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
@@ -1,4 +1,4 @@
|
|
1
|
-
_
|
1
|
+
_ 2622
|
2
2
|
e 773
|
3
3
|
t 520
|
4
4
|
i 515
|
@@ -11,26 +11,26 @@ u 337
|
|
11
11
|
l 264
|
12
12
|
m 234
|
13
13
|
d 226
|
14
|
-
e_
|
14
|
+
e_ 213
|
15
15
|
c 198
|
16
16
|
h 188
|
17
17
|
p 178
|
18
|
-
s_
|
18
|
+
s_ 153
|
19
19
|
re 134
|
20
20
|
_a 127
|
21
|
+
_t 127
|
21
22
|
t_ 127
|
22
23
|
in 123
|
23
|
-
|
24
|
+
m_ 105
|
24
25
|
or 103
|
25
|
-
m_ 101
|
26
26
|
f 99
|
27
27
|
b 91
|
28
|
+
n_ 89
|
29
|
+
_o 87
|
28
30
|
g 87
|
29
|
-
_o 85
|
30
|
-
n_ 85
|
31
31
|
th 84
|
32
|
+
d_ 84
|
32
33
|
er 83
|
33
|
-
d_ 83
|
34
34
|
_i 82
|
35
35
|
he 81
|
36
36
|
y 80
|
@@ -39,362 +39,362 @@ _e 78
|
|
39
39
|
at 78
|
40
40
|
,_ 75
|
41
41
|
, 75
|
42
|
+
_s 73
|
42
43
|
on 73
|
43
44
|
es 72
|
44
|
-
_s 72
|
45
45
|
te 72
|
46
46
|
_th 70
|
47
47
|
is 69
|
48
48
|
_p 65
|
49
49
|
. 64
|
50
50
|
v 63
|
51
|
-
o_ 63
|
52
51
|
um 63
|
52
|
+
o_ 63
|
53
53
|
se 62
|
54
|
-
|
54
|
+
r_ 62
|
55
55
|
w 60
|
56
|
-
|
56
|
+
en 60
|
57
57
|
ti 59
|
58
58
|
it 58
|
59
59
|
nd 58
|
60
60
|
_d 56
|
61
|
-
|
62
|
-
ur 52
|
61
|
+
._ 55
|
63
62
|
as 52
|
64
63
|
the 52
|
64
|
+
ur 52
|
65
|
+
nt 51
|
66
|
+
a_ 50
|
65
67
|
_the 50
|
66
68
|
su 50
|
67
|
-
|
68
|
-
|
69
|
+
_c 49
|
70
|
+
y_ 49
|
69
71
|
q 48
|
70
72
|
he_ 48
|
71
73
|
qu 48
|
72
|
-
y_ 47
|
73
74
|
_w 47
|
75
|
+
um_ 47
|
76
|
+
_b 47
|
74
77
|
us 46
|
75
|
-
_b 46
|
76
|
-
um_ 45
|
77
|
-
._ 45
|
78
78
|
le 45
|
79
79
|
of 44
|
80
80
|
em 44
|
81
|
-
ta 43
|
82
81
|
si 43
|
82
|
+
ta 43
|
83
|
+
re_ 43
|
83
84
|
ed 42
|
84
85
|
f_ 42
|
85
86
|
ore 42
|
86
87
|
_of 42
|
87
|
-
k 41
|
88
88
|
to 41
|
89
|
-
|
89
|
+
k 41
|
90
90
|
li 40
|
91
|
-
re_ 40
|
92
91
|
et 40
|
93
|
-
|
92
|
+
ng 40
|
94
93
|
the_ 39
|
95
94
|
ea 39
|
96
|
-
_of_ 39
|
97
|
-
is_ 39
|
98
|
-
_the_ 39
|
99
95
|
of_ 39
|
100
|
-
|
96
|
+
_the_ 39
|
97
|
+
is_ 39
|
98
|
+
_of_ 39
|
99
|
+
and 39
|
101
100
|
in_ 38
|
102
101
|
ol 38
|
103
|
-
|
102
|
+
st 38
|
104
103
|
_m 37
|
105
104
|
_in 37
|
105
|
+
de 37
|
106
106
|
_an 36
|
107
107
|
io 35
|
108
108
|
_h 35
|
109
109
|
_r 35
|
110
|
-
la 34
|
111
|
-
ed_ 34
|
112
110
|
ri 34
|
113
|
-
ar 34
|
114
111
|
ve 34
|
115
|
-
|
112
|
+
la 34
|
113
|
+
ar 34
|
114
|
+
ed_ 34
|
116
115
|
ou 33
|
117
|
-
ce 33
|
118
116
|
_f 33
|
119
|
-
|
120
|
-
|
121
|
-
|
117
|
+
ce 33
|
118
|
+
ing 33
|
119
|
+
_I 32
|
122
120
|
ec 32
|
121
|
+
I 32
|
122
|
+
lo 32
|
123
|
+
ro 32
|
124
|
+
_l 31
|
125
|
+
nd_ 31
|
123
126
|
ng_ 31
|
124
|
-
_I 31
|
125
127
|
g_ 31
|
126
|
-
nd_ 31
|
127
|
-
_to 30
|
128
|
-
_l 30
|
129
|
-
al 30
|
130
128
|
em_ 30
|
131
|
-
ing_ 30
|
132
129
|
el 30
|
133
|
-
|
134
|
-
|
130
|
+
es_ 30
|
131
|
+
_n 30
|
135
132
|
ha 30
|
136
133
|
co 30
|
137
|
-
|
134
|
+
ing_ 30
|
135
|
+
al 30
|
136
|
+
to_ 30
|
137
|
+
ni 30
|
138
|
+
_to 30
|
138
139
|
no 29
|
139
|
-
ra 29
|
140
140
|
di 29
|
141
|
-
ut 29
|
142
|
-
es_ 29
|
143
141
|
om 29
|
144
|
-
|
145
|
-
|
146
|
-
ai 28
|
142
|
+
ra 29
|
143
|
+
ut 29
|
147
144
|
am 28
|
145
|
+
ct 28
|
148
146
|
_u 28
|
149
147
|
l_ 28
|
150
148
|
ne 28
|
149
|
+
ic 28
|
150
|
+
ai 28
|
151
|
+
_v 27
|
151
152
|
ion 27
|
152
|
-
|
153
|
-
_re 27
|
154
|
-
do 27
|
153
|
+
ns 27
|
155
154
|
_and 27
|
156
|
-
ll 27
|
157
155
|
and_ 27
|
158
156
|
_and_ 27
|
159
|
-
|
160
|
-
|
161
|
-
|
157
|
+
_re 27
|
158
|
+
ll 27
|
159
|
+
rem 27
|
160
|
+
do 26
|
161
|
+
_a_ 26
|
162
162
|
_to_ 26
|
163
163
|
sum 26
|
164
|
+
L 26
|
165
|
+
_L 26
|
164
166
|
ia 26
|
165
|
-
_a_ 26
|
166
|
-
_q 25
|
167
|
-
ps 25
|
168
|
-
ci 25
|
169
167
|
ru 25
|
170
168
|
_qu 25
|
169
|
+
ps 25
|
170
|
+
_q 25
|
171
171
|
pa 25
|
172
|
-
il 25
|
173
172
|
tio 25
|
174
|
-
|
175
|
-
|
176
|
-
ati 24
|
177
|
-
ui 24
|
173
|
+
ci 25
|
174
|
+
il 25
|
178
175
|
un 24
|
179
176
|
x 24
|
180
|
-
|
181
|
-
|
182
|
-
|
177
|
+
on_ 24
|
178
|
+
ui 24
|
179
|
+
ati 24
|
180
|
+
me 24
|
183
181
|
ss 23
|
184
182
|
_co 23
|
185
|
-
pl 23
|
186
183
|
orem 23
|
187
|
-
|
184
|
+
psu 23
|
188
185
|
psum 23
|
189
186
|
_in_ 23
|
190
|
-
|
191
|
-
|
187
|
+
pl 23
|
188
|
+
rem_ 23
|
189
|
+
hi 23
|
190
|
+
tion 23
|
191
|
+
or_ 23
|
192
|
+
ure 22
|
193
|
+
mo 22
|
192
194
|
_do 22
|
193
|
-
id 22
|
194
195
|
se_ 22
|
195
|
-
nc 22
|
196
|
-
on_ 22
|
197
|
-
or_ 22
|
198
|
-
mo 22
|
199
|
-
im 22
|
200
196
|
ma 22
|
201
|
-
|
197
|
+
orem_ 22
|
202
198
|
tr 22
|
203
|
-
|
199
|
+
id 22
|
200
|
+
im 22
|
201
|
+
sum_ 22
|
202
|
+
_pa 22
|
204
203
|
ac 21
|
205
204
|
it_ 21
|
205
|
+
nc 21
|
206
206
|
lor 21
|
207
207
|
_si 20
|
208
|
-
ex 20
|
209
|
-
psum_ 20
|
210
208
|
at_ 20
|
211
|
-
|
209
|
+
psum_ 20
|
212
210
|
i_ 20
|
213
211
|
ut_ 20
|
212
|
+
tu 20
|
214
213
|
ge 20
|
215
|
-
|
216
|
-
et_ 19
|
217
|
-
Lor 19
|
218
|
-
Lore 19
|
214
|
+
ex 20
|
219
215
|
ons 19
|
216
|
+
pt 19
|
220
217
|
Lo 19
|
221
218
|
Lorem 19
|
219
|
+
_Lore 19
|
220
|
+
er_ 19
|
221
|
+
_Lo 19
|
222
|
+
_Lor 19
|
223
|
+
Lore 19
|
224
|
+
qui 19
|
222
225
|
us_ 19
|
223
|
-
|
224
|
-
|
226
|
+
et_ 19
|
227
|
+
Lor 19
|
228
|
+
ab 18
|
229
|
+
ect 18
|
225
230
|
ain 18
|
231
|
+
_no 18
|
226
232
|
be 18
|
227
233
|
ho 18
|
228
|
-
_Lore 18
|
229
|
-
_de 18
|
230
|
-
pe 18
|
231
|
-
ect 18
|
232
234
|
as_ 18
|
233
|
-
|
234
|
-
ab 18
|
235
|
-
_Lo 18
|
236
|
-
er_ 18
|
237
|
-
nt_ 18
|
235
|
+
pe 18
|
238
236
|
T 18
|
237
|
+
_de 18
|
238
|
+
ple 17
|
239
|
+
Ipsu 17
|
240
|
+
sa 17
|
239
241
|
_Ips 17
|
240
|
-
rum 17
|
241
|
-
vo 17
|
242
|
-
Ip 17
|
243
|
-
eas 17
|
244
|
-
wh 17
|
245
242
|
up 17
|
246
|
-
|
247
|
-
|
248
|
-
|
249
|
-
|
243
|
+
bl 17
|
244
|
+
_T 17
|
245
|
+
vo 17
|
246
|
+
Ips 17
|
250
247
|
_et 17
|
251
|
-
|
248
|
+
rum 17
|
249
|
+
_Ip 17
|
252
250
|
_wh 17
|
253
|
-
|
254
|
-
Ips 17
|
255
|
-
rs 17
|
256
|
-
sa 17
|
251
|
+
ca 17
|
257
252
|
_be 17
|
258
|
-
h_ 17
|
259
253
|
_Ipsu 17
|
260
|
-
|
261
|
-
|
254
|
+
Ipsum 17
|
255
|
+
rs 17
|
256
|
+
wh 17
|
257
|
+
pr 17
|
258
|
+
Ip 17
|
259
|
+
h_ 17
|
260
|
+
_is 17
|
261
|
+
eas 17
|
262
|
+
ate 16
|
263
|
+
ep 16
|
264
|
+
au 16
|
265
|
+
_ma 16
|
266
|
+
tur 16
|
262
267
|
po 16
|
268
|
+
rum_ 16
|
263
269
|
cu 16
|
264
|
-
du 16
|
265
270
|
ch 16
|
266
|
-
|
267
|
-
ate 16
|
268
|
-
ent 16
|
269
|
-
ag 16
|
270
|
-
ep 16
|
271
|
+
du 16
|
271
272
|
ul 16
|
272
|
-
|
273
|
-
|
274
|
-
ere 16
|
275
|
-
au 16
|
273
|
+
olo 16
|
274
|
+
lu 16
|
276
275
|
ua 16
|
277
|
-
|
276
|
+
ag 16
|
277
|
+
nt_ 16
|
278
278
|
_qui 16
|
279
|
-
|
279
|
+
ere 16
|
280
|
+
bu 16
|
281
|
+
ent 16
|
280
282
|
lea 16
|
281
|
-
s, 15
|
282
|
-
na 15
|
283
|
-
_ex 15
|
284
|
-
dolor 15
|
285
|
-
os 15
|
286
|
-
_dolo 15
|
287
283
|
leas 15
|
284
|
+
_dol 15
|
288
285
|
C 15
|
289
|
-
|
290
|
-
dolo 15
|
291
|
-
tat 15
|
286
|
+
_dolo 15
|
292
287
|
dol 15
|
293
|
-
|
288
|
+
_is_ 15
|
289
|
+
ter 15
|
290
|
+
os 15
|
291
|
+
na 15
|
292
|
+
_ex 15
|
294
293
|
_et_ 15
|
294
|
+
tat 15
|
295
295
|
olor 15
|
296
|
-
|
296
|
+
dolor 15
|
297
|
+
s, 15
|
297
298
|
s,_ 15
|
298
|
-
|
299
|
+
ver 15
|
300
|
+
dolo 15
|
301
|
+
sur 14
|
302
|
+
te_ 14
|
299
303
|
ke 14
|
300
|
-
|
304
|
+
ure_ 14
|
301
305
|
so 14
|
302
|
-
rum_ 14
|
303
|
-
_pl 14
|
304
|
-
ip 14
|
305
|
-
qua 14
|
306
306
|
t,_ 14
|
307
|
+
_con 14
|
308
|
+
wi 14
|
309
|
+
_pl 14
|
307
310
|
t, 14
|
311
|
+
con 14
|
312
|
+
qua 14
|
308
313
|
ue 14
|
309
|
-
|
310
|
-
|
311
|
-
|
312
|
-
|
313
|
-
|
314
|
+
ur_ 14
|
315
|
+
en_ 14
|
316
|
+
ip 14
|
317
|
+
vol 13
|
318
|
+
_by_ 13
|
319
|
+
atio 13
|
320
|
+
ation 13
|
321
|
+
_plea 13
|
322
|
+
_ha 13
|
323
|
+
olu 13
|
324
|
+
plea 13
|
325
|
+
sure 13
|
314
326
|
_ve 13
|
315
327
|
_ple 13
|
316
|
-
|
317
|
-
_by_ 13
|
318
|
-
by 13
|
319
|
-
ir 13
|
328
|
+
her 13
|
320
329
|
_mo 13
|
321
|
-
olu 13
|
322
330
|
res 13
|
323
|
-
|
324
|
-
Th 13
|
331
|
+
upt 13
|
325
332
|
pleas 13
|
333
|
+
by_ 13
|
326
334
|
od 13
|
327
|
-
_ha 13
|
328
|
-
ation 13
|
329
|
-
ure_ 13
|
330
|
-
ur_ 13
|
331
335
|
_by 13
|
332
|
-
|
333
|
-
|
334
|
-
|
335
|
-
|
336
|
-
by_ 13
|
337
|
-
upt 13
|
338
|
-
sin 12
|
339
|
-
nte 12
|
340
|
-
da 12
|
336
|
+
by 13
|
337
|
+
ir 13
|
338
|
+
Th 13
|
339
|
+
_Th 13
|
341
340
|
_volu 12
|
342
|
-
volup 12
|
343
|
-
ly_ 12
|
344
|
-
easur 12
|
345
341
|
easu 12
|
346
|
-
|
347
|
-
|
348
|
-
|
349
|
-
lup 12
|
342
|
+
_wi 12
|
343
|
+
easur 12
|
344
|
+
_vol 12
|
350
345
|
ae 12
|
346
|
+
_fr 12
|
347
|
+
olup 12
|
348
|
+
mp 12
|
349
|
+
volu 12
|
350
|
+
sin 12
|
351
|
+
bo 12
|
351
352
|
oo 12
|
353
|
+
olupt 12
|
354
|
+
am_ 12
|
355
|
+
unt 12
|
352
356
|
lupta 12
|
353
|
-
|
354
|
-
|
357
|
+
ly 12
|
358
|
+
asu 12
|
359
|
+
fr 12
|
355
360
|
lupt 12
|
356
|
-
|
361
|
+
pta 12
|
362
|
+
upta 12
|
363
|
+
asur 12
|
357
364
|
leasu 12
|
358
|
-
|
365
|
+
ly_ 12
|
366
|
+
nte 12
|
359
367
|
age 12
|
360
|
-
|
361
|
-
|
362
|
-
|
368
|
+
_pr 12
|
369
|
+
da 12
|
370
|
+
asure 12
|
371
|
+
lup 12
|
363
372
|
est 12
|
364
|
-
_vol 12
|
365
|
-
volu 12
|
366
|
-
asu 12
|
367
|
-
olup 12
|
368
|
-
upta 12
|
369
373
|
_vo 12
|
370
|
-
|
371
|
-
|
372
|
-
|
373
|
-
ly 12
|
374
|
-
asure 12
|
375
|
-
The 11
|
374
|
+
volup 12
|
375
|
+
fo 11
|
376
|
+
_y 11
|
376
377
|
tion_ 11
|
377
|
-
|
378
|
-
|
379
|
-
B 11
|
380
|
-
ain_ 11
|
378
|
+
eq 11
|
379
|
+
_it 11
|
381
380
|
cons 11
|
382
|
-
|
381
|
+
equ 11
|
382
|
+
_us 11
|
383
|
+
cc 11
|
384
|
+
ib 11
|
383
385
|
_pain 11
|
386
|
+
ain_ 11
|
384
387
|
_te 11
|
385
|
-
|
388
|
+
_g 11
|
389
|
+
B 11
|
390
|
+
The 11
|
391
|
+
_se 11
|
386
392
|
oru 11
|
387
|
-
|
393
|
+
_The 11
|
388
394
|
pai 11
|
389
|
-
|
390
|
-
|
391
|
-
|
392
|
-
|
393
|
-
|
394
|
-
|
395
|
-
equ 11
|
396
|
-
fo 11
|
397
|
-
here 11
|
398
|
-
_g 11
|
399
|
-
_us 11
|
400
|
-
eq 11
|
395
|
+
nce 11
|
396
|
+
yo 11
|
397
|
+
_B 11
|
398
|
+
ion_ 11
|
399
|
+
tin 11
|
400
|
+
ore_ 11
|