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/romanian.lm
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 1680
|
2
2
|
a 539
|
3
3
|
i 460
|
4
4
|
e 442
|
@@ -9,392 +9,392 @@ u 220
|
|
9
9
|
c 200
|
10
10
|
s 194
|
11
11
|
o 188
|
12
|
+
e_ 186
|
12
13
|
l 174
|
13
|
-
|
14
|
-
|
14
|
+
a_ 172
|
15
|
+
i_ 123
|
15
16
|
d 115
|
16
17
|
m 114
|
17
18
|
p 113
|
18
|
-
i_ 112
|
19
19
|
in 101
|
20
|
-
_c
|
20
|
+
_c 99
|
21
|
+
_s 88
|
21
22
|
ar 87
|
22
|
-
|
23
|
+
_d 77
|
24
|
+
_a 73
|
23
25
|
re 71
|
24
|
-
|
26
|
+
,_ 66
|
25
27
|
, 66
|
26
|
-
_a 64
|
27
28
|
de 64
|
28
|
-
|
29
|
-
|
29
|
+
_p 64
|
30
|
+
ra 62
|
31
|
+
at 61
|
30
32
|
f 57
|
31
|
-
|
32
|
-
|
33
|
-
st 53
|
33
|
+
n_ 54
|
34
|
+
_i 54
|
34
35
|
ta 53
|
36
|
+
st 53
|
35
37
|
ti 51
|
36
|
-
n_ 50
|
37
|
-
ca 50
|
38
38
|
te 50
|
39
|
+
ca 50
|
40
|
+
u_ 48
|
39
41
|
si 47
|
40
|
-
|
42
|
+
_de 47
|
41
43
|
un 45
|
42
|
-
|
43
|
-
|
44
|
+
de_ 43
|
45
|
+
_o 43
|
44
46
|
g 42
|
47
|
+
_m 42
|
48
|
+
_in 42
|
45
49
|
ce 41
|
46
50
|
ri 41
|
47
|
-
_m 41
|
48
51
|
nt 41
|
49
52
|
ul 40
|
50
|
-
b 39
|
51
53
|
or 39
|
52
|
-
|
53
|
-
|
54
|
-
|
55
|
-
|
54
|
+
_ca 39
|
55
|
+
b 39
|
56
|
+
es 38
|
57
|
+
_de_ 38
|
56
58
|
la 37
|
57
|
-
ma 37
|
58
59
|
are 37
|
59
|
-
|
60
|
-
|
60
|
+
t_ 37
|
61
|
+
ma 35
|
62
|
+
_f 35
|
61
63
|
tr 34
|
62
64
|
. 34
|
65
|
+
_si 34
|
63
66
|
ci 33
|
64
|
-
_f 33
|
65
67
|
ea 33
|
68
|
+
l_ 32
|
69
|
+
._ 32
|
66
70
|
el 32
|
67
|
-
|
68
|
-
ni 30
|
69
|
-
oa 30
|
71
|
+
ta_ 32
|
70
72
|
ia 30
|
71
|
-
|
72
|
-
|
73
|
+
si_ 30
|
74
|
+
oa 30
|
75
|
+
in_ 30
|
76
|
+
te_ 30
|
77
|
+
ni 29
|
73
78
|
se 29
|
74
|
-
|
79
|
+
_t 29
|
80
|
+
re_ 29
|
81
|
+
v 29
|
82
|
+
_l 29
|
83
|
+
_u 29
|
75
84
|
cu 29
|
76
|
-
|
77
|
-
_si 28
|
78
|
-
_u 28
|
79
|
-
l_ 27
|
80
|
-
as 27
|
85
|
+
_si_ 28
|
81
86
|
z 27
|
82
|
-
re_ 27
|
83
|
-
ac 26
|
84
|
-
si_ 26
|
85
|
-
ic 26
|
86
|
-
_l 26
|
87
|
-
le 26
|
88
|
-
ne 26
|
89
87
|
an 26
|
90
|
-
|
88
|
+
as 26
|
89
|
+
ne 26
|
90
|
+
le 26
|
91
|
+
ic 25
|
91
92
|
pe 25
|
92
|
-
|
93
|
-
|
94
|
-
|
95
|
-
_un 24
|
96
|
-
er 24
|
93
|
+
_un 25
|
94
|
+
are_ 25
|
95
|
+
ac 24
|
97
96
|
int 24
|
98
|
-
|
97
|
+
er 24
|
98
|
+
li 24
|
99
|
+
_e 23
|
99
100
|
lu 23
|
100
|
-
|
101
|
-
|
102
|
-
|
103
|
-
ste 22
|
101
|
+
est 23
|
102
|
+
_ma 23
|
103
|
+
ei 22
|
104
104
|
la_ 22
|
105
|
+
ste 22
|
105
106
|
pa 22
|
107
|
+
_pe 21
|
108
|
+
r_ 21
|
106
109
|
car 21
|
107
|
-
|
110
|
+
sa 21
|
111
|
+
_n 21
|
112
|
+
e, 20
|
108
113
|
na 20
|
109
|
-
_e 20
|
110
|
-
il 20
|
111
114
|
al 20
|
112
|
-
e, 20
|
113
|
-
|
114
|
-
|
115
|
+
e,_ 20
|
116
|
+
it 20
|
117
|
+
_cu 20
|
118
|
+
ie 20
|
115
119
|
ai 19
|
120
|
+
en 19
|
116
121
|
da 19
|
117
|
-
|
118
|
-
_pe 19
|
119
|
-
_n 19
|
122
|
+
o_ 19
|
120
123
|
care 19
|
121
|
-
|
122
|
-
|
123
|
-
|
124
|
-
|
125
|
-
ara 18
|
126
|
-
ata 18
|
127
|
-
ap 18
|
128
|
-
o_ 18
|
124
|
+
il 19
|
125
|
+
ii 19
|
126
|
+
to 19
|
127
|
+
_o_ 18
|
129
128
|
cu_ 18
|
129
|
+
este 18
|
130
130
|
au 18
|
131
|
+
_in_ 18
|
132
|
+
ra_ 18
|
133
|
+
ui 18
|
134
|
+
care_ 18
|
135
|
+
ul_ 17
|
136
|
+
ata 17
|
137
|
+
un_ 17
|
138
|
+
ara 17
|
139
|
+
_se 17
|
140
|
+
lo 17
|
131
141
|
am 17
|
132
|
-
|
133
|
-
|
142
|
+
se_ 17
|
143
|
+
D 17
|
134
144
|
me 17
|
145
|
+
_cu_ 17
|
135
146
|
_car 17
|
136
|
-
|
137
|
-
|
138
|
-
r_ 17
|
139
|
-
ra_ 16
|
140
|
-
om 16
|
141
|
-
ru 16
|
142
|
-
sa_ 16
|
143
|
-
fa 16
|
147
|
+
_b 16
|
148
|
+
pe_ 16
|
144
149
|
pr 16
|
145
150
|
co 16
|
146
|
-
|
151
|
+
om 16
|
152
|
+
_v 16
|
153
|
+
ste_ 16
|
154
|
+
este_ 16
|
155
|
+
fa 16
|
147
156
|
_care 16
|
148
|
-
care_ 16
|
149
|
-
un_ 16
|
150
|
-
pe_ 15
|
151
|
-
_cu_ 15
|
152
|
-
a, 15
|
153
|
-
ste_ 15
|
154
|
-
e,_ 15
|
155
|
-
ul_ 15
|
156
157
|
h 15
|
157
|
-
este_ 15
|
158
|
-
_o_ 15
|
159
158
|
rt 15
|
160
|
-
|
161
|
-
|
162
|
-
|
159
|
+
ru 15
|
160
|
+
_sa 15
|
161
|
+
ap 15
|
162
|
+
ata_ 15
|
163
|
+
_ce 15
|
164
|
+
nu 14
|
165
|
+
sa_ 14
|
166
|
+
a,_ 14
|
167
|
+
ei_ 14
|
168
|
+
ace 14
|
169
|
+
ui_ 14
|
170
|
+
tu 14
|
171
|
+
le_ 14
|
172
|
+
a, 14
|
163
173
|
tra 14
|
164
174
|
ur 14
|
175
|
+
_pe_ 14
|
165
176
|
ca_ 14
|
166
|
-
ei_ 14
|
167
|
-
le_ 14
|
168
|
-
_se 14
|
169
|
-
nu 14
|
170
|
-
is 14
|
171
|
-
tu 14
|
172
|
-
ace 14
|
173
|
-
ata_ 14
|
174
|
-
_v 14
|
175
177
|
io 13
|
176
|
-
|
177
|
-
|
178
|
-
ot 13
|
178
|
+
zi 13
|
179
|
+
au_ 13
|
179
180
|
sc 13
|
181
|
+
_la 13
|
182
|
+
ot 13
|
183
|
+
mi 13
|
180
184
|
lui 13
|
181
|
-
zi 13
|
182
185
|
mu 13
|
183
|
-
|
184
|
-
|
185
|
-
|
186
|
-
|
186
|
+
is 13
|
187
|
+
na_ 13
|
188
|
+
ii_ 12
|
189
|
+
_D 12
|
187
190
|
oar 12
|
191
|
+
_ac 12
|
192
|
+
po 12
|
188
193
|
nd 12
|
189
|
-
|
190
|
-
_fa 12
|
191
|
-
ec 12
|
194
|
+
pi 12
|
192
195
|
os 12
|
196
|
+
ele 12
|
197
|
+
fe 12
|
193
198
|
_un_ 12
|
199
|
+
_se_ 12
|
200
|
+
_a_ 12
|
201
|
+
_fa 12
|
194
202
|
ut 12
|
203
|
+
_r 12
|
204
|
+
ia_ 12
|
205
|
+
ea_ 12
|
195
206
|
ve 12
|
196
|
-
|
197
|
-
ui_ 12
|
207
|
+
ci_ 12
|
198
208
|
bi 12
|
199
|
-
|
200
|
-
|
201
|
-
|
202
|
-
ii_ 12
|
203
|
-
_r 11
|
209
|
+
di 11
|
210
|
+
_ca_ 11
|
211
|
+
ne_ 11
|
204
212
|
ir 11
|
205
|
-
|
206
|
-
ci_ 11
|
207
|
-
tat 11
|
208
|
-
_se_ 11
|
213
|
+
fo 11
|
209
214
|
et 11
|
215
|
+
ent 11
|
216
|
+
tat 11
|
217
|
+
_int 11
|
210
218
|
E 11
|
211
219
|
um 11
|
212
|
-
|
213
|
-
|
214
|
-
|
215
|
-
|
216
|
-
|
217
|
-
pu 10
|
218
|
-
_co 10
|
219
|
-
cel 10
|
220
|
-
_est 10
|
221
|
-
ne_ 10
|
220
|
+
_co 11
|
221
|
+
_la_ 11
|
222
|
+
ce_ 10
|
223
|
+
_sa_ 10
|
224
|
+
m_ 10
|
222
225
|
at_ 10
|
223
|
-
_este 10
|
224
|
-
ai_ 10
|
225
|
-
op 10
|
226
226
|
_pa 10
|
227
|
-
ol 10
|
228
|
-
im 10
|
229
227
|
ulu 10
|
228
|
+
ol 10
|
230
229
|
ga 10
|
230
|
+
ntr 10
|
231
|
+
ai_ 10
|
232
|
+
pu 10
|
233
|
+
_este 10
|
234
|
+
ec 10
|
235
|
+
op 10
|
231
236
|
i, 10
|
232
|
-
|
237
|
+
_est 10
|
238
|
+
lui_ 10
|
233
239
|
ici 10
|
234
|
-
|
235
|
-
|
240
|
+
im 10
|
241
|
+
cel 10
|
242
|
+
_es 10
|
243
|
+
i,_ 10
|
244
|
+
_nu 10
|
236
245
|
_ar 9
|
237
|
-
|
246
|
+
ara_ 9
|
247
|
+
hi 9
|
248
|
+
_po 9
|
249
|
+
_g 9
|
250
|
+
mo 9
|
238
251
|
iu 9
|
239
|
-
|
252
|
+
_da 9
|
253
|
+
ului 9
|
254
|
+
A 9
|
255
|
+
ori 9
|
240
256
|
sta 9
|
241
|
-
mo 9
|
242
|
-
id 9
|
243
257
|
ns 9
|
258
|
+
su 9
|
259
|
+
_fo 9
|
260
|
+
or_ 9
|
261
|
+
ele_ 9
|
244
262
|
on 9
|
245
|
-
_ca_ 9
|
246
263
|
ati 9
|
247
|
-
ori 9
|
248
|
-
or_ 9
|
249
|
-
ului 9
|
250
|
-
_la_ 9
|
251
|
-
_nu 9
|
252
264
|
_di 9
|
253
|
-
|
254
|
-
A 9
|
255
|
-
lui_ 9
|
256
|
-
_D 9
|
257
|
-
i. 8
|
258
|
-
i,_ 8
|
259
|
-
ad 8
|
260
|
-
ce_ 8
|
261
|
-
mai 8
|
262
|
-
tie 8
|
263
|
-
nc 8
|
264
|
-
ate 8
|
265
|
-
ng 8
|
266
|
-
_a_ 8
|
267
|
-
str 8
|
268
|
-
mai_ 8
|
269
|
-
lt 8
|
265
|
+
s_ 8
|
270
266
|
lor 8
|
267
|
+
_st 8
|
268
|
+
une 8
|
269
|
+
ini 8
|
271
270
|
nic 8
|
272
|
-
|
273
|
-
em 8
|
274
|
-
ia_ 8
|
271
|
+
mai_ 8
|
275
272
|
mul 8
|
276
|
-
|
277
|
-
|
278
|
-
|
279
|
-
|
280
|
-
|
281
|
-
|
273
|
+
mar 8
|
274
|
+
_pr 8
|
275
|
+
nc 8
|
276
|
+
em 8
|
277
|
+
tru 8
|
278
|
+
ng 8
|
282
279
|
gi 8
|
283
|
-
|
284
|
-
par 8
|
285
|
-
_lu 8
|
286
|
-
ara_ 8
|
280
|
+
I 8
|
287
281
|
ine 8
|
288
|
-
|
289
|
-
|
290
|
-
|
282
|
+
mai 8
|
283
|
+
ti_ 8
|
284
|
+
ate 8
|
285
|
+
ost 8
|
286
|
+
par 8
|
287
|
+
_tr 8
|
288
|
+
tie 8
|
289
|
+
dat 8
|
291
290
|
_ace 8
|
292
|
-
|
293
|
-
|
294
|
-
|
295
|
-
|
296
|
-
|
297
|
-
|
298
|
-
|
299
|
-
|
300
|
-
|
301
|
-
|
291
|
+
i._ 8
|
292
|
+
_or 8
|
293
|
+
_E 8
|
294
|
+
str 8
|
295
|
+
nu_ 8
|
296
|
+
oc 8
|
297
|
+
_lu 8
|
298
|
+
i. 8
|
299
|
+
una 7
|
300
|
+
ind 7
|
301
|
+
sin 7
|
302
302
|
_mai 7
|
303
|
+
do 7
|
304
|
+
ar_ 7
|
305
|
+
j 7
|
306
|
+
_nu_ 7
|
303
307
|
far 7
|
304
|
-
|
305
|
-
|
306
|
-
_da 7
|
307
|
-
pl 7
|
308
|
+
c_ 7
|
309
|
+
it_ 7
|
308
310
|
_mai_ 7
|
309
|
-
|
310
|
-
una 7
|
311
|
-
_din 7
|
312
|
-
_ci 7
|
313
|
-
m_ 7
|
314
|
-
pri 7
|
311
|
+
mp 7
|
315
312
|
ator 7
|
316
|
-
az 7
|
317
|
-
rea 7
|
318
313
|
res 7
|
314
|
+
tor 7
|
315
|
+
_din 7
|
316
|
+
az 7
|
317
|
+
ie_ 7
|
318
|
+
din 7
|
319
|
+
tul 7
|
320
|
+
pl 7
|
321
|
+
nta 7
|
322
|
+
art 7
|
323
|
+
ina 7
|
319
324
|
ani 7
|
320
|
-
sin 7
|
321
325
|
ato 7
|
322
|
-
|
326
|
+
lt 7
|
327
|
+
min 7
|
328
|
+
tin 7
|
329
|
+
esc 7
|
323
330
|
ran 7
|
324
|
-
|
325
|
-
|
331
|
+
cr 7
|
332
|
+
pri 7
|
333
|
+
fi 7
|
334
|
+
rea 7
|
326
335
|
ilo 7
|
327
|
-
|
328
|
-
|
329
|
-
|
330
|
-
|
331
|
-
|
332
|
-
ez 6
|
333
|
-
C 6
|
334
|
-
lor_ 6
|
335
|
-
nde 6
|
336
|
-
it_ 6
|
337
|
-
pin 6
|
338
|
-
ag 6
|
339
|
-
ie_ 6
|
340
|
-
nei 6
|
341
|
-
eri 6
|
336
|
+
_ci 7
|
337
|
+
man 6
|
338
|
+
og 6
|
339
|
+
rul 6
|
340
|
+
lin 6
|
342
341
|
_pu 6
|
343
|
-
|
344
|
-
|
345
|
-
|
346
|
-
tot 6
|
347
|
-
s_ 6
|
342
|
+
pt 6
|
343
|
+
_z 6
|
344
|
+
_to 6
|
348
345
|
da_ 6
|
349
|
-
|
350
|
-
gr 6
|
351
|
-
ric 6
|
352
|
-
rti 6
|
353
|
-
ra,_ 6
|
346
|
+
_ve 6
|
354
347
|
so 6
|
355
|
-
|
356
|
-
bo 6
|
357
|
-
rul 6
|
348
|
+
tre 6
|
358
349
|
ch 6
|
350
|
+
imp 6
|
351
|
+
_do 6
|
352
|
+
tot 6
|
353
|
+
pin 6
|
354
|
+
ului_ 6
|
355
|
+
lor_ 6
|
356
|
+
oas 6
|
357
|
+
S 6
|
358
|
+
vi 6
|
359
|
+
nti 6
|
360
|
+
esc_ 6
|
359
361
|
_op 6
|
360
|
-
|
361
|
-
ari 6
|
362
|
+
ra,_ 6
|
362
363
|
_ti 6
|
364
|
+
ag 6
|
365
|
+
nde 6
|
366
|
+
gr 6
|
363
367
|
intr 6
|
364
|
-
|
365
|
-
|
368
|
+
_mu 6
|
369
|
+
ari 6
|
370
|
+
st_ 6
|
371
|
+
nta_ 6
|
372
|
+
ez 6
|
373
|
+
_au_ 6
|
374
|
+
ro 6
|
375
|
+
up 6
|
376
|
+
ba 6
|
377
|
+
rm 6
|
378
|
+
ge 6
|
379
|
+
ad 6
|
380
|
+
iat 6
|
381
|
+
ast 6
|
366
382
|
iv 6
|
367
|
-
e. 6
|
368
|
-
imp 6
|
369
383
|
oare 6
|
370
|
-
|
371
|
-
|
372
|
-
|
384
|
+
ina_ 6
|
385
|
+
id 6
|
386
|
+
no 6
|
387
|
+
_mar 6
|
388
|
+
omu 6
|
373
389
|
ate_ 6
|
390
|
+
eri 6
|
391
|
+
bo 6
|
392
|
+
sc_ 6
|
393
|
+
rti 6
|
374
394
|
_cel 6
|
375
|
-
|
376
|
-
|
377
|
-
tre 6
|
378
|
-
_po 6
|
379
|
-
vi 6
|
380
|
-
_st 6
|
381
|
-
og 6
|
382
|
-
ast 6
|
383
|
-
rm 6
|
384
|
-
man 6
|
385
|
-
_mar 6
|
386
|
-
ilor 6
|
395
|
+
_mo 6
|
396
|
+
_ra 6
|
387
397
|
ra, 6
|
388
|
-
|
389
|
-
|
390
|
-
|
391
|
-
_to 6
|
392
|
-
up 6
|
393
|
-
nti 6
|
394
|
-
P 5
|
395
|
-
ing 5
|
396
|
-
ora 5
|
397
|
-
rat 5
|
398
|
-
_al 5
|
399
|
-
ril 5
|
400
|
-
ult 5
|
398
|
+
_au 6
|
399
|
+
C 6
|
400
|
+
ilor 6
|