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
|
+
_ 1404
|
2
|
+
a 445
|
3
|
+
o 425
|
4
|
+
e 409
|
5
|
+
s 292
|
6
|
+
r 260
|
7
|
+
i 259
|
8
|
+
t 203
|
9
|
+
d 195
|
10
|
+
n 193
|
11
|
+
m 162
|
12
|
+
o_ 147
|
13
|
+
u 144
|
14
|
+
c 130
|
15
|
+
a_ 118
|
16
|
+
e_ 103
|
17
|
+
p 100
|
18
|
+
s_ 96
|
19
|
+
_d 96
|
20
|
+
l 94
|
21
|
+
de 77
|
22
|
+
os 67
|
23
|
+
_a 65
|
24
|
+
es 65
|
25
|
+
, 62
|
26
|
+
do 61
|
27
|
+
ra 60
|
28
|
+
nt 59
|
29
|
+
,_ 54
|
30
|
+
_de 52
|
31
|
+
_p 49
|
32
|
+
v 49
|
33
|
+
re 48
|
34
|
+
os_ 48
|
35
|
+
to 47
|
36
|
+
ar 46
|
37
|
+
ta 45
|
38
|
+
or 45
|
39
|
+
. 45
|
40
|
+
te 44
|
41
|
+
en 44
|
42
|
+
de_ 44
|
43
|
+
g 43
|
44
|
+
co 42
|
45
|
+
_c 41
|
46
|
+
_s 41
|
47
|
+
er 39
|
48
|
+
ri 38
|
49
|
+
f 38
|
50
|
+
se 37
|
51
|
+
as 37
|
52
|
+
do_ 36
|
53
|
+
da 36
|
54
|
+
b 36
|
55
|
+
_e 36
|
56
|
+
_n 36
|
57
|
+
ad 35
|
58
|
+
r_ 35
|
59
|
+
_m 35
|
60
|
+
m_ 35
|
61
|
+
ma 34
|
62
|
+
q 33
|
63
|
+
qu 33
|
64
|
+
st 33
|
65
|
+
_t 33
|
66
|
+
no 32
|
67
|
+
� 32
|
68
|
+
�o 32
|
69
|
+
� 32
|
70
|
+
_o 31
|
71
|
+
_de_ 31
|
72
|
+
ia 30
|
73
|
+
is 30
|
74
|
+
an 29
|
75
|
+
pa 28
|
76
|
+
me 28
|
77
|
+
__ 28
|
78
|
+
_co 28
|
79
|
+
ue 28
|
80
|
+
in 27
|
81
|
+
io 27
|
82
|
+
on 27
|
83
|
+
al 27
|
84
|
+
h 27
|
85
|
+
nte 26
|
86
|
+
ti 26
|
87
|
+
�o_ 26
|
88
|
+
que 26
|
89
|
+
am 26
|
90
|
+
ent 25
|
91
|
+
om 25
|
92
|
+
_do 25
|
93
|
+
ca 24
|
94
|
+
po 24
|
95
|
+
_qu 24
|
96
|
+
em 24
|
97
|
+
_q 24
|
98
|
+
_se 23
|
99
|
+
_f 22
|
100
|
+
_que 21
|
101
|
+
� 21
|
102
|
+
_a_ 21
|
103
|
+
ci 21
|
104
|
+
ec 20
|
105
|
+
as_ 20
|
106
|
+
ei 20
|
107
|
+
to_ 19
|
108
|
+
ic 19
|
109
|
+
o, 19
|
110
|
+
tr 19
|
111
|
+
ou 18
|
112
|
+
ue_ 18
|
113
|
+
que_ 18
|
114
|
+
ado 18
|
115
|
+
ss 18
|
116
|
+
_pa 18
|
117
|
+
a� 18
|
118
|
+
ra_ 18
|
119
|
+
na 18
|
120
|
+
ce 18
|
121
|
+
li 17
|
122
|
+
par 17
|
123
|
+
._ 17
|
124
|
+
si 17
|
125
|
+
u_ 17
|
126
|
+
_r 17
|
127
|
+
mi 17
|
128
|
+
_do_ 17
|
129
|
+
nd 17
|
130
|
+
id 17
|
131
|
+
nto 17
|
132
|
+
_no 17
|
133
|
+
_da 16
|
134
|
+
men 16
|
135
|
+
es_ 16
|
136
|
+
um 16
|
137
|
+
o,_ 16
|
138
|
+
S 16
|
139
|
+
im 16
|
140
|
+
_que_ 16
|
141
|
+
em_ 16
|
142
|
+
� 16
|
143
|
+
s, 16
|
144
|
+
pr 16
|
145
|
+
te_ 15
|
146
|
+
� 15
|
147
|
+
it 15
|
148
|
+
mo 15
|
149
|
+
sa 15
|
150
|
+
_re 15
|
151
|
+
res 15
|
152
|
+
rt 15
|
153
|
+
el 15
|
154
|
+
ma_ 14
|
155
|
+
.. 14
|
156
|
+
_po 14
|
157
|
+
ara 14
|
158
|
+
s,_ 14
|
159
|
+
ve 14
|
160
|
+
�� 14
|
161
|
+
��o 14
|
162
|
+
" 14
|
163
|
+
da_ 14
|
164
|
+
ant 14
|
165
|
+
ac 14
|
166
|
+
ro 14
|
167
|
+
so 14
|
168
|
+
_par 13
|
169
|
+
ment 13
|
170
|
+
con 13
|
171
|
+
ont 13
|
172
|
+
fo 13
|
173
|
+
ir 13
|
174
|
+
dos 13
|
175
|
+
il 13
|
176
|
+
la 13
|
177
|
+
ai 13
|
178
|
+
no_ 13
|
179
|
+
_� 13
|
180
|
+
��o_ 13
|
181
|
+
com 13
|
182
|
+
� 13
|
183
|
+
pe 12
|
184
|
+
tu 12
|
185
|
+
di 12
|
186
|
+
uma 12
|
187
|
+
sta 12
|
188
|
+
uma_ 12
|
189
|
+
dos_ 12
|
190
|
+
_o_ 12
|
191
|
+
ho 12
|
192
|
+
lh 12
|
193
|
+
est 12
|
194
|
+
� 12
|
195
|
+
tra 11
|
196
|
+
vo 11
|
197
|
+
I 11
|
198
|
+
ni 11
|
199
|
+
at 11
|
200
|
+
ep 11
|
201
|
+
rio 11
|
202
|
+
_com 11
|
203
|
+
ente 11
|
204
|
+
tos 11
|
205
|
+
er_ 11
|
206
|
+
_b 11
|
207
|
+
ap 11
|
208
|
+
_u 11
|
209
|
+
gu 11
|
210
|
+
_um 11
|
211
|
+
or_ 11
|
212
|
+
vi 10
|
213
|
+
ol 10
|
214
|
+
gr 10
|
215
|
+
ua 10
|
216
|
+
dad 10
|
217
|
+
x 10
|
218
|
+
ar_ 10
|
219
|
+
lo 10
|
220
|
+
_l 10
|
221
|
+
mu 10
|
222
|
+
ist 10
|
223
|
+
ica 10
|
224
|
+
nc 10
|
225
|
+
a��o 10
|
226
|
+
ria 10
|
227
|
+
E 10
|
228
|
+
_uma 10
|
229
|
+
nte_ 10
|
230
|
+
_uma_ 10
|
231
|
+
nto_ 10
|
232
|
+
a�� 10
|
233
|
+
_S 10
|
234
|
+
va 10
|
235
|
+
mp 9
|
236
|
+
ct 9
|
237
|
+
ia_ 9
|
238
|
+
_pr 9
|
239
|
+
ara_ 9
|
240
|
+
am_ 9
|
241
|
+
para 9
|
242
|
+
ur 9
|
243
|
+
� 9
|
244
|
+
iv 9
|
245
|
+
l_ 9
|
246
|
+
des 9
|
247
|
+
�a 9
|
248
|
+
ida 9
|
249
|
+
rec 9
|
250
|
+
_ap 9
|
251
|
+
A 9
|
252
|
+
_fo 9
|
253
|
+
_ta 9
|
254
|
+
ou_ 9
|
255
|
+
ul 9
|
256
|
+
eg 9
|
257
|
+
ne 9
|
258
|
+
�es 9
|
259
|
+
ui 9
|
260
|
+
_i 9
|
261
|
+
a��o_ 9
|
262
|
+
le 9
|
263
|
+
�e 9
|
264
|
+
sen 9
|
265
|
+
e, 8
|
266
|
+
fi 8
|
267
|
+
tes 8
|
268
|
+
ter 8
|
269
|
+
para_ 8
|
270
|
+
_e_ 8
|
271
|
+
_con 8
|
272
|
+
nta 8
|
273
|
+
_no_ 8
|
274
|
+
ade 8
|
275
|
+
os, 8
|
276
|
+
_me 8
|
277
|
+
_v 8
|
278
|
+
ba 8
|
279
|
+
ns 8
|
280
|
+
C 8
|
281
|
+
gi 8
|
282
|
+
ov 8
|
283
|
+
omo 8
|
284
|
+
oc 8
|
285
|
+
_na 8
|
286
|
+
gra 8
|
287
|
+
tado 8
|
288
|
+
ab 8
|
289
|
+
_os 8
|
290
|
+
io_ 8
|
291
|
+
ed 8
|
292
|
+
ime 8
|
293
|
+
z 8
|
294
|
+
_os_ 8
|
295
|
+
cont 8
|
296
|
+
tiv 8
|
297
|
+
_da_ 8
|
298
|
+
tad 8
|
299
|
+
rr 8
|
300
|
+
_mu 8
|
301
|
+
a, 7
|
302
|
+
ito 7
|
303
|
+
omo_ 7
|
304
|
+
min 7
|
305
|
+
das_ 7
|
306
|
+
mo_ 7
|
307
|
+
... 7
|
308
|
+
_mi 7
|
309
|
+
_pe 7
|
310
|
+
mento 7
|
311
|
+
das 7
|
312
|
+
_te 7
|
313
|
+
idad 7
|
314
|
+
od 7
|
315
|
+
ento 7
|
316
|
+
R 7
|
317
|
+
os,_ 7
|
318
|
+
dep 7
|
319
|
+
ece 7
|
320
|
+
ado_ 7
|
321
|
+
str 7
|
322
|
+
�es_ 7
|
323
|
+
_das_ 7
|
324
|
+
_para 7
|
325
|
+
un 7
|
326
|
+
_em 7
|
327
|
+
dade 7
|
328
|
+
cia 7
|
329
|
+
tan 7
|
330
|
+
av 7
|
331
|
+
ut 7
|
332
|
+
ort 7
|
333
|
+
is_ 7
|
334
|
+
_ma 7
|
335
|
+
� 7
|
336
|
+
br 7
|
337
|
+
tar 7
|
338
|
+
nos 7
|
339
|
+
M 7
|
340
|
+
eu 7
|
341
|
+
ndo 7
|
342
|
+
_das 7
|
343
|
+
ess 7
|
344
|
+
j 7
|
345
|
+
va_ 7
|
346
|
+
�ri 6
|
347
|
+
tant 6
|
348
|
+
o. 6
|
349
|
+
ao 6
|
350
|
+
rte 6
|
351
|
+
sti 6
|
352
|
+
eri 6
|
353
|
+
ori 6
|
354
|
+
ig 6
|
355
|
+
_dep 6
|
356
|
+
como 6
|
357
|
+
_tr 6
|
358
|
+
�rio 6
|
359
|
+
se_ 6
|
360
|
+
_des 6
|
361
|
+
pu 6
|
362
|
+
muit 6
|
363
|
+
ram 6
|
364
|
+
P 6
|
365
|
+
_muit 6
|
366
|
+
lho 6
|
367
|
+
_in 6
|
368
|
+
esta 6
|
369
|
+
af 6
|
370
|
+
eu_ 6
|
371
|
+
ntes 6
|
372
|
+
anto 6
|
373
|
+
al_ 6
|
374
|
+
imen 6
|
375
|
+
- 6
|
376
|
+
ect 6
|
377
|
+
ios 6
|
378
|
+
tic 6
|
379
|
+
ge 6
|
380
|
+
ome 6
|
381
|
+
�r 6
|
382
|
+
�a_ 6
|
383
|
+
us 6
|
384
|
+
e,_ 6
|
385
|
+
a,_ 6
|
386
|
+
_ao 6
|
387
|
+
sc 6
|
388
|
+
T 6
|
389
|
+
_� 6
|
390
|
+
cor 6
|
391
|
+
ndo_ 6
|
392
|
+
tor 6
|
393
|
+
ser 6
|
394
|
+
ali 6
|
395
|
+
ente_ 6
|
396
|
+
D 6
|
397
|
+
nh 6
|
398
|
+
nos_ 6
|
399
|
+
_como 6
|
400
|
+
ta_ 6
|