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
|
+
_ 1432
|
2
|
+
a 336
|
3
|
+
r 312
|
4
|
+
n 283
|
5
|
+
i 254
|
6
|
+
u 245
|
7
|
+
e 242
|
8
|
+
s 194
|
9
|
+
t 176
|
10
|
+
� 175
|
11
|
+
l 166
|
12
|
+
g 157
|
13
|
+
k 143
|
14
|
+
m 135
|
15
|
+
f 132
|
16
|
+
r_ 98
|
17
|
+
�_ 76
|
18
|
+
v 74
|
19
|
+
ar 73
|
20
|
+
� 71
|
21
|
+
o 70
|
22
|
+
_s 64
|
23
|
+
� 63
|
24
|
+
a� 63
|
25
|
+
j 62
|
26
|
+
m_ 56
|
27
|
+
in 55
|
28
|
+
� 55
|
29
|
+
a_ 54
|
30
|
+
_e 51
|
31
|
+
ur 48
|
32
|
+
um 48
|
33
|
+
_f 48
|
34
|
+
n_ 47
|
35
|
+
_a 47
|
36
|
+
h 47
|
37
|
+
. 46
|
38
|
+
d 46
|
39
|
+
_� 45
|
40
|
+
er 44
|
41
|
+
st 44
|
42
|
+
g_ 44
|
43
|
+
b 44
|
44
|
+
u_ 43
|
45
|
+
i_ 43
|
46
|
+
a�_ 43
|
47
|
+
� 43
|
48
|
+
� 43
|
49
|
+
nn 42
|
50
|
+
nu 41
|
51
|
+
�_ 40
|
52
|
+
ei 40
|
53
|
+
_�_ 39
|
54
|
+
__ 39
|
55
|
+
� 38
|
56
|
+
i� 38
|
57
|
+
y 37
|
58
|
+
�_ 36
|
59
|
+
an 36
|
60
|
+
_v 36
|
61
|
+
ir 36
|
62
|
+
ve 35
|
63
|
+
p 35
|
64
|
+
_� 34
|
65
|
+
og 34
|
66
|
+
og_ 33
|
67
|
+
_a� 33
|
68
|
+
un 33
|
69
|
+
um_ 33
|
70
|
+
_o 32
|
71
|
+
_h 31
|
72
|
+
_� 30
|
73
|
+
ta 30
|
74
|
+
na 29
|
75
|
+
en 29
|
76
|
+
�u 29
|
77
|
+
_m 29
|
78
|
+
_og_ 29
|
79
|
+
_og 29
|
80
|
+
ti 28
|
81
|
+
la 28
|
82
|
+
lu 28
|
83
|
+
ri 28
|
84
|
+
ur_ 27
|
85
|
+
� 26
|
86
|
+
ar_ 26
|
87
|
+
�i 25
|
88
|
+
t_ 25
|
89
|
+
_a�_ 25
|
90
|
+
._ 25
|
91
|
+
_ve 24
|
92
|
+
_b 24
|
93
|
+
ra 24
|
94
|
+
ng 24
|
95
|
+
nd 24
|
96
|
+
ja 24
|
97
|
+
r� 23
|
98
|
+
ki 23
|
99
|
+
kk 23
|
100
|
+
ir_ 22
|
101
|
+
i�_ 22
|
102
|
+
sl 21
|
103
|
+
ef 21
|
104
|
+
_�_ 21
|
105
|
+
tu 20
|
106
|
+
_u 20
|
107
|
+
ku 20
|
108
|
+
em 20
|
109
|
+
_t 20
|
110
|
+
il 19
|
111
|
+
inn 19
|
112
|
+
se 19
|
113
|
+
sk 19
|
114
|
+
_l 18
|
115
|
+
� 18
|
116
|
+
_g 18
|
117
|
+
_n 18
|
118
|
+
ga 18
|
119
|
+
ver 18
|
120
|
+
�a 18
|
121
|
+
ek 17
|
122
|
+
ni 17
|
123
|
+
af 17
|
124
|
+
num 16
|
125
|
+
sem 16
|
126
|
+
eg 16
|
127
|
+
ag 16
|
128
|
+
am 15
|
129
|
+
rf 15
|
130
|
+
em_ 15
|
131
|
+
sem_ 15
|
132
|
+
gu 15
|
133
|
+
, 15
|
134
|
+
gi 15
|
135
|
+
_er 15
|
136
|
+
da 15
|
137
|
+
mi 15
|
138
|
+
ka 15
|
139
|
+
es 15
|
140
|
+
�k 14
|
141
|
+
�ur 14
|
142
|
+
l� 14
|
143
|
+
�e 14
|
144
|
+
b� 14
|
145
|
+
yr 14
|
146
|
+
nn_ 14
|
147
|
+
_ver 14
|
148
|
+
_se 14
|
149
|
+
,_ 14
|
150
|
+
nar 14
|
151
|
+
j� 14
|
152
|
+
ll 13
|
153
|
+
re 13
|
154
|
+
is 13
|
155
|
+
_sem 13
|
156
|
+
vi 13
|
157
|
+
_sem_ 13
|
158
|
+
li 13
|
159
|
+
al 13
|
160
|
+
�g 13
|
161
|
+
S 13
|
162
|
+
u� 13
|
163
|
+
fl 13
|
164
|
+
tt 13
|
165
|
+
l_ 13
|
166
|
+
ge 13
|
167
|
+
_�e 13
|
168
|
+
ne 13
|
169
|
+
s_ 12
|
170
|
+
he 12
|
171
|
+
me 12
|
172
|
+
inu 12
|
173
|
+
ki_ 12
|
174
|
+
ha 12
|
175
|
+
ru 12
|
176
|
+
�k 12
|
177
|
+
ey 12
|
178
|
+
te 12
|
179
|
+
fr 12
|
180
|
+
_k 12
|
181
|
+
ekk 12
|
182
|
+
fyrir 11
|
183
|
+
yrir 11
|
184
|
+
us 11
|
185
|
+
fyr 11
|
186
|
+
fy 11
|
187
|
+
di 11
|
188
|
+
ju 11
|
189
|
+
yri 11
|
190
|
+
�s 11
|
191
|
+
ma 11
|
192
|
+
num_ 11
|
193
|
+
slu 11
|
194
|
+
er� 11
|
195
|
+
rir 11
|
196
|
+
fyri 11
|
197
|
+
rs 11
|
198
|
+
_mi 10
|
199
|
+
_�a 10
|
200
|
+
le 10
|
201
|
+
_ha 10
|
202
|
+
�a 10
|
203
|
+
kj 10
|
204
|
+
pp 10
|
205
|
+
fj 10
|
206
|
+
or 10
|
207
|
+
arf 10
|
208
|
+
_he 10
|
209
|
+
rn 10
|
210
|
+
ekki 10
|
211
|
+
_ek 10
|
212
|
+
si 10
|
213
|
+
kki 10
|
214
|
+
_ekk 10
|
215
|
+
f_ 10
|
216
|
+
ko 10
|
217
|
+
il_ 10
|
218
|
+
fu 10
|
219
|
+
et 10
|
220
|
+
_ekki 10
|
221
|
+
r�u 10
|
222
|
+
ns 10
|
223
|
+
�i_ 10
|
224
|
+
er_ 9
|
225
|
+
ann 9
|
226
|
+
_st 9
|
227
|
+
gn 9
|
228
|
+
av 9
|
229
|
+
_ti 9
|
230
|
+
ekki_ 9
|
231
|
+
kur 9
|
232
|
+
_um 9
|
233
|
+
kki_ 9
|
234
|
+
K 9
|
235
|
+
til_ 9
|
236
|
+
_er_ 9
|
237
|
+
nni 9
|
238
|
+
_til_ 9
|
239
|
+
sa 9
|
240
|
+
ta_ 9
|
241
|
+
v� 9
|
242
|
+
_til 9
|
243
|
+
f� 9
|
244
|
+
til 9
|
245
|
+
� 9
|
246
|
+
u�u 8
|
247
|
+
�a_ 8
|
248
|
+
e� 8
|
249
|
+
hef 8
|
250
|
+
_ei 8
|
251
|
+
an_ 8
|
252
|
+
ut 8
|
253
|
+
G 8
|
254
|
+
ss 8
|
255
|
+
nda 8
|
256
|
+
ik 8
|
257
|
+
H 8
|
258
|
+
_S 8
|
259
|
+
du 8
|
260
|
+
ing 8
|
261
|
+
tu_ 8
|
262
|
+
�r 8
|
263
|
+
l�g 8
|
264
|
+
_en 8
|
265
|
+
va 8
|
266
|
+
_vi 8
|
267
|
+
kt 8
|
268
|
+
stu 8
|
269
|
+
st_ 8
|
270
|
+
�t 8
|
271
|
+
nes 8
|
272
|
+
_sk 8
|
273
|
+
_me 8
|
274
|
+
fa 8
|
275
|
+
ngi 8
|
276
|
+
a�i 8
|
277
|
+
�n 8
|
278
|
+
fe 8
|
279
|
+
ru_ 8
|
280
|
+
_um_ 8
|
281
|
+
gr 8
|
282
|
+
it 8
|
283
|
+
ein 7
|
284
|
+
as 7
|
285
|
+
f�k 7
|
286
|
+
_G 7
|
287
|
+
_H 7
|
288
|
+
_� 7
|
289
|
+
�kk 7
|
290
|
+
ei� 7
|
291
|
+
av� 7
|
292
|
+
lu_ 7
|
293
|
+
jar 7
|
294
|
+
rt 7
|
295
|
+
gl 7
|
296
|
+
r�ur 7
|
297
|
+
eru_ 7
|
298
|
+
_fj 7
|
299
|
+
rl 7
|
300
|
+
rk 7
|
301
|
+
ust 7
|
302
|
+
m. 7
|
303
|
+
lj 7
|
304
|
+
_af 7
|
305
|
+
_f� 7
|
306
|
+
_fr 7
|
307
|
+
br 7
|
308
|
+
und 7
|
309
|
+
eru 7
|
310
|
+
�� 7
|
311
|
+
B 7
|
312
|
+
eng 7
|
313
|
+
er�ur 7
|
314
|
+
kun 7
|
315
|
+
f�kk 7
|
316
|
+
�t 7
|
317
|
+
_hef 7
|
318
|
+
ig 7
|
319
|
+
inni 7
|
320
|
+
_f�kk 7
|
321
|
+
yrir_ 7
|
322
|
+
gre 7
|
323
|
+
�ar 7
|
324
|
+
�l 7
|
325
|
+
ga_ 7
|
326
|
+
rir_ 7
|
327
|
+
_f�k 7
|
328
|
+
fn 7
|
329
|
+
av�k 7
|
330
|
+
un_ 7
|
331
|
+
nar_ 7
|
332
|
+
en_ 7
|
333
|
+
fi 7
|
334
|
+
_b� 7
|
335
|
+
el 7
|
336
|
+
v�k 7
|
337
|
+
r. 7
|
338
|
+
ram 7
|
339
|
+
ri� 7
|
340
|
+
er�u 7
|
341
|
+
_en_ 7
|
342
|
+
ld 7
|
343
|
+
k_ 6
|
344
|
+
enn 6
|
345
|
+
% 6
|
346
|
+
ja_ 6
|
347
|
+
at 6
|
348
|
+
_%_ 6
|
349
|
+
mu 6
|
350
|
+
au 6
|
351
|
+
_ge 6
|
352
|
+
v�kur 6
|
353
|
+
tir 6
|
354
|
+
j� 6
|
355
|
+
i�s 6
|
356
|
+
�r_ 6
|
357
|
+
li� 6
|
358
|
+
�ku 6
|
359
|
+
um. 6
|
360
|
+
v�ku 6
|
361
|
+
tir_ 6
|
362
|
+
av�ku 6
|
363
|
+
ka�i 6
|
364
|
+
�l 6
|
365
|
+
_B 6
|
366
|
+
f� 6
|
367
|
+
nga 6
|
368
|
+
tr 6
|
369
|
+
eit 6
|
370
|
+
eir 6
|
371
|
+
nu� 6
|
372
|
+
nna 6
|
373
|
+
upp 6
|
374
|
+
_upp 6
|
375
|
+
t� 6
|
376
|
+
fra 6
|
377
|
+
yk 6
|
378
|
+
�r 6
|
379
|
+
ra_ 6
|
380
|
+
stu_ 6
|
381
|
+
�n 6
|
382
|
+
tar 6
|
383
|
+
dur 6
|
384
|
+
_�t 6
|
385
|
+
ann_ 6
|
386
|
+
�_ 6
|
387
|
+
dag 6
|
388
|
+
ug 6
|
389
|
+
rst 6
|
390
|
+
" 6
|
391
|
+
ka� 6
|
392
|
+
ys 6
|
393
|
+
_% 6
|
394
|
+
_up 6
|
395
|
+
fur 6
|
396
|
+
R 6
|
397
|
+
tarf 6
|
398
|
+
gar 6
|
399
|
+
up 6
|
400
|
+
sko 6
|