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
|
+
_ 1464
|
2
|
+
y 347
|
3
|
+
d 347
|
4
|
+
a 333
|
5
|
+
n 286
|
6
|
+
e 283
|
7
|
+
r 265
|
8
|
+
i 249
|
9
|
+
o 178
|
10
|
+
l 162
|
11
|
+
h 152
|
12
|
+
g 125
|
13
|
+
f 124
|
14
|
+
w 122
|
15
|
+
t 122
|
16
|
+
_y 116
|
17
|
+
n_ 107
|
18
|
+
dd 106
|
19
|
+
u 98
|
20
|
+
m 88
|
21
|
+
s 86
|
22
|
+
yn 85
|
23
|
+
c 80
|
24
|
+
d_ 80
|
25
|
+
r_ 80
|
26
|
+
_a 66
|
27
|
+
yd 65
|
28
|
+
th 64
|
29
|
+
yn_ 62
|
30
|
+
. 59
|
31
|
+
ym 51
|
32
|
+
i_ 51
|
33
|
+
_yn 50
|
34
|
+
_d 50
|
35
|
+
u_ 49
|
36
|
+
l_ 49
|
37
|
+
ydd 49
|
38
|
+
ae 48
|
39
|
+
_i 47
|
40
|
+
_yn_ 46
|
41
|
+
wy 44
|
42
|
+
ra 43
|
43
|
+
an 42
|
44
|
+
ol 42
|
45
|
+
b 41
|
46
|
+
y_ 40
|
47
|
+
ar 40
|
48
|
+
ia 39
|
49
|
+
ei 39
|
50
|
+
' 39
|
51
|
+
di 37
|
52
|
+
_g 37
|
53
|
+
h_ 36
|
54
|
+
ed 35
|
55
|
+
dd_ 34
|
56
|
+
_y_ 34
|
57
|
+
_c 33
|
58
|
+
._ 32
|
59
|
+
'r 32
|
60
|
+
ai 31
|
61
|
+
da 31
|
62
|
+
th_ 30
|
63
|
+
it 30
|
64
|
+
au 30
|
65
|
+
ne 30
|
66
|
+
ith 30
|
67
|
+
er 29
|
68
|
+
_e 29
|
69
|
+
, 29
|
70
|
+
g_ 27
|
71
|
+
en 27
|
72
|
+
'r_ 27
|
73
|
+
od 27
|
74
|
+
de 27
|
75
|
+
p 27
|
76
|
+
yr 26
|
77
|
+
ha 26
|
78
|
+
o_ 26
|
79
|
+
_n 26
|
80
|
+
ddi 26
|
81
|
+
eg 25
|
82
|
+
,_ 25
|
83
|
+
wyd 25
|
84
|
+
_h 25
|
85
|
+
mr 25
|
86
|
+
cy 24
|
87
|
+
_f 24
|
88
|
+
au_ 24
|
89
|
+
hy 24
|
90
|
+
a_ 24
|
91
|
+
ll 24
|
92
|
+
ymr 24
|
93
|
+
ol_ 23
|
94
|
+
if 23
|
95
|
+
io 23
|
96
|
+
_p 23
|
97
|
+
_dd 23
|
98
|
+
G 22
|
99
|
+
ad 22
|
100
|
+
_o 22
|
101
|
+
ny 22
|
102
|
+
ri 22
|
103
|
+
_i_ 22
|
104
|
+
rae 21
|
105
|
+
wn 21
|
106
|
+
ew 21
|
107
|
+
fe 21
|
108
|
+
no 20
|
109
|
+
_. 20
|
110
|
+
_._ 20
|
111
|
+
_s 20
|
112
|
+
_ar 20
|
113
|
+
_cy 20
|
114
|
+
do 19
|
115
|
+
wydd 19
|
116
|
+
ydd_ 19
|
117
|
+
ch 19
|
118
|
+
eth 19
|
119
|
+
__ 19
|
120
|
+
_m 19
|
121
|
+
_G 19
|
122
|
+
yf 19
|
123
|
+
et 19
|
124
|
+
gy 18
|
125
|
+
nyd 18
|
126
|
+
nydd 18
|
127
|
+
la 18
|
128
|
+
at 18
|
129
|
+
aeth 17
|
130
|
+
yr_ 17
|
131
|
+
mrae 17
|
132
|
+
ymra 17
|
133
|
+
eu 17
|
134
|
+
el 17
|
135
|
+
s_ 17
|
136
|
+
ymrae 17
|
137
|
+
ho 17
|
138
|
+
aeg 17
|
139
|
+
mra 17
|
140
|
+
rh 17
|
141
|
+
aet 17
|
142
|
+
mraeg 17
|
143
|
+
ef 17
|
144
|
+
raeg 17
|
145
|
+
Gy 16
|
146
|
+
me 16
|
147
|
+
fa 16
|
148
|
+
aith 16
|
149
|
+
nt 16
|
150
|
+
ni 16
|
151
|
+
ait 16
|
152
|
+
Gym 15
|
153
|
+
ff 15
|
154
|
+
_b 15
|
155
|
+
efn 15
|
156
|
+
we 15
|
157
|
+
_Gy 15
|
158
|
+
Gymr 15
|
159
|
+
le 15
|
160
|
+
er_ 15
|
161
|
+
ac 15
|
162
|
+
fn 15
|
163
|
+
edd 15
|
164
|
+
yddi 15
|
165
|
+
ro 14
|
166
|
+
nn 14
|
167
|
+
_Gymr 14
|
168
|
+
ys 14
|
169
|
+
_yr 14
|
170
|
+
_yr_ 14
|
171
|
+
si 14
|
172
|
+
_Gym 14
|
173
|
+
Gymra 14
|
174
|
+
dde 13
|
175
|
+
efny 13
|
176
|
+
_ei 13
|
177
|
+
al 13
|
178
|
+
eit 13
|
179
|
+
oed 13
|
180
|
+
efnyd 13
|
181
|
+
fny 13
|
182
|
+
fnydd 13
|
183
|
+
eth_ 13
|
184
|
+
oe 13
|
185
|
+
fnyd 13
|
186
|
+
_a_ 13
|
187
|
+
_l 13
|
188
|
+
gw 13
|
189
|
+
defn 13
|
190
|
+
def 13
|
191
|
+
eith 13
|
192
|
+
rha 13
|
193
|
+
defny 13
|
194
|
+
sy 12
|
195
|
+
rif 12
|
196
|
+
c_ 12
|
197
|
+
_w 12
|
198
|
+
aeth_ 12
|
199
|
+
ng 12
|
200
|
+
_hy 12
|
201
|
+
_ne 12
|
202
|
+
ga 12
|
203
|
+
nyddi 12
|
204
|
+
wr 12
|
205
|
+
oedd 12
|
206
|
+
dol 12
|
207
|
+
_gy 12
|
208
|
+
es 12
|
209
|
+
C 12
|
210
|
+
wydd_ 11
|
211
|
+
ar_ 11
|
212
|
+
ig 11
|
213
|
+
_ei_ 11
|
214
|
+
iait 11
|
215
|
+
_me 11
|
216
|
+
rth 11
|
217
|
+
_o_ 11
|
218
|
+
_ia 11
|
219
|
+
ry 11
|
220
|
+
iaith 11
|
221
|
+
rd 11
|
222
|
+
aw 11
|
223
|
+
t_ 11
|
224
|
+
o'r 11
|
225
|
+
rt 11
|
226
|
+
o' 11
|
227
|
+
li 11
|
228
|
+
id 11
|
229
|
+
iai 11
|
230
|
+
re 11
|
231
|
+
ewn 11
|
232
|
+
ei_ 11
|
233
|
+
an_ 10
|
234
|
+
fo 10
|
235
|
+
dda 10
|
236
|
+
dio 10
|
237
|
+
eg_ 10
|
238
|
+
on 10
|
239
|
+
_da 10
|
240
|
+
fr 10
|
241
|
+
ith_ 10
|
242
|
+
yw 10
|
243
|
+
ddio 10
|
244
|
+
wn_ 10
|
245
|
+
na 10
|
246
|
+
_ac 10
|
247
|
+
eu_ 10
|
248
|
+
S 10
|
249
|
+
_dde 10
|
250
|
+
te 10
|
251
|
+
gr 10
|
252
|
+
ad_ 10
|
253
|
+
ddo 10
|
254
|
+
af 10
|
255
|
+
hw 10
|
256
|
+
cr 10
|
257
|
+
f_ 9
|
258
|
+
og 9
|
259
|
+
M 9
|
260
|
+
_gw 9
|
261
|
+
sg 9
|
262
|
+
_t 9
|
263
|
+
os 9
|
264
|
+
un 9
|
265
|
+
il 9
|
266
|
+
o'r_ 9
|
267
|
+
aith_ 9
|
268
|
+
A 9
|
269
|
+
Y 9
|
270
|
+
fy 9
|
271
|
+
Cy 9
|
272
|
+
new 9
|
273
|
+
od_ 9
|
274
|
+
st 9
|
275
|
+
_ym 9
|
276
|
+
yddio 9
|
277
|
+
bl 9
|
278
|
+
fer 9
|
279
|
+
ac_ 9
|
280
|
+
mewn 9
|
281
|
+
dr 9
|
282
|
+
mew 9
|
283
|
+
_ar_ 8
|
284
|
+
dy 8
|
285
|
+
so 8
|
286
|
+
ly 8
|
287
|
+
hr 8
|
288
|
+
_r 8
|
289
|
+
ma 8
|
290
|
+
_iai 8
|
291
|
+
lw 8
|
292
|
+
_C 8
|
293
|
+
cyf 8
|
294
|
+
gwe 8
|
295
|
+
u' 8
|
296
|
+
* 8
|
297
|
+
ic 8
|
298
|
+
_mew 8
|
299
|
+
iad 8
|
300
|
+
or 8
|
301
|
+
ge 8
|
302
|
+
aeg_ 8
|
303
|
+
_ac_ 8
|
304
|
+
he 8
|
305
|
+
raeg_ 8
|
306
|
+
_iait 8
|
307
|
+
E 8
|
308
|
+
_fe 8
|
309
|
+
is 8
|
310
|
+
_mewn 8
|
311
|
+
g, 8
|
312
|
+
_sy 8
|
313
|
+
dia 8
|
314
|
+
in 8
|
315
|
+
.a 7
|
316
|
+
ewyd 7
|
317
|
+
di_ 7
|
318
|
+
han 7
|
319
|
+
nd 7
|
320
|
+
_new 7
|
321
|
+
odol 7
|
322
|
+
_ll 7
|
323
|
+
fl 7
|
324
|
+
rth_ 7
|
325
|
+
_Y 7
|
326
|
+
edd_ 7
|
327
|
+
ddefn 7
|
328
|
+
_eu_ 7
|
329
|
+
nt_ 7
|
330
|
+
i' 7
|
331
|
+
_ddef 7
|
332
|
+
ewn_ 7
|
333
|
+
yg 7
|
334
|
+
Cym 7
|
335
|
+
ent 7
|
336
|
+
my 7
|
337
|
+
_eu 7
|
338
|
+
pa 7
|
339
|
+
u'r 7
|
340
|
+
id_ 7
|
341
|
+
newyd 7
|
342
|
+
oedd_ 7
|
343
|
+
ewydd 7
|
344
|
+
_cyf 7
|
345
|
+
ewy 7
|
346
|
+
_M 7
|
347
|
+
ddef 7
|
348
|
+
du 7
|
349
|
+
m_ 7
|
350
|
+
B 7
|
351
|
+
g. 7
|
352
|
+
w_ 7
|
353
|
+
yd_ 7
|
354
|
+
mewn_ 7
|
355
|
+
yddo 7
|
356
|
+
tr 7
|
357
|
+
dat 7
|
358
|
+
odo 7
|
359
|
+
ll_ 7
|
360
|
+
rw 7
|
361
|
+
gu 7
|
362
|
+
nol 7
|
363
|
+
ig_ 7
|
364
|
+
newy 7
|
365
|
+
ob 7
|
366
|
+
hyn 6
|
367
|
+
hyd 6
|
368
|
+
cyn 6
|
369
|
+
_ga 6
|
370
|
+
a' 6
|
371
|
+
N 6
|
372
|
+
ant 6
|
373
|
+
rwy 6
|
374
|
+
h. 6
|
375
|
+
_i' 6
|
376
|
+
lwyd 6
|
377
|
+
_si 6
|
378
|
+
pe 6
|
379
|
+
fan 6
|
380
|
+
eg, 6
|
381
|
+
gh 6
|
382
|
+
rhau 6
|
383
|
+
dal 6
|
384
|
+
ann 6
|
385
|
+
us 6
|
386
|
+
ian 6
|
387
|
+
_dda 6
|
388
|
+
_pa 6
|
389
|
+
fle 6
|
390
|
+
pr 6
|
391
|
+
I 6
|
392
|
+
_de 6
|
393
|
+
as 6
|
394
|
+
lwy 6
|
395
|
+
fod 6
|
396
|
+
ned 6
|
397
|
+
_ddi 6
|
398
|
+
ir 6
|
399
|
+
rdd 6
|
400
|
+
_rh 6
|