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/icelandic.lm
CHANGED
@@ -19,382 +19,382 @@ v 74
|
|
19
19
|
ar 73
|
20
20
|
� 71
|
21
21
|
o 70
|
22
|
-
_s
|
22
|
+
_s 65
|
23
23
|
� 63
|
24
24
|
a� 63
|
25
25
|
j 62
|
26
26
|
m_ 56
|
27
|
-
in 55
|
28
27
|
� 55
|
28
|
+
in 55
|
29
29
|
a_ 54
|
30
30
|
_e 51
|
31
|
-
ur 48
|
32
|
-
um 48
|
33
31
|
_f 48
|
34
|
-
|
32
|
+
um 48
|
33
|
+
ur 48
|
35
34
|
_a 47
|
36
35
|
h 47
|
37
|
-
|
36
|
+
n_ 47
|
38
37
|
d 46
|
38
|
+
. 46
|
39
|
+
__ 45
|
39
40
|
_� 45
|
40
|
-
er 44
|
41
|
-
st 44
|
42
41
|
g_ 44
|
42
|
+
st 44
|
43
|
+
i_ 44
|
43
44
|
b 44
|
45
|
+
er 44
|
44
46
|
u_ 43
|
45
|
-
i_ 43
|
46
|
-
a�_ 43
|
47
|
-
� 43
|
48
47
|
� 43
|
48
|
+
� 43
|
49
|
+
a�_ 43
|
49
50
|
nn 42
|
50
51
|
nu 41
|
51
|
-
�_ 40
|
52
52
|
ei 40
|
53
|
+
�_ 40
|
53
54
|
_�_ 39
|
54
|
-
__ 39
|
55
|
-
� 38
|
56
55
|
i� 38
|
56
|
+
� 38
|
57
57
|
y 37
|
58
|
+
ir 36
|
58
59
|
�_ 36
|
59
60
|
an 36
|
60
61
|
_v 36
|
61
|
-
ir 36
|
62
|
-
ve 35
|
63
62
|
p 35
|
64
|
-
|
63
|
+
ve 35
|
65
64
|
og 34
|
66
|
-
|
65
|
+
_� 34
|
67
66
|
_a� 33
|
68
|
-
un 33
|
69
67
|
um_ 33
|
68
|
+
og_ 33
|
69
|
+
un 33
|
70
|
+
_h 32
|
70
71
|
_o 32
|
71
|
-
_h 31
|
72
72
|
_� 30
|
73
73
|
ta 30
|
74
|
-
na 29
|
75
|
-
en 29
|
76
|
-
�u 29
|
77
|
-
_m 29
|
78
74
|
_og_ 29
|
75
|
+
_m 29
|
76
|
+
na 29
|
79
77
|
_og 29
|
78
|
+
�u 29
|
79
|
+
en 29
|
80
80
|
ti 28
|
81
|
-
la 28
|
82
81
|
lu 28
|
83
82
|
ri 28
|
83
|
+
la 28
|
84
84
|
ur_ 27
|
85
|
-
� 26
|
86
85
|
ar_ 26
|
86
|
+
� 26
|
87
87
|
�i 25
|
88
|
-
t_ 25
|
89
|
-
_a�_ 25
|
90
88
|
._ 25
|
89
|
+
_a�_ 25
|
90
|
+
t_ 25
|
91
|
+
ja 24
|
91
92
|
_ve 24
|
92
93
|
_b 24
|
94
|
+
nd 24
|
93
95
|
ra 24
|
94
96
|
ng 24
|
95
|
-
nd 24
|
96
|
-
ja 24
|
97
97
|
r� 23
|
98
98
|
ki 23
|
99
99
|
kk 23
|
100
100
|
ir_ 22
|
101
101
|
i�_ 22
|
102
102
|
sl 21
|
103
|
-
ef 21
|
104
103
|
_�_ 21
|
104
|
+
ef 21
|
105
105
|
tu 20
|
106
|
-
_u 20
|
107
|
-
ku 20
|
108
106
|
em 20
|
107
|
+
ku 20
|
108
|
+
_u 20
|
109
109
|
_t 20
|
110
110
|
il 19
|
111
111
|
inn 19
|
112
112
|
se 19
|
113
113
|
sk 19
|
114
|
-
|
114
|
+
ga 18
|
115
115
|
� 18
|
116
116
|
_g 18
|
117
|
+
�a 18
|
118
|
+
_l 18
|
117
119
|
_n 18
|
118
|
-
ga 18
|
119
120
|
ver 18
|
120
|
-
�a 18
|
121
|
-
ek 17
|
122
121
|
ni 17
|
123
122
|
af 17
|
124
|
-
|
125
|
-
sem 16
|
123
|
+
ek 17
|
126
124
|
eg 16
|
127
125
|
ag 16
|
128
|
-
|
129
|
-
|
130
|
-
|
131
|
-
sem_ 15
|
126
|
+
num 16
|
127
|
+
sem 16
|
128
|
+
ka 15
|
132
129
|
gu 15
|
133
|
-
, 15
|
134
130
|
gi 15
|
131
|
+
mi 15
|
135
132
|
_er 15
|
133
|
+
em_ 15
|
134
|
+
rf 15
|
136
135
|
da 15
|
137
|
-
mi 15
|
138
|
-
ka 15
|
139
136
|
es 15
|
137
|
+
am 15
|
138
|
+
, 15
|
139
|
+
sem_ 15
|
140
140
|
�k 14
|
141
|
-
|
142
|
-
l� 14
|
143
|
-
�e 14
|
141
|
+
nar 14
|
144
142
|
b� 14
|
145
|
-
yr 14
|
146
143
|
nn_ 14
|
147
|
-
|
148
|
-
|
144
|
+
l� 14
|
145
|
+
�e 14
|
149
146
|
,_ 14
|
150
|
-
|
147
|
+
_ver 14
|
148
|
+
�ur 14
|
151
149
|
j� 14
|
152
|
-
|
153
|
-
|
150
|
+
yr 14
|
151
|
+
_se 14
|
152
|
+
vi 13
|
154
153
|
is 13
|
154
|
+
S 13
|
155
155
|
_sem 13
|
156
|
-
|
157
|
-
|
156
|
+
s_ 13
|
157
|
+
ge 13
|
158
|
+
_�e 13
|
158
159
|
li 13
|
160
|
+
l_ 13
|
161
|
+
ll 13
|
162
|
+
tt 13
|
163
|
+
u� 13
|
159
164
|
al 13
|
160
165
|
�g 13
|
161
|
-
S 13
|
162
|
-
u� 13
|
163
|
-
fl 13
|
164
|
-
tt 13
|
165
|
-
l_ 13
|
166
|
-
ge 13
|
167
|
-
_�e 13
|
168
166
|
ne 13
|
169
|
-
|
170
|
-
|
171
|
-
|
172
|
-
inu 12
|
167
|
+
fl 13
|
168
|
+
_sem_ 13
|
169
|
+
re 13
|
173
170
|
ki_ 12
|
174
|
-
|
175
|
-
ru 12
|
171
|
+
ekk 12
|
176
172
|
�k 12
|
177
|
-
ey 12
|
178
|
-
te 12
|
179
173
|
fr 12
|
174
|
+
ru 12
|
175
|
+
me 12
|
176
|
+
ey 12
|
177
|
+
he 12
|
180
178
|
_k 12
|
181
|
-
|
179
|
+
ha 12
|
180
|
+
inu 12
|
181
|
+
te 12
|
182
182
|
fyrir 11
|
183
|
-
|
184
|
-
|
183
|
+
slu 11
|
184
|
+
�s 11
|
185
|
+
ma 11
|
185
186
|
fyr 11
|
186
|
-
fy 11
|
187
187
|
di 11
|
188
|
-
|
188
|
+
us 11
|
189
|
+
fyri 11
|
189
190
|
yri 11
|
190
|
-
�s 11
|
191
|
-
ma 11
|
192
191
|
num_ 11
|
193
|
-
slu 11
|
194
|
-
er� 11
|
195
192
|
rir 11
|
196
|
-
|
193
|
+
_ha 11
|
194
|
+
ju 11
|
195
|
+
fy 11
|
196
|
+
yrir 11
|
197
197
|
rs 11
|
198
|
+
er� 11
|
199
|
+
pp 10
|
200
|
+
or 10
|
201
|
+
�a 10
|
202
|
+
fu 10
|
198
203
|
_mi 10
|
204
|
+
ns 10
|
205
|
+
kj 10
|
199
206
|
_�a 10
|
207
|
+
il_ 10
|
208
|
+
arf 10
|
209
|
+
_ekki 10
|
210
|
+
ekki 10
|
211
|
+
et 10
|
200
212
|
le 10
|
201
|
-
|
202
|
-
�a 10
|
203
|
-
kj 10
|
204
|
-
pp 10
|
213
|
+
ko 10
|
205
214
|
fj 10
|
206
|
-
|
207
|
-
|
208
|
-
_he 10
|
215
|
+
_ekk 10
|
216
|
+
�i_ 10
|
209
217
|
rn 10
|
210
|
-
ekki 10
|
211
218
|
_ek 10
|
212
|
-
|
213
|
-
kki 10
|
214
|
-
_ekk 10
|
219
|
+
_he 10
|
215
220
|
f_ 10
|
216
|
-
|
217
|
-
|
218
|
-
|
219
|
-
et 10
|
220
|
-
_ekki 10
|
221
|
+
kki 10
|
222
|
+
si 10
|
223
|
+
_st 10
|
221
224
|
r�u 10
|
222
|
-
ns 10
|
223
|
-
�i_ 10
|
224
|
-
er_ 9
|
225
225
|
ann 9
|
226
|
-
_st 9
|
227
226
|
gn 9
|
228
|
-
av 9
|
229
|
-
_ti 9
|
230
|
-
ekki_ 9
|
231
|
-
kur 9
|
232
|
-
_um 9
|
233
|
-
kki_ 9
|
234
227
|
K 9
|
235
|
-
til_ 9
|
236
|
-
_er_ 9
|
237
|
-
nni 9
|
238
|
-
_til_ 9
|
239
228
|
sa 9
|
240
|
-
|
229
|
+
kki_ 9
|
241
230
|
v� 9
|
242
|
-
|
243
|
-
|
231
|
+
er_ 9
|
232
|
+
nni 9
|
233
|
+
_ti 9
|
234
|
+
_til_ 9
|
244
235
|
til 9
|
245
236
|
� 9
|
246
|
-
|
247
|
-
|
237
|
+
_er_ 9
|
238
|
+
_til 9
|
239
|
+
av 9
|
240
|
+
f� 9
|
241
|
+
kur 9
|
242
|
+
ekki_ 9
|
243
|
+
til_ 9
|
244
|
+
_um 9
|
245
|
+
ta_ 9
|
246
|
+
a�i 8
|
248
247
|
e� 8
|
249
|
-
|
250
|
-
_ei 8
|
251
|
-
an_ 8
|
252
|
-
ut 8
|
248
|
+
fe 8
|
253
249
|
G 8
|
254
|
-
|
255
|
-
|
256
|
-
|
250
|
+
kt 8
|
251
|
+
�a_ 8
|
252
|
+
ru_ 8
|
257
253
|
H 8
|
258
|
-
|
259
|
-
|
260
|
-
|
254
|
+
�t 8
|
255
|
+
ut 8
|
256
|
+
hef 8
|
257
|
+
_vi 8
|
261
258
|
tu_ 8
|
259
|
+
ing 8
|
260
|
+
stu 8
|
261
|
+
ik 8
|
262
|
+
_sk 8
|
262
263
|
�r 8
|
264
|
+
�n 8
|
265
|
+
an_ 8
|
266
|
+
_S 8
|
267
|
+
u�u 8
|
263
268
|
l�g 8
|
264
|
-
_en 8
|
265
|
-
va 8
|
266
|
-
_vi 8
|
267
|
-
kt 8
|
268
|
-
stu 8
|
269
269
|
st_ 8
|
270
|
-
|
271
|
-
nes 8
|
272
|
-
_sk 8
|
273
|
-
_me 8
|
270
|
+
_en 8
|
274
271
|
fa 8
|
272
|
+
nda 8
|
273
|
+
it 8
|
275
274
|
ngi 8
|
276
|
-
|
277
|
-
|
278
|
-
|
279
|
-
|
280
|
-
|
275
|
+
ss 8
|
276
|
+
_me 8
|
277
|
+
va 8
|
278
|
+
_ei 8
|
279
|
+
nes 8
|
281
280
|
gr 8
|
282
|
-
|
281
|
+
_um_ 8
|
282
|
+
du 8
|
283
|
+
und 7
|
284
|
+
fn 7
|
285
|
+
br 7
|
286
|
+
r�ur 7
|
287
|
+
r. 7
|
288
|
+
jar 7
|
289
|
+
_hef 7
|
283
290
|
ein 7
|
284
|
-
|
285
|
-
|
286
|
-
|
291
|
+
v�k 7
|
292
|
+
av�k 7
|
293
|
+
�ar 7
|
294
|
+
lj 7
|
287
295
|
_H 7
|
288
|
-
_� 7
|
289
296
|
�kk 7
|
290
|
-
|
291
|
-
|
292
|
-
lu_ 7
|
293
|
-
jar 7
|
294
|
-
rt 7
|
295
|
-
gl 7
|
296
|
-
r�ur 7
|
297
|
-
eru_ 7
|
298
|
-
_fj 7
|
299
|
-
rl 7
|
300
|
-
rk 7
|
297
|
+
_f�kk 7
|
298
|
+
�t 7
|
301
299
|
ust 7
|
302
|
-
|
303
|
-
|
304
|
-
_af 7
|
300
|
+
ga_ 7
|
301
|
+
en_ 7
|
305
302
|
_f� 7
|
306
|
-
|
307
|
-
|
308
|
-
|
309
|
-
|
310
|
-
�� 7
|
303
|
+
rl 7
|
304
|
+
ri� 7
|
305
|
+
rir_ 7
|
306
|
+
_b� 7
|
311
307
|
B 7
|
312
|
-
|
313
|
-
|
308
|
+
_G 7
|
309
|
+
as 7
|
314
310
|
kun 7
|
315
|
-
|
316
|
-
|
317
|
-
|
318
|
-
|
319
|
-
|
320
|
-
|
311
|
+
er�ur 7
|
312
|
+
_fr 7
|
313
|
+
�� 7
|
314
|
+
er�u 7
|
315
|
+
_fj 7
|
316
|
+
_af 7
|
317
|
+
lu_ 7
|
318
|
+
un_ 7
|
321
319
|
yrir_ 7
|
322
|
-
|
323
|
-
�ar 7
|
324
|
-
�l 7
|
325
|
-
ga_ 7
|
326
|
-
rir_ 7
|
320
|
+
av� 7
|
327
321
|
_f�k 7
|
328
|
-
|
329
|
-
|
330
|
-
un_ 7
|
322
|
+
rk 7
|
323
|
+
eru 7
|
331
324
|
nar_ 7
|
332
|
-
|
325
|
+
m. 7
|
326
|
+
f�k 7
|
327
|
+
eru_ 7
|
328
|
+
eng 7
|
329
|
+
ld 7
|
330
|
+
�l 7
|
331
|
+
rt 7
|
332
|
+
ig 7
|
333
|
+
_en_ 7
|
334
|
+
gre 7
|
335
|
+
inni 7
|
336
|
+
ram 7
|
333
337
|
fi 7
|
334
|
-
|
338
|
+
ei� 7
|
335
339
|
el 7
|
336
|
-
|
337
|
-
|
338
|
-
|
339
|
-
ri� 7
|
340
|
-
er�u 7
|
341
|
-
_en_ 7
|
342
|
-
ld 7
|
343
|
-
k_ 6
|
344
|
-
enn 6
|
345
|
-
% 6
|
346
|
-
ja_ 6
|
347
|
-
at 6
|
348
|
-
_%_ 6
|
349
|
-
mu 6
|
350
|
-
au 6
|
351
|
-
_ge 6
|
352
|
-
v�kur 6
|
353
|
-
tir 6
|
354
|
-
j� 6
|
355
|
-
i�s 6
|
340
|
+
gl 7
|
341
|
+
_� 7
|
342
|
+
f�kk 7
|
356
343
|
�r_ 6
|
357
|
-
li� 6
|
358
|
-
�ku 6
|
359
|
-
um. 6
|
360
|
-
v�ku 6
|
361
|
-
tir_ 6
|
362
|
-
av�ku 6
|
363
|
-
ka�i 6
|
364
|
-
�l 6
|
365
|
-
_B 6
|
366
|
-
f� 6
|
367
|
-
nga 6
|
368
|
-
tr 6
|
369
|
-
eit 6
|
370
|
-
eir 6
|
371
|
-
nu� 6
|
372
|
-
nna 6
|
373
344
|
upp 6
|
374
|
-
|
375
|
-
|
376
|
-
fra 6
|
377
|
-
yk 6
|
378
|
-
�r 6
|
379
|
-
ra_ 6
|
345
|
+
�kur 6
|
346
|
+
R 6
|
380
347
|
stu_ 6
|
381
|
-
|
348
|
+
sko 6
|
349
|
+
rst 6
|
350
|
+
av�ku 6
|
351
|
+
_K 6
|
352
|
+
ka� 6
|
382
353
|
tar 6
|
354
|
+
i�s 6
|
355
|
+
�r 6
|
356
|
+
tr 6
|
357
|
+
nga 6
|
358
|
+
_B 6
|
383
359
|
dur 6
|
384
|
-
|
385
|
-
|
386
|
-
|
360
|
+
_ge 6
|
361
|
+
fur 6
|
362
|
+
rg 6
|
363
|
+
_up 6
|
364
|
+
j� 6
|
365
|
+
v�ku 6
|
366
|
+
fra 6
|
367
|
+
and 6
|
387
368
|
dag 6
|
388
|
-
|
389
|
-
|
390
|
-
|
391
|
-
|
369
|
+
_ef 6
|
370
|
+
_upp 6
|
371
|
+
nna 6
|
372
|
+
s� 6
|
373
|
+
yk 6
|
374
|
+
tir_ 6
|
375
|
+
lg 6
|
376
|
+
nu� 6
|
377
|
+
enn 6
|
378
|
+
kja 6
|
379
|
+
ka�i 6
|
380
|
+
f� 6
|
381
|
+
�t 6
|
392
382
|
ys 6
|
393
|
-
|
394
|
-
_up 6
|
395
|
-
fur 6
|
396
|
-
R 6
|
383
|
+
up 6
|
397
384
|
tarf 6
|
398
385
|
gar 6
|
399
|
-
|
400
|
-
|
386
|
+
�_ 6
|
387
|
+
ra_ 6
|
388
|
+
�ku 6
|
389
|
+
ug 6
|
390
|
+
�n 6
|
391
|
+
eir 6
|
392
|
+
eit 6
|
393
|
+
�l 6
|
394
|
+
v�kur 6
|
395
|
+
ja_ 6
|
396
|
+
at 6
|
397
|
+
au 6
|
398
|
+
k_ 6
|
399
|
+
li� 6
|
400
|
+
ann_ 6
|