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
|
+
_ 2736
|
2
|
+
e 773
|
3
|
+
t 520
|
4
|
+
i 515
|
5
|
+
a 507
|
6
|
+
o 495
|
7
|
+
s 453
|
8
|
+
n 422
|
9
|
+
r 391
|
10
|
+
u 337
|
11
|
+
l 264
|
12
|
+
m 234
|
13
|
+
d 226
|
14
|
+
e_ 207
|
15
|
+
c 198
|
16
|
+
h 188
|
17
|
+
p 178
|
18
|
+
s_ 150
|
19
|
+
re 134
|
20
|
+
_a 127
|
21
|
+
t_ 126
|
22
|
+
_t 125
|
23
|
+
in 123
|
24
|
+
or 103
|
25
|
+
f 99
|
26
|
+
m_ 98
|
27
|
+
b 91
|
28
|
+
g 87
|
29
|
+
_o 85
|
30
|
+
n_ 84
|
31
|
+
th 84
|
32
|
+
d_ 83
|
33
|
+
er 83
|
34
|
+
_i 81
|
35
|
+
he 81
|
36
|
+
y 80
|
37
|
+
an 79
|
38
|
+
__ 78
|
39
|
+
_e 78
|
40
|
+
at 78
|
41
|
+
, 75
|
42
|
+
,_ 75
|
43
|
+
on 73
|
44
|
+
es 72
|
45
|
+
_s 72
|
46
|
+
te 72
|
47
|
+
_th 70
|
48
|
+
is 69
|
49
|
+
_p 65
|
50
|
+
. 64
|
51
|
+
um 63
|
52
|
+
v 63
|
53
|
+
o_ 63
|
54
|
+
se 62
|
55
|
+
en 60
|
56
|
+
w 60
|
57
|
+
ti 59
|
58
|
+
r_ 58
|
59
|
+
it 58
|
60
|
+
nd 58
|
61
|
+
ur 52
|
62
|
+
as 52
|
63
|
+
._ 52
|
64
|
+
the 52
|
65
|
+
_d 52
|
66
|
+
nt 51
|
67
|
+
_the 50
|
68
|
+
a_ 50
|
69
|
+
su 50
|
70
|
+
qu 48
|
71
|
+
q 48
|
72
|
+
_c 48
|
73
|
+
he_ 48
|
74
|
+
y_ 47
|
75
|
+
_w 47
|
76
|
+
us 46
|
77
|
+
_b 46
|
78
|
+
le 45
|
79
|
+
of 44
|
80
|
+
em 44
|
81
|
+
si 43
|
82
|
+
ta 43
|
83
|
+
f_ 42
|
84
|
+
ore 42
|
85
|
+
um_ 42
|
86
|
+
_of 42
|
87
|
+
ed 42
|
88
|
+
to 41
|
89
|
+
k 41
|
90
|
+
li 40
|
91
|
+
ng 40
|
92
|
+
re_ 40
|
93
|
+
et 40
|
94
|
+
the_ 39
|
95
|
+
_of_ 39
|
96
|
+
of_ 39
|
97
|
+
ea 39
|
98
|
+
and 39
|
99
|
+
is_ 39
|
100
|
+
_the_ 39
|
101
|
+
ol 38
|
102
|
+
in_ 38
|
103
|
+
st 38
|
104
|
+
de 37
|
105
|
+
_m 37
|
106
|
+
_an 36
|
107
|
+
_in 36
|
108
|
+
io 35
|
109
|
+
_h 35
|
110
|
+
_r 35
|
111
|
+
ri 34
|
112
|
+
ve 34
|
113
|
+
ed_ 34
|
114
|
+
ar 34
|
115
|
+
la 34
|
116
|
+
ce 33
|
117
|
+
_f 33
|
118
|
+
ing 33
|
119
|
+
ou 33
|
120
|
+
I 32
|
121
|
+
lo 32
|
122
|
+
ec 32
|
123
|
+
ro 32
|
124
|
+
nd_ 31
|
125
|
+
_I 31
|
126
|
+
g_ 31
|
127
|
+
ng_ 31
|
128
|
+
to_ 30
|
129
|
+
_n 30
|
130
|
+
em_ 30
|
131
|
+
al 30
|
132
|
+
el 30
|
133
|
+
ha 30
|
134
|
+
_to 30
|
135
|
+
ni 30
|
136
|
+
ing_ 30
|
137
|
+
co 30
|
138
|
+
es_ 29
|
139
|
+
_l 29
|
140
|
+
no 29
|
141
|
+
di 29
|
142
|
+
ut 29
|
143
|
+
ra 29
|
144
|
+
om 29
|
145
|
+
_u 28
|
146
|
+
ic 28
|
147
|
+
ct 28
|
148
|
+
am 28
|
149
|
+
ne 28
|
150
|
+
ai 28
|
151
|
+
rem 27
|
152
|
+
ion 27
|
153
|
+
_and 27
|
154
|
+
_v 27
|
155
|
+
ll 27
|
156
|
+
_and_ 27
|
157
|
+
and_ 27
|
158
|
+
ns 27
|
159
|
+
l_ 27
|
160
|
+
_re 27
|
161
|
+
ia 26
|
162
|
+
sum 26
|
163
|
+
do 26
|
164
|
+
_a_ 26
|
165
|
+
L 26
|
166
|
+
_to_ 26
|
167
|
+
_q 25
|
168
|
+
_qu 25
|
169
|
+
pa 25
|
170
|
+
ru 25
|
171
|
+
tio 25
|
172
|
+
ci 25
|
173
|
+
ps 25
|
174
|
+
il 25
|
175
|
+
ui 24
|
176
|
+
ati 24
|
177
|
+
un 24
|
178
|
+
me 24
|
179
|
+
x 24
|
180
|
+
psu 23
|
181
|
+
rem_ 23
|
182
|
+
_co 23
|
183
|
+
orem 23
|
184
|
+
tion 23
|
185
|
+
ss 23
|
186
|
+
_L 23
|
187
|
+
psum 23
|
188
|
+
pl 23
|
189
|
+
hi 23
|
190
|
+
_in_ 23
|
191
|
+
se_ 22
|
192
|
+
ure 22
|
193
|
+
ma 22
|
194
|
+
im 22
|
195
|
+
mo 22
|
196
|
+
orem_ 22
|
197
|
+
tr 22
|
198
|
+
_pa 22
|
199
|
+
id 22
|
200
|
+
_do 22
|
201
|
+
or_ 22
|
202
|
+
sum_ 21
|
203
|
+
lor 21
|
204
|
+
nc 21
|
205
|
+
ac 21
|
206
|
+
on_ 21
|
207
|
+
ge 20
|
208
|
+
it_ 20
|
209
|
+
ex 20
|
210
|
+
i_ 20
|
211
|
+
_si 20
|
212
|
+
ut_ 20
|
213
|
+
" 20
|
214
|
+
at_ 20
|
215
|
+
tu 20
|
216
|
+
Lore 19
|
217
|
+
et_ 19
|
218
|
+
Lor 19
|
219
|
+
Lo 19
|
220
|
+
us_ 19
|
221
|
+
qui 19
|
222
|
+
Lorem 19
|
223
|
+
pt 19
|
224
|
+
psum_ 19
|
225
|
+
ons 19
|
226
|
+
_no 18
|
227
|
+
be 18
|
228
|
+
as_ 18
|
229
|
+
ho 18
|
230
|
+
ect 18
|
231
|
+
pe 18
|
232
|
+
er_ 18
|
233
|
+
ain 18
|
234
|
+
ab 18
|
235
|
+
T 18
|
236
|
+
bl 17
|
237
|
+
h_ 17
|
238
|
+
_Ip 17
|
239
|
+
ple 17
|
240
|
+
eas 17
|
241
|
+
rs 17
|
242
|
+
_Ipsu 17
|
243
|
+
sa 17
|
244
|
+
rum 17
|
245
|
+
Ips 17
|
246
|
+
_Lo 17
|
247
|
+
ca 17
|
248
|
+
pr 17
|
249
|
+
_is 17
|
250
|
+
wh 17
|
251
|
+
up 17
|
252
|
+
_Lore 17
|
253
|
+
_Lor 17
|
254
|
+
_et 17
|
255
|
+
Ipsu 17
|
256
|
+
_be 17
|
257
|
+
vo 17
|
258
|
+
Ip 17
|
259
|
+
_wh 17
|
260
|
+
Ipsum 17
|
261
|
+
_Ips 17
|
262
|
+
du 16
|
263
|
+
ep 16
|
264
|
+
tur 16
|
265
|
+
cu 16
|
266
|
+
olo 16
|
267
|
+
ent 16
|
268
|
+
ch 16
|
269
|
+
ate 16
|
270
|
+
lea 16
|
271
|
+
ere 16
|
272
|
+
bu 16
|
273
|
+
au 16
|
274
|
+
ul 16
|
275
|
+
nt_ 16
|
276
|
+
_qui 16
|
277
|
+
po 16
|
278
|
+
ua 16
|
279
|
+
_ma 16
|
280
|
+
ag 16
|
281
|
+
lu 16
|
282
|
+
na 15
|
283
|
+
olor 15
|
284
|
+
_. 15
|
285
|
+
_is_ 15
|
286
|
+
s,_ 15
|
287
|
+
dol 15
|
288
|
+
C 15
|
289
|
+
os 15
|
290
|
+
_et_ 15
|
291
|
+
ter 15
|
292
|
+
tat 15
|
293
|
+
ver 15
|
294
|
+
_dol 15
|
295
|
+
_dolo 15
|
296
|
+
s, 15
|
297
|
+
leas 15
|
298
|
+
_ex 15
|
299
|
+
dolo 15
|
300
|
+
dolor 15
|
301
|
+
sur 14
|
302
|
+
t,_ 14
|
303
|
+
so 14
|
304
|
+
_._ 14
|
305
|
+
_con 14
|
306
|
+
con 14
|
307
|
+
_de 14
|
308
|
+
qua 14
|
309
|
+
ip 14
|
310
|
+
_pl 14
|
311
|
+
wi 14
|
312
|
+
ke 14
|
313
|
+
ue 14
|
314
|
+
t, 14
|
315
|
+
ure_ 13
|
316
|
+
te_ 13
|
317
|
+
her 13
|
318
|
+
ir 13
|
319
|
+
plea 13
|
320
|
+
atio 13
|
321
|
+
by_ 13
|
322
|
+
sure 13
|
323
|
+
_by 13
|
324
|
+
_ve 13
|
325
|
+
en_ 13
|
326
|
+
Th 13
|
327
|
+
od 13
|
328
|
+
pleas 13
|
329
|
+
_mo 13
|
330
|
+
_ha 13
|
331
|
+
by 13
|
332
|
+
_ple 13
|
333
|
+
_by_ 13
|
334
|
+
upt 13
|
335
|
+
ation 13
|
336
|
+
olu 13
|
337
|
+
res 13
|
338
|
+
vol 13
|
339
|
+
_plea 13
|
340
|
+
ur_ 12
|
341
|
+
lup 12
|
342
|
+
leasu 12
|
343
|
+
_fr 12
|
344
|
+
_vo 12
|
345
|
+
lupta 12
|
346
|
+
mp 12
|
347
|
+
oo 12
|
348
|
+
upta 12
|
349
|
+
fr 12
|
350
|
+
bo 12
|
351
|
+
ly 12
|
352
|
+
ly_ 12
|
353
|
+
lupt 12
|
354
|
+
asur 12
|
355
|
+
olupt 12
|
356
|
+
asure 12
|
357
|
+
olup 12
|
358
|
+
_volu 12
|
359
|
+
_vol 12
|
360
|
+
_pr 12
|
361
|
+
asu 12
|
362
|
+
_wi 12
|
363
|
+
volu 12
|
364
|
+
da 12
|
365
|
+
easu 12
|
366
|
+
age 12
|
367
|
+
unt 12
|
368
|
+
volup 12
|
369
|
+
rum_ 12
|
370
|
+
easur 12
|
371
|
+
ae 12
|
372
|
+
est 12
|
373
|
+
pta 12
|
374
|
+
nte 12
|
375
|
+
sin 12
|
376
|
+
cons 11
|
377
|
+
_cons 11
|
378
|
+
here 11
|
379
|
+
_it 11
|
380
|
+
yo 11
|
381
|
+
cc 11
|
382
|
+
_pain 11
|
383
|
+
equ 11
|
384
|
+
_y 11
|
385
|
+
_al 11
|
386
|
+
fo 11
|
387
|
+
The 11
|
388
|
+
_T 11
|
389
|
+
oi 11
|
390
|
+
B 11
|
391
|
+
orum 11
|
392
|
+
_se 11
|
393
|
+
pain 11
|
394
|
+
_te 11
|
395
|
+
pai 11
|
396
|
+
ain_ 11
|
397
|
+
nce 11
|
398
|
+
_g 11
|
399
|
+
tin 11
|
400
|
+
_us 11
|