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
|
+
_ 1780
|
2
|
+
e 577
|
3
|
+
n 391
|
4
|
+
r 299
|
5
|
+
t 268
|
6
|
+
a 248
|
7
|
+
s 208
|
8
|
+
o 194
|
9
|
+
l 175
|
10
|
+
i 173
|
11
|
+
n_ 158
|
12
|
+
g 152
|
13
|
+
k 150
|
14
|
+
r_ 145
|
15
|
+
en 135
|
16
|
+
e_ 128
|
17
|
+
m 126
|
18
|
+
d 120
|
19
|
+
h 117
|
20
|
+
er 116
|
21
|
+
_h 101
|
22
|
+
t_ 98
|
23
|
+
v 96
|
24
|
+
an 89
|
25
|
+
er_ 85
|
26
|
+
_s 81
|
27
|
+
u 80
|
28
|
+
en_ 76
|
29
|
+
f 68
|
30
|
+
. 67
|
31
|
+
g_ 65
|
32
|
+
� 63
|
33
|
+
p 62
|
34
|
+
ha 62
|
35
|
+
te 59
|
36
|
+
_ha 59
|
37
|
+
_. 58
|
38
|
+
et 57
|
39
|
+
or 54
|
40
|
+
de 54
|
41
|
+
, 53
|
42
|
+
_o 52
|
43
|
+
ne 52
|
44
|
+
_e 51
|
45
|
+
_, 51
|
46
|
+
,_ 49
|
47
|
+
_,_ 47
|
48
|
+
an_ 47
|
49
|
+
et_ 45
|
50
|
+
nn 44
|
51
|
+
_f 44
|
52
|
+
ke 43
|
53
|
+
_d 42
|
54
|
+
_i 41
|
55
|
+
re 39
|
56
|
+
�_ 39
|
57
|
+
b 39
|
58
|
+
st 38
|
59
|
+
me 38
|
60
|
+
og 37
|
61
|
+
ar 37
|
62
|
+
om 37
|
63
|
+
m_ 37
|
64
|
+
se 36
|
65
|
+
el 34
|
66
|
+
_m 34
|
67
|
+
ge 34
|
68
|
+
_og 34
|
69
|
+
_v 33
|
70
|
+
in 32
|
71
|
+
og_ 32
|
72
|
+
ng 32
|
73
|
+
_og_ 31
|
74
|
+
_t 31
|
75
|
+
� 30
|
76
|
+
fo 30
|
77
|
+
han 30
|
78
|
+
_han 30
|
79
|
+
_a 30
|
80
|
+
_k 29
|
81
|
+
_de 29
|
82
|
+
for 29
|
83
|
+
il 29
|
84
|
+
le 28
|
85
|
+
H 28
|
86
|
+
sk 28
|
87
|
+
un 28
|
88
|
+
_b 27
|
89
|
+
l_ 27
|
90
|
+
i_ 27
|
91
|
+
_er 26
|
92
|
+
j 26
|
93
|
+
ve 25
|
94
|
+
_for 25
|
95
|
+
kk 25
|
96
|
+
_fo 25
|
97
|
+
al 25
|
98
|
+
om_ 24
|
99
|
+
ne_ 24
|
100
|
+
ti 24
|
101
|
+
_er_ 23
|
102
|
+
li 23
|
103
|
+
_g 23
|
104
|
+
han_ 23
|
105
|
+
_han_ 23
|
106
|
+
kke 22
|
107
|
+
tt 22
|
108
|
+
nne 22
|
109
|
+
va 21
|
110
|
+
is 21
|
111
|
+
rt 21
|
112
|
+
at 21
|
113
|
+
y 21
|
114
|
+
" 21
|
115
|
+
ar_ 21
|
116
|
+
_p 20
|
117
|
+
_n 20
|
118
|
+
_me 20
|
119
|
+
or_ 20
|
120
|
+
d_ 19
|
121
|
+
eg 19
|
122
|
+
ed 19
|
123
|
+
te_ 19
|
124
|
+
un_ 19
|
125
|
+
ke_ 18
|
126
|
+
�r 18
|
127
|
+
_l 18
|
128
|
+
vi 18
|
129
|
+
so 18
|
130
|
+
he 18
|
131
|
+
Ha 18
|
132
|
+
nge 18
|
133
|
+
es 18
|
134
|
+
ka 18
|
135
|
+
ll 17
|
136
|
+
det 17
|
137
|
+
il_ 17
|
138
|
+
pe 17
|
139
|
+
la 16
|
140
|
+
som 16
|
141
|
+
Han 16
|
142
|
+
ter 16
|
143
|
+
_so 16
|
144
|
+
hu 16
|
145
|
+
D 16
|
146
|
+
ig 16
|
147
|
+
ste 16
|
148
|
+
Han_ 15
|
149
|
+
s_ 15
|
150
|
+
for_ 15
|
151
|
+
_se 15
|
152
|
+
_som 15
|
153
|
+
til 15
|
154
|
+
ik 15
|
155
|
+
nd 15
|
156
|
+
am 15
|
157
|
+
"_ 15
|
158
|
+
ns 15
|
159
|
+
har 15
|
160
|
+
_ti 15
|
161
|
+
ten 14
|
162
|
+
har_ 14
|
163
|
+
enn 14
|
164
|
+
ikk 14
|
165
|
+
_har 14
|
166
|
+
ene 14
|
167
|
+
_� 14
|
168
|
+
det_ 14
|
169
|
+
_i_ 14
|
170
|
+
p� 14
|
171
|
+
gen 14
|
172
|
+
av 14
|
173
|
+
nt 14
|
174
|
+
_til 14
|
175
|
+
_som_ 13
|
176
|
+
hun 13
|
177
|
+
�r 13
|
178
|
+
_r 13
|
179
|
+
re_ 13
|
180
|
+
de_ 13
|
181
|
+
a_ 13
|
182
|
+
_ka 13
|
183
|
+
ut 13
|
184
|
+
_p� 13
|
185
|
+
mm 13
|
186
|
+
p�_ 13
|
187
|
+
v_ 13
|
188
|
+
_har_ 13
|
189
|
+
mme 13
|
190
|
+
som_ 13
|
191
|
+
eg_ 13
|
192
|
+
on 13
|
193
|
+
je 13
|
194
|
+
_hu 13
|
195
|
+
ta 13
|
196
|
+
hun_ 13
|
197
|
+
_ik 12
|
198
|
+
hen 12
|
199
|
+
no 12
|
200
|
+
kke_ 12
|
201
|
+
ko 12
|
202
|
+
De 12
|
203
|
+
_av 12
|
204
|
+
lig 12
|
205
|
+
til_ 12
|
206
|
+
ikke 12
|
207
|
+
_p�_ 12
|
208
|
+
_ikk 12
|
209
|
+
em 12
|
210
|
+
enne 12
|
211
|
+
_he 12
|
212
|
+
_hun 12
|
213
|
+
_hun_ 12
|
214
|
+
_ikke 12
|
215
|
+
_for_ 12
|
216
|
+
pen 11
|
217
|
+
tte 11
|
218
|
+
_en 11
|
219
|
+
lo 11
|
220
|
+
den_ 11
|
221
|
+
ni 11
|
222
|
+
_vi 11
|
223
|
+
S 11
|
224
|
+
den 11
|
225
|
+
nne_ 11
|
226
|
+
_til_ 11
|
227
|
+
ei 11
|
228
|
+
ham 11
|
229
|
+
tr 11
|
230
|
+
ing 11
|
231
|
+
_det 11
|
232
|
+
�r_ 11
|
233
|
+
ed_ 10
|
234
|
+
_hen 10
|
235
|
+
_" 10
|
236
|
+
inn 10
|
237
|
+
pen_ 10
|
238
|
+
ere 10
|
239
|
+
ten_ 10
|
240
|
+
ans 10
|
241
|
+
be 10
|
242
|
+
� 10
|
243
|
+
_u 10
|
244
|
+
_ham 10
|
245
|
+
_at 10
|
246
|
+
_st 10
|
247
|
+
am_ 10
|
248
|
+
k_ 10
|
249
|
+
it 10
|
250
|
+
ste_ 10
|
251
|
+
�r 10
|
252
|
+
ham_ 10
|
253
|
+
ikke_ 10
|
254
|
+
s� 9
|
255
|
+
rd 9
|
256
|
+
le_ 9
|
257
|
+
ra 9
|
258
|
+
da 9
|
259
|
+
_den 9
|
260
|
+
_et 9
|
261
|
+
_ve 9
|
262
|
+
av_ 9
|
263
|
+
els 9
|
264
|
+
_kan 9
|
265
|
+
_.H 9
|
266
|
+
men 9
|
267
|
+
rs 9
|
268
|
+
at_ 9
|
269
|
+
ord 9
|
270
|
+
ig_ 9
|
271
|
+
du 9
|
272
|
+
kan 9
|
273
|
+
s�_ 9
|
274
|
+
ak 9
|
275
|
+
_den_ 9
|
276
|
+
E 9
|
277
|
+
lt 9
|
278
|
+
ls 9
|
279
|
+
seg 9
|
280
|
+
.H 9
|
281
|
+
ang 9
|
282
|
+
oe 9
|
283
|
+
_ham_ 9
|
284
|
+
hv 9
|
285
|
+
ser 9
|
286
|
+
nni 9
|
287
|
+
est 9
|
288
|
+
eng 9
|
289
|
+
ld 9
|
290
|
+
med 9
|
291
|
+
.. 9
|
292
|
+
enne_ 8
|
293
|
+
rt_ 8
|
294
|
+
Unn 8
|
295
|
+
ske 8
|
296
|
+
Unni 8
|
297
|
+
ser_ 8
|
298
|
+
_in 8
|
299
|
+
_s� 8
|
300
|
+
ng_ 8
|
301
|
+
gan 8
|
302
|
+
_s�_ 8
|
303
|
+
_va 8
|
304
|
+
henne 8
|
305
|
+
nde 8
|
306
|
+
U 8
|
307
|
+
ga 8
|
308
|
+
_henn 8
|
309
|
+
sv 8
|
310
|
+
ss 8
|
311
|
+
_det_ 8
|
312
|
+
_kan_ 8
|
313
|
+
_be 8
|
314
|
+
ngen 8
|
315
|
+
sp 8
|
316
|
+
kan_ 8
|
317
|
+
ie 8
|
318
|
+
_med 8
|
319
|
+
lle 8
|
320
|
+
sa 8
|
321
|
+
kt 8
|
322
|
+
pp 8
|
323
|
+
_om 8
|
324
|
+
end 8
|
325
|
+
_�_ 8
|
326
|
+
_av_ 8
|
327
|
+
_at_ 8
|
328
|
+
Un 8
|
329
|
+
der 8
|
330
|
+
tt_ 8
|
331
|
+
henn 8
|
332
|
+
gen_ 7
|
333
|
+
mer_ 7
|
334
|
+
_.Ha 7
|
335
|
+
F 7
|
336
|
+
lan 7
|
337
|
+
ger 7
|
338
|
+
Hu 7
|
339
|
+
ek 7
|
340
|
+
inge 7
|
341
|
+
.Han_ 7
|
342
|
+
ner 7
|
343
|
+
ene_ 7
|
344
|
+
.Ha 7
|
345
|
+
ann 7
|
346
|
+
._ 7
|
347
|
+
_.Han 7
|
348
|
+
.Han 7
|
349
|
+
si 7
|
350
|
+
var 7
|
351
|
+
sl 7
|
352
|
+
noe 7
|
353
|
+
vo 7
|
354
|
+
ro 7
|
355
|
+
lig_ 7
|
356
|
+
_seg 7
|
357
|
+
lv 7
|
358
|
+
o_ 7
|
359
|
+
ri 7
|
360
|
+
mer 7
|
361
|
+
ker 7
|
362
|
+
_no 7
|
363
|
+
bl 7
|
364
|
+
ort 7
|
365
|
+
_du 7
|
366
|
+
_hv 7
|
367
|
+
_med_ 7
|
368
|
+
gj 7
|
369
|
+
der_ 7
|
370
|
+
med_ 7
|
371
|
+
seg_ 7
|
372
|
+
men_ 7
|
373
|
+
_et_ 7
|
374
|
+
_om_ 7
|
375
|
+
ger_ 6
|
376
|
+
j� 6
|
377
|
+
nk 6
|
378
|
+
nen_ 6
|
379
|
+
mel 6
|
380
|
+
eli 6
|
381
|
+
dd 6
|
382
|
+
_tr 6
|
383
|
+
�r_ 6
|
384
|
+
nn_ 6
|
385
|
+
sva 6
|
386
|
+
ter_ 6
|
387
|
+
ell 6
|
388
|
+
ma 6
|
389
|
+
O 6
|
390
|
+
rg 6
|
391
|
+
_men 6
|
392
|
+
oen 6
|
393
|
+
ver 6
|
394
|
+
_ser 6
|
395
|
+
vet 6
|
396
|
+
gu 6
|
397
|
+
att 6
|
398
|
+
vil 6
|
399
|
+
g� 6
|
400
|
+
ye 6
|