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
|
+
_ 1566
|
2
|
+
f 617
|
3
|
+
] 256
|
4
|
+
g 203
|
5
|
+
s 192
|
6
|
+
l 175
|
7
|
+
/ 165
|
8
|
+
; 150
|
9
|
+
k 148
|
10
|
+
d 142
|
11
|
+
sf 127
|
12
|
+
f_ 126
|
13
|
+
]_ 123
|
14
|
+
n 123
|
15
|
+
f] 116
|
16
|
+
t 107
|
17
|
+
j 96
|
18
|
+
L 86
|
19
|
+
u 83
|
20
|
+
x 81
|
21
|
+
b 79
|
22
|
+
_; 77
|
23
|
+
' 77
|
24
|
+
f]_ 71
|
25
|
+
{ 70
|
26
|
+
_l 69
|
27
|
+
df 66
|
28
|
+
a 64
|
29
|
+
sf] 63
|
30
|
+
o 62
|
31
|
+
__ 60
|
32
|
+
_k 59
|
33
|
+
e 57
|
34
|
+
/_ 56
|
35
|
+
| 53
|
36
|
+
f/ 53
|
37
|
+
g] 51
|
38
|
+
G 50
|
39
|
+
c 50
|
40
|
+
sf]_ 49
|
41
|
+
{_ 46
|
42
|
+
_c 44
|
43
|
+
L_ 43
|
44
|
+
df_ 41
|
45
|
+
h 40
|
46
|
+
tf 40
|
47
|
+
} 40
|
48
|
+
+ 40
|
49
|
+
g_ 39
|
50
|
+
k| 36
|
51
|
+
_s 36
|
52
|
+
r 36
|
53
|
+
_u 35
|
54
|
+
_d 35
|
55
|
+
kf 35
|
56
|
+
fn 34
|
57
|
+
_/ 33
|
58
|
+
m 33
|
59
|
+
_e 32
|
60
|
+
_g 31
|
61
|
+
_f 31
|
62
|
+
p 31
|
63
|
+
P 30
|
64
|
+
/f 30
|
65
|
+
. 29
|
66
|
+
lj 28
|
67
|
+
D 27
|
68
|
+
jf 27
|
69
|
+
lg 27
|
70
|
+
O 26
|
71
|
+
n] 26
|
72
|
+
: 26
|
73
|
+
sf_ 26
|
74
|
+
;f 26
|
75
|
+
_. 26
|
76
|
+
_k| 25
|
77
|
+
gf 25
|
78
|
+
_a 25
|
79
|
+
cf 24
|
80
|
+
nf 24
|
81
|
+
, 24
|
82
|
+
? 23
|
83
|
+
_lj 23
|
84
|
+
fd 22
|
85
|
+
_sf 22
|
86
|
+
s_ 22
|
87
|
+
of 22
|
88
|
+
kl 22
|
89
|
+
t_ 22
|
90
|
+
fk 21
|
91
|
+
af 21
|
92
|
+
n]_ 20
|
93
|
+
_cf 20
|
94
|
+
f{ 20
|
95
|
+
}_ 20
|
96
|
+
,_ 20
|
97
|
+
g]_ 20
|
98
|
+
fg 20
|
99
|
+
f/_ 19
|
100
|
+
q 19
|
101
|
+
\ 19
|
102
|
+
w 19
|
103
|
+
fj 18
|
104
|
+
Ps 18
|
105
|
+
y 18
|
106
|
+
]s 18
|
107
|
+
_p 18
|
108
|
+
_/_ 17
|
109
|
+
xf 17
|
110
|
+
_h 16
|
111
|
+
f{_ 16
|
112
|
+
sf/ 16
|
113
|
+
x? 15
|
114
|
+
z 15
|
115
|
+
fx 15
|
116
|
+
fl 15
|
117
|
+
u_ 15
|
118
|
+
km 15
|
119
|
+
_n 15
|
120
|
+
= 15
|
121
|
+
ef 15
|
122
|
+
_b 15
|
123
|
+
;D 14
|
124
|
+
:t 14
|
125
|
+
lt 14
|
126
|
+
_df 14
|
127
|
+
_/f 14
|
128
|
+
d_ 14
|
129
|
+
lg_ 14
|
130
|
+
/s 14
|
131
|
+
/sf 14
|
132
|
+
g' 14
|
133
|
+
T 14
|
134
|
+
._ 14
|
135
|
+
fs 14
|
136
|
+
Gb 13
|
137
|
+
_eP 13
|
138
|
+
eP 13
|
139
|
+
j_ 13
|
140
|
+
]k 13
|
141
|
+
/L 13
|
142
|
+
]; 13
|
143
|
+
v 12
|
144
|
+
O{ 12
|
145
|
+
ug 12
|
146
|
+
;+ 12
|
147
|
+
fO 12
|
148
|
+
klg_ 12
|
149
|
+
klg 12
|
150
|
+
_kl 12
|
151
|
+
+u 12
|
152
|
+
b' 12
|
153
|
+
f+ 12
|
154
|
+
Psf 12
|
155
|
+
g\ 12
|
156
|
+
f} 12
|
157
|
+
_g] 12
|
158
|
+
'/ 12
|
159
|
+
\_ 12
|
160
|
+
_._ 12
|
161
|
+
fsf 11
|
162
|
+
]d 11
|
163
|
+
]{ 11
|
164
|
+
GqL 11
|
165
|
+
rf 11
|
166
|
+
fb 11
|
167
|
+
Psf] 11
|
168
|
+
dGqL 11
|
169
|
+
of] 11
|
170
|
+
O{_ 11
|
171
|
+
bf 11
|
172
|
+
:tf 11
|
173
|
+
dGq 11
|
174
|
+
ePs 11
|
175
|
+
_x 11
|
176
|
+
lb 11
|
177
|
+
" 11
|
178
|
+
dG 11
|
179
|
+
fp 11
|
180
|
+
_;+ 11
|
181
|
+
_r 11
|
182
|
+
;/ 11
|
183
|
+
;b 11
|
184
|
+
u| 11
|
185
|
+
_ePs 11
|
186
|
+
_ug 11
|
187
|
+
qL 11
|
188
|
+
Gq 11
|
189
|
+
hf 11
|
190
|
+
hg 10
|
191
|
+
f; 10
|
192
|
+
nL 10
|
193
|
+
cg 10
|
194
|
+
F 10
|
195
|
+
De 10
|
196
|
+
_cg 10
|
197
|
+
tfj 10
|
198
|
+
cg' 10
|
199
|
+
]sf 10
|
200
|
+
i 10
|
201
|
+
g]{ 10
|
202
|
+
_t 10
|
203
|
+
fo 10
|
204
|
+
fu 10
|
205
|
+
yf 10
|
206
|
+
_cg' 10
|
207
|
+
'g 10
|
208
|
+
gf_ 10
|
209
|
+
n_ 10
|
210
|
+
kfn 10
|
211
|
+
s] 10
|
212
|
+
|] 10
|
213
|
+
_;D 10
|
214
|
+
_j 10
|
215
|
+
! 9
|
216
|
+
_g]k 9
|
217
|
+
]kfn 9
|
218
|
+
k|:t 9
|
219
|
+
gd 9
|
220
|
+
k|: 9
|
221
|
+
g\_ 9
|
222
|
+
l/ 9
|
223
|
+
|:t 9
|
224
|
+
bg 9
|
225
|
+
|: 9
|
226
|
+
ePsf 9
|
227
|
+
_lg 9
|
228
|
+
ut 9
|
229
|
+
]n 9
|
230
|
+
b_ 9
|
231
|
+
a} 9
|
232
|
+
g]k 9
|
233
|
+
ln 9
|
234
|
+
af_ 9
|
235
|
+
l_ 9
|
236
|
+
g]kfn 9
|
237
|
+
_klg_ 9
|
238
|
+
;l 9
|
239
|
+
_ePsf 9
|
240
|
+
o; 9
|
241
|
+
u/ 9
|
242
|
+
_;l 9
|
243
|
+
]kf 9
|
244
|
+
_klg 9
|
245
|
+
To 9
|
246
|
+
_g]kf 9
|
247
|
+
g]kf 9
|
248
|
+
I 8
|
249
|
+
|:tfj 8
|
250
|
+
lx 8
|
251
|
+
sf+u 8
|
252
|
+
|:tf 8
|
253
|
+
dl 8
|
254
|
+
f+u| 8
|
255
|
+
;s 8
|
256
|
+
_af 8
|
257
|
+
fdf 8
|
258
|
+
tfj_ 8
|
259
|
+
:tfj 8
|
260
|
+
]sf] 8
|
261
|
+
=_ 8
|
262
|
+
+u|]; 8
|
263
|
+
_lb 8
|
264
|
+
If 8
|
265
|
+
;/sf 8
|
266
|
+
]{_ 8
|
267
|
+
_] 8
|
268
|
+
+u|] 8
|
269
|
+
gs 8
|
270
|
+
tf_ 8
|
271
|
+
em 8
|
272
|
+
Psf]_ 8
|
273
|
+
;/sf/ 8
|
274
|
+
ePsf] 8
|
275
|
+
;/s 8
|
276
|
+
/] 8
|
277
|
+
/L_ 8
|
278
|
+
nL_ 8
|
279
|
+
Q 8
|
280
|
+
_;f 8
|
281
|
+
f+u 8
|
282
|
+
pg 8
|
283
|
+
kf_ 8
|
284
|
+
;f/ 8
|
285
|
+
fj_ 8
|
286
|
+
fO{ 8
|
287
|
+
S 8
|
288
|
+
o_ 8
|
289
|
+
]sf]_ 8
|
290
|
+
u|]; 8
|
291
|
+
;_ 8
|
292
|
+
|]; 8
|
293
|
+
sf+u| 8
|
294
|
+
sf+ 8
|
295
|
+
x' 8
|
296
|
+
fO{_ 8
|
297
|
+
f+u|] 8
|
298
|
+
/sf/ 8
|
299
|
+
u|] 8
|
300
|
+
k|:tf 8
|
301
|
+
d' 8
|
302
|
+
g} 8
|
303
|
+
+u| 8
|
304
|
+
_;/sf 7
|
305
|
+
> 7
|
306
|
+
?sf 7
|
307
|
+
fnL 7
|
308
|
+
|f 7
|
309
|
+
_sf+u 7
|
310
|
+
?s 7
|
311
|
+
'; 7
|
312
|
+
]t 7
|
313
|
+
ld 7
|
314
|
+
_sf+ 7
|
315
|
+
x?s 7
|
316
|
+
Da 7
|
317
|
+
_;/ 7
|
318
|
+
;De 7
|
319
|
+
hgf 7
|
320
|
+
g';f/ 7
|
321
|
+
';f 7
|
322
|
+
lr 7
|
323
|
+
x?sf] 7
|
324
|
+
lu 7
|
325
|
+
_;/s 7
|
326
|
+
fk| 7
|
327
|
+
_k|: 7
|
328
|
+
cg'; 7
|
329
|
+
g]{_ 7
|
330
|
+
nd 7
|
331
|
+
_o 7
|
332
|
+
x_ 7
|
333
|
+
';f/ 7
|
334
|
+
;f] 7
|
335
|
+
]/ 7
|
336
|
+
rfn 7
|
337
|
+
- 7
|
338
|
+
a}_ 7
|
339
|
+
x?sf 7
|
340
|
+
_u/ 7
|
341
|
+
?sf] 7
|
342
|
+
_jf 7
|
343
|
+
_nf 7
|
344
|
+
g';f 7
|
345
|
+
;f/_ 7
|
346
|
+
x'g 7
|
347
|
+
_cg'; 7
|
348
|
+
mn 7
|
349
|
+
g'; 7
|
350
|
+
';f/_ 7
|
351
|
+
_rf 7
|
352
|
+
_k|:t 7
|
353
|
+
cg';f 7
|
354
|
+
_! 6
|
355
|
+
_lk 6
|
356
|
+
_;lr 6
|
357
|
+
tf{_ 6
|
358
|
+
_dGqL 6
|
359
|
+
fkf 6
|
360
|
+
ns 6
|
361
|
+
/f] 6
|
362
|
+
nk 6
|
363
|
+
nsf 6
|
364
|
+
rGb 6
|
365
|
+
rG 6
|
366
|
+
fsf] 6
|
367
|
+
ng 6
|
368
|
+
_ug{_ 6
|
369
|
+
_;De 6
|
370
|
+
g}_ 6
|
371
|
+
u/] 6
|
372
|
+
rj 6
|
373
|
+
_u/] 6
|
374
|
+
]df_ 6
|
375
|
+
;sf 6
|
376
|
+
nfO{ 6
|
377
|
+
mtf 6
|
378
|
+
f/s 6
|
379
|
+
]x 6
|
380
|
+
_ug{ 6
|
381
|
+
|l 6
|
382
|
+
nfO 6
|
383
|
+
ljj 6
|
384
|
+
ug{ 6
|
385
|
+
fb' 6
|
386
|
+
_kf 6
|
387
|
+
Z 6
|
388
|
+
_ljjf 6
|
389
|
+
_dG 6
|
390
|
+
ax 6
|
391
|
+
_ljj 6
|
392
|
+
ng_ 6
|
393
|
+
jj 6
|
394
|
+
_f_ 6
|
395
|
+
ljjf 6
|
396
|
+
Qm 6
|
397
|
+
k|l 6
|
398
|
+
f/L 6
|
399
|
+
;lr 6
|
400
|
+
dt 6
|