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
|
+
_ 1354
|
2
|
+
a 856
|
3
|
+
n 460
|
4
|
+
i 336
|
5
|
+
g 302
|
6
|
+
ng 210
|
7
|
+
t 183
|
8
|
+
g_ 175
|
9
|
+
o 173
|
10
|
+
ng_ 169
|
11
|
+
a_ 156
|
12
|
+
an 155
|
13
|
+
k 155
|
14
|
+
s 150
|
15
|
+
l 147
|
16
|
+
_n 132
|
17
|
+
m 131
|
18
|
+
y 105
|
19
|
+
p 105
|
20
|
+
u 103
|
21
|
+
na 101
|
22
|
+
ang 98
|
23
|
+
. 85
|
24
|
+
ang_ 83
|
25
|
+
la 80
|
26
|
+
in 79
|
27
|
+
_a 77
|
28
|
+
r 77
|
29
|
+
ka 72
|
30
|
+
b 72
|
31
|
+
sa 67
|
32
|
+
ak 67
|
33
|
+
_m 65
|
34
|
+
pa 65
|
35
|
+
_s 64
|
36
|
+
ma 64
|
37
|
+
h 63
|
38
|
+
_na 61
|
39
|
+
d 57
|
40
|
+
al 57
|
41
|
+
at 54
|
42
|
+
_p 52
|
43
|
+
ag 52
|
44
|
+
ta 49
|
45
|
+
_k 45
|
46
|
+
ni 45
|
47
|
+
t_ 44
|
48
|
+
_sa 43
|
49
|
+
n_ 42
|
50
|
+
" 42
|
51
|
+
ya 42
|
52
|
+
_ng 42
|
53
|
+
ay 41
|
54
|
+
it 40
|
55
|
+
_pa 40
|
56
|
+
ga 39
|
57
|
+
on 39
|
58
|
+
e 39
|
59
|
+
sa_ 38
|
60
|
+
y_ 37
|
61
|
+
iy 36
|
62
|
+
il 36
|
63
|
+
ala 35
|
64
|
+
o_ 35
|
65
|
+
w 35
|
66
|
+
_ng_ 34
|
67
|
+
am 34
|
68
|
+
_sa_ 33
|
69
|
+
_ma 32
|
70
|
+
na_ 32
|
71
|
+
i_ 32
|
72
|
+
._ 32
|
73
|
+
_an 31
|
74
|
+
ra 31
|
75
|
+
, 31
|
76
|
+
ba 30
|
77
|
+
_ang 29
|
78
|
+
_ang_ 29
|
79
|
+
_ni 29
|
80
|
+
ar 29
|
81
|
+
iya 29
|
82
|
+
_t 29
|
83
|
+
_i 28
|
84
|
+
_ka 28
|
85
|
+
li 27
|
86
|
+
_l 27
|
87
|
+
ha 27
|
88
|
+
as 27
|
89
|
+
is 27
|
90
|
+
aka 27
|
91
|
+
hi 27
|
92
|
+
,_ 27
|
93
|
+
ong 27
|
94
|
+
_na_ 26
|
95
|
+
ko 26
|
96
|
+
gi 26
|
97
|
+
ri 25
|
98
|
+
ap 25
|
99
|
+
to 25
|
100
|
+
ong_ 24
|
101
|
+
un 24
|
102
|
+
ah 24
|
103
|
+
lan 24
|
104
|
+
ay_ 24
|
105
|
+
ata 23
|
106
|
+
um 23
|
107
|
+
si 23
|
108
|
+
wa 23
|
109
|
+
o. 23
|
110
|
+
ing 23
|
111
|
+
di 23
|
112
|
+
ki 22
|
113
|
+
ti 22
|
114
|
+
s_ 22
|
115
|
+
_niy 21
|
116
|
+
niy 21
|
117
|
+
_d 21
|
118
|
+
ab 21
|
119
|
+
_niya 21
|
120
|
+
an_ 21
|
121
|
+
niya 21
|
122
|
+
mo 21
|
123
|
+
at_ 20
|
124
|
+
N 20
|
125
|
+
a. 20
|
126
|
+
ila 19
|
127
|
+
ot 19
|
128
|
+
yo 19
|
129
|
+
- 19
|
130
|
+
aw 19
|
131
|
+
nga 18
|
132
|
+
_ak 18
|
133
|
+
ig 18
|
134
|
+
_mo 18
|
135
|
+
lang 18
|
136
|
+
A 18
|
137
|
+
nag 17
|
138
|
+
ama 17
|
139
|
+
tu 17
|
140
|
+
in_ 16
|
141
|
+
_b 16
|
142
|
+
ali 16
|
143
|
+
ina 16
|
144
|
+
aki 16
|
145
|
+
ara 16
|
146
|
+
P 16
|
147
|
+
"_ 16
|
148
|
+
_at 15
|
149
|
+
' 15
|
150
|
+
ing_ 15
|
151
|
+
lang_ 15
|
152
|
+
_si 15
|
153
|
+
ai 14
|
154
|
+
bi 14
|
155
|
+
aa 14
|
156
|
+
_r 14
|
157
|
+
ga_ 14
|
158
|
+
o._ 14
|
159
|
+
nd 14
|
160
|
+
ib 14
|
161
|
+
da 14
|
162
|
+
hin 13
|
163
|
+
ro 13
|
164
|
+
iya_ 13
|
165
|
+
lo 13
|
166
|
+
ito 13
|
167
|
+
_at_ 13
|
168
|
+
ik 13
|
169
|
+
_h 13
|
170
|
+
ako 13
|
171
|
+
ya_ 13
|
172
|
+
_ta 12
|
173
|
+
ul 12
|
174
|
+
la_ 12
|
175
|
+
_la 12
|
176
|
+
Na 12
|
177
|
+
mag 12
|
178
|
+
S 12
|
179
|
+
rin 12
|
180
|
+
a, 12
|
181
|
+
K 12
|
182
|
+
ahi 12
|
183
|
+
man 11
|
184
|
+
a,_ 11
|
185
|
+
_ri 11
|
186
|
+
k_ 11
|
187
|
+
lu 11
|
188
|
+
'y 11
|
189
|
+
." 11
|
190
|
+
gk 11
|
191
|
+
kin 11
|
192
|
+
mi 11
|
193
|
+
go 11
|
194
|
+
'y_ 11
|
195
|
+
asa 11
|
196
|
+
M 11
|
197
|
+
_mag 11
|
198
|
+
ilan 11
|
199
|
+
apa 11
|
200
|
+
ung 11
|
201
|
+
_tu 11
|
202
|
+
pan 11
|
203
|
+
_di 11
|
204
|
+
ot_ 10
|
205
|
+
Ma 10
|
206
|
+
is_ 10
|
207
|
+
wal 10
|
208
|
+
nak 10
|
209
|
+
mg 10
|
210
|
+
mu 10
|
211
|
+
_is 10
|
212
|
+
yon 10
|
213
|
+
I 10
|
214
|
+
mga 10
|
215
|
+
ir 10
|
216
|
+
ilang 10
|
217
|
+
mga_ 10
|
218
|
+
su 10
|
219
|
+
uma 10
|
220
|
+
yan 10
|
221
|
+
agk 10
|
222
|
+
.. 10
|
223
|
+
pa_ 10
|
224
|
+
awa 10
|
225
|
+
Ka 10
|
226
|
+
wala 10
|
227
|
+
pi 10
|
228
|
+
akin 10
|
229
|
+
ari 10
|
230
|
+
_aki 9
|
231
|
+
An 9
|
232
|
+
_K 9
|
233
|
+
ini 9
|
234
|
+
pu 9
|
235
|
+
no 9
|
236
|
+
aba 9
|
237
|
+
_mg 9
|
238
|
+
n. 9
|
239
|
+
_mga_ 9
|
240
|
+
_mga 9
|
241
|
+
agka 9
|
242
|
+
gka 9
|
243
|
+
isa 9
|
244
|
+
n, 9
|
245
|
+
_A 9
|
246
|
+
pag 9
|
247
|
+
alan 9
|
248
|
+
nan 9
|
249
|
+
san 9
|
250
|
+
it_ 9
|
251
|
+
_N 9
|
252
|
+
_akin 9
|
253
|
+
ayo 8
|
254
|
+
_lu 8
|
255
|
+
naka 8
|
256
|
+
_wala 8
|
257
|
+
t. 8
|
258
|
+
aha 8
|
259
|
+
_ako 8
|
260
|
+
ob 8
|
261
|
+
si_ 8
|
262
|
+
mo_ 8
|
263
|
+
_nag 8
|
264
|
+
_wa 8
|
265
|
+
dib 8
|
266
|
+
niya_ 8
|
267
|
+
mat 8
|
268
|
+
alang 8
|
269
|
+
aman 8
|
270
|
+
ngi 8
|
271
|
+
ili 8
|
272
|
+
aga 8
|
273
|
+
as_ 8
|
274
|
+
Pa 8
|
275
|
+
l_ 8
|
276
|
+
di_ 8
|
277
|
+
tay 8
|
278
|
+
_Ka 8
|
279
|
+
iti 8
|
280
|
+
_w 8
|
281
|
+
aking 8
|
282
|
+
igi 8
|
283
|
+
abi 8
|
284
|
+
_ba 8
|
285
|
+
umi 8
|
286
|
+
_wal 8
|
287
|
+
a' 8
|
288
|
+
_P 8
|
289
|
+
king 8
|
290
|
+
tan 8
|
291
|
+
p_ 8
|
292
|
+
yang 8
|
293
|
+
pak 7
|
294
|
+
_isa 7
|
295
|
+
er 7
|
296
|
+
_rin 7
|
297
|
+
_pag 7
|
298
|
+
tak 7
|
299
|
+
anga 7
|
300
|
+
tum 7
|
301
|
+
B 7
|
302
|
+
tat 7
|
303
|
+
_An 7
|
304
|
+
_mo_ 7
|
305
|
+
ail 7
|
306
|
+
o, 7
|
307
|
+
king_ 7
|
308
|
+
ut 7
|
309
|
+
a._ 7
|
310
|
+
iyo 7
|
311
|
+
mata 7
|
312
|
+
n,_ 7
|
313
|
+
o' 7
|
314
|
+
kan 7
|
315
|
+
_pa_ 7
|
316
|
+
ala_ 7
|
317
|
+
bo 7
|
318
|
+
.n 7
|
319
|
+
ra_ 7
|
320
|
+
e_ 7
|
321
|
+
g- 7
|
322
|
+
oo 7
|
323
|
+
gin 7
|
324
|
+
tang 7
|
325
|
+
_ko 7
|
326
|
+
lis 7
|
327
|
+
ban 7
|
328
|
+
_si_ 7
|
329
|
+
ram 7
|
330
|
+
ip 7
|
331
|
+
ka_ 7
|
332
|
+
tin 7
|
333
|
+
ana 7
|
334
|
+
to_ 7
|
335
|
+
_M 7
|
336
|
+
ku 7
|
337
|
+
kat 7
|
338
|
+
kak 6
|
339
|
+
ula 6
|
340
|
+
ago 6
|
341
|
+
lis_ 6
|
342
|
+
_nga 6
|
343
|
+
.na 6
|
344
|
+
siy 6
|
345
|
+
isang 6
|
346
|
+
ung_ 6
|
347
|
+
par 6
|
348
|
+
_I 6
|
349
|
+
man_ 6
|
350
|
+
up 6
|
351
|
+
pal 6
|
352
|
+
nang 6
|
353
|
+
ig_ 6
|
354
|
+
_" 6
|
355
|
+
kah 6
|
356
|
+
aila 6
|
357
|
+
tang_ 6
|
358
|
+
agi 6
|
359
|
+
nt 6
|
360
|
+
siya 6
|
361
|
+
nit 6
|
362
|
+
isan 6
|
363
|
+
sang 6
|
364
|
+
_iy 6
|
365
|
+
_mu 6
|
366
|
+
o'y 6
|
367
|
+
Sa 6
|
368
|
+
_S 6
|
369
|
+
c 6
|
370
|
+
_tum 6
|
371
|
+
mb 6
|
372
|
+
kun 6
|
373
|
+
tata 6
|
374
|
+
_par 6
|
375
|
+
_ha 6
|
376
|
+
? 6
|
377
|
+
mba 6
|
378
|
+
yang_ 6
|
379
|
+
gay 6
|
380
|
+
ap_ 6
|
381
|
+
bang 6
|
382
|
+
_Na 6
|
383
|
+
im 6
|
384
|
+
d_ 6
|
385
|
+
o,_ 6
|
386
|
+
os 6
|
387
|
+
ag- 6
|
388
|
+
una 6
|
389
|
+
_Ma 6
|
390
|
+
ak_ 6
|
391
|
+
_hi 6
|
392
|
+
st 6
|
393
|
+
o'y_ 6
|
394
|
+
ita 6
|
395
|
+
_ku 6
|
396
|
+
gan 6
|
397
|
+
walan 6
|
398
|
+
kaka 6
|
399
|
+
_iyo 6
|
400
|
+
o." 6
|