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
|
+
_ 1512
|
2
|
+
a 539
|
3
|
+
i 460
|
4
|
+
e 442
|
5
|
+
t 272
|
6
|
+
r 265
|
7
|
+
n 234
|
8
|
+
u 220
|
9
|
+
c 200
|
10
|
+
s 194
|
11
|
+
o 188
|
12
|
+
l 174
|
13
|
+
e_ 170
|
14
|
+
a_ 155
|
15
|
+
d 115
|
16
|
+
m 114
|
17
|
+
p 113
|
18
|
+
i_ 108
|
19
|
+
in 101
|
20
|
+
_c 92
|
21
|
+
ar 87
|
22
|
+
_s 75
|
23
|
+
re 71
|
24
|
+
_d 69
|
25
|
+
, 66
|
26
|
+
de 64
|
27
|
+
_a 64
|
28
|
+
ra 63
|
29
|
+
at 62
|
30
|
+
f 57
|
31
|
+
_p 55
|
32
|
+
,_ 54
|
33
|
+
st 53
|
34
|
+
ta 53
|
35
|
+
ti 51
|
36
|
+
ca 50
|
37
|
+
te 50
|
38
|
+
n_ 50
|
39
|
+
si 47
|
40
|
+
u_ 46
|
41
|
+
_i 45
|
42
|
+
un 45
|
43
|
+
_de 43
|
44
|
+
g 42
|
45
|
+
ri 41
|
46
|
+
ce 41
|
47
|
+
nt 41
|
48
|
+
ul 40
|
49
|
+
_m 39
|
50
|
+
or 39
|
51
|
+
b 39
|
52
|
+
_o 38
|
53
|
+
de_ 38
|
54
|
+
es 38
|
55
|
+
_in 38
|
56
|
+
la 37
|
57
|
+
are 37
|
58
|
+
_ca 36
|
59
|
+
ma 35
|
60
|
+
tr 34
|
61
|
+
. 34
|
62
|
+
t_ 33
|
63
|
+
ea 33
|
64
|
+
ci 33
|
65
|
+
_f 33
|
66
|
+
_de_ 32
|
67
|
+
el 32
|
68
|
+
ia 30
|
69
|
+
oa 30
|
70
|
+
ni 30
|
71
|
+
ta_ 29
|
72
|
+
in_ 29
|
73
|
+
se 29
|
74
|
+
te_ 29
|
75
|
+
v 29
|
76
|
+
cu 29
|
77
|
+
_si 28
|
78
|
+
as 27
|
79
|
+
z 27
|
80
|
+
re_ 27
|
81
|
+
_u 27
|
82
|
+
si_ 26
|
83
|
+
l_ 26
|
84
|
+
le 26
|
85
|
+
ic 26
|
86
|
+
an 26
|
87
|
+
ac 26
|
88
|
+
ne 26
|
89
|
+
_l 26
|
90
|
+
_t 25
|
91
|
+
pe 25
|
92
|
+
li 25
|
93
|
+
ei 24
|
94
|
+
int 24
|
95
|
+
er 24
|
96
|
+
are_ 23
|
97
|
+
_un 23
|
98
|
+
lu 23
|
99
|
+
est 23
|
100
|
+
ie 22
|
101
|
+
la_ 22
|
102
|
+
ste 22
|
103
|
+
pa 22
|
104
|
+
sa 21
|
105
|
+
_ma 21
|
106
|
+
car 21
|
107
|
+
e, 20
|
108
|
+
il 20
|
109
|
+
na 20
|
110
|
+
_e 20
|
111
|
+
al 20
|
112
|
+
it 20
|
113
|
+
_pe 19
|
114
|
+
da 19
|
115
|
+
en 19
|
116
|
+
ai 19
|
117
|
+
_n 19
|
118
|
+
to 19
|
119
|
+
ii 19
|
120
|
+
_si_ 19
|
121
|
+
care 19
|
122
|
+
_cu 18
|
123
|
+
ap 18
|
124
|
+
ara 18
|
125
|
+
o_ 18
|
126
|
+
cu_ 18
|
127
|
+
ata 18
|
128
|
+
ui 18
|
129
|
+
au 18
|
130
|
+
este 18
|
131
|
+
lo 17
|
132
|
+
am 17
|
133
|
+
_in_ 17
|
134
|
+
me 17
|
135
|
+
D 17
|
136
|
+
co 16
|
137
|
+
care_ 16
|
138
|
+
_care 16
|
139
|
+
fa 16
|
140
|
+
ra_ 16
|
141
|
+
om 16
|
142
|
+
r_ 16
|
143
|
+
un_ 16
|
144
|
+
_car 16
|
145
|
+
._ 16
|
146
|
+
pr 16
|
147
|
+
este_ 15
|
148
|
+
pe_ 15
|
149
|
+
h 15
|
150
|
+
ste_ 15
|
151
|
+
ru 15
|
152
|
+
_cu_ 15
|
153
|
+
_o_ 15
|
154
|
+
e,_ 15
|
155
|
+
ul_ 15
|
156
|
+
_sa 15
|
157
|
+
se_ 15
|
158
|
+
rt 15
|
159
|
+
sa_ 14
|
160
|
+
nu 14
|
161
|
+
ca_ 14
|
162
|
+
le_ 14
|
163
|
+
a, 14
|
164
|
+
tra 14
|
165
|
+
is 14
|
166
|
+
_b 14
|
167
|
+
_v 14
|
168
|
+
ata_ 14
|
169
|
+
ace 14
|
170
|
+
_ce 14
|
171
|
+
ur 14
|
172
|
+
tu 14
|
173
|
+
_se 14
|
174
|
+
zi 13
|
175
|
+
au_ 13
|
176
|
+
sc 13
|
177
|
+
mi 13
|
178
|
+
lui 13
|
179
|
+
mu 13
|
180
|
+
ot 13
|
181
|
+
io 13
|
182
|
+
a,_ 13
|
183
|
+
nd 12
|
184
|
+
bi 12
|
185
|
+
po 12
|
186
|
+
ei_ 12
|
187
|
+
ve 12
|
188
|
+
na_ 12
|
189
|
+
ut 12
|
190
|
+
ii_ 12
|
191
|
+
ec 12
|
192
|
+
_ac 12
|
193
|
+
ele 12
|
194
|
+
oar 12
|
195
|
+
os 12
|
196
|
+
pi 12
|
197
|
+
fe 12
|
198
|
+
_fa 12
|
199
|
+
__ 12
|
200
|
+
ui_ 12
|
201
|
+
ir 11
|
202
|
+
_pe_ 11
|
203
|
+
um 11
|
204
|
+
tat 11
|
205
|
+
_un_ 11
|
206
|
+
di 11
|
207
|
+
E 11
|
208
|
+
_se_ 11
|
209
|
+
_r 11
|
210
|
+
ent 11
|
211
|
+
fo 11
|
212
|
+
et 11
|
213
|
+
ea_ 11
|
214
|
+
at_ 10
|
215
|
+
_es 10
|
216
|
+
op 10
|
217
|
+
ci_ 10
|
218
|
+
ici 10
|
219
|
+
_sa_ 10
|
220
|
+
ai_ 10
|
221
|
+
" 10
|
222
|
+
I 10
|
223
|
+
pu 10
|
224
|
+
i, 10
|
225
|
+
ulu 10
|
226
|
+
cel 10
|
227
|
+
_pa 10
|
228
|
+
_est 10
|
229
|
+
_la 10
|
230
|
+
ol 10
|
231
|
+
im 10
|
232
|
+
ntr 10
|
233
|
+
_este 10
|
234
|
+
_co 10
|
235
|
+
ga 10
|
236
|
+
ne_ 10
|
237
|
+
mo 9
|
238
|
+
_nu 9
|
239
|
+
or_ 9
|
240
|
+
_la_ 9
|
241
|
+
ului 9
|
242
|
+
ori 9
|
243
|
+
ati 9
|
244
|
+
ns 9
|
245
|
+
on 9
|
246
|
+
su 9
|
247
|
+
_ca_ 9
|
248
|
+
A 9
|
249
|
+
ele_ 9
|
250
|
+
iu 9
|
251
|
+
_ar 9
|
252
|
+
hi 9
|
253
|
+
_di 9
|
254
|
+
sta 9
|
255
|
+
lui_ 9
|
256
|
+
id 9
|
257
|
+
i,_ 8
|
258
|
+
_int 8
|
259
|
+
ad 8
|
260
|
+
une 8
|
261
|
+
_D 8
|
262
|
+
_lu 8
|
263
|
+
i. 8
|
264
|
+
_ace 8
|
265
|
+
_g 8
|
266
|
+
tru 8
|
267
|
+
ine 8
|
268
|
+
oc 8
|
269
|
+
ost 8
|
270
|
+
dat 8
|
271
|
+
mar 8
|
272
|
+
ate 8
|
273
|
+
em 8
|
274
|
+
ini 8
|
275
|
+
ng 8
|
276
|
+
gi 8
|
277
|
+
nc 8
|
278
|
+
mai 8
|
279
|
+
_a_ 8
|
280
|
+
_fo 8
|
281
|
+
mul 8
|
282
|
+
par 8
|
283
|
+
ti_ 8
|
284
|
+
lor 8
|
285
|
+
mai_ 8
|
286
|
+
ce_ 8
|
287
|
+
ara_ 8
|
288
|
+
nic 8
|
289
|
+
str 8
|
290
|
+
lt 8
|
291
|
+
tie 8
|
292
|
+
ani 7
|
293
|
+
ato 7
|
294
|
+
pri 7
|
295
|
+
_ci 7
|
296
|
+
tin 7
|
297
|
+
art 7
|
298
|
+
_din 7
|
299
|
+
ran 7
|
300
|
+
pl 7
|
301
|
+
m_ 7
|
302
|
+
din 7
|
303
|
+
ator 7
|
304
|
+
res 7
|
305
|
+
_da 7
|
306
|
+
mp 7
|
307
|
+
sin 7
|
308
|
+
ilo 7
|
309
|
+
j 7
|
310
|
+
cr 7
|
311
|
+
min 7
|
312
|
+
tul 7
|
313
|
+
fi 7
|
314
|
+
az 7
|
315
|
+
- 7
|
316
|
+
ind 7
|
317
|
+
ina 7
|
318
|
+
' 7
|
319
|
+
_E 7
|
320
|
+
rea 7
|
321
|
+
_pr 7
|
322
|
+
una 7
|
323
|
+
_or 7
|
324
|
+
do 7
|
325
|
+
esc 7
|
326
|
+
far 7
|
327
|
+
lin 7
|
328
|
+
ia_ 7
|
329
|
+
nta 7
|
330
|
+
tor 7
|
331
|
+
oare 6
|
332
|
+
oas 6
|
333
|
+
rti 6
|
334
|
+
_ti 6
|
335
|
+
_z 6
|
336
|
+
_to 6
|
337
|
+
iv 6
|
338
|
+
_st 6
|
339
|
+
ez 6
|
340
|
+
eri 6
|
341
|
+
ast 6
|
342
|
+
rul 6
|
343
|
+
_tr 6
|
344
|
+
it_ 6
|
345
|
+
pin 6
|
346
|
+
nde 6
|
347
|
+
_do 6
|
348
|
+
s_ 6
|
349
|
+
no 6
|
350
|
+
nti 6
|
351
|
+
iat 6
|
352
|
+
_op 6
|
353
|
+
tre 6
|
354
|
+
? 6
|
355
|
+
ge 6
|
356
|
+
ag 6
|
357
|
+
vi 6
|
358
|
+
ica 6
|
359
|
+
ric 6
|
360
|
+
e. 6
|
361
|
+
so 6
|
362
|
+
C 6
|
363
|
+
_mar 6
|
364
|
+
man 6
|
365
|
+
ch 6
|
366
|
+
tot 6
|
367
|
+
nu_ 6
|
368
|
+
lor_ 6
|
369
|
+
og 6
|
370
|
+
c_ 6
|
371
|
+
_po 6
|
372
|
+
omu 6
|
373
|
+
up 6
|
374
|
+
ari 6
|
375
|
+
pt 6
|
376
|
+
ate_ 6
|
377
|
+
_mo 6
|
378
|
+
_pu 6
|
379
|
+
nei 6
|
380
|
+
S 6
|
381
|
+
ra,_ 6
|
382
|
+
ba 6
|
383
|
+
ro 6
|
384
|
+
gr 6
|
385
|
+
ilor 6
|
386
|
+
ie_ 6
|
387
|
+
intr 6
|
388
|
+
imp 6
|
389
|
+
_cel 6
|
390
|
+
bo 6
|
391
|
+
rm 6
|
392
|
+
ra, 6
|
393
|
+
_au_ 5
|
394
|
+
P 5
|
395
|
+
uti 5
|
396
|
+
rin 5
|
397
|
+
ora 5
|
398
|
+
ada 5
|
399
|
+
?_ 5
|
400
|
+
ab 5
|