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
|
+
_ 1474
|
2
|
+
a 538
|
3
|
+
i 304
|
4
|
+
h 268
|
5
|
+
n 236
|
6
|
+
r 190
|
7
|
+
s 181
|
8
|
+
_a 176
|
9
|
+
e 167
|
10
|
+
t 144
|
11
|
+
l 135
|
12
|
+
c 128
|
13
|
+
g 117
|
14
|
+
o 115
|
15
|
+
d 106
|
16
|
+
a_ 100
|
17
|
+
n_ 95
|
18
|
+
m 87
|
19
|
+
u 85
|
20
|
+
an 82
|
21
|
+
� 79
|
22
|
+
� 76
|
23
|
+
b 75
|
24
|
+
ea 74
|
25
|
+
ai 74
|
26
|
+
� 73
|
27
|
+
ch 71
|
28
|
+
_s 68
|
29
|
+
h_ 62
|
30
|
+
ar 56
|
31
|
+
in 55
|
32
|
+
" 54
|
33
|
+
, 53
|
34
|
+
r_ 52
|
35
|
+
. 51
|
36
|
+
_b 50
|
37
|
+
f 48
|
38
|
+
ac 47
|
39
|
+
_a_ 47
|
40
|
+
an_ 47
|
41
|
+
ag 47
|
42
|
+
s_ 46
|
43
|
+
,_ 45
|
44
|
+
ir 44
|
45
|
+
_d 43
|
46
|
+
bh 43
|
47
|
+
ha 43
|
48
|
+
�_ 42
|
49
|
+
th 41
|
50
|
+
ach 40
|
51
|
+
_m 38
|
52
|
+
_an 37
|
53
|
+
_c 36
|
54
|
+
_ag 35
|
55
|
+
_l 35
|
56
|
+
le 34
|
57
|
+
�_ 33
|
58
|
+
il 33
|
59
|
+
na 31
|
60
|
+
is 31
|
61
|
+
id 31
|
62
|
+
� 30
|
63
|
+
_an_ 30
|
64
|
+
g_ 30
|
65
|
+
_t 29
|
66
|
+
l_ 29
|
67
|
+
_bh 28
|
68
|
+
nn 28
|
69
|
+
_i 27
|
70
|
+
T 27
|
71
|
+
ar_ 27
|
72
|
+
p 27
|
73
|
+
mh 27
|
74
|
+
_f 27
|
75
|
+
it 25
|
76
|
+
_g 25
|
77
|
+
am 25
|
78
|
+
�_ 25
|
79
|
+
dh 25
|
80
|
+
ra 24
|
81
|
+
s� 24
|
82
|
+
ei 24
|
83
|
+
�i 24
|
84
|
+
_le 24
|
85
|
+
_s� 23
|
86
|
+
� 23
|
87
|
+
ean 22
|
88
|
+
o_ 22
|
89
|
+
._ 22
|
90
|
+
�a 22
|
91
|
+
he 22
|
92
|
+
e_ 21
|
93
|
+
al 21
|
94
|
+
gu 21
|
95
|
+
us 21
|
96
|
+
ui 21
|
97
|
+
s�_ 21
|
98
|
+
t_ 21
|
99
|
+
_s�_ 20
|
100
|
+
_ch 20
|
101
|
+
ig 20
|
102
|
+
_ar 20
|
103
|
+
_n 20
|
104
|
+
ch_ 19
|
105
|
+
de 19
|
106
|
+
as 19
|
107
|
+
hu 19
|
108
|
+
A 19
|
109
|
+
hai 19
|
110
|
+
oi 19
|
111
|
+
se 18
|
112
|
+
te 18
|
113
|
+
agu 18
|
114
|
+
sa 18
|
115
|
+
agus 18
|
116
|
+
gus 18
|
117
|
+
ir_ 18
|
118
|
+
ach_ 18
|
119
|
+
agus_ 17
|
120
|
+
st 17
|
121
|
+
ua 17
|
122
|
+
ith 17
|
123
|
+
C 17
|
124
|
+
us_ 17
|
125
|
+
gus_ 17
|
126
|
+
ag_ 17
|
127
|
+
_agu 16
|
128
|
+
h� 16
|
129
|
+
ad 16
|
130
|
+
_agus 16
|
131
|
+
ga 16
|
132
|
+
rt 16
|
133
|
+
h� 15
|
134
|
+
tha 15
|
135
|
+
each 15
|
136
|
+
ia 15
|
137
|
+
d_ 15
|
138
|
+
ann 15
|
139
|
+
�i 15
|
140
|
+
na_ 15
|
141
|
+
go 15
|
142
|
+
dh_ 15
|
143
|
+
eac 15
|
144
|
+
_" 14
|
145
|
+
_p 14
|
146
|
+
gh 14
|
147
|
+
_T 14
|
148
|
+
ta 14
|
149
|
+
amh 14
|
150
|
+
re 14
|
151
|
+
at 14
|
152
|
+
M 13
|
153
|
+
_ac 13
|
154
|
+
la 13
|
155
|
+
�o 13
|
156
|
+
ear 13
|
157
|
+
il_ 13
|
158
|
+
nn_ 13
|
159
|
+
go_ 13
|
160
|
+
_ag_ 13
|
161
|
+
hi 13
|
162
|
+
in_ 13
|
163
|
+
eo 13
|
164
|
+
igh 13
|
165
|
+
hea 13
|
166
|
+
h�_ 13
|
167
|
+
ait 13
|
168
|
+
_ar_ 13
|
169
|
+
r� 13
|
170
|
+
ma 12
|
171
|
+
B 12
|
172
|
+
h�i 12
|
173
|
+
inn 12
|
174
|
+
air 12
|
175
|
+
_go 12
|
176
|
+
! 12
|
177
|
+
r, 12
|
178
|
+
- 12
|
179
|
+
: 11
|
180
|
+
_r 11
|
181
|
+
N 11
|
182
|
+
ho 11
|
183
|
+
fa 11
|
184
|
+
_de 11
|
185
|
+
�n 11
|
186
|
+
fh 11
|
187
|
+
rai 11
|
188
|
+
or 11
|
189
|
+
aid 11
|
190
|
+
_go_ 11
|
191
|
+
cha 10
|
192
|
+
_se 10
|
193
|
+
c_ 10
|
194
|
+
aith 10
|
195
|
+
ain 10
|
196
|
+
acha 10
|
197
|
+
h� 10
|
198
|
+
_fh 10
|
199
|
+
om 10
|
200
|
+
ng 10
|
201
|
+
har 10
|
202
|
+
_in 10
|
203
|
+
ann_ 10
|
204
|
+
art 10
|
205
|
+
? 10
|
206
|
+
_� 10
|
207
|
+
F 10
|
208
|
+
sc 10
|
209
|
+
aig 10
|
210
|
+
is_ 10
|
211
|
+
im 9
|
212
|
+
_M 9
|
213
|
+
"_ 9
|
214
|
+
ne 9
|
215
|
+
bh� 9
|
216
|
+
le_ 9
|
217
|
+
eag 9
|
218
|
+
e. 9
|
219
|
+
idh 9
|
220
|
+
ti 9
|
221
|
+
be 9
|
222
|
+
r,_ 9
|
223
|
+
aga 9
|
224
|
+
aigh 9
|
225
|
+
io 9
|
226
|
+
_dh 9
|
227
|
+
si 9
|
228
|
+
i_ 9
|
229
|
+
�an 9
|
230
|
+
_� 9
|
231
|
+
nt 9
|
232
|
+
ht 9
|
233
|
+
idh_ 9
|
234
|
+
th_ 9
|
235
|
+
uil 9
|
236
|
+
ile 9
|
237
|
+
rea 9
|
238
|
+
as_ 9
|
239
|
+
li 9
|
240
|
+
." 8
|
241
|
+
sea 8
|
242
|
+
_m� 8
|
243
|
+
id_ 8
|
244
|
+
chu 8
|
245
|
+
ist 8
|
246
|
+
m� 8
|
247
|
+
hr 8
|
248
|
+
ean_ 8
|
249
|
+
�s 8
|
250
|
+
ca 8
|
251
|
+
ic 8
|
252
|
+
tea 8
|
253
|
+
t� 8
|
254
|
+
s� 8
|
255
|
+
ri 8
|
256
|
+
ail 8
|
257
|
+
bea 8
|
258
|
+
�i 8
|
259
|
+
_s� 8
|
260
|
+
t�_ 8
|
261
|
+
bhe 8
|
262
|
+
on 8
|
263
|
+
hf 8
|
264
|
+
oc 8
|
265
|
+
_C 8
|
266
|
+
hean 8
|
267
|
+
ith_ 8
|
268
|
+
N� 8
|
269
|
+
_ach 8
|
270
|
+
L 7
|
271
|
+
bhf 7
|
272
|
+
hui 7
|
273
|
+
T�_ 7
|
274
|
+
deir_ 7
|
275
|
+
Bh 7
|
276
|
+
mh_ 7
|
277
|
+
�id 7
|
278
|
+
adh 7
|
279
|
+
_bea 7
|
280
|
+
_lei 7
|
281
|
+
eann 7
|
282
|
+
rt_ 7
|
283
|
+
_deir 7
|
284
|
+
lt 7
|
285
|
+
n� 7
|
286
|
+
bh�_ 7
|
287
|
+
mha 7
|
288
|
+
_o 7
|
289
|
+
_dei 7
|
290
|
+
al_ 7
|
291
|
+
_ma 7
|
292
|
+
en 7
|
293
|
+
eir 7
|
294
|
+
eacha 7
|
295
|
+
iste 7
|
296
|
+
deir 7
|
297
|
+
ba 7
|
298
|
+
_na 7
|
299
|
+
ing 7
|
300
|
+
cu 7
|
301
|
+
h� 7
|
302
|
+
seo 7
|
303
|
+
hua 7
|
304
|
+
�n_ 7
|
305
|
+
gh_ 7
|
306
|
+
' 7
|
307
|
+
_bhe 7
|
308
|
+
sean 7
|
309
|
+
," 7
|
310
|
+
eir_ 7
|
311
|
+
igh_ 7
|
312
|
+
_bhf 7
|
313
|
+
cht 7
|
314
|
+
lei 7
|
315
|
+
m_ 7
|
316
|
+
T� 7
|
317
|
+
?" 7
|
318
|
+
ll 7
|
319
|
+
ha_ 7
|
320
|
+
ste 7
|
321
|
+
D 7
|
322
|
+
ana 7
|
323
|
+
dea 7
|
324
|
+
_be 7
|
325
|
+
dei 7
|
326
|
+
rra 6
|
327
|
+
amh_ 6
|
328
|
+
_am 6
|
329
|
+
_mh 6
|
330
|
+
ta_ 6
|
331
|
+
l� 6
|
332
|
+
air_ 6
|
333
|
+
sa_ 6
|
334
|
+
sh 6
|
335
|
+
!_ 6
|
336
|
+
Bh� 6
|
337
|
+
ob 6
|
338
|
+
da 6
|
339
|
+
bhea 6
|
340
|
+
aidh 6
|
341
|
+
u�_ 6
|
342
|
+
uai 6
|
343
|
+
acha_ 6
|
344
|
+
u� 6
|
345
|
+
ois 6
|
346
|
+
eis 6
|
347
|
+
_chu 6
|
348
|
+
�_ 6
|
349
|
+
_at 6
|
350
|
+
_aga 6
|
351
|
+
ic_ 6
|
352
|
+
fe 6
|
353
|
+
I 6
|
354
|
+
adh_ 6
|
355
|
+
arra 6
|
356
|
+
arr 6
|
357
|
+
aidh_ 6
|
358
|
+
_ina_ 6
|
359
|
+
_ina 6
|
360
|
+
Bh�_ 6
|
361
|
+
thair 6
|
362
|
+
_n� 6
|
363
|
+
_br 6
|
364
|
+
�st 6
|
365
|
+
ath 6
|
366
|
+
teach 6
|
367
|
+
thai 6
|
368
|
+
ra_ 6
|
369
|
+
t� 6
|
370
|
+
_ach_ 6
|
371
|
+
_si 6
|
372
|
+
_sc 6
|
373
|
+
tr 6
|
374
|
+
�al 6
|
375
|
+
_sa 6
|
376
|
+
n,_ 6
|
377
|
+
_m�_ 6
|
378
|
+
Ta 6
|
379
|
+
n, 6
|
380
|
+
n. 6
|
381
|
+
cha_ 6
|
382
|
+
ns 6
|
383
|
+
ina_ 6
|
384
|
+
,"_ 6
|
385
|
+
teac 6
|
386
|
+
hair 6
|
387
|
+
os 6
|
388
|
+
dr 6
|
389
|
+
a� 6
|
390
|
+
P 6
|
391
|
+
uil_ 6
|
392
|
+
pa 6
|
393
|
+
a, 6
|
394
|
+
Ch 6
|
395
|
+
_le_ 6
|
396
|
+
ina 6
|
397
|
+
fai 6
|
398
|
+
och 6
|
399
|
+
br 6
|
400
|
+
�il 6
|