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
|
+
a 1131
|
2
|
+
_ 984
|
3
|
+
h 314
|
4
|
+
i 269
|
5
|
+
t 206
|
6
|
+
aa 186
|
7
|
+
n 182
|
8
|
+
s 181
|
9
|
+
r 177
|
10
|
+
| 171
|
11
|
+
ha 141
|
12
|
+
m 131
|
13
|
+
v 130
|
14
|
+
a_ 130
|
15
|
+
d 121
|
16
|
+
y 116
|
17
|
+
e 108
|
18
|
+
_| 103
|
19
|
+
u 93
|
20
|
+
p 90
|
21
|
+
ya 90
|
22
|
+
va 89
|
23
|
+
na 89
|
24
|
+
ar 88
|
25
|
+
ta 85
|
26
|
+
an 82
|
27
|
+
A 78
|
28
|
+
ra 78
|
29
|
+
k 76
|
30
|
+
am 75
|
31
|
+
ma 75
|
32
|
+
sh 74
|
33
|
+
__ 72
|
34
|
+
. 68
|
35
|
+
|| 68
|
36
|
+
_|| 66
|
37
|
+
at 66
|
38
|
+
M 61
|
39
|
+
as 59
|
40
|
+
i_ 55
|
41
|
+
o 55
|
42
|
+
g 52
|
43
|
+
N 50
|
44
|
+
aM 50
|
45
|
+
pa 49
|
46
|
+
M_ 49
|
47
|
+
b 48
|
48
|
+
c 43
|
49
|
+
ch 43
|
50
|
+
aM_ 43
|
51
|
+
e_ 42
|
52
|
+
j 42
|
53
|
+
ana 42
|
54
|
+
hi 42
|
55
|
+
it 41
|
56
|
+
_s 40
|
57
|
+
ad 40
|
58
|
+
aan 40
|
59
|
+
sa 37
|
60
|
+
ama 37
|
61
|
+
|_ 37
|
62
|
+
av 36
|
63
|
+
H 36
|
64
|
+
ay 35
|
65
|
+
da 35
|
66
|
+
dh 34
|
67
|
+
_n 34
|
68
|
+
ah 34
|
69
|
+
sha 33
|
70
|
+
ka 32
|
71
|
+
||_ 32
|
72
|
+
aN 32
|
73
|
+
bh 31
|
74
|
+
ara 31
|
75
|
+
is 31
|
76
|
+
ii 31
|
77
|
+
l 30
|
78
|
+
H_ 30
|
79
|
+
_||_ 30
|
80
|
+
ap 29
|
81
|
+
aa_ 29
|
82
|
+
aH 29
|
83
|
+
a. 28
|
84
|
+
_p 28
|
85
|
+
na_ 28
|
86
|
+
ja 28
|
87
|
+
aH_ 27
|
88
|
+
ai 26
|
89
|
+
ga 26
|
90
|
+
.n 26
|
91
|
+
_na 26
|
92
|
+
a.n 24
|
93
|
+
ti 24
|
94
|
+
aana 23
|
95
|
+
aya 23
|
96
|
+
Na 23
|
97
|
+
vi 22
|
98
|
+
aha 22
|
99
|
+
st 22
|
100
|
+
ava 22
|
101
|
+
ata 22
|
102
|
+
.h 22
|
103
|
+
ish 22
|
104
|
+
di 22
|
105
|
+
_j 21
|
106
|
+
haa 21
|
107
|
+
la 21
|
108
|
+
.h_ 21
|
109
|
+
vaa 21
|
110
|
+
_b 21
|
111
|
+
h_ 21
|
112
|
+
al 20
|
113
|
+
ni 20
|
114
|
+
_d 20
|
115
|
+
hh 19
|
116
|
+
es 19
|
117
|
+
_sa 18
|
118
|
+
ak 18
|
119
|
+
esh 18
|
120
|
+
ha_ 18
|
121
|
+
_v 18
|
122
|
+
ri 18
|
123
|
+
ita 18
|
124
|
+
chi 17
|
125
|
+
_k 17
|
126
|
+
yaa 17
|
127
|
+
_ch 17
|
128
|
+
_t 17
|
129
|
+
_c 17
|
130
|
+
maa 17
|
131
|
+
nam 17
|
132
|
+
_m 17
|
133
|
+
x 16
|
134
|
+
ala 16
|
135
|
+
ag 16
|
136
|
+
id 16
|
137
|
+
me 16
|
138
|
+
taa 16
|
139
|
+
tva 16
|
140
|
+
tv 16
|
141
|
+
pr 16
|
142
|
+
bha 16
|
143
|
+
T 16
|
144
|
+
_pa 15
|
145
|
+
^ 15
|
146
|
+
aNa 15
|
147
|
+
th 15
|
148
|
+
har 15
|
149
|
+
ya_ 15
|
150
|
+
shh 15
|
151
|
+
D 15
|
152
|
+
cha 15
|
153
|
+
_ja 15
|
154
|
+
I 14
|
155
|
+
aka 14
|
156
|
+
paa 14
|
157
|
+
sy 14
|
158
|
+
ik 14
|
159
|
+
yat 14
|
160
|
+
tas 14
|
161
|
+
ash 14
|
162
|
+
_g 14
|
163
|
+
sya 14
|
164
|
+
te 14
|
165
|
+
sta 13
|
166
|
+
esha 13
|
167
|
+
A_ 13
|
168
|
+
_na_ 13
|
169
|
+
in 13
|
170
|
+
pra 13
|
171
|
+
ru 13
|
172
|
+
asya 13
|
173
|
+
o_ 13
|
174
|
+
hA 13
|
175
|
+
su 13
|
176
|
+
asy 13
|
177
|
+
hy 13
|
178
|
+
uu 13
|
179
|
+
re 12
|
180
|
+
naa 12
|
181
|
+
R 12
|
182
|
+
_ma 12
|
183
|
+
eva 12
|
184
|
+
^i 12
|
185
|
+
hya 12
|
186
|
+
ab 12
|
187
|
+
R^ 12
|
188
|
+
hav 12
|
189
|
+
ev 12
|
190
|
+
ada 12
|
191
|
+
nama 12
|
192
|
+
par 12
|
193
|
+
R^i 12
|
194
|
+
_nam 11
|
195
|
+
m.h_ 11
|
196
|
+
mi 11
|
197
|
+
sar 11
|
198
|
+
rt 11
|
199
|
+
tr 11
|
200
|
+
ye 11
|
201
|
+
m. 11
|
202
|
+
\ 11
|
203
|
+
ast 11
|
204
|
+
haM 11
|
205
|
+
dha 11
|
206
|
+
_bh 11
|
207
|
+
am.h_ 11
|
208
|
+
m.h 11
|
209
|
+
ir 11
|
210
|
+
haM_ 11
|
211
|
+
am. 11
|
212
|
+
aas 11
|
213
|
+
am.h 11
|
214
|
+
aay 11
|
215
|
+
daa 11
|
216
|
+
aam 11
|
217
|
+
tra 10
|
218
|
+
aj 10
|
219
|
+
ati 10
|
220
|
+
hava 10
|
221
|
+
kh 10
|
222
|
+
_y 10
|
223
|
+
ii_ 10
|
224
|
+
jaa 10
|
225
|
+
_sh 10
|
226
|
+
.a 10
|
227
|
+
_cha 10
|
228
|
+
ham 10
|
229
|
+
kaa 10
|
230
|
+
ra_ 10
|
231
|
+
ishh 10
|
232
|
+
ed 10
|
233
|
+
iv 10
|
234
|
+
aah 10
|
235
|
+
apa 10
|
236
|
+
asta 10
|
237
|
+
ur 9
|
238
|
+
ai_ 9
|
239
|
+
anaa 9
|
240
|
+
nt 9
|
241
|
+
ani 9
|
242
|
+
adh 9
|
243
|
+
vaM 9
|
244
|
+
aga 9
|
245
|
+
va_ 9
|
246
|
+
he 9
|
247
|
+
ari 9
|
248
|
+
te_ 9
|
249
|
+
_bha 9
|
250
|
+
yai 9
|
251
|
+
var 9
|
252
|
+
Ax 9
|
253
|
+
nd 9
|
254
|
+
rA 9
|
255
|
+
jaan 9
|
256
|
+
ke 9
|
257
|
+
dhi 9
|
258
|
+
ami 9
|
259
|
+
^it 8
|
260
|
+
mas 8
|
261
|
+
tasya 8
|
262
|
+
aya_ 8
|
263
|
+
Ar 8
|
264
|
+
ana_ 8
|
265
|
+
R^it 8
|
266
|
+
bhav 8
|
267
|
+
raa 8
|
268
|
+
syai 8
|
269
|
+
tha 8
|
270
|
+
rv 8
|
271
|
+
art 8
|
272
|
+
adi 8
|
273
|
+
rva 8
|
274
|
+
ti_ 8
|
275
|
+
ram 8
|
276
|
+
u_ 8
|
277
|
+
amas 8
|
278
|
+
are 8
|
279
|
+
_jaa 8
|
280
|
+
us 8
|
281
|
+
hch 8
|
282
|
+
vaan 8
|
283
|
+
aar 8
|
284
|
+
vaM_ 8
|
285
|
+
ve 8
|
286
|
+
ye_ 8
|
287
|
+
ath 8
|
288
|
+
asyai 8
|
289
|
+
_pr 8
|
290
|
+
_ya 8
|
291
|
+
asha 8
|
292
|
+
_nama 8
|
293
|
+
tasy 8
|
294
|
+
ut 8
|
295
|
+
hit 8
|
296
|
+
_vi 8
|
297
|
+
hc 8
|
298
|
+
aad 8
|
299
|
+
na.n 7
|
300
|
+
G 7
|
301
|
+
stasy 7
|
302
|
+
iit 7
|
303
|
+
GY 7
|
304
|
+
arva 7
|
305
|
+
_par 7
|
306
|
+
yam 7
|
307
|
+
Am 7
|
308
|
+
na. 7
|
309
|
+
ame 7
|
310
|
+
hva 7
|
311
|
+
_ni 7
|
312
|
+
tat 7
|
313
|
+
.ah 7
|
314
|
+
_jaan 7
|
315
|
+
raN 7
|
316
|
+
aaya 7
|
317
|
+
vat 7
|
318
|
+
hv 7
|
319
|
+
aD 7
|
320
|
+
|n 7
|
321
|
+
aru 7
|
322
|
+
aat 7
|
323
|
+
Y 7
|
324
|
+
_ga 7
|
325
|
+
araN 7
|
326
|
+
aaN 7
|
327
|
+
stas 7
|
328
|
+
Ad 7
|
329
|
+
arv 7
|
330
|
+
yai_ 7
|
331
|
+
aa. 7
|
332
|
+
saa 7
|
333
|
+
mar 7
|
334
|
+
hha 7
|
335
|
+
amaa 7
|
336
|
+
cha_ 7
|
337
|
+
bhava 7
|
338
|
+
man 7
|
339
|
+
yo 7
|
340
|
+
up 7
|
341
|
+
om 7
|
342
|
+
ika 7
|
343
|
+
ida 7
|
344
|
+
tu 7
|
345
|
+
pi 7
|
346
|
+
_h 7
|
347
|
+
ba 7
|
348
|
+
ho 7
|
349
|
+
shi 7
|
350
|
+
jaana 7
|
351
|
+
avi 7
|
352
|
+
de 7
|
353
|
+
_dh 7
|
354
|
+
_pra 7
|
355
|
+
ip 7
|
356
|
+
_va 7
|
357
|
+
ta_ 7
|
358
|
+
.aha 7
|
359
|
+
raM 6
|
360
|
+
hT 6
|
361
|
+
hat 6
|
362
|
+
atra 6
|
363
|
+
to 6
|
364
|
+
n_ 6
|
365
|
+
shc 6
|
366
|
+
aal 6
|
367
|
+
a.n_ 6
|
368
|
+
namas 6
|
369
|
+
At 6
|
370
|
+
mast 6
|
371
|
+
gu 6
|
372
|
+
_cha_ 6
|
373
|
+
taa_ 6
|
374
|
+
re_ 6
|
375
|
+
kar 6
|
376
|
+
tan 6
|
377
|
+
atr 6
|
378
|
+
avaa 6
|
379
|
+
tar 6
|
380
|
+
op 6
|
381
|
+
ku 6
|
382
|
+
aham 6
|
383
|
+
syai_ 6
|
384
|
+
hhT 6
|
385
|
+
pu 6
|
386
|
+
amast 6
|
387
|
+
gat 6
|
388
|
+
masta 6
|
389
|
+
ac 6
|
390
|
+
.\ 6
|
391
|
+
|t 6
|
392
|
+
sarva 6
|
393
|
+
para 6
|
394
|
+
rat 6
|
395
|
+
ina 6
|
396
|
+
sarv 6
|
397
|
+
nA 6
|
398
|
+
maH 6
|
399
|
+
jay 6
|
400
|
+
dar 6
|