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/turkish.lm
CHANGED
@@ -1,400 +1,400 @@
|
|
1
|
-
_
|
1
|
+
_ 2134
|
2
2
|
i 470
|
3
3
|
a 439
|
4
4
|
e 316
|
5
5
|
n 276
|
6
|
+
i_ 249
|
6
7
|
l 244
|
7
8
|
r 239
|
9
|
+
_i 218
|
10
|
+
_i_ 181
|
8
11
|
k 175
|
9
12
|
s 172
|
10
13
|
d 148
|
14
|
+
n_ 128
|
11
15
|
t 119
|
12
|
-
__ 114
|
13
16
|
y 113
|
14
17
|
m 110
|
15
|
-
in 107
|
16
18
|
u 105
|
17
|
-
|
18
|
-
i_ 99
|
19
|
+
a_ 98
|
19
20
|
o 97
|
21
|
+
_s 93
|
20
22
|
b 90
|
23
|
+
s_ 87
|
24
|
+
e_ 81
|
21
25
|
ar 75
|
22
|
-
la 73
|
23
26
|
g 73
|
24
|
-
|
25
|
-
|
27
|
+
la 73
|
28
|
+
_b 70
|
26
29
|
an 66
|
27
|
-
a_ 65
|
28
30
|
� 65
|
29
|
-
|
30
|
-
|
31
|
-
|
31
|
+
_s_ 64
|
32
|
+
_g 62
|
33
|
+
_k 60
|
34
|
+
in 59
|
35
|
+
r_ 58
|
36
|
+
k_ 56
|
37
|
+
,_ 54
|
32
38
|
ra 54
|
39
|
+
_, 54
|
33
40
|
, 54
|
41
|
+
_,_ 54
|
42
|
+
_n 53
|
34
43
|
le 52
|
35
|
-
|
44
|
+
_y 50
|
45
|
+
il 49
|
36
46
|
er 48
|
37
|
-
_,_ 48
|
38
|
-
is 48
|
39
47
|
da 48
|
40
|
-
|
48
|
+
_a 45
|
41
49
|
z 44
|
42
|
-
|
43
|
-
ni 43
|
44
|
-
k_ 42
|
45
|
-
li 41
|
46
|
-
in_ 41
|
47
|
-
_k 41
|
48
|
-
en 40
|
49
|
-
di 40
|
50
|
-
nd 40
|
50
|
+
_d 43
|
51
51
|
de 40
|
52
|
-
|
53
|
-
p 39
|
52
|
+
en 40
|
54
53
|
. 39
|
55
|
-
|
54
|
+
p 39
|
55
|
+
_t 39
|
56
|
+
_._ 39
|
57
|
+
nd 39
|
58
|
+
_. 39
|
59
|
+
._ 39
|
60
|
+
_l 38
|
61
|
+
l_ 37
|
56
62
|
lar 37
|
57
|
-
ka 36
|
58
|
-
_s 35
|
59
|
-
r_ 35
|
60
63
|
ya 34
|
61
|
-
|
64
|
+
ri 34
|
65
|
+
ka 34
|
62
66
|
c 33
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
� 30
|
67
|
+
v 33
|
68
|
+
g_ 33
|
69
|
+
u_ 32
|
70
|
+
in_ 31
|
68
71
|
ma 30
|
69
72
|
ak 30
|
73
|
+
� 30
|
74
|
+
_g_ 30
|
75
|
+
bi 30
|
76
|
+
an_ 30
|
77
|
+
ar_ 29
|
70
78
|
ara 29
|
71
79
|
ol 29
|
72
|
-
|
73
|
-
|
74
|
-
as 28
|
75
|
-
gi 28
|
80
|
+
_n_ 28
|
81
|
+
ki 28
|
76
82
|
ler 28
|
77
|
-
|
83
|
+
_o 28
|
78
84
|
h 27
|
85
|
+
eri 27
|
79
86
|
re 27
|
80
87
|
ek 26
|
81
|
-
|
82
|
-
|
83
|
-
|
84
|
-
|
85
|
-
|
86
|
-
|
87
|
-
ba 23
|
88
|
+
si 26
|
89
|
+
ir 26
|
90
|
+
da_ 26
|
91
|
+
li 24
|
92
|
+
_ka 24
|
93
|
+
_m 24
|
88
94
|
me 23
|
89
|
-
|
90
|
-
|
95
|
+
ba 23
|
96
|
+
ni 23
|
97
|
+
on 22
|
91
98
|
leri 22
|
92
|
-
|
99
|
+
_bi 22
|
100
|
+
di 22
|
93
101
|
nda 22
|
94
|
-
|
95
|
-
|
96
|
-
|
97
|
-
� 21
|
98
|
-
ve 21
|
99
|
-
mi 21
|
100
|
-
un 21
|
102
|
+
te 22
|
103
|
+
_v 21
|
104
|
+
f 21
|
101
105
|
al 21
|
102
|
-
se 21
|
103
106
|
en_ 21
|
104
|
-
|
105
|
-
|
107
|
+
ve 21
|
108
|
+
� 21
|
109
|
+
at 20
|
110
|
+
lar_ 20
|
111
|
+
un 20
|
106
112
|
et 20
|
107
|
-
|
113
|
+
t_ 20
|
108
114
|
ay 20
|
109
|
-
|
110
|
-
|
111
|
-
|
115
|
+
_r 20
|
116
|
+
_ya 19
|
117
|
+
_ba 19
|
118
|
+
d_ 19
|
119
|
+
_e 19
|
112
120
|
bu 19
|
113
121
|
ile 19
|
114
|
-
|
115
|
-
|
116
|
-
|
117
|
-
|
118
|
-
|
119
|
-
|
120
|
-
nin 17
|
122
|
+
_ol 19
|
123
|
+
_nd 18
|
124
|
+
_ve 18
|
125
|
+
es 18
|
126
|
+
de_ 18
|
127
|
+
_p 17
|
121
128
|
nu 17
|
122
|
-
|
123
|
-
|
124
|
-
|
125
|
-
|
126
|
-
inda 16
|
127
|
-
iy 16
|
129
|
+
mi 17
|
130
|
+
se 16
|
131
|
+
_nda 16
|
132
|
+
is 16
|
128
133
|
or 16
|
129
|
-
ola 16
|
130
134
|
ye 16
|
131
|
-
|
135
|
+
_� 16
|
136
|
+
_bu 16
|
137
|
+
ola 16
|
138
|
+
y_ 16
|
139
|
+
ki_ 16
|
132
140
|
pa 16
|
133
|
-
|
134
|
-
|
135
|
-
|
141
|
+
ta 15
|
142
|
+
ge 15
|
143
|
+
ak_ 15
|
136
144
|
nl 15
|
137
|
-
|
138
|
-
|
139
|
-
el 15
|
145
|
+
as 15
|
146
|
+
ve_ 15
|
140
147
|
ke 15
|
141
|
-
|
142
|
-
_ba 15
|
143
|
-
ge 15
|
144
|
-
im 15
|
148
|
+
_ve_ 15
|
145
149
|
az 15
|
146
|
-
|
147
|
-
|
148
|
-
|
149
|
-
|
150
|
+
na 15
|
151
|
+
am 15
|
152
|
+
ed 15
|
153
|
+
el 15
|
150
154
|
ko 14
|
151
|
-
|
155
|
+
ik 14
|
156
|
+
as_ 14
|
157
|
+
_ge 14
|
158
|
+
rl 14
|
152
159
|
erin 14
|
153
|
-
|
154
|
-
|
155
|
-
|
156
|
-
|
157
|
-
|
160
|
+
rin 14
|
161
|
+
_ola 13
|
162
|
+
z_ 13
|
163
|
+
_ko 13
|
164
|
+
sa 13
|
165
|
+
nda_ 13
|
166
|
+
rk 13
|
167
|
+
m_ 13
|
168
|
+
y� 13
|
169
|
+
ra_ 13
|
158
170
|
dan 13
|
159
|
-
|
171
|
+
esi 13
|
160
172
|
em 13
|
161
|
-
|
162
|
-
|
163
|
-
|
164
|
-
inin_ 13
|
165
|
-
rk 13
|
173
|
+
iy 13
|
174
|
+
_h 13
|
175
|
+
ad 13
|
166
176
|
yo 13
|
167
|
-
|
168
|
-
ap 13
|
169
|
-
ld 13
|
170
|
-
anl 12
|
171
|
-
_h 12
|
172
|
-
s_ 12
|
173
|
-
_e 12
|
174
|
-
lerin 12
|
177
|
+
ur 12
|
175
178
|
lm 12
|
176
|
-
_p 12
|
177
|
-
ha 12
|
178
|
-
gin 12
|
179
179
|
to 12
|
180
|
-
|
181
|
-
|
180
|
+
ne 12
|
181
|
+
ti 12
|
182
|
+
im 12
|
182
183
|
lara 12
|
183
|
-
|
184
|
-
|
185
|
-
|
184
|
+
anl 12
|
185
|
+
ap 12
|
186
|
+
ha 12
|
187
|
+
_pa 12
|
188
|
+
ld 12
|
189
|
+
lerin 12
|
190
|
+
_de 12
|
186
191
|
ek_ 11
|
187
|
-
|
188
|
-
|
189
|
-
|
190
|
-
|
191
|
-
_ola 11
|
192
|
-
t� 11
|
193
|
-
ag 11
|
192
|
+
_da 11
|
193
|
+
dan_ 11
|
194
|
+
ini 11
|
195
|
+
_bir 11
|
194
196
|
rak 11
|
195
197
|
bir 11
|
196
|
-
|
197
|
-
arin 11
|
198
|
+
ir_ 11
|
198
199
|
tl 11
|
199
|
-
|
200
|
-
_ge 10
|
201
|
-
_si 10
|
202
|
-
af 10
|
203
|
-
ada 10
|
204
|
-
�k 10
|
205
|
-
sl 10
|
200
|
+
t� 11
|
206
201
|
ce 10
|
207
|
-
|
208
|
-
|
209
|
-
|
210
|
-
|
211
|
-
|
202
|
+
er_ 10
|
203
|
+
_ar 10
|
204
|
+
kan 10
|
205
|
+
iz 10
|
206
|
+
�k 10
|
212
207
|
_� 10
|
208
|
+
bil 10
|
213
209
|
lan 10
|
214
|
-
ig 10
|
215
|
-
rin_ 10
|
216
|
-
ni_ 10
|
217
|
-
za 10
|
218
|
-
_bir 10
|
219
210
|
�r 10
|
220
|
-
|
211
|
+
nde 10
|
212
|
+
_il 10
|
221
213
|
ru 10
|
222
|
-
|
214
|
+
nin_ 10
|
215
|
+
nin 10
|
216
|
+
_ba_ 9
|
217
|
+
_te 9
|
218
|
+
si_ 9
|
219
|
+
la_ 9
|
220
|
+
sin 9
|
221
|
+
_f 9
|
222
|
+
_ha 9
|
223
|
+
za 9
|
224
|
+
ya_ 9
|
225
|
+
af 9
|
226
|
+
bu_ 9
|
227
|
+
li_ 9
|
228
|
+
bir_ 9
|
223
229
|
_bir_ 9
|
224
|
-
|
225
|
-
|
226
|
-
|
227
|
-
|
230
|
+
_sa 9
|
231
|
+
ul 9
|
232
|
+
ba_ 9
|
233
|
+
ada 9
|
234
|
+
_bu_ 9
|
235
|
+
_y� 9
|
228
236
|
ec 9
|
237
|
+
_kon 9
|
238
|
+
iler 9
|
229
239
|
kon 9
|
230
|
-
|
231
|
-
|
240
|
+
ala 9
|
241
|
+
_la 9
|
242
|
+
su 9
|
232
243
|
olar 9
|
233
|
-
_de 9
|
234
|
-
sind 9
|
235
|
-
_il 9
|
236
|
-
larin 9
|
237
|
-
isin 9
|
238
|
-
_y� 9
|
239
|
-
bir_ 9
|
240
|
-
ak_ 9
|
241
|
-
ra_ 9
|
242
|
-
li_ 9
|
243
|
-
lk 9
|
244
244
|
rd 9
|
245
|
-
|
246
|
-
unu 8
|
247
|
-
bas 8
|
248
|
-
�e 8
|
249
|
-
asi_ 8
|
250
|
-
zi 8
|
251
|
-
e� 8
|
252
|
-
rla 8
|
253
|
-
bu_ 8
|
254
|
-
_yil 8
|
255
|
-
eni 8
|
256
|
-
ild 8
|
257
|
-
on_ 8
|
245
|
+
eri_ 8
|
258
246
|
nla 8
|
259
|
-
igin 8
|
260
|
-
rini 8
|
261
247
|
onu 8
|
262
|
-
it 8
|
263
|
-
_l 8
|
264
|
-
_di 8
|
265
|
-
_is 8
|
266
|
-
ece 8
|
267
|
-
lik 8
|
268
|
-
lma 8
|
269
|
-
ldi 8
|
270
|
-
ab 8
|
271
|
-
_ha 8
|
272
248
|
lu 8
|
273
|
-
|
274
|
-
|
249
|
+
e� 8
|
250
|
+
ri_ 8
|
251
|
+
ab 8
|
252
|
+
_ra 8
|
253
|
+
on_ 8
|
254
|
+
rak_ 8
|
255
|
+
_nda_ 8
|
256
|
+
_li 8
|
257
|
+
di_ 8
|
258
|
+
_me 8
|
259
|
+
esi_ 8
|
260
|
+
ara_ 8
|
261
|
+
_da_ 8
|
262
|
+
lk 8
|
263
|
+
eki 8
|
264
|
+
un_ 8
|
265
|
+
_y_ 8
|
266
|
+
_t� 8
|
267
|
+
rin_ 8
|
268
|
+
lma 8
|
269
|
+
ci 8
|
270
|
+
�e 8
|
271
|
+
_l_ 8
|
272
|
+
ind 8
|
275
273
|
um 8
|
274
|
+
ama 8
|
275
|
+
_k_ 8
|
276
276
|
edi 8
|
277
|
-
_kon 8
|
278
|
-
eki 8
|
279
|
-
_yi 8
|
280
|
-
iye 8
|
281
|
-
esi_ 8
|
282
|
-
_te 8
|
283
|
-
yil 8
|
284
|
-
sm 8
|
285
|
-
_f 8
|
286
277
|
arak 8
|
287
|
-
|
288
|
-
|
289
|
-
|
290
|
-
|
291
|
-
|
292
|
-
�_
|
293
|
-
|
294
|
-
|
295
|
-
|
296
|
-
|
278
|
+
erin_ 8
|
279
|
+
ye_ 8
|
280
|
+
inin 8
|
281
|
+
inin_ 8
|
282
|
+
ece 8
|
283
|
+
�_ 8
|
284
|
+
leri_ 8
|
285
|
+
eni 8
|
286
|
+
rla 8
|
287
|
+
iye 8
|
288
|
+
_ta 7
|
289
|
+
_bin 7
|
290
|
+
ndan_ 7
|
297
291
|
t�rk 7
|
298
|
-
|
299
|
-
|
300
|
-
|
301
|
-
|
302
|
-
|
303
|
-
sinin 7
|
304
|
-
ge� 7
|
305
|
-
ini_ 7
|
306
|
-
ili 7
|
307
|
-
m_ 7
|
308
|
-
kanl 7
|
309
|
-
ey 7
|
310
|
-
leri_ 7
|
311
|
-
_li 7
|
312
|
-
aza 7
|
292
|
+
_par 7
|
293
|
+
anla 7
|
294
|
+
al_ 7
|
295
|
+
at_ 7
|
296
|
+
ay_ 7
|
313
297
|
t�r 7
|
314
|
-
|
315
|
-
|
298
|
+
ndan 7
|
299
|
+
_t�r 7
|
316
300
|
olara 7
|
317
|
-
|
318
|
-
|
319
|
-
|
320
|
-
lik_ 7
|
321
|
-
yan 7
|
322
|
-
lke 7
|
323
|
-
un_ 7
|
301
|
+
ma_ 7
|
302
|
+
_ge� 7
|
303
|
+
and 7
|
324
304
|
�r 7
|
325
|
-
�rk 7
|
326
|
-
_da 7
|
327
|
-
eri_ 7
|
328
|
-
lir 7
|
329
|
-
sil 7
|
330
|
-
�n 7
|
331
|
-
mes 7
|
332
|
-
ndan 7
|
333
|
-
bin_ 7
|
334
|
-
par 7
|
335
|
-
er_ 7
|
336
|
-
_r 7
|
337
305
|
_to 7
|
338
|
-
|
339
|
-
|
306
|
+
ik_ 7
|
307
|
+
yan 7
|
308
|
+
inde 7
|
309
|
+
unu 7
|
310
|
+
_c 7
|
340
311
|
aya 7
|
341
312
|
cu 7
|
342
|
-
|
313
|
+
bin 7
|
314
|
+
_t�rk 7
|
315
|
+
mes 7
|
316
|
+
mesi 7
|
317
|
+
az_ 7
|
318
|
+
arak_ 7
|
319
|
+
_bin_ 7
|
320
|
+
�n 7
|
321
|
+
_ma 7
|
322
|
+
_an 7
|
323
|
+
lir 7
|
324
|
+
ge� 7
|
325
|
+
kanl 7
|
326
|
+
_z 7
|
327
|
+
lke 7
|
328
|
+
dil 7
|
329
|
+
par 7
|
330
|
+
bin_ 7
|
331
|
+
�rk 7
|
343
332
|
yl 6
|
344
|
-
|
345
|
-
|
346
|
-
|
333
|
+
aka 6
|
334
|
+
lam 6
|
335
|
+
ah 6
|
336
|
+
_so 6
|
337
|
+
bul 6
|
338
|
+
mas 6
|
339
|
+
mas_ 6
|
347
340
|
usu 6
|
348
|
-
|
349
|
-
|
350
|
-
|
351
|
-
z_ 6
|
352
|
-
ye_ 6
|
353
|
-
ildi 6
|
354
|
-
ndan_ 6
|
355
|
-
irl 6
|
356
|
-
ta_ 6
|
357
|
-
gini 6
|
358
|
-
ard 6
|
341
|
+
mesi_ 6
|
342
|
+
ac 6
|
343
|
+
_u 6
|
359
344
|
re_ 6
|
360
|
-
|
345
|
+
yap 6
|
346
|
+
_ki 6
|
347
|
+
ili 6
|
348
|
+
aza 6
|
349
|
+
�l 6
|
350
|
+
g� 6
|
351
|
+
_yap 6
|
352
|
+
_in 6
|
353
|
+
_is 6
|
354
|
+
it 6
|
355
|
+
so 6
|
361
356
|
�y 6
|
357
|
+
ce_ 6
|
362
358
|
�z 6
|
363
|
-
|
364
|
-
|
365
|
-
sk 6
|
366
|
-
lig 6
|
367
|
-
ng 6
|
368
|
-
lara_ 6
|
369
|
-
ileri 6
|
370
|
-
nli 6
|
371
|
-
azi 6
|
359
|
+
ede 6
|
360
|
+
ey 6
|
372
361
|
eki_ 6
|
373
|
-
|
374
|
-
|
375
|
-
nlar 6
|
376
|
-
isl 6
|
377
|
-
asin 6
|
378
|
-
masi 6
|
379
|
-
sinda 6
|
380
|
-
y�k 6
|
381
|
-
mas 6
|
382
|
-
rs 6
|
383
|
-
ah 6
|
384
|
-
lam 6
|
362
|
+
ileri 6
|
363
|
+
us 6
|
385
364
|
etl 6
|
386
|
-
inda_ 6
|
387
|
-
la_ 6
|
388
|
-
_bas 6
|
389
365
|
ks 6
|
390
|
-
|
391
|
-
|
392
|
-
|
393
|
-
ti_ 6
|
366
|
+
gi 6
|
367
|
+
ard 6
|
368
|
+
i� 6
|
394
369
|
zal 6
|
395
|
-
|
396
|
-
|
397
|
-
aki 6
|
370
|
+
_kan 6
|
371
|
+
nlar 6
|
398
372
|
kl 6
|
399
|
-
|
373
|
+
ere 6
|
400
374
|
du 6
|
375
|
+
ze 6
|
376
|
+
ele 6
|
377
|
+
gr 6
|
378
|
+
_ndan 6
|
379
|
+
lara_ 6
|
380
|
+
st 6
|
381
|
+
den 6
|
382
|
+
pl 6
|
383
|
+
_olar 6
|
384
|
+
sil 6
|
385
|
+
larak 6
|
386
|
+
�_ 6
|
387
|
+
y�k 6
|
388
|
+
ken 5
|
389
|
+
ras_ 5
|
390
|
+
me_ 5
|
391
|
+
dek 5
|
392
|
+
_ara 5
|
393
|
+
yon 5
|
394
|
+
yor 5
|
395
|
+
mu 5
|
396
|
+
tem 5
|
397
|
+
men 5
|
398
|
+
�lke 5
|
399
|
+
f_ 5
|
400
|
+
_konu 5
|