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
|
+
_ 962
|
2
|
+
a 844
|
3
|
+
n 323
|
4
|
+
i 270
|
5
|
+
u 256
|
6
|
+
h 194
|
7
|
+
t 186
|
8
|
+
s 185
|
9
|
+
y 169
|
10
|
+
k 165
|
11
|
+
q 164
|
12
|
+
p 155
|
13
|
+
c 150
|
14
|
+
m 149
|
15
|
+
r 137
|
16
|
+
ch 136
|
17
|
+
a_ 130
|
18
|
+
an 126
|
19
|
+
ta 119
|
20
|
+
ay 106
|
21
|
+
qa 104
|
22
|
+
e 96
|
23
|
+
ma 96
|
24
|
+
ha 96
|
25
|
+
pa 88
|
26
|
+
l 84
|
27
|
+
ku 79
|
28
|
+
j 76
|
29
|
+
na 74
|
30
|
+
o 73
|
31
|
+
cha 69
|
32
|
+
, 66
|
33
|
+
in 66
|
34
|
+
as 60
|
35
|
+
un 58
|
36
|
+
ar 57
|
37
|
+
,_ 54
|
38
|
+
man 52
|
39
|
+
ac 48
|
40
|
+
am 44
|
41
|
+
_k 42
|
42
|
+
nt 42
|
43
|
+
n_ 42
|
44
|
+
ri 42
|
45
|
+
at 42
|
46
|
+
w 41
|
47
|
+
qa_ 41
|
48
|
+
ach 39
|
49
|
+
ka 38
|
50
|
+
_m 38
|
51
|
+
y_ 38
|
52
|
+
pi 37
|
53
|
+
sq 37
|
54
|
+
ta_ 37
|
55
|
+
__ 37
|
56
|
+
. 36
|
57
|
+
wa 36
|
58
|
+
nc 36
|
59
|
+
sqa 35
|
60
|
+
hu 35
|
61
|
+
rq 35
|
62
|
+
uy 34
|
63
|
+
nch 34
|
64
|
+
i_ 34
|
65
|
+
_p 34
|
66
|
+
aj 34
|
67
|
+
rqa 34
|
68
|
+
aq 32
|
69
|
+
a, 32
|
70
|
+
sp 32
|
71
|
+
hay 31
|
72
|
+
ata 31
|
73
|
+
una 31
|
74
|
+
nta 31
|
75
|
+
us 30
|
76
|
+
ll 29
|
77
|
+
ni 29
|
78
|
+
_ma 29
|
79
|
+
ay_ 28
|
80
|
+
is 28
|
81
|
+
a,_ 27
|
82
|
+
' 27
|
83
|
+
spa 27
|
84
|
+
_ka 27
|
85
|
+
_c 26
|
86
|
+
ya 26
|
87
|
+
hi 26
|
88
|
+
ama 26
|
89
|
+
_s 25
|
90
|
+
_ch 25
|
91
|
+
kun 25
|
92
|
+
chay 24
|
93
|
+
ant 24
|
94
|
+
la 24
|
95
|
+
acha 24
|
96
|
+
ti 24
|
97
|
+
ik 23
|
98
|
+
yk 23
|
99
|
+
u_ 23
|
100
|
+
chu 22
|
101
|
+
nk 22
|
102
|
+
he 22
|
103
|
+
ari 22
|
104
|
+
an_ 21
|
105
|
+
ak 21
|
106
|
+
kuna 21
|
107
|
+
lla 21
|
108
|
+
chi 21
|
109
|
+
a. 21
|
110
|
+
._ 21
|
111
|
+
ap 20
|
112
|
+
taj 20
|
113
|
+
su 20
|
114
|
+
s_ 20
|
115
|
+
anta 20
|
116
|
+
_t 20
|
117
|
+
anch 20
|
118
|
+
ayk 20
|
119
|
+
tu 20
|
120
|
+
al 20
|
121
|
+
uk 20
|
122
|
+
anc 20
|
123
|
+
yt 19
|
124
|
+
ki 19
|
125
|
+
ana 19
|
126
|
+
aw 19
|
127
|
+
na_ 19
|
128
|
+
im 19
|
129
|
+
ra 19
|
130
|
+
_q 18
|
131
|
+
asqa 18
|
132
|
+
_a 18
|
133
|
+
st 18
|
134
|
+
asq 18
|
135
|
+
_n 18
|
136
|
+
sqa_ 18
|
137
|
+
nin 18
|
138
|
+
yta 18
|
139
|
+
awa 18
|
140
|
+
qan 18
|
141
|
+
iku 17
|
142
|
+
J 17
|
143
|
+
arq 17
|
144
|
+
j_ 17
|
145
|
+
A 17
|
146
|
+
� 17
|
147
|
+
_pa 17
|
148
|
+
che 16
|
149
|
+
ncha 16
|
150
|
+
yn 16
|
151
|
+
_j 16
|
152
|
+
_r 16
|
153
|
+
os 16
|
154
|
+
_chay 16
|
155
|
+
kuy 16
|
156
|
+
pi_ 16
|
157
|
+
q_ 16
|
158
|
+
arqa 16
|
159
|
+
_cha 16
|
160
|
+
aq_ 15
|
161
|
+
_man 15
|
162
|
+
up 15
|
163
|
+
a._ 15
|
164
|
+
si 15
|
165
|
+
pa_ 14
|
166
|
+
_i 14
|
167
|
+
nku 14
|
168
|
+
mp 14
|
169
|
+
ru 14
|
170
|
+
man_ 14
|
171
|
+
ej 14
|
172
|
+
mant 14
|
173
|
+
rik 14
|
174
|
+
aman 14
|
175
|
+
ayku 14
|
176
|
+
yku 14
|
177
|
+
manta 14
|
178
|
+
ur 13
|
179
|
+
er 13
|
180
|
+
_J 13
|
181
|
+
pu 13
|
182
|
+
ayt 13
|
183
|
+
taq 13
|
184
|
+
ank 13
|
185
|
+
nta_ 13
|
186
|
+
en 13
|
187
|
+
�a 13
|
188
|
+
ina 13
|
189
|
+
all 13
|
190
|
+
C 13
|
191
|
+
ima 13
|
192
|
+
um 12
|
193
|
+
ayta 12
|
194
|
+
aku 12
|
195
|
+
mi 12
|
196
|
+
erqa 12
|
197
|
+
mu 12
|
198
|
+
uc 12
|
199
|
+
tin 12
|
200
|
+
li 12
|
201
|
+
ancha 12
|
202
|
+
it 12
|
203
|
+
� 12
|
204
|
+
nan 12
|
205
|
+
_y 12
|
206
|
+
n, 12
|
207
|
+
uch 12
|
208
|
+
nq 12
|
209
|
+
_u 12
|
210
|
+
es 12
|
211
|
+
aj_ 12
|
212
|
+
erq 12
|
213
|
+
_h 11
|
214
|
+
pay 11
|
215
|
+
yta_ 11
|
216
|
+
g 11
|
217
|
+
_su 11
|
218
|
+
iy 11
|
219
|
+
M 11
|
220
|
+
'a 11
|
221
|
+
ut 11
|
222
|
+
Ch 11
|
223
|
+
taq_ 11
|
224
|
+
_w 11
|
225
|
+
uma 10
|
226
|
+
n,_ 10
|
227
|
+
qa, 10
|
228
|
+
yni 10
|
229
|
+
asp 10
|
230
|
+
sta 10
|
231
|
+
chej 10
|
232
|
+
mana 10
|
233
|
+
ku_ 10
|
234
|
+
qh 10
|
235
|
+
ray 10
|
236
|
+
io 10
|
237
|
+
har 10
|
238
|
+
yp 10
|
239
|
+
_C 10
|
240
|
+
hej 10
|
241
|
+
kh 10
|
242
|
+
hay_ 10
|
243
|
+
_tu 10
|
244
|
+
riku 10
|
245
|
+
ia 10
|
246
|
+
khu 9
|
247
|
+
ypi 9
|
248
|
+
kay 9
|
249
|
+
anku 9
|
250
|
+
inc 9
|
251
|
+
usq 9
|
252
|
+
nche 9
|
253
|
+
uya 9
|
254
|
+
nqa 9
|
255
|
+
ayn 9
|
256
|
+
_pu 9
|
257
|
+
qha 9
|
258
|
+
ita 9
|
259
|
+
Je 9
|
260
|
+
ynin 9
|
261
|
+
K 9
|
262
|
+
nchej 9
|
263
|
+
ir 9
|
264
|
+
ha_ 9
|
265
|
+
rqan 9
|
266
|
+
_mana 9
|
267
|
+
rqa_ 9
|
268
|
+
aspa 9
|
269
|
+
may 9
|
270
|
+
asqa_ 9
|
271
|
+
: 9
|
272
|
+
ayp 9
|
273
|
+
qo 9
|
274
|
+
qay 9
|
275
|
+
_ni 9
|
276
|
+
usqa 9
|
277
|
+
ta, 9
|
278
|
+
in_ 9
|
279
|
+
ne 9
|
280
|
+
Jes 9
|
281
|
+
_Ch 9
|
282
|
+
_wa 8
|
283
|
+
nas 8
|
284
|
+
manch 8
|
285
|
+
S 8
|
286
|
+
spa, 8
|
287
|
+
_Dios 8
|
288
|
+
_l 8
|
289
|
+
pac 8
|
290
|
+
_qh 8
|
291
|
+
yki 8
|
292
|
+
tukuy 8
|
293
|
+
qa,_ 8
|
294
|
+
yq 8
|
295
|
+
_Di 8
|
296
|
+
kar 8
|
297
|
+
aypi 8
|
298
|
+
upa 8
|
299
|
+
tuku 8
|
300
|
+
sn 8
|
301
|
+
re 8
|
302
|
+
int 8
|
303
|
+
api 8
|
304
|
+
alla 8
|
305
|
+
taj_ 8
|
306
|
+
una_ 8
|
307
|
+
inch 8
|
308
|
+
oq 8
|
309
|
+
sus 8
|
310
|
+
Di 8
|
311
|
+
ataj 8
|
312
|
+
uku 8
|
313
|
+
pa,_ 8
|
314
|
+
d 8
|
315
|
+
_D 8
|
316
|
+
apa 8
|
317
|
+
sa 8
|
318
|
+
ast 8
|
319
|
+
Ma 8
|
320
|
+
lo 8
|
321
|
+
D 8
|
322
|
+
kus 8
|
323
|
+
_ya 8
|
324
|
+
ios 8
|
325
|
+
anta_ 8
|
326
|
+
arik 8
|
327
|
+
Dio 8
|
328
|
+
ja 8
|
329
|
+
Dios 8
|
330
|
+
inta 8
|
331
|
+
Cha 8
|
332
|
+
ukuy 8
|
333
|
+
ana_ 8
|
334
|
+
spa,_ 8
|
335
|
+
wan 8
|
336
|
+
au 8
|
337
|
+
_Dio 8
|
338
|
+
tuk 8
|
339
|
+
run 8
|
340
|
+
cha_ 8
|
341
|
+
pa, 8
|
342
|
+
ayq 8
|
343
|
+
manc 8
|
344
|
+
_pay 8
|
345
|
+
nat 7
|
346
|
+
Chay 7
|
347
|
+
_im 7
|
348
|
+
ikun 7
|
349
|
+
paj 7
|
350
|
+
_ima 7
|
351
|
+
yqa 7
|
352
|
+
chay_ 7
|
353
|
+
_M 7
|
354
|
+
aj, 7
|
355
|
+
aman_ 7
|
356
|
+
ikuna 7
|
357
|
+
nata 7
|
358
|
+
unc 7
|
359
|
+
_tuk 7
|
360
|
+
_tuku 7
|
361
|
+
ariku 7
|
362
|
+
paq 7
|
363
|
+
_kar 7
|
364
|
+
mpa 7
|
365
|
+
r� 7
|
366
|
+
e_ 7
|
367
|
+
Jesus 7
|
368
|
+
pat 7
|
369
|
+
an, 7
|
370
|
+
_ku 7
|
371
|
+
pach 7
|
372
|
+
mana_ 7
|
373
|
+
L 7
|
374
|
+
em 7
|
375
|
+
jt 7
|
376
|
+
ispa 7
|
377
|
+
sqan 7
|
378
|
+
mach 7
|
379
|
+
i, 7
|
380
|
+
kay_ 7
|
381
|
+
_may 7
|
382
|
+
rayku 7
|
383
|
+
rin 7
|
384
|
+
ayqa 7
|
385
|
+
ta,_ 7
|
386
|
+
kuna_ 7
|
387
|
+
achi 7
|
388
|
+
uspa 7
|
389
|
+
ym 7
|
390
|
+
:_ 7
|
391
|
+
Jesu 7
|
392
|
+
was 7
|
393
|
+
j, 7
|
394
|
+
or 7
|
395
|
+
mac 7
|
396
|
+
_qha 7
|
397
|
+
esu 7
|
398
|
+
usp 7
|
399
|
+
ic 7
|
400
|
+
ayta_ 7
|