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
|
+
_ 1282
|
2
|
+
a 810
|
3
|
+
i 478
|
4
|
+
a_ 310
|
5
|
+
u 246
|
6
|
+
k 242
|
7
|
+
n 187
|
8
|
+
w 176
|
9
|
+
o 159
|
10
|
+
e 158
|
11
|
+
m 158
|
12
|
+
h 151
|
13
|
+
wa 147
|
14
|
+
l 131
|
15
|
+
s 130
|
16
|
+
t 125
|
17
|
+
i_ 116
|
18
|
+
_k 102
|
19
|
+
y 97
|
20
|
+
ku 76
|
21
|
+
wa_ 75
|
22
|
+
_w 75
|
23
|
+
li 73
|
24
|
+
r 72
|
25
|
+
z 69
|
26
|
+
ka 68
|
27
|
+
_wa 66
|
28
|
+
an 63
|
29
|
+
ma 61
|
30
|
+
ya 59
|
31
|
+
ik 58
|
32
|
+
b 57
|
33
|
+
o_ 57
|
34
|
+
_m 56
|
35
|
+
g 55
|
36
|
+
ha 54
|
37
|
+
na 52
|
38
|
+
j 51
|
39
|
+
am 50
|
40
|
+
d 49
|
41
|
+
f 48
|
42
|
+
at 48
|
43
|
+
is 47
|
44
|
+
hi 46
|
45
|
+
_ku 46
|
46
|
+
ya_ 45
|
47
|
+
u_ 43
|
48
|
+
al 41
|
49
|
+
ki 41
|
50
|
+
ta 40
|
51
|
+
sh 40
|
52
|
+
_y 39
|
53
|
+
ia 39
|
54
|
+
_ya 39
|
55
|
+
ri 39
|
56
|
+
_n 39
|
57
|
+
il 39
|
58
|
+
ti 37
|
59
|
+
e_ 36
|
60
|
+
A 35
|
61
|
+
ni 34
|
62
|
+
_h 34
|
63
|
+
. 34
|
64
|
+
zi 34
|
65
|
+
ng 33
|
66
|
+
_ya_ 33
|
67
|
+
ak 33
|
68
|
+
_wa_ 31
|
69
|
+
ba 30
|
70
|
+
ali 30
|
71
|
+
la 30
|
72
|
+
p 30
|
73
|
+
, 30
|
74
|
+
ar 29
|
75
|
+
na_ 28
|
76
|
+
v 28
|
77
|
+
mb 28
|
78
|
+
_ma 28
|
79
|
+
ika 28
|
80
|
+
ili 27
|
81
|
+
in 26
|
82
|
+
_a 26
|
83
|
+
_u 25
|
84
|
+
as 25
|
85
|
+
ati 25
|
86
|
+
kw 25
|
87
|
+
ia_ 25
|
88
|
+
,_ 24
|
89
|
+
kwa 23
|
90
|
+
si 23
|
91
|
+
za 22
|
92
|
+
ni_ 22
|
93
|
+
_ka 22
|
94
|
+
ka_ 21
|
95
|
+
sa 21
|
96
|
+
hu 21
|
97
|
+
ana 21
|
98
|
+
zi_ 20
|
99
|
+
M 20
|
100
|
+
fa 20
|
101
|
+
un 20
|
102
|
+
_kw 20
|
103
|
+
ut 20
|
104
|
+
kat 20
|
105
|
+
c 20
|
106
|
+
se 20
|
107
|
+
ish 20
|
108
|
+
sha 19
|
109
|
+
di 19
|
110
|
+
_v 19
|
111
|
+
_s 19
|
112
|
+
ch 19
|
113
|
+
_l 19
|
114
|
+
mba 19
|
115
|
+
nd 19
|
116
|
+
kati 19
|
117
|
+
K 19
|
118
|
+
_na 19
|
119
|
+
_na_ 18
|
120
|
+
ja 18
|
121
|
+
amb 18
|
122
|
+
li_ 18
|
123
|
+
_kwa 18
|
124
|
+
ai 18
|
125
|
+
er 18
|
126
|
+
it 18
|
127
|
+
yo 18
|
128
|
+
ma_ 18
|
129
|
+
aa 17
|
130
|
+
ika_ 17
|
131
|
+
mi 16
|
132
|
+
rik 16
|
133
|
+
bi 16
|
134
|
+
fu 16
|
135
|
+
tu 16
|
136
|
+
W 16
|
137
|
+
kwa_ 16
|
138
|
+
a. 16
|
139
|
+
_hi 16
|
140
|
+
ama 16
|
141
|
+
on 16
|
142
|
+
aj 16
|
143
|
+
en 16
|
144
|
+
iki 15
|
145
|
+
_t 15
|
146
|
+
iw 15
|
147
|
+
he 15
|
148
|
+
iz 15
|
149
|
+
la_ 15
|
150
|
+
ao 15
|
151
|
+
ji 15
|
152
|
+
ko 15
|
153
|
+
amba 15
|
154
|
+
_M 15
|
155
|
+
._ 15
|
156
|
+
if 15
|
157
|
+
tik 14
|
158
|
+
em 14
|
159
|
+
_ki 14
|
160
|
+
_A 14
|
161
|
+
ek 14
|
162
|
+
eri 14
|
163
|
+
za_ 14
|
164
|
+
um 14
|
165
|
+
iwa 14
|
166
|
+
_la 14
|
167
|
+
B 14
|
168
|
+
us 14
|
169
|
+
le 14
|
170
|
+
ul 13
|
171
|
+
tika 13
|
172
|
+
ny 13
|
173
|
+
wan 13
|
174
|
+
atika 13
|
175
|
+
uu 13
|
176
|
+
_i 13
|
177
|
+
N 13
|
178
|
+
go 13
|
179
|
+
atik 13
|
180
|
+
_z 13
|
181
|
+
ari 12
|
182
|
+
_ha 12
|
183
|
+
ini 12
|
184
|
+
iy 12
|
185
|
+
pi 12
|
186
|
+
_kwa_ 12
|
187
|
+
ye 12
|
188
|
+
tika_ 12
|
189
|
+
ua 12
|
190
|
+
_K 12
|
191
|
+
af 12
|
192
|
+
aw 12
|
193
|
+
vy 12
|
194
|
+
_j 11
|
195
|
+
uu_ 11
|
196
|
+
vi 11
|
197
|
+
ifa 11
|
198
|
+
au 11
|
199
|
+
kuwa 11
|
200
|
+
Wa 11
|
201
|
+
ra 11
|
202
|
+
I 11
|
203
|
+
ad 11
|
204
|
+
to 11
|
205
|
+
im 11
|
206
|
+
kut 11
|
207
|
+
aki 11
|
208
|
+
mu 11
|
209
|
+
ga 11
|
210
|
+
ke 11
|
211
|
+
az 11
|
212
|
+
ah 11
|
213
|
+
uwa 11
|
214
|
+
uw 11
|
215
|
+
ti_ 11
|
216
|
+
kuw 11
|
217
|
+
katik 11
|
218
|
+
ndi 11
|
219
|
+
ha_ 10
|
220
|
+
we 10
|
221
|
+
me 10
|
222
|
+
da 10
|
223
|
+
uz 10
|
224
|
+
ang 10
|
225
|
+
di_ 10
|
226
|
+
_B 10
|
227
|
+
_kat 10
|
228
|
+
_se 10
|
229
|
+
ay 10
|
230
|
+
a, 10
|
231
|
+
ab 10
|
232
|
+
_ali 10
|
233
|
+
uta 10
|
234
|
+
_kati 10
|
235
|
+
ao_ 10
|
236
|
+
rika 10
|
237
|
+
_al 10
|
238
|
+
ge 10
|
239
|
+
sa_ 10
|
240
|
+
ho 10
|
241
|
+
no 10
|
242
|
+
_W 10
|
243
|
+
es 10
|
244
|
+
_vy 10
|
245
|
+
uh 10
|
246
|
+
iyo 10
|
247
|
+
iku 10
|
248
|
+
kuu 9
|
249
|
+
O 9
|
250
|
+
T 9
|
251
|
+
hi_ 9
|
252
|
+
uo 9
|
253
|
+
ur 9
|
254
|
+
wana 9
|
255
|
+
ata 9
|
256
|
+
o. 9
|
257
|
+
lis 9
|
258
|
+
ani 9
|
259
|
+
cha 9
|
260
|
+
gu 9
|
261
|
+
wak 9
|
262
|
+
_ta 9
|
263
|
+
id 9
|
264
|
+
ngo 9
|
265
|
+
_vya 9
|
266
|
+
no_ 9
|
267
|
+
vya 9
|
268
|
+
awa 9
|
269
|
+
dh 9
|
270
|
+
_am 9
|
271
|
+
pa 9
|
272
|
+
_vi 9
|
273
|
+
kal 9
|
274
|
+
ez 9
|
275
|
+
je 9
|
276
|
+
ali_ 8
|
277
|
+
_za 8
|
278
|
+
uwa_ 8
|
279
|
+
a,_ 8
|
280
|
+
ili_ 8
|
281
|
+
atu 8
|
282
|
+
_Wa 8
|
283
|
+
P 8
|
284
|
+
ok 8
|
285
|
+
kam 8
|
286
|
+
Ka 8
|
287
|
+
zo 8
|
288
|
+
aji 8
|
289
|
+
mar 8
|
290
|
+
_ni 8
|
291
|
+
iwa_ 8
|
292
|
+
azi 8
|
293
|
+
ash 8
|
294
|
+
nga 8
|
295
|
+
tu_ 8
|
296
|
+
sha_ 8
|
297
|
+
kuwa_ 8
|
298
|
+
ib 8
|
299
|
+
isha 8
|
300
|
+
aka 8
|
301
|
+
ikal 8
|
302
|
+
wi 8
|
303
|
+
ana_ 8
|
304
|
+
ot 8
|
305
|
+
isa 8
|
306
|
+
aku 8
|
307
|
+
ag 8
|
308
|
+
su 8
|
309
|
+
kuu_ 8
|
310
|
+
wal 8
|
311
|
+
ama_ 8
|
312
|
+
ini_ 8
|
313
|
+
_mk 8
|
314
|
+
o, 8
|
315
|
+
sem 8
|
316
|
+
th 8
|
317
|
+
ema 8
|
318
|
+
kali 8
|
319
|
+
nz 8
|
320
|
+
mk 8
|
321
|
+
liw 7
|
322
|
+
heri 7
|
323
|
+
el 7
|
324
|
+
ju 7
|
325
|
+
Bw 7
|
326
|
+
ikali 7
|
327
|
+
erika 7
|
328
|
+
_la_ 7
|
329
|
+
fa_ 7
|
330
|
+
ita 7
|
331
|
+
nj 7
|
332
|
+
ho_ 7
|
333
|
+
S 7
|
334
|
+
mo 7
|
335
|
+
ara 7
|
336
|
+
ip 7
|
337
|
+
hus 7
|
338
|
+
uhu 7
|
339
|
+
_hiyo 7
|
340
|
+
_wak 7
|
341
|
+
hiy 7
|
342
|
+
R 7
|
343
|
+
_ili 7
|
344
|
+
erik 7
|
345
|
+
hiyo 7
|
346
|
+
ung 7
|
347
|
+
E 7
|
348
|
+
Wak 7
|
349
|
+
liwa 7
|
350
|
+
asi 7
|
351
|
+
uli 7
|
352
|
+
har 7
|
353
|
+
_hiy 7
|
354
|
+
her 7
|
355
|
+
rikal 7
|
356
|
+
_kam 7
|
357
|
+
ir 7
|
358
|
+
hil 7
|
359
|
+
sema 7
|
360
|
+
_za_ 7
|
361
|
+
om 7
|
362
|
+
_il 7
|
363
|
+
ndi_ 7
|
364
|
+
kis 7
|
365
|
+
uf 7
|
366
|
+
ati_ 7
|
367
|
+
ala 7
|
368
|
+
kali_ 7
|
369
|
+
nye 7
|
370
|
+
te 7
|
371
|
+
taifa 6
|
372
|
+
io 6
|
373
|
+
ifa_ 6
|
374
|
+
ema_ 6
|
375
|
+
undi_ 6
|
376
|
+
_Ka 6
|
377
|
+
yo_ 6
|
378
|
+
tia 6
|
379
|
+
asha 6
|
380
|
+
o._ 6
|
381
|
+
ala_ 6
|
382
|
+
izo 6
|
383
|
+
alis 6
|
384
|
+
dhi 6
|
385
|
+
ani_ 6
|
386
|
+
Bw_ 6
|
387
|
+
eh 6
|
388
|
+
ye_ 6
|
389
|
+
aifa 6
|
390
|
+
_N 6
|
391
|
+
sia 6
|
392
|
+
ahi 6
|
393
|
+
ria 6
|
394
|
+
undi 6
|
395
|
+
eke 6
|
396
|
+
_hu 6
|
397
|
+
tai 6
|
398
|
+
aif 6
|
399
|
+
izi 6
|
400
|
+
ong 6
|