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
|
+
_ 1062
|
2
|
+
e 329
|
3
|
+
a 276
|
4
|
+
t 261
|
5
|
+
k 203
|
6
|
+
s 200
|
7
|
+
l 188
|
8
|
+
n 172
|
9
|
+
r 154
|
10
|
+
z 143
|
11
|
+
i 140
|
12
|
+
� 136
|
13
|
+
o 126
|
14
|
+
g 121
|
15
|
+
� 114
|
16
|
+
m 93
|
17
|
+
y 80
|
18
|
+
b 73
|
19
|
+
d 71
|
20
|
+
_a 70
|
21
|
+
v 68
|
22
|
+
t_ 63
|
23
|
+
a_ 62
|
24
|
+
, 54
|
25
|
+
sz 53
|
26
|
+
gy 52
|
27
|
+
k_ 49
|
28
|
+
,_ 49
|
29
|
+
� 48
|
30
|
+
et 46
|
31
|
+
h 44
|
32
|
+
p 43
|
33
|
+
_m 42
|
34
|
+
� 41
|
35
|
+
_a_ 40
|
36
|
+
en 39
|
37
|
+
u 38
|
38
|
+
eg 37
|
39
|
+
_k 37
|
40
|
+
le 34
|
41
|
+
el 33
|
42
|
+
_e 33
|
43
|
+
. 33
|
44
|
+
j 32
|
45
|
+
n_ 31
|
46
|
+
s_ 31
|
47
|
+
_s 31
|
48
|
+
te 30
|
49
|
+
i_ 30
|
50
|
+
ek 29
|
51
|
+
al 29
|
52
|
+
ak 29
|
53
|
+
_� 29
|
54
|
+
f 28
|
55
|
+
�s 27
|
56
|
+
�r 27
|
57
|
+
tt 26
|
58
|
+
� 26
|
59
|
+
er 26
|
60
|
+
ta 26
|
61
|
+
y_ 26
|
62
|
+
es 25
|
63
|
+
A 25
|
64
|
+
e_ 25
|
65
|
+
ke 25
|
66
|
+
_h 25
|
67
|
+
� 24
|
68
|
+
ze 24
|
69
|
+
re 24
|
70
|
+
t� 23
|
71
|
+
_i 23
|
72
|
+
_t 23
|
73
|
+
or 23
|
74
|
+
_sz 22
|
75
|
+
az 22
|
76
|
+
z_ 22
|
77
|
+
ag 21
|
78
|
+
ny 20
|
79
|
+
ki 20
|
80
|
+
ne 20
|
81
|
+
zt 20
|
82
|
+
_v 20
|
83
|
+
gy_ 20
|
84
|
+
ko 20
|
85
|
+
ll 19
|
86
|
+
_n 19
|
87
|
+
�r 19
|
88
|
+
me 18
|
89
|
+
�n 18
|
90
|
+
at 18
|
91
|
+
_az 18
|
92
|
+
t� 18
|
93
|
+
an 18
|
94
|
+
ve 18
|
95
|
+
is 17
|
96
|
+
�s 17
|
97
|
+
l_ 17
|
98
|
+
egy 17
|
99
|
+
ol 17
|
100
|
+
_f 17
|
101
|
+
va 16
|
102
|
+
� 16
|
103
|
+
os 16
|
104
|
+
_b 16
|
105
|
+
�t 16
|
106
|
+
�g 16
|
107
|
+
nk 16
|
108
|
+
ye 16
|
109
|
+
na 16
|
110
|
+
__ 16
|
111
|
+
be 15
|
112
|
+
ho 15
|
113
|
+
rt 15
|
114
|
+
agy 15
|
115
|
+
c 15
|
116
|
+
mi 15
|
117
|
+
A_ 14
|
118
|
+
ra 14
|
119
|
+
�p 14
|
120
|
+
on 14
|
121
|
+
tt_ 14
|
122
|
+
se 14
|
123
|
+
la 14
|
124
|
+
z� 14
|
125
|
+
ak_ 14
|
126
|
+
em 14
|
127
|
+
�l 13
|
128
|
+
_az_ 13
|
129
|
+
_ki 13
|
130
|
+
za 13
|
131
|
+
sze 13
|
132
|
+
_l 13
|
133
|
+
�s_ 13
|
134
|
+
� 13
|
135
|
+
ok 13
|
136
|
+
_eg 13
|
137
|
+
az_ 13
|
138
|
+
s� 13
|
139
|
+
to 12
|
140
|
+
_�s 12
|
141
|
+
k� 12
|
142
|
+
ik 12
|
143
|
+
ar 12
|
144
|
+
it 12
|
145
|
+
�n 12
|
146
|
+
ro 12
|
147
|
+
_�s_ 12
|
148
|
+
r_ 12
|
149
|
+
sa 12
|
150
|
+
_egy 12
|
151
|
+
ez 11
|
152
|
+
g_ 11
|
153
|
+
ma 11
|
154
|
+
ett 11
|
155
|
+
_ho 11
|
156
|
+
S 11
|
157
|
+
da 11
|
158
|
+
�t 11
|
159
|
+
_is 11
|
160
|
+
nd 11
|
161
|
+
ba 11
|
162
|
+
bb 11
|
163
|
+
kor 10
|
164
|
+
._ 10
|
165
|
+
et_ 10
|
166
|
+
ge 10
|
167
|
+
m� 10
|
168
|
+
� 10
|
169
|
+
oz 10
|
170
|
+
lt 10
|
171
|
+
rs 10
|
172
|
+
en_ 10
|
173
|
+
mo 10
|
174
|
+
og 10
|
175
|
+
ek_ 10
|
176
|
+
ap 10
|
177
|
+
an_ 10
|
178
|
+
E 10
|
179
|
+
iz 10
|
180
|
+
sz� 10
|
181
|
+
zer 10
|
182
|
+
�l 10
|
183
|
+
_me 10
|
184
|
+
cs 10
|
185
|
+
in 10
|
186
|
+
_va 10
|
187
|
+
_d 9
|
188
|
+
v� 9
|
189
|
+
egy_ 9
|
190
|
+
�g 9
|
191
|
+
_mi 9
|
192
|
+
z� 9
|
193
|
+
ha 9
|
194
|
+
ai 9
|
195
|
+
n� 9
|
196
|
+
l� 9
|
197
|
+
pe 9
|
198
|
+
so 9
|
199
|
+
li 9
|
200
|
+
m� 9
|
201
|
+
nt 9
|
202
|
+
_j 9
|
203
|
+
ka 9
|
204
|
+
t. 9
|
205
|
+
as 9
|
206
|
+
�_ 9
|
207
|
+
M 9
|
208
|
+
de 9
|
209
|
+
st 9
|
210
|
+
ban 8
|
211
|
+
�v 8
|
212
|
+
s� 8
|
213
|
+
�ll 8
|
214
|
+
ban_ 8
|
215
|
+
do 8
|
216
|
+
�ny 8
|
217
|
+
a, 8
|
218
|
+
meg 8
|
219
|
+
�k 8
|
220
|
+
szer 8
|
221
|
+
lle 8
|
222
|
+
k, 8
|
223
|
+
bi 8
|
224
|
+
nn 8
|
225
|
+
ele 8
|
226
|
+
ut 8
|
227
|
+
: 8
|
228
|
+
_le 8
|
229
|
+
_el 8
|
230
|
+
ss 8
|
231
|
+
s�t 8
|
232
|
+
ad 8
|
233
|
+
s�g 8
|
234
|
+
ul 8
|
235
|
+
k� 8
|
236
|
+
let 8
|
237
|
+
l� 8
|
238
|
+
zi 8
|
239
|
+
t� 8
|
240
|
+
_egy_ 8
|
241
|
+
v� 7
|
242
|
+
k�r 7
|
243
|
+
m_ 7
|
244
|
+
�l 7
|
245
|
+
hog 7
|
246
|
+
�k 7
|
247
|
+
sza 7
|
248
|
+
� 7
|
249
|
+
ya 7
|
250
|
+
_ke 7
|
251
|
+
gye 7
|
252
|
+
b_ 7
|
253
|
+
ket 7
|
254
|
+
re_ 7
|
255
|
+
ud 7
|
256
|
+
_ha 7
|
257
|
+
_A 7
|
258
|
+
tet 7
|
259
|
+
e, 7
|
260
|
+
v�n 7
|
261
|
+
�r 7
|
262
|
+
N 7
|
263
|
+
t�s 7
|
264
|
+
_hog 7
|
265
|
+
�t 7
|
266
|
+
min 7
|
267
|
+
ga 7
|
268
|
+
_n� 7
|
269
|
+
�b 7
|
270
|
+
�t 7
|
271
|
+
kr 7
|
272
|
+
nak 7
|
273
|
+
_r 7
|
274
|
+
k,_ 7
|
275
|
+
�_ 7
|
276
|
+
r� 7
|
277
|
+
_�r 7
|
278
|
+
ri 7
|
279
|
+
_meg 7
|
280
|
+
�v 7
|
281
|
+
ot 7
|
282
|
+
ik_ 7
|
283
|
+
_� 7
|
284
|
+
ett_ 7
|
285
|
+
�k 7
|
286
|
+
am 6
|
287
|
+
izto 6
|
288
|
+
j� 6
|
289
|
+
ai_ 6
|
290
|
+
_te 6
|
291
|
+
id 6
|
292
|
+
hogy 6
|
293
|
+
_k� 6
|
294
|
+
yi 6
|
295
|
+
_hogy 6
|
296
|
+
esz 6
|
297
|
+
eh 6
|
298
|
+
sk 6
|
299
|
+
ben 6
|
300
|
+
_mo 6
|
301
|
+
k. 6
|
302
|
+
rz 6
|
303
|
+
izt 6
|
304
|
+
yek 6
|
305
|
+
nt_ 6
|
306
|
+
�n 6
|
307
|
+
_�v 6
|
308
|
+
_es 6
|
309
|
+
e,_ 6
|
310
|
+
ell 6
|
311
|
+
rv 6
|
312
|
+
zs 6
|
313
|
+
os� 6
|
314
|
+
tos�t 6
|
315
|
+
pa 6
|
316
|
+
il 6
|
317
|
+
t� 6
|
318
|
+
ogy 6
|
319
|
+
rd 6
|
320
|
+
t, 6
|
321
|
+
_min 6
|
322
|
+
z� 6
|
323
|
+
t,_ 6
|
324
|
+
zto 6
|
325
|
+
_be 6
|
326
|
+
biz 6
|
327
|
+
kb 6
|
328
|
+
Sz 6
|
329
|
+
H 6
|
330
|
+
ps 6
|
331
|
+
bizt 6
|
332
|
+
ly 6
|
333
|
+
ztos 6
|
334
|
+
zet 6
|
335
|
+
ere 6
|
336
|
+
os�t 6
|
337
|
+
k� 6
|
338
|
+
bizto 6
|
339
|
+
di 6
|
340
|
+
om 6
|
341
|
+
tos� 6
|
342
|
+
tos 6
|
343
|
+
nye 6
|
344
|
+
iztos 6
|
345
|
+
fe 6
|
346
|
+
a,_ 6
|
347
|
+
K 6
|
348
|
+
sok 6
|
349
|
+
uda 6
|
350
|
+
- 6
|
351
|
+
agy_ 6
|
352
|
+
_p 6
|
353
|
+
ztos� 6
|
354
|
+
�t�s 5
|
355
|
+
em_ 5
|
356
|
+
ln 5
|
357
|
+
d� 5
|
358
|
+
�v� 5
|
359
|
+
ev 5
|
360
|
+
isk 5
|
361
|
+
ny_ 5
|
362
|
+
elle 5
|
363
|
+
lm 5
|
364
|
+
vagy 5
|
365
|
+
fa 5
|
366
|
+
ren 5
|
367
|
+
ors 5
|
368
|
+
�g_ 5
|
369
|
+
bb_ 5
|
370
|
+
_A_ 5
|
371
|
+
�ps 5
|
372
|
+
zak 5
|
373
|
+
_ma 5
|
374
|
+
ben_ 5
|
375
|
+
vagy_ 5
|
376
|
+
vag 5
|
377
|
+
po 5
|
378
|
+
kel 5
|
379
|
+
h� 5
|
380
|
+
yo 5
|
381
|
+
I 5
|
382
|
+
�l 5
|
383
|
+
_t� 5
|
384
|
+
t._ 5
|
385
|
+
�v�n 5
|
386
|
+
nyek 5
|
387
|
+
tal 5
|
388
|
+
lj 5
|
389
|
+
�t�s 5
|
390
|
+
�nye 5
|
391
|
+
�sz 5
|
392
|
+
_vagy 5
|
393
|
+
gya 5
|
394
|
+
_vag 5
|
395
|
+
v�ny 5
|
396
|
+
ete 5
|
397
|
+
s�t� 5
|
398
|
+
G 5
|
399
|
+
est 5
|
400
|
+
�t� 5
|