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
|
+
_ 1413
|
2
|
+
a 829
|
3
|
+
n 397
|
4
|
+
e 319
|
5
|
+
i 290
|
6
|
+
an 239
|
7
|
+
k 213
|
8
|
+
d 188
|
9
|
+
u 174
|
10
|
+
r 172
|
11
|
+
t 168
|
12
|
+
g 162
|
13
|
+
m 159
|
14
|
+
s 128
|
15
|
+
l 126
|
16
|
+
__ 123
|
17
|
+
p 123
|
18
|
+
n_ 120
|
19
|
+
ng 114
|
20
|
+
b 108
|
21
|
+
da 106
|
22
|
+
an_ 105
|
23
|
+
h 102
|
24
|
+
a_ 93
|
25
|
+
_d 89
|
26
|
+
ka 83
|
27
|
+
y 74
|
28
|
+
ang 74
|
29
|
+
en 68
|
30
|
+
ya 64
|
31
|
+
la 62
|
32
|
+
ah 62
|
33
|
+
er 61
|
34
|
+
i_ 60
|
35
|
+
_m 60
|
36
|
+
o 59
|
37
|
+
. 59
|
38
|
+
___ 56
|
39
|
+
ar 55
|
40
|
+
____ 54
|
41
|
+
me 53
|
42
|
+
at 53
|
43
|
+
di 53
|
44
|
+
_____ 52
|
45
|
+
ra 52
|
46
|
+
ng_ 51
|
47
|
+
g_ 51
|
48
|
+
ba 48
|
49
|
+
al 47
|
50
|
+
ak 47
|
51
|
+
ang_ 46
|
52
|
+
_da 45
|
53
|
+
ga 45
|
54
|
+
_k 44
|
55
|
+
ta 44
|
56
|
+
_me 43
|
57
|
+
kan 43
|
58
|
+
_p 42
|
59
|
+
._ 41
|
60
|
+
_b 41
|
61
|
+
ke 40
|
62
|
+
pa 39
|
63
|
+
h_ 38
|
64
|
+
am 37
|
65
|
+
as 36
|
66
|
+
kan_ 36
|
67
|
+
j 36
|
68
|
+
k_ 36
|
69
|
+
_s 36
|
70
|
+
in 35
|
71
|
+
sa 35
|
72
|
+
_di 35
|
73
|
+
se 34
|
74
|
+
pe 34
|
75
|
+
_a 33
|
76
|
+
yang 33
|
77
|
+
yan 33
|
78
|
+
em 32
|
79
|
+
dan 32
|
80
|
+
ti 32
|
81
|
+
c 32
|
82
|
+
ha 31
|
83
|
+
it 30
|
84
|
+
be 30
|
85
|
+
_y 29
|
86
|
+
_t 29
|
87
|
+
_yang 29
|
88
|
+
el 29
|
89
|
+
_yan 29
|
90
|
+
ah_ 29
|
91
|
+
_ya 29
|
92
|
+
ala 28
|
93
|
+
ad 28
|
94
|
+
tu 28
|
95
|
+
ik 28
|
96
|
+
nd 27
|
97
|
+
yang_ 27
|
98
|
+
men 26
|
99
|
+
_ke 26
|
100
|
+
un 25
|
101
|
+
ma 25
|
102
|
+
t_ 25
|
103
|
+
_pe 25
|
104
|
+
ia 24
|
105
|
+
ri 24
|
106
|
+
li 24
|
107
|
+
ny 24
|
108
|
+
_dan 24
|
109
|
+
na 23
|
110
|
+
S 23
|
111
|
+
, 23
|
112
|
+
ada 23
|
113
|
+
r_ 22
|
114
|
+
,_ 22
|
115
|
+
te 22
|
116
|
+
ja 22
|
117
|
+
nga 22
|
118
|
+
_men 21
|
119
|
+
eng 21
|
120
|
+
ep 21
|
121
|
+
ap 21
|
122
|
+
nya 21
|
123
|
+
_se 21
|
124
|
+
_i 20
|
125
|
+
u_ 20
|
126
|
+
mb 20
|
127
|
+
si 20
|
128
|
+
m_ 19
|
129
|
+
w 19
|
130
|
+
_ba 19
|
131
|
+
et 19
|
132
|
+
aka 19
|
133
|
+
ber 18
|
134
|
+
dan_ 18
|
135
|
+
uk 18
|
136
|
+
ua 18
|
137
|
+
nda 18
|
138
|
+
ara 18
|
139
|
+
wa 17
|
140
|
+
M 17
|
141
|
+
ran 17
|
142
|
+
gk 17
|
143
|
+
ai 17
|
144
|
+
per 17
|
145
|
+
at_ 17
|
146
|
+
ek 17
|
147
|
+
ata 17
|
148
|
+
ngk 17
|
149
|
+
aha 17
|
150
|
+
ak_ 17
|
151
|
+
pu 17
|
152
|
+
mem 16
|
153
|
+
lam 16
|
154
|
+
_be 16
|
155
|
+
_dan_ 16
|
156
|
+
ir 16
|
157
|
+
gan 15
|
158
|
+
de 15
|
159
|
+
_mem 15
|
160
|
+
end 15
|
161
|
+
id 15
|
162
|
+
da_ 15
|
163
|
+
ur 15
|
164
|
+
eb 15
|
165
|
+
dal 15
|
166
|
+
lah 15
|
167
|
+
ngan 15
|
168
|
+
am_ 15
|
169
|
+
- 14
|
170
|
+
gi 14
|
171
|
+
le 14
|
172
|
+
ada_ 14
|
173
|
+
pad 14
|
174
|
+
pada 14
|
175
|
+
asa 14
|
176
|
+
tan 14
|
177
|
+
ki 14
|
178
|
+
dala 13
|
179
|
+
ca 13
|
180
|
+
f 13
|
181
|
+
ban 13
|
182
|
+
gka 13
|
183
|
+
il 13
|
184
|
+
ut 13
|
185
|
+
_M 13
|
186
|
+
ni 13
|
187
|
+
era 13
|
188
|
+
ing 13
|
189
|
+
ari 13
|
190
|
+
dar 13
|
191
|
+
ngka 13
|
192
|
+
mp 13
|
193
|
+
A 13
|
194
|
+
gan_ 12
|
195
|
+
ngan_ 12
|
196
|
+
mu 12
|
197
|
+
ag 12
|
198
|
+
_. 12
|
199
|
+
ay 12
|
200
|
+
alam 12
|
201
|
+
itu 12
|
202
|
+
pi 12
|
203
|
+
enga 12
|
204
|
+
pada_ 12
|
205
|
+
_S 12
|
206
|
+
ku 12
|
207
|
+
ela 12
|
208
|
+
es 12
|
209
|
+
and 12
|
210
|
+
p_ 11
|
211
|
+
emb 11
|
212
|
+
_c 11
|
213
|
+
bi 11
|
214
|
+
_._ 11
|
215
|
+
nt 11
|
216
|
+
us 11
|
217
|
+
ih 11
|
218
|
+
dalam 11
|
219
|
+
_te 11
|
220
|
+
N 11
|
221
|
+
bu 11
|
222
|
+
pat 11
|
223
|
+
_ber 11
|
224
|
+
ika 11
|
225
|
+
s_ 11
|
226
|
+
angk 11
|
227
|
+
au 11
|
228
|
+
_itu 10
|
229
|
+
ya_ 10
|
230
|
+
lan 10
|
231
|
+
dak 10
|
232
|
+
_ban 10
|
233
|
+
" 10
|
234
|
+
enda 10
|
235
|
+
mba 10
|
236
|
+
epa 10
|
237
|
+
_it 10
|
238
|
+
alam_ 10
|
239
|
+
di_ 10
|
240
|
+
lah_ 10
|
241
|
+
ali 10
|
242
|
+
ar_ 10
|
243
|
+
ter 10
|
244
|
+
ko 10
|
245
|
+
apa 10
|
246
|
+
K 10
|
247
|
+
ed 10
|
248
|
+
Se 10
|
249
|
+
akan 10
|
250
|
+
atan 10
|
251
|
+
_ti 10
|
252
|
+
lam_ 10
|
253
|
+
on 10
|
254
|
+
_pa 9
|
255
|
+
T 9
|
256
|
+
_dala 9
|
257
|
+
_ma 9
|
258
|
+
_per 9
|
259
|
+
_j 9
|
260
|
+
aj 9
|
261
|
+
ru 9
|
262
|
+
eg 9
|
263
|
+
_dal 9
|
264
|
+
ib 9
|
265
|
+
asi 9
|
266
|
+
tu_ 9
|
267
|
+
_h 9
|
268
|
+
awa 9
|
269
|
+
ka_ 9
|
270
|
+
angka 9
|
271
|
+
nj 9
|
272
|
+
is 9
|
273
|
+
_l 9
|
274
|
+
rang 9
|
275
|
+
nya_ 9
|
276
|
+
hu 9
|
277
|
+
rk 9
|
278
|
+
aw 9
|
279
|
+
du 9
|
280
|
+
mi 9
|
281
|
+
dari 8
|
282
|
+
ita 8
|
283
|
+
ju 8
|
284
|
+
eli 8
|
285
|
+
ana 8
|
286
|
+
aa 8
|
287
|
+
ert 8
|
288
|
+
re 8
|
289
|
+
iha 8
|
290
|
+
ri_ 8
|
291
|
+
dik 8
|
292
|
+
atan_ 8
|
293
|
+
_K 8
|
294
|
+
ta_ 8
|
295
|
+
ida 8
|
296
|
+
ena 8
|
297
|
+
um 8
|
298
|
+
ian 8
|
299
|
+
ai_ 8
|
300
|
+
bag 8
|
301
|
+
nc 8
|
302
|
+
or 8
|
303
|
+
pun 8
|
304
|
+
memb 8
|
305
|
+
sa_ 8
|
306
|
+
emp 8
|
307
|
+
ol 8
|
308
|
+
den 8
|
309
|
+
B 8
|
310
|
+
tan_ 8
|
311
|
+
a. 8
|
312
|
+
anda 8
|
313
|
+
eh 8
|
314
|
+
aya 8
|
315
|
+
rt 8
|
316
|
+
akan_ 8
|
317
|
+
eta 8
|
318
|
+
su 8
|
319
|
+
nja 8
|
320
|
+
_di_ 8
|
321
|
+
_o 8
|
322
|
+
ura 8
|
323
|
+
_de 8
|
324
|
+
ul 7
|
325
|
+
ti_ 7
|
326
|
+
ras 7
|
327
|
+
kep 7
|
328
|
+
man 7
|
329
|
+
ati 7
|
330
|
+
tid 7
|
331
|
+
seb 7
|
332
|
+
_n 7
|
333
|
+
epada 7
|
334
|
+
un_ 7
|
335
|
+
ra_ 7
|
336
|
+
_sa 7
|
337
|
+
n. 7
|
338
|
+
aan 7
|
339
|
+
gu 7
|
340
|
+
ama 7
|
341
|
+
meng 7
|
342
|
+
si_ 7
|
343
|
+
apat 7
|
344
|
+
na_ 7
|
345
|
+
engan 7
|
346
|
+
_ka 7
|
347
|
+
pen 7
|
348
|
+
idak 7
|
349
|
+
sep 7
|
350
|
+
dapa 7
|
351
|
+
_den 7
|
352
|
+
eba 7
|
353
|
+
Me 7
|
354
|
+
I 7
|
355
|
+
ira 7
|
356
|
+
dapat 7
|
357
|
+
ne 7
|
358
|
+
inya 7
|
359
|
+
pat_ 7
|
360
|
+
kepa 7
|
361
|
+
bah 7
|
362
|
+
_memb 7
|
363
|
+
om 7
|
364
|
+
_pen 7
|
365
|
+
pert 7
|
366
|
+
asa_ 7
|
367
|
+
ab 7
|
368
|
+
kepad 7
|
369
|
+
dak_ 7
|
370
|
+
ig 7
|
371
|
+
lu 7
|
372
|
+
agi 7
|
373
|
+
epad 7
|
374
|
+
iny 7
|
375
|
+
dap 7
|
376
|
+
ge 7
|
377
|
+
ci 7
|
378
|
+
_B 7
|
379
|
+
an. 6
|
380
|
+
oleh 6
|
381
|
+
_kepa 6
|
382
|
+
u. 6
|
383
|
+
band 6
|
384
|
+
uan 6
|
385
|
+
car 6
|
386
|
+
leh 6
|
387
|
+
tidak 6
|
388
|
+
alah 6
|
389
|
+
) 6
|
390
|
+
_dari 6
|
391
|
+
ip 6
|
392
|
+
ap_ 6
|
393
|
+
Ma 6
|
394
|
+
aja 6
|
395
|
+
rah 6
|
396
|
+
_T 6
|
397
|
+
( 6
|
398
|
+
nk 6
|
399
|
+
epe 6
|
400
|
+
i. 6
|