
114
114
|
es 18
|
115
|
+
S 18
|
115
116
|
me 18
|
116
|
-
ov_
|
117
|
-
|
118
|
-
|
117
|
+
ov_ 18
|
118
|
+
t_ 18
|
119
|
+
_d 17
|
120
|
+
oc 17
|
119
121
|
aj 17
|
120
122
|
ej 17
|
121
|
-
|
122
|
-
pre 16
|
123
|
+
_c 17
|
123
124
|
ky 16
|
124
|
-
|
125
|
-
_a_ 16
|
126
|
-
P 16
|
125
|
+
pre 16
|
127
126
|
ur 16
|
127
|
+
ol 16
|
128
|
+
_sa 16
|
128
129
|
on 16
|
129
|
-
av 16
|
130
130
|
el 16
|
131
131
|
at 16
|
132
|
-
|
133
|
-
|
134
|
-
|
135
|
-
vo 15
|
136
|
-
as 15
|
132
|
+
_vy 16
|
133
|
+
P 16
|
134
|
+
_b 16
|
137
135
|
rok 15
|
138
|
-
lo 15
|
139
|
-
_za 15
|
140
136
|
ri 15
|
141
|
-
|
142
|
-
|
137
|
+
_. 15
|
138
|
+
ap 15
|
143
139
|
_ro 15
|
140
|
+
vo 15
|
141
|
+
_za 15
|
142
|
+
lo 15
|
143
|
+
ic 15
|
144
|
+
sa_ 15
|
145
|
+
_pre 15
|
146
|
+
as 15
|
147
|
+
_._ 15
|
148
|
+
nyc 14
|
149
|
+
nych_ 14
|
150
|
+
av 14
|
151
|
+
l_ 14
|
152
|
+
m_ 14
|
153
|
+
ob 14
|
144
154
|
ke 14
|
145
|
-
|
155
|
+
zi 14
|
156
|
+
nych 14
|
146
157
|
D 14
|
147
|
-
_b 14
|
148
158
|
N 14
|
149
|
-
|
159
|
+
_sa_ 14
|
150
160
|
eh 14
|
151
|
-
|
152
|
-
|
153
|
-
zi 14
|
154
|
-
ob 14
|
155
|
-
nyc 14
|
156
|
-
_pre 14
|
161
|
+
_u 14
|
162
|
+
di 13
|
157
163
|
am 13
|
158
|
-
nu 13
|
159
164
|
eho 13
|
160
|
-
|
165
|
+
ne_ 13
|
166
|
+
ho_ 13
|
167
|
+
eho_ 13
|
168
|
+
ot 13
|
169
|
+
nu 13
|
161
170
|
ln 13
|
162
|
-
|
163
|
-
|
171
|
+
sp 12
|
172
|
+
dn 12
|
173
|
+
co 12
|
174
|
+
rov 12
|
164
175
|
_ak 12
|
176
|
+
pa 12
|
177
|
+
k_ 12
|
165
178
|
_do 12
|
166
|
-
|
179
|
+
_N 12
|
167
180
|
nt 12
|
168
|
-
|
169
|
-
dn 12
|
170
|
-
_u 12
|
171
|
-
co 12
|
172
|
-
sa_ 12
|
173
|
-
ne_ 12
|
174
|
-
sp 12
|
175
|
-
n_ 11
|
176
|
-
ho_ 11
|
177
|
-
l_ 11
|
178
|
-
j_ 11
|
179
|
-
ny_ 11
|
180
|
-
eho_ 11
|
181
|
-
_sa_ 11
|
182
|
-
cen 11
|
183
|
-
ovy 11
|
181
|
+
_P 12
|
184
182
|
ar 11
|
183
|
+
_tr 11
|
185
184
|
vi 11
|
186
|
-
|
185
|
+
n_ 11
|
187
186
|
kt 11
|
188
|
-
|
189
|
-
_. 11
|
187
|
+
ny_ 11
|
190
188
|
zn 11
|
191
|
-
|
192
|
-
|
193
|
-
|
194
|
-
|
195
|
-
|
196
|
-
|
197
|
-
|
189
|
+
j_ 11
|
190
|
+
az 11
|
191
|
+
r_ 11
|
192
|
+
ky_ 11
|
193
|
+
_h 10
|
194
|
+
ej_ 10
|
195
|
+
ove 10
|
198
196
|
nan 10
|
199
|
-
|
200
|
-
|
197
|
+
_Na 10
|
198
|
+
R 10
|
199
|
+
ju 10
|
200
|
+
ka_ 10
|
201
|
+
zv 10
|
201
202
|
_j 10
|
203
|
+
ik 10
|
204
|
+
ova 10
|
205
|
+
g 10
|
206
|
+
om_ 10
|
207
|
+
_ob 10
|
202
208
|
du 10
|
203
|
-
ast 10
|
204
|
-
ky_ 10
|
205
209
|
nc 10
|
206
|
-
|
207
|
-
ek 10
|
208
|
-
Na 10
|
209
|
-
ove 10
|
210
|
-
R 10
|
210
|
+
pe 10
|
211
211
|
de 10
|
212
|
-
|
213
|
-
|
214
|
-
|
215
|
-
|
216
|
-
|
212
|
+
cen 10
|
213
|
+
ovy 10
|
214
|
+
_S 10
|
215
|
+
oz 10
|
216
|
+
Na 10
|
217
|
+
ast 10
|
217
218
|
kov 9
|
218
|
-
|
219
|
+
z_ 9
|
220
|
+
pl 9
|
221
|
+
pod 9
|
219
222
|
ska 9
|
220
223
|
cov 9
|
221
|
-
|
224
|
+
li_ 9
|
222
225
|
ku_ 9
|
223
|
-
|
224
|
-
r_ 9
|
225
|
-
et 9
|
226
|
-
lad 9
|
227
|
-
uro 9
|
226
|
+
ek 9
|
228
227
|
_mi 9
|
229
|
-
|
228
|
+
uro 9
|
229
|
+
em 9
|
230
|
+
iv 9
|
231
|
+
lad 9
|
232
|
+
_ce 9
|
233
|
+
la_ 9
|
234
|
+
_V 9
|
235
|
+
ti_ 9
|
236
|
+
_l 9
|
230
237
|
f 9
|
231
|
-
|
238
|
+
tor 9
|
239
|
+
V 9
|
240
|
+
kl 9
|
232
241
|
je 9
|
233
|
-
|
234
|
-
|
235
|
-
|
236
|
-
|
237
|
-
_S 8
|
238
|
-
en_ 8
|
239
|
-
trh 8
|
240
|
-
ia_ 8
|
242
|
+
_sp 8
|
243
|
+
_pred 8
|
244
|
+
U 8
|
245
|
+
ent 8
|
241
246
|
vn 8
|
242
|
-
|
247
|
+
en_ 8
|
248
|
+
uc 8
|
243
249
|
pri 8
|
250
|
+
est 8
|
251
|
+
tu 8
|
252
|
+
ani 8
|
253
|
+
mi_ 8
|
254
|
+
_ur 8
|
244
255
|
ys 8
|
245
|
-
|
246
|
-
st_ 8
|
247
|
-
_trh 8
|
256
|
+
trh 8
|
248
257
|
ske 8
|
249
|
-
|
250
|
-
|
251
|
-
sl 8
|
252
|
-
uc 8
|
253
|
-
red 8
|
258
|
+
pred 8
|
259
|
+
et 8
|
254
260
|
_U 8
|
255
|
-
ti_ 8
|
256
|
-
vys 8
|
257
|
-
rh 8
|
258
|
-
_sp 8
|
259
|
-
est 8
|
260
|
-
M 8
|
261
261
|
Po 8
|
262
|
-
|
262
|
+
sl 8
|
263
263
|
_rok 8
|
264
|
-
|
265
|
-
tu 8
|
264
|
+
_trh 8
|
266
265
|
ie_ 8
|
267
|
-
|
268
|
-
|
269
|
-
|
270
|
-
|
271
|
-
|
272
|
-
|
273
|
-
|
274
|
-
|
275
|
-
|
276
|
-
|
277
|
-
|
278
|
-
|
279
|
-
|
280
|
-
|
281
|
-
nu_ 7
|
266
|
+
ina 8
|
267
|
+
M 8
|
268
|
+
_e 8
|
269
|
+
red 8
|
270
|
+
nej 8
|
271
|
+
ca 8
|
272
|
+
vys 8
|
273
|
+
st_ 8
|
274
|
+
_zv 8
|
275
|
+
rh 8
|
276
|
+
_Po 8
|
277
|
+
ze 8
|
278
|
+
ia_ 8
|
279
|
+
mo 7
|
282
280
|
kc 7
|
283
|
-
|
284
|
-
_Po 7
|
285
|
-
akc 7
|
286
|
-
_akci 7
|
287
|
-
SD 7
|
288
|
-
_ce 7
|
289
|
-
spo 7
|
290
|
-
br 7
|
291
|
-
_USD 7
|
292
|
-
ud 7
|
293
|
-
up 7
|
294
|
-
ec 7
|
281
|
+
_uro 7
|
295
282
|
hod 7
|
296
|
-
sti 7
|
297
|
-
US 7
|
298
|
-
_l 7
|
299
283
|
_akc 7
|
300
|
-
eni 7
|
301
|
-
ost 7
|
302
|
-
er_ 7
|
303
|
-
z_ 7
|
304
|
-
neh 7
|
305
284
|
ru 7
|
306
|
-
|
285
|
+
neho_ 7
|
286
|
+
uj 7
|
287
|
+
US 7
|
288
|
+
neh 7
|
289
|
+
sti 7
|
290
|
+
su 7
|
291
|
+
ati 7
|
292
|
+
_cen 7
|
293
|
+
_i 7
|
307
294
|
_ne 7
|
308
|
-
|
295
|
+
te_ 7
|
296
|
+
ns 7
|
297
|
+
ost 7
|
298
|
+
akc 7
|
299
|
+
ali 7
|
300
|
+
ud 7
|
301
|
+
_pod 7
|
302
|
+
ec 7
|
303
|
+
USD 7
|
304
|
+
eni 7
|
305
|
+
_me 7
|
306
|
+
oro 7
|
307
|
+
spo 7
|
308
|
+
_USD 7
|
309
309
|
kci 7
|
310
|
-
|
311
|
-
|
310
|
+
akci 7
|
311
|
+
to_ 7
|
312
|
+
_D 7
|
313
|
+
er_ 7
|
314
|
+
SD 7
|
315
|
+
_akci 7
|
316
|
+
is 7
|
317
|
+
ep 7
|
318
|
+
van 7
|
319
|
+
up 7
|
320
|
+
_pri 7
|
321
|
+
_US 7
|
312
322
|
neho 7
|
313
|
-
|
314
|
-
|
315
|
-
|
316
|
-
|
317
|
-
|
318
|
-
|
323
|
+
br 7
|
324
|
+
nu_ 7
|
325
|
+
osl 6
|
326
|
+
rod 6
|
327
|
+
ly 6
|
328
|
+
ni_ 6
|
329
|
+
ast_ 6
|
330
|
+
sil 6
|
331
|
+
ja 6
|
332
|
+
roku 6
|
333
|
+
odn 6
|
334
|
+
by 6
|
335
|
+
ska_ 6
|
319
336
|
re_ 6
|
337
|
+
tre 6
|
338
|
+
nsk 6
|
339
|
+
_pos 6
|
340
|
+
_st 6
|
341
|
+
kon 6
|
320
342
|
us 6
|
321
|
-
|
322
|
-
|
323
|
-
|
324
|
-
|
343
|
+
alo 6
|
344
|
+
mie 6
|
345
|
+
nej_ 6
|
346
|
+
ach 6
|
325
347
|
u. 6
|
326
|
-
|
327
|
-
|
328
|
-
|
329
|
-
|
348
|
+
je_ 6
|
349
|
+
ii 6
|
350
|
+
e. 6
|
351
|
+
sta 6
|
352
|
+
_pl 6
|
353
|
+
u._ 6
|
354
|
+
cho 6
|
355
|
+
_C 6
|
356
|
+
ri_ 6
|
330
357
|
ty 6
|
358
|
+
C 6
|
359
|
+
tn 6
|
331
360
|
ke_ 6
|
332
|
-
|
333
|
-
pos 6
|
334
|
-
ly 6
|
335
|
-
por 6
|
336
|
-
ore 6
|
337
|
-
nov 6
|
338
|
-
_st 6
|
339
|
-
il_ 6
|
340
|
-
cii 6
|
341
|
-
he 6
|
342
|
-
nsk 6
|
361
|
+
_o_ 6
|
343
362
|
_ku 6
|
344
|
-
|
363
|
+
he 6
|
345
364
|
tiv 6
|
346
|
-
|
347
|
-
|
348
|
-
|
349
|
-
|
350
|
-
oku_ 6
|
351
|
-
zac 6
|
352
|
-
_pod 6
|
353
|
-
osl 6
|
354
|
-
e. 6
|
365
|
+
ore 6
|
366
|
+
aci 6
|
367
|
+
cii 6
|
368
|
+
_M 6
|
355
369
|
otr 6
|
356
|
-
|
357
|
-
|
358
|
-
mie 6
|
359
|
-
sil 6
|
360
|
-
iny 6
|
361
|
-
ach 6
|
370
|
+
V_ 6
|
371
|
+
roku_ 6
|
362
372
|
hr 6
|
363
|
-
|
364
|
-
|
365
|
-
kon 6
|
366
|
-
aci 6
|
367
|
-
C 6
|
368
|
-
_me 6
|
369
|
-
tn 6
|
370
|
-
ja 6
|
371
|
-
J 6
|
372
|
-
ii 6
|
373
|
-
rod 6
|
373
|
+
oku 6
|
374
|
+
e._ 6
|
374
375
|
eb 6
|
375
|
-
ni_ 6
|
376
376
|
F 6
|
377
|
-
|
378
|
-
|
379
|
-
|
380
|
-
|
381
|
-
|
382
|
-
|
383
|
-
|
384
|
-
|
385
|
-
|
386
|
-
|
387
|
-
|
388
|
-
|
377
|
+
pos 6
|
378
|
+
_su 6
|
379
|
+
por 6
|
380
|
+
cie 6
|
381
|
+
ele 6
|
382
|
+
_V_ 6
|
383
|
+
iny_ 6
|
384
|
+
sti_ 6
|
385
|
+
iny 6
|
386
|
+
zac 6
|
387
|
+
J 6
|
388
|
+
oku_ 6
|
389
|
+
id 6
|
390
|
+
sia 6
|
391
|
+
_vo 6
|
392
|
+
nov 6
|
393
|
+
nom 5
|
394
|
+
vyr 5
|
389
395
|
dol 5
|
390
|
-
|
391
|
-
|
392
|
-
|
393
|
-
|
394
|
-
|
395
|
-
anc 5
|
396
|
-
hra 5
|
397
|
-
_oc 5
|
398
|
-
uk 5
|
399
|
-
ska_ 5
|
400
|
-
za_ 5
|
396
|
+
dz 5
|
397
|
+
potr 5
|
398
|
+
oven 5
|
399
|
+
naj 5
|
400
|
+
bc 5
|