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/finnish.lm
CHANGED
@@ -1,400 +1,400 @@
|
|
1
|
-
_
|
2
|
-
a
|
3
|
-
i
|
4
|
-
t
|
5
|
-
s
|
6
|
-
n
|
7
|
-
e
|
8
|
-
u
|
9
|
-
l
|
10
|
-
o
|
11
|
-
k
|
12
|
-
n_
|
13
|
-
a_
|
14
|
-
m
|
15
|
-
ä
|
16
|
-
v
|
17
|
-
|
18
|
-
|
19
|
-
j
|
20
|
-
is
|
21
|
-
ta
|
22
|
-
in
|
23
|
-
_s
|
1
|
+
_ 17816
|
2
|
+
a 8207
|
3
|
+
i 6998
|
4
|
+
t 5894
|
5
|
+
s 5774
|
6
|
+
n 5584
|
7
|
+
e 5077
|
8
|
+
u 4260
|
9
|
+
l 4242
|
10
|
+
o 3945
|
11
|
+
k 3180
|
12
|
+
n_ 2817
|
13
|
+
a_ 2656
|
14
|
+
m 2463
|
15
|
+
ä 2245
|
16
|
+
v 1759
|
17
|
+
en 1462
|
18
|
+
r 1462
|
19
|
+
j 1426
|
20
|
+
is 1363
|
21
|
+
ta 1237
|
22
|
+
in 1151
|
23
|
+
_s 1149
|
24
24
|
st 1103
|
25
|
-
y
|
26
|
-
en_
|
27
|
-
p
|
28
|
-
h
|
29
|
-
al
|
30
|
-
_k
|
31
|
-
i_
|
25
|
+
y 1045
|
26
|
+
en_ 1007
|
27
|
+
p 997
|
28
|
+
h 952
|
29
|
+
al 932
|
30
|
+
_k 910
|
31
|
+
i_ 882
|
32
32
|
an 874
|
33
|
-
si
|
34
|
-
li
|
33
|
+
si 868
|
34
|
+
li 852
|
35
35
|
_j 847
|
36
|
-
uo
|
37
|
-
ll
|
38
|
-
sa
|
39
|
-
ja
|
40
|
-
|
41
|
-
|
36
|
+
uo 833
|
37
|
+
ll 791
|
38
|
+
sa 777
|
39
|
+
ja 771
|
40
|
+
aa 747
|
41
|
+
se 746
|
42
42
|
va 745
|
43
|
-
_m
|
44
|
-
_v
|
45
|
-
ä_
|
46
|
-
t_
|
47
|
-
tt
|
48
|
-
|
49
|
-
it
|
50
|
-
|
43
|
+
_m 725
|
44
|
+
_v 710
|
45
|
+
ä_ 709
|
46
|
+
t_ 698
|
47
|
+
tt 689
|
48
|
+
ai 681
|
49
|
+
it 680
|
50
|
+
ma 679
|
51
51
|
la 675
|
52
|
-
su
|
53
|
-
_o
|
54
|
-
ti 647
|
52
|
+
su 675
|
53
|
+
_o 668
|
55
54
|
on 641
|
56
|
-
|
57
|
-
|
55
|
+
ti 641
|
56
|
+
ka 637
|
57
|
+
te 636
|
58
58
|
ja_ 598
|
59
|
-
ta_
|
60
|
-
in_
|
61
|
-
tu
|
62
|
-
_t
|
63
|
-
_l
|
64
|
-
el
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
om
|
69
|
-
es
|
70
|
-
oi
|
71
|
-
at
|
59
|
+
ta_ 593
|
60
|
+
in_ 583
|
61
|
+
tu 579
|
62
|
+
_t 576
|
63
|
+
_l 559
|
64
|
+
el 552
|
65
|
+
d 539
|
66
|
+
_su 538
|
67
|
+
_ja 534
|
68
|
+
om 533
|
69
|
+
es 529
|
70
|
+
oi 520
|
71
|
+
at 501
|
72
|
+
me 494
|
72
73
|
_a 494
|
73
|
-
|
74
|
-
et
|
75
|
-
ss 474
|
76
|
-
as 473
|
74
|
+
ss 480
|
75
|
+
et 479
|
77
76
|
ist 470
|
78
|
-
ku
|
79
|
-
|
77
|
+
ku 468
|
78
|
+
as 467
|
79
|
+
uu 467
|
80
80
|
ko 460
|
81
81
|
mi 454
|
82
82
|
lu 451
|
83
|
-
suo
|
84
|
-
an_
|
85
|
-
_p
|
86
|
-
uom
|
87
|
-
|
88
|
-
|
89
|
-
|
90
|
-
il
|
91
|
-
ii 409
|
83
|
+
suo 443
|
84
|
+
an_ 437
|
85
|
+
_p 436
|
86
|
+
uom 430
|
87
|
+
un 420
|
88
|
+
nt 417
|
89
|
+
tä 415
|
90
|
+
il 413
|
92
91
|
on_ 408
|
93
|
-
|
92
|
+
ii 408
|
93
|
+
us 404
|
94
94
|
sta 402
|
95
|
-
ik
|
96
|
-
|
97
|
-
|
98
|
-
|
99
|
-
|
100
|
-
|
101
|
-
|
95
|
+
ik 400
|
96
|
+
ki 399
|
97
|
+
ne 398
|
98
|
+
ut 396
|
99
|
+
sa_ 394
|
100
|
+
to 386
|
101
|
+
_e 386
|
102
102
|
ks 386
|
103
|
-
ke
|
104
|
-
os 370
|
105
|
-
ol 370
|
103
|
+
ke 373
|
106
104
|
le 369
|
107
|
-
|
108
|
-
nn
|
105
|
+
ol 368
|
106
|
+
nn 368
|
107
|
+
ssa 367
|
108
|
+
os 367
|
109
109
|
ei 352
|
110
110
|
na 346
|
111
111
|
ee 345
|
112
112
|
ri 339
|
113
|
-
jo
|
113
|
+
jo 322
|
114
114
|
ul 320
|
115
115
|
_va 315
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
vu
|
120
|
-
|
121
|
-
|
122
|
-
ty
|
116
|
+
ö 311
|
117
|
+
er 311
|
118
|
+
ise 310
|
119
|
+
vu 302
|
120
|
+
_on 297
|
121
|
+
_n 297
|
122
|
+
ty 294
|
123
123
|
im 292
|
124
|
-
lli
|
124
|
+
lli 288
|
125
125
|
ia 288
|
126
|
-
de
|
127
|
-
lis
|
128
|
-
|
129
|
-
ome 271
|
126
|
+
de 287
|
127
|
+
lis 284
|
128
|
+
ome 275
|
130
129
|
at_ 271
|
131
|
-
|
130
|
+
s_ 271
|
131
|
+
ää 267
|
132
132
|
ak 263
|
133
|
-
_h
|
134
|
-
lä
|
135
|
-
mu
|
136
|
-
|
137
|
-
|
138
|
-
|
133
|
+
_h 261
|
134
|
+
lä 259
|
135
|
+
mu 256
|
136
|
+
sä 251
|
137
|
+
ot 251
|
138
|
+
la_ 247
|
139
|
+
lla 246
|
139
140
|
aan 246
|
140
|
-
|
141
|
-
|
142
|
-
_ka
|
143
|
-
|
144
|
-
sen
|
145
|
-
vi
|
146
|
-
|
147
|
-
|
148
|
-
_al 226
|
149
|
-
ni 225
|
141
|
+
ie 244
|
142
|
+
e_ 237
|
143
|
+
_ka 236
|
144
|
+
all 233
|
145
|
+
sen 232
|
146
|
+
vi 230
|
147
|
+
ais 229
|
148
|
+
_al 225
|
150
149
|
ur 224
|
151
|
-
|
152
|
-
|
153
|
-
|
150
|
+
ni 222
|
151
|
+
uv 219
|
152
|
+
maa 218
|
153
|
+
_ma 218
|
154
154
|
ksi 217
|
155
155
|
lt 215
|
156
156
|
_ku 214
|
157
|
-
si_ 213
|
158
157
|
est 212
|
158
|
+
si_ 210
|
159
159
|
_jo 209
|
160
|
-
tä_
|
161
|
-
pi
|
162
|
-
än
|
163
|
-
vä
|
164
|
-
sk 201
|
160
|
+
tä_ 207
|
161
|
+
pi 205
|
162
|
+
än 204
|
163
|
+
vä 202
|
165
164
|
vat 201
|
166
|
-
|
165
|
+
sk 199
|
167
166
|
_mu 198
|
168
|
-
uk
|
167
|
+
uk 197
|
168
|
+
ra 197
|
169
169
|
_r 196
|
170
|
-
tta
|
171
|
-
ns
|
172
|
-
|
173
|
-
|
174
|
-
ok 193
|
170
|
+
tta 195
|
171
|
+
ns 194
|
172
|
+
men 193
|
173
|
+
een 193
|
175
174
|
ht 191
|
176
|
-
|
175
|
+
ar 191
|
176
|
+
ok 191
|
177
|
+
pa 191
|
177
178
|
ui 189
|
178
|
-
|
179
|
-
|
180
|
-
|
181
|
-
|
179
|
+
ia_ 187
|
180
|
+
itt 185
|
181
|
+
val 184
|
182
|
+
au 182
|
182
183
|
lo 182
|
183
|
-
|
184
|
-
ti_ 179
|
184
|
+
_y 181
|
185
185
|
aa_ 179
|
186
|
-
|
187
|
-
|
188
|
-
|
189
|
-
|
190
|
-
|
191
|
-
|
192
|
-
isi
|
193
|
-
ala
|
194
|
-
|
195
|
-
iin
|
196
|
-
|
186
|
+
mm 179
|
187
|
+
ti_ 179
|
188
|
+
no 177
|
189
|
+
kk 173
|
190
|
+
tti 173
|
191
|
+
ha 172
|
192
|
+
isi 171
|
193
|
+
ala 170
|
194
|
+
suu 169
|
195
|
+
iin 168
|
196
|
+
ill 168
|
197
197
|
o_ 164
|
198
|
-
|
198
|
+
_ko 163
|
199
199
|
kä 163
|
200
|
+
am 163
|
200
201
|
lai 162
|
201
|
-
|
202
|
-
|
203
|
-
|
204
|
-
|
205
|
-
den 159
|
206
|
-
oli 158
|
207
|
-
mä 156
|
202
|
+
_sa 162
|
203
|
+
na_ 161
|
204
|
+
den 161
|
205
|
+
oli 157
|
208
206
|
g 156
|
209
207
|
pu 156
|
210
|
-
|
211
|
-
|
212
|
-
|
213
|
-
_ta
|
208
|
+
mä 156
|
209
|
+
av 156
|
210
|
+
nen 156
|
211
|
+
_ta 155
|
212
|
+
ine 154
|
213
|
+
vuo 154
|
214
|
+
nk 151
|
214
215
|
iv 150
|
215
|
-
|
216
|
-
|
217
|
-
|
218
|
-
|
219
|
-
|
220
|
-
_lu 146
|
216
|
+
ell 149
|
217
|
+
et_ 148
|
218
|
+
ts 148
|
219
|
+
sti 147
|
220
|
+
aj 146
|
221
221
|
_tu 145
|
222
|
-
|
223
|
-
|
224
|
-
_vu
|
225
|
-
|
226
|
-
|
227
|
-
he 143
|
222
|
+
ess 145
|
223
|
+
_lu 145
|
224
|
+
_vu 145
|
225
|
+
he 144
|
226
|
+
so 143
|
228
227
|
eu 142
|
229
|
-
|
230
|
-
|
231
|
-
|
232
|
-
|
233
|
-
|
234
|
-
|
235
|
-
|
236
|
-
|
237
|
-
|
238
|
-
ve 134
|
239
|
-
_ol 134
|
228
|
+
lk 142
|
229
|
+
ast 142
|
230
|
+
_se 139
|
231
|
+
ste 138
|
232
|
+
oma 138
|
233
|
+
un_ 137
|
234
|
+
kan 136
|
235
|
+
rk 135
|
236
|
+
jä 135
|
240
237
|
lle 134
|
241
|
-
|
242
|
-
|
243
|
-
|
238
|
+
ve 134
|
239
|
+
nna 133
|
240
|
+
_ol 132
|
241
|
+
ro 132
|
242
|
+
io 131
|
244
243
|
äl 131
|
245
|
-
|
246
|
-
stä 129
|
247
|
-
ois 129
|
244
|
+
_ke 130
|
248
245
|
ät 129
|
246
|
+
eis 129
|
247
|
+
stä 129
|
249
248
|
alu 128
|
250
|
-
|
251
|
-
|
249
|
+
ois 128
|
250
|
+
ou 128
|
252
251
|
ain 126
|
253
252
|
ten 126
|
254
|
-
ou 126
|
255
253
|
lm 126
|
254
|
+
ek 125
|
255
|
+
yö 125
|
256
256
|
u_ 125
|
257
|
-
ett
|
257
|
+
ett 125
|
258
258
|
vo 124
|
259
|
-
|
260
|
-
|
261
|
-
|
262
|
-
|
259
|
+
ru 124
|
260
|
+
ir 123
|
261
|
+
utt 122
|
262
|
+
_ 122
|
263
263
|
taa 122
|
264
|
-
|
265
|
-
äi 121
|
264
|
+
122
|
266
265
|
kun 121
|
266
|
+
or 120
|
267
|
+
äi 120
|
267
268
|
mis 119
|
269
|
+
ent 119
|
268
270
|
ue 118
|
269
|
-
_ 118
|
270
|
-
118
|
271
|
-
tel 117
|
272
|
-
_i 117
|
273
271
|
op 117
|
272
|
+
_i 117
|
274
273
|
em 117
|
274
|
+
kse 116
|
275
275
|
yt 116
|
276
|
-
|
277
|
-
kse 115
|
276
|
+
tel 116
|
278
277
|
le_ 115
|
278
|
+
od 115
|
279
|
+
sin 114
|
279
280
|
oh 114
|
280
|
-
|
281
|
-
|
281
|
+
li_ 113
|
282
|
+
än_ 113
|
282
283
|
_me 112
|
283
|
-
ust
|
284
|
-
|
285
|
-
li_ 111
|
284
|
+
ust 112
|
285
|
+
nta 111
|
286
286
|
aik 111
|
287
|
-
_u 110
|
288
287
|
lue 110
|
289
|
-
|
288
|
+
po 110
|
289
|
+
oit 110
|
290
290
|
uot 110
|
291
|
-
|
291
|
+
_u 107
|
292
292
|
lin 107
|
293
|
-
|
294
|
-
id 106
|
293
|
+
_si 106
|
295
294
|
ov 106
|
296
|
-
nä
|
297
|
-
|
298
|
-
_si 105
|
299
|
-
yh 105
|
295
|
+
nä 106
|
296
|
+
id 106
|
300
297
|
alt 105
|
301
|
-
|
298
|
+
yh 105
|
299
|
+
mal 105
|
302
300
|
ses 105
|
301
|
+
lii 105
|
303
302
|
_ha 104
|
304
|
-
lii 104
|
305
303
|
ali 104
|
304
|
+
sto 104
|
306
305
|
luv 104
|
307
|
-
|
306
|
+
_la 104
|
307
|
+
hi 104
|
308
|
+
je 103
|
308
309
|
oll 103
|
309
|
-
|
310
|
-
|
311
|
-
je 102
|
312
|
-
mat 101
|
310
|
+
ien 103
|
311
|
+
iss 103
|
313
312
|
lta 101
|
314
|
-
iss 101
|
315
313
|
är 101
|
316
|
-
|
314
|
+
yk 101
|
315
|
+
f 101
|
317
316
|
omi 100
|
318
|
-
|
319
|
-
|
320
|
-
|
317
|
+
kuu 100
|
318
|
+
mat 100
|
319
|
+
sä_ 100
|
320
|
+
int 99
|
321
|
+
ud 99
|
322
|
+
ans 99
|
323
|
+
ka_ 98
|
324
|
+
unn 97
|
321
325
|
lä_ 97
|
322
|
-
kuu 97
|
323
|
-
ttä 96
|
324
|
-
ap 96
|
325
326
|
pe 96
|
326
|
-
|
327
|
-
|
328
|
-
|
329
|
-
|
330
|
-
|
331
|
-
|
332
|
-
|
333
|
-
|
334
|
-
|
327
|
+
ap 96
|
328
|
+
ttä 96
|
329
|
+
äm 95
|
330
|
+
uks 94
|
331
|
+
ita 94
|
332
|
+
toi 94
|
333
|
+
ttu 94
|
334
|
+
ost 94
|
335
|
+
uvu 93
|
335
336
|
uur 93
|
336
|
-
|
337
|
-
|
338
|
-
|
337
|
+
_ 93
|
338
|
+
tai 93
|
339
|
+
_ _ 93
|
339
340
|
tii 91
|
341
|
+
nsa 91
|
340
342
|
eh 91
|
341
|
-
|
342
|
-
ova 90
|
343
|
-
_to 90
|
344
|
-
tet 90
|
345
|
-
ass 90
|
343
|
+
kaa 91
|
346
344
|
mes 90
|
347
|
-
|
348
|
-
|
349
|
-
|
345
|
+
ova 90
|
346
|
+
_to 89
|
347
|
+
ass 89
|
350
348
|
_li 89
|
351
|
-
|
349
|
+
ika 89
|
350
|
+
eli 88
|
352
351
|
ava 88
|
353
|
-
|
354
|
-
|
355
|
-
|
356
|
-
tei 87
|
352
|
+
tei 88
|
353
|
+
tet 88
|
354
|
+
min 88
|
357
355
|
stu 87
|
358
|
-
|
356
|
+
joi 87
|
357
|
+
my 87
|
358
|
+
utu 87
|
359
|
+
_vä 86
|
359
360
|
uri 86
|
361
|
+
kes 85
|
360
362
|
_ov 85
|
363
|
+
re 85
|
361
364
|
ään 85
|
362
|
-
|
363
|
-
|
364
|
-
|
365
|
-
|
366
|
-
|
367
|
-
pä 83
|
365
|
+
yl 85
|
366
|
+
oin 85
|
367
|
+
pä 84
|
368
|
+
sii 83
|
369
|
+
mp 83
|
368
370
|
mi_ 83
|
369
371
|
uon 83
|
370
|
-
sii 83
|
371
372
|
uus 83
|
372
|
-
|
373
|
-
|
373
|
+
ide 81
|
374
|
+
ssä 81
|
374
375
|
ull 81
|
375
376
|
äh 81
|
376
|
-
|
377
|
-
|
377
|
+
ös 81
|
378
|
+
nu 81
|
378
379
|
tal 81
|
379
|
-
llä 81
|
380
|
-
uva 80
|
381
|
-
äk 80
|
382
|
-
osi 80
|
383
|
-
_my 80
|
384
|
-
nu 80
|
385
380
|
imm 80
|
386
|
-
|
387
|
-
|
388
|
-
|
389
|
-
sia
|
381
|
+
uva 80
|
382
|
+
llä 80
|
383
|
+
ude 80
|
384
|
+
sia 80
|
385
|
+
äk 79
|
386
|
+
ij 79
|
387
|
+
saa 79
|
388
|
+
osi 79
|
389
|
+
ih 79
|
390
|
+
_my 79
|
391
|
+
us_ 79
|
390
392
|
_po 78
|
391
|
-
|
392
|
-
ikk 78
|
393
|
-
ih 78
|
393
|
+
ulu 78
|
394
394
|
kau 78
|
395
|
-
|
396
|
-
|
397
|
-
voi 77
|
398
|
-
ama 77
|
399
|
-
onn 77
|
395
|
+
tav 77
|
396
|
+
ikk 77
|
400
397
|
ys 77
|
398
|
+
onn 77
|
399
|
+
ama 77
|
400
|
+
myö 76
|