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
|
+
_ 1540
|
2
|
+
a 492
|
3
|
+
e 342
|
4
|
+
i 317
|
5
|
+
s 308
|
6
|
+
n 295
|
7
|
+
r 240
|
8
|
+
t 188
|
9
|
+
l 181
|
10
|
+
u 172
|
11
|
+
a_ 168
|
12
|
+
c 157
|
13
|
+
d 147
|
14
|
+
o 132
|
15
|
+
g 107
|
16
|
+
m 104
|
17
|
+
h 100
|
18
|
+
s_ 92
|
19
|
+
er 81
|
20
|
+
p 78
|
21
|
+
n_ 74
|
22
|
+
v 72
|
23
|
+
ch 72
|
24
|
+
_s 69
|
25
|
+
_d 64
|
26
|
+
in 63
|
27
|
+
_e 62
|
28
|
+
en 60
|
29
|
+
sc 57
|
30
|
+
, 57
|
31
|
+
da 56
|
32
|
+
f 54
|
33
|
+
. 53
|
34
|
+
r_ 53
|
35
|
+
_c 50
|
36
|
+
ra 48
|
37
|
+
__ 48
|
38
|
+
,_ 47
|
39
|
+
l_ 46
|
40
|
+
an 45
|
41
|
+
sch 43
|
42
|
+
ar 43
|
43
|
+
_da 42
|
44
|
+
z 41
|
45
|
+
_p 40
|
46
|
+
na 40
|
47
|
+
ta 40
|
48
|
+
ai 39
|
49
|
+
un 38
|
50
|
+
nt 37
|
51
|
+
ma 37
|
52
|
+
_f 37
|
53
|
+
_m 36
|
54
|
+
la 35
|
55
|
+
._ 34
|
56
|
+
_i 34
|
57
|
+
da_ 33
|
58
|
+
' 32
|
59
|
+
as 32
|
60
|
+
b 29
|
61
|
+
_a 29
|
62
|
+
i_ 29
|
63
|
+
es 29
|
64
|
+
ia 28
|
65
|
+
_da_ 28
|
66
|
+
er_ 28
|
67
|
+
t_ 28
|
68
|
+
al 27
|
69
|
+
re 27
|
70
|
+
is 27
|
71
|
+
va 27
|
72
|
+
_t 26
|
73
|
+
st 26
|
74
|
+
gl 25
|
75
|
+
ei 25
|
76
|
+
de 25
|
77
|
+
e_ 25
|
78
|
+
cu 25
|
79
|
+
or 24
|
80
|
+
di 24
|
81
|
+
el 24
|
82
|
+
_v 24
|
83
|
+
he 24
|
84
|
+
ha 24
|
85
|
+
ve 23
|
86
|
+
_l 23
|
87
|
+
sa 23
|
88
|
+
ad 23
|
89
|
+
ts 22
|
90
|
+
il 22
|
91
|
+
te 22
|
92
|
+
� 22
|
93
|
+
ss 22
|
94
|
+
pe 21
|
95
|
+
on 21
|
96
|
+
d_ 20
|
97
|
+
ns 20
|
98
|
+
ain 20
|
99
|
+
ur 20
|
100
|
+
as_ 20
|
101
|
+
rt 20
|
102
|
+
_n 20
|
103
|
+
u_ 20
|
104
|
+
tg 19
|
105
|
+
ig 19
|
106
|
+
ng 19
|
107
|
+
_sc 18
|
108
|
+
rs 18
|
109
|
+
per 18
|
110
|
+
ir 18
|
111
|
+
li 18
|
112
|
+
_g 17
|
113
|
+
se 17
|
114
|
+
ti 17
|
115
|
+
q 17
|
116
|
+
to 17
|
117
|
+
eg 17
|
118
|
+
_in 17
|
119
|
+
qu 17
|
120
|
+
che 17
|
121
|
+
_o 17
|
122
|
+
ie 17
|
123
|
+
na_ 16
|
124
|
+
ha_ 16
|
125
|
+
_ch 16
|
126
|
+
et 16
|
127
|
+
iv 16
|
128
|
+
in_ 16
|
129
|
+
en_ 16
|
130
|
+
un_ 16
|
131
|
+
iu 16
|
132
|
+
ll 16
|
133
|
+
ls 16
|
134
|
+
g_ 16
|
135
|
+
nd 15
|
136
|
+
za 15
|
137
|
+
ent 15
|
138
|
+
mi 15
|
139
|
+
ns_ 15
|
140
|
+
fi 15
|
141
|
+
cha 15
|
142
|
+
at 15
|
143
|
+
I 15
|
144
|
+
_en 15
|
145
|
+
ic 14
|
146
|
+
_qu 14
|
147
|
+
sta 14
|
148
|
+
ra_ 14
|
149
|
+
gn 14
|
150
|
+
co 14
|
151
|
+
vi 14
|
152
|
+
ri 14
|
153
|
+
_b 14
|
154
|
+
_cu 14
|
155
|
+
_q 14
|
156
|
+
igl 14
|
157
|
+
gi 13
|
158
|
+
it 13
|
159
|
+
" 13
|
160
|
+
pr 13
|
161
|
+
_ma 13
|
162
|
+
_h 13
|
163
|
+
_e_ 13
|
164
|
+
ta_ 13
|
165
|
+
me 13
|
166
|
+
pa 13
|
167
|
+
int 13
|
168
|
+
ni 13
|
169
|
+
us 13
|
170
|
+
el_ 13
|
171
|
+
ed 12
|
172
|
+
nz 12
|
173
|
+
nu 12
|
174
|
+
uo 12
|
175
|
+
ca 12
|
176
|
+
sa_ 12
|
177
|
+
_fi 12
|
178
|
+
s, 12
|
179
|
+
ue 12
|
180
|
+
av 12
|
181
|
+
su 12
|
182
|
+
ga 12
|
183
|
+
ot 12
|
184
|
+
hi 12
|
185
|
+
_per 12
|
186
|
+
_pe 12
|
187
|
+
A 12
|
188
|
+
le 11
|
189
|
+
era 11
|
190
|
+
lla 11
|
191
|
+
au 11
|
192
|
+
um 11
|
193
|
+
ls_ 11
|
194
|
+
mai 11
|
195
|
+
ei_ 11
|
196
|
+
chi 11
|
197
|
+
per_ 11
|
198
|
+
gl_ 11
|
199
|
+
_di 11
|
200
|
+
ia_ 11
|
201
|
+
a. 11
|
202
|
+
lu 11
|
203
|
+
_in_ 11
|
204
|
+
que 11
|
205
|
+
scha 11
|
206
|
+
iss 11
|
207
|
+
- 11
|
208
|
+
si 11
|
209
|
+
M 11
|
210
|
+
am 11
|
211
|
+
rt_ 10
|
212
|
+
_r 10
|
213
|
+
_mi 10
|
214
|
+
ge 10
|
215
|
+
a._ 10
|
216
|
+
mp 10
|
217
|
+
o_ 10
|
218
|
+
main 10
|
219
|
+
os 10
|
220
|
+
s. 10
|
221
|
+
esc 10
|
222
|
+
L 10
|
223
|
+
fe 10
|
224
|
+
mo 10
|
225
|
+
S 10
|
226
|
+
nza 10
|
227
|
+
ar_ 10
|
228
|
+
ut 10
|
229
|
+
zi 10
|
230
|
+
_ve 10
|
231
|
+
man 10
|
232
|
+
pi 10
|
233
|
+
_per_ 10
|
234
|
+
ter 10
|
235
|
+
iun 10
|
236
|
+
_que 9
|
237
|
+
_nu 9
|
238
|
+
nta 9
|
239
|
+
cun 9
|
240
|
+
P 9
|
241
|
+
�n 9
|
242
|
+
ing 9
|
243
|
+
a, 9
|
244
|
+
ama 9
|
245
|
+
des 9
|
246
|
+
esch 9
|
247
|
+
tsc 9
|
248
|
+
em 9
|
249
|
+
_ha 9
|
250
|
+
igl_ 9
|
251
|
+
_ha_ 9
|
252
|
+
fa 9
|
253
|
+
ac 9
|
254
|
+
tsch 9
|
255
|
+
la_ 9
|
256
|
+
s,_ 9
|
257
|
+
ts_ 9
|
258
|
+
gli 9
|
259
|
+
las 9
|
260
|
+
'e 9
|
261
|
+
_st 9
|
262
|
+
be 9
|
263
|
+
om 9
|
264
|
+
rm 9
|
265
|
+
_se 8
|
266
|
+
ch' 8
|
267
|
+
no 8
|
268
|
+
ro 8
|
269
|
+
ver 8
|
270
|
+
_A 8
|
271
|
+
ng_ 8
|
272
|
+
_la 8
|
273
|
+
a,_ 8
|
274
|
+
an_ 8
|
275
|
+
va_ 8
|
276
|
+
ev 8
|
277
|
+
h' 8
|
278
|
+
_u 8
|
279
|
+
_pa 8
|
280
|
+
ne 8
|
281
|
+
x 8
|
282
|
+
ssa 8
|
283
|
+
nc 8
|
284
|
+
cl 8
|
285
|
+
desc 8
|
286
|
+
_M 8
|
287
|
+
_il 8
|
288
|
+
ier 8
|
289
|
+
E 8
|
290
|
+
ins 7
|
291
|
+
h_ 7
|
292
|
+
_me 7
|
293
|
+
za_ 7
|
294
|
+
R 7
|
295
|
+
im 7
|
296
|
+
vai 7
|
297
|
+
us_ 7
|
298
|
+
ura 7
|
299
|
+
schi 7
|
300
|
+
al_ 7
|
301
|
+
cha_ 7
|
302
|
+
nte 7
|
303
|
+
ed_ 7
|
304
|
+
sche 7
|
305
|
+
C 7
|
306
|
+
pl 7
|
307
|
+
ag 7
|
308
|
+
_er 7
|
309
|
+
eu 7
|
310
|
+
nas 7
|
311
|
+
od 7
|
312
|
+
aint 7
|
313
|
+
_fa 7
|
314
|
+
ran 7
|
315
|
+
_na 7
|
316
|
+
las_ 7
|
317
|
+
s._ 7
|
318
|
+
_ch' 7
|
319
|
+
n. 7
|
320
|
+
c_ 7
|
321
|
+
_sa 7
|
322
|
+
nts 7
|
323
|
+
end 7
|
324
|
+
ava 7
|
325
|
+
_or 7
|
326
|
+
sen 7
|
327
|
+
ch_ 7
|
328
|
+
il_ 7
|
329
|
+
sp 7
|
330
|
+
az 7
|
331
|
+
_sch 7
|
332
|
+
_cun 7
|
333
|
+
ert 7
|
334
|
+
lla_ 7
|
335
|
+
_I 7
|
336
|
+
ors 7
|
337
|
+
_su 7
|
338
|
+
_vi 7
|
339
|
+
gia 7
|
340
|
+
all 7
|
341
|
+
uel 7
|
342
|
+
desch 7
|
343
|
+
l' 7
|
344
|
+
_co 7
|
345
|
+
ir_ 7
|
346
|
+
sta_ 6
|
347
|
+
cun_ 6
|
348
|
+
_fe 6
|
349
|
+
_pr 6
|
350
|
+
lar 6
|
351
|
+
_E 6
|
352
|
+
_bu 6
|
353
|
+
_C 6
|
354
|
+
una 6
|
355
|
+
vair 6
|
356
|
+
ziun 6
|
357
|
+
_las 6
|
358
|
+
ad_ 6
|
359
|
+
Il 6
|
360
|
+
oz 6
|
361
|
+
_re 6
|
362
|
+
egn 6
|
363
|
+
art 6
|
364
|
+
tg_ 6
|
365
|
+
air 6
|
366
|
+
_las_ 6
|
367
|
+
_en_ 6
|
368
|
+
_ed 6
|
369
|
+
_�n 6
|
370
|
+
_. 6
|
371
|
+
quel 6
|
372
|
+
! 6
|
373
|
+
_es 6
|
374
|
+
maing 6
|
375
|
+
_l' 6
|
376
|
+
amain 6
|
377
|
+
res 6
|
378
|
+
_te 6
|
379
|
+
rd 6
|
380
|
+
fiss 6
|
381
|
+
ert_ 6
|
382
|
+
_ed_ 6
|
383
|
+
ats 6
|
384
|
+
ina 6
|
385
|
+
fis 6
|
386
|
+
�s 6
|
387
|
+
ziu 6
|
388
|
+
hen 6
|
389
|
+
ist 6
|
390
|
+
_R 6
|
391
|
+
aing 6
|
392
|
+
_fiss 6
|
393
|
+
_� 6
|
394
|
+
nt_ 6
|
395
|
+
ari 6
|
396
|
+
chen 6
|
397
|
+
_de 6
|
398
|
+
_fis 6
|
399
|
+
tad 6
|
400
|
+
G 6
|