scylla 0.7.5 → 0.8.0
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/scylla/classifier.rb +1 -1
- data/scylla.gemspec +1 -1
- data/test/fixtures/lms/danish.lm +168 -168
- data/test/fixtures/lms/english.lm +217 -217
- data/test/fixtures/lms/french.lm +216 -216
- data/test/fixtures/lms/german.lm +274 -274
- data/test/fixtures/lms/hindi.lm +241 -241
- data/test/fixtures/lms/italian.lm +280 -280
- data/test/fixtures/lms/japanese.lm +110 -110
- data/test/fixtures/lms/norwegian.lm +239 -239
- data/test/fixtures/lms/spanish.lm +188 -188
- data/test/generator_test.rb +1 -1
- metadata +4 -4
data/test/fixtures/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
|
-
he 36
|
48
|
+
m_ 38
|
49
|
+
ne 38
|
48
50
|
z 36
|
49
|
-
,_ 36
|
50
51
|
. 36
|
52
|
+
._ 36
|
53
|
+
_i 36
|
54
|
+
_a 35
|
55
|
+
ie_ 35
|
56
|
+
he 35
|
51
57
|
re 34
|
52
|
-
s_ 34
|
53
58
|
di 34
|
54
|
-
m_ 34
|
55
|
-
es 34
|
56
59
|
v 33
|
57
60
|
it 33
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
au 31
|
61
|
+
es 33
|
62
|
+
h_ 32
|
63
|
+
der_ 32
|
62
64
|
be 31
|
63
65
|
ein 31
|
64
66
|
S 31
|
67
|
+
au 31
|
68
|
+
_w 30
|
69
|
+
d_ 30
|
65
70
|
ti 30
|
66
|
-
|
71
|
+
_S 30
|
72
|
+
ch_ 30
|
67
73
|
� 29
|
68
74
|
ic 29
|
69
|
-
_a 29
|
70
|
-
_w 28
|
71
75
|
� 28
|
72
|
-
le 28
|
73
76
|
sc 27
|
77
|
+
le 27
|
74
78
|
sch 27
|
75
|
-
nt 26
|
76
79
|
ung 26
|
80
|
+
nt 26
|
81
|
+
_der 26
|
77
82
|
is 25
|
83
|
+
_di 25
|
78
84
|
si 25
|
79
|
-
die 25
|
80
85
|
an 25
|
86
|
+
_die 25
|
87
|
+
_der_ 25
|
88
|
+
die 25
|
81
89
|
ich 25
|
82
90
|
or 24
|
83
|
-
h_ 24
|
84
|
-
p 24
|
85
91
|
el 24
|
86
|
-
|
87
|
-
|
92
|
+
p 24
|
93
|
+
nd_ 24
|
88
94
|
on 23
|
95
|
+
_die_ 23
|
96
|
+
_ei 23
|
97
|
+
che 23
|
98
|
+
in_ 23
|
89
99
|
al 23
|
90
|
-
|
91
|
-
|
92
|
-
|
93
|
-
_ei 22
|
100
|
+
die_ 23
|
101
|
+
_ein 23
|
102
|
+
te_ 22
|
94
103
|
rt 22
|
95
|
-
_ein 22
|
96
|
-
ch_ 22
|
97
|
-
ht 21
|
98
104
|
em 21
|
99
|
-
|
105
|
+
ht 21
|
100
106
|
und 21
|
101
|
-
|
102
|
-
die_ 21
|
103
|
-
_S 21
|
104
|
-
li 21
|
105
|
-
at 20
|
107
|
+
ten 21
|
106
108
|
ke 20
|
109
|
+
at 20
|
110
|
+
ra 20
|
111
|
+
_u 20
|
107
112
|
hr 20
|
108
|
-
|
109
|
-
|
110
|
-
|
113
|
+
li 20
|
114
|
+
_v 20
|
115
|
+
A 19
|
116
|
+
_in 19
|
111
117
|
me 19
|
118
|
+
_h 19
|
112
119
|
ur 19
|
113
|
-
A 19
|
114
|
-
_v 19
|
115
120
|
se 18
|
116
|
-
_in 18
|
117
|
-
ns 18
|
118
|
-
ll 18
|
119
121
|
ine 18
|
122
|
+
ll 18
|
120
123
|
im 17
|
121
|
-
ter 17
|
122
124
|
eine 17
|
123
|
-
|
125
|
+
ter 17
|
124
126
|
ar 17
|
125
|
-
|
127
|
+
ns 17
|
128
|
+
_A 17
|
126
129
|
ri 17
|
130
|
+
_au 17
|
131
|
+
g_ 17
|
127
132
|
eit 17
|
128
133
|
L 17
|
129
|
-
|
134
|
+
_er 17
|
135
|
+
_g 16
|
136
|
+
den 16
|
130
137
|
we 16
|
131
|
-
|
132
|
-
|
138
|
+
_un 16
|
139
|
+
ten_ 16
|
133
140
|
D 16
|
134
|
-
|
135
|
-
|
136
|
-
|
141
|
+
gen 16
|
142
|
+
_b 16
|
143
|
+
nge 16
|
144
|
+
da 16
|
145
|
+
cht 15
|
146
|
+
eu 15
|
147
|
+
_F 15
|
148
|
+
_K 15
|
137
149
|
K 15
|
138
|
-
_er 15
|
139
150
|
F 15
|
140
|
-
|
141
|
-
|
142
|
-
|
143
|
-
|
144
|
-
|
145
|
-
E 14
|
146
|
-
und_ 14
|
151
|
+
zu 15
|
152
|
+
on_ 15
|
153
|
+
ig 15
|
154
|
+
_da 14
|
155
|
+
_L 14
|
147
156
|
us 14
|
148
|
-
vo 14
|
149
|
-
nde 14
|
150
157
|
ach 14
|
151
|
-
|
158
|
+
_si 14
|
159
|
+
_in_ 14
|
160
|
+
E 14
|
152
161
|
ac 14
|
153
|
-
mm 14
|
154
|
-
eh 14
|
155
162
|
rs 14
|
156
|
-
|
163
|
+
und_ 14
|
164
|
+
mm 14
|
165
|
+
_z 14
|
166
|
+
vo 14
|
167
|
+
_D 14
|
157
168
|
B 13
|
158
|
-
|
159
|
-
|
160
|
-
|
169
|
+
_E 13
|
170
|
+
n._ 13
|
171
|
+
nde 13
|
172
|
+
n. 13
|
173
|
+
ab 13
|
174
|
+
ng_ 13
|
161
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
|
162
184
|
� 13
|
185
|
+
fe 13
|
163
186
|
ls 13
|
164
|
-
|
165
|
-
|
166
|
-
|
167
|
-
|
168
|
-
|
169
|
-
_der_ 12
|
170
|
-
as 12
|
171
|
-
et 12
|
172
|
-
rd 12
|
173
|
-
rn 12
|
187
|
+
ha 13
|
188
|
+
_f 13
|
189
|
+
_T 12
|
190
|
+
_be 12
|
191
|
+
ht_ 12
|
174
192
|
am 12
|
193
|
+
es_ 12
|
194
|
+
_k 12
|
195
|
+
_B 12
|
196
|
+
as 12
|
197
|
+
ste 12
|
175
198
|
lic 12
|
176
|
-
g_ 12
|
177
|
-
rk 12
|
178
|
-
em_ 12
|
179
|
-
_z 12
|
180
|
-
R 12
|
181
|
-
_b 12
|
182
|
-
_D 12
|
183
199
|
wi 12
|
184
|
-
|
185
|
-
ste 12
|
200
|
+
rn 12
|
186
201
|
T 12
|
187
|
-
|
188
|
-
|
189
|
-
|
190
|
-
|
202
|
+
et 12
|
203
|
+
lle 12
|
204
|
+
_zu 12
|
205
|
+
R 12
|
206
|
+
f� 11
|
191
207
|
lich 11
|
192
|
-
|
193
|
-
|
194
|
-
|
208
|
+
he_ 11
|
209
|
+
it_ 11
|
210
|
+
_Sch 11
|
195
211
|
U 11
|
196
|
-
|
197
|
-
|
198
|
-
|
199
|
-
|
212
|
+
tr 11
|
213
|
+
den_ 11
|
214
|
+
ck 11
|
215
|
+
rte 11
|
216
|
+
ge_ 11
|
217
|
+
_Sc 11
|
218
|
+
rk 11
|
219
|
+
tt 11
|
220
|
+
_vo 11
|
200
221
|
uf 11
|
222
|
+
ers 11
|
223
|
+
Sch 11
|
201
224
|
Sc 11
|
202
|
-
|
203
|
-
f� 11
|
204
|
-
rte 11
|
205
|
-
ren 11
|
206
|
-
ve 11
|
225
|
+
ent 11
|
207
226
|
nn 11
|
208
|
-
|
209
|
-
|
210
|
-
tt 11
|
211
|
-
ck 11
|
212
|
-
n, 11
|
213
|
-
ts 11
|
227
|
+
nte 11
|
228
|
+
G 11
|
214
229
|
hl 11
|
215
|
-
|
216
|
-
|
217
|
-
|
218
|
-
|
219
|
-
|
220
|
-
_K 10
|
221
|
-
hi 10
|
222
|
-
gs 10
|
230
|
+
ni 11
|
231
|
+
�r_ 11
|
232
|
+
ve 11
|
233
|
+
ren 11
|
234
|
+
men 11
|
223
235
|
als 10
|
224
|
-
|
225
|
-
|
226
|
-
|
227
|
-
|
228
|
-
run 10
|
229
|
-
ht_ 10
|
230
|
-
sin 10
|
231
|
-
rc 10
|
236
|
+
auf 10
|
237
|
+
n,_ 10
|
238
|
+
_ge 10
|
239
|
+
ung_ 10
|
232
240
|
isch 10
|
233
|
-
|
241
|
+
_f�r 10
|
242
|
+
n, 10
|
243
|
+
ts 10
|
234
244
|
f�r 10
|
245
|
+
ls_ 10
|
246
|
+
hi 10
|
247
|
+
_G 10
|
248
|
+
_f�r_ 10
|
249
|
+
ru 10
|
250
|
+
en._ 10
|
251
|
+
sin 10
|
252
|
+
gs 10
|
235
253
|
isc 10
|
236
|
-
�
|
237
|
-
_E 10
|
254
|
+
_f� 10
|
238
255
|
um 10
|
239
|
-
|
240
|
-
|
241
|
-
|
242
|
-
|
243
|
-
|
244
|
-
|
245
|
-
|
246
|
-
|
247
|
-
|
248
|
-
|
249
|
-
ik 9
|
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
|
250
266
|
nen 9
|
267
|
+
no 9
|
268
|
+
ma 9
|
269
|
+
o_ 9
|
270
|
+
u_ 9
|
271
|
+
ren_ 9
|
272
|
+
ver 9
|
251
273
|
ere 9
|
252
|
-
|
253
|
-
|
254
|
-
|
274
|
+
_Un 9
|
275
|
+
_ha 9
|
276
|
+
nder 9
|
255
277
|
ngs 9
|
256
|
-
ver 9
|
257
|
-
f�r_ 9
|
258
|
-
hre 9
|
259
|
-
so 9
|
260
|
-
no 9
|
261
|
-
_Sch 9
|
262
|
-
O 9
|
263
278
|
ze 9
|
279
|
+
M 9
|
280
|
+
che_ 9
|
281
|
+
om 9
|
264
282
|
rch 9
|
265
|
-
|
283
|
+
ungs 9
|
284
|
+
_M 9
|
285
|
+
ich_ 9
|
286
|
+
als_ 9
|
287
|
+
e,_ 9
|
288
|
+
O 9
|
266
289
|
il 9
|
267
|
-
|
268
|
-
|
290
|
+
ik 9
|
291
|
+
e, 9
|
292
|
+
so 9
|
293
|
+
hre 9
|
269
294
|
Un 9
|
270
|
-
|
271
|
-
|
272
|
-
|
273
|
-
le_ 8
|
274
|
-
_ha 8
|
275
|
-
es_ 8
|
276
|
-
_f 8
|
295
|
+
lt 9
|
296
|
+
_Le 8
|
297
|
+
kei 8
|
277
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
|
278
308
|
_das 8
|
309
|
+
Le 8
|
310
|
+
du 8
|
279
311
|
uc 8
|
280
|
-
|
281
|
-
|
312
|
+
ner 8
|
313
|
+
das_ 8
|
314
|
+
V 8
|
282
315
|
sic 8
|
283
|
-
_Le 8
|
284
|
-
_Un 8
|
285
|
-
das 8
|
286
|
-
ute 8
|
287
|
-
wo 8
|
288
316
|
la 8
|
289
|
-
|
317
|
+
le_ 8
|
318
|
+
tig 8
|
290
319
|
ol 8
|
291
|
-
|
292
|
-
|
320
|
+
erk 8
|
321
|
+
tra 8
|
322
|
+
ber 8
|
323
|
+
ein_ 8
|
324
|
+
mme 8
|
325
|
+
nen_ 8
|
326
|
+
ind 8
|
327
|
+
im_ 8
|
293
328
|
ir 8
|
294
|
-
|
295
|
-
|
296
|
-
du 8
|
329
|
+
bei 8
|
330
|
+
das 8
|
297
331
|
sich 8
|
298
|
-
|
299
|
-
ind 8
|
300
|
-
rde 8
|
301
|
-
ens 8
|
332
|
+
_das_ 8
|
302
333
|
urc 8
|
303
|
-
|
304
|
-
|
305
|
-
|
306
|
-
|
307
|
-
|
308
|
-
|
309
|
-
|
310
|
-
|
311
|
-
ih 7
|
312
|
-
f_ 7
|
313
|
-
ein_ 7
|
314
|
-
ba 7
|
315
|
-
durch 7
|
316
|
-
_al 7
|
317
|
-
_un 7
|
318
|
-
en, 7
|
319
|
-
_wi 7
|
334
|
+
ter_ 8
|
335
|
+
od 7
|
336
|
+
_durc 7
|
337
|
+
do 7
|
338
|
+
von_ 7
|
339
|
+
ko 7
|
340
|
+
mi 7
|
341
|
+
urch 7
|
320
342
|
des 7
|
343
|
+
_o 7
|
344
|
+
dur 7
|
345
|
+
y 7
|
321
346
|
ho 7
|
322
|
-
|
323
|
-
das_ 7
|
324
|
-
nh 7
|
325
|
-
unge 7
|
347
|
+
_hat 7
|
326
348
|
io 7
|
327
|
-
|
328
|
-
|
329
|
-
|
330
|
-
|
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
|
331
360
|
eut 7
|
361
|
+
_als_ 7
|
362
|
+
zu_ 7
|
363
|
+
en,_ 7
|
364
|
+
en, 7
|
365
|
+
ne_ 7
|
332
366
|
durc 7
|
333
|
-
|
334
|
-
|
367
|
+
durch 7
|
368
|
+
�_ 7
|
369
|
+
_ve 7
|
370
|
+
_von 7
|
371
|
+
_auf 7
|
372
|
+
ing 7
|
373
|
+
eit_ 7
|
335
374
|
keit 7
|
336
|
-
|
375
|
+
ih 7
|
337
376
|
eute 7
|
338
|
-
|
377
|
+
_dur 7
|
378
|
+
_ih 7
|
339
379
|
P 7
|
340
|
-
|
341
|
-
as_ 7
|
342
|
-
n._ 7
|
343
|
-
r� 7
|
344
|
-
rei 7
|
345
|
-
_ve 7
|
346
|
-
ert 7
|
347
|
-
y 7
|
348
|
-
urch 7
|
349
|
-
do 7
|
350
|
-
uch 7
|
351
|
-
ich_ 7
|
380
|
+
ba 7
|
352
381
|
sti 7
|
353
382
|
von 7
|
354
383
|
tte 7
|
355
|
-
|
356
|
-
|
357
|
-
|
358
|
-
|
359
|
-
|
360
|
-
_ver 7
|
384
|
+
H 7
|
385
|
+
_von_ 7
|
386
|
+
_P 7
|
387
|
+
rei 7
|
388
|
+
_du 7
|
361
389
|
_Leu 7
|
362
|
-
|
363
|
-
|
364
|
-
|
365
|
-
|
366
|
-
|
367
|
-
|
368
|
-
|
369
|
-
|
370
|
-
|
371
|
-
|
372
|
-
hw 6
|
373
|
-
hu 6
|
374
|
-
von_ 6
|
390
|
+
_St 7
|
391
|
+
icht 7
|
392
|
+
uch 7
|
393
|
+
r� 7
|
394
|
+
run 7
|
395
|
+
_we 7
|
396
|
+
unge 7
|
397
|
+
imm 6
|
398
|
+
_V 6
|
399
|
+
ngen 6
|
375
400
|
sind 6
|
376
|
-
nge_ 6
|
377
|
-
ren_ 6
|
378
|
-
mmen 6
|
379
|
-
nter 6
|
380
|
-
_sich 6
|
381
|
-
Z 6
|
382
|
-
rst 6
|
383
|
-
he_ 6
|
384
|
-
ter_ 6
|
385
|
-
_f� 6
|
386
|
-
_we 6
|
387
|
-
ute_ 6
|
388
|
-
_hat 6
|
389
|
-
vor 6
|
390
|
-
ung_ 6
|
391
|
-
th 6
|
392
|
-
eru 6
|
393
|
-
_ih 6
|
394
|
-
gu 6
|
395
|
-
t. 6
|
396
|
-
_im 6
|
397
|
-
x 6
|
398
|
-
N 6
|
399
|
-
ben 6
|
400
|
-
_ers 6
|