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 417
|
3
|
+
o 413
|
4
|
+
i 372
|
5
|
+
e 330
|
6
|
+
n 254
|
7
|
+
s 218
|
8
|
+
j 192
|
9
|
+
t 190
|
10
|
+
u 162
|
11
|
+
r 153
|
12
|
+
d 148
|
13
|
+
l 147
|
14
|
+
a_ 129
|
15
|
+
v 127
|
16
|
+
y 124
|
17
|
+
m 120
|
18
|
+
k 116
|
19
|
+
e_ 116
|
20
|
+
p 107
|
21
|
+
o_ 105
|
22
|
+
je 94
|
23
|
+
c 91
|
24
|
+
z 90
|
25
|
+
i_ 84
|
26
|
+
b 74
|
27
|
+
_s 74
|
28
|
+
, 65
|
29
|
+
g 64
|
30
|
+
_n 60
|
31
|
+
u_ 59
|
32
|
+
_i 59
|
33
|
+
,_ 55
|
34
|
+
_p 55
|
35
|
+
st 55
|
36
|
+
sy 53
|
37
|
+
je_ 53
|
38
|
+
_d 51
|
39
|
+
cy 50
|
40
|
+
ta 49
|
41
|
+
na 48
|
42
|
+
_j 46
|
43
|
+
. 45
|
44
|
+
os 45
|
45
|
+
da 44
|
46
|
+
ko 43
|
47
|
+
_je 42
|
48
|
+
po 42
|
49
|
+
ni 41
|
50
|
+
_u 40
|
51
|
+
bi 39
|
52
|
+
to 38
|
53
|
+
_b 37
|
54
|
+
ti 37
|
55
|
+
no 36
|
56
|
+
_o 36
|
57
|
+
ra 35
|
58
|
+
ne 35
|
59
|
+
an 35
|
60
|
+
_je_ 34
|
61
|
+
en 34
|
62
|
+
is 34
|
63
|
+
re 33
|
64
|
+
la 32
|
65
|
+
yi 32
|
66
|
+
ov 32
|
67
|
+
li 31
|
68
|
+
il 31
|
69
|
+
._ 31
|
70
|
+
vo 30
|
71
|
+
_m 29
|
72
|
+
_po 29
|
73
|
+
m_ 29
|
74
|
+
lo 29
|
75
|
+
_z 28
|
76
|
+
og 28
|
77
|
+
_bi 28
|
78
|
+
iz 28
|
79
|
+
cj 27
|
80
|
+
ja 27
|
81
|
+
ro 27
|
82
|
+
pr 27
|
83
|
+
in 27
|
84
|
+
ij 27
|
85
|
+
oj 27
|
86
|
+
le 26
|
87
|
+
om 26
|
88
|
+
_i_ 26
|
89
|
+
on 26
|
90
|
+
im 26
|
91
|
+
za 25
|
92
|
+
nj 25
|
93
|
+
_k 25
|
94
|
+
es 24
|
95
|
+
_da 24
|
96
|
+
cyi 23
|
97
|
+
od 23
|
98
|
+
va 23
|
99
|
+
av 23
|
100
|
+
ar 22
|
101
|
+
_t 22
|
102
|
+
da_ 22
|
103
|
+
n_ 22
|
104
|
+
na_ 22
|
105
|
+
ka 22
|
106
|
+
ju 22
|
107
|
+
ad 22
|
108
|
+
vi 21
|
109
|
+
it 21
|
110
|
+
ma 21
|
111
|
+
ve 21
|
112
|
+
ed 21
|
113
|
+
_ne 21
|
114
|
+
sa 21
|
115
|
+
se 20
|
116
|
+
ak 20
|
117
|
+
_iz 20
|
118
|
+
zy 20
|
119
|
+
ao 19
|
120
|
+
nu 19
|
121
|
+
al 19
|
122
|
+
mo 19
|
123
|
+
_da_ 19
|
124
|
+
de 19
|
125
|
+
_v 18
|
126
|
+
_za 18
|
127
|
+
h 18
|
128
|
+
tr 18
|
129
|
+
ek 18
|
130
|
+
syt 18
|
131
|
+
lj 18
|
132
|
+
_na 18
|
133
|
+
do 18
|
134
|
+
yt 18
|
135
|
+
to_ 17
|
136
|
+
bil 17
|
137
|
+
ri 17
|
138
|
+
ac 17
|
139
|
+
a, 17
|
140
|
+
ob 17
|
141
|
+
et 16
|
142
|
+
_c 16
|
143
|
+
ye 16
|
144
|
+
ec 16
|
145
|
+
ji 16
|
146
|
+
_u_ 16
|
147
|
+
_pr 16
|
148
|
+
go 16
|
149
|
+
a,_ 16
|
150
|
+
ik 16
|
151
|
+
or 16
|
152
|
+
ot 15
|
153
|
+
ic 15
|
154
|
+
_ko 15
|
155
|
+
ije 15
|
156
|
+
at 15
|
157
|
+
osy 15
|
158
|
+
d_ 15
|
159
|
+
sta 15
|
160
|
+
no_ 15
|
161
|
+
_se 15
|
162
|
+
ost 15
|
163
|
+
sto 15
|
164
|
+
__ 14
|
165
|
+
_r 14
|
166
|
+
koj 14
|
167
|
+
_g 14
|
168
|
+
em 14
|
169
|
+
ih 14
|
170
|
+
_bil 14
|
171
|
+
te 13
|
172
|
+
iv 13
|
173
|
+
sl 13
|
174
|
+
su 13
|
175
|
+
ti_ 13
|
176
|
+
_cy 13
|
177
|
+
mi 13
|
178
|
+
ao_ 13
|
179
|
+
ta_ 13
|
180
|
+
_l 13
|
181
|
+
dn 13
|
182
|
+
ovo 13
|
183
|
+
jo 13
|
184
|
+
me 12
|
185
|
+
pos 12
|
186
|
+
_na_ 12
|
187
|
+
e, 12
|
188
|
+
om_ 12
|
189
|
+
ga 12
|
190
|
+
ol 12
|
191
|
+
h_ 12
|
192
|
+
ki 12
|
193
|
+
_on 12
|
194
|
+
la_ 12
|
195
|
+
im_ 12
|
196
|
+
ih_ 12
|
197
|
+
am 12
|
198
|
+
ut 12
|
199
|
+
up 12
|
200
|
+
lo_ 12
|
201
|
+
az 11
|
202
|
+
_a 11
|
203
|
+
pa 11
|
204
|
+
io 11
|
205
|
+
gl 11
|
206
|
+
_koj 11
|
207
|
+
_sy 11
|
208
|
+
a. 11
|
209
|
+
e,_ 11
|
210
|
+
nje 11
|
211
|
+
as 11
|
212
|
+
_se_ 11
|
213
|
+
_sa 11
|
214
|
+
j_ 11
|
215
|
+
se_ 11
|
216
|
+
li_ 11
|
217
|
+
yn 11
|
218
|
+
gu 10
|
219
|
+
acy 10
|
220
|
+
ist 10
|
221
|
+
aj 10
|
222
|
+
_ni 10
|
223
|
+
nos 10
|
224
|
+
_do 10
|
225
|
+
iti 10
|
226
|
+
ba 10
|
227
|
+
ju_ 10
|
228
|
+
uc 10
|
229
|
+
sti 10
|
230
|
+
io_ 10
|
231
|
+
ima 10
|
232
|
+
ko_ 10
|
233
|
+
jen 10
|
234
|
+
pi 10
|
235
|
+
_pos 9
|
236
|
+
yi_ 9
|
237
|
+
di 9
|
238
|
+
ke 9
|
239
|
+
_is 9
|
240
|
+
er 9
|
241
|
+
e. 9
|
242
|
+
ga_ 9
|
243
|
+
yl 9
|
244
|
+
sk 9
|
245
|
+
nij 9
|
246
|
+
est 9
|
247
|
+
el 8
|
248
|
+
le_ 8
|
249
|
+
ili 8
|
250
|
+
ecy 8
|
251
|
+
sp 8
|
252
|
+
N 8
|
253
|
+
_to 8
|
254
|
+
lik 8
|
255
|
+
iz_ 8
|
256
|
+
ap 8
|
257
|
+
ilo 8
|
258
|
+
_sv 8
|
259
|
+
oc 8
|
260
|
+
ni_ 8
|
261
|
+
_zy 8
|
262
|
+
a._ 8
|
263
|
+
_re 8
|
264
|
+
icy 8
|
265
|
+
ucj 8
|
266
|
+
jao 8
|
267
|
+
anj 8
|
268
|
+
ila 8
|
269
|
+
P 8
|
270
|
+
pre 8
|
271
|
+
_ka 8
|
272
|
+
vr 8
|
273
|
+
enu 8
|
274
|
+
_iz_ 8
|
275
|
+
esy 8
|
276
|
+
zn 8
|
277
|
+
sv 8
|
278
|
+
isy 8
|
279
|
+
z_ 8
|
280
|
+
cje 8
|
281
|
+
on_ 8
|
282
|
+
nije 7
|
283
|
+
t_ 7
|
284
|
+
syto 7
|
285
|
+
pot 7
|
286
|
+
nji 7
|
287
|
+
yu 7
|
288
|
+
_st 7
|
289
|
+
mog 7
|
290
|
+
nu_ 7
|
291
|
+
sam 7
|
292
|
+
u, 7
|
293
|
+
ne_ 7
|
294
|
+
bio_ 7
|
295
|
+
ila_ 7
|
296
|
+
jed 7
|
297
|
+
_syt 7
|
298
|
+
bio 7
|
299
|
+
edn 7
|
300
|
+
V 7
|
301
|
+
ru 7
|
302
|
+
gov 7
|
303
|
+
odi 7
|
304
|
+
nek 7
|
305
|
+
ren 7
|
306
|
+
be 7
|
307
|
+
ecj 7
|
308
|
+
bila 7
|
309
|
+
_ve 7
|
310
|
+
jim 7
|
311
|
+
T 7
|
312
|
+
jao_ 7
|
313
|
+
dan 7
|
314
|
+
nut 7
|
315
|
+
cyin 7
|
316
|
+
un 7
|
317
|
+
ako 7
|
318
|
+
recy 7
|
319
|
+
ora 7
|
320
|
+
yto 7
|
321
|
+
ije_ 7
|
322
|
+
ok 7
|
323
|
+
ovi 7
|
324
|
+
S 7
|
325
|
+
eg 7
|
326
|
+
id 7
|
327
|
+
pro 7
|
328
|
+
oje 7
|
329
|
+
kom 7
|
330
|
+
du 7
|
331
|
+
rec 7
|
332
|
+
yin 7
|
333
|
+
_mo 7
|
334
|
+
ogu 6
|
335
|
+
ma_ 6
|
336
|
+
_no 6
|
337
|
+
govo 6
|
338
|
+
br 6
|
339
|
+
an_ 6
|
340
|
+
_od 6
|
341
|
+
ros 6
|
342
|
+
ocy 6
|
343
|
+
tan 6
|
344
|
+
_su 6
|
345
|
+
_bila 6
|
346
|
+
oje_ 6
|
347
|
+
i, 6
|
348
|
+
e._ 6
|
349
|
+
lic 6
|
350
|
+
su_ 6
|
351
|
+
rat 6
|
352
|
+
uta 6
|
353
|
+
ez 6
|
354
|
+
_rec 6
|
355
|
+
za_ 6
|
356
|
+
_za_ 6
|
357
|
+
jima 6
|
358
|
+
tav 6
|
359
|
+
zna 6
|
360
|
+
ye_ 6
|
361
|
+
va_ 6
|
362
|
+
bila_ 6
|
363
|
+
_os 6
|
364
|
+
tu 6
|
365
|
+
ata 6
|
366
|
+
I 6
|
367
|
+
cja 6
|
368
|
+
ad_ 6
|
369
|
+
_go 6
|
370
|
+
slo 6
|
371
|
+
tv 6
|
372
|
+
ogl 6
|
373
|
+
ija 6
|
374
|
+
syl 6
|
375
|
+
dj 6
|
376
|
+
te_ 6
|
377
|
+
vn 6
|
378
|
+
tim 6
|
379
|
+
bilo 6
|
380
|
+
_de 6
|
381
|
+
iti_ 6
|
382
|
+
ka_ 6
|
383
|
+
vo_ 6
|
384
|
+
vl 6
|
385
|
+
y_ 6
|
386
|
+
_S 6
|
387
|
+
dno 6
|
388
|
+
_tr 6
|
389
|
+
ja_ 6
|
390
|
+
cyi_ 6
|
391
|
+
ya 6
|
392
|
+
_nije 6
|
393
|
+
ita 6
|
394
|
+
renu 6
|
395
|
+
lje 6
|
396
|
+
oj_ 6
|
397
|
+
_P 6
|
398
|
+
i,_ 6
|
399
|
+
zye 6
|
400
|
+
ilo_ 6
|