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/spanish.lm
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 35393
|
2
2
|
a 10584
|
3
3
|
e 10526
|
4
4
|
o 7129
|
@@ -10,391 +10,391 @@ l 5112
|
|
10
10
|
d 4622
|
11
11
|
t 3867
|
12
12
|
c 3674
|
13
|
-
a_
|
14
|
-
e_
|
13
|
+
a_ 3187
|
14
|
+
e_ 2979
|
15
15
|
u 2914
|
16
|
+
s_ 2600
|
16
17
|
� 2572
|
17
|
-
s_ 2533
|
18
18
|
de 2468
|
19
|
-
_d
|
19
|
+
_d 2355
|
20
20
|
p 2303
|
21
21
|
m 2195
|
22
|
-
_de
|
23
|
-
o_
|
24
|
-
|
25
|
-
|
22
|
+
_de 2113
|
23
|
+
o_ 1939
|
24
|
+
n_ 1801
|
25
|
+
_e 1792
|
26
26
|
en 1746
|
27
|
-
de_
|
28
|
-
_de_
|
27
|
+
de_ 1690
|
28
|
+
_de_ 1615
|
29
29
|
la 1459
|
30
30
|
es 1454
|
31
|
-
_l
|
31
|
+
_l 1389
|
32
|
+
l_ 1290
|
32
33
|
, 1276
|
33
|
-
,_
|
34
|
-
l_ 1259
|
34
|
+
,_ 1274
|
35
35
|
os 1221
|
36
|
-
er
|
36
|
+
er 1193
|
37
37
|
on 1122
|
38
38
|
as 1103
|
39
39
|
ci 1095
|
40
|
-
_p
|
41
|
-
_c
|
42
|
-
el
|
40
|
+
_p 1085
|
41
|
+
_c 1065
|
42
|
+
el 1048
|
43
43
|
an 1032
|
44
44
|
ra 1018
|
45
|
-
al
|
46
|
-
os_
|
45
|
+
al 994
|
46
|
+
os_ 957
|
47
47
|
g 941
|
48
|
-
_la
|
48
|
+
_la 940
|
49
49
|
nt 926
|
50
50
|
te 922
|
51
|
+
_a 906
|
51
52
|
co 901
|
52
|
-
_a 898
|
53
53
|
b 896
|
54
54
|
re 888
|
55
55
|
ta 858
|
56
|
-
|
56
|
+
la_ 834
|
57
57
|
ri 825
|
58
|
-
|
58
|
+
ad 822
|
59
59
|
ar 816
|
60
|
-
or
|
61
|
-
_s
|
62
|
-
el_
|
60
|
+
or 811
|
61
|
+
_s 805
|
62
|
+
el_ 802
|
63
63
|
. 766
|
64
64
|
pa 757
|
65
65
|
� 756
|
66
66
|
ó 755
|
67
67
|
do 751
|
68
|
+
as_ 744
|
68
69
|
st 737
|
69
|
-
|
70
|
+
._ 727
|
70
71
|
ro 725
|
72
|
+
_la_ 724
|
71
73
|
y 717
|
72
|
-
|
73
|
-
na 691
|
74
|
+
na 689
|
74
75
|
ue 688
|
75
76
|
v 663
|
77
|
+
es_ 660
|
76
78
|
in 658
|
77
79
|
_en 651
|
78
80
|
ca 643
|
79
|
-
es_ 636
|
80
81
|
ic 635
|
81
|
-
en_
|
82
|
+
en_ 634
|
82
83
|
da 621
|
83
84
|
ia 620
|
84
85
|
E 615
|
85
86
|
to 609
|
87
|
+
_m 608
|
86
88
|
lo 605
|
87
|
-
|
89
|
+
_co 598
|
88
90
|
f 596
|
89
|
-
|
90
|
-
y_
|
91
|
-
_el
|
92
|
-
� 557
|
91
|
+
_E 581
|
92
|
+
y_ 566
|
93
|
+
_el 558
|
93
94
|
í 557
|
94
|
-
|
95
|
+
� 557
|
96
|
+
_en_ 537
|
95
97
|
ti 535
|
96
98
|
no 532
|
97
|
-
_y
|
98
|
-
|
99
|
+
_y 531
|
100
|
+
r_ 520
|
101
|
+
_el_ 513
|
99
102
|
un 513
|
100
|
-
|
101
|
-
|
102
|
-
|
103
|
+
ent 513
|
104
|
+
le 506
|
105
|
+
_y_ 500
|
103
106
|
io 495
|
104
|
-
_y_ 494
|
105
|
-
ón 488
|
106
107
|
�n 488
|
108
|
+
ón 488
|
107
109
|
i� 487
|
108
110
|
po 475
|
109
111
|
a� 472
|
110
112
|
se 468
|
111
|
-
_E 464
|
112
113
|
sp 460
|
113
114
|
q 456
|
114
115
|
qu 455
|
115
116
|
ñ 453
|
116
117
|
� 453
|
118
|
+
_t 452
|
117
119
|
C 451
|
118
120
|
tr 450
|
119
|
-
_t 449
|
120
121
|
ma 440
|
121
|
-
._ 438
|
122
122
|
id 432
|
123
123
|
ac 431
|
124
124
|
ió 428
|
125
|
+
_C 427
|
125
126
|
is 427
|
126
127
|
ni 426
|
127
128
|
om 425
|
128
|
-
|
129
|
+
do_ 415
|
129
130
|
ne 414
|
131
|
+
nte 414
|
130
132
|
con 410
|
131
|
-
|
132
|
-
nc
|
133
|
-
|
134
|
-
|
135
|
-
li 403
|
133
|
+
_r 407
|
134
|
+
nc 405
|
135
|
+
nd 403
|
136
|
+
li 402
|
136
137
|
ie 401
|
137
138
|
si 399
|
139
|
+
ón_ 396
|
140
|
+
�n_ 396
|
138
141
|
me 396
|
139
142
|
añ 395
|
140
|
-
� 391
|
141
143
|
á 391
|
144
|
+
� 391
|
142
145
|
h 383
|
143
146
|
pr 382
|
144
|
-
�n_ 379
|
145
|
-
ón_ 379
|
146
|
-
_C 376
|
147
147
|
spa 375
|
148
148
|
que 374
|
149
149
|
ión 373
|
150
|
-
ue_
|
150
|
+
ue_ 372
|
151
151
|
pa� 363
|
152
|
-
|
153
|
-
|
154
|
-
|
152
|
+
ión_ 350
|
153
|
+
al_ 349
|
154
|
+
_con 343
|
155
|
+
te_ 342
|
155
156
|
mi 340
|
156
|
-
_re
|
157
|
+
_re 340
|
158
|
+
ec 339
|
157
159
|
di 336
|
158
160
|
rt 336
|
159
161
|
pe 333
|
160
|
-
|
161
|
-
te_ 332
|
162
|
-
_pr 330
|
162
|
+
_pr 331
|
163
163
|
A 327
|
164
|
-
que_
|
165
|
-
|
166
|
-
|
164
|
+
que_ 326
|
165
|
+
_qu 324
|
166
|
+
_q 324
|
167
167
|
it 317
|
168
|
+
_es 317
|
168
169
|
pañ 315
|
169
170
|
Es 313
|
170
|
-
|
171
|
-
_se
|
171
|
+
_que 313
|
172
|
+
_se 312
|
173
|
+
_Es 311
|
174
|
+
_lo 311
|
172
175
|
mo 310
|
173
|
-
|
174
|
-
spañ 309
|
176
|
+
_po 310
|
175
177
|
spa� 309
|
176
|
-
|
177
|
-
|
178
|
+
spañ 309
|
179
|
+
_A 306
|
178
180
|
los 305
|
179
|
-
a, 305
|
180
|
-
a,_ 303
|
181
|
-
ol 302
|
182
|
-
aci 300
|
183
181
|
ci� 300
|
182
|
+
aci 300
|
183
|
+
ol 300
|
184
184
|
ció 299
|
185
|
-
los_
|
186
|
-
_i
|
185
|
+
los_ 299
|
186
|
+
_i 298
|
187
|
+
_que_ 296
|
187
188
|
I 295
|
189
|
+
a, 294
|
188
190
|
ado 294
|
189
|
-
|
191
|
+
a,_ 293
|
190
192
|
ur 293
|
191
|
-
__ 292
|
192
|
-
_Es 287
|
193
193
|
ción 285
|
194
194
|
su 282
|
195
|
-
_f
|
196
|
-
ña 278
|
195
|
+
_f 282
|
197
196
|
�a 278
|
197
|
+
ña 278
|
198
|
+
_u 276
|
198
199
|
z 275
|
199
|
-
|
200
|
-
on_ 273
|
200
|
+
on_ 274
|
201
201
|
ica 271
|
202
202
|
del 270
|
203
|
+
_del 268
|
203
204
|
ce 267
|
204
205
|
cia 267
|
205
|
-
|
206
|
-
|
207
|
-
|
206
|
+
or_ 263
|
207
|
+
ra_ 263
|
208
|
+
_h 262
|
209
|
+
_del_ 262
|
210
|
+
del_ 262
|
208
211
|
� 261
|
209
|
-
|
210
|
-
|
212
|
+
é 261
|
213
|
+
_o 260
|
211
214
|
nci 260
|
212
|
-
_del_ 259
|
213
|
-
_o 259
|
214
|
-
s, 259
|
215
|
-
s,_ 258
|
216
215
|
tu 258
|
217
|
-
|
218
|
-
|
219
|
-
|
220
|
-
|
216
|
+
_los_ 258
|
217
|
+
_los 258
|
218
|
+
_un 257
|
219
|
+
am 254
|
221
220
|
sta 253
|
222
|
-
ra_ 251
|
223
|
-
Esp 250
|
224
221
|
Espa� 250
|
222
|
+
Esp 250
|
225
223
|
Espa 250
|
226
|
-
|
227
|
-
|
224
|
+
_Esp 249
|
225
|
+
s,_ 249
|
226
|
+
s, 249
|
227
|
+
_Espa 249
|
228
228
|
ab 245
|
229
|
-
|
229
|
+
est 245
|
230
|
+
ll 245
|
230
231
|
las 244
|
231
|
-
|
232
|
+
por 244
|
232
233
|
�a 243
|
233
234
|
aña 243
|
234
|
-
|
235
|
+
ía 243
|
236
|
+
ia_ 240
|
235
237
|
at 239
|
236
|
-
|
237
|
-
|
238
|
+
r� 239
|
239
|
+
na_ 239
|
238
240
|
so 234
|
239
|
-
_a_
|
241
|
+
_a_ 234
|
242
|
+
paña 234
|
243
|
+
las_ 233
|
240
244
|
im 231
|
241
|
-
las_ 230
|
242
|
-
_Esp 230
|
243
|
-
_Espa 230
|
244
245
|
ns 228
|
245
|
-
na_ 228
|
246
|
-
em 226
|
247
246
|
cu 226
|
247
|
+
em 226
|
248
|
+
nte_ 226
|
248
249
|
j 224
|
250
|
+
to_ 223
|
249
251
|
_n 220
|
250
252
|
ul 220
|
251
|
-
ia_ 220
|
252
|
-
nte_ 220
|
253
|
-
P 219
|
254
253
|
ant 219
|
255
|
-
|
254
|
+
P 219
|
256
255
|
rr 218
|
257
256
|
ente 218
|
258
|
-
se_
|
257
|
+
se_ 218
|
259
258
|
dad 215
|
260
|
-
il 213
|
261
259
|
vi 213
|
260
|
+
il 213
|
261
|
+
da_ 211
|
262
262
|
L 211
|
263
|
+
_L 210
|
264
|
+
_pa 210
|
263
265
|
ter 209
|
264
|
-
_pa 208
|
265
266
|
ada 205
|
266
|
-
|
267
|
+
ña_ 205
|
268
|
+
_. 205
|
269
|
+
�a_ 205
|
267
270
|
men 203
|
268
|
-
o,_ 202
|
269
|
-
da_ 202
|
270
271
|
era 202
|
271
272
|
ran 201
|
272
|
-
|
273
|
+
_P 200
|
273
274
|
_su 200
|
275
|
+
les 200
|
274
276
|
ig 198
|
277
|
+
o,_ 197
|
278
|
+
o, 197
|
275
279
|
ien 195
|
280
|
+
_ca 194
|
276
281
|
tra 193
|
282
|
+
no_ 192
|
283
|
+
_,_ 192
|
284
|
+
_, 192
|
277
285
|
res 192
|
278
|
-
|
286
|
+
aña_ 191
|
279
287
|
com 190
|
280
288
|
cio 190
|
281
289
|
one 189
|
282
290
|
ida 189
|
291
|
+
_las 188
|
292
|
+
_las_ 188
|
283
293
|
M 188
|
284
|
-
ed 188
|
285
294
|
S 187
|
286
|
-
_las_ 186
|
287
|
-
_las 186
|
288
295
|
m� 185
|
289
296
|
t� 185
|
297
|
+
_M 185
|
290
298
|
ona 185
|
291
|
-
|
292
|
-
ha 184
|
299
|
+
_._ 184
|
293
300
|
ion 184
|
294
|
-
|
301
|
+
_I 184
|
302
|
+
ed 184
|
303
|
+
ha 184
|
295
304
|
nes 183
|
305
|
+
od 182
|
306
|
+
_in 180
|
296
307
|
ale 180
|
297
|
-
_com
|
298
|
-
|
299
|
-
_por 178
|
300
|
-
br 178
|
308
|
+
_com 180
|
309
|
+
_por 179
|
301
310
|
sa 178
|
311
|
+
ía_ 178
|
312
|
+
�a_ 178
|
313
|
+
br 178
|
302
314
|
mp 177
|
303
315
|
bi 176
|
304
316
|
pro 175
|
305
317
|
ist 175
|
306
318
|
ació 173
|
319
|
+
_S 173
|
307
320
|
dos 173
|
308
321
|
aci� 173
|
309
|
-
ct 172
|
310
322
|
oc 172
|
311
323
|
des 172
|
312
|
-
|
324
|
+
ct 172
|
325
|
+
d_ 169
|
326
|
+
_por_ 168
|
327
|
+
por_ 168
|
313
328
|
_al 168
|
329
|
+
_se_ 168
|
314
330
|
eg 167
|
331
|
+
_v 167
|
315
332
|
_pro 166
|
316
|
-
por_ 166
|
317
333
|
an_ 166
|
318
|
-
a. 165
|
319
|
-
_P 165
|
320
|
-
_se_ 165
|
321
|
-
_por_ 165
|
322
|
-
_v 165
|
323
334
|
ero 165
|
324
|
-
�o 163
|
325
|
-
�a_ 163
|
326
335
|
ño 163
|
327
|
-
|
336
|
+
�o 163
|
337
|
+
lo_ 163
|
328
338
|
va 161
|
329
339
|
ment 161
|
330
|
-
lo_ 161
|
331
340
|
iv 160
|
332
|
-
gu 159
|
333
341
|
ndo 159
|
342
|
+
ca_ 159
|
343
|
+
gu 159
|
334
344
|
mu 158
|
335
345
|
_si 157
|
336
|
-
et
|
337
|
-
|
338
|
-
ici 155
|
346
|
+
et 156
|
347
|
+
mo_ 156
|
339
348
|
fi 155
|
340
|
-
|
341
|
-
ria 154
|
349
|
+
ici 155
|
342
350
|
go 154
|
343
|
-
|
344
|
-
mo_ 153
|
345
|
-
s. 152
|
351
|
+
ria 154
|
346
352
|
ron 152
|
353
|
+
a. 152
|
347
354
|
ga 151
|
348
|
-
|
355
|
+
nes_ 151
|
349
356
|
_ha 151
|
350
|
-
op 151
|
351
357
|
ones 151
|
358
|
+
op 151
|
359
|
+
za 151
|
360
|
+
ado_ 150
|
352
361
|
us 150
|
362
|
+
a._ 150
|
353
363
|
mb 149
|
354
|
-
|
364
|
+
_Ca 148
|
355
365
|
Ca 148
|
356
366
|
año 148
|
357
|
-
|
358
|
-
_pe 147
|
359
|
-
nes_ 147
|
367
|
+
ba 148
|
360
368
|
sti 147
|
369
|
+
ente_ 147
|
361
370
|
ncia 147
|
362
|
-
|
363
|
-
ua 146
|
364
|
-
ico 146
|
365
|
-
�a_ 146
|
371
|
+
_pe 147
|
366
372
|
uc 146
|
367
|
-
|
368
|
-
|
373
|
+
ico 146
|
374
|
+
ua 146
|
375
|
+
io_ 146
|
369
376
|
ve 144
|
377
|
+
ta_ 144
|
378
|
+
s. 144
|
370
379
|
cion 143
|
371
380
|
rio 143
|
381
|
+
s._ 142
|
372
382
|
_con_ 142
|
373
383
|
con_ 142
|
374
|
-
|
375
|
-
io_ 141
|
384
|
+
les_ 141
|
376
385
|
ip 141
|
377
|
-
|
386
|
+
_g 140
|
378
387
|
ntr 140
|
379
|
-
|
380
|
-
nto 139
|
388
|
+
rc 140
|
381
389
|
tor 139
|
382
|
-
|
383
|
-
aña_ 138
|
384
|
-
par 138
|
390
|
+
nto 139
|
385
391
|
ob 138
|
392
|
+
par 138
|
386
393
|
dos_ 137
|
387
394
|
ir 137
|
388
395
|
G 137
|
389
|
-
_. 137
|
390
|
-
ante 136
|
391
|
-
_, 136
|
392
|
-
bl 136
|
393
396
|
n� 136
|
394
|
-
|
395
|
-
|
396
|
-
|
397
|
-
|
398
|
-
�_ 134
|
399
|
-
ó_ 134
|
400
|
-
err 134
|
397
|
+
bl 136
|
398
|
+
�_ 136
|
399
|
+
ó_ 136
|
400
|
+
ante 136
|