scylla 0.5.0 → 0.6.0
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/Gemfile +4 -2
- data/Gemfile.lock +16 -1
- data/lib/scylla/classifier.rb +1 -1
- data/lib/scylla/generator.rb +16 -4
- data/lib/scylla/lms/afrikaans.lm +232 -232
- data/lib/scylla/lms/arabic.lm +175 -175
- data/lib/scylla/lms/bulgarian.lm +225 -225
- data/lib/scylla/lms/catalan.lm +309 -309
- data/lib/scylla/lms/danish.lm +167 -167
- data/lib/scylla/lms/english.lm +398 -398
- data/lib/scylla/lms/finnish.lm +237 -237
- data/lib/scylla/lms/french.lm +148 -148
- data/lib/scylla/lms/german.lm +258 -258
- data/lib/scylla/lms/greek.lm +236 -236
- data/lib/scylla/lms/hebrew.lm +154 -154
- data/lib/scylla/lms/hindi.lm +139 -139
- data/lib/scylla/lms/icelandic.lm +239 -239
- data/lib/scylla/lms/indonesian.lm +244 -244
- data/lib/scylla/lms/italian.lm +248 -248
- data/lib/scylla/lms/japanese.lm +90 -90
- data/lib/scylla/lms/korean.lm +306 -306
- data/lib/scylla/lms/norwegian.lm +193 -193
- data/lib/scylla/lms/polish.lm +241 -241
- data/lib/scylla/lms/portuguese.lm +232 -232
- data/lib/scylla/lms/romanian.lm +246 -246
- data/lib/scylla/lms/slovak.lm +242 -242
- data/lib/scylla/lms/slovenian.lm +229 -229
- data/lib/scylla/lms/spanish.lm +164 -164
- data/lib/scylla/lms/swedish.lm +157 -157
- data/lib/scylla/lms/tagalog.lm +247 -247
- data/lib/scylla/lms/thai.lm +252 -252
- data/lib/scylla/lms/turkish.lm +285 -285
- data/lib/scylla/lms/vietnamese.lm +250 -250
- data/lib/scylla/lms/welsh.lm +248 -248
- data/lib/scylla/resources.rb +1 -9
- data/lib/scylla.rb +4 -0
- data/scylla.gemspec +2 -120
- data/source_texts/english.txt +62 -27
- data/test/classifier_test.rb +1 -3
- data/test/fixtures/lms/danish.lm +173 -173
- data/test/fixtures/lms/english.lm +220 -220
- data/test/fixtures/lms/french.lm +175 -175
- data/test/fixtures/lms/german.lm +254 -254
- data/test/fixtures/lms/hindi.lm +139 -139
- data/test/fixtures/lms/italian.lm +236 -236
- data/test/fixtures/lms/japanese.lm +88 -88
- data/test/fixtures/lms/norwegian.lm +182 -182
- data/test/fixtures/lms/spanish.lm +164 -164
- data/test/fixtures/test_languages/spanish +0 -1
- data/test/generator_test.rb +13 -0
- data/test/helper.rb +2 -0
- metadata +18 -25
- data/.document +0 -5
- data/lib/scylla/lms/13375P33K.lm +0 -400
- data/scylla-0.1.0.gem +0 -0
- data/source_texts/13375P33K.txt +0 -199
- data/test/fixtures/lms/13375p33k.lm +0 -400
- data/test/fixtures/source_texts/13375P33K.txt +0 -199
data/lib/scylla/lms/slovak.lm
CHANGED
@@ -8,393 +8,393 @@ r 191
|
|
8
8
|
v 181
|
9
9
|
t 164
|
10
10
|
s 161
|
11
|
-
l 150
|
12
11
|
k 150
|
12
|
+
l 150
|
13
|
+
__ 147
|
13
14
|
c 142
|
14
|
-
__ 137
|
15
15
|
u 130
|
16
16
|
p 127
|
17
17
|
d 123
|
18
18
|
y 106
|
19
|
-
a_
|
19
|
+
a_ 99
|
20
20
|
h 91
|
21
21
|
m 88
|
22
22
|
z 79
|
23
23
|
na 69
|
24
|
-
e_
|
24
|
+
e_ 65
|
25
25
|
. 62
|
26
26
|
ov 62
|
27
27
|
_p 61
|
28
28
|
j 59
|
29
29
|
_s 54
|
30
30
|
ro 53
|
31
|
-
_v 52
|
32
31
|
po 52
|
32
|
+
_v 52
|
33
33
|
b 49
|
34
|
-
ch 46
|
35
34
|
, 46
|
36
|
-
|
35
|
+
ch 46
|
37
36
|
o_ 45
|
37
|
+
._ 45
|
38
38
|
,_ 44
|
39
39
|
v_ 43
|
40
|
+
en 42
|
40
41
|
u_ 42
|
41
42
|
i_ 42
|
42
|
-
en 42
|
43
43
|
_n 41
|
44
44
|
ne 41
|
45
45
|
re 40
|
46
46
|
_z 39
|
47
|
-
la 38
|
48
47
|
an 38
|
48
|
+
la 38
|
49
49
|
st 37
|
50
50
|
_a 36
|
51
51
|
y_ 34
|
52
52
|
vy 33
|
53
53
|
_na 32
|
54
54
|
h_ 32
|
55
|
-
ie 31
|
56
55
|
pr 31
|
56
|
+
ie 31
|
57
57
|
od 31
|
58
58
|
ko 30
|
59
|
+
ch_ 29
|
59
60
|
ci 29
|
60
61
|
er 29
|
61
|
-
ch_ 29
|
62
62
|
ti 28
|
63
|
-
_o 27
|
64
63
|
al 27
|
65
|
-
|
64
|
+
_o 27
|
66
65
|
sk 27
|
66
|
+
ed 27
|
67
67
|
ve 26
|
68
68
|
na_ 26
|
69
|
-
or 26
|
70
|
-
ni 26
|
71
69
|
_po 26
|
72
|
-
|
73
|
-
|
74
|
-
ac 25
|
70
|
+
ni 26
|
71
|
+
or 26
|
75
72
|
ak 25
|
76
|
-
|
77
|
-
ny 25
|
73
|
+
yc 25
|
78
74
|
_t 25
|
75
|
+
ny 25
|
76
|
+
_pr 25
|
79
77
|
va 25
|
80
|
-
|
78
|
+
mi 25
|
79
|
+
ac 25
|
80
|
+
to 24
|
81
81
|
ra 24
|
82
|
+
_k 24
|
82
83
|
in 24
|
83
|
-
to 24
|
84
84
|
ych 24
|
85
|
-
_k 24
|
86
85
|
le 24
|
87
|
-
|
88
|
-
|
86
|
+
ho 24
|
87
|
+
il 23
|
89
88
|
ad 23
|
90
89
|
tr 23
|
91
|
-
|
90
|
+
_v_ 23
|
91
|
+
_m 23
|
92
|
+
ce 22
|
93
|
+
si 22
|
92
94
|
ka 22
|
93
95
|
no 22
|
94
96
|
li 22
|
95
|
-
si 22
|
96
|
-
ce 22
|
97
97
|
_r 21
|
98
98
|
ia 21
|
99
|
-
|
100
|
-
os 20
|
99
|
+
_,_ 20
|
101
100
|
om 20
|
102
|
-
te 20
|
103
101
|
ok 20
|
104
102
|
ych_ 20
|
103
|
+
sa 20
|
104
|
+
te 20
|
105
|
+
_, 20
|
106
|
+
os 20
|
105
107
|
it 20
|
106
|
-
do 19
|
107
108
|
ta 19
|
108
|
-
ku 19
|
109
109
|
da 19
|
110
|
-
|
110
|
+
ku 19
|
111
|
+
do 19
|
111
112
|
S 18
|
112
113
|
za 18
|
113
|
-
me 18
|
114
|
-
_, 18
|
115
114
|
es 18
|
116
|
-
|
117
|
-
ap 17
|
118
|
-
aj 17
|
115
|
+
me 18
|
119
116
|
ov_ 17
|
120
117
|
_na_ 17
|
118
|
+
ap 17
|
119
|
+
aj 17
|
120
|
+
ej 17
|
121
121
|
oc 17
|
122
|
-
ol 16
|
123
122
|
pre 16
|
124
|
-
el 16
|
125
123
|
ky 16
|
126
|
-
|
127
|
-
at 16
|
128
|
-
on 16
|
124
|
+
_sa 16
|
129
125
|
_a_ 16
|
130
126
|
P 16
|
131
|
-
|
127
|
+
ur 16
|
128
|
+
on 16
|
132
129
|
av 16
|
133
|
-
|
130
|
+
el 16
|
131
|
+
at 16
|
132
|
+
ol 16
|
133
|
+
t_ 15
|
134
|
+
_c 15
|
134
135
|
vo 15
|
135
136
|
as 15
|
136
|
-
|
137
|
+
rok 15
|
137
138
|
lo 15
|
138
|
-
% 15
|
139
|
-
ic 15
|
140
139
|
_za 15
|
141
|
-
_ro 15
|
142
140
|
ri 15
|
143
|
-
|
144
|
-
|
145
|
-
|
146
|
-
zi 14
|
147
|
-
ot 14
|
148
|
-
_% 14
|
141
|
+
ic 15
|
142
|
+
_d 15
|
143
|
+
_ro 15
|
149
144
|
ke 14
|
150
|
-
|
151
|
-
m_ 14
|
152
|
-
nych 14
|
153
|
-
N 14
|
154
|
-
_b 14
|
145
|
+
ot 14
|
155
146
|
D 14
|
147
|
+
_b 14
|
148
|
+
N 14
|
156
149
|
nych_ 14
|
157
|
-
_pre 14
|
158
150
|
eh 14
|
159
|
-
|
151
|
+
m_ 14
|
152
|
+
nych 14
|
153
|
+
zi 14
|
154
|
+
ob 14
|
155
|
+
nyc 14
|
156
|
+
_pre 14
|
157
|
+
am 13
|
160
158
|
nu 13
|
161
|
-
ln 13
|
162
159
|
eho 13
|
163
160
|
_vy 13
|
164
|
-
|
161
|
+
ln 13
|
162
|
+
di 13
|
163
|
+
pa 12
|
165
164
|
_ak 12
|
166
|
-
|
167
|
-
|
165
|
+
_do 12
|
166
|
+
zv 12
|
167
|
+
nt 12
|
168
168
|
rov 12
|
169
|
+
dn 12
|
169
170
|
_u 12
|
170
171
|
co 12
|
171
|
-
|
172
|
-
|
173
|
-
|
174
|
-
nt 12
|
175
|
-
pa 12
|
176
|
-
sa_ 11
|
172
|
+
sa_ 12
|
173
|
+
ne_ 12
|
174
|
+
sp 12
|
177
175
|
n_ 11
|
178
|
-
kt 11
|
179
|
-
vi 11
|
180
176
|
ho_ 11
|
181
|
-
ne_ 11
|
182
177
|
l_ 11
|
183
|
-
|
178
|
+
j_ 11
|
184
179
|
ny_ 11
|
185
|
-
( 11
|
186
180
|
eho_ 11
|
187
|
-
|
188
|
-
az 11
|
181
|
+
_sa_ 11
|
189
182
|
cen 11
|
183
|
+
ovy 11
|
190
184
|
ar 11
|
191
|
-
|
185
|
+
vi 11
|
186
|
+
az 11
|
187
|
+
kt 11
|
192
188
|
_tr 11
|
193
|
-
|
194
|
-
|
195
|
-
|
196
|
-
|
189
|
+
_. 11
|
190
|
+
zn 11
|
191
|
+
_N 11
|
192
|
+
g 10
|
193
|
+
k_ 10
|
197
194
|
om_ 10
|
198
|
-
|
195
|
+
- 10
|
196
|
+
pe 10
|
197
|
+
_._ 10
|
199
198
|
nan 10
|
200
|
-
|
201
|
-
|
202
|
-
|
203
|
-
nc 10
|
204
|
-
ast 10
|
199
|
+
iv 10
|
200
|
+
oz 10
|
201
|
+
_j 10
|
205
202
|
du 10
|
206
|
-
|
207
|
-
|
208
|
-
|
203
|
+
ast 10
|
204
|
+
ky_ 10
|
205
|
+
nc 10
|
209
206
|
ju 10
|
210
|
-
|
211
|
-
|
212
|
-
ik 10
|
213
|
-
ova 10
|
207
|
+
ek 10
|
208
|
+
Na 10
|
214
209
|
ove 10
|
215
|
-
oz 10
|
216
210
|
R 10
|
211
|
+
de 10
|
212
|
+
ej_ 10
|
213
|
+
ova 10
|
214
|
+
ik 10
|
217
215
|
tor 9
|
218
216
|
ina 9
|
219
|
-
|
220
|
-
uro 9
|
221
|
-
je 9
|
222
|
-
em 9
|
223
|
-
lad 9
|
224
|
-
pod 9
|
225
|
-
V 9
|
226
|
-
_mi 9
|
227
|
-
et 9
|
217
|
+
kov 9
|
228
218
|
kl 9
|
229
|
-
cov 9
|
230
|
-
la_ 9
|
231
219
|
ska 9
|
232
|
-
|
233
|
-
f 9
|
234
|
-
_j 9
|
220
|
+
cov 9
|
235
221
|
_P 9
|
222
|
+
ku_ 9
|
223
|
+
pod 9
|
236
224
|
r_ 9
|
237
|
-
|
238
|
-
|
239
|
-
|
240
|
-
|
241
|
-
|
242
|
-
|
243
|
-
|
225
|
+
et 9
|
226
|
+
lad 9
|
227
|
+
uro 9
|
228
|
+
_mi 9
|
229
|
+
V 9
|
230
|
+
f 9
|
231
|
+
_Na 9
|
232
|
+
je 9
|
233
|
+
la_ 9
|
234
|
+
em 9
|
235
|
+
pl 9
|
236
|
+
ze 8
|
244
237
|
_S 8
|
245
|
-
|
238
|
+
en_ 8
|
239
|
+
trh 8
|
246
240
|
ia_ 8
|
247
|
-
|
248
|
-
ep 8
|
249
|
-
est 8
|
250
|
-
_ob 8
|
251
|
-
tu 8
|
252
|
-
ani 8
|
241
|
+
vn 8
|
253
242
|
ka_ 8
|
254
|
-
_trh 8
|
255
|
-
ys 8
|
256
|
-
ti_ 8
|
257
243
|
pri 8
|
258
|
-
|
259
|
-
|
244
|
+
ys 8
|
245
|
+
_h 8
|
246
|
+
st_ 8
|
247
|
+
_trh 8
|
260
248
|
ske 8
|
261
|
-
rh 8
|
262
|
-
sl 8
|
263
|
-
ent 8
|
264
|
-
vn 8
|
265
|
-
_ur 8
|
266
249
|
nej 8
|
250
|
+
ca 8
|
251
|
+
sl 8
|
252
|
+
uc 8
|
253
|
+
red 8
|
254
|
+
_U 8
|
255
|
+
ti_ 8
|
256
|
+
vys 8
|
257
|
+
rh 8
|
258
|
+
_sp 8
|
259
|
+
est 8
|
267
260
|
M 8
|
261
|
+
Po 8
|
268
262
|
U 8
|
269
|
-
|
263
|
+
_rok 8
|
264
|
+
ani 8
|
265
|
+
tu 8
|
270
266
|
ie_ 8
|
271
|
-
|
272
|
-
|
273
|
-
|
274
|
-
|
275
|
-
|
276
|
-
|
277
|
-
ns 7
|
278
|
-
_zv 7
|
279
|
-
_V 7
|
280
|
-
kci 7
|
281
|
-
_ce 7
|
282
|
-
br 7
|
283
|
-
ec 7
|
284
|
-
z_ 7
|
285
|
-
ost 7
|
286
|
-
nu_ 7
|
287
|
-
ati 7
|
288
|
-
_Po 7
|
289
|
-
akci 7
|
267
|
+
_ob 8
|
268
|
+
ep 8
|
269
|
+
_ur 8
|
270
|
+
ent 8
|
271
|
+
pred 8
|
272
|
+
_V 8
|
290
273
|
van 7
|
291
|
-
|
292
|
-
eni 7
|
293
|
-
ali 7
|
294
|
-
ru 7
|
295
|
-
spo 7
|
274
|
+
akci 7
|
296
275
|
_US 7
|
297
|
-
|
298
|
-
_ne 7
|
276
|
+
USD 7
|
299
277
|
_e 7
|
300
278
|
uj 7
|
301
|
-
|
279
|
+
_uro 7
|
302
280
|
is 7
|
281
|
+
nu_ 7
|
282
|
+
kc 7
|
283
|
+
ali 7
|
284
|
+
_Po 7
|
303
285
|
akc 7
|
304
286
|
_akci 7
|
305
|
-
|
306
|
-
|
307
|
-
|
308
|
-
|
287
|
+
SD 7
|
288
|
+
_ce 7
|
289
|
+
spo 7
|
290
|
+
br 7
|
309
291
|
_USD 7
|
292
|
+
ud 7
|
310
293
|
up 7
|
311
|
-
|
312
|
-
|
313
|
-
|
294
|
+
ec 7
|
295
|
+
hod 7
|
296
|
+
sti 7
|
314
297
|
US 7
|
315
|
-
|
316
|
-
|
317
|
-
|
298
|
+
_l 7
|
299
|
+
_akc 7
|
300
|
+
eni 7
|
301
|
+
ost 7
|
302
|
+
er_ 7
|
303
|
+
z_ 7
|
304
|
+
neh 7
|
305
|
+
ru 7
|
306
|
+
ns 7
|
307
|
+
_ne 7
|
318
308
|
mo 7
|
319
|
-
|
320
|
-
|
309
|
+
kci 7
|
310
|
+
ati 7
|
311
|
+
_zv 7
|
312
|
+
neho 7
|
313
|
+
_pred 7
|
314
|
+
oro 7
|
315
|
+
su 7
|
316
|
+
id 6
|
321
317
|
li_ 6
|
322
|
-
|
323
|
-
ty 6
|
324
|
-
F 6
|
325
|
-
cii 6
|
318
|
+
yr 6
|
326
319
|
re_ 6
|
327
|
-
|
328
|
-
|
329
|
-
|
330
|
-
|
331
|
-
|
332
|
-
|
333
|
-
_%. 6
|
334
|
-
V_ 6
|
335
|
-
J 6
|
336
|
-
tre 6
|
337
|
-
otr 6
|
320
|
+
us 6
|
321
|
+
ele 6
|
322
|
+
_pl 6
|
323
|
+
sia 6
|
324
|
+
by 6
|
325
|
+
u. 6
|
338
326
|
odn 6
|
339
|
-
_pod 6
|
340
327
|
_vo 6
|
341
|
-
alo 6
|
342
|
-
u. 6
|
343
|
-
nov 6
|
344
|
-
ni_ 6
|
345
|
-
roku_ 6
|
346
|
-
oku_ 6
|
347
|
-
id 6
|
348
328
|
cie 6
|
349
|
-
|
350
|
-
|
351
|
-
|
352
|
-
hr 6
|
353
|
-
osl 6
|
354
|
-
us 6
|
355
|
-
mi_ 6
|
356
|
-
sta 6
|
357
|
-
cho 6
|
358
|
-
ja 6
|
359
|
-
ele 6
|
360
|
-
tiv 6
|
329
|
+
roku 6
|
330
|
+
ty 6
|
331
|
+
ke_ 6
|
361
332
|
iny_ 6
|
362
|
-
|
363
|
-
|
364
|
-
|
333
|
+
pos 6
|
334
|
+
ly 6
|
335
|
+
por 6
|
365
336
|
ore 6
|
366
|
-
|
337
|
+
nov 6
|
338
|
+
_st 6
|
367
339
|
il_ 6
|
368
|
-
|
369
|
-
|
370
|
-
|
340
|
+
cii 6
|
341
|
+
he 6
|
342
|
+
nsk 6
|
343
|
+
_ku 6
|
344
|
+
cho 6
|
345
|
+
tiv 6
|
346
|
+
ri_ 6
|
347
|
+
alo 6
|
348
|
+
V_ 6
|
349
|
+
nej_ 6
|
350
|
+
oku_ 6
|
351
|
+
zac 6
|
352
|
+
_pod 6
|
353
|
+
osl 6
|
371
354
|
e. 6
|
372
|
-
|
373
|
-
|
374
|
-
|
375
|
-
|
376
|
-
|
377
|
-
|
355
|
+
otr 6
|
356
|
+
-_ 6
|
357
|
+
ast_ 6
|
358
|
+
mie 6
|
359
|
+
sil 6
|
360
|
+
iny 6
|
378
361
|
ach 6
|
379
|
-
|
380
|
-
|
381
|
-
|
362
|
+
hr 6
|
363
|
+
mi_ 6
|
364
|
+
_cen 6
|
365
|
+
kon 6
|
382
366
|
aci 6
|
383
|
-
|
384
|
-
|
385
|
-
|
367
|
+
C 6
|
368
|
+
_me 6
|
369
|
+
tn 6
|
370
|
+
ja 6
|
371
|
+
J 6
|
386
372
|
ii 6
|
387
|
-
|
388
|
-
|
389
|
-
|
390
|
-
|
373
|
+
rod 6
|
374
|
+
eb 6
|
375
|
+
ni_ 6
|
376
|
+
F 6
|
377
|
+
sta 6
|
378
|
+
roku_ 6
|
379
|
+
tre 6
|
380
|
+
oku 6
|
381
|
+
_pri 6
|
382
|
+
to_ 5
|
383
|
+
oven 5
|
384
|
+
kor 5
|
385
|
+
kla 5
|
386
|
+
op 5
|
391
387
|
neho_ 5
|
388
|
+
lov 5
|
389
|
+
dol 5
|
392
390
|
_ze 5
|
393
|
-
|
394
|
-
|
395
|
-
|
391
|
+
pla 5
|
392
|
+
_o_ 5
|
393
|
+
sky 5
|
394
|
+
ier 5
|
395
|
+
anc 5
|
396
|
+
hra 5
|
397
|
+
_oc 5
|
398
|
+
uk 5
|
399
|
+
ska_ 5
|
396
400
|
za_ 5
|
397
|
-
op 5
|
398
|
-
_%._ 5
|
399
|
-
rn 5
|
400
|
-
_- 5
|