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
|
+
_ 1242
|
2
|
+
a 715
|
3
|
+
n 366
|
4
|
+
e 308
|
5
|
+
i 298
|
6
|
+
u 211
|
7
|
+
r 208
|
8
|
+
k 205
|
9
|
+
t 205
|
10
|
+
an 185
|
11
|
+
g 152
|
12
|
+
s 152
|
13
|
+
d 149
|
14
|
+
m 149
|
15
|
+
l 108
|
16
|
+
ng 108
|
17
|
+
p 99
|
18
|
+
a_ 91
|
19
|
+
o 91
|
20
|
+
er 85
|
21
|
+
b 85
|
22
|
+
n_ 81
|
23
|
+
, 77
|
24
|
+
ka 76
|
25
|
+
_d 74
|
26
|
+
an_ 74
|
27
|
+
h 73
|
28
|
+
i_ 72
|
29
|
+
en 65
|
30
|
+
ar 65
|
31
|
+
_m 65
|
32
|
+
,_ 64
|
33
|
+
ta 59
|
34
|
+
di 59
|
35
|
+
me 58
|
36
|
+
ang 56
|
37
|
+
ra 55
|
38
|
+
_k 55
|
39
|
+
at 54
|
40
|
+
ak 54
|
41
|
+
y 53
|
42
|
+
_me 51
|
43
|
+
da 49
|
44
|
+
ga 48
|
45
|
+
in 46
|
46
|
+
ya 43
|
47
|
+
. 42
|
48
|
+
tu 41
|
49
|
+
_di 41
|
50
|
+
un 40
|
51
|
+
_p 39
|
52
|
+
j 38
|
53
|
+
la 38
|
54
|
+
_s 37
|
55
|
+
ma 37
|
56
|
+
k_ 36
|
57
|
+
na 36
|
58
|
+
ah 35
|
59
|
+
ri 34
|
60
|
+
_t 33
|
61
|
+
se 33
|
62
|
+
ke 33
|
63
|
+
ng_ 33
|
64
|
+
g_ 33
|
65
|
+
be 33
|
66
|
+
al 32
|
67
|
+
as 32
|
68
|
+
pe 32
|
69
|
+
_b 32
|
70
|
+
__ 32
|
71
|
+
ia 31
|
72
|
+
men 31
|
73
|
+
_men 29
|
74
|
+
_ke 29
|
75
|
+
h_ 29
|
76
|
+
P 29
|
77
|
+
si 29
|
78
|
+
ti 28
|
79
|
+
it 28
|
80
|
+
pa 28
|
81
|
+
ny 28
|
82
|
+
em 27
|
83
|
+
_a 27
|
84
|
+
sa 26
|
85
|
+
am 26
|
86
|
+
kan 26
|
87
|
+
u_ 25
|
88
|
+
eng 24
|
89
|
+
te 24
|
90
|
+
_pe 24
|
91
|
+
c 24
|
92
|
+
ang_ 24
|
93
|
+
nga 23
|
94
|
+
ja 23
|
95
|
+
_se 23
|
96
|
+
s_ 23
|
97
|
+
ba 23
|
98
|
+
S 23
|
99
|
+
ber 22
|
100
|
+
li 22
|
101
|
+
ni 22
|
102
|
+
el 22
|
103
|
+
di_ 22
|
104
|
+
nt 22
|
105
|
+
r_ 22
|
106
|
+
_da 21
|
107
|
+
t_ 21
|
108
|
+
ik 20
|
109
|
+
bu 20
|
110
|
+
nya 20
|
111
|
+
ad 20
|
112
|
+
ata 20
|
113
|
+
ak_ 20
|
114
|
+
ara 19
|
115
|
+
_i 19
|
116
|
+
is 19
|
117
|
+
ran 19
|
118
|
+
us 19
|
119
|
+
_P 19
|
120
|
+
gan 19
|
121
|
+
ap 19
|
122
|
+
._ 19
|
123
|
+
ru 18
|
124
|
+
_be 18
|
125
|
+
era 18
|
126
|
+
_ka 18
|
127
|
+
dan 18
|
128
|
+
ah_ 17
|
129
|
+
ari 17
|
130
|
+
- 17
|
131
|
+
to 17
|
132
|
+
es 17
|
133
|
+
nd 17
|
134
|
+
ur 17
|
135
|
+
a, 17
|
136
|
+
uk 17
|
137
|
+
yan 16
|
138
|
+
ala 16
|
139
|
+
ha 16
|
140
|
+
yang 16
|
141
|
+
ter 16
|
142
|
+
ol 16
|
143
|
+
su 16
|
144
|
+
I 16
|
145
|
+
ngan 16
|
146
|
+
ung 16
|
147
|
+
_y 15
|
148
|
+
J 15
|
149
|
+
M 15
|
150
|
+
kan_ 15
|
151
|
+
_ya 15
|
152
|
+
_di_ 15
|
153
|
+
_ber 15
|
154
|
+
A 14
|
155
|
+
du 14
|
156
|
+
enga 14
|
157
|
+
_yan 14
|
158
|
+
lu 14
|
159
|
+
de 14
|
160
|
+
itu 14
|
161
|
+
" 14
|
162
|
+
ok 14
|
163
|
+
ek 14
|
164
|
+
_yang 14
|
165
|
+
ai 13
|
166
|
+
dan_ 13
|
167
|
+
rang 13
|
168
|
+
per 13
|
169
|
+
a,_ 13
|
170
|
+
_dan 13
|
171
|
+
eri 13
|
172
|
+
yang_ 13
|
173
|
+
l_ 13
|
174
|
+
ge 13
|
175
|
+
R 13
|
176
|
+
da_ 13
|
177
|
+
at_ 13
|
178
|
+
D 13
|
179
|
+
_te 13
|
180
|
+
kar 13
|
181
|
+
ko 13
|
182
|
+
_S 13
|
183
|
+
ina 13
|
184
|
+
ku 13
|
185
|
+
ul 12
|
186
|
+
et 12
|
187
|
+
w 12
|
188
|
+
po 12
|
189
|
+
ut 12
|
190
|
+
ya_ 12
|
191
|
+
gi 12
|
192
|
+
e_ 12
|
193
|
+
aka 12
|
194
|
+
_dan_ 12
|
195
|
+
rin 12
|
196
|
+
ua 12
|
197
|
+
ju 12
|
198
|
+
pen 12
|
199
|
+
nya_ 11
|
200
|
+
ngg 11
|
201
|
+
ena 11
|
202
|
+
ama 11
|
203
|
+
mp 11
|
204
|
+
ca 11
|
205
|
+
_pen 11
|
206
|
+
re 11
|
207
|
+
ika 11
|
208
|
+
_J 11
|
209
|
+
B 11
|
210
|
+
_ter 11
|
211
|
+
gg 11
|
212
|
+
na_ 11
|
213
|
+
ia_ 11
|
214
|
+
ed 11
|
215
|
+
or 11
|
216
|
+
lan 11
|
217
|
+
ni_ 10
|
218
|
+
ngk 10
|
219
|
+
ab 10
|
220
|
+
gk 10
|
221
|
+
mi 10
|
222
|
+
arina 10
|
223
|
+
T 10
|
224
|
+
eru 10
|
225
|
+
Zar 10
|
226
|
+
uk_ 10
|
227
|
+
Za 10
|
228
|
+
arin 10
|
229
|
+
ela 10
|
230
|
+
adi 10
|
231
|
+
rina 10
|
232
|
+
wa 10
|
233
|
+
rt 10
|
234
|
+
Z 10
|
235
|
+
us_ 10
|
236
|
+
Zari 10
|
237
|
+
im 10
|
238
|
+
_T 10
|
239
|
+
Zarin 10
|
240
|
+
uh 10
|
241
|
+
ini 10
|
242
|
+
il 9
|
243
|
+
jad 9
|
244
|
+
_mem 9
|
245
|
+
i, 9
|
246
|
+
i. 9
|
247
|
+
mu 9
|
248
|
+
ntu 9
|
249
|
+
i,_ 9
|
250
|
+
ing 9
|
251
|
+
_c 9
|
252
|
+
gan_ 9
|
253
|
+
eb 9
|
254
|
+
ngan_ 9
|
255
|
+
ta_ 9
|
256
|
+
ada 9
|
257
|
+
si_ 9
|
258
|
+
apa 9
|
259
|
+
engan 9
|
260
|
+
asi 9
|
261
|
+
_de 9
|
262
|
+
_ta 9
|
263
|
+
mem 9
|
264
|
+
K 9
|
265
|
+
ant 9
|
266
|
+
tu_ 9
|
267
|
+
ag 9
|
268
|
+
os 9
|
269
|
+
jadi 9
|
270
|
+
_Zari 8
|
271
|
+
dia 8
|
272
|
+
oko 8
|
273
|
+
_ma 8
|
274
|
+
ki 8
|
275
|
+
nj 8
|
276
|
+
_meng 8
|
277
|
+
mb 8
|
278
|
+
au 8
|
279
|
+
le 8
|
280
|
+
man 8
|
281
|
+
_A 8
|
282
|
+
rk 8
|
283
|
+
pat 8
|
284
|
+
ep 8
|
285
|
+
oh 8
|
286
|
+
_Zar 8
|
287
|
+
isi 8
|
288
|
+
itu_ 8
|
289
|
+
emb 8
|
290
|
+
eny 8
|
291
|
+
aga 8
|
292
|
+
ip 8
|
293
|
+
_Za 8
|
294
|
+
ri_ 8
|
295
|
+
ar_ 8
|
296
|
+
_in 8
|
297
|
+
st 8
|
298
|
+
ian 8
|
299
|
+
_M 8
|
300
|
+
L 8
|
301
|
+
meng 8
|
302
|
+
_Z 8
|
303
|
+
bur 7
|
304
|
+
gga 7
|
305
|
+
ot 7
|
306
|
+
ay 7
|
307
|
+
uga 7
|
308
|
+
rl 7
|
309
|
+
Ta 7
|
310
|
+
nu 7
|
311
|
+
tan 7
|
312
|
+
peng 7
|
313
|
+
ug 7
|
314
|
+
ej 7
|
315
|
+
ce 7
|
316
|
+
_peng 7
|
317
|
+
ng,_ 7
|
318
|
+
tak 7
|
319
|
+
ada_ 7
|
320
|
+
ro 7
|
321
|
+
atan 7
|
322
|
+
ntuk_ 7
|
323
|
+
_ini 7
|
324
|
+
_meny 7
|
325
|
+
as_ 7
|
326
|
+
erl 7
|
327
|
+
art 7
|
328
|
+
ih 7
|
329
|
+
ma_ 7
|
330
|
+
um 7
|
331
|
+
eka 7
|
332
|
+
lu_ 7
|
333
|
+
and 7
|
334
|
+
_it 7
|
335
|
+
tok 7
|
336
|
+
nda 7
|
337
|
+
ntuk 7
|
338
|
+
ngga 7
|
339
|
+
alan 7
|
340
|
+
ib 7
|
341
|
+
g, 7
|
342
|
+
rah 7
|
343
|
+
_Ja 7
|
344
|
+
gka 7
|
345
|
+
aya 7
|
346
|
+
pu 7
|
347
|
+
_Ta 7
|
348
|
+
Ja 7
|
349
|
+
ger 7
|
350
|
+
_I 7
|
351
|
+
meny 7
|
352
|
+
tuk 7
|
353
|
+
a. 7
|
354
|
+
n. 7
|
355
|
+
_itu 7
|
356
|
+
tuk_ 7
|
357
|
+
ng, 7
|
358
|
+
_per 7
|
359
|
+
_ba 7
|
360
|
+
al_ 7
|
361
|
+
ita 7
|
362
|
+
aran 7
|
363
|
+
g,_ 7
|
364
|
+
kal 7
|
365
|
+
arang 7
|
366
|
+
p_ 7
|
367
|
+
ngka 7
|
368
|
+
toko 7
|
369
|
+
u, 7
|
370
|
+
sia 7
|
371
|
+
pol 6
|
372
|
+
pi 6
|
373
|
+
den 6
|
374
|
+
kart 6
|
375
|
+
_L 6
|
376
|
+
akart 6
|
377
|
+
lis 6
|
378
|
+
mel 6
|
379
|
+
ngi 6
|
380
|
+
_den 6
|
381
|
+
n,_ 6
|
382
|
+
Pol 6
|
383
|
+
ang,_ 6
|
384
|
+
aha 6
|
385
|
+
uny 6
|
386
|
+
PR 6
|
387
|
+
ra_ 6
|
388
|
+
oli 6
|
389
|
+
an,_ 6
|
390
|
+
sus 6
|
391
|
+
an. 6
|
392
|
+
kat 6
|
393
|
+
n, 6
|
394
|
+
_itu_ 6
|
395
|
+
ang, 6
|
396
|
+
Po 6
|
397
|
+
tin 6
|
398
|
+
mun 6
|
399
|
+
U 6
|
400
|
+
nge 6
|