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
|
+
_ 1444
|
2
|
+
e 430
|
3
|
+
a 407
|
4
|
+
o 348
|
5
|
+
i 340
|
6
|
+
n 282
|
7
|
+
r 204
|
8
|
+
s 198
|
9
|
+
l 197
|
10
|
+
t 175
|
11
|
+
j 171
|
12
|
+
v 148
|
13
|
+
k 146
|
14
|
+
d 137
|
15
|
+
e_ 121
|
16
|
+
z 119
|
17
|
+
y 119
|
18
|
+
p 117
|
19
|
+
a_ 105
|
20
|
+
m 97
|
21
|
+
c 89
|
22
|
+
_s 88
|
23
|
+
o_ 84
|
24
|
+
je 78
|
25
|
+
i_ 73
|
26
|
+
cy 70
|
27
|
+
_p 69
|
28
|
+
_n 69
|
29
|
+
u 61
|
30
|
+
b 60
|
31
|
+
, 58
|
32
|
+
_v 56
|
33
|
+
st 53
|
34
|
+
na 53
|
35
|
+
,_ 52
|
36
|
+
ra 51
|
37
|
+
ni 50
|
38
|
+
_j 49
|
39
|
+
_z 48
|
40
|
+
g 48
|
41
|
+
je_ 47
|
42
|
+
al 46
|
43
|
+
_je 45
|
44
|
+
. 45
|
45
|
+
se 44
|
46
|
+
in 44
|
47
|
+
po 43
|
48
|
+
h 42
|
49
|
+
la 41
|
50
|
+
el 40
|
51
|
+
no 40
|
52
|
+
ye 39
|
53
|
+
_k 38
|
54
|
+
ti 38
|
55
|
+
il 37
|
56
|
+
en 37
|
57
|
+
_je_ 36
|
58
|
+
re 36
|
59
|
+
n_ 35
|
60
|
+
ne 35
|
61
|
+
ko 34
|
62
|
+
pr 34
|
63
|
+
lo 33
|
64
|
+
va 33
|
65
|
+
de 33
|
66
|
+
ja 33
|
67
|
+
ov 31
|
68
|
+
_po 31
|
69
|
+
ka 31
|
70
|
+
ve 31
|
71
|
+
_na 31
|
72
|
+
._ 31
|
73
|
+
_i 30
|
74
|
+
le 30
|
75
|
+
_d 30
|
76
|
+
ri 29
|
77
|
+
an 29
|
78
|
+
nj 29
|
79
|
+
za 29
|
80
|
+
te 28
|
81
|
+
li 28
|
82
|
+
aj 28
|
83
|
+
_m 28
|
84
|
+
od 28
|
85
|
+
zy 28
|
86
|
+
l_ 27
|
87
|
+
et 27
|
88
|
+
_se 27
|
89
|
+
_o 26
|
90
|
+
_t 26
|
91
|
+
ro 25
|
92
|
+
ek 25
|
93
|
+
da 25
|
94
|
+
ih 24
|
95
|
+
ed 24
|
96
|
+
v_ 24
|
97
|
+
_b 24
|
98
|
+
yi 23
|
99
|
+
to 23
|
100
|
+
oc 23
|
101
|
+
ocy 23
|
102
|
+
ad 22
|
103
|
+
_pr 22
|
104
|
+
se_ 22
|
105
|
+
es 21
|
106
|
+
_za 21
|
107
|
+
so 21
|
108
|
+
_se_ 21
|
109
|
+
_r 21
|
110
|
+
tr 20
|
111
|
+
ih_ 20
|
112
|
+
ji 20
|
113
|
+
ar 20
|
114
|
+
h_ 20
|
115
|
+
em 20
|
116
|
+
ob 20
|
117
|
+
_v_ 19
|
118
|
+
is 19
|
119
|
+
ic 19
|
120
|
+
ya 19
|
121
|
+
az 19
|
122
|
+
lo_ 19
|
123
|
+
r_ 18
|
124
|
+
er 18
|
125
|
+
cye 18
|
126
|
+
la_ 18
|
127
|
+
_in 18
|
128
|
+
mo 18
|
129
|
+
ak 18
|
130
|
+
ta 18
|
131
|
+
iz 18
|
132
|
+
lj 17
|
133
|
+
mi 17
|
134
|
+
ki 17
|
135
|
+
in_ 17
|
136
|
+
_ne 17
|
137
|
+
on 17
|
138
|
+
as 17
|
139
|
+
_in_ 17
|
140
|
+
ga 17
|
141
|
+
os 17
|
142
|
+
sy 17
|
143
|
+
bi 17
|
144
|
+
ik 16
|
145
|
+
ot 16
|
146
|
+
ns 16
|
147
|
+
pre 16
|
148
|
+
ec 16
|
149
|
+
og 16
|
150
|
+
pa 16
|
151
|
+
na_ 15
|
152
|
+
m_ 15
|
153
|
+
_so 15
|
154
|
+
no_ 15
|
155
|
+
sa 15
|
156
|
+
kr 15
|
157
|
+
at 15
|
158
|
+
u_ 15
|
159
|
+
ol 15
|
160
|
+
av 15
|
161
|
+
or 15
|
162
|
+
so_ 15
|
163
|
+
zye 14
|
164
|
+
dn 14
|
165
|
+
im 14
|
166
|
+
j_ 14
|
167
|
+
di 14
|
168
|
+
ecy 14
|
169
|
+
vo 14
|
170
|
+
yn 14
|
171
|
+
cyi 14
|
172
|
+
nje 14
|
173
|
+
t_ 14
|
174
|
+
om 14
|
175
|
+
ev 13
|
176
|
+
raz 13
|
177
|
+
ke 13
|
178
|
+
ins 13
|
179
|
+
me 13
|
180
|
+
ye_ 13
|
181
|
+
_pre 13
|
182
|
+
i, 13
|
183
|
+
ne_ 13
|
184
|
+
go 13
|
185
|
+
ap 13
|
186
|
+
z_ 13
|
187
|
+
ir 13
|
188
|
+
_bi 13
|
189
|
+
ez 13
|
190
|
+
_ve 13
|
191
|
+
do 12
|
192
|
+
sto 12
|
193
|
+
cya 12
|
194
|
+
eg 12
|
195
|
+
vi 12
|
196
|
+
ij 12
|
197
|
+
ja_ 12
|
198
|
+
ova 12
|
199
|
+
li_ 12
|
200
|
+
bil 12
|
201
|
+
ok 12
|
202
|
+
- 12
|
203
|
+
ko_ 12
|
204
|
+
ti_ 12
|
205
|
+
_ko 12
|
206
|
+
_st 12
|
207
|
+
_na_ 12
|
208
|
+
i,_ 12
|
209
|
+
a, 12
|
210
|
+
_bil 11
|
211
|
+
elo 11
|
212
|
+
_ra 11
|
213
|
+
_ni 11
|
214
|
+
_c 11
|
215
|
+
jo 11
|
216
|
+
ilo 11
|
217
|
+
ala 11
|
218
|
+
da_ 11
|
219
|
+
ni_ 11
|
220
|
+
cyn 11
|
221
|
+
nst 11
|
222
|
+
_iz 11
|
223
|
+
_so_ 11
|
224
|
+
del 11
|
225
|
+
sk 11
|
226
|
+
ga_ 11
|
227
|
+
__ 11
|
228
|
+
nsto 10
|
229
|
+
_g 10
|
230
|
+
inst 10
|
231
|
+
insto 10
|
232
|
+
ala_ 10
|
233
|
+
ston 10
|
234
|
+
_da 10
|
235
|
+
eti 10
|
236
|
+
un 10
|
237
|
+
nston 10
|
238
|
+
Wins 10
|
239
|
+
Wi 10
|
240
|
+
_mo 10
|
241
|
+
Winst 10
|
242
|
+
ost 10
|
243
|
+
Win 10
|
244
|
+
ton 10
|
245
|
+
ln 10
|
246
|
+
anj 10
|
247
|
+
am 10
|
248
|
+
it 10
|
249
|
+
aj_ 10
|
250
|
+
W 10
|
251
|
+
_l 10
|
252
|
+
ac 10
|
253
|
+
ali 10
|
254
|
+
yal 10
|
255
|
+
le_ 9
|
256
|
+
nic 9
|
257
|
+
il_ 9
|
258
|
+
em_ 9
|
259
|
+
br 9
|
260
|
+
acy 9
|
261
|
+
rj 9
|
262
|
+
nu 9
|
263
|
+
ilo_ 9
|
264
|
+
jen 9
|
265
|
+
_pa 9
|
266
|
+
kra 9
|
267
|
+
icy 9
|
268
|
+
ce 9
|
269
|
+
al_ 9
|
270
|
+
oz 9
|
271
|
+
elo_ 9
|
272
|
+
pi 9
|
273
|
+
a,_ 8
|
274
|
+
ej 8
|
275
|
+
ran 8
|
276
|
+
ali_ 8
|
277
|
+
imi 8
|
278
|
+
o. 8
|
279
|
+
d_ 8
|
280
|
+
rat 8
|
281
|
+
_zy 8
|
282
|
+
ma 8
|
283
|
+
pe 8
|
284
|
+
yil 8
|
285
|
+
ese 8
|
286
|
+
O 8
|
287
|
+
_ka 8
|
288
|
+
tv 8
|
289
|
+
_do 8
|
290
|
+
ze 8
|
291
|
+
kl 8
|
292
|
+
_cy 8
|
293
|
+
k_ 8
|
294
|
+
vr 8
|
295
|
+
stv 8
|
296
|
+
val 8
|
297
|
+
y_ 8
|
298
|
+
a. 8
|
299
|
+
ist 8
|
300
|
+
ezy 8
|
301
|
+
ah 8
|
302
|
+
_nj 8
|
303
|
+
bo 8
|
304
|
+
var 7
|
305
|
+
cy_ 7
|
306
|
+
pol 7
|
307
|
+
ega 7
|
308
|
+
dr 7
|
309
|
+
sti 7
|
310
|
+
nost 7
|
311
|
+
sed 7
|
312
|
+
I 7
|
313
|
+
ji_ 7
|
314
|
+
str 7
|
315
|
+
eni 7
|
316
|
+
yno 7
|
317
|
+
_od 7
|
318
|
+
za_ 7
|
319
|
+
e,_ 7
|
320
|
+
pri 7
|
321
|
+
o._ 7
|
322
|
+
_de 7
|
323
|
+
_ob 7
|
324
|
+
op 7
|
325
|
+
_kr 7
|
326
|
+
ste 7
|
327
|
+
en_ 7
|
328
|
+
pa_ 7
|
329
|
+
nov 7
|
330
|
+
tak 7
|
331
|
+
kih 7
|
332
|
+
nih 7
|
333
|
+
el_ 7
|
334
|
+
o,_ 7
|
335
|
+
e, 7
|
336
|
+
_le 7
|
337
|
+
_da_ 7
|
338
|
+
_V 7
|
339
|
+
ci 7
|
340
|
+
ep 7
|
341
|
+
S 7
|
342
|
+
kih_ 7
|
343
|
+
ju 7
|
344
|
+
set 7
|
345
|
+
tem 7
|
346
|
+
dno 7
|
347
|
+
nos 7
|
348
|
+
ocye 7
|
349
|
+
V 7
|
350
|
+
cye_ 7
|
351
|
+
o, 7
|
352
|
+
_ko_ 7
|
353
|
+
_pol 6
|
354
|
+
_te 6
|
355
|
+
cyno 6
|
356
|
+
to_ 6
|
357
|
+
T 6
|
358
|
+
or_ 6
|
359
|
+
yno_ 6
|
360
|
+
dese 6
|
361
|
+
ede 6
|
362
|
+
-- 6
|
363
|
+
zap 6
|
364
|
+
tk 6
|
365
|
+
des 6
|
366
|
+
iv 6
|
367
|
+
ecye 6
|
368
|
+
tvar 6
|
369
|
+
_nje 6
|
370
|
+
on_ 6
|
371
|
+
nih_ 6
|
372
|
+
nja 6
|
373
|
+
_a 6
|
374
|
+
va_ 6
|
375
|
+
be 6
|
376
|
+
sn 6
|
377
|
+
ale 6
|
378
|
+
dal 6
|
379
|
+
_re 6
|
380
|
+
_pri 6
|
381
|
+
vs 6
|
382
|
+
_- 6
|
383
|
+
zya 6
|
384
|
+
mog 6
|
385
|
+
nik 6
|
386
|
+
nil 6
|
387
|
+
stvar 6
|
388
|
+
_u 6
|
389
|
+
lad 6
|
390
|
+
gl 6
|
391
|
+
_-- 6
|
392
|
+
_stv 6
|
393
|
+
i. 6
|
394
|
+
vec 6
|
395
|
+
_ta 6
|
396
|
+
et_ 6
|
397
|
+
ved 6
|
398
|
+
ton_ 6
|
399
|
+
si 6
|
400
|
+
er_ 6
|