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
|
+
_ 8664
|
2
|
+
o 2534
|
3
|
+
i 2204
|
4
|
+
a 2154
|
5
|
+
e 2086
|
6
|
+
t 1488
|
7
|
+
n 1469
|
8
|
+
r 1262
|
9
|
+
o_ 1097
|
10
|
+
l 974
|
11
|
+
s 937
|
12
|
+
k 880
|
13
|
+
m 777
|
14
|
+
u 677
|
15
|
+
p 676
|
16
|
+
d 558
|
17
|
+
a_ 556
|
18
|
+
v 516
|
19
|
+
. 514
|
20
|
+
, 475
|
21
|
+
,_ 475
|
22
|
+
._ 415
|
23
|
+
g 379
|
24
|
+
i_ 365
|
25
|
+
f 327
|
26
|
+
e_ 323
|
27
|
+
_a 322
|
28
|
+
_p 311
|
29
|
+
_s 296
|
30
|
+
_i 295
|
31
|
+
ti 294
|
32
|
+
b 291
|
33
|
+
an 291
|
34
|
+
j 281
|
35
|
+
c 274
|
36
|
+
ta 272
|
37
|
+
_k 271
|
38
|
+
nt 270
|
39
|
+
_t 268
|
40
|
+
_n 266
|
41
|
+
en 262
|
42
|
+
to 254
|
43
|
+
ek 249
|
44
|
+
on 249
|
45
|
+
al 248
|
46
|
+
_e 245
|
47
|
+
ri 237
|
48
|
+
te 236
|
49
|
+
ro 235
|
50
|
+
_d 228
|
51
|
+
er 218
|
52
|
+
_m 218
|
53
|
+
re 217
|
54
|
+
li 213
|
55
|
+
in 210
|
56
|
+
ra 208
|
57
|
+
z 207
|
58
|
+
no 204
|
59
|
+
st 201
|
60
|
+
ia 199
|
61
|
+
h 191
|
62
|
+
lo 189
|
63
|
+
_f 183
|
64
|
+
tr 179
|
65
|
+
io 172
|
66
|
+
to_ 172
|
67
|
+
vo 172
|
68
|
+
at 172
|
69
|
+
_o 171
|
70
|
+
po 168
|
71
|
+
me 163
|
72
|
+
om 162
|
73
|
+
or 161
|
74
|
+
ko 158
|
75
|
+
de 156
|
76
|
+
� 151
|
77
|
+
ŭ 151
|
78
|
+
� 151
|
79
|
+
_v 150
|
80
|
+
o. 148
|
81
|
+
ne 148
|
82
|
+
pr 146
|
83
|
+
ci 139
|
84
|
+
a� 138
|
85
|
+
aŭ 138
|
86
|
+
ma 137
|
87
|
+
la 136
|
88
|
+
n_ 135
|
89
|
+
iv 134
|
90
|
+
il 130
|
91
|
+
it 130
|
92
|
+
et 128
|
93
|
+
_h 126
|
94
|
+
mo 123
|
95
|
+
es 120
|
96
|
+
em 120
|
97
|
+
_ne 119
|
98
|
+
is 119
|
99
|
+
ol 118
|
100
|
+
o, 116
|
101
|
+
o,_ 116
|
102
|
+
o._ 116
|
103
|
+
s_ 115
|
104
|
+
ar 115
|
105
|
+
mi 115
|
106
|
+
el 113
|
107
|
+
ni 112
|
108
|
+
ant 112
|
109
|
+
pe 111
|
110
|
+
_r 108
|
111
|
+
ie 107
|
112
|
+
no_ 106
|
113
|
+
ig 105
|
114
|
+
le 105
|
115
|
+
do 105
|
116
|
+
vi 101
|
117
|
+
ro_ 99
|
118
|
+
_pr 99
|
119
|
+
un 97
|
120
|
+
_de 96
|
121
|
+
gi 96
|
122
|
+
ta_ 96
|
123
|
+
l_ 95
|
124
|
+
_l 95
|
125
|
+
tiv 93
|
126
|
+
va 92
|
127
|
+
ka 92
|
128
|
+
su 92
|
129
|
+
ks 92
|
130
|
+
os 91
|
131
|
+
am 90
|
132
|
+
se 90
|
133
|
+
si 89
|
134
|
+
r_ 89
|
135
|
+
na 88
|
136
|
+
ono 87
|
137
|
+
ki 87
|
138
|
+
_ek 85
|
139
|
+
pl 84
|
140
|
+
_se 80
|
141
|
+
rt 79
|
142
|
+
ter 79
|
143
|
+
_al 78
|
144
|
+
_su 78
|
145
|
+
ati 78
|
146
|
+
j_ 77
|
147
|
+
lo_ 77
|
148
|
+
nd 77
|
149
|
+
_po 77
|
150
|
+
fi 76
|
151
|
+
pa 75
|
152
|
+
_an 75
|
153
|
+
_ti 74
|
154
|
+
nta 74
|
155
|
+
sa 74
|
156
|
+
ent 74
|
157
|
+
_b 74
|
158
|
+
_u 73
|
159
|
+
eks 73
|
160
|
+
nu 73
|
161
|
+
_g 72
|
162
|
+
ik 72
|
163
|
+
ns 71
|
164
|
+
_tr 71
|
165
|
+
kr 71
|
166
|
+
fr 71
|
167
|
+
m_ 70
|
168
|
+
_j 70
|
169
|
+
di 70
|
170
|
+
ec 70
|
171
|
+
ga 70
|
172
|
+
_ki 70
|
173
|
+
t_ 69
|
174
|
+
ng 69
|
175
|
+
ost 69
|
176
|
+
a, 67
|
177
|
+
a,_ 67
|
178
|
+
sk 66
|
179
|
+
ia_ 66
|
180
|
+
do_ 65
|
181
|
+
so 65
|
182
|
+
io_ 65
|
183
|
+
_re 65
|
184
|
+
per 65
|
185
|
+
ok 65
|
186
|
+
_ko 64
|
187
|
+
ku 64
|
188
|
+
nte 64
|
189
|
+
_c 64
|
190
|
+
_in 64
|
191
|
+
nk 63
|
192
|
+
ta� 62
|
193
|
+
taŭ 62
|
194
|
+
en_ 62
|
195
|
+
fa 62
|
196
|
+
mp 61
|
197
|
+
ed 61
|
198
|
+
anta 60
|
199
|
+
az 60
|
200
|
+
k_ 60
|
201
|
+
v_ 60
|
202
|
+
ve 60
|
203
|
+
_ma 59
|
204
|
+
u_ 59
|
205
|
+
du 58
|
206
|
+
ort 58
|
207
|
+
kt 58
|
208
|
+
mo_ 58
|
209
|
+
vo_ 57
|
210
|
+
d_ 57
|
211
|
+
ili 57
|
212
|
+
zo 57
|
213
|
+
_vi 57
|
214
|
+
ali 57
|
215
|
+
je 57
|
216
|
+
igi 57
|
217
|
+
ur 57
|
218
|
+
era 56
|
219
|
+
_du 55
|
220
|
+
ativ 55
|
221
|
+
da 55
|
222
|
+
id 55
|
223
|
+
_fr 54
|
224
|
+
S 54
|
225
|
+
_mi 54
|
226
|
+
ub 54
|
227
|
+
fo 54
|
228
|
+
ic 54
|
229
|
+
sp 54
|
230
|
+
nto 53
|
231
|
+
_ali 53
|
232
|
+
ho 53
|
233
|
+
fra 53
|
234
|
+
ad 53
|
235
|
+
sub 52
|
236
|
+
a. 52
|
237
|
+
pre 52
|
238
|
+
nom 52
|
239
|
+
uo 52
|
240
|
+
ke 52
|
241
|
+
oj 51
|
242
|
+
i,_ 51
|
243
|
+
i, 51
|
244
|
+
im 51
|
245
|
+
iva 51
|
246
|
+
mal 51
|
247
|
+
ivo 51
|
248
|
+
sta 51
|
249
|
+
kri 51
|
250
|
+
um 50
|
251
|
+
i. 50
|
252
|
+
vor 50
|
253
|
+
vort 50
|
254
|
+
I 50
|
255
|
+
post 49
|
256
|
+
ez 49
|
257
|
+
tro 49
|
258
|
+
ko_ 49
|
259
|
+
eko 49
|
260
|
+
pos 49
|
261
|
+
_sub 48
|
262
|
+
ono_ 48
|
263
|
+
ir 48
|
264
|
+
go 48
|
265
|
+
bi 48
|
266
|
+
he 48
|
267
|
+
_pl 47
|
268
|
+
ul 47
|
269
|
+
lt 47
|
270
|
+
bl 47
|
271
|
+
tivo 47
|
272
|
+
ri_ 46
|
273
|
+
_vo 46
|
274
|
+
� 46
|
275
|
+
fin 46
|
276
|
+
re_ 46
|
277
|
+
lu 46
|
278
|
+
_te 46
|
279
|
+
ze 46
|
280
|
+
_mal 46
|
281
|
+
alo 45
|
282
|
+
_nu 45
|
283
|
+
nti 44
|
284
|
+
str 44
|
285
|
+
pro 44
|
286
|
+
tu 44
|
287
|
+
i._ 44
|
288
|
+
kv 44
|
289
|
+
eni 44
|
290
|
+
ej 43
|
291
|
+
ma_ 43
|
292
|
+
ep 43
|
293
|
+
_fra 43
|
294
|
+
_he 42
|
295
|
+
gi_ 42
|
296
|
+
_pe 42
|
297
|
+
ntaŭ 42
|
298
|
+
vol 42
|
299
|
+
raz 42
|
300
|
+
nta� 42
|
301
|
+
anta� 42
|
302
|
+
_me 41
|
303
|
+
fraz 41
|
304
|
+
skri 41
|
305
|
+
skr 41
|
306
|
+
a� 41
|
307
|
+
rto 41
|
308
|
+
nst 40
|
309
|
+
_eks 40
|
310
|
+
tra 40
|
311
|
+
_fo 40
|
312
|
+
bo 40
|
313
|
+
tiva 40
|
314
|
+
ra_ 40
|
315
|
+
ot 40
|
316
|
+
ivo_ 40
|
317
|
+
_ant 40
|
318
|
+
ren 40
|
319
|
+
_ci 40
|
320
|
+
ib 40
|
321
|
+
tivo_ 40
|
322
|
+
a._ 39
|
323
|
+
omo 39
|
324
|
+
ce 39
|
325
|
+
int 39
|
326
|
+
ita 38
|
327
|
+
cio 38
|
328
|
+
zo_ 38
|
329
|
+
_vol 38
|
330
|
+
jo 38
|
331
|
+
_si 38
|
332
|
+
_ho 38
|
333
|
+
_I 38
|
334
|
+
lon 38
|
335
|
+
e,_ 38
|
336
|
+
ba 38
|
337
|
+
_pa 38
|
338
|
+
e, 38
|
339
|
+
ha 38
|
340
|
+
men 38
|
341
|
+
ilo 37
|
342
|
+
_fa 37
|
343
|
+
iu 37
|
344
|
+
zi 37
|
345
|
+
kom 37
|
346
|
+
met 37
|
347
|
+
tre 37
|
348
|
+
us 37
|
349
|
+
op 36
|
350
|
+
eb 36
|
351
|
+
ĵ 36
|
352
|
+
_mo 36
|
353
|
+
� 36
|
354
|
+
la_ 36
|
355
|
+
nen 36
|
356
|
+
li_ 36
|
357
|
+
A 36
|
358
|
+
_S 36
|
359
|
+
aĵ 36
|
360
|
+
ici 36
|
361
|
+
ano 36
|
362
|
+
ru 35
|
363
|
+
e. 35
|
364
|
+
_nen 35
|
365
|
+
kon 35
|
366
|
+
ka_ 35
|
367
|
+
' 35
|
368
|
+
ome 35
|
369
|
+
K 35
|
370
|
+
go_ 35
|
371
|
+
up 35
|
372
|
+
_ku 35
|
373
|
+
_so 35
|
374
|
+
lio 35
|
375
|
+
ip 35
|
376
|
+
ag 35
|
377
|
+
ado 35
|
378
|
+
emp 35
|
379
|
+
va_ 35
|
380
|
+
eg 35
|
381
|
+
iva_ 35
|
382
|
+
ans 35
|
383
|
+
ion 34
|
384
|
+
_ve 34
|
385
|
+
_ha 34
|
386
|
+
_sa 34
|
387
|
+
sa_ 33
|
388
|
+
rib 33
|
389
|
+
as 33
|
390
|
+
_pos 33
|
391
|
+
_fraz 33
|
392
|
+
_post 33
|
393
|
+
ov 33
|
394
|
+
orto 33
|
395
|
+
_no 33
|
396
|
+
P 33
|
397
|
+
tem 33
|
398
|
+
vorto 33
|
399
|
+
_on 33
|
400
|
+
skrib 33
|