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
|
+
_ 1548
|
2
|
+
e 554
|
3
|
+
s 334
|
4
|
+
i 300
|
5
|
+
n 282
|
6
|
+
r 280
|
7
|
+
a 268
|
8
|
+
t 252
|
9
|
+
o 214
|
10
|
+
u 206
|
11
|
+
l 182
|
12
|
+
e_ 180
|
13
|
+
d 175
|
14
|
+
s_ 139
|
15
|
+
c 130
|
16
|
+
� 127
|
17
|
+
p 125
|
18
|
+
_d 121
|
19
|
+
es 99
|
20
|
+
m 93
|
21
|
+
_l 79
|
22
|
+
on 78
|
23
|
+
de 76
|
24
|
+
le 70
|
25
|
+
re 68
|
26
|
+
en 67
|
27
|
+
_de 67
|
28
|
+
es_ 65
|
29
|
+
, 63
|
30
|
+
t_ 60
|
31
|
+
,_ 59
|
32
|
+
f 57
|
33
|
+
nt 53
|
34
|
+
__ 52
|
35
|
+
_p 50
|
36
|
+
de_ 50
|
37
|
+
v 48
|
38
|
+
er 46
|
39
|
+
_de_ 46
|
40
|
+
g 45
|
41
|
+
n_ 45
|
42
|
+
_s 43
|
43
|
+
an 43
|
44
|
+
_a 42
|
45
|
+
_e 41
|
46
|
+
q 40
|
47
|
+
_c 40
|
48
|
+
_le 40
|
49
|
+
ai 40
|
50
|
+
qu 40
|
51
|
+
h 39
|
52
|
+
' 39
|
53
|
+
ou 38
|
54
|
+
it 38
|
55
|
+
is 38
|
56
|
+
ns 37
|
57
|
+
te 35
|
58
|
+
ra 35
|
59
|
+
r_ 35
|
60
|
+
io 35
|
61
|
+
a_ 34
|
62
|
+
ti 34
|
63
|
+
se 34
|
64
|
+
co 33
|
65
|
+
ion 32
|
66
|
+
in 30
|
67
|
+
ie 30
|
68
|
+
ur 29
|
69
|
+
la 28
|
70
|
+
le_ 28
|
71
|
+
les 28
|
72
|
+
. 28
|
73
|
+
pr 27
|
74
|
+
tr 26
|
75
|
+
ent 26
|
76
|
+
di 25
|
77
|
+
me 25
|
78
|
+
et 25
|
79
|
+
ar 25
|
80
|
+
u_ 24
|
81
|
+
_m 24
|
82
|
+
� 24
|
83
|
+
ui 24
|
84
|
+
nd 23
|
85
|
+
au 23
|
86
|
+
�_ 23
|
87
|
+
ce 23
|
88
|
+
ir 23
|
89
|
+
_q 23
|
90
|
+
_qu 23
|
91
|
+
eu 22
|
92
|
+
les_ 22
|
93
|
+
po 22
|
94
|
+
or 22
|
95
|
+
ue 22
|
96
|
+
at 22
|
97
|
+
ro 22
|
98
|
+
pa 22
|
99
|
+
tio 21
|
100
|
+
._ 21
|
101
|
+
_t 21
|
102
|
+
nc 21
|
103
|
+
_r 21
|
104
|
+
tion 21
|
105
|
+
_f 21
|
106
|
+
nt_ 21
|
107
|
+
b 21
|
108
|
+
ts 20
|
109
|
+
ons 20
|
110
|
+
on_ 20
|
111
|
+
ne 20
|
112
|
+
_le_ 20
|
113
|
+
si 20
|
114
|
+
st 20
|
115
|
+
ns_ 19
|
116
|
+
_co 19
|
117
|
+
que 19
|
118
|
+
d� 19
|
119
|
+
ch 19
|
120
|
+
ve 19
|
121
|
+
ss 19
|
122
|
+
el 19
|
123
|
+
un 18
|
124
|
+
_pa 18
|
125
|
+
e, 18
|
126
|
+
t� 18
|
127
|
+
_la 18
|
128
|
+
e,_ 18
|
129
|
+
r� 17
|
130
|
+
sa 17
|
131
|
+
ion_ 17
|
132
|
+
L 17
|
133
|
+
re_ 17
|
134
|
+
_les 17
|
135
|
+
i_ 16
|
136
|
+
ec 16
|
137
|
+
x 16
|
138
|
+
la_ 16
|
139
|
+
_la_ 16
|
140
|
+
_n 15
|
141
|
+
il 15
|
142
|
+
�_ 15
|
143
|
+
_et 15
|
144
|
+
ap 15
|
145
|
+
li 15
|
146
|
+
� 15
|
147
|
+
ri 15
|
148
|
+
ut 15
|
149
|
+
_� 15
|
150
|
+
ci 15
|
151
|
+
_i 15
|
152
|
+
et_ 15
|
153
|
+
_�_ 15
|
154
|
+
om 15
|
155
|
+
pe 14
|
156
|
+
em 14
|
157
|
+
rt 14
|
158
|
+
_en 14
|
159
|
+
con 14
|
160
|
+
_L 14
|
161
|
+
�r 14
|
162
|
+
he 14
|
163
|
+
ont 14
|
164
|
+
A 14
|
165
|
+
l' 14
|
166
|
+
par 14
|
167
|
+
ait 14
|
168
|
+
_se 14
|
169
|
+
_d� 14
|
170
|
+
oi 14
|
171
|
+
as 14
|
172
|
+
_par 13
|
173
|
+
ma 13
|
174
|
+
s, 13
|
175
|
+
su 13
|
176
|
+
ts_ 13
|
177
|
+
_pr 13
|
178
|
+
it_ 13
|
179
|
+
d' 13
|
180
|
+
mi 13
|
181
|
+
ue_ 13
|
182
|
+
ire 13
|
183
|
+
mp 13
|
184
|
+
_les_ 13
|
185
|
+
_l' 13
|
186
|
+
�s 13
|
187
|
+
is_ 12
|
188
|
+
our 12
|
189
|
+
fi 12
|
190
|
+
so 12
|
191
|
+
j 12
|
192
|
+
_d' 12
|
193
|
+
ur_ 12
|
194
|
+
ta 12
|
195
|
+
�s 12
|
196
|
+
_et_ 12
|
197
|
+
vi 12
|
198
|
+
y 12
|
199
|
+
ni 12
|
200
|
+
ge 12
|
201
|
+
s,_ 12
|
202
|
+
mo 11
|
203
|
+
_M 11
|
204
|
+
est 11
|
205
|
+
que_ 11
|
206
|
+
- 11
|
207
|
+
er_ 11
|
208
|
+
bl 11
|
209
|
+
des 11
|
210
|
+
ais 11
|
211
|
+
n� 11
|
212
|
+
_su 11
|
213
|
+
che 11
|
214
|
+
M 11
|
215
|
+
te_ 11
|
216
|
+
�t 11
|
217
|
+
ons_ 11
|
218
|
+
_des 11
|
219
|
+
en_ 11
|
220
|
+
res 11
|
221
|
+
av 11
|
222
|
+
ne_ 11
|
223
|
+
rs 11
|
224
|
+
tion_ 11
|
225
|
+
" 11
|
226
|
+
up 10
|
227
|
+
_re 10
|
228
|
+
ions 10
|
229
|
+
ans 10
|
230
|
+
iq 10
|
231
|
+
ic 10
|
232
|
+
t�_ 10
|
233
|
+
tre 10
|
234
|
+
_o 10
|
235
|
+
�e 10
|
236
|
+
us 10
|
237
|
+
s� 10
|
238
|
+
pp 10
|
239
|
+
pro 10
|
240
|
+
_di 10
|
241
|
+
ati 10
|
242
|
+
_des_ 10
|
243
|
+
des_ 10
|
244
|
+
_" 10
|
245
|
+
ien 10
|
246
|
+
ui_ 10
|
247
|
+
ux 10
|
248
|
+
du 10
|
249
|
+
l_ 10
|
250
|
+
_av 10
|
251
|
+
iqu 10
|
252
|
+
ces 10
|
253
|
+
�c 10
|
254
|
+
ent_ 10
|
255
|
+
ation 9
|
256
|
+
nte 9
|
257
|
+
_con 9
|
258
|
+
ll 9
|
259
|
+
ait_ 9
|
260
|
+
com 9
|
261
|
+
fo 9
|
262
|
+
t, 9
|
263
|
+
_j 9
|
264
|
+
_au 9
|
265
|
+
qui 9
|
266
|
+
al 9
|
267
|
+
r� 9
|
268
|
+
nn 9
|
269
|
+
_g 9
|
270
|
+
_so 9
|
271
|
+
se_ 9
|
272
|
+
_ce 9
|
273
|
+
qui_ 9
|
274
|
+
ces_ 9
|
275
|
+
_in 9
|
276
|
+
pl 9
|
277
|
+
dr 9
|
278
|
+
anc 9
|
279
|
+
atio 9
|
280
|
+
id 9
|
281
|
+
men 9
|
282
|
+
D 9
|
283
|
+
r�s 9
|
284
|
+
un_ 9
|
285
|
+
ique 9
|
286
|
+
'a 9
|
287
|
+
pu 8
|
288
|
+
app 8
|
289
|
+
_u 8
|
290
|
+
�g 8
|
291
|
+
Le 8
|
292
|
+
oup 8
|
293
|
+
rs_ 8
|
294
|
+
ement 8
|
295
|
+
ig 8
|
296
|
+
da 8
|
297
|
+
_qui 8
|
298
|
+
au_ 8
|
299
|
+
ier 8
|
300
|
+
rec 8
|
301
|
+
e. 8
|
302
|
+
ca 8
|
303
|
+
it� 8
|
304
|
+
_un 8
|
305
|
+
to 8
|
306
|
+
if 8
|
307
|
+
ions_ 8
|
308
|
+
do 8
|
309
|
+
ff 8
|
310
|
+
_tr 8
|
311
|
+
sp 8
|
312
|
+
ha 8
|
313
|
+
G 8
|
314
|
+
_qui_ 8
|
315
|
+
� 8
|
316
|
+
ndi 8
|
317
|
+
l� 8
|
318
|
+
ct 8
|
319
|
+
emen 8
|
320
|
+
na 8
|
321
|
+
ment 8
|
322
|
+
ser 8
|
323
|
+
�e_ 8
|
324
|
+
�s_ 8
|
325
|
+
m� 8
|
326
|
+
ndr 8
|
327
|
+
no 8
|
328
|
+
_mo 8
|
329
|
+
eme 8
|
330
|
+
La 7
|
331
|
+
va 7
|
332
|
+
ont_ 7
|
333
|
+
im 7
|
334
|
+
rc 7
|
335
|
+
_"_ 7
|
336
|
+
_h 7
|
337
|
+
_pro 7
|
338
|
+
ble 7
|
339
|
+
t,_ 7
|
340
|
+
sion 7
|
341
|
+
end 7
|
342
|
+
ell 7
|
343
|
+
�l 7
|
344
|
+
lle 7
|
345
|
+
ect 7
|
346
|
+
omp 7
|
347
|
+
tions 7
|
348
|
+
um 7
|
349
|
+
gr 7
|
350
|
+
ans_ 7
|
351
|
+
du_ 7
|
352
|
+
x_ 7
|
353
|
+
ce_ 7
|
354
|
+
_ch 7
|
355
|
+
for 7
|
356
|
+
B 7
|
357
|
+
os 7
|
358
|
+
eur 7
|
359
|
+
_Le 7
|
360
|
+
"_ 7
|
361
|
+
C 7
|
362
|
+
sio 7
|
363
|
+
F 7
|
364
|
+
_fo 7
|
365
|
+
ire_ 7
|
366
|
+
uis 7
|
367
|
+
ort 7
|
368
|
+
r�s 7
|
369
|
+
rai 7
|
370
|
+
u' 6
|
371
|
+
r, 6
|
372
|
+
aire 6
|
373
|
+
pas 6
|
374
|
+
qu' 6
|
375
|
+
iss 6
|
376
|
+
_do 6
|
377
|
+
'i 6
|
378
|
+
lu 6
|
379
|
+
ues 6
|
380
|
+
ja 6
|
381
|
+
_to 6
|
382
|
+
_du 6
|
383
|
+
ess 6
|
384
|
+
ist 6
|
385
|
+
s. 6
|
386
|
+
_ma 6
|
387
|
+
ac 6
|
388
|
+
_que 6
|
389
|
+
urs 6
|
390
|
+
st_ 6
|
391
|
+
enc 6
|
392
|
+
�s_ 6
|
393
|
+
lo 6
|
394
|
+
_au_ 6
|
395
|
+
ng 6
|
396
|
+
ea 6
|
397
|
+
cou 6
|
398
|
+
_ap 6
|
399
|
+
ass 6
|
400
|
+
mai 6
|