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
|
+
_ 1596
|
2
|
+
e 609
|
3
|
+
a 326
|
4
|
+
n 308
|
5
|
+
i 281
|
6
|
+
o 229
|
7
|
+
r 224
|
8
|
+
t 206
|
9
|
+
s 202
|
10
|
+
d 190
|
11
|
+
e_ 141
|
12
|
+
l 126
|
13
|
+
g 125
|
14
|
+
m 124
|
15
|
+
ie 123
|
16
|
+
k 122
|
17
|
+
n_ 111
|
18
|
+
t_ 92
|
19
|
+
h 89
|
20
|
+
an 83
|
21
|
+
er 83
|
22
|
+
v 82
|
23
|
+
y 81
|
24
|
+
_d 76
|
25
|
+
aa 75
|
26
|
+
ie_ 74
|
27
|
+
_h 73
|
28
|
+
w 73
|
29
|
+
di 73
|
30
|
+
s_ 71
|
31
|
+
_v 66
|
32
|
+
en 65
|
33
|
+
. 62
|
34
|
+
ge 60
|
35
|
+
r_ 60
|
36
|
+
y_ 59
|
37
|
+
u 59
|
38
|
+
_di 58
|
39
|
+
_s 57
|
40
|
+
et 56
|
41
|
+
_n 56
|
42
|
+
_m 53
|
43
|
+
die 51
|
44
|
+
b 50
|
45
|
+
te 48
|
46
|
+
ee 47
|
47
|
+
ni 46
|
48
|
+
_w 46
|
49
|
+
in 46
|
50
|
+
_die 45
|
51
|
+
die_ 45
|
52
|
+
an_ 45
|
53
|
+
et_ 44
|
54
|
+
_e 43
|
55
|
+
p 43
|
56
|
+
de 42
|
57
|
+
_die_ 41
|
58
|
+
_o 40
|
59
|
+
._ 36
|
60
|
+
nd 36
|
61
|
+
_g 35
|
62
|
+
el 35
|
63
|
+
ar 35
|
64
|
+
at 35
|
65
|
+
nie 34
|
66
|
+
oe 34
|
67
|
+
k_ 34
|
68
|
+
wa 34
|
69
|
+
_ni 33
|
70
|
+
, 33
|
71
|
+
_a 33
|
72
|
+
he 32
|
73
|
+
oo 32
|
74
|
+
g_ 32
|
75
|
+
_nie 32
|
76
|
+
ek 30
|
77
|
+
,_ 30
|
78
|
+
om 29
|
79
|
+
_i 29
|
80
|
+
en_ 28
|
81
|
+
me 28
|
82
|
+
va 28
|
83
|
+
_k 28
|
84
|
+
_he 28
|
85
|
+
aan 28
|
86
|
+
_wa 28
|
87
|
+
is 27
|
88
|
+
_en 26
|
89
|
+
f 26
|
90
|
+
at_ 26
|
91
|
+
_ge 26
|
92
|
+
es 25
|
93
|
+
or 25
|
94
|
+
it 24
|
95
|
+
as 24
|
96
|
+
_t 24
|
97
|
+
ma 24
|
98
|
+
er_ 24
|
99
|
+
on 24
|
100
|
+
_b 24
|
101
|
+
m_ 24
|
102
|
+
l_ 24
|
103
|
+
het 24
|
104
|
+
aar 24
|
105
|
+
d_ 23
|
106
|
+
van 23
|
107
|
+
li 22
|
108
|
+
_het 22
|
109
|
+
ou 22
|
110
|
+
ra 22
|
111
|
+
_va 21
|
112
|
+
be 21
|
113
|
+
het_ 21
|
114
|
+
" 21
|
115
|
+
_het_ 20
|
116
|
+
rd 20
|
117
|
+
ng 20
|
118
|
+
om_ 20
|
119
|
+
al 20
|
120
|
+
da 20
|
121
|
+
_van 19
|
122
|
+
st 19
|
123
|
+
ke 19
|
124
|
+
' 19
|
125
|
+
_en_ 19
|
126
|
+
sy 18
|
127
|
+
ag 18
|
128
|
+
is_ 18
|
129
|
+
sy_ 18
|
130
|
+
van_ 18
|
131
|
+
te_ 18
|
132
|
+
re 17
|
133
|
+
and 17
|
134
|
+
aar_ 17
|
135
|
+
se 17
|
136
|
+
ro 17
|
137
|
+
- 17
|
138
|
+
_van_ 17
|
139
|
+
hy 17
|
140
|
+
le 17
|
141
|
+
der 17
|
142
|
+
ar_ 17
|
143
|
+
nde 17
|
144
|
+
_ma 17
|
145
|
+
_hy 16
|
146
|
+
_me 16
|
147
|
+
H 16
|
148
|
+
we 16
|
149
|
+
as_ 16
|
150
|
+
ei 16
|
151
|
+
aan_ 16
|
152
|
+
ns 15
|
153
|
+
ik 15
|
154
|
+
ho 15
|
155
|
+
em 15
|
156
|
+
so 15
|
157
|
+
nie_ 15
|
158
|
+
_sy_ 15
|
159
|
+
_sy 15
|
160
|
+
_' 15
|
161
|
+
ko 15
|
162
|
+
it_ 15
|
163
|
+
_H 15
|
164
|
+
ig 15
|
165
|
+
'n 14
|
166
|
+
hy_ 14
|
167
|
+
mo 14
|
168
|
+
ha 14
|
169
|
+
vi 14
|
170
|
+
ve 14
|
171
|
+
nt 14
|
172
|
+
_nie_ 14
|
173
|
+
vo 14
|
174
|
+
rs 14
|
175
|
+
si 14
|
176
|
+
in_ 14
|
177
|
+
ou_ 13
|
178
|
+
'n_ 13
|
179
|
+
_in 13
|
180
|
+
_be 13
|
181
|
+
_'n 13
|
182
|
+
_'n_ 13
|
183
|
+
no 13
|
184
|
+
_vi 13
|
185
|
+
_hy_ 13
|
186
|
+
rt 13
|
187
|
+
u_ 13
|
188
|
+
ag_ 13
|
189
|
+
op 13
|
190
|
+
e, 13
|
191
|
+
wo 13
|
192
|
+
eer 13
|
193
|
+
ed 12
|
194
|
+
ing 12
|
195
|
+
ne 12
|
196
|
+
e,_ 12
|
197
|
+
ver 12
|
198
|
+
ew 12
|
199
|
+
_te_ 12
|
200
|
+
ek_ 12
|
201
|
+
_vo 12
|
202
|
+
_is 12
|
203
|
+
was 12
|
204
|
+
_te 12
|
205
|
+
_om 12
|
206
|
+
_om_ 12
|
207
|
+
wat 12
|
208
|
+
al_ 12
|
209
|
+
_is_ 11
|
210
|
+
bl 11
|
211
|
+
ta 11
|
212
|
+
_mo 11
|
213
|
+
_no 11
|
214
|
+
_so 11
|
215
|
+
moe 11
|
216
|
+
ord 11
|
217
|
+
met 11
|
218
|
+
maa 11
|
219
|
+
_was 11
|
220
|
+
ka 11
|
221
|
+
vir 11
|
222
|
+
ir 11
|
223
|
+
_on 11
|
224
|
+
vir_ 11
|
225
|
+
_ko 11
|
226
|
+
ir_ 11
|
227
|
+
_p 11
|
228
|
+
wat_ 11
|
229
|
+
e. 11
|
230
|
+
S 11
|
231
|
+
met_ 10
|
232
|
+
sie 10
|
233
|
+
p_ 10
|
234
|
+
nge 10
|
235
|
+
was_ 10
|
236
|
+
vr 10
|
237
|
+
_aa 10
|
238
|
+
to 10
|
239
|
+
_ha 10
|
240
|
+
ers 10
|
241
|
+
raa 10
|
242
|
+
_in_ 10
|
243
|
+
oor 10
|
244
|
+
ri 10
|
245
|
+
nder 10
|
246
|
+
eg 10
|
247
|
+
lik 10
|
248
|
+
E 10
|
249
|
+
ui 10
|
250
|
+
_da 10
|
251
|
+
_ve 10
|
252
|
+
sta 10
|
253
|
+
nk 10
|
254
|
+
f_ 10
|
255
|
+
_vir 10
|
256
|
+
_was_ 10
|
257
|
+
_aan 10
|
258
|
+
_vir_ 10
|
259
|
+
_ver 9
|
260
|
+
ges 9
|
261
|
+
ie. 9
|
262
|
+
ll 9
|
263
|
+
man 9
|
264
|
+
_met 9
|
265
|
+
de_ 9
|
266
|
+
_ho 9
|
267
|
+
_vr 9
|
268
|
+
_moe 9
|
269
|
+
pr 9
|
270
|
+
el_ 9
|
271
|
+
_ek 9
|
272
|
+
_maa 9
|
273
|
+
Hy 9
|
274
|
+
_wat 9
|
275
|
+
og 9
|
276
|
+
." 9
|
277
|
+
_se 9
|
278
|
+
A 9
|
279
|
+
_met_ 9
|
280
|
+
rte 8
|
281
|
+
_l 8
|
282
|
+
_my 8
|
283
|
+
aat 8
|
284
|
+
M 8
|
285
|
+
wor 8
|
286
|
+
_Hy 8
|
287
|
+
_my_ 8
|
288
|
+
ga 8
|
289
|
+
my_ 8
|
290
|
+
een 8
|
291
|
+
my 8
|
292
|
+
es_ 8
|
293
|
+
Hy_ 8
|
294
|
+
_op 8
|
295
|
+
din 8
|
296
|
+
kl 8
|
297
|
+
_Hy_ 8
|
298
|
+
taa 8
|
299
|
+
_ek_ 8
|
300
|
+
ewe 8
|
301
|
+
_to 8
|
302
|
+
j 8
|
303
|
+
eu 8
|
304
|
+
ak 8
|
305
|
+
sk 8
|
306
|
+
_nie. 8
|
307
|
+
_r 8
|
308
|
+
word 8
|
309
|
+
nie. 8
|
310
|
+
na 8
|
311
|
+
_al 8
|
312
|
+
_wat_ 8
|
313
|
+
pa 8
|
314
|
+
D 8
|
315
|
+
le_ 7
|
316
|
+
erd 7
|
317
|
+
uit 7
|
318
|
+
br 7
|
319
|
+
staa 7
|
320
|
+
a_ 7
|
321
|
+
op_ 7
|
322
|
+
_pr 7
|
323
|
+
ier 7
|
324
|
+
er. 7
|
325
|
+
lin 7
|
326
|
+
_maar 7
|
327
|
+
oe_ 7
|
328
|
+
nd_ 7
|
329
|
+
id 7
|
330
|
+
do 7
|
331
|
+
ders 7
|
332
|
+
ke_ 7
|
333
|
+
_ges 7
|
334
|
+
r. 7
|
335
|
+
gew 7
|
336
|
+
ie,_ 7
|
337
|
+
end 7
|
338
|
+
_st 7
|
339
|
+
O 7
|
340
|
+
tee 7
|
341
|
+
ur 7
|
342
|
+
dit 7
|
343
|
+
gaan 7
|
344
|
+
_ne 7
|
345
|
+
wee 7
|
346
|
+
ger 7
|
347
|
+
oet 7
|
348
|
+
s. 7
|
349
|
+
maar 7
|
350
|
+
ie, 7
|
351
|
+
maar_ 7
|
352
|
+
gaa 7
|
353
|
+
_dit 7
|
354
|
+
og_ 7
|
355
|
+
la 7
|
356
|
+
ste 7
|
357
|
+
nog 6
|
358
|
+
eer_ 6
|
359
|
+
_bl 6
|
360
|
+
_hier 6
|
361
|
+
_hi 6
|
362
|
+
ns_ 6
|
363
|
+
gaan_ 6
|
364
|
+
toe 6
|
365
|
+
yd 6
|
366
|
+
lle 6
|
367
|
+
ens 6
|
368
|
+
eur 6
|
369
|
+
_u 6
|
370
|
+
nders 6
|
371
|
+
dat_ 6
|
372
|
+
os 6
|
373
|
+
hi 6
|
374
|
+
eid 6
|
375
|
+
_wo 6
|
376
|
+
t. 6
|
377
|
+
_uit 6
|
378
|
+
ert 6
|
379
|
+
_as 6
|
380
|
+
nda 6
|
381
|
+
aak 6
|
382
|
+
ng_ 6
|
383
|
+
ind 6
|
384
|
+
dat 6
|
385
|
+
mer 6
|
386
|
+
oet_ 6
|
387
|
+
nie, 6
|
388
|
+
_nie, 6
|
389
|
+
rs_ 6
|
390
|
+
nig 6
|
391
|
+
lo 6
|
392
|
+
e._ 6
|
393
|
+
r,_ 6
|
394
|
+
ie._ 6
|
395
|
+
ad 6
|
396
|
+
hier 6
|
397
|
+
am 6
|
398
|
+
eke 6
|
399
|
+
ige 6
|
400
|
+
eli 6
|