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/finnish.lm
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 988
|
2
2
|
a 476
|
3
3
|
i 448
|
4
4
|
t 395
|
@@ -10,391 +10,391 @@ u 215
|
|
10
10
|
k 210
|
11
11
|
o 209
|
12
12
|
� 163
|
13
|
+
n_ 141
|
13
14
|
m 134
|
14
|
-
n_ 130
|
15
15
|
v 99
|
16
|
+
a_ 93
|
16
17
|
y 82
|
17
|
-
a_ 79
|
18
|
-
an 78
|
19
18
|
r 78
|
20
19
|
ta 78
|
20
|
+
an 77
|
21
21
|
h 76
|
22
22
|
st 75
|
23
23
|
in 73
|
24
|
-
en 68
|
25
24
|
is 68
|
25
|
+
en 68
|
26
26
|
p 67
|
27
27
|
j 61
|
28
28
|
it 58
|
29
29
|
si 54
|
30
|
+
_k 54
|
30
31
|
aa 53
|
31
32
|
tt 51
|
33
|
+
i_ 50
|
32
34
|
ll 49
|
33
35
|
li 48
|
36
|
+
en_ 48
|
34
37
|
se 47
|
35
|
-
_k 46
|
36
|
-
en_ 46
|
37
|
-
mi 45
|
38
38
|
va 45
|
39
|
+
mi 45
|
39
40
|
ka 45
|
40
|
-
|
41
|
+
_t 44
|
41
42
|
t� 44
|
42
|
-
|
43
|
-
_t 42
|
44
|
-
el 42
|
45
|
-
ai 42
|
43
|
+
te 44
|
46
44
|
tu 42
|
45
|
+
ai 42
|
46
|
+
el 42
|
47
47
|
oi 40
|
48
48
|
. 40
|
49
49
|
es 39
|
50
|
+
an_ 39
|
51
|
+
�_ 38
|
52
|
+
_o 37
|
50
53
|
ma 37
|
51
|
-
|
52
|
-
|
53
|
-
d 33
|
54
|
-
_o 33
|
55
|
-
il 33
|
54
|
+
._ 36
|
55
|
+
_v 34
|
56
56
|
to 33
|
57
|
+
il 33
|
58
|
+
d 33
|
57
59
|
et 33
|
60
|
+
t_ 33
|
58
61
|
ki 32
|
59
|
-
|
62
|
+
_s 32
|
60
63
|
al 32
|
64
|
+
,_ 32
|
61
65
|
, 32
|
62
|
-
la 31
|
63
66
|
on 31
|
64
|
-
|
65
|
-
ik 30
|
67
|
+
la 31
|
66
68
|
us 30
|
67
|
-
|
69
|
+
ks 30
|
70
|
+
ja 29
|
68
71
|
ku 29
|
69
|
-
im 29
|
70
72
|
ri 29
|
71
|
-
ja 29
|
72
73
|
sa 29
|
73
|
-
|
74
|
-
|
74
|
+
_e 28
|
75
|
+
_p 28
|
75
76
|
ss 28
|
77
|
+
e_ 28
|
78
|
+
ik 28
|
79
|
+
im 28
|
80
|
+
at 28
|
76
81
|
ol 28
|
77
|
-
,_ 27
|
78
82
|
le 27
|
79
83
|
uu 27
|
80
|
-
|
81
|
-
nn 26
|
84
|
+
lu 26
|
82
85
|
ist 26
|
86
|
+
nn 26
|
83
87
|
ti 26
|
84
|
-
|
85
|
-
lu 26
|
88
|
+
na 25
|
86
89
|
aan 25
|
87
|
-
ko 25
|
88
|
-
._ 25
|
89
90
|
sta 25
|
90
|
-
|
91
|
-
|
92
|
-
|
91
|
+
ko 25
|
92
|
+
_j 24
|
93
|
+
_m 24
|
94
|
+
as 23
|
93
95
|
ii 23
|
96
|
+
_h 22
|
97
|
+
in_ 22
|
94
98
|
uo 22
|
95
|
-
|
96
|
-
_j 22
|
97
|
-
un 21
|
98
|
-
_h 21
|
99
|
-
ei 21
|
100
|
-
ke 21
|
99
|
+
ta_ 22
|
101
100
|
ut 21
|
101
|
+
ke 21
|
102
|
+
ei 21
|
103
|
+
un 21
|
102
104
|
ne 21
|
105
|
+
nk 20
|
106
|
+
_va 20
|
103
107
|
ssa 20
|
104
|
-
in_ 20
|
105
|
-
__ 19
|
106
|
-
os 19
|
107
108
|
ha 19
|
108
|
-
|
109
|
-
|
110
|
-
|
111
|
-
me 18
|
112
|
-
am 18
|
109
|
+
os 19
|
110
|
+
v� 18
|
111
|
+
ia 18
|
113
112
|
tta 18
|
114
|
-
|
113
|
+
_a 18
|
114
|
+
me 18
|
115
115
|
t�_ 18
|
116
|
-
ia 18
|
117
116
|
ar 18
|
118
|
-
|
117
|
+
on_ 18
|
118
|
+
ak 18
|
119
119
|
sk 17
|
120
|
-
ty 17
|
121
|
-
nt 17
|
122
|
-
oim 17
|
123
|
-
�� 17
|
124
120
|
� 17
|
125
|
-
|
121
|
+
_l 17
|
126
122
|
l� 17
|
123
|
+
ty 17
|
127
124
|
er 17
|
125
|
+
ie 17
|
126
|
+
�� 17
|
127
|
+
oim 17
|
128
128
|
_ka 16
|
129
|
-
ksi 16
|
130
|
-
_l 16
|
131
129
|
yt 16
|
132
|
-
|
130
|
+
ksi 16
|
131
|
+
nt 16
|
133
132
|
om 16
|
134
133
|
ul 16
|
134
|
+
am 16
|
135
135
|
lli 16
|
136
|
-
toi 15
|
137
|
-
ste 15
|
138
|
-
K 15
|
139
|
-
aan_ 15
|
140
|
-
ee 15
|
141
|
-
_a 15
|
142
|
-
taa 15
|
143
136
|
vi 15
|
144
|
-
|
137
|
+
_ja 15
|
145
138
|
ise 15
|
146
|
-
|
139
|
+
taa 15
|
147
140
|
ell 15
|
148
|
-
|
149
|
-
|
150
|
-
|
151
|
-
|
141
|
+
aan_ 15
|
142
|
+
imi 15
|
143
|
+
toi 15
|
144
|
+
ee 15
|
145
|
+
de 15
|
146
|
+
ais 15
|
147
|
+
ste 15
|
148
|
+
K 15
|
149
|
+
ja_ 15
|
152
150
|
min 14
|
153
|
-
|
154
|
-
|
155
|
-
|
151
|
+
_y 14
|
152
|
+
ett 14
|
153
|
+
pa 14
|
156
154
|
oimi 14
|
155
|
+
O 14
|
156
|
+
ni 14
|
157
|
+
T 14
|
158
|
+
itt 14
|
157
159
|
_on 14
|
160
|
+
est 14
|
158
161
|
lla 14
|
159
|
-
T 14
|
160
|
-
on_ 14
|
161
|
-
O 14
|
162
|
-
_ja 14
|
163
|
-
lt 13
|
164
|
-
s� 13
|
165
162
|
toim 13
|
166
|
-
em 13
|
167
|
-
kse 13
|
168
|
-
ok 13
|
169
163
|
_ol 13
|
170
|
-
|
164
|
+
au 13
|
165
|
+
s� 13
|
166
|
+
kse 13
|
167
|
+
uk 13
|
171
168
|
su 13
|
169
|
+
_ko 13
|
170
|
+
lt 13
|
172
171
|
all 13
|
172
|
+
ok 13
|
173
|
+
sa_ 13
|
173
174
|
_to 13
|
174
|
-
|
175
|
-
|
176
|
-
|
177
|
-
|
178
|
-
|
179
|
-
|
180
|
-
I 12
|
181
|
-
nki 12
|
175
|
+
je 13
|
176
|
+
em 13
|
177
|
+
si_ 13
|
178
|
+
_ha 13
|
179
|
+
le_ 12
|
180
|
+
E 12
|
182
181
|
sen 12
|
183
|
-
|
184
|
-
|
182
|
+
I 12
|
183
|
+
_on_ 12
|
184
|
+
ssa_ 12
|
185
|
+
ot 12
|
186
|
+
toimi 12
|
187
|
+
_ja_ 12
|
185
188
|
iin 12
|
186
|
-
|
187
|
-
|
188
|
-
|
189
|
-
|
190
|
-
tus 11
|
191
|
-
nna 11
|
192
|
-
p� 11
|
189
|
+
vo 12
|
190
|
+
kk 12
|
191
|
+
nki 12
|
192
|
+
aa_ 11
|
193
193
|
ust 11
|
194
|
-
av 11
|
195
|
-
_ja_ 11
|
196
|
-
lis 11
|
197
|
-
�n 11
|
198
194
|
�l 11
|
199
|
-
|
195
|
+
nna 11
|
196
|
+
av 11
|
197
|
+
p� 11
|
200
198
|
up 11
|
201
|
-
|
199
|
+
lis 11
|
200
|
+
a. 11
|
201
|
+
_tu 11
|
202
202
|
ht 11
|
203
|
+
_K 11
|
204
|
+
ten 11
|
205
|
+
�n 11
|
203
206
|
he 11
|
207
|
+
mis 11
|
208
|
+
ksi_ 11
|
209
|
+
ts 11
|
204
210
|
�i 11
|
211
|
+
tt� 11
|
205
212
|
iv 11
|
206
|
-
|
207
|
-
|
213
|
+
sta_ 11
|
214
|
+
tus 11
|
215
|
+
�t 10
|
216
|
+
a, 10
|
217
|
+
pi 10
|
218
|
+
ama 10
|
219
|
+
_ma 10
|
220
|
+
nne 10
|
221
|
+
lin 10
|
222
|
+
at_ 10
|
223
|
+
yy 10
|
208
224
|
_toim 10
|
209
225
|
yh 10
|
210
|
-
|
211
|
-
|
212
|
-
�t 10
|
213
|
-
�v 10
|
226
|
+
_n 10
|
227
|
+
_toi 10
|
214
228
|
lle 10
|
215
|
-
|
229
|
+
ast 10
|
230
|
+
mm 10
|
216
231
|
ah 10
|
217
|
-
|
218
|
-
|
219
|
-
|
232
|
+
a._ 10
|
233
|
+
�v 10
|
234
|
+
a,_ 10
|
220
235
|
j� 10
|
221
|
-
lin 10
|
222
|
-
a, 10
|
223
236
|
aj 10
|
224
|
-
|
225
|
-
|
226
|
-
|
227
|
-
|
228
|
-
|
237
|
+
iks 9
|
238
|
+
kau 9
|
239
|
+
�. 9
|
240
|
+
hu 9
|
241
|
+
eri 9
|
242
|
+
_ku 9
|
229
243
|
uut 9
|
230
|
-
|
231
|
-
le_ 9
|
244
|
+
u_ 9
|
232
245
|
mu 9
|
233
|
-
|
246
|
+
ite 9
|
234
247
|
io 9
|
248
|
+
ra 9
|
235
249
|
_ta 9
|
236
250
|
hd 9
|
237
|
-
|
238
|
-
ra 9
|
239
|
-
V 9
|
251
|
+
ole 9
|
240
252
|
st� 9
|
241
|
-
|
242
|
-
|
243
|
-
|
244
|
-
|
245
|
-
|
253
|
+
oj 9
|
254
|
+
�._ 9
|
255
|
+
H 9
|
256
|
+
oit 9
|
257
|
+
sti 9
|
246
258
|
S 9
|
247
|
-
at_ 9
|
248
259
|
voi 9
|
249
|
-
|
250
|
-
hu 9
|
251
|
-
H 9
|
252
|
-
sa_ 9
|
253
|
-
ole 9
|
254
|
-
ite 9
|
260
|
+
V 9
|
255
261
|
eh 9
|
256
|
-
|
257
|
-
|
258
|
-
oit 9
|
259
|
-
n. 8
|
260
|
-
van 8
|
261
|
-
kaup 8
|
262
|
-
iksi 8
|
263
|
-
�r 8
|
262
|
+
alli 9
|
263
|
+
uks 9
|
264
264
|
ari 8
|
265
|
-
_si 8
|
266
|
-
sia 8
|
267
|
-
ou 8
|
268
265
|
stu 8
|
269
|
-
|
270
|
-
|
271
|
-
|
272
|
-
no 8
|
273
|
-
ses 8
|
274
|
-
esk 8
|
266
|
+
nen 8
|
267
|
+
�r 8
|
268
|
+
ine 8
|
275
269
|
lai 8
|
276
|
-
ess 8
|
277
|
-
rk 8
|
278
270
|
ila 8
|
279
|
-
|
280
|
-
hal 8
|
281
|
-
A 8
|
282
|
-
ank 8
|
283
|
-
ulu 8
|
284
|
-
isi 8
|
285
|
-
uv 8
|
271
|
+
ou 8
|
286
272
|
L 8
|
287
|
-
|
288
|
-
|
289
|
-
|
290
|
-
|
291
|
-
|
292
|
-
ien 8
|
293
|
-
kin 8
|
273
|
+
esk 8
|
274
|
+
kaup 8
|
275
|
+
_si 8
|
276
|
+
ank 8
|
277
|
+
pe 8
|
294
278
|
M 8
|
295
|
-
aup 8
|
296
279
|
iste 8
|
297
|
-
|
298
|
-
|
299
|
-
|
300
|
-
t�v 8
|
280
|
+
kin 8
|
281
|
+
lle_ 8
|
282
|
+
ien 8
|
301
283
|
ur 8
|
284
|
+
aup 8
|
285
|
+
ess 8
|
302
286
|
N 8
|
303
|
-
|
287
|
+
k� 8
|
288
|
+
A 8
|
289
|
+
rk 8
|
290
|
+
nta 8
|
304
291
|
ss� 8
|
305
|
-
|
292
|
+
oli 8
|
293
|
+
hal 8
|
294
|
+
sia 8
|
295
|
+
uv 8
|
296
|
+
van 8
|
297
|
+
nen_ 8
|
298
|
+
ses 8
|
299
|
+
n._ 8
|
300
|
+
no 8
|
306
301
|
s_ 8
|
307
|
-
|
308
|
-
|
309
|
-
|
310
|
-
|
311
|
-
|
312
|
-
|
313
|
-
|
314
|
-
|
315
|
-
|
316
|
-
|
302
|
+
ulu 8
|
303
|
+
iksi_ 8
|
304
|
+
ttaa 8
|
305
|
+
iksi 8
|
306
|
+
t�v 8
|
307
|
+
n, 8
|
308
|
+
_i 8
|
309
|
+
n,_ 8
|
310
|
+
n. 8
|
311
|
+
isi 8
|
312
|
+
ain 7
|
313
|
+
ost 7
|
314
|
+
taan 7
|
315
|
+
_H 7
|
316
|
+
_E 7
|
317
|
+
y_ 7
|
318
|
+
_et 7
|
317
319
|
ill 7
|
318
|
-
|
319
|
-
|
320
|
-
|
321
|
-
|
322
|
-
|
320
|
+
lm 7
|
321
|
+
ns 7
|
322
|
+
n� 7
|
323
|
+
suu 7
|
324
|
+
til 7
|
323
325
|
sku 7
|
324
|
-
|
325
|
-
_yh 7
|
326
|
-
a,_ 7
|
327
|
-
vai 7
|
328
|
-
ten_ 7
|
329
|
-
ri_ 7
|
326
|
+
vat 7
|
330
327
|
inen_ 7
|
331
328
|
rj 7
|
332
|
-
|
333
|
-
|
329
|
+
sen_ 7
|
330
|
+
ita 7
|
331
|
+
inn 7
|
332
|
+
ella 7
|
333
|
+
P 7
|
334
334
|
oll 7
|
335
|
-
|
336
|
-
|
337
|
-
|
338
|
-
|
339
|
-
taan 7
|
340
|
-
m� 7
|
335
|
+
_T 7
|
336
|
+
ten_ 7
|
337
|
+
_V 7
|
338
|
+
een 7
|
341
339
|
inen 7
|
342
|
-
|
340
|
+
pp 7
|
343
341
|
ll� 7
|
344
|
-
suu 7
|
345
|
-
a._ 7
|
346
|
-
lm 7
|
347
|
-
inn 7
|
348
342
|
la_ 7
|
343
|
+
maa 7
|
349
344
|
lo 7
|
350
345
|
ava 7
|
351
346
|
tav 7
|
352
|
-
|
347
|
+
ukse 7
|
353
348
|
sit 7
|
354
|
-
|
355
|
-
|
349
|
+
ui 7
|
350
|
+
_yh 7
|
351
|
+
ri_ 7
|
352
|
+
_se 7
|
353
|
+
iss 7
|
354
|
+
m� 7
|
355
|
+
pu 7
|
356
|
+
�s 7
|
357
|
+
aka 7
|
358
|
+
tel 7
|
359
|
+
vai 7
|
356
360
|
lla_ 7
|
357
|
-
|
358
|
-
|
361
|
+
jo 7
|
362
|
+
_r 7
|
363
|
+
J 7
|
364
|
+
omi 7
|
359
365
|
so 7
|
366
|
+
kan 7
|
367
|
+
lais 7
|
368
|
+
�v� 7
|
369
|
+
_u 7
|
360
370
|
int 7
|
361
|
-
ukse 7
|
362
|
-
kin_ 6
|
363
|
-
nis 6
|
364
371
|
mme 6
|
365
|
-
|
366
|
-
|
367
|
-
|
368
|
-
|
369
|
-
|
370
|
-
|
371
|
-
lan 6
|
372
|
-
_-_ 6
|
373
|
-
sy 6
|
374
|
-
nist 6
|
375
|
-
tee 6
|
376
|
-
_T 6
|
377
|
-
iku 6
|
378
|
-
_E 6
|
379
|
-
mar 6
|
380
|
-
_l� 6
|
372
|
+
mari 6
|
373
|
+
mme_ 6
|
374
|
+
ti_ 6
|
375
|
+
ima 6
|
376
|
+
_su 6
|
377
|
+
aja 6
|
381
378
|
�li 6
|
382
|
-
|
379
|
+
kus 6
|
383
380
|
ih 6
|
384
|
-
|
385
|
-
Ke 6
|
386
|
-
sten 6
|
387
|
-
its 6
|
388
|
-
assa 6
|
389
|
-
op 6
|
390
|
-
_es 6
|
381
|
+
et_ 6
|
391
382
|
ytt 6
|
383
|
+
den 6
|
384
|
+
mar 6
|
385
|
+
l�_ 6
|
392
386
|
_vo 6
|
393
|
-
|
394
|
-
|
395
|
-
mari 6
|
396
|
-
ev 6
|
397
|
-
po 6
|
398
|
-
ska 6
|
387
|
+
nan_ 6
|
388
|
+
me_ 6
|
399
389
|
ista 6
|
400
|
-
|
390
|
+
lan 6
|
391
|
+
_mu 6
|
392
|
+
iit 6
|
393
|
+
unn 6
|
394
|
+
esi 6
|
395
|
+
ho 6
|
396
|
+
assa 6
|
397
|
+
oje 6
|
398
|
+
it� 6
|
399
|
+
sy 6
|
400
|
+
Ke 6
|