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
|
+
_ 17430
|
2
|
+
e 5759
|
3
|
+
r 3334
|
4
|
+
n 3061
|
5
|
+
t 2636
|
6
|
+
a 2502
|
7
|
+
d 2293
|
8
|
+
i 2280
|
9
|
+
s 2224
|
10
|
+
o 1932
|
11
|
+
l 1884
|
12
|
+
g 1617
|
13
|
+
__ 1390
|
14
|
+
k 1278
|
15
|
+
m 1273
|
16
|
+
er 1209
|
17
|
+
e_ 1174
|
18
|
+
de 1045
|
19
|
+
en 993
|
20
|
+
� 940
|
21
|
+
f 939
|
22
|
+
r_ 825
|
23
|
+
v 770
|
24
|
+
t_ 724
|
25
|
+
an 724
|
26
|
+
n_ 710
|
27
|
+
u 605
|
28
|
+
nd 598
|
29
|
+
b 585
|
30
|
+
et 574
|
31
|
+
. 546
|
32
|
+
_s 545
|
33
|
+
re 543
|
34
|
+
te 540
|
35
|
+
st 530
|
36
|
+
er_ 528
|
37
|
+
en_ 526
|
38
|
+
g_ 519
|
39
|
+
_o 501
|
40
|
+
_d 484
|
41
|
+
, 480
|
42
|
+
ge 474
|
43
|
+
h 474
|
44
|
+
,_ 463
|
45
|
+
_a 462
|
46
|
+
in 440
|
47
|
+
p 436
|
48
|
+
ar 430
|
49
|
+
_f 423
|
50
|
+
og 415
|
51
|
+
or 411
|
52
|
+
ti 406
|
53
|
+
et_ 395
|
54
|
+
_e 390
|
55
|
+
ed 381
|
56
|
+
_i 378
|
57
|
+
_m 378
|
58
|
+
sk 365
|
59
|
+
ne 365
|
60
|
+
le 353
|
61
|
+
_og 344
|
62
|
+
ke 343
|
63
|
+
el 342
|
64
|
+
og_ 338
|
65
|
+
� 332
|
66
|
+
ø 332
|
67
|
+
d_ 325
|
68
|
+
me 324
|
69
|
+
ng 317
|
70
|
+
_de 314
|
71
|
+
_og_ 313
|
72
|
+
._ 294
|
73
|
+
ig 293
|
74
|
+
� 293
|
75
|
+
å 293
|
76
|
+
_b 288
|
77
|
+
� 286
|
78
|
+
æ 286
|
79
|
+
i_ 283
|
80
|
+
_h 274
|
81
|
+
de_ 274
|
82
|
+
ri 273
|
83
|
+
s_ 271
|
84
|
+
D 268
|
85
|
+
nde 263
|
86
|
+
li 262
|
87
|
+
om 262
|
88
|
+
ma 259
|
89
|
+
ve 257
|
90
|
+
y 256
|
91
|
+
af 254
|
92
|
+
_i_ 252
|
93
|
+
_t 249
|
94
|
+
at 245
|
95
|
+
il 244
|
96
|
+
and 241
|
97
|
+
es 240
|
98
|
+
al 234
|
99
|
+
be 234
|
100
|
+
is 233
|
101
|
+
fo 232
|
102
|
+
se 232
|
103
|
+
ns 229
|
104
|
+
la 224
|
105
|
+
_D 222
|
106
|
+
[ 221
|
107
|
+
] 221
|
108
|
+
on 221
|
109
|
+
rk 219
|
110
|
+
_af 217
|
111
|
+
[_ 217
|
112
|
+
_] 217
|
113
|
+
den 216
|
114
|
+
der 214
|
115
|
+
_me 210
|
116
|
+
_k 210
|
117
|
+
m_ 208
|
118
|
+
ing 207
|
119
|
+
_v 203
|
120
|
+
k_ 196
|
121
|
+
ra 191
|
122
|
+
f_ 188
|
123
|
+
af_ 186
|
124
|
+
for 184
|
125
|
+
_p 181
|
126
|
+
_af_ 180
|
127
|
+
ol 174
|
128
|
+
_fo 172
|
129
|
+
ark 172
|
130
|
+
ere 172
|
131
|
+
ste 169
|
132
|
+
lan 169
|
133
|
+
te_ 168
|
134
|
+
.[ 168
|
135
|
+
.[_ 165
|
136
|
+
_l 165
|
137
|
+
mar 165
|
138
|
+
l_ 163
|
139
|
+
ll 162
|
140
|
+
ter 161
|
141
|
+
j 159
|
142
|
+
ske 159
|
143
|
+
om_ 155
|
144
|
+
Da 153
|
145
|
+
den_ 153
|
146
|
+
ha 153
|
147
|
+
mark 153
|
148
|
+
ke_ 153
|
149
|
+
land 153
|
150
|
+
_st 151
|
151
|
+
ni 151
|
152
|
+
ed_ 151
|
153
|
+
_for 149
|
154
|
+
so 149
|
155
|
+
ta 148
|
156
|
+
Dan 148
|
157
|
+
ger 147
|
158
|
+
nge 144
|
159
|
+
det 143
|
160
|
+
re_ 140
|
161
|
+
ede 139
|
162
|
+
vi 138
|
163
|
+
nm 138
|
164
|
+
nma 138
|
165
|
+
nmark 137
|
166
|
+
_en 137
|
167
|
+
nmar 137
|
168
|
+
anmar 136
|
169
|
+
anma 136
|
170
|
+
anm 136
|
171
|
+
ev 135
|
172
|
+
rs 135
|
173
|
+
un 133
|
174
|
+
Danma 133
|
175
|
+
_Da 133
|
176
|
+
]_ 133
|
177
|
+
S 133
|
178
|
+
der_ 133
|
179
|
+
Danm 133
|
180
|
+
_]_ 132
|
181
|
+
ans 132
|
182
|
+
_er 131
|
183
|
+
med 130
|
184
|
+
da 130
|
185
|
+
_Dan 129
|
186
|
+
io 127
|
187
|
+
ro 127
|
188
|
+
til 126
|
189
|
+
ik 125
|
190
|
+
som 125
|
191
|
+
_er_ 125
|
192
|
+
_ti 124
|
193
|
+
rn 124
|
194
|
+
ds 123
|
195
|
+
em 122
|
196
|
+
_u 122
|
197
|
+
�_ 121
|
198
|
+
eg 121
|
199
|
+
å_ 121
|
200
|
+
_ha 120
|
201
|
+
_Danm 120
|
202
|
+
rt 120
|
203
|
+
_med 119
|
204
|
+
ld 119
|
205
|
+
som_ 118
|
206
|
+
to 117
|
207
|
+
_so 116
|
208
|
+
ske_ 116
|
209
|
+
_g 116
|
210
|
+
det_ 115
|
211
|
+
_r 115
|
212
|
+
tr 114
|
213
|
+
ern 114
|
214
|
+
ar_ 114
|
215
|
+
end 114
|
216
|
+
_som 113
|
217
|
+
ud 111
|
218
|
+
ko 111
|
219
|
+
id 111
|
220
|
+
del 110
|
221
|
+
_som_ 110
|
222
|
+
_til 109
|
223
|
+
lig 108
|
224
|
+
nsk 108
|
225
|
+
si 108
|
226
|
+
mi 108
|
227
|
+
va 108
|
228
|
+
ls 107
|
229
|
+
ion 105
|
230
|
+
ør 105
|
231
|
+
bl 105
|
232
|
+
ka 105
|
233
|
+
�r 105
|
234
|
+
_be 105
|
235
|
+
ind 105
|
236
|
+
gs 105
|
237
|
+
lle 104
|
238
|
+
_da 104
|
239
|
+
t� 103
|
240
|
+
_S 102
|
241
|
+
ne_ 102
|
242
|
+
med_ 102
|
243
|
+
dt 101
|
244
|
+
tt 101
|
245
|
+
ag 101
|
246
|
+
_en_ 101
|
247
|
+
r� 100
|
248
|
+
c 100
|
249
|
+
_� 100
|
250
|
+
ansk 99
|
251
|
+
ie 99
|
252
|
+
nt 99
|
253
|
+
dan 99
|
254
|
+
_med_ 98
|
255
|
+
or_ 97
|
256
|
+
ær 95
|
257
|
+
il_ 95
|
258
|
+
- 95
|
259
|
+
�r 95
|
260
|
+
De 95
|
261
|
+
lt 94
|
262
|
+
rne 94
|
263
|
+
nin 94
|
264
|
+
ning 94
|
265
|
+
ner 94
|
266
|
+
na 94
|
267
|
+
at_ 92
|
268
|
+
til_ 92
|
269
|
+
fr 92
|
270
|
+
I 92
|
271
|
+
ru 91
|
272
|
+
op 91
|
273
|
+
erne 89
|
274
|
+
rd 89
|
275
|
+
_bl 89
|
276
|
+
_dan 89
|
277
|
+
ge_ 89
|
278
|
+
ige 89
|
279
|
+
gt 88
|
280
|
+
v_ 88
|
281
|
+
ng_ 88
|
282
|
+
tte 87
|
283
|
+
a_ 87
|
284
|
+
p� 87
|
285
|
+
inge 87
|
286
|
+
kr 87
|
287
|
+
_den 87
|
288
|
+
dans 86
|
289
|
+
s� 86
|
290
|
+
dansk 86
|
291
|
+
men 86
|
292
|
+
ver 85
|
293
|
+
_til_ 85
|
294
|
+
isk 85
|
295
|
+
it 85
|
296
|
+
_at 84
|
297
|
+
els 84
|
298
|
+
f� 84
|
299
|
+
_dans 84
|
300
|
+
am 84
|
301
|
+
_re 84
|
302
|
+
est 83
|
303
|
+
es_ 83
|
304
|
+
ur 82
|
305
|
+
gen 82
|
306
|
+
_den_ 82
|
307
|
+
he 81
|
308
|
+
_ud 81
|
309
|
+
_at_ 81
|
310
|
+
_n 81
|
311
|
+
ble 80
|
312
|
+
ene 80
|
313
|
+
od 79
|
314
|
+
und 79
|
315
|
+
sa 79
|
316
|
+
ede_ 79
|
317
|
+
_. 79
|
318
|
+
ande 79
|
319
|
+
_in 78
|
320
|
+
_la 78
|
321
|
+
nde_ 78
|
322
|
+
eri 78
|
323
|
+
ende 77
|
324
|
+
ov 77
|
325
|
+
_fr 76
|
326
|
+
rk_ 76
|
327
|
+
_I 76
|
328
|
+
r. 76
|
329
|
+
tor 76
|
330
|
+
av 75
|
331
|
+
lk 75
|
332
|
+
lev 75
|
333
|
+
ing_ 75
|
334
|
+
sk_ 75
|
335
|
+
ft 74
|
336
|
+
_si 74
|
337
|
+
an_ 74
|
338
|
+
e. 73
|
339
|
+
us 73
|
340
|
+
på 73
|
341
|
+
mm 73
|
342
|
+
F 73
|
343
|
+
E 72
|
344
|
+
_De 72
|
345
|
+
di 72
|
346
|
+
e, 72
|
347
|
+
rin 72
|
348
|
+
_p� 71
|
349
|
+
_lan 71
|
350
|
+
ark_ 71
|
351
|
+
_på 71
|
352
|
+
_der 71
|
353
|
+
nske 71
|
354
|
+
le_ 70
|
355
|
+
st� 70
|
356
|
+
get 70
|
357
|
+
gi 70
|
358
|
+
e,_ 69
|
359
|
+
pr 69
|
360
|
+
ist 69
|
361
|
+
var 68
|
362
|
+
blev 68
|
363
|
+
mark_ 68
|
364
|
+
_ble 68
|
365
|
+
_blev 68
|
366
|
+
ks 68
|
367
|
+
på_ 67
|
368
|
+
_va 67
|
369
|
+
nd_ 67
|
370
|
+
anske 67
|
371
|
+
ss 67
|
372
|
+
år 66
|
373
|
+
�r 66
|
374
|
+
gr 66
|
375
|
+
tio 66
|
376
|
+
lse 66
|
377
|
+
_land 66
|
378
|
+
_på_ 66
|
379
|
+
) 66
|
380
|
+
tion 66
|
381
|
+
ati 66
|
382
|
+
fi 66
|
383
|
+
( 66
|
384
|
+
_( 66
|
385
|
+
one 65
|
386
|
+
ef 65
|
387
|
+
sto 65
|
388
|
+
kt 65
|
389
|
+
_._ 64
|
390
|
+
sen 64
|
391
|
+
else 64
|
392
|
+
ev_ 64
|
393
|
+
ring 63
|
394
|
+
A 63
|
395
|
+
ende_ 63
|
396
|
+
ren 63
|
397
|
+
for_ 62
|
398
|
+
ho 62
|
399
|
+
_ko 62
|
400
|
+
rig 61
|