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/slovenian.lm
CHANGED
@@ -12,20 +12,20 @@ j 171
|
|
12
12
|
v 148
|
13
13
|
k 146
|
14
14
|
d 137
|
15
|
-
e_
|
15
|
+
e_ 122
|
16
16
|
z 119
|
17
17
|
y 119
|
18
18
|
p 117
|
19
|
-
a_
|
19
|
+
a_ 106
|
20
20
|
m 97
|
21
21
|
c 89
|
22
22
|
_s 88
|
23
|
-
o_
|
23
|
+
o_ 85
|
24
24
|
je 78
|
25
25
|
i_ 73
|
26
26
|
cy 70
|
27
|
-
_p 69
|
28
27
|
_n 69
|
28
|
+
_p 69
|
29
29
|
u 61
|
30
30
|
b 60
|
31
31
|
, 58
|
@@ -40,361 +40,361 @@ _z 48
|
|
40
40
|
g 48
|
41
41
|
je_ 47
|
42
42
|
al 46
|
43
|
-
_je 45
|
44
43
|
. 45
|
45
|
-
|
44
|
+
_je 45
|
46
45
|
in 44
|
46
|
+
se 44
|
47
47
|
po 43
|
48
48
|
h 42
|
49
49
|
la 41
|
50
|
-
el 40
|
51
50
|
no 40
|
51
|
+
el 40
|
52
52
|
ye 39
|
53
53
|
_k 38
|
54
54
|
ti 38
|
55
|
-
il 37
|
56
55
|
en 37
|
57
|
-
|
56
|
+
il 37
|
58
57
|
re 36
|
58
|
+
_je_ 36
|
59
59
|
n_ 35
|
60
60
|
ne 35
|
61
|
-
ko 34
|
62
61
|
pr 34
|
62
|
+
ko 34
|
63
|
+
ja 33
|
63
64
|
lo 33
|
64
|
-
va 33
|
65
65
|
de 33
|
66
|
-
|
66
|
+
va 33
|
67
|
+
._ 31
|
68
|
+
_na 31
|
67
69
|
ov 31
|
68
70
|
_po 31
|
69
71
|
ka 31
|
70
72
|
ve 31
|
71
|
-
_na 31
|
72
|
-
._ 31
|
73
|
-
_i 30
|
74
|
-
le 30
|
75
73
|
_d 30
|
74
|
+
le 30
|
75
|
+
_i 30
|
76
76
|
ri 29
|
77
|
-
an 29
|
78
77
|
nj 29
|
79
78
|
za 29
|
80
|
-
|
81
|
-
|
82
|
-
aj 28
|
83
|
-
_m 28
|
79
|
+
an 29
|
80
|
+
aj 29
|
84
81
|
od 28
|
82
|
+
_m 28
|
85
83
|
zy 28
|
84
|
+
li 28
|
85
|
+
te 28
|
86
|
+
_se 27
|
86
87
|
l_ 27
|
87
88
|
et 27
|
88
|
-
_se 27
|
89
89
|
_o 26
|
90
90
|
_t 26
|
91
|
+
v_ 25
|
91
92
|
ro 25
|
92
93
|
ek 25
|
93
94
|
da 25
|
95
|
+
_b 24
|
94
96
|
ih 24
|
95
97
|
ed 24
|
96
|
-
v_ 24
|
97
|
-
_b 24
|
98
98
|
yi 23
|
99
|
+
ocy 23
|
99
100
|
to 23
|
100
101
|
oc 23
|
101
|
-
|
102
|
+
se_ 22
|
102
103
|
ad 22
|
103
104
|
_pr 22
|
104
|
-
|
105
|
+
_se_ 21
|
105
106
|
es 21
|
106
107
|
_za 21
|
107
|
-
so 21
|
108
|
-
_se_ 21
|
109
108
|
_r 21
|
109
|
+
so 21
|
110
|
+
ji 20
|
110
111
|
tr 20
|
112
|
+
ob 20
|
111
113
|
ih_ 20
|
112
|
-
ji 20
|
113
114
|
ar 20
|
114
|
-
h_ 20
|
115
115
|
em 20
|
116
|
-
|
117
|
-
|
118
|
-
is 19
|
119
|
-
ic 19
|
120
|
-
ya 19
|
116
|
+
h_ 20
|
117
|
+
ic 20
|
121
118
|
az 19
|
119
|
+
_v_ 19
|
122
120
|
lo_ 19
|
123
|
-
|
124
|
-
|
125
|
-
cye 18
|
126
|
-
la_ 18
|
121
|
+
ya 19
|
122
|
+
is 19
|
127
123
|
_in 18
|
128
|
-
mo 18
|
129
124
|
ak 18
|
125
|
+
er 18
|
130
126
|
ta 18
|
127
|
+
la_ 18
|
128
|
+
r_ 18
|
131
129
|
iz 18
|
132
|
-
|
133
|
-
|
134
|
-
|
130
|
+
mo 18
|
131
|
+
cye 18
|
132
|
+
bi 17
|
133
|
+
os 17
|
135
134
|
in_ 17
|
136
135
|
_ne 17
|
137
|
-
|
138
|
-
|
136
|
+
ki 17
|
137
|
+
mi 17
|
139
138
|
_in_ 17
|
140
|
-
|
141
|
-
os 17
|
139
|
+
lj 17
|
142
140
|
sy 17
|
143
|
-
|
144
|
-
|
145
|
-
|
146
|
-
|
141
|
+
as 17
|
142
|
+
ga 17
|
143
|
+
on 17
|
144
|
+
t_ 16
|
147
145
|
pre 16
|
146
|
+
ns 16
|
148
147
|
ec 16
|
149
148
|
og 16
|
149
|
+
ot 16
|
150
|
+
ik 16
|
150
151
|
pa 16
|
151
|
-
na_ 15
|
152
|
-
m_ 15
|
153
|
-
_so 15
|
154
|
-
no_ 15
|
155
|
-
sa 15
|
156
|
-
kr 15
|
157
|
-
at 15
|
158
152
|
u_ 15
|
159
|
-
|
153
|
+
sa 15
|
160
154
|
av 15
|
161
155
|
or 15
|
156
|
+
m_ 15
|
157
|
+
kr 15
|
158
|
+
no_ 15
|
159
|
+
ol 15
|
160
|
+
na_ 15
|
162
161
|
so_ 15
|
163
|
-
|
162
|
+
_so 15
|
163
|
+
at 15
|
164
|
+
yn 14
|
164
165
|
dn 14
|
166
|
+
nje 14
|
167
|
+
cyi 14
|
168
|
+
om 14
|
165
169
|
im 14
|
166
|
-
j_ 14
|
167
170
|
di 14
|
171
|
+
j_ 14
|
168
172
|
ecy 14
|
173
|
+
zye 14
|
169
174
|
vo 14
|
170
|
-
yn 14
|
171
|
-
cyi 14
|
172
|
-
nje 14
|
173
|
-
t_ 14
|
174
|
-
om 14
|
175
|
-
ev 13
|
176
175
|
raz 13
|
176
|
+
ne_ 13
|
177
177
|
ke 13
|
178
|
-
|
179
|
-
me 13
|
180
|
-
ye_ 13
|
181
|
-
_pre 13
|
178
|
+
_bi 13
|
182
179
|
i, 13
|
183
|
-
ne_ 13
|
184
|
-
go 13
|
185
180
|
ap 13
|
181
|
+
go 13
|
182
|
+
ye_ 13
|
186
183
|
z_ 13
|
187
|
-
|
188
|
-
_bi 13
|
184
|
+
_pre 13
|
189
185
|
ez 13
|
186
|
+
ev 13
|
190
187
|
_ve 13
|
191
|
-
|
192
|
-
|
193
|
-
|
194
|
-
|
188
|
+
me 13
|
189
|
+
ir 13
|
190
|
+
ins 13
|
191
|
+
_st 12
|
192
|
+
a, 12
|
193
|
+
ok 12
|
195
194
|
vi 12
|
195
|
+
ko_ 12
|
196
|
+
cya 12
|
196
197
|
ij 12
|
197
|
-
|
198
|
-
|
198
|
+
eg 12
|
199
|
+
sto 12
|
199
200
|
li_ 12
|
200
|
-
bil 12
|
201
|
-
ok 12
|
202
|
-
- 12
|
203
|
-
ko_ 12
|
204
|
-
ti_ 12
|
205
|
-
_ko 12
|
206
|
-
_st 12
|
207
201
|
_na_ 12
|
208
202
|
i,_ 12
|
209
|
-
|
210
|
-
|
203
|
+
do 12
|
204
|
+
ova 12
|
205
|
+
ti_ 12
|
206
|
+
- 12
|
207
|
+
ja_ 12
|
208
|
+
_ko 12
|
209
|
+
bil 12
|
210
|
+
cyn 11
|
211
|
+
da_ 11
|
211
212
|
elo 11
|
212
213
|
_ra 11
|
213
|
-
_ni 11
|
214
|
-
_c 11
|
215
|
-
jo 11
|
216
|
-
ilo 11
|
217
|
-
ala 11
|
218
|
-
da_ 11
|
219
|
-
ni_ 11
|
220
|
-
cyn 11
|
221
|
-
nst 11
|
222
214
|
_iz 11
|
215
|
+
nst 11
|
223
216
|
_so_ 11
|
224
|
-
del 11
|
225
|
-
sk 11
|
226
217
|
ga_ 11
|
218
|
+
sk 11
|
219
|
+
ilo 11
|
220
|
+
ala 11
|
221
|
+
del 11
|
227
222
|
__ 11
|
228
|
-
|
223
|
+
_c 11
|
224
|
+
jo 11
|
225
|
+
_ni 11
|
226
|
+
ni_ 11
|
227
|
+
_bil 11
|
228
|
+
aj_ 10
|
229
|
+
W 10
|
229
230
|
_g 10
|
230
|
-
|
231
|
+
Winst 10
|
232
|
+
Wi 10
|
233
|
+
ali 10
|
234
|
+
icy 10
|
235
|
+
it 10
|
236
|
+
un 10
|
237
|
+
nston 10
|
238
|
+
ln 10
|
239
|
+
anj 10
|
231
240
|
insto 10
|
232
|
-
|
241
|
+
nsto 10
|
233
242
|
ston 10
|
243
|
+
Win 10
|
234
244
|
_da 10
|
235
|
-
|
236
|
-
un 10
|
237
|
-
nston 10
|
238
|
-
Wins 10
|
239
|
-
Wi 10
|
240
|
-
_mo 10
|
241
|
-
Winst 10
|
245
|
+
ac 10
|
242
246
|
ost 10
|
243
|
-
|
247
|
+
ala_ 10
|
244
248
|
ton 10
|
245
|
-
|
246
|
-
anj 10
|
247
|
-
am 10
|
248
|
-
it 10
|
249
|
-
aj_ 10
|
250
|
-
W 10
|
249
|
+
_mo 10
|
251
250
|
_l 10
|
252
|
-
|
253
|
-
|
251
|
+
Wins 10
|
252
|
+
inst 10
|
253
|
+
eti 10
|
254
|
+
am 10
|
254
255
|
yal 10
|
255
|
-
le_ 9
|
256
|
-
nic 9
|
257
|
-
il_ 9
|
258
|
-
em_ 9
|
259
|
-
br 9
|
260
|
-
acy 9
|
261
256
|
rj 9
|
262
|
-
|
263
|
-
|
257
|
+
br 9
|
258
|
+
il_ 9
|
264
259
|
jen 9
|
265
|
-
|
266
|
-
kra 9
|
267
|
-
icy 9
|
260
|
+
elo_ 9
|
268
261
|
ce 9
|
262
|
+
kra 9
|
263
|
+
nu 9
|
264
|
+
em_ 9
|
265
|
+
ilo_ 9
|
269
266
|
al_ 9
|
270
267
|
oz 9
|
271
|
-
|
268
|
+
y_ 9
|
269
|
+
nic 9
|
270
|
+
le_ 9
|
271
|
+
_pa 9
|
272
|
+
acy 9
|
272
273
|
pi 9
|
274
|
+
za_ 8
|
275
|
+
ze 8
|
276
|
+
_do 8
|
273
277
|
a,_ 8
|
274
278
|
ej 8
|
275
|
-
|
276
|
-
|
279
|
+
ese 8
|
280
|
+
_cy 8
|
281
|
+
ezy 8
|
282
|
+
vr 8
|
283
|
+
ma 8
|
284
|
+
ah 8
|
285
|
+
bo 8
|
286
|
+
tv 8
|
277
287
|
imi 8
|
278
|
-
o. 8
|
279
288
|
d_ 8
|
289
|
+
yil 8
|
290
|
+
_nj 8
|
291
|
+
val 8
|
292
|
+
ali_ 8
|
280
293
|
rat 8
|
294
|
+
cy_ 8
|
281
295
|
_zy 8
|
282
|
-
ma 8
|
283
|
-
pe 8
|
284
|
-
yil 8
|
285
|
-
ese 8
|
286
|
-
O 8
|
287
|
-
_ka 8
|
288
|
-
tv 8
|
289
|
-
_do 8
|
290
|
-
ze 8
|
291
|
-
kl 8
|
292
|
-
_cy 8
|
293
296
|
k_ 8
|
294
|
-
|
297
|
+
_ka 8
|
298
|
+
ist 8
|
295
299
|
stv 8
|
296
|
-
|
297
|
-
|
300
|
+
pe 8
|
301
|
+
kl 8
|
302
|
+
ran 8
|
303
|
+
O 8
|
304
|
+
o. 8
|
298
305
|
a. 8
|
299
|
-
|
300
|
-
|
301
|
-
ah 8
|
302
|
-
_nj 8
|
303
|
-
bo 8
|
304
|
-
var 7
|
305
|
-
cy_ 7
|
306
|
-
pol 7
|
307
|
-
ega 7
|
308
|
-
dr 7
|
309
|
-
sti 7
|
306
|
+
kih 7
|
307
|
+
dno 7
|
310
308
|
nost 7
|
311
|
-
|
312
|
-
|
313
|
-
ji_ 7
|
314
|
-
str 7
|
315
|
-
eni 7
|
309
|
+
var 7
|
310
|
+
ste 7
|
316
311
|
yno 7
|
317
|
-
|
318
|
-
za_ 7
|
319
|
-
e,_ 7
|
312
|
+
kih_ 7
|
320
313
|
pri 7
|
321
|
-
|
322
|
-
|
314
|
+
ep 7
|
315
|
+
_ko_ 7
|
316
|
+
nov 7
|
317
|
+
ci 7
|
323
318
|
_ob 7
|
324
|
-
|
319
|
+
_od 7
|
320
|
+
o,_ 7
|
321
|
+
dr 7
|
325
322
|
_kr 7
|
326
|
-
ste 7
|
327
323
|
en_ 7
|
324
|
+
_le 7
|
325
|
+
o, 7
|
328
326
|
pa_ 7
|
329
|
-
nov 7
|
330
327
|
tak 7
|
331
|
-
kih 7
|
332
328
|
nih 7
|
333
|
-
|
334
|
-
|
335
|
-
e, 7
|
336
|
-
_le 7
|
337
|
-
_da_ 7
|
338
|
-
_V 7
|
339
|
-
ci 7
|
340
|
-
ep 7
|
329
|
+
e,_ 7
|
330
|
+
op 7
|
341
331
|
S 7
|
342
|
-
|
343
|
-
ju 7
|
332
|
+
e, 7
|
344
333
|
set 7
|
334
|
+
sti 7
|
335
|
+
_da_ 7
|
336
|
+
o._ 7
|
337
|
+
pol 7
|
345
338
|
tem 7
|
346
|
-
|
347
|
-
|
339
|
+
et_ 7
|
340
|
+
cye_ 7
|
341
|
+
_V 7
|
342
|
+
eni 7
|
343
|
+
I 7
|
348
344
|
ocye 7
|
345
|
+
ega 7
|
349
346
|
V 7
|
350
|
-
|
351
|
-
|
352
|
-
|
353
|
-
|
354
|
-
|
355
|
-
|
356
|
-
|
357
|
-
|
347
|
+
nos 7
|
348
|
+
str 7
|
349
|
+
_de 7
|
350
|
+
ju 7
|
351
|
+
sed 7
|
352
|
+
ji_ 7
|
353
|
+
el_ 7
|
354
|
+
eset 6
|
355
|
+
nicy 6
|
356
|
+
stvar 6
|
357
|
+
_za_ 6
|
358
|
+
deset 6
|
359
|
+
_raz 6
|
360
|
+
ved 6
|
361
|
+
_Wins 6
|
362
|
+
vec 6
|
363
|
+
aja 6
|
364
|
+
lad 6
|
365
|
+
_- 6
|
366
|
+
eka 6
|
358
367
|
or_ 6
|
359
|
-
yno_ 6
|
360
|
-
dese 6
|
361
|
-
ede 6
|
362
|
-
-- 6
|
363
|
-
zap 6
|
364
|
-
tk 6
|
365
|
-
des 6
|
366
|
-
iv 6
|
367
|
-
ecye 6
|
368
|
-
tvar 6
|
369
|
-
_nje 6
|
370
|
-
on_ 6
|
371
|
-
nih_ 6
|
372
|
-
nja 6
|
373
368
|
_a 6
|
369
|
+
_Win 6
|
370
|
+
_W 6
|
371
|
+
-- 6
|
374
372
|
va_ 6
|
375
|
-
|
376
|
-
sn 6
|
373
|
+
vs 6
|
377
374
|
ale 6
|
375
|
+
_pol 6
|
378
376
|
dal 6
|
379
|
-
|
380
|
-
|
381
|
-
|
382
|
-
_- 6
|
377
|
+
be 6
|
378
|
+
eli 6
|
379
|
+
vl 6
|
383
380
|
zya 6
|
384
|
-
|
385
|
-
|
386
|
-
|
387
|
-
|
381
|
+
tvar 6
|
382
|
+
stva 6
|
383
|
+
_re 6
|
384
|
+
T 6
|
385
|
+
ston_ 6
|
386
|
+
dese 6
|
387
|
+
_ta 6
|
388
|
+
_stva 6
|
389
|
+
ecye 6
|
390
|
+
yno_ 6
|
388
391
|
_u 6
|
389
|
-
|
392
|
+
_mi 6
|
393
|
+
on_ 6
|
394
|
+
tva 6
|
395
|
+
iv 6
|
396
|
+
nik 6
|
397
|
+
nja 6
|
398
|
+
_te 6
|
390
399
|
gl 6
|
391
|
-
|
392
|
-
_stv 6
|
393
|
-
i. 6
|
394
|
-
vec 6
|
395
|
-
_ta 6
|
396
|
-
et_ 6
|
397
|
-
ved 6
|
398
|
-
ton_ 6
|
399
|
-
si 6
|
400
|
-
er_ 6
|
400
|
+
ki_ 6
|