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/polish.lm
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 1350
|
2
2
|
e 336
|
3
3
|
i 319
|
4
4
|
a 317
|
@@ -20,381 +20,381 @@ u 97
|
|
20
20
|
ni 91
|
21
21
|
l 90
|
22
22
|
j 86
|
23
|
+
_p 80
|
24
|
+
o_ 79
|
23
25
|
� 75
|
24
|
-
|
25
|
-
|
26
|
+
a_ 70
|
27
|
+
e_ 67
|
26
28
|
g 65
|
27
|
-
a_ 65
|
28
29
|
, 64
|
29
|
-
|
30
|
+
,_ 64
|
30
31
|
b 58
|
31
|
-
|
32
|
-
_w
|
33
|
-
|
32
|
+
_n 52
|
33
|
+
_w 52
|
34
|
+
i_ 51
|
34
35
|
ze 48
|
35
|
-
i_ 47
|
36
|
-
__ 46
|
37
36
|
� 45
|
37
|
+
y_ 43
|
38
38
|
. 42
|
39
39
|
� 41
|
40
|
-
na 40
|
41
40
|
pr 40
|
41
|
+
._ 40
|
42
|
+
na 40
|
43
|
+
_z 39
|
42
44
|
sz 39
|
43
45
|
cz 39
|
44
|
-
|
46
|
+
_s 39
|
47
|
+
_d 38
|
45
48
|
wi 37
|
46
|
-
|
47
|
-
|
48
|
-
_z 36
|
49
|
-
y_ 36
|
49
|
+
nie 37
|
50
|
+
ie_ 35
|
50
51
|
rz 35
|
51
52
|
an 34
|
52
|
-
|
53
|
-
st 32
|
53
|
+
_pr 33
|
54
54
|
ra 32
|
55
55
|
za 32
|
56
56
|
en 32
|
57
|
-
|
58
|
-
ow 31
|
57
|
+
st 32
|
59
58
|
h 31
|
59
|
+
ow 31
|
60
|
+
ej 31
|
60
61
|
ki 30
|
61
62
|
zy 30
|
62
|
-
|
63
|
+
m_ 30
|
64
|
+
_t 30
|
63
65
|
po 29
|
64
|
-
ro 28
|
65
66
|
ch 28
|
66
|
-
|
67
|
-
._ 28
|
67
|
+
ro 28
|
68
68
|
� 28
|
69
|
+
eg 28
|
69
70
|
do 28
|
70
|
-
|
71
|
-
m_ 27
|
71
|
+
_na 27
|
72
72
|
ne 27
|
73
|
-
|
74
|
-
|
73
|
+
� 27
|
74
|
+
j_ 26
|
75
75
|
_po 26
|
76
76
|
ia 26
|
77
|
-
em 25
|
78
|
-
wa 25
|
79
77
|
ko 25
|
80
|
-
|
78
|
+
u_ 25
|
79
|
+
wa 25
|
80
|
+
_k 25
|
81
|
+
em 25
|
82
|
+
w_ 24
|
83
|
+
_j 24
|
84
|
+
ej_ 24
|
81
85
|
_b 24
|
82
|
-
|
86
|
+
li 24
|
83
87
|
dz 24
|
84
|
-
u_ 24
|
85
88
|
to 23
|
86
|
-
|
87
|
-
|
89
|
+
_ni 22
|
90
|
+
_o 22
|
91
|
+
_i 22
|
88
92
|
� 21
|
89
|
-
ta 21
|
90
|
-
i� 21
|
91
|
-
_ni 21
|
92
|
-
_i 21
|
93
|
-
yc 21
|
94
93
|
go 21
|
94
|
+
i� 21
|
95
|
+
ta 21
|
96
|
+
ci 21
|
97
|
+
nie_ 21
|
95
98
|
or 20
|
96
99
|
le 20
|
97
|
-
nie_ 20
|
98
|
-
_j 20
|
99
100
|
te 20
|
101
|
+
a� 19
|
102
|
+
_nie 19
|
103
|
+
re 19
|
104
|
+
�_ 19
|
100
105
|
al 19
|
101
|
-
|
102
|
-
|
106
|
+
_do 19
|
107
|
+
yc 19
|
103
108
|
ego 19
|
104
|
-
|
109
|
+
P 19
|
105
110
|
wy 19
|
106
|
-
a� 19
|
107
|
-
re 19
|
108
|
-
_nie 18
|
109
|
-
cze 18
|
110
|
-
ac 18
|
111
|
-
sk 18
|
112
111
|
ani 18
|
113
|
-
ej_ 18
|
114
112
|
�o 18
|
113
|
+
go_ 18
|
114
|
+
_i_ 18
|
115
|
+
cze 18
|
116
|
+
ego_ 18
|
115
117
|
aw 18
|
116
|
-
|
117
|
-
|
118
|
+
ac 18
|
119
|
+
sk 18
|
118
120
|
ak 17
|
119
|
-
�_ 17
|
120
|
-
_w_ 17
|
121
121
|
zi 17
|
122
|
-
go_ 17
|
123
|
-
ar 17
|
124
|
-
_do 17
|
125
|
-
_i_ 17
|
126
122
|
rze 17
|
127
|
-
|
123
|
+
_za 17
|
124
|
+
_w_ 17
|
125
|
+
by 17
|
126
|
+
_m 17
|
127
|
+
ar 17
|
128
128
|
ty 16
|
129
|
-
je 16
|
130
|
-
es 16
|
131
129
|
mi 16
|
130
|
+
z_ 16
|
131
|
+
_r 16
|
132
|
+
es 16
|
132
133
|
ka 16
|
134
|
+
on 16
|
133
135
|
kie 16
|
136
|
+
_c 16
|
137
|
+
je 16
|
134
138
|
dzi 16
|
135
|
-
_m 16
|
136
|
-
z_ 16
|
137
|
-
_za 15
|
138
|
-
dzie 15
|
139
139
|
wie 15
|
140
|
-
� 15
|
141
|
-
prz 15
|
142
140
|
do_ 15
|
143
|
-
|
144
|
-
|
141
|
+
prz 15
|
142
|
+
_do_ 15
|
143
|
+
ch_ 15
|
145
144
|
�w 15
|
146
|
-
zie 15
|
147
145
|
om 15
|
148
|
-
|
149
|
-
|
146
|
+
S 15
|
147
|
+
_P 15
|
148
|
+
_prz 15
|
149
|
+
� 15
|
150
|
+
dzie 15
|
151
|
+
h_ 15
|
152
|
+
zie 15
|
150
153
|
ny 14
|
151
|
-
em_ 14
|
152
|
-
W 14
|
153
154
|
ych 14
|
154
|
-
�a 14
|
155
|
-
el 14
|
156
|
-
_do_ 14
|
157
155
|
na_ 14
|
158
|
-
ic 14
|
159
|
-
ec 14
|
160
156
|
eni 14
|
157
|
+
ic 14
|
158
|
+
W 14
|
159
|
+
�a 14
|
160
|
+
el 14
|
161
161
|
am 14
|
162
|
-
|
163
|
-
|
162
|
+
�e 14
|
163
|
+
em_ 14
|
164
|
+
ek 13
|
165
|
+
er 13
|
164
166
|
de 13
|
167
|
+
�_ 13
|
165
168
|
f 13
|
166
169
|
� 13
|
170
|
+
ym 13
|
167
171
|
zc 13
|
168
|
-
|
169
|
-
er 13
|
170
|
-
�_ 13
|
172
|
+
_l 13
|
171
173
|
ez 13
|
172
|
-
ed 13
|
173
|
-
ws 13
|
174
174
|
pra 13
|
175
|
-
|
176
|
-
|
177
|
-
dn 12
|
178
|
-
pi 12
|
179
|
-
_c 12
|
180
|
-
_wy 12
|
175
|
+
ed 13
|
176
|
+
ec 13
|
181
177
|
�e_ 12
|
182
|
-
|
183
|
-
_P 12
|
184
|
-
ch_ 12
|
185
|
-
as 12
|
178
|
+
ja 12
|
186
179
|
zn 12
|
187
|
-
to_ 12
|
188
|
-
pa 12
|
189
180
|
od 12
|
190
|
-
|
181
|
+
�_ 12
|
182
|
+
ws 12
|
191
183
|
ol 12
|
192
|
-
|
184
|
+
_W 12
|
185
|
+
as 12
|
186
|
+
pa 12
|
193
187
|
nej 12
|
194
|
-
|
195
|
-
|
196
|
-
|
188
|
+
owa 12
|
189
|
+
to_ 12
|
190
|
+
ob 12
|
191
|
+
_je 12
|
192
|
+
ce 12
|
193
|
+
pi 12
|
194
|
+
dn 12
|
195
|
+
_wy 12
|
196
|
+
i, 11
|
197
|
+
ys 11
|
198
|
+
_g 11
|
197
199
|
ok 11
|
200
|
+
wo 11
|
198
201
|
no 11
|
202
|
+
_� 11
|
203
|
+
tr 11
|
204
|
+
A 11
|
205
|
+
_S 11
|
199
206
|
_wi 11
|
207
|
+
k_ 11
|
208
|
+
zcz 11
|
200
209
|
prze 11
|
201
|
-
|
202
|
-
i, 11
|
203
|
-
ys 11
|
204
|
-
-_ 11
|
210
|
+
�_ 11
|
205
211
|
i,_ 11
|
206
|
-
|
207
|
-
|
208
|
-
|
209
|
-
ku 10
|
210
|
-
Po 10
|
211
|
-
_prze 10
|
212
|
-
szc 10
|
213
|
-
T 10
|
214
|
-
�_ 10
|
212
|
+
dy 11
|
213
|
+
_prze 11
|
214
|
+
e,_ 10
|
215
215
|
e, 10
|
216
|
-
|
216
|
+
_u 10
|
217
|
+
T 10
|
218
|
+
ud 10
|
219
|
+
Po 10
|
220
|
+
ln 10
|
221
|
+
rzy 10
|
222
|
+
aj 10
|
223
|
+
_na_ 10
|
217
224
|
nia 10
|
218
|
-
|
219
|
-
ad 10
|
220
|
-
ma 10
|
225
|
+
_�e_ 10
|
221
226
|
_z_ 10
|
222
|
-
_� 10
|
223
|
-
|
227
|
+
_�e 10
|
228
|
+
ent 10
|
229
|
+
ma 10
|
224
230
|
iej 10
|
231
|
+
ski 10
|
225
232
|
og 10
|
233
|
+
ku 10
|
234
|
+
we 10
|
235
|
+
at 10
|
236
|
+
ad 10
|
237
|
+
is 10
|
238
|
+
szc 10
|
226
239
|
nt 10
|
227
|
-
|
228
|
-
|
229
|
-
|
240
|
+
nej_ 10
|
241
|
+
_nie_ 10
|
242
|
+
ych_ 10
|
243
|
+
_Po 10
|
230
244
|
cj 10
|
231
|
-
k_ 10
|
232
|
-
ent 10
|
233
|
-
ud 10
|
234
|
-
we 10
|
235
|
-
_u 10
|
236
|
-
�_ 9
|
237
|
-
_nie_ 9
|
238
|
-
_je 9
|
239
|
-
gr 9
|
240
|
-
szcz 9
|
241
|
-
ot 9
|
242
|
-
_na_ 9
|
243
|
-
_to 9
|
244
|
-
_g 9
|
245
|
-
us 9
|
246
|
-
si 9
|
247
|
-
_to_ 9
|
248
245
|
y� 9
|
249
|
-
|
246
|
+
my 9
|
247
|
+
us 9
|
250
248
|
_a 9
|
251
|
-
_�e 9
|
252
249
|
ru 9
|
253
|
-
|
250
|
+
szcz 9
|
251
|
+
�o_ 9
|
252
|
+
_to 9
|
254
253
|
da 9
|
255
|
-
|
256
|
-
|
254
|
+
_to_ 9
|
255
|
+
ot 9
|
256
|
+
in 9
|
257
|
+
si 9
|
257
258
|
tw 9
|
259
|
+
gr 9
|
260
|
+
ym_ 9
|
261
|
+
a� 8
|
262
|
+
t� 8
|
263
|
+
_si 8
|
258
264
|
�s 8
|
259
|
-
|
260
|
-
|
261
|
-
|
262
|
-
by_ 8
|
263
|
-
nej_ 8
|
265
|
+
_sz 8
|
266
|
+
_by 8
|
267
|
+
zcze 8
|
264
268
|
neg 8
|
265
|
-
_si 8
|
266
269
|
la 8
|
267
|
-
wsk 8
|
268
|
-
�y 8
|
269
|
-
ap 8
|
270
|
-
esz 8
|
271
|
-
ia_ 8
|
272
270
|
raw 8
|
273
|
-
|
274
|
-
kt 8
|
275
|
-
zcze 8
|
276
|
-
_by 8
|
277
|
-
�o_ 8
|
278
|
-
a� 8
|
271
|
+
_pa 8
|
279
272
|
pre 8
|
280
|
-
|
273
|
+
_ja 8
|
274
|
+
by_ 8
|
275
|
+
�y 8
|
276
|
+
_ty 8
|
277
|
+
N 8
|
281
278
|
nego 8
|
279
|
+
praw 8
|
280
|
+
_pra 8
|
281
|
+
ia_ 8
|
282
|
+
os 8
|
283
|
+
zy_ 8
|
284
|
+
ga 8
|
285
|
+
esz 8
|
282
286
|
pan 8
|
283
|
-
|
284
|
-
|
285
|
-
|
286
|
-
|
287
|
-
|
288
|
-
Z 7
|
289
|
-
_W 7
|
290
|
-
_sz 7
|
291
|
-
_- 7
|
292
|
-
ni_ 7
|
293
|
-
_ja 7
|
287
|
+
li_ 8
|
288
|
+
kt 8
|
289
|
+
K 7
|
290
|
+
wsk 7
|
291
|
+
a� 7
|
294
292
|
edn 7
|
295
|
-
tu 7
|
296
293
|
icz 7
|
297
|
-
I 7
|
298
|
-
_ty 7
|
299
|
-
et 7
|
300
|
-
_si� 7
|
301
294
|
si� 7
|
302
|
-
|
303
|
-
|
304
|
-
|
305
|
-
|
306
|
-
iu 7
|
307
|
-
K 7
|
308
|
-
gi 7
|
309
|
-
u� 7
|
310
|
-
sp 7
|
295
|
+
rac 7
|
296
|
+
W_ 7
|
297
|
+
tu 7
|
298
|
+
_pre 7
|
311
299
|
bi 7
|
312
|
-
|
313
|
-
|
314
|
-
|
300
|
+
I 7
|
301
|
+
iu 7
|
302
|
+
iej_ 7
|
303
|
+
_te 7
|
304
|
+
O 7
|
305
|
+
i�_ 7
|
315
306
|
cie 7
|
316
|
-
|
317
|
-
rac 7
|
318
|
-
ieg 7
|
319
|
-
R 7
|
307
|
+
et 7
|
320
308
|
�_ 7
|
321
|
-
|
322
|
-
skie 7
|
323
|
-
�d 7
|
309
|
+
_ro 7
|
324
310
|
nia_ 7
|
325
|
-
|
311
|
+
ni_ 7
|
312
|
+
o� 7
|
313
|
+
ko_ 7
|
314
|
+
_si� 7
|
326
315
|
�u 7
|
316
|
+
_T 7
|
317
|
+
iel 7
|
318
|
+
_kt 7
|
319
|
+
R 7
|
320
|
+
�d 7
|
321
|
+
G 7
|
322
|
+
ieg 7
|
327
323
|
ry 7
|
324
|
+
_W_ 7
|
328
325
|
tem 7
|
326
|
+
Z 7
|
327
|
+
lu 7
|
328
|
+
u� 7
|
329
|
+
sp 7
|
330
|
+
gi 7
|
331
|
+
nego_ 7
|
329
332
|
bo 7
|
330
|
-
|
331
|
-
|
333
|
+
skie 7
|
334
|
+
ze_ 7
|
335
|
+
wan 6
|
336
|
+
czn 6
|
337
|
+
ba 6
|
338
|
+
est 6
|
339
|
+
_sp 6
|
340
|
+
y. 6
|
341
|
+
ji 6
|
342
|
+
dent 6
|
343
|
+
by� 6
|
344
|
+
si�_ 6
|
345
|
+
B 6
|
332
346
|
szcze 6
|
333
|
-
|
334
|
-
W_ 6
|
335
|
-
iego 6
|
336
|
-
t�r 6
|
337
|
-
oc 6
|
338
|
-
m� 6
|
339
|
-
_kt�r 6
|
347
|
+
sze 6
|
340
348
|
un 6
|
341
|
-
|
342
|
-
�
|
343
|
-
|
344
|
-
|
345
|
-
|
346
|
-
|
347
|
-
|
348
|
-
|
349
|
-
|
349
|
+
e� 6
|
350
|
+
_kt�r 6
|
351
|
+
�d 6
|
352
|
+
oz 6
|
353
|
+
�w_ 6
|
354
|
+
ali 6
|
355
|
+
niu 6
|
356
|
+
t�r 6
|
357
|
+
iem 6
|
358
|
+
no_ 6
|
350
359
|
yd 6
|
351
|
-
|
352
|
-
iego_ 6
|
353
|
-
den 6
|
354
|
-
ze_ 6
|
355
|
-
�a 6
|
360
|
+
_kt� 6
|
356
361
|
�c 6
|
357
362
|
�r 6
|
358
|
-
|
359
|
-
|
363
|
+
den 6
|
364
|
+
m� 6
|
365
|
+
zen 6
|
366
|
+
jak 6
|
367
|
+
_jak 6
|
360
368
|
yb 6
|
361
|
-
dent 6
|
362
|
-
wski 6
|
363
|
-
J 6
|
364
|
-
iem 6
|
365
|
-
oz 6
|
366
|
-
lne 6
|
367
|
-
ji 6
|
368
|
-
a�_ 6
|
369
|
-
usz 6
|
370
|
-
ba 6
|
371
|
-
il 6
|
372
|
-
g� 6
|
373
|
-
ien 6
|
374
|
-
io 6
|
375
369
|
_ko 6
|
376
|
-
|
377
|
-
|
378
|
-
|
379
|
-
|
380
|
-
|
381
|
-
|
382
|
-
|
370
|
+
uk 6
|
371
|
+
oc 6
|
372
|
+
ien 6
|
373
|
+
�a 6
|
374
|
+
naj 6
|
375
|
+
mie 6
|
376
|
+
g� 6
|
377
|
+
_. 6
|
378
|
+
�dz 6
|
379
|
+
_J 6
|
380
|
+
ak_ 6
|
381
|
+
i�c 6
|
383
382
|
be 6
|
383
|
+
a�_ 6
|
384
|
+
_ob 6
|
385
|
+
aln 6
|
384
386
|
kt�r 6
|
385
|
-
|
386
|
-
|
387
|
-
|
388
|
-
|
389
|
-
|
390
|
-
|
387
|
+
mo 6
|
388
|
+
s� 6
|
389
|
+
i� 6
|
390
|
+
a,_ 6
|
391
|
+
iego_ 6
|
392
|
+
dr 6
|
393
|
+
dni 6
|
394
|
+
_G 6
|
395
|
+
iego 6
|
396
|
+
lne 6
|
397
|
+
J 6
|
391
398
|
nd 6
|
392
|
-
|
393
|
-
|
394
|
-
i�_ 6
|
395
|
-
a, 6
|
396
|
-
B 6
|
397
|
-
czy 6
|
398
|
-
est 6
|
399
|
-
_sp 6
|
400
|
-
nego_ 6
|
399
|
+
wski 6
|
400
|
+
owi 6
|