scylla 1.0.0 → 1.0.7
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 -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
data/lib/scylla/lms/english.lm
CHANGED
@@ -1,400 +1,400 @@
|
|
1
|
-
_
|
2
|
-
e
|
3
|
-
t
|
4
|
-
n
|
5
|
-
a
|
6
|
-
i
|
7
|
-
o
|
8
|
-
s
|
9
|
-
r
|
10
|
-
h
|
11
|
-
e_
|
12
|
-
d
|
13
|
-
l
|
14
|
-
_t
|
15
|
-
th
|
16
|
-
c
|
17
|
-
s_
|
18
|
-
he
|
1
|
+
_ 19390
|
2
|
+
e 5754
|
3
|
+
t 4202
|
4
|
+
n 3921
|
5
|
+
a 3788
|
6
|
+
i 3488
|
7
|
+
o 3276
|
8
|
+
s 3003
|
9
|
+
r 2925
|
10
|
+
h 2480
|
11
|
+
e_ 2120
|
12
|
+
d 2039
|
13
|
+
l 2023
|
14
|
+
_t 1702
|
15
|
+
th 1595
|
16
|
+
c 1442
|
17
|
+
s_ 1398
|
18
|
+
he 1379
|
19
19
|
_th 1342
|
20
|
-
_a
|
21
|
-
d_
|
22
|
-
the
|
23
|
-
u
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
n_
|
31
|
-
p
|
20
|
+
_a 1292
|
21
|
+
d_ 1277
|
22
|
+
the 1262
|
23
|
+
u 1194
|
24
|
+
g 1111
|
25
|
+
he_ 1080
|
26
|
+
m 1067
|
27
|
+
in 1067
|
28
|
+
an 992
|
29
|
+
f 987
|
30
|
+
n_ 913
|
31
|
+
p 894
|
32
32
|
_i 809
|
33
|
-
nd
|
34
|
-
w
|
35
|
-
re
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
en
|
42
|
-
|
43
|
-
|
44
|
-
b
|
45
|
-
|
46
|
-
|
47
|
-
y_
|
48
|
-
|
49
|
-
|
50
|
-
es
|
51
|
-
ed
|
52
|
-
is
|
53
|
-
|
54
|
-
|
55
|
-
|
56
|
-
ed_
|
57
|
-
_e
|
33
|
+
nd 781
|
34
|
+
w 741
|
35
|
+
re 722
|
36
|
+
y 666
|
37
|
+
_o 656
|
38
|
+
nd_ 651
|
39
|
+
t_ 649
|
40
|
+
er 648
|
41
|
+
en 640
|
42
|
+
on 629
|
43
|
+
and 626
|
44
|
+
b 611
|
45
|
+
ng 602
|
46
|
+
_s 602
|
47
|
+
y_ 545
|
48
|
+
ar 530
|
49
|
+
_w 521
|
50
|
+
es 517
|
51
|
+
ed 506
|
52
|
+
is 501
|
53
|
+
_c 496
|
54
|
+
_an 487
|
55
|
+
_in 481
|
56
|
+
ed_ 479
|
57
|
+
_e 475
|
58
|
+
ti 465
|
58
59
|
or 459
|
59
|
-
|
60
|
-
st
|
61
|
-
|
62
|
-
of
|
63
|
-
la 425
|
60
|
+
it 455
|
61
|
+
st 453
|
62
|
+
la 441
|
63
|
+
of 430
|
64
64
|
f_ 425
|
65
|
-
|
66
|
-
|
67
|
-
|
65
|
+
te 425
|
66
|
+
_of 423
|
67
|
+
h_ 422
|
68
68
|
as 416
|
69
|
-
_b
|
70
|
-
|
71
|
-
nt
|
72
|
-
|
73
|
-
r_
|
74
|
-
|
75
|
-
ri
|
76
|
-
|
77
|
-
al
|
78
|
-
|
79
|
-
|
80
|
-
ro
|
81
|
-
ing
|
82
|
-
as_
|
83
|
-
re_
|
84
|
-
to
|
85
|
-
_m
|
86
|
-
|
87
|
-
|
88
|
-
|
89
|
-
|
69
|
+
_b 412
|
70
|
+
at 410
|
71
|
+
nt 409
|
72
|
+
of_ 407
|
73
|
+
r_ 406
|
74
|
+
v 403
|
75
|
+
ri 386
|
76
|
+
_p 379
|
77
|
+
al 379
|
78
|
+
_f 377
|
79
|
+
in_ 372
|
80
|
+
ro 332
|
81
|
+
ing 311
|
82
|
+
as_ 306
|
83
|
+
re_ 302
|
84
|
+
to 298
|
85
|
+
_m 296
|
86
|
+
de 295
|
87
|
+
co 289
|
88
|
+
g_ 284
|
89
|
+
o_ 283
|
90
|
+
io 278
|
90
91
|
ng_ 277
|
91
|
-
|
92
|
-
|
93
|
-
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
li
|
98
|
-
|
99
|
-
|
100
|
-
|
101
|
-
|
102
|
-
|
103
|
-
|
104
|
-
|
105
|
-
_en
|
92
|
+
l_ 275
|
93
|
+
le 270
|
94
|
+
_l 269
|
95
|
+
om 268
|
96
|
+
es_ 265
|
97
|
+
_r 263
|
98
|
+
li 260
|
99
|
+
ou 259
|
100
|
+
ea 257
|
101
|
+
on_ 256
|
102
|
+
se 254
|
103
|
+
ve 252
|
104
|
+
me 250
|
105
|
+
_h 249
|
106
|
+
_en 245
|
106
107
|
ch 242
|
107
|
-
|
108
|
-
|
109
|
-
|
108
|
+
ion 241
|
109
|
+
a_ 239
|
110
|
+
ur 239
|
110
111
|
is_ 229
|
111
|
-
|
112
|
-
|
113
|
-
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
120
|
-
eng
|
112
|
+
ce 225
|
113
|
+
lan 224
|
114
|
+
er_ 224
|
115
|
+
gl 224
|
116
|
+
ic 222
|
117
|
+
ngl 220
|
118
|
+
_co 220
|
119
|
+
ent 219
|
120
|
+
_d 219
|
121
|
+
eng 218
|
121
122
|
_to 213
|
122
|
-
|
123
|
-
to_
|
124
|
-
|
125
|
-
|
126
|
-
|
123
|
+
k 208
|
124
|
+
to_ 208
|
125
|
+
st_ 208
|
126
|
+
ra 207
|
127
|
+
hi 204
|
128
|
+
_ar 203
|
129
|
+
si 202
|
127
130
|
ha 198
|
128
|
-
ra 197
|
129
|
-
si 197
|
130
|
-
k 195
|
131
131
|
_is 193
|
132
|
-
un
|
133
|
-
al_
|
134
|
-
|
135
|
-
|
136
|
-
|
137
|
-
|
138
|
-
|
132
|
+
un 192
|
133
|
+
al_ 191
|
134
|
+
m_ 188
|
135
|
+
_n 184
|
136
|
+
nc 182
|
137
|
+
ns 180
|
138
|
+
_a_ 177
|
139
139
|
fo 173
|
140
|
-
tr
|
140
|
+
tr 171
|
141
|
+
ma 169
|
142
|
+
pe 167
|
143
|
+
_re 166
|
141
144
|
wa 162
|
142
|
-
|
143
|
-
|
144
|
-
|
145
|
-
|
145
|
+
ll 162
|
146
|
+
ne 160
|
147
|
+
po 160
|
148
|
+
tio 159
|
149
|
+
ly 158
|
150
|
+
na 158
|
146
151
|
_fo 158
|
147
|
-
|
152
|
+
ly_ 156
|
153
|
+
are 155
|
148
154
|
th_ 154
|
149
|
-
|
150
|
-
|
151
|
-
|
152
|
-
|
153
|
-
|
154
|
-
are 151
|
155
|
-
el 151
|
156
|
-
tio 150
|
155
|
+
ca 154
|
156
|
+
ge 153
|
157
|
+
el 152
|
158
|
+
her 152
|
159
|
+
rt 151
|
157
160
|
be 150
|
158
|
-
|
159
|
-
|
160
|
-
|
161
|
+
ni 148
|
162
|
+
gla 148
|
163
|
+
sh 148
|
161
164
|
ec 147
|
162
|
-
|
163
|
-
|
164
|
-
|
165
|
-
|
166
|
-
|
167
|
-
mo 143
|
165
|
+
no 147
|
166
|
+
ol 145
|
167
|
+
_as 145
|
168
|
+
mo 145
|
169
|
+
_u 144
|
168
170
|
ere 143
|
169
|
-
|
170
|
-
ie
|
171
|
+
ho 143
|
172
|
+
ie 140
|
171
173
|
_wa 140
|
172
|
-
|
173
|
-
|
174
|
-
|
175
|
-
|
176
|
-
|
177
|
-
|
178
|
-
est 131
|
174
|
+
lo 139
|
175
|
+
ta 138
|
176
|
+
est 136
|
177
|
+
ch_ 134
|
178
|
+
we 133
|
179
|
+
op 130
|
179
180
|
il 129
|
180
|
-
|
181
|
-
ts
|
182
|
-
|
183
|
-
|
184
|
-
|
181
|
+
om_ 127
|
182
|
+
ts 127
|
183
|
+
ati 127
|
184
|
+
di 127
|
185
|
+
_be 127
|
186
|
+
ted 126
|
187
|
+
ate 126
|
188
|
+
tu 125
|
185
189
|
pr 124
|
186
|
-
|
187
|
-
|
190
|
+
pa 123
|
191
|
+
ct 123
|
188
192
|
ot 122
|
189
|
-
|
190
|
-
|
191
|
-
|
192
|
-
|
193
|
-
|
194
|
-
ts_ 119
|
195
|
-
op 119
|
193
|
+
wi 121
|
194
|
+
wh 121
|
195
|
+
os 120
|
196
|
+
_g 120
|
197
|
+
ts_ 120
|
196
198
|
rs 119
|
197
|
-
rom
|
198
|
-
|
199
|
-
|
200
|
-
|
199
|
+
rom 119
|
200
|
+
fr 117
|
201
|
+
us 116
|
202
|
+
for 116
|
203
|
+
am 115
|
201
204
|
_ha 115
|
202
|
-
ai 115
|
203
205
|
an_ 115
|
204
|
-
|
206
|
+
ai 115
|
205
207
|
or_ 114
|
206
|
-
|
207
|
-
|
208
|
+
su 114
|
209
|
+
_wh 114
|
210
|
+
_fr 114
|
211
|
+
nt_ 112
|
212
|
+
ish 112
|
213
|
+
ia 112
|
208
214
|
ter 112
|
209
|
-
|
210
|
-
ia 111
|
211
|
-
nt_ 110
|
212
|
-
su 110
|
213
|
-
ry 110
|
214
|
-
ish 109
|
215
|
+
ry 109
|
215
216
|
ow 109
|
216
|
-
|
217
|
+
_wi 108
|
218
|
+
_la 107
|
217
219
|
_pr 107
|
218
|
-
|
219
|
-
|
220
|
-
|
221
|
-
|
222
|
-
|
223
|
-
|
224
|
-
|
225
|
-
con
|
220
|
+
_mo 107
|
221
|
+
by 106
|
222
|
+
_by 106
|
223
|
+
iv 106
|
224
|
+
ul 106
|
225
|
+
by_ 106
|
226
|
+
et 103
|
227
|
+
con 103
|
228
|
+
_s_ 103
|
229
|
+
ad 103
|
230
|
+
ry_ 103
|
231
|
+
em 103
|
232
|
+
ut 102
|
226
233
|
so 102
|
227
|
-
|
228
|
-
|
229
|
-
|
230
|
-
|
231
|
-
was 99
|
232
|
-
ut 99
|
233
|
-
ad 99
|
234
|
-
et 98
|
235
|
-
_it 97
|
234
|
+
le_ 101
|
235
|
+
mi 100
|
236
|
+
me_ 99
|
237
|
+
was 98
|
236
238
|
cl 97
|
237
239
|
ns_ 96
|
238
|
-
|
239
|
-
|
240
|
-
|
241
|
-
wo 95
|
242
|
-
ac 95
|
240
|
+
sh_ 96
|
241
|
+
_ma 96
|
242
|
+
ac 96
|
243
243
|
ee 95
|
244
|
-
|
245
|
-
ig
|
246
|
-
|
244
|
+
_it 95
|
245
|
+
ig 95
|
246
|
+
wo 94
|
247
247
|
ons 94
|
248
|
-
|
248
|
+
do 94
|
249
|
+
ver 94
|
250
|
+
ci 94
|
251
|
+
inc 94
|
249
252
|
ir 93
|
250
|
-
|
251
|
-
|
252
|
-
|
253
|
-
tur 92
|
253
|
+
fro 93
|
254
|
+
tur 93
|
255
|
+
oun 92
|
254
256
|
uc 92
|
255
|
-
|
256
|
-
|
257
|
-
|
257
|
+
_de 91
|
258
|
+
ith 90
|
259
|
+
_pa 90
|
258
260
|
ies 90
|
259
|
-
|
260
|
-
|
261
|
-
|
261
|
+
ce_ 89
|
262
|
+
_on 89
|
263
|
+
lis 88
|
264
|
+
wit 88
|
265
|
+
_we 87
|
262
266
|
du 86
|
263
|
-
|
264
|
-
|
265
|
-
lis 85
|
266
|
-
tin 84
|
267
|
+
_k 85
|
268
|
+
iti 85
|
267
269
|
rl 84
|
268
|
-
|
269
|
-
nce 84
|
270
|
-
at_ 84
|
271
|
-
_de 84
|
272
|
-
mp 83
|
270
|
+
all 84
|
273
271
|
en_ 83
|
274
|
-
|
272
|
+
tin 83
|
273
|
+
ev 83
|
274
|
+
_no 83
|
275
|
+
ld 83
|
276
|
+
nce 83
|
277
|
+
mp 83
|
278
|
+
at_ 83
|
275
279
|
id 82
|
276
|
-
|
277
|
-
|
278
|
-
lu
|
279
|
-
_k 82
|
280
|
+
te_ 82
|
281
|
+
im 81
|
282
|
+
lu 81
|
280
283
|
_su 80
|
281
284
|
pl 80
|
282
|
-
|
283
|
-
|
285
|
+
rea 80
|
286
|
+
fi 80
|
287
|
+
gi 79
|
284
288
|
_se 78
|
289
|
+
ov 77
|
285
290
|
par 77
|
286
|
-
|
291
|
+
sp 77
|
292
|
+
ag 76
|
287
293
|
rs_ 76
|
288
|
-
|
289
|
-
|
290
|
-
rea 76
|
291
|
-
te_ 76
|
294
|
+
_un 76
|
295
|
+
ss 76
|
292
296
|
gh 75
|
297
|
+
x 75
|
293
298
|
vi 75
|
294
|
-
_un 75
|
295
|
-
ss 75
|
296
|
-
man 74
|
297
|
-
x 74
|
298
299
|
art 74
|
299
|
-
ite
|
300
|
-
|
301
|
-
|
302
|
-
ain
|
303
|
-
|
304
|
-
|
305
|
-
|
306
|
-
|
307
|
-
|
308
|
-
br 70
|
300
|
+
ite 74
|
301
|
+
man 74
|
302
|
+
_po 73
|
303
|
+
ain 72
|
304
|
+
rit 72
|
305
|
+
od 72
|
306
|
+
lat 71
|
307
|
+
br 71
|
308
|
+
und 69
|
309
309
|
ve_ 69
|
310
310
|
res 69
|
311
|
-
|
312
|
-
|
311
|
+
it_ 69
|
312
|
+
gli 69
|
313
313
|
ist 68
|
314
|
-
|
315
|
-
|
314
|
+
cen 68
|
315
|
+
whi 68
|
316
|
+
der 68
|
317
|
+
ty 67
|
318
|
+
rn 67
|
319
|
+
ntr 67
|
320
|
+
ive 66
|
321
|
+
eg 65
|
316
322
|
_st 65
|
317
|
-
|
323
|
+
ba 64
|
318
324
|
_so 64
|
319
|
-
|
320
|
-
|
321
|
-
|
322
|
-
|
323
|
-
|
325
|
+
lar 64
|
326
|
+
_wo 64
|
327
|
+
int 64
|
328
|
+
ost 64
|
329
|
+
ki 63
|
330
|
+
_ce 63
|
331
|
+
ove 63
|
324
332
|
_si 63
|
325
|
-
ost 63
|
326
|
-
_po 63
|
327
|
-
eg 62
|
328
|
-
ki 62
|
329
|
-
ud 62
|
330
|
-
ty 62
|
331
|
-
ove 62
|
332
333
|
men 62
|
334
|
+
_pe 62
|
335
|
+
ud 62
|
333
336
|
nti 62
|
337
|
+
_le 61
|
338
|
+
ame 61
|
339
|
+
ld_ 61
|
334
340
|
ers 61
|
335
|
-
|
336
|
-
cou 61
|
337
|
-
pro 60
|
338
|
-
ld_ 60
|
339
|
-
rin 60
|
341
|
+
_br 61
|
340
342
|
has 60
|
341
|
-
|
343
|
+
cou 60
|
344
|
+
rin 60
|
345
|
+
ear 60
|
346
|
+
pro 60
|
342
347
|
rm 60
|
343
|
-
|
344
|
-
|
348
|
+
gr 60
|
349
|
+
rou 59
|
350
|
+
_lo 59
|
345
351
|
ern 59
|
352
|
+
rd 59
|
346
353
|
_al 59
|
347
|
-
ort 59
|
348
|
-
lat 58
|
349
|
-
gr 58
|
350
|
-
_pe 58
|
351
|
-
bo 58
|
352
354
|
ug 58
|
353
355
|
ine 58
|
356
|
+
bo 58
|
357
|
+
nal 57
|
358
|
+
kin 57
|
359
|
+
ort 57
|
360
|
+
ue 57
|
354
361
|
ica 57
|
355
|
-
|
356
|
-
|
362
|
+
sc 56
|
363
|
+
wor 56
|
357
364
|
ect 56
|
358
|
-
|
359
|
-
kin 56
|
365
|
+
c_ 56
|
360
366
|
clu 56
|
361
|
-
|
362
|
-
oth 56
|
363
|
-
ue 56
|
364
|
-
av 55
|
365
|
-
_le 55
|
366
|
-
_lo 55
|
367
|
+
uri 56
|
367
368
|
uch 55
|
368
|
-
|
369
|
-
|
370
|
-
|
371
|
-
|
372
|
-
|
373
|
-
|
374
|
-
|
375
|
-
|
369
|
+
av 55
|
370
|
+
cal 55
|
371
|
+
eve 55
|
372
|
+
bri 55
|
373
|
+
se_ 55
|
374
|
+
oth 55
|
375
|
+
p_ 54
|
376
|
+
uni 54
|
377
|
+
com 54
|
378
|
+
eat 53
|
379
|
+
ona 53
|
380
|
+
ls 53
|
376
381
|
wer 53
|
382
|
+
pu 53
|
383
|
+
cr 53
|
384
|
+
rie 53
|
377
385
|
his 53
|
378
|
-
|
379
|
-
|
380
|
-
|
381
|
-
c_ 52
|
386
|
+
ula 53
|
387
|
+
de_ 53
|
388
|
+
_ca 52
|
382
389
|
ori 52
|
390
|
+
rc 52
|
391
|
+
ex 52
|
392
|
+
ide 51
|
393
|
+
_ki 51
|
394
|
+
rg 51
|
395
|
+
lon 51
|
383
396
|
_at 51
|
384
|
-
|
385
|
-
nal 51
|
386
|
-
tra 51
|
387
|
-
sed 51
|
388
|
-
ls 51
|
389
|
-
rc 51
|
397
|
+
ty_ 51
|
390
398
|
ncl 51
|
391
|
-
|
392
|
-
|
393
|
-
hic 50
|
394
|
-
ga 50
|
395
|
-
lud 50
|
396
|
-
unt 50
|
397
|
-
bl 50
|
398
|
-
suc 50
|
399
|
-
_ki 50
|
400
|
-
de_ 49
|
399
|
+
_ch 51
|
400
|
+
tra 51
|