scylla 0.7.0 → 0.7.5
Sign up to get free protection for your applications and to get access to all the features.
- 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/english.lm
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 3692
|
2
2
|
e 1020
|
3
3
|
n 845
|
4
4
|
a 787
|
@@ -10,7 +10,7 @@ r 545
|
|
10
10
|
l 453
|
11
11
|
h 416
|
12
12
|
d 352
|
13
|
-
e_
|
13
|
+
e_ 343
|
14
14
|
g 317
|
15
15
|
c 303
|
16
16
|
an 270
|
@@ -21,380 +21,380 @@ m 213
|
|
21
21
|
f 206
|
22
22
|
ng 201
|
23
23
|
in 195
|
24
|
-
s_
|
24
|
+
s_ 194
|
25
25
|
_th 193
|
26
26
|
he 191
|
27
|
-
_a
|
28
|
-
d_
|
27
|
+
_a 190
|
28
|
+
d_ 188
|
29
29
|
the 168
|
30
|
-
n_
|
30
|
+
n_ 166
|
31
31
|
he_ 157
|
32
32
|
_the 152
|
33
33
|
er 146
|
34
|
-
the_ 143
|
35
34
|
_the_ 143
|
35
|
+
the_ 143
|
36
36
|
w 134
|
37
|
-
, 132
|
38
37
|
,_ 132
|
38
|
+
, 132
|
39
39
|
is 131
|
40
|
-
_o
|
40
|
+
_o 130
|
41
41
|
nd 126
|
42
42
|
p 126
|
43
|
-
|
44
|
-
|
45
|
-
es
|
43
|
+
_i 114
|
44
|
+
h_ 114
|
45
|
+
es 110
|
46
46
|
on 105
|
47
|
-
y 102
|
48
47
|
ti 102
|
48
|
+
y 102
|
49
49
|
v 99
|
50
50
|
and 98
|
51
51
|
nd_ 97
|
52
|
-
re 96
|
53
52
|
en 96
|
54
|
-
|
53
|
+
re 96
|
55
54
|
la 93
|
55
|
+
of 93
|
56
|
+
t_ 93
|
56
57
|
f_ 93
|
57
58
|
or 92
|
58
59
|
at 92
|
59
60
|
_of 91
|
60
|
-
t_ 90
|
61
61
|
of_ 89
|
62
62
|
_of_ 89
|
63
63
|
li 89
|
64
64
|
and_ 88
|
65
|
-
|
66
|
-
_an
|
65
|
+
_s 87
|
66
|
+
_an 85
|
67
|
+
_l 85
|
67
68
|
b 83
|
68
69
|
gl 81
|
69
|
-
_in
|
70
|
+
_in 81
|
71
|
+
_w 80
|
70
72
|
ed 79
|
71
|
-
|
72
|
-
_and 78
|
73
|
-
_s 78
|
73
|
+
al 78
|
74
74
|
_and_ 78
|
75
75
|
ngl 78
|
76
|
-
|
76
|
+
_and 78
|
77
|
+
_E 77
|
77
78
|
E 77
|
79
|
+
y_ 76
|
78
80
|
. 74
|
79
|
-
_E 74
|
80
81
|
sh 73
|
81
82
|
om 72
|
82
|
-
y_ 72
|
83
83
|
ro 71
|
84
84
|
ic 70
|
85
|
+
_c 70
|
85
86
|
ish 69
|
86
|
-
|
87
|
-
_c 69
|
87
|
+
o_ 69
|
88
88
|
ri 69
|
89
|
-
|
90
|
-
|
91
|
-
nt 67
|
89
|
+
._ 69
|
90
|
+
te 69
|
92
91
|
ma 67
|
92
|
+
nt 67
|
93
|
+
as 67
|
94
|
+
ce 67
|
93
95
|
ve 66
|
94
|
-
Engl 65
|
95
96
|
Eng 65
|
97
|
+
_Eng 65
|
98
|
+
_En 65
|
96
99
|
En 65
|
97
|
-
|
98
|
-
|
99
|
-
_Engl 64
|
100
|
+
_Engl 65
|
101
|
+
Engl 65
|
100
102
|
st 64
|
101
103
|
ing 63
|
102
104
|
ar 62
|
103
105
|
lan 62
|
104
106
|
ge 61
|
107
|
+
gli 60
|
105
108
|
lis 60
|
106
109
|
ed_ 60
|
107
110
|
ngli 60
|
108
|
-
|
109
|
-
nglis 59
|
111
|
+
le 59
|
110
112
|
Engli 59
|
113
|
+
nglis 59
|
111
114
|
glis 59
|
112
|
-
le 59
|
113
|
-
lish 58
|
114
115
|
glish 58
|
116
|
+
lish 58
|
115
117
|
co 58
|
116
|
-
|
118
|
+
in_ 58
|
117
119
|
_la 57
|
118
|
-
|
120
|
+
ua 57
|
119
121
|
it 56
|
120
|
-
o_ 56
|
121
122
|
nc 55
|
123
|
+
r_ 55
|
122
124
|
gu 54
|
123
|
-
r_ 54
|
124
125
|
to 54
|
125
|
-
|
126
|
+
sh_ 53
|
126
127
|
_b 53
|
127
|
-
|
128
|
-
|
129
|
-
|
128
|
+
ish_ 53
|
129
|
+
ngu 53
|
130
|
+
g_ 52
|
131
|
+
ngua 51
|
130
132
|
gua 51
|
133
|
+
_d 51
|
131
134
|
ni 51
|
132
|
-
- 51
|
133
135
|
es_ 51
|
134
|
-
|
135
|
-
_d 51
|
136
|
-
ang 50
|
136
|
+
ng_ 51
|
137
137
|
io 50
|
138
138
|
rm 50
|
139
|
+
ang 50
|
139
140
|
man 50
|
141
|
+
to_ 49
|
140
142
|
se 49
|
141
143
|
ag 49
|
142
|
-
ng_ 48
|
143
|
-
g_ 48
|
144
|
-
_f 47
|
145
144
|
age 47
|
145
|
+
_f 47
|
146
146
|
l_ 47
|
147
147
|
_lan 46
|
148
|
-
to_ 46
|
149
148
|
lang 46
|
150
|
-
|
149
|
+
lish_ 45
|
151
150
|
ati 45
|
152
|
-
|
153
|
-
|
151
|
+
angua 45
|
152
|
+
_e 45
|
153
|
+
nguag 45
|
154
154
|
_lang 45
|
155
|
+
uage 45
|
155
156
|
guag 45
|
156
|
-
guage 45
|
157
157
|
uag 45
|
158
|
+
langu 45
|
159
|
+
guage 45
|
158
160
|
angu 45
|
159
|
-
nguag 45
|
160
|
-
lish_ 44
|
161
161
|
ion 44
|
162
|
-
ur 44
|
163
162
|
a_ 44
|
164
|
-
|
163
|
+
ur 44
|
165
164
|
di 43
|
166
|
-
|
165
|
+
el 43
|
167
166
|
rma 42
|
168
167
|
_p 42
|
168
|
+
ea 42
|
169
|
+
ing_ 42
|
170
|
+
as_ 41
|
169
171
|
_to 41
|
170
172
|
_to_ 41
|
171
|
-
as_ 41
|
172
|
-
ca 40
|
173
173
|
_in_ 40
|
174
|
-
th_
|
174
|
+
th_ 40
|
175
|
+
ca 40
|
176
|
+
an_ 40
|
175
177
|
_r 39
|
176
|
-
__ 39
|
177
|
-
ing_ 39
|
178
|
-
ia 38
|
179
|
-
an_ 38
|
180
|
-
ra 38
|
181
178
|
rman 38
|
179
|
+
ra 38
|
180
|
+
ia 38
|
181
|
+
_co 38
|
182
182
|
ha 37
|
183
|
-
_co 37
|
184
|
-
_e 37
|
185
183
|
me 37
|
184
|
+
m_ 36
|
185
|
+
lo 36
|
186
186
|
G 36
|
187
187
|
si 36
|
188
|
-
|
189
|
-
m_ 35
|
188
|
+
_G 36
|
190
189
|
ll 35
|
191
|
-
ec 35
|
192
|
-
fr 35
|
193
190
|
de 35
|
194
|
-
|
195
|
-
|
191
|
+
fr 35
|
192
|
+
ec 35
|
193
|
+
erm 34
|
194
|
+
on_ 34
|
196
195
|
ow 34
|
196
|
+
s, 34
|
197
|
+
er_ 34
|
197
198
|
s,_ 34
|
198
|
-
erm 34
|
199
199
|
ly 34
|
200
200
|
k 33
|
201
|
-
er_ 33
|
202
201
|
al_ 33
|
203
|
-
|
204
|
-
tion 32
|
205
|
-
ou 32
|
202
|
+
_fr 32
|
206
203
|
tio 32
|
207
204
|
nce 32
|
208
|
-
|
209
|
-
|
210
|
-
|
205
|
+
tion 32
|
206
|
+
_n 32
|
207
|
+
ou 32
|
211
208
|
Ge 31
|
212
|
-
|
213
|
-
|
214
|
-
|
209
|
+
ge_ 31
|
210
|
+
S 31
|
211
|
+
pe 31
|
215
212
|
na 31
|
216
|
-
|
217
|
-
|
213
|
+
_Ge 31
|
214
|
+
_re 31
|
215
|
+
ent 31
|
218
216
|
erman 30
|
217
|
+
be 30
|
218
|
+
_Ger 30
|
219
219
|
Germa 30
|
220
|
+
erma 30
|
221
|
+
ch 30
|
220
222
|
Ger 30
|
221
|
-
|
223
|
+
_S 30
|
222
224
|
ts 30
|
223
|
-
|
224
|
-
|
225
|
-
|
226
|
-
ge_ 29
|
225
|
+
_Germ 30
|
226
|
+
Germ 30
|
227
|
+
_m 29
|
227
228
|
x 29
|
228
229
|
ly_ 29
|
229
|
-
_m 29
|
230
|
-
om_ 28
|
231
|
-
_Germ 28
|
232
230
|
iv 28
|
233
|
-
_Ger 28
|
234
231
|
no 28
|
232
|
+
ns 28
|
233
|
+
om_ 28
|
235
234
|
I 27
|
235
|
+
c_ 27
|
236
236
|
wo 27
|
237
|
+
st_ 27
|
238
|
+
ce_ 27
|
239
|
+
_as 27
|
240
|
+
age_ 27
|
237
241
|
wi 27
|
238
|
-
|
239
|
-
ic_ 26
|
240
|
-
ta 26
|
241
|
-
_as 26
|
242
|
+
uage_ 26
|
242
243
|
ne 26
|
244
|
+
ic_ 26
|
243
245
|
ive 26
|
244
|
-
|
245
|
-
|
246
|
+
_I 26
|
247
|
+
ta 26
|
248
|
+
A 25
|
249
|
+
rom 25
|
246
250
|
is_ 25
|
247
251
|
atio 25
|
248
|
-
|
249
|
-
|
250
|
-
ani 25
|
251
|
-
st_ 25
|
252
|
+
_wo 25
|
253
|
+
ct 25
|
252
254
|
_wor 25
|
253
|
-
|
255
|
+
we 25
|
256
|
+
ani 25
|
257
|
+
wor 25
|
254
258
|
nic 25
|
259
|
+
_A 25
|
260
|
+
ation 25
|
255
261
|
_a_ 25
|
256
|
-
|
257
|
-
A 25
|
258
|
-
_wo 25
|
259
|
-
we 25
|
260
|
-
ct 25
|
261
|
-
from_ 24
|
262
|
-
rom_ 24
|
263
|
-
_from 24
|
264
|
-
enc 24
|
262
|
+
ot 24
|
265
263
|
_fro 24
|
266
264
|
rt 24
|
267
|
-
fro 24
|
268
|
-
uage_ 24
|
269
265
|
_as_ 24
|
270
|
-
|
271
|
-
|
266
|
+
enc 24
|
267
|
+
fro 24
|
272
268
|
from 24
|
273
|
-
|
269
|
+
from_ 24
|
270
|
+
ts_ 24
|
271
|
+
rom_ 24
|
272
|
+
_from 24
|
274
273
|
pa 23
|
275
|
-
|
276
|
-
|
277
|
-
|
274
|
+
_h 23
|
275
|
+
nce_ 23
|
276
|
+
re_ 23
|
277
|
+
N 22
|
278
|
+
mani 22
|
278
279
|
_B 22
|
280
|
+
ion_ 22
|
281
|
+
ted 22
|
282
|
+
_F 22
|
283
|
+
ol 22
|
284
|
+
_N 22
|
279
285
|
ate 22
|
280
286
|
ted_ 22
|
281
|
-
_be 22
|
282
|
-
ted 22
|
283
|
-
ut 22
|
284
287
|
F 22
|
285
|
-
ion_ 22
|
286
|
-
_A 22
|
287
|
-
N 22
|
288
288
|
_is 22
|
289
289
|
tu 22
|
290
|
-
|
291
|
-
|
290
|
+
ut 22
|
291
|
+
B 22
|
292
|
+
_be 22
|
293
|
+
manic 21
|
294
|
+
_di 21
|
292
295
|
anic 21
|
296
|
+
ve_ 21
|
293
297
|
rmani 21
|
298
|
+
ie 21
|
294
299
|
ry 21
|
295
|
-
_di 21
|
296
|
-
hi 21
|
297
|
-
nce_ 21
|
298
300
|
rd 21
|
299
|
-
|
301
|
+
hi 21
|
300
302
|
sp 21
|
301
|
-
_N 21
|
302
|
-
ve_ 21
|
303
|
-
manic 21
|
304
|
-
ie 21
|
305
|
-
her 20
|
306
303
|
at_ 20
|
304
|
+
se_ 20
|
307
305
|
ter 20
|
306
|
+
tin 20
|
308
307
|
_is_ 20
|
309
308
|
so 20
|
309
|
+
her 20
|
310
310
|
us 20
|
311
|
-
ges 20
|
312
|
-
tin 20
|
313
|
-
fi 20
|
314
311
|
ver 20
|
312
|
+
fi 20
|
313
|
+
ica 19
|
314
|
+
com 19
|
315
315
|
nic_ 19
|
316
|
+
_v 19
|
316
317
|
all 19
|
317
318
|
ld 19
|
318
|
-
ica 19
|
319
319
|
su 19
|
320
|
-
|
321
|
-
ages 19
|
322
|
-
se_ 19
|
323
|
-
No 18
|
324
|
-
h, 18
|
325
|
-
rs 18
|
320
|
+
ges 19
|
326
321
|
anic_ 18
|
327
|
-
|
328
|
-
uages 18
|
329
|
-
if 18
|
330
|
-
tr 18
|
322
|
+
No 18
|
331
323
|
anc 18
|
324
|
+
_No 18
|
332
325
|
ord 18
|
333
|
-
|
326
|
+
if 18
|
334
327
|
po 18
|
328
|
+
ages 18
|
329
|
+
h,_ 18
|
330
|
+
_g 18
|
335
331
|
ss 18
|
332
|
+
tr 18
|
333
|
+
h, 18
|
334
|
+
ir 17
|
335
|
+
rs 17
|
336
|
+
tur 17
|
337
|
+
ence 17
|
336
338
|
_li 17
|
339
|
+
uages 17
|
340
|
+
rit 17
|
341
|
+
cen 17
|
337
342
|
ist 17
|
338
|
-
|
343
|
+
mp 17
|
344
|
+
con 17
|
339
345
|
ch_ 17
|
340
346
|
ther 17
|
341
|
-
con 17
|
342
|
-
_No 17
|
343
|
-
_F 17
|
344
|
-
tur 17
|
345
|
-
rit 17
|
346
|
-
ir 17
|
347
347
|
ue 17
|
348
348
|
mo 17
|
349
|
-
n, 17
|
350
|
-
mp 17
|
351
|
-
n,_ 17
|
352
|
-
cen 17
|
353
|
-
orm 16
|
354
|
-
word 16
|
355
|
-
ial 16
|
356
349
|
_Br 16
|
357
350
|
ect 16
|
358
|
-
|
359
|
-
|
351
|
+
tion_ 16
|
352
|
+
orm 16
|
360
353
|
_L 16
|
361
|
-
|
354
|
+
_T 16
|
355
|
+
L 16
|
362
356
|
rn 16
|
363
|
-
|
364
|
-
|
357
|
+
T 16
|
358
|
+
pl 16
|
359
|
+
ial 16
|
360
|
+
_word 16
|
365
361
|
_th_ 16
|
366
362
|
am 16
|
367
|
-
|
368
|
-
|
369
|
-
|
370
|
-
hat 15
|
371
|
-
ds 15
|
372
|
-
_Brit 15
|
373
|
-
or_ 15
|
374
|
-
ran 15
|
375
|
-
Brit 15
|
376
|
-
en_ 15
|
377
|
-
ev 15
|
378
|
-
iti 15
|
379
|
-
wh 15
|
363
|
+
Br 16
|
364
|
+
nt_ 16
|
365
|
+
word 16
|
380
366
|
O 15
|
381
|
-
|
382
|
-
ant 15
|
383
|
-
lat 15
|
384
|
-
Bri 15
|
385
|
-
hat_ 15
|
386
|
-
do 15
|
387
|
-
land 15
|
388
|
-
_Bri 15
|
367
|
+
or_ 15
|
389
368
|
ges_ 15
|
369
|
+
ac 15
|
370
|
+
ant 15
|
371
|
+
me_ 15
|
372
|
+
_Brit 15
|
373
|
+
mi 15
|
374
|
+
hat 15
|
375
|
+
_O 15
|
376
|
+
ds 15
|
390
377
|
ad 15
|
391
|
-
|
392
|
-
_wh 15
|
378
|
+
lat 15
|
393
379
|
wa 15
|
394
|
-
ac 15
|
395
380
|
Nor 15
|
381
|
+
_Nor 15
|
382
|
+
land 15
|
383
|
+
en_ 15
|
396
384
|
op 15
|
397
|
-
|
398
|
-
|
399
|
-
|
385
|
+
iti 15
|
386
|
+
_Bri 15
|
387
|
+
ran 15
|
388
|
+
do 15
|
400
389
|
_ha 15
|
390
|
+
Bri 15
|
391
|
+
Brit 15
|
392
|
+
_no 15
|
393
|
+
_wa 15
|
394
|
+
ex 15
|
395
|
+
ev 15
|
396
|
+
_wi 15
|
397
|
+
_wh 15
|
398
|
+
wh 15
|
399
|
+
hat_ 15
|
400
|
+
pr 14
|