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
|
+
_ 1538
|
2
|
+
a 370
|
3
|
+
o 334
|
4
|
+
e 307
|
5
|
+
n 255
|
6
|
+
i 245
|
7
|
+
r 191
|
8
|
+
v 181
|
9
|
+
t 164
|
10
|
+
s 161
|
11
|
+
l 150
|
12
|
+
k 150
|
13
|
+
c 142
|
14
|
+
__ 137
|
15
|
+
u 130
|
16
|
+
p 127
|
17
|
+
d 123
|
18
|
+
y 106
|
19
|
+
a_ 98
|
20
|
+
h 91
|
21
|
+
m 88
|
22
|
+
z 79
|
23
|
+
na 69
|
24
|
+
e_ 63
|
25
|
+
. 62
|
26
|
+
ov 62
|
27
|
+
_p 61
|
28
|
+
j 59
|
29
|
+
_s 54
|
30
|
+
ro 53
|
31
|
+
_v 52
|
32
|
+
po 52
|
33
|
+
b 49
|
34
|
+
ch 46
|
35
|
+
, 46
|
36
|
+
._ 45
|
37
|
+
o_ 45
|
38
|
+
,_ 44
|
39
|
+
v_ 43
|
40
|
+
u_ 42
|
41
|
+
i_ 42
|
42
|
+
en 42
|
43
|
+
_n 41
|
44
|
+
ne 41
|
45
|
+
re 40
|
46
|
+
_z 39
|
47
|
+
la 38
|
48
|
+
an 38
|
49
|
+
st 37
|
50
|
+
_a 36
|
51
|
+
y_ 34
|
52
|
+
vy 33
|
53
|
+
_na 32
|
54
|
+
h_ 32
|
55
|
+
ie 31
|
56
|
+
pr 31
|
57
|
+
od 31
|
58
|
+
ko 30
|
59
|
+
ci 29
|
60
|
+
er 29
|
61
|
+
ch_ 29
|
62
|
+
ti 28
|
63
|
+
_o 27
|
64
|
+
al 27
|
65
|
+
ed 27
|
66
|
+
sk 27
|
67
|
+
ve 26
|
68
|
+
na_ 26
|
69
|
+
or 26
|
70
|
+
ni 26
|
71
|
+
_po 26
|
72
|
+
yc 25
|
73
|
+
_pr 25
|
74
|
+
ac 25
|
75
|
+
ak 25
|
76
|
+
mi 25
|
77
|
+
ny 25
|
78
|
+
_t 25
|
79
|
+
va 25
|
80
|
+
ho 24
|
81
|
+
ra 24
|
82
|
+
in 24
|
83
|
+
to 24
|
84
|
+
ych 24
|
85
|
+
_k 24
|
86
|
+
le 24
|
87
|
+
_m 23
|
88
|
+
_v_ 23
|
89
|
+
ad 23
|
90
|
+
tr 23
|
91
|
+
il 23
|
92
|
+
ka 22
|
93
|
+
no 22
|
94
|
+
li 22
|
95
|
+
si 22
|
96
|
+
ce 22
|
97
|
+
_r 21
|
98
|
+
ia 21
|
99
|
+
sa 20
|
100
|
+
os 20
|
101
|
+
om 20
|
102
|
+
te 20
|
103
|
+
ok 20
|
104
|
+
ych_ 20
|
105
|
+
it 20
|
106
|
+
do 19
|
107
|
+
ta 19
|
108
|
+
ku 19
|
109
|
+
da 19
|
110
|
+
_,_ 18
|
111
|
+
S 18
|
112
|
+
za 18
|
113
|
+
me 18
|
114
|
+
_, 18
|
115
|
+
es 18
|
116
|
+
ej 17
|
117
|
+
ap 17
|
118
|
+
aj 17
|
119
|
+
ov_ 17
|
120
|
+
_na_ 17
|
121
|
+
oc 17
|
122
|
+
ol 16
|
123
|
+
pre 16
|
124
|
+
el 16
|
125
|
+
ky 16
|
126
|
+
ur 16
|
127
|
+
at 16
|
128
|
+
on 16
|
129
|
+
_a_ 16
|
130
|
+
P 16
|
131
|
+
_sa 16
|
132
|
+
av 16
|
133
|
+
_d 15
|
134
|
+
vo 15
|
135
|
+
as 15
|
136
|
+
t_ 15
|
137
|
+
lo 15
|
138
|
+
% 15
|
139
|
+
ic 15
|
140
|
+
_za 15
|
141
|
+
_ro 15
|
142
|
+
ri 15
|
143
|
+
rok 15
|
144
|
+
_c 15
|
145
|
+
nyc 14
|
146
|
+
zi 14
|
147
|
+
ot 14
|
148
|
+
_% 14
|
149
|
+
ke 14
|
150
|
+
ob 14
|
151
|
+
m_ 14
|
152
|
+
nych 14
|
153
|
+
N 14
|
154
|
+
_b 14
|
155
|
+
D 14
|
156
|
+
nych_ 14
|
157
|
+
_pre 14
|
158
|
+
eh 14
|
159
|
+
di 13
|
160
|
+
nu 13
|
161
|
+
ln 13
|
162
|
+
eho 13
|
163
|
+
_vy 13
|
164
|
+
am 13
|
165
|
+
_ak 12
|
166
|
+
) 12
|
167
|
+
sp 12
|
168
|
+
rov 12
|
169
|
+
_u 12
|
170
|
+
co 12
|
171
|
+
zv 12
|
172
|
+
dn 12
|
173
|
+
_do 12
|
174
|
+
nt 12
|
175
|
+
pa 12
|
176
|
+
sa_ 11
|
177
|
+
n_ 11
|
178
|
+
kt 11
|
179
|
+
vi 11
|
180
|
+
ho_ 11
|
181
|
+
ne_ 11
|
182
|
+
l_ 11
|
183
|
+
ovy 11
|
184
|
+
ny_ 11
|
185
|
+
( 11
|
186
|
+
eho_ 11
|
187
|
+
zn 11
|
188
|
+
az 11
|
189
|
+
cen 11
|
190
|
+
ar 11
|
191
|
+
j_ 11
|
192
|
+
_tr 11
|
193
|
+
ej_ 10
|
194
|
+
iv 10
|
195
|
+
ky_ 10
|
196
|
+
pe 10
|
197
|
+
om_ 10
|
198
|
+
_sa_ 10
|
199
|
+
nan 10
|
200
|
+
ek 10
|
201
|
+
k_ 10
|
202
|
+
Na 10
|
203
|
+
nc 10
|
204
|
+
ast 10
|
205
|
+
du 10
|
206
|
+
_N 10
|
207
|
+
_( 10
|
208
|
+
de 10
|
209
|
+
ju 10
|
210
|
+
g 10
|
211
|
+
- 10
|
212
|
+
ik 10
|
213
|
+
ova 10
|
214
|
+
ove 10
|
215
|
+
oz 10
|
216
|
+
R 10
|
217
|
+
tor 9
|
218
|
+
ina 9
|
219
|
+
pl 9
|
220
|
+
uro 9
|
221
|
+
je 9
|
222
|
+
em 9
|
223
|
+
lad 9
|
224
|
+
pod 9
|
225
|
+
V 9
|
226
|
+
_mi 9
|
227
|
+
et 9
|
228
|
+
kl 9
|
229
|
+
cov 9
|
230
|
+
la_ 9
|
231
|
+
ska 9
|
232
|
+
ku_ 9
|
233
|
+
f 9
|
234
|
+
_j 9
|
235
|
+
_P 9
|
236
|
+
r_ 9
|
237
|
+
kov 9
|
238
|
+
_Na 8
|
239
|
+
_h 8
|
240
|
+
ca 8
|
241
|
+
vys 8
|
242
|
+
Po 8
|
243
|
+
_rok 8
|
244
|
+
_S 8
|
245
|
+
uc 8
|
246
|
+
ia_ 8
|
247
|
+
ze 8
|
248
|
+
ep 8
|
249
|
+
est 8
|
250
|
+
_ob 8
|
251
|
+
tu 8
|
252
|
+
ani 8
|
253
|
+
ka_ 8
|
254
|
+
_trh 8
|
255
|
+
ys 8
|
256
|
+
ti_ 8
|
257
|
+
pri 8
|
258
|
+
pred 8
|
259
|
+
_U 8
|
260
|
+
ske 8
|
261
|
+
rh 8
|
262
|
+
sl 8
|
263
|
+
ent 8
|
264
|
+
vn 8
|
265
|
+
_ur 8
|
266
|
+
nej 8
|
267
|
+
M 8
|
268
|
+
U 8
|
269
|
+
_sp 8
|
270
|
+
ie_ 8
|
271
|
+
en_ 8
|
272
|
+
st_ 8
|
273
|
+
red 8
|
274
|
+
trh 8
|
275
|
+
hod 7
|
276
|
+
_akc 7
|
277
|
+
ns 7
|
278
|
+
_zv 7
|
279
|
+
_V 7
|
280
|
+
kci 7
|
281
|
+
_ce 7
|
282
|
+
br 7
|
283
|
+
ec 7
|
284
|
+
z_ 7
|
285
|
+
ost 7
|
286
|
+
nu_ 7
|
287
|
+
ati 7
|
288
|
+
_Po 7
|
289
|
+
akci 7
|
290
|
+
van 7
|
291
|
+
SD 7
|
292
|
+
eni 7
|
293
|
+
ali 7
|
294
|
+
ru 7
|
295
|
+
spo 7
|
296
|
+
_US 7
|
297
|
+
neh 7
|
298
|
+
_ne 7
|
299
|
+
_e 7
|
300
|
+
uj 7
|
301
|
+
kc 7
|
302
|
+
is 7
|
303
|
+
akc 7
|
304
|
+
_akci 7
|
305
|
+
neho 7
|
306
|
+
er_ 7
|
307
|
+
oro 7
|
308
|
+
sti 7
|
309
|
+
_USD 7
|
310
|
+
up 7
|
311
|
+
su 7
|
312
|
+
_l 7
|
313
|
+
_pred 7
|
314
|
+
US 7
|
315
|
+
_uro 7
|
316
|
+
USD 7
|
317
|
+
ud 7
|
318
|
+
mo 7
|
319
|
+
zac 6
|
320
|
+
he 6
|
321
|
+
li_ 6
|
322
|
+
_cen 6
|
323
|
+
ty 6
|
324
|
+
F 6
|
325
|
+
cii 6
|
326
|
+
re_ 6
|
327
|
+
ly 6
|
328
|
+
_me 6
|
329
|
+
ke_ 6
|
330
|
+
ast_ 6
|
331
|
+
-_ 6
|
332
|
+
(_ 6
|
333
|
+
_%. 6
|
334
|
+
V_ 6
|
335
|
+
J 6
|
336
|
+
tre 6
|
337
|
+
otr 6
|
338
|
+
odn 6
|
339
|
+
_pod 6
|
340
|
+
_vo 6
|
341
|
+
alo 6
|
342
|
+
u. 6
|
343
|
+
nov 6
|
344
|
+
ni_ 6
|
345
|
+
roku_ 6
|
346
|
+
oku_ 6
|
347
|
+
id 6
|
348
|
+
cie 6
|
349
|
+
_pl 6
|
350
|
+
nej_ 6
|
351
|
+
iny 6
|
352
|
+
hr 6
|
353
|
+
osl 6
|
354
|
+
us 6
|
355
|
+
mi_ 6
|
356
|
+
sta 6
|
357
|
+
cho 6
|
358
|
+
ja 6
|
359
|
+
ele 6
|
360
|
+
tiv 6
|
361
|
+
iny_ 6
|
362
|
+
nsk 6
|
363
|
+
by 6
|
364
|
+
%. 6
|
365
|
+
ore 6
|
366
|
+
mie 6
|
367
|
+
il_ 6
|
368
|
+
sia 6
|
369
|
+
yr 6
|
370
|
+
eb 6
|
371
|
+
e. 6
|
372
|
+
rod 6
|
373
|
+
_st 6
|
374
|
+
roku 6
|
375
|
+
kon 6
|
376
|
+
_pri 6
|
377
|
+
oku 6
|
378
|
+
ach 6
|
379
|
+
tn 6
|
380
|
+
_ku 6
|
381
|
+
C 6
|
382
|
+
aci 6
|
383
|
+
ri_ 6
|
384
|
+
pos 6
|
385
|
+
por 6
|
386
|
+
ii 6
|
387
|
+
sil 6
|
388
|
+
%._ 5
|
389
|
+
dpo 5
|
390
|
+
A 5
|
391
|
+
neho_ 5
|
392
|
+
_ze 5
|
393
|
+
vl 5
|
394
|
+
vych 5
|
395
|
+
zo 5
|
396
|
+
za_ 5
|
397
|
+
op 5
|
398
|
+
_%._ 5
|
399
|
+
rn 5
|
400
|
+
_- 5
|