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
|
+
_ 1306
|
2
|
+
e 336
|
3
|
+
i 319
|
4
|
+
a 317
|
5
|
+
o 276
|
6
|
+
n 226
|
7
|
+
z 215
|
8
|
+
r 166
|
9
|
+
w 160
|
10
|
+
y 151
|
11
|
+
s 140
|
12
|
+
c 138
|
13
|
+
t 137
|
14
|
+
d 127
|
15
|
+
k 124
|
16
|
+
p 112
|
17
|
+
ie 108
|
18
|
+
m 101
|
19
|
+
u 97
|
20
|
+
ni 91
|
21
|
+
l 90
|
22
|
+
j 86
|
23
|
+
� 75
|
24
|
+
o_ 73
|
25
|
+
_p 70
|
26
|
+
g 65
|
27
|
+
, 64
|
28
|
+
a_ 63
|
29
|
+
e_ 61
|
30
|
+
b 58
|
31
|
+
,_ 56
|
32
|
+
_w 51
|
33
|
+
_n 49
|
34
|
+
ze 48
|
35
|
+
i_ 46
|
36
|
+
� 45
|
37
|
+
__ 42
|
38
|
+
. 42
|
39
|
+
� 41
|
40
|
+
pr 40
|
41
|
+
na 40
|
42
|
+
sz 39
|
43
|
+
cz 39
|
44
|
+
nie 37
|
45
|
+
wi 37
|
46
|
+
y_ 36
|
47
|
+
_s 36
|
48
|
+
rz 35
|
49
|
+
_z 35
|
50
|
+
an 34
|
51
|
+
_d 33
|
52
|
+
en 32
|
53
|
+
st 32
|
54
|
+
ie_ 32
|
55
|
+
za 32
|
56
|
+
ra 32
|
57
|
+
ow 31
|
58
|
+
ej 31
|
59
|
+
h 31
|
60
|
+
_pr 30
|
61
|
+
zy 30
|
62
|
+
ki 30
|
63
|
+
po 29
|
64
|
+
ro 28
|
65
|
+
do 28
|
66
|
+
� 28
|
67
|
+
eg 28
|
68
|
+
._ 28
|
69
|
+
ch 28
|
70
|
+
_t 27
|
71
|
+
� 27
|
72
|
+
ne 27
|
73
|
+
ia 26
|
74
|
+
m_ 26
|
75
|
+
_na 26
|
76
|
+
ko 25
|
77
|
+
_po 25
|
78
|
+
em 25
|
79
|
+
wa 25
|
80
|
+
u_ 24
|
81
|
+
li 24
|
82
|
+
dz 24
|
83
|
+
_k 24
|
84
|
+
_b 24
|
85
|
+
to 23
|
86
|
+
_ni 21
|
87
|
+
ta 21
|
88
|
+
i� 21
|
89
|
+
go 21
|
90
|
+
� 21
|
91
|
+
w_ 21
|
92
|
+
_i 21
|
93
|
+
ci 21
|
94
|
+
yc 21
|
95
|
+
" 20
|
96
|
+
or 20
|
97
|
+
te 20
|
98
|
+
le 20
|
99
|
+
_j 20
|
100
|
+
a� 19
|
101
|
+
j_ 19
|
102
|
+
P 19
|
103
|
+
nie_ 19
|
104
|
+
re 19
|
105
|
+
wy 19
|
106
|
+
_o 19
|
107
|
+
al 19
|
108
|
+
ego 19
|
109
|
+
cze 18
|
110
|
+
_nie 18
|
111
|
+
aw 18
|
112
|
+
�o 18
|
113
|
+
ac 18
|
114
|
+
ej_ 18
|
115
|
+
ani 18
|
116
|
+
sk 18
|
117
|
+
ar 17
|
118
|
+
zi 17
|
119
|
+
_w_ 17
|
120
|
+
rze 17
|
121
|
+
_i_ 17
|
122
|
+
by 17
|
123
|
+
ak 17
|
124
|
+
on 16
|
125
|
+
ego_ 16
|
126
|
+
z_ 16
|
127
|
+
ka 16
|
128
|
+
ty 16
|
129
|
+
go_ 16
|
130
|
+
es 16
|
131
|
+
mi 16
|
132
|
+
dzi 16
|
133
|
+
_do 16
|
134
|
+
_m 16
|
135
|
+
�_ 16
|
136
|
+
je 16
|
137
|
+
kie 16
|
138
|
+
prz 15
|
139
|
+
� 15
|
140
|
+
zie 15
|
141
|
+
_r 15
|
142
|
+
S 15
|
143
|
+
_za 15
|
144
|
+
do_ 15
|
145
|
+
om 15
|
146
|
+
dzie 15
|
147
|
+
wie 15
|
148
|
+
�w 15
|
149
|
+
am 14
|
150
|
+
ec 14
|
151
|
+
eni 14
|
152
|
+
ny 14
|
153
|
+
W 14
|
154
|
+
- 14
|
155
|
+
_prz 14
|
156
|
+
�a 14
|
157
|
+
ych 14
|
158
|
+
el 14
|
159
|
+
�e 14
|
160
|
+
em_ 14
|
161
|
+
ic 14
|
162
|
+
na_ 14
|
163
|
+
de 13
|
164
|
+
_do_ 13
|
165
|
+
f 13
|
166
|
+
ez 13
|
167
|
+
er 13
|
168
|
+
pra 13
|
169
|
+
ws 13
|
170
|
+
zc 13
|
171
|
+
ed 13
|
172
|
+
�_ 13
|
173
|
+
� 13
|
174
|
+
ym 13
|
175
|
+
ek 13
|
176
|
+
nej 12
|
177
|
+
pa 12
|
178
|
+
to_ 12
|
179
|
+
dn 12
|
180
|
+
ob 12
|
181
|
+
�e_ 12
|
182
|
+
_c 12
|
183
|
+
as 12
|
184
|
+
zn 12
|
185
|
+
_wy 12
|
186
|
+
owa 12
|
187
|
+
ol 12
|
188
|
+
ja 12
|
189
|
+
od 12
|
190
|
+
pi 12
|
191
|
+
ce 12
|
192
|
+
in 11
|
193
|
+
wo 11
|
194
|
+
ok 11
|
195
|
+
_wi 11
|
196
|
+
prze 11
|
197
|
+
zcz 11
|
198
|
+
tr 11
|
199
|
+
ys 11
|
200
|
+
A 11
|
201
|
+
h_ 11
|
202
|
+
no 11
|
203
|
+
-_ 11
|
204
|
+
i, 11
|
205
|
+
ch_ 11
|
206
|
+
i,_ 11
|
207
|
+
dy 11
|
208
|
+
aj 11
|
209
|
+
nt 10
|
210
|
+
T 10
|
211
|
+
ma 10
|
212
|
+
ad 10
|
213
|
+
we 10
|
214
|
+
cj 10
|
215
|
+
e, 10
|
216
|
+
_u 10
|
217
|
+
ent 10
|
218
|
+
szc 10
|
219
|
+
is 10
|
220
|
+
ku 10
|
221
|
+
ski 10
|
222
|
+
iej 10
|
223
|
+
_P 10
|
224
|
+
_prze 10
|
225
|
+
og 10
|
226
|
+
ln 10
|
227
|
+
rzy 10
|
228
|
+
ud 10
|
229
|
+
Po 10
|
230
|
+
nia 10
|
231
|
+
_� 10
|
232
|
+
_l 10
|
233
|
+
k_ 10
|
234
|
+
�_ 10
|
235
|
+
at 10
|
236
|
+
y� 9
|
237
|
+
_S 9
|
238
|
+
_nie_ 9
|
239
|
+
da 9
|
240
|
+
tw 9
|
241
|
+
_je 9
|
242
|
+
us 9
|
243
|
+
_�e 9
|
244
|
+
szcz 9
|
245
|
+
ot 9
|
246
|
+
_" 9
|
247
|
+
�_ 9
|
248
|
+
si 9
|
249
|
+
gr 9
|
250
|
+
_z_ 9
|
251
|
+
_to_ 9
|
252
|
+
_g 9
|
253
|
+
my 9
|
254
|
+
e,_ 9
|
255
|
+
_�e_ 9
|
256
|
+
_to 9
|
257
|
+
_na_ 9
|
258
|
+
ru 9
|
259
|
+
N 8
|
260
|
+
�y 8
|
261
|
+
�s 8
|
262
|
+
os 8
|
263
|
+
ga 8
|
264
|
+
nej_ 8
|
265
|
+
ym_ 8
|
266
|
+
esz 8
|
267
|
+
ap 8
|
268
|
+
ia_ 8
|
269
|
+
pan 8
|
270
|
+
_a 8
|
271
|
+
kt 8
|
272
|
+
zcze 8
|
273
|
+
by_ 8
|
274
|
+
neg 8
|
275
|
+
_by 8
|
276
|
+
nego 8
|
277
|
+
wsk 8
|
278
|
+
�o_ 8
|
279
|
+
praw 8
|
280
|
+
la 8
|
281
|
+
pre 8
|
282
|
+
a� 8
|
283
|
+
_si 8
|
284
|
+
t� 8
|
285
|
+
raw 8
|
286
|
+
gi 7
|
287
|
+
ieg 7
|
288
|
+
ry 7
|
289
|
+
iu 7
|
290
|
+
_te 7
|
291
|
+
edn 7
|
292
|
+
_W 7
|
293
|
+
si� 7
|
294
|
+
skie 7
|
295
|
+
u� 7
|
296
|
+
G 7
|
297
|
+
_- 7
|
298
|
+
rac 7
|
299
|
+
Z 7
|
300
|
+
_-_ 7
|
301
|
+
a� 7
|
302
|
+
o� 7
|
303
|
+
et 7
|
304
|
+
bi 7
|
305
|
+
�d 7
|
306
|
+
_ro 7
|
307
|
+
li_ 7
|
308
|
+
I 7
|
309
|
+
icz 7
|
310
|
+
tem 7
|
311
|
+
_ja 7
|
312
|
+
�u 7
|
313
|
+
lu 7
|
314
|
+
nia_ 7
|
315
|
+
�_ 7
|
316
|
+
sp 7
|
317
|
+
_ty 7
|
318
|
+
K 7
|
319
|
+
cie 7
|
320
|
+
_sz 7
|
321
|
+
R 7
|
322
|
+
_pra 7
|
323
|
+
bo 7
|
324
|
+
? 7
|
325
|
+
_si� 7
|
326
|
+
_kt 7
|
327
|
+
tu 7
|
328
|
+
iel 7
|
329
|
+
O 7
|
330
|
+
ych_ 7
|
331
|
+
ko_ 7
|
332
|
+
zy_ 7
|
333
|
+
a�_ 6
|
334
|
+
_sp 6
|
335
|
+
�dz 6
|
336
|
+
czy 6
|
337
|
+
no_ 6
|
338
|
+
_ob 6
|
339
|
+
ni_ 6
|
340
|
+
usz 6
|
341
|
+
s� 6
|
342
|
+
_kt� 6
|
343
|
+
io 6
|
344
|
+
lne 6
|
345
|
+
kt�r 6
|
346
|
+
ba 6
|
347
|
+
yt 6
|
348
|
+
il 6
|
349
|
+
yb 6
|
350
|
+
ze_ 6
|
351
|
+
ien 6
|
352
|
+
owi 6
|
353
|
+
op 6
|
354
|
+
un 6
|
355
|
+
dr 6
|
356
|
+
�c 6
|
357
|
+
naj 6
|
358
|
+
_ko 6
|
359
|
+
m� 6
|
360
|
+
kt� 6
|
361
|
+
i�_ 6
|
362
|
+
iem 6
|
363
|
+
uk 6
|
364
|
+
nic 6
|
365
|
+
ku_ 6
|
366
|
+
iego 6
|
367
|
+
_kt�r 6
|
368
|
+
�a 6
|
369
|
+
J 6
|
370
|
+
be 6
|
371
|
+
mo 6
|
372
|
+
yd 6
|
373
|
+
zen 6
|
374
|
+
aln 6
|
375
|
+
dni 6
|
376
|
+
�d 6
|
377
|
+
szcze 6
|
378
|
+
oz 6
|
379
|
+
�r 6
|
380
|
+
jak 6
|
381
|
+
stw 6
|
382
|
+
ji 6
|
383
|
+
wski 6
|
384
|
+
zu 6
|
385
|
+
oc 6
|
386
|
+
B 6
|
387
|
+
den 6
|
388
|
+
e� 6
|
389
|
+
dent 6
|
390
|
+
ali 6
|
391
|
+
mie 6
|
392
|
+
y. 6
|
393
|
+
nego_ 6
|
394
|
+
_J 6
|
395
|
+
W_ 6
|
396
|
+
t�r 6
|
397
|
+
nd 6
|
398
|
+
by� 6
|
399
|
+
czn 6
|
400
|
+
a, 6
|