scylla 0.1.0 → 0.2.0
Sign up to get free protection for your applications and to get access to all the features.
- data/Gemfile +0 -1
- data/Gemfile.lock +0 -10
- data/README.rdoc +22 -0
- data/VERSION +1 -1
- data/bin/scylla +13 -0
- data/lib/scylla/classifier.rb +2 -2
- data/lib/scylla/generator.rb +1 -1
- data/lib/scylla/lms/13375P33K.lm +400 -0
- data/lib/scylla/lms/afrikaans.lm +400 -0
- data/lib/scylla/lms/arabic.lm +400 -0
- data/lib/scylla/lms/bulgarian.lm +400 -0
- data/lib/scylla/lms/catalan.lm +400 -0
- data/lib/scylla/lms/chinese.lm +400 -0
- data/lib/scylla/lms/danish.lm +400 -0
- data/lib/scylla/lms/english.lm +400 -0
- data/lib/scylla/lms/esperanto.lm +400 -0
- data/lib/scylla/lms/finnish.lm +400 -0
- data/lib/scylla/lms/french.lm +400 -0
- data/lib/scylla/lms/german.lm +400 -0
- data/lib/scylla/lms/greek-iso8859-7.lm +400 -0
- data/lib/scylla/lms/hebrew.lm +400 -0
- data/lib/scylla/lms/hindi.lm +400 -0
- data/lib/scylla/lms/hungarian.lm +400 -0
- data/lib/scylla/lms/icelandic.lm +400 -0
- data/lib/scylla/lms/indonesian.lm +400 -0
- data/lib/scylla/lms/irish.lm +400 -0
- data/lib/scylla/lms/italian.lm +400 -0
- data/lib/scylla/lms/japanese.lm +400 -0
- data/lib/scylla/lms/kannada.lm +400 -0
- data/lib/scylla/lms/korean.lm +400 -0
- data/lib/scylla/lms/latin.lm +400 -0
- data/lib/scylla/lms/malay.lm +400 -0
- data/lib/scylla/lms/marathi.lm +400 -0
- data/lib/scylla/lms/mingo.lm +400 -0
- data/lib/scylla/lms/nepali.lm +400 -0
- data/lib/scylla/lms/norwegian.lm +400 -0
- data/lib/scylla/lms/polish.lm +400 -0
- data/lib/scylla/lms/portuguese.lm +400 -0
- data/lib/scylla/lms/quechua.lm +400 -0
- data/lib/scylla/lms/romanian.lm +400 -0
- data/lib/scylla/lms/rumantsch.lm +400 -0
- data/lib/scylla/lms/russian.lm +400 -0
- data/lib/scylla/lms/sanskrit.lm +400 -0
- data/lib/scylla/lms/scots_gaelic.lm +400 -0
- data/lib/scylla/lms/serbian-ascii.lm +400 -0
- data/lib/scylla/lms/slovak-ascii.lm +400 -0
- data/lib/scylla/lms/slovenian-ascii.lm +400 -0
- data/lib/scylla/lms/spanish.lm +400 -0
- data/lib/scylla/lms/swahili.lm +400 -0
- data/lib/scylla/lms/swedish.lm +400 -0
- data/lib/scylla/lms/tagalog.lm +400 -0
- data/lib/scylla/lms/tamil.lm +400 -0
- data/lib/scylla/lms/thai.lm +400 -0
- data/lib/scylla/lms/turkish.lm +400 -0
- data/lib/scylla/lms/ukrainian-koi8_u.lm +400 -0
- data/lib/scylla/lms/vietnamese.lm +400 -0
- data/lib/scylla/lms/welsh.lm +400 -0
- data/lib/scylla/lms/yiddish-utf.lm +400 -0
- data/lib/scylla/loader.rb +8 -1
- data/scylla-0.1.0.gem +0 -0
- data/scylla.gemspec +69 -3
- data/source_texts/kannada.txt +283 -0
- data/test/classifier_test.rb +7 -0
- data/test/fixtures/lms/13375p33k.lm +400 -0
- data/test/fixtures/lms/danish.lm +400 -0
- data/test/fixtures/lms/english.lm +400 -0
- data/test/fixtures/lms/french.lm +400 -0
- data/test/fixtures/lms/german.lm +400 -0
- data/test/fixtures/lms/japanese.lm +400 -0
- data/test/fixtures/lms/kannada.lm +400 -0
- data/test/fixtures/lms/spanish.lm +400 -0
- data/test/fixtures/source_texts/13375P33K.txt +199 -0
- data/test/fixtures/source_texts/japanese.txt +199 -0
- data/test/fixtures/source_texts/kannada.txt +283 -0
- data/test/generator_test.rb +10 -7
- data/test/helper.rb +5 -6
- data/test/loader_test.rb +1 -0
- data/test/scylla_test.rb +1 -0
- metadata +78 -14
- data/source_texts/armenian.txt +0 -86
@@ -0,0 +1,400 @@
|
|
1
|
+
_ 1074
|
2
|
+
e 312
|
3
|
+
n 307
|
4
|
+
a 273
|
5
|
+
t 252
|
6
|
+
r 250
|
7
|
+
i 234
|
8
|
+
s 228
|
9
|
+
l 158
|
10
|
+
d 145
|
11
|
+
m 117
|
12
|
+
o 112
|
13
|
+
g 102
|
14
|
+
k 102
|
15
|
+
en 87
|
16
|
+
n_ 87
|
17
|
+
v 81
|
18
|
+
� 76
|
19
|
+
f 62
|
20
|
+
de 57
|
21
|
+
_s 57
|
22
|
+
h 57
|
23
|
+
u 56
|
24
|
+
t_ 56
|
25
|
+
ar 54
|
26
|
+
en_ 54
|
27
|
+
an 53
|
28
|
+
r_ 53
|
29
|
+
er 50
|
30
|
+
� 49
|
31
|
+
a_ 44
|
32
|
+
p 43
|
33
|
+
et 42
|
34
|
+
_d 39
|
35
|
+
in 38
|
36
|
+
� 38
|
37
|
+
. 38
|
38
|
+
_e 37
|
39
|
+
st 36
|
40
|
+
re 36
|
41
|
+
c 35
|
42
|
+
e_ 35
|
43
|
+
b 33
|
44
|
+
ti 33
|
45
|
+
_a 31
|
46
|
+
ng 31
|
47
|
+
ll 31
|
48
|
+
te 31
|
49
|
+
_i 30
|
50
|
+
_f 29
|
51
|
+
ra 28
|
52
|
+
_m 28
|
53
|
+
_v 28
|
54
|
+
�r 28
|
55
|
+
sk 28
|
56
|
+
s_ 27
|
57
|
+
is 27
|
58
|
+
tt 26
|
59
|
+
m_ 26
|
60
|
+
ni 26
|
61
|
+
si 26
|
62
|
+
ta 25
|
63
|
+
y 25
|
64
|
+
on 25
|
65
|
+
ik 25
|
66
|
+
na 25
|
67
|
+
ig 24
|
68
|
+
j 24
|
69
|
+
__ 24
|
70
|
+
ns 24
|
71
|
+
at 23
|
72
|
+
ka 23
|
73
|
+
ge 23
|
74
|
+
._ 22
|
75
|
+
il 22
|
76
|
+
_o 22
|
77
|
+
kt 22
|
78
|
+
i_ 22
|
79
|
+
_en 22
|
80
|
+
�r 21
|
81
|
+
nd 21
|
82
|
+
om 21
|
83
|
+
_t 21
|
84
|
+
_de 20
|
85
|
+
, 19
|
86
|
+
f� 19
|
87
|
+
li 19
|
88
|
+
es 19
|
89
|
+
vi 19
|
90
|
+
ch 19
|
91
|
+
or 18
|
92
|
+
v_ 18
|
93
|
+
va 18
|
94
|
+
_h 18
|
95
|
+
ar_ 18
|
96
|
+
la 18
|
97
|
+
av 18
|
98
|
+
_i_ 17
|
99
|
+
d_ 17
|
100
|
+
nn 17
|
101
|
+
,_ 17
|
102
|
+
den 17
|
103
|
+
am 17
|
104
|
+
�_ 17
|
105
|
+
ga 17
|
106
|
+
sa 17
|
107
|
+
ri 17
|
108
|
+
av_ 16
|
109
|
+
so 16
|
110
|
+
f�r 16
|
111
|
+
di 16
|
112
|
+
_en_ 16
|
113
|
+
h_ 16
|
114
|
+
ha 16
|
115
|
+
ikt 16
|
116
|
+
et_ 16
|
117
|
+
�n 16
|
118
|
+
se 16
|
119
|
+
me 16
|
120
|
+
oc 16
|
121
|
+
id 15
|
122
|
+
ill 15
|
123
|
+
ne 15
|
124
|
+
_k 15
|
125
|
+
al 15
|
126
|
+
nt 15
|
127
|
+
_p 14
|
128
|
+
io 14
|
129
|
+
_b 14
|
130
|
+
de_ 14
|
131
|
+
ch_ 14
|
132
|
+
an_ 14
|
133
|
+
" 14
|
134
|
+
el 14
|
135
|
+
den_ 14
|
136
|
+
om_ 14
|
137
|
+
som 14
|
138
|
+
ke 14
|
139
|
+
le 14
|
140
|
+
tr 14
|
141
|
+
us 14
|
142
|
+
och 14
|
143
|
+
da 14
|
144
|
+
_vi 14
|
145
|
+
er_ 13
|
146
|
+
_f� 13
|
147
|
+
att 13
|
148
|
+
he 13
|
149
|
+
_ha 13
|
150
|
+
l_ 13
|
151
|
+
_ti 13
|
152
|
+
rn 13
|
153
|
+
_och 13
|
154
|
+
och_ 13
|
155
|
+
_av 13
|
156
|
+
_oc 13
|
157
|
+
til 12
|
158
|
+
ska 12
|
159
|
+
rd 12
|
160
|
+
_den 12
|
161
|
+
ing 12
|
162
|
+
ion 12
|
163
|
+
it 12
|
164
|
+
ls 12
|
165
|
+
_och_ 12
|
166
|
+
som_ 12
|
167
|
+
till 12
|
168
|
+
are 12
|
169
|
+
_av_ 12
|
170
|
+
oni 11
|
171
|
+
un 11
|
172
|
+
sin 11
|
173
|
+
ll_ 11
|
174
|
+
em 11
|
175
|
+
_till 11
|
176
|
+
gt 11
|
177
|
+
_u 11
|
178
|
+
and 11
|
179
|
+
_til 11
|
180
|
+
tt_ 11
|
181
|
+
as 11
|
182
|
+
isk 11
|
183
|
+
_den_ 11
|
184
|
+
_so 10
|
185
|
+
der 10
|
186
|
+
g_ 10
|
187
|
+
_si 10
|
188
|
+
lig 10
|
189
|
+
ck 10
|
190
|
+
mi 10
|
191
|
+
na_ 10
|
192
|
+
_l 10
|
193
|
+
_som 10
|
194
|
+
ds 10
|
195
|
+
ad 10
|
196
|
+
_g 10
|
197
|
+
p�_ 10
|
198
|
+
_f�r 10
|
199
|
+
p� 10
|
200
|
+
ans 10
|
201
|
+
nde 9
|
202
|
+
gen 9
|
203
|
+
S 9
|
204
|
+
ter 9
|
205
|
+
re_ 9
|
206
|
+
x 9
|
207
|
+
m� 9
|
208
|
+
v� 9
|
209
|
+
_r 9
|
210
|
+
ns_ 9
|
211
|
+
var 9
|
212
|
+
�r_ 9
|
213
|
+
D 9
|
214
|
+
_at 9
|
215
|
+
ed 9
|
216
|
+
to 9
|
217
|
+
k_ 9
|
218
|
+
_att 9
|
219
|
+
�n 9
|
220
|
+
rs 8
|
221
|
+
ste 8
|
222
|
+
_me 8
|
223
|
+
pr 8
|
224
|
+
_in 8
|
225
|
+
_D 8
|
226
|
+
ern 8
|
227
|
+
ss 8
|
228
|
+
_p�_ 8
|
229
|
+
gar 8
|
230
|
+
l� 8
|
231
|
+
_di 8
|
232
|
+
ut 8
|
233
|
+
_p� 8
|
234
|
+
ning 8
|
235
|
+
nin 8
|
236
|
+
_som_ 8
|
237
|
+
ag 8
|
238
|
+
ve 8
|
239
|
+
ill_ 8
|
240
|
+
ld 8
|
241
|
+
_va 8
|
242
|
+
ton 8
|
243
|
+
�g 7
|
244
|
+
�ng 7
|
245
|
+
ade 7
|
246
|
+
igt 7
|
247
|
+
rm 7
|
248
|
+
tar 7
|
249
|
+
t� 7
|
250
|
+
lan 7
|
251
|
+
ol 7
|
252
|
+
_� 7
|
253
|
+
pp 7
|
254
|
+
all 7
|
255
|
+
st_ 7
|
256
|
+
sm 7
|
257
|
+
ts 7
|
258
|
+
_har 7
|
259
|
+
inn 7
|
260
|
+
sam 7
|
261
|
+
E 7
|
262
|
+
har 7
|
263
|
+
r� 7
|
264
|
+
ro 7
|
265
|
+
�l 7
|
266
|
+
are_ 7
|
267
|
+
�r 7
|
268
|
+
till_ 7
|
269
|
+
els 7
|
270
|
+
n. 7
|
271
|
+
ma 7
|
272
|
+
bl 7
|
273
|
+
j� 7
|
274
|
+
kr 7
|
275
|
+
_st 7
|
276
|
+
iska 7
|
277
|
+
nis 7
|
278
|
+
rna 7
|
279
|
+
med 7
|
280
|
+
rk 7
|
281
|
+
nga 7
|
282
|
+
era 7
|
283
|
+
_sin 7
|
284
|
+
in_ 6
|
285
|
+
est 6
|
286
|
+
d� 6
|
287
|
+
ktoni 6
|
288
|
+
ja 6
|
289
|
+
toniu 6
|
290
|
+
iu 6
|
291
|
+
iv 6
|
292
|
+
niu 6
|
293
|
+
ren 6
|
294
|
+
att_ 6
|
295
|
+
sion 6
|
296
|
+
m� 6
|
297
|
+
no 6
|
298
|
+
Di 6
|
299
|
+
tion 6
|
300
|
+
ex 6
|
301
|
+
gr 6
|
302
|
+
_S 6
|
303
|
+
be 6
|
304
|
+
ligt 6
|
305
|
+
van 6
|
306
|
+
_n 6
|
307
|
+
mu 6
|
308
|
+
_dikt 6
|
309
|
+
_var 6
|
310
|
+
ess 6
|
311
|
+
ism 6
|
312
|
+
Dikto 6
|
313
|
+
fi 6
|
314
|
+
tio 6
|
315
|
+
ikton 6
|
316
|
+
ra_ 6
|
317
|
+
else 6
|
318
|
+
ius 6
|
319
|
+
f�r_ 6
|
320
|
+
Dik 6
|
321
|
+
dikt 6
|
322
|
+
ga_ 6
|
323
|
+
ande 6
|
324
|
+
_H 6
|
325
|
+
_sk 6
|
326
|
+
kton 6
|
327
|
+
dik 6
|
328
|
+
lse 6
|
329
|
+
ten 6
|
330
|
+
kto 6
|
331
|
+
r� 6
|
332
|
+
d�r 6
|
333
|
+
Dikt 6
|
334
|
+
gt_ 6
|
335
|
+
sio 6
|
336
|
+
_d� 6
|
337
|
+
toni 6
|
338
|
+
nius 6
|
339
|
+
han 6
|
340
|
+
oniu 6
|
341
|
+
_sa 6
|
342
|
+
mm 6
|
343
|
+
tid 6
|
344
|
+
rb 6
|
345
|
+
res 6
|
346
|
+
het 6
|
347
|
+
for 6
|
348
|
+
_dik 6
|
349
|
+
fo 6
|
350
|
+
ikto 6
|
351
|
+
fa 6
|
352
|
+
sl 6
|
353
|
+
_d�r 6
|
354
|
+
ord 6
|
355
|
+
rg 6
|
356
|
+
onius 6
|
357
|
+
H 6
|
358
|
+
�r_ 6
|
359
|
+
nni 5
|
360
|
+
up 5
|
361
|
+
ny 5
|
362
|
+
tra 5
|
363
|
+
lle 5
|
364
|
+
_�r_ 5
|
365
|
+
pre 5
|
366
|
+
ei 5
|
367
|
+
ens 5
|
368
|
+
nte 5
|
369
|
+
lj 5
|
370
|
+
_sin_ 5
|
371
|
+
kl 5
|
372
|
+
nne 5
|
373
|
+
_Dikt 5
|
374
|
+
_Dik 5
|
375
|
+
_vid 5
|
376
|
+
iska_ 5
|
377
|
+
ka_ 5
|
378
|
+
ko 5
|
379
|
+
ati 5
|
380
|
+
ver 5
|
381
|
+
_med 5
|
382
|
+
st� 5
|
383
|
+
det 5
|
384
|
+
nge 5
|
385
|
+
vid 5
|
386
|
+
sin_ 5
|
387
|
+
ade_ 5
|
388
|
+
gs 5
|
389
|
+
lt 5
|
390
|
+
ak 5
|
391
|
+
_att_ 5
|
392
|
+
ler 5
|
393
|
+
lv 5
|
394
|
+
�r_ 5
|
395
|
+
_ka 5
|
396
|
+
net 5
|
397
|
+
kan 5
|
398
|
+
ly 5
|
399
|
+
�d 5
|
400
|
+
gen_ 5
|