scylla 1.0.0 → 1.0.7
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/scylla/classifier.rb +3 -2
- data/lib/scylla/generator.rb +11 -4
- data/lib/scylla/lms/arabic.lm +398 -398
- data/lib/scylla/lms/bulgarian.lm +268 -268
- data/lib/scylla/lms/catalan.lm +400 -400
- data/lib/scylla/lms/chinese.lm +345 -345
- data/lib/scylla/lms/czech.lm +382 -382
- data/lib/scylla/lms/danish.lm +354 -354
- data/lib/scylla/lms/dutch.lm +380 -380
- data/lib/scylla/lms/english.lm +327 -327
- data/lib/scylla/lms/finnish.lm +297 -297
- data/lib/scylla/lms/french.lm +348 -348
- data/lib/scylla/lms/german.lm +386 -386
- data/lib/scylla/lms/greek.lm +352 -352
- data/lib/scylla/lms/hebrew.lm +385 -385
- data/lib/scylla/lms/hindi.lm +400 -400
- data/lib/scylla/lms/icelandic.lm +195 -195
- data/lib/scylla/lms/indonesian.lm +374 -374
- data/lib/scylla/lms/italian.lm +365 -365
- data/lib/scylla/lms/japanese.lm +368 -368
- data/lib/scylla/lms/kannada.lm +299 -299
- data/lib/scylla/lms/korean.lm +335 -335
- data/lib/scylla/lms/marathi.lm +240 -240
- data/lib/scylla/lms/norwegian.lm +348 -348
- data/lib/scylla/lms/persian.lm +337 -337
- data/lib/scylla/lms/polish.lm +399 -399
- data/lib/scylla/lms/portuguese.lm +386 -386
- data/lib/scylla/lms/romanian.lm +255 -255
- data/lib/scylla/lms/russian.lm +400 -400
- data/lib/scylla/lms/slovak.lm +267 -267
- data/lib/scylla/lms/slovenian.lm +243 -243
- data/lib/scylla/lms/spanish.lm +371 -371
- data/lib/scylla/lms/swedish.lm +236 -236
- data/lib/scylla/lms/tagalog.lm +287 -287
- data/lib/scylla/lms/thai.lm +369 -369
- data/lib/scylla/lms/turkish.lm +341 -341
- data/lib/scylla/lms/vietnamese.lm +392 -392
- data/lib/scylla/lms/welsh.lm +275 -275
- data/lib/scylla/loader.rb +1 -1
- metadata +2 -2
@@ -1,400 +1,400 @@
|
|
1
|
-
_
|
2
|
-
a
|
3
|
-
n
|
4
|
-
i
|
5
|
-
e
|
6
|
-
d
|
7
|
-
r
|
8
|
-
|
9
|
-
|
10
|
-
u
|
11
|
-
t
|
12
|
-
k
|
13
|
-
a_
|
14
|
-
m
|
15
|
-
g
|
16
|
-
l
|
17
|
-
n_
|
18
|
-
p
|
19
|
-
_d
|
20
|
-
an_
|
21
|
-
b
|
22
|
-
i_
|
23
|
-
h
|
24
|
-
o
|
25
|
-
da
|
26
|
-
ng
|
27
|
-
er
|
28
|
-
in
|
29
|
-
y
|
30
|
-
_p
|
31
|
-
_m
|
32
|
-
|
33
|
-
|
34
|
-
ya
|
35
|
-
ar
|
36
|
-
|
37
|
-
|
38
|
-
ta
|
39
|
-
_s
|
40
|
-
ga
|
41
|
-
ra
|
42
|
-
me
|
43
|
-
_b
|
44
|
-
ah
|
45
|
-
ang
|
46
|
-
_da
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
se
|
55
|
-
h_
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
_k
|
60
|
-
on
|
61
|
-
al
|
62
|
-
|
63
|
-
j
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
_in
|
74
|
-
ak
|
75
|
-
at
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
|
84
|
-
|
85
|
-
|
86
|
-
|
87
|
-
_y
|
88
|
-
|
89
|
-
|
90
|
-
|
91
|
-
r_
|
92
|
-
kan
|
93
|
-
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
|
98
|
-
el
|
99
|
-
|
100
|
-
|
101
|
-
|
102
|
-
|
103
|
-
|
104
|
-
don
|
105
|
-
|
106
|
-
|
107
|
-
|
108
|
-
|
109
|
-
|
110
|
-
|
111
|
-
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
120
|
-
nt
|
121
|
-
|
122
|
-
|
123
|
-
|
124
|
-
|
125
|
-
|
126
|
-
|
127
|
-
|
128
|
-
|
129
|
-
|
130
|
-
de
|
131
|
-
|
132
|
-
|
133
|
-
|
134
|
-
|
135
|
-
|
136
|
-
|
137
|
-
|
138
|
-
|
139
|
-
|
140
|
-
|
141
|
-
|
142
|
-
|
143
|
-
|
144
|
-
|
145
|
-
|
146
|
-
|
147
|
-
|
148
|
-
|
149
|
-
|
150
|
-
|
151
|
-
|
152
|
-
|
153
|
-
|
154
|
-
|
155
|
-
|
156
|
-
us
|
157
|
-
|
158
|
-
lah
|
159
|
-
|
160
|
-
|
161
|
-
|
162
|
-
mi
|
163
|
-
|
164
|
-
|
165
|
-
|
166
|
-
|
1
|
+
_ 9050
|
2
|
+
a 5286
|
3
|
+
n 2944
|
4
|
+
i 2449
|
5
|
+
e 2351
|
6
|
+
d 1552
|
7
|
+
r 1349
|
8
|
+
s 1336
|
9
|
+
an 1300
|
10
|
+
u 1221
|
11
|
+
t 1205
|
12
|
+
k 1065
|
13
|
+
a_ 1006
|
14
|
+
m 985
|
15
|
+
g 962
|
16
|
+
l 936
|
17
|
+
n_ 893
|
18
|
+
p 794
|
19
|
+
_d 730
|
20
|
+
an_ 716
|
21
|
+
b 692
|
22
|
+
i_ 686
|
23
|
+
h 671
|
24
|
+
o 660
|
25
|
+
da 640
|
26
|
+
ng 601
|
27
|
+
er 546
|
28
|
+
in 487
|
29
|
+
y 472
|
30
|
+
_p 465
|
31
|
+
_m 437
|
32
|
+
di 432
|
33
|
+
en 431
|
34
|
+
ya 418
|
35
|
+
ar 412
|
36
|
+
la 405
|
37
|
+
si 402
|
38
|
+
ta 391
|
39
|
+
_s 384
|
40
|
+
ga 361
|
41
|
+
ra 360
|
42
|
+
me 357
|
43
|
+
_b 352
|
44
|
+
ah 351
|
45
|
+
ang 329
|
46
|
+
_da 322
|
47
|
+
nd 319
|
48
|
+
g_ 314
|
49
|
+
ka 314
|
50
|
+
ng_ 312
|
51
|
+
ia 311
|
52
|
+
_t 310
|
53
|
+
_i 303
|
54
|
+
se 303
|
55
|
+
h_ 301
|
56
|
+
_me 301
|
57
|
+
es 292
|
58
|
+
_di 291
|
59
|
+
_k 284
|
60
|
+
on 275
|
61
|
+
al 274
|
62
|
+
ad 271
|
63
|
+
j 269
|
64
|
+
as 267
|
65
|
+
_a 263
|
66
|
+
be 261
|
67
|
+
ne 260
|
68
|
+
sa 260
|
69
|
+
pe 255
|
70
|
+
pa 254
|
71
|
+
ba 254
|
72
|
+
_se 252
|
73
|
+
_in 245
|
74
|
+
ak 240
|
75
|
+
at 235
|
76
|
+
ri 225
|
77
|
+
dan 217
|
78
|
+
te 217
|
79
|
+
ia_ 217
|
80
|
+
un 215
|
81
|
+
k_ 212
|
82
|
+
ke 208
|
83
|
+
ind 206
|
84
|
+
_pe 205
|
85
|
+
ah_ 202
|
86
|
+
ma 201
|
87
|
+
_y 194
|
88
|
+
_be 193
|
89
|
+
esi 192
|
90
|
+
_ya 190
|
91
|
+
r_ 186
|
92
|
+
kan 184
|
93
|
+
na 183
|
94
|
+
do 183
|
95
|
+
ada 181
|
96
|
+
em 181
|
97
|
+
ndo 179
|
98
|
+
el 178
|
99
|
+
ny 178
|
100
|
+
sia 178
|
101
|
+
nes 177
|
102
|
+
_ke 177
|
103
|
+
one 176
|
104
|
+
don 176
|
105
|
+
men 174
|
106
|
+
di_ 174
|
107
|
+
yan 169
|
108
|
+
ja 168
|
109
|
+
ha 165
|
110
|
+
t_ 164
|
111
|
+
am 164
|
112
|
+
ai 162
|
113
|
+
is 160
|
114
|
+
nya 159
|
115
|
+
da_ 156
|
116
|
+
ti 156
|
117
|
+
ara 155
|
118
|
+
tu 152
|
119
|
+
ber 150
|
120
|
+
nt 149
|
121
|
+
ya_ 149
|
122
|
+
_pa 147
|
123
|
+
s_ 146
|
124
|
+
_te 144
|
125
|
+
eng 139
|
126
|
+
li 138
|
127
|
+
u_ 137
|
128
|
+
ik 136
|
129
|
+
l_ 132
|
130
|
+
de 131
|
131
|
+
c 130
|
132
|
+
nga 127
|
133
|
+
ag 127
|
134
|
+
ua 126
|
135
|
+
il 124
|
136
|
+
ek 124
|
137
|
+
ri_ 122
|
138
|
+
eb 121
|
139
|
+
ter 121
|
140
|
+
it 120
|
141
|
+
gan 118
|
142
|
+
uk 117
|
143
|
+
pad 115
|
144
|
+
era 115
|
145
|
+
w 114
|
146
|
+
_l 113
|
147
|
+
ni 113
|
148
|
+
ela 112
|
149
|
+
ra_ 109
|
150
|
+
_ba 109
|
151
|
+
_n 106
|
152
|
+
per 104
|
153
|
+
ala 104
|
154
|
+
ul 103
|
155
|
+
du 102
|
156
|
+
us 101
|
157
|
+
at_ 100
|
158
|
+
lah 98
|
159
|
+
aga 97
|
160
|
+
ari 96
|
161
|
+
_j 94
|
162
|
+
mi 94
|
163
|
+
asa 94
|
164
|
+
pu 94
|
165
|
+
_h 93
|
166
|
+
le 93
|
167
|
+
ut 92
|
168
|
+
m_ 92
|
169
|
+
ing 91
|
170
|
+
asi 91
|
171
|
+
un_ 90
|
172
|
+
al_ 89
|
173
|
+
_ta 87
|
174
|
+
pen 86
|
167
175
|
bu 86
|
168
|
-
|
169
|
-
|
170
|
-
|
171
|
-
|
172
|
-
|
173
|
-
|
174
|
-
|
175
|
-
|
176
|
-
|
177
|
-
|
178
|
-
|
179
|
-
|
180
|
-
|
181
|
-
|
182
|
-
|
183
|
-
|
184
|
-
|
185
|
-
|
186
|
-
|
187
|
-
|
188
|
-
|
189
|
-
|
190
|
-
|
191
|
-
|
192
|
-
|
193
|
-
|
194
|
-
|
195
|
-
|
196
|
-
|
197
|
-
|
198
|
-
|
199
|
-
|
200
|
-
|
201
|
-
|
202
|
-
|
203
|
-
|
204
|
-
|
205
|
-
|
206
|
-
|
207
|
-
|
208
|
-
uk_ 67
|
209
|
-
seb 67
|
210
|
-
den 66
|
211
|
-
mb 66
|
176
|
+
ru 85
|
177
|
+
si_ 84
|
178
|
+
ap 83
|
179
|
+
tah 82
|
180
|
+
_de 82
|
181
|
+
hu 81
|
182
|
+
ai_ 81
|
183
|
+
_o 81
|
184
|
+
rt 80
|
185
|
+
ki 80
|
186
|
+
e_ 79
|
187
|
+
et 79
|
188
|
+
aka 79
|
189
|
+
mu 78
|
190
|
+
ak_ 77
|
191
|
+
au 77
|
192
|
+
ama 77
|
193
|
+
ol 77
|
194
|
+
lu 76
|
195
|
+
ar_ 75
|
196
|
+
wa 75
|
197
|
+
ju 75
|
198
|
+
nta 75
|
199
|
+
dar 74
|
200
|
+
ir 74
|
201
|
+
ay 74
|
202
|
+
ur 73
|
203
|
+
re 72
|
204
|
+
ngg 71
|
205
|
+
gg 71
|
206
|
+
seb 70
|
207
|
+
st 70
|
208
|
+
ga_ 70
|
209
|
+
_ma 70
|
210
|
+
uk_ 69
|
211
|
+
tan 69
|
212
|
+
mb 68
|
213
|
+
den 68
|
214
|
+
mer 67
|
215
|
+
bag 67
|
212
216
|
ku 66
|
213
|
-
|
214
|
-
|
215
|
-
|
216
|
-
|
217
|
-
|
218
|
-
|
219
|
-
|
220
|
-
eg 62
|
221
|
-
ta_ 62
|
217
|
+
nj 66
|
218
|
+
ta_ 65
|
219
|
+
or 65
|
220
|
+
ata 64
|
221
|
+
eg 64
|
222
|
+
f 63
|
223
|
+
su 62
|
222
224
|
hi 62
|
225
|
+
end 62
|
226
|
+
aa 62
|
223
227
|
ahu 61
|
228
|
+
gar 61
|
224
229
|
hun 60
|
225
|
-
|
226
|
-
|
227
|
-
|
228
|
-
|
229
|
-
|
230
|
-
|
231
|
-
|
232
|
-
|
233
|
-
|
234
|
-
|
235
|
-
|
236
|
-
|
237
|
-
|
238
|
-
|
239
|
-
|
240
|
-
|
241
|
-
|
242
|
-
tar
|
243
|
-
|
244
|
-
|
245
|
-
|
246
|
-
|
247
|
-
|
248
|
-
|
249
|
-
|
250
|
-
|
230
|
+
aha 60
|
231
|
+
ula 60
|
232
|
+
ko 59
|
233
|
+
adi 57
|
234
|
+
id 57
|
235
|
+
lan 57
|
236
|
+
ud 57
|
237
|
+
mp 57
|
238
|
+
gi 56
|
239
|
+
eri 56
|
240
|
+
_an 56
|
241
|
+
ma_ 55
|
242
|
+
_la 55
|
243
|
+
ert 54
|
244
|
+
_r 54
|
245
|
+
ab 53
|
246
|
+
dia 53
|
247
|
+
tar 53
|
248
|
+
pr 53
|
249
|
+
dal 53
|
250
|
+
aya 52
|
251
|
+
ni_ 52
|
252
|
+
bi 52
|
253
|
+
_e 52
|
254
|
+
eh 52
|
255
|
+
mem 51
|
256
|
+
han 51
|
257
|
+
ep 51
|
258
|
+
ik_ 51
|
259
|
+
eba 51
|
260
|
+
lam 50
|
261
|
+
ega 50
|
262
|
+
aan 50
|
263
|
+
_ne 50
|
264
|
+
pul 50
|
251
265
|
_sa 50
|
252
|
-
|
253
|
-
|
254
|
-
|
255
|
-
|
256
|
-
|
257
|
-
|
258
|
-
|
266
|
+
ran 50
|
267
|
+
um 50
|
268
|
+
ban 50
|
269
|
+
sar 49
|
270
|
+
rd 49
|
271
|
+
mas 49
|
272
|
+
any 48
|
259
273
|
nda 48
|
260
|
-
|
261
|
-
|
262
|
-
|
263
|
-
|
264
|
-
|
265
|
-
|
266
|
-
|
267
|
-
|
268
|
-
|
274
|
+
_ad 48
|
275
|
+
tu_ 48
|
276
|
+
_u 48
|
277
|
+
io 47
|
278
|
+
po 47
|
279
|
+
ant 47
|
280
|
+
sa_ 47
|
281
|
+
ca 47
|
282
|
+
neg 47
|
283
|
+
lai 46
|
284
|
+
ih 46
|
269
285
|
eka 46
|
270
|
-
|
271
|
-
tu_ 46
|
286
|
+
nja 46
|
272
287
|
as_ 46
|
273
|
-
|
274
|
-
|
275
|
-
|
276
|
-
|
277
|
-
|
278
|
-
|
279
|
-
|
280
|
-
|
281
|
-
|
282
|
-
|
283
|
-
|
288
|
+
om 46
|
289
|
+
aj 45
|
290
|
+
ndi 45
|
291
|
+
aw 45
|
292
|
+
_ha 45
|
293
|
+
san 45
|
294
|
+
enj 45
|
295
|
+
ain 44
|
296
|
+
rb 44
|
297
|
+
ian 44
|
298
|
+
awa 44
|
299
|
+
in_ 44
|
300
|
+
_ju 44
|
284
301
|
_w 44
|
285
|
-
|
286
|
-
|
287
|
-
|
288
|
-
|
302
|
+
erd 43
|
303
|
+
eme 43
|
304
|
+
erb 43
|
305
|
+
nal 43
|
306
|
+
ali 43
|
289
307
|
esa 43
|
290
|
-
|
291
|
-
|
292
|
-
|
293
|
-
erd 42
|
308
|
+
_ti 42
|
309
|
+
jad 42
|
310
|
+
emb 42
|
294
311
|
_ol 42
|
295
|
-
|
296
|
-
_ha 42
|
297
|
-
ndi 42
|
298
|
-
ca 42
|
299
|
-
eme 41
|
300
|
-
au_ 41
|
301
|
-
in_ 41
|
302
|
-
ali 41
|
312
|
+
gai 42
|
303
313
|
bes 41
|
304
|
-
|
305
|
-
|
306
|
-
|
307
|
-
|
308
|
-
|
309
|
-
|
310
|
-
|
314
|
+
apa 41
|
315
|
+
au_ 41
|
316
|
+
v 41
|
317
|
+
_c 41
|
318
|
+
itu 40
|
319
|
+
lau 40
|
320
|
+
d_ 40
|
321
|
+
eh_ 40
|
322
|
+
ip 40
|
311
323
|
ila 40
|
312
|
-
|
313
|
-
|
314
|
-
|
315
|
-
|
316
|
-
|
324
|
+
and 40
|
325
|
+
no 40
|
326
|
+
ntu 40
|
327
|
+
_ja 40
|
328
|
+
ent 39
|
329
|
+
rn 39
|
330
|
+
ed 39
|
331
|
+
has 39
|
332
|
+
ion 38
|
317
333
|
p_ 38
|
318
|
-
itu 38
|
319
|
-
_pr 38
|
320
|
-
ini 38
|
321
|
-
ntu 38
|
322
334
|
gu 38
|
323
|
-
|
335
|
+
_pr 38
|
324
336
|
isi 38
|
325
|
-
|
326
|
-
|
327
|
-
|
328
|
-
|
329
|
-
|
330
|
-
|
331
|
-
|
332
|
-
up
|
333
|
-
|
334
|
-
|
335
|
-
|
336
|
-
|
337
|
+
bah 38
|
338
|
+
rah 38
|
339
|
+
ini 38
|
340
|
+
_ka 38
|
341
|
+
rin 37
|
342
|
+
tr 37
|
343
|
+
dis 37
|
344
|
+
up 37
|
345
|
+
ole 37
|
346
|
+
leh 37
|
347
|
+
emi 36
|
348
|
+
am_ 36
|
349
|
+
sel 36
|
350
|
+
rk 36
|
351
|
+
im 36
|
337
352
|
lay 36
|
338
|
-
|
339
|
-
|
340
|
-
|
341
|
-
|
342
|
-
rta 35
|
343
|
-
_ka 35
|
344
|
-
mel 35
|
353
|
+
ana 36
|
354
|
+
mel 36
|
355
|
+
man 36
|
356
|
+
uh 36
|
345
357
|
_pu 35
|
346
|
-
|
347
|
-
|
348
|
-
rin 35
|
349
|
-
uh 35
|
350
|
-
_c 35
|
358
|
+
nu 35
|
359
|
+
ena 35
|
351
360
|
mba 35
|
361
|
+
ut_ 35
|
362
|
+
is_ 35
|
363
|
+
eru 35
|
364
|
+
rs 35
|
365
|
+
rta 35
|
366
|
+
_na 34
|
352
367
|
gga 34
|
353
|
-
|
354
|
-
_ja 34
|
355
|
-
iri 34
|
356
|
-
uas 34
|
357
|
-
sel 34
|
358
|
-
is_ 34
|
368
|
+
ej 34
|
359
369
|
lo 34
|
360
|
-
pi 34
|
361
|
-
am_ 34
|
362
|
-
ngk 34
|
363
370
|
gk 34
|
364
|
-
|
365
|
-
|
371
|
+
ngk 34
|
372
|
+
_mu 34
|
373
|
+
iri 34
|
374
|
+
uas 34
|
375
|
+
aja 34
|
366
376
|
mi_ 33
|
367
|
-
|
368
|
-
|
369
|
-
|
370
|
-
|
371
|
-
|
372
|
-
|
373
|
-
|
374
|
-
|
375
|
-
_na 32
|
376
|
-
kh 32
|
377
|
+
kh 33
|
378
|
+
ndu 33
|
379
|
+
ro 33
|
380
|
+
pi 33
|
381
|
+
ika 33
|
382
|
+
to 33
|
383
|
+
int 32
|
384
|
+
ks 32
|
377
385
|
ung 32
|
378
|
-
|
379
|
-
|
380
|
-
|
381
|
-
|
382
|
-
|
383
|
-
|
384
|
-
|
386
|
+
ili 32
|
387
|
+
bel 32
|
388
|
+
nny 31
|
389
|
+
nn 31
|
390
|
+
tel 31
|
391
|
+
tas 31
|
392
|
+
nc 31
|
393
|
+
usa 31
|
394
|
+
_re 31
|
395
|
+
yak 31
|
396
|
+
ita 30
|
397
|
+
duk 30
|
398
|
+
_po 30
|
385
399
|
ke_ 30
|
386
|
-
|
387
|
-
usa 30
|
388
|
-
int 30
|
389
|
-
tuk 29
|
390
|
-
ili 29
|
391
|
-
ih_ 29
|
392
|
-
nn 29
|
393
|
-
nny 29
|
394
|
-
_hi 29
|
395
|
-
ita 29
|
396
|
-
nc 29
|
397
|
-
duk 28
|
398
|
-
pat 28
|
399
|
-
yak 28
|
400
|
-
ebe 28
|
400
|
+
tuk 30
|