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/german.lm
CHANGED
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 1406
|
2
2
|
e 644
|
3
3
|
n 386
|
4
4
|
i 318
|
@@ -13,388 +13,388 @@ er 137
|
|
13
13
|
en 137
|
14
14
|
l 131
|
15
15
|
c 125
|
16
|
+
n_ 123
|
17
|
+
e_ 117
|
16
18
|
o 116
|
17
19
|
ch 112
|
18
20
|
g 105
|
19
21
|
m 101
|
20
|
-
|
21
|
-
|
22
|
-
te
|
23
|
-
_d 78
|
22
|
+
_d 91
|
23
|
+
r_ 89
|
24
|
+
te 79
|
24
25
|
in 77
|
25
26
|
de 76
|
26
|
-
|
27
|
+
en_ 75
|
27
28
|
ei 73
|
28
29
|
k 68
|
30
|
+
er_ 68
|
29
31
|
b 66
|
30
32
|
f 58
|
31
|
-
er_ 56
|
32
33
|
un 56
|
34
|
+
t_ 55
|
35
|
+
_e 54
|
33
36
|
ie 54
|
34
|
-
nd 52
|
35
|
-
en_ 52
|
36
37
|
w 50
|
37
|
-
|
38
|
+
nd 49
|
38
39
|
ge 48
|
39
|
-
|
40
|
-
ng
|
41
|
-
t_ 44
|
40
|
+
s_ 44
|
41
|
+
ng 43
|
42
42
|
, 42
|
43
|
+
_s 41
|
43
44
|
der 41
|
45
|
+
,_ 41
|
46
|
+
_de 40
|
44
47
|
st 39
|
45
|
-
|
46
|
-
|
47
|
-
,_ 36
|
48
|
-
. 36
|
49
|
-
he 36
|
48
|
+
m_ 38
|
49
|
+
ne 38
|
50
50
|
z 36
|
51
|
-
|
51
|
+
. 36
|
52
|
+
._ 36
|
53
|
+
_i 36
|
54
|
+
_a 35
|
55
|
+
ie_ 35
|
56
|
+
he 35
|
52
57
|
re 34
|
53
|
-
m_ 34
|
54
|
-
s_ 34
|
55
58
|
di 34
|
56
|
-
it 33
|
57
|
-
_de 33
|
58
59
|
v 33
|
59
|
-
|
60
|
-
|
61
|
-
|
60
|
+
it 33
|
61
|
+
es 33
|
62
|
+
h_ 32
|
63
|
+
der_ 32
|
62
64
|
be 31
|
65
|
+
ein 31
|
63
66
|
S 31
|
64
67
|
au 31
|
68
|
+
_w 30
|
69
|
+
d_ 30
|
65
70
|
ti 30
|
66
|
-
|
71
|
+
_S 30
|
72
|
+
ch_ 30
|
67
73
|
� 29
|
68
|
-
|
69
|
-
d_ 29
|
70
|
-
le 28
|
71
|
-
_w 28
|
74
|
+
ic 29
|
72
75
|
� 28
|
73
76
|
sc 27
|
77
|
+
le 27
|
74
78
|
sch 27
|
75
|
-
nt 26
|
76
79
|
ung 26
|
77
|
-
|
78
|
-
|
79
|
-
si 25
|
80
|
+
nt 26
|
81
|
+
_der 26
|
80
82
|
is 25
|
83
|
+
_di 25
|
84
|
+
si 25
|
85
|
+
an 25
|
86
|
+
_die 25
|
87
|
+
_der_ 25
|
81
88
|
die 25
|
82
|
-
|
89
|
+
ich 25
|
83
90
|
or 24
|
84
|
-
p 24
|
85
|
-
h_ 24
|
86
91
|
el 24
|
87
|
-
|
88
|
-
|
89
|
-
_die 23
|
92
|
+
p 24
|
93
|
+
nd_ 24
|
90
94
|
on 23
|
91
|
-
|
95
|
+
_die_ 23
|
96
|
+
_ei 23
|
97
|
+
che 23
|
98
|
+
in_ 23
|
92
99
|
al 23
|
100
|
+
die_ 23
|
101
|
+
_ein 23
|
102
|
+
te_ 22
|
93
103
|
rt 22
|
94
|
-
|
95
|
-
_ei 22
|
96
|
-
ch_ 22
|
104
|
+
em 21
|
97
105
|
ht 21
|
98
106
|
und 21
|
99
|
-
em 21
|
100
107
|
ten 21
|
101
|
-
|
102
|
-
_S 21
|
103
|
-
ra 21
|
104
|
-
die_ 21
|
108
|
+
ke 20
|
105
109
|
at 20
|
110
|
+
ra 20
|
111
|
+
_u 20
|
106
112
|
hr 20
|
107
|
-
|
108
|
-
|
109
|
-
ur 19
|
110
|
-
_v 19
|
113
|
+
li 20
|
114
|
+
_v 20
|
111
115
|
A 19
|
116
|
+
_in 19
|
112
117
|
me 19
|
113
|
-
|
114
|
-
|
115
|
-
ine 18
|
116
|
-
ns 18
|
118
|
+
_h 19
|
119
|
+
ur 19
|
117
120
|
se 18
|
118
|
-
|
121
|
+
ine 18
|
119
122
|
ll 18
|
120
|
-
eine 17
|
121
123
|
im 17
|
122
|
-
|
123
|
-
._ 17
|
124
|
-
nge 17
|
125
|
-
ar 17
|
124
|
+
eine 17
|
126
125
|
ter 17
|
127
|
-
|
126
|
+
ar 17
|
127
|
+
ns 17
|
128
|
+
_A 17
|
129
|
+
ri 17
|
130
|
+
_au 17
|
131
|
+
g_ 17
|
128
132
|
eit 17
|
133
|
+
L 17
|
134
|
+
_er 17
|
135
|
+
_g 16
|
136
|
+
den 16
|
129
137
|
we 16
|
138
|
+
_un 16
|
139
|
+
ten_ 16
|
130
140
|
D 16
|
131
141
|
gen 16
|
132
|
-
|
133
|
-
|
142
|
+
_b 16
|
143
|
+
nge 16
|
134
144
|
da 16
|
135
|
-
|
145
|
+
cht 15
|
136
146
|
eu 15
|
137
|
-
|
138
|
-
|
147
|
+
_F 15
|
148
|
+
_K 15
|
139
149
|
K 15
|
140
150
|
F 15
|
141
|
-
|
142
|
-
|
143
|
-
|
144
|
-
|
151
|
+
zu 15
|
152
|
+
on_ 15
|
153
|
+
ig 15
|
154
|
+
_da 14
|
155
|
+
_L 14
|
145
156
|
us 14
|
146
|
-
|
147
|
-
|
148
|
-
|
157
|
+
ach 14
|
158
|
+
_si 14
|
159
|
+
_in_ 14
|
160
|
+
E 14
|
149
161
|
ac 14
|
162
|
+
rs 14
|
163
|
+
und_ 14
|
150
164
|
mm 14
|
165
|
+
_z 14
|
151
166
|
vo 14
|
152
|
-
|
153
|
-
rs 14
|
154
|
-
ach 14
|
155
|
-
ha 14
|
156
|
-
�r 13
|
157
|
-
ab 13
|
167
|
+
_D 14
|
158
168
|
B 13
|
159
|
-
|
160
|
-
|
169
|
+
_E 13
|
170
|
+
n._ 13
|
171
|
+
nde 13
|
161
172
|
n. 13
|
162
|
-
|
163
|
-
|
173
|
+
ab 13
|
174
|
+
ng_ 13
|
175
|
+
�r 13
|
176
|
+
� 13
|
177
|
+
_n 13
|
178
|
+
em_ 13
|
179
|
+
eh 13
|
180
|
+
_und_ 13
|
181
|
+
_und 13
|
182
|
+
l_ 13
|
183
|
+
_eine 13
|
184
|
+
� 13
|
164
185
|
fe 13
|
165
186
|
ls 13
|
166
|
-
|
167
|
-
|
168
|
-
|
169
|
-
|
170
|
-
|
171
|
-
|
172
|
-
|
187
|
+
ha 13
|
188
|
+
_f 13
|
189
|
+
_T 12
|
190
|
+
_be 12
|
191
|
+
ht_ 12
|
192
|
+
am 12
|
193
|
+
es_ 12
|
194
|
+
_k 12
|
195
|
+
_B 12
|
173
196
|
as 12
|
174
|
-
|
175
|
-
rd 12
|
176
|
-
T 12
|
197
|
+
ste 12
|
177
198
|
lic 12
|
178
|
-
_b 12
|
179
|
-
_eine 12
|
180
|
-
lle 12
|
181
|
-
nte 12
|
182
|
-
g_ 12
|
183
|
-
rn 12
|
184
|
-
_der_ 12
|
185
199
|
wi 12
|
186
|
-
|
187
|
-
|
188
|
-
|
189
|
-
|
190
|
-
|
191
|
-
|
192
|
-
|
193
|
-
- 11
|
200
|
+
rn 12
|
201
|
+
T 12
|
202
|
+
et 12
|
203
|
+
lle 12
|
204
|
+
_zu 12
|
205
|
+
R 12
|
206
|
+
f� 11
|
194
207
|
lich 11
|
195
|
-
|
208
|
+
he_ 11
|
209
|
+
it_ 11
|
210
|
+
_Sch 11
|
211
|
+
U 11
|
212
|
+
tr 11
|
213
|
+
den_ 11
|
196
214
|
ck 11
|
197
|
-
|
215
|
+
rte 11
|
216
|
+
ge_ 11
|
217
|
+
_Sc 11
|
218
|
+
rk 11
|
219
|
+
tt 11
|
220
|
+
_vo 11
|
221
|
+
uf 11
|
222
|
+
ers 11
|
223
|
+
Sch 11
|
198
224
|
Sc 11
|
199
|
-
_n 11
|
200
|
-
men 11
|
201
225
|
ent 11
|
202
|
-
ve 11
|
203
226
|
nn 11
|
227
|
+
nte 11
|
204
228
|
G 11
|
205
|
-
|
206
|
-
|
207
|
-
|
208
|
-
|
209
|
-
n, 11
|
229
|
+
hl 11
|
230
|
+
ni 11
|
231
|
+
�r_ 11
|
232
|
+
ve 11
|
210
233
|
ren 11
|
211
|
-
|
212
|
-
|
213
|
-
ge_ 11
|
214
|
-
tr 11
|
215
|
-
ts 11
|
216
|
-
_g 11
|
217
|
-
na 10
|
218
|
-
_E 10
|
219
|
-
ten_ 10
|
220
|
-
rc 10
|
221
|
-
sa 10
|
234
|
+
men 11
|
235
|
+
als 10
|
222
236
|
auf 10
|
223
|
-
|
237
|
+
n,_ 10
|
238
|
+
_ge 10
|
239
|
+
ung_ 10
|
240
|
+
isch 10
|
241
|
+
_f�r 10
|
242
|
+
n, 10
|
243
|
+
ts 10
|
224
244
|
f�r 10
|
245
|
+
ls_ 10
|
225
246
|
hi 10
|
226
|
-
|
227
|
-
�r_ 10
|
247
|
+
_G 10
|
248
|
+
_f�r_ 10
|
249
|
+
ru 10
|
250
|
+
en._ 10
|
251
|
+
sin 10
|
228
252
|
gs 10
|
229
|
-
ut 10
|
230
|
-
ht_ 10
|
231
|
-
en. 10
|
232
253
|
isc 10
|
233
|
-
|
234
|
-
_K 10
|
254
|
+
_f� 10
|
235
255
|
um 10
|
236
|
-
|
237
|
-
|
238
|
-
|
239
|
-
|
240
|
-
|
241
|
-
|
242
|
-
|
256
|
+
k_ 10
|
257
|
+
rd 10
|
258
|
+
ut 10
|
259
|
+
_R 10
|
260
|
+
_U 10
|
261
|
+
rc 10
|
262
|
+
na 10
|
263
|
+
f�r_ 10
|
264
|
+
en. 10
|
265
|
+
sa 9
|
266
|
+
nen 9
|
267
|
+
no 9
|
268
|
+
ma 9
|
269
|
+
o_ 9
|
270
|
+
u_ 9
|
271
|
+
ren_ 9
|
272
|
+
ver 9
|
243
273
|
ere 9
|
244
|
-
|
274
|
+
_Un 9
|
275
|
+
_ha 9
|
276
|
+
nder 9
|
277
|
+
ngs 9
|
278
|
+
ze 9
|
279
|
+
M 9
|
280
|
+
che_ 9
|
281
|
+
om 9
|
245
282
|
rch 9
|
246
|
-
|
247
|
-
|
283
|
+
ungs 9
|
284
|
+
_M 9
|
285
|
+
ich_ 9
|
286
|
+
als_ 9
|
248
287
|
e,_ 9
|
249
|
-
|
250
|
-
om 9
|
251
|
-
ng_ 9
|
252
|
-
erk 9
|
253
|
-
no 9
|
254
|
-
hre 9
|
288
|
+
O 9
|
255
289
|
il 9
|
256
|
-
ngs 9
|
257
290
|
ik 9
|
258
|
-
|
291
|
+
e, 9
|
292
|
+
so 9
|
293
|
+
hre 9
|
259
294
|
Un 9
|
260
295
|
lt 9
|
261
|
-
|
262
|
-
|
263
|
-
|
264
|
-
|
265
|
-
|
266
|
-
|
267
|
-
hen
|
268
|
-
|
269
|
-
|
270
|
-
|
271
|
-
|
272
|
-
|
273
|
-
|
296
|
+
_Le 8
|
297
|
+
kei 8
|
298
|
+
sp 8
|
299
|
+
_al 8
|
300
|
+
ute 8
|
301
|
+
um_ 8
|
302
|
+
hen 8
|
303
|
+
wo 8
|
304
|
+
as_ 8
|
305
|
+
ft 8
|
306
|
+
chen 8
|
307
|
+
_wi 8
|
308
|
+
_das 8
|
309
|
+
Le 8
|
310
|
+
du 8
|
311
|
+
uc 8
|
274
312
|
ner 8
|
313
|
+
das_ 8
|
314
|
+
V 8
|
275
315
|
sic 8
|
276
|
-
|
316
|
+
la 8
|
277
317
|
le_ 8
|
278
|
-
|
279
|
-
_G 8
|
280
|
-
_ha 8
|
281
|
-
mme 8
|
282
|
-
_Un 8
|
283
|
-
rde 8
|
284
|
-
ute 8
|
285
|
-
uc 8
|
318
|
+
tig 8
|
286
319
|
ol 8
|
287
|
-
|
288
|
-
_Le 8
|
320
|
+
erk 8
|
289
321
|
tra 8
|
290
|
-
|
291
|
-
|
292
|
-
|
293
|
-
|
294
|
-
|
295
|
-
|
296
|
-
ens 8
|
297
|
-
_U 8
|
298
|
-
kei 8
|
299
|
-
tig 8
|
300
|
-
bei 8
|
301
|
-
_f 8
|
322
|
+
ber 8
|
323
|
+
ein_ 8
|
324
|
+
mme 8
|
325
|
+
nen_ 8
|
326
|
+
ind 8
|
327
|
+
im_ 8
|
302
328
|
ir 8
|
303
|
-
|
304
|
-
|
305
|
-
end 8
|
306
|
-
_k 8
|
329
|
+
bei 8
|
330
|
+
das 8
|
307
331
|
sich 8
|
308
|
-
|
309
|
-
|
310
|
-
|
311
|
-
|
312
|
-
|
313
|
-
|
314
|
-
|
332
|
+
_das_ 8
|
333
|
+
urc 8
|
334
|
+
ter_ 8
|
335
|
+
od 7
|
336
|
+
_durc 7
|
337
|
+
do 7
|
338
|
+
von_ 7
|
339
|
+
ko 7
|
340
|
+
mi 7
|
341
|
+
urch 7
|
315
342
|
des 7
|
316
|
-
|
317
|
-
|
318
|
-
|
319
|
-
|
343
|
+
_o 7
|
344
|
+
dur 7
|
345
|
+
y 7
|
346
|
+
ho 7
|
347
|
+
_hat 7
|
320
348
|
io 7
|
321
|
-
|
349
|
+
ert 7
|
350
|
+
Leu 7
|
351
|
+
and 7
|
352
|
+
f_ 7
|
353
|
+
hat 7
|
354
|
+
ens 7
|
355
|
+
len 7
|
356
|
+
_als 7
|
357
|
+
St 7
|
358
|
+
rde 7
|
359
|
+
_ver 7
|
360
|
+
eut 7
|
361
|
+
_als_ 7
|
362
|
+
zu_ 7
|
363
|
+
en,_ 7
|
364
|
+
en, 7
|
365
|
+
ne_ 7
|
366
|
+
durc 7
|
322
367
|
durch 7
|
323
|
-
|
368
|
+
�_ 7
|
369
|
+
_ve 7
|
370
|
+
_von 7
|
371
|
+
_auf 7
|
372
|
+
ing 7
|
373
|
+
eit_ 7
|
324
374
|
keit 7
|
325
|
-
ert 7
|
326
|
-
ein_ 7
|
327
375
|
ih 7
|
328
|
-
|
329
|
-
|
330
|
-
|
331
|
-
|
332
|
-
|
333
|
-
|
376
|
+
eute 7
|
377
|
+
_dur 7
|
378
|
+
_ih 7
|
379
|
+
P 7
|
380
|
+
ba 7
|
381
|
+
sti 7
|
334
382
|
von 7
|
383
|
+
tte 7
|
384
|
+
H 7
|
385
|
+
_von_ 7
|
386
|
+
_P 7
|
335
387
|
rei 7
|
336
|
-
|
337
|
-
|
338
|
-
|
388
|
+
_du 7
|
389
|
+
_Leu 7
|
390
|
+
_St 7
|
339
391
|
icht 7
|
340
|
-
als_ 7
|
341
|
-
ba 7
|
342
|
-
P 7
|
343
|
-
nh 7
|
344
|
-
f_ 7
|
345
392
|
uch 7
|
346
|
-
e. 7
|
347
|
-
_und_ 7
|
348
|
-
_ge 7
|
349
|
-
n._ 7
|
350
|
-
hat 7
|
351
|
-
das_ 7
|
352
|
-
Leu 7
|
353
|
-
_das_ 7
|
354
393
|
r� 7
|
355
|
-
|
356
|
-
|
357
|
-
eute 7
|
358
|
-
_wi 7
|
359
|
-
do 7
|
360
|
-
and 7
|
361
|
-
im_ 7
|
362
|
-
y 7
|
363
|
-
_ver 7
|
364
|
-
dur 7
|
365
|
-
_o 7
|
366
|
-
ing 7
|
367
|
-
mi 7
|
368
|
-
eb 7
|
369
|
-
len 7
|
394
|
+
run 7
|
395
|
+
_we 7
|
370
396
|
unge 7
|
371
|
-
|
372
|
-
|
373
|
-
|
374
|
-
bi 6
|
375
|
-
hw 6
|
376
|
-
hu 6
|
377
|
-
ung_ 6
|
397
|
+
imm 6
|
398
|
+
_V 6
|
399
|
+
ngen 6
|
378
400
|
sind 6
|
379
|
-
von_ 6
|
380
|
-
nge_ 6
|
381
|
-
ren_ 6
|
382
|
-
_f� 6
|
383
|
-
nter 6
|
384
|
-
Z 6
|
385
|
-
ter_ 6
|
386
|
-
ische 6
|
387
|
-
rst 6
|
388
|
-
_St 6
|
389
|
-
he_ 6
|
390
|
-
_we 6
|
391
|
-
_sich 6
|
392
|
-
mmen 6
|
393
|
-
th 6
|
394
|
-
x 6
|
395
|
-
_hat 6
|
396
|
-
ute_ 6
|
397
|
-
_ih 6
|
398
|
-
gu 6
|
399
|
-
t. 6
|
400
|
-
vor 6
|