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
|
+
_ 1998
|
2
|
+
n 418
|
3
|
+
h 330
|
4
|
+
i 203
|
5
|
+
t 202
|
6
|
+
c 191
|
7
|
+
g 183
|
8
|
+
ng 147
|
9
|
+
_t 134
|
10
|
+
a 123
|
11
|
+
_n 117
|
12
|
+
u 113
|
13
|
+
_c 107
|
14
|
+
nh 105
|
15
|
+
g_ 101
|
16
|
+
ng_ 101
|
17
|
+
i_ 101
|
18
|
+
n_ 99
|
19
|
+
� 92
|
20
|
+
m 74
|
21
|
+
o 70
|
22
|
+
r 65
|
23
|
+
� 64
|
24
|
+
. 64
|
25
|
+
� 63
|
26
|
+
l 63
|
27
|
+
_� 59
|
28
|
+
th 57
|
29
|
+
c_ 55
|
30
|
+
_th 53
|
31
|
+
h_ 52
|
32
|
+
s 51
|
33
|
+
_nh 50
|
34
|
+
t_ 47
|
35
|
+
, 47
|
36
|
+
y 47
|
37
|
+
_l 46
|
38
|
+
� 45
|
39
|
+
_s 45
|
40
|
+
a_ 44
|
41
|
+
nh_ 43
|
42
|
+
ch 42
|
43
|
+
,_ 41
|
44
|
+
k 39
|
45
|
+
_h 38
|
46
|
+
._ 38
|
47
|
+
u_ 37
|
48
|
+
hi 37
|
49
|
+
o_ 37
|
50
|
+
v 37
|
51
|
+
_k 36
|
52
|
+
_v 35
|
53
|
+
T 35
|
54
|
+
�_ 35
|
55
|
+
kh 34
|
56
|
+
_m 34
|
57
|
+
� 34
|
58
|
+
� 33
|
59
|
+
_kh 33
|
60
|
+
p 32
|
61
|
+
� 31
|
62
|
+
b 31
|
63
|
+
_ch 31
|
64
|
+
� 30
|
65
|
+
� 30
|
66
|
+
_b 30
|
67
|
+
d 30
|
68
|
+
_ng 29
|
69
|
+
__ 29
|
70
|
+
y_ 28
|
71
|
+
N 27
|
72
|
+
tr 27
|
73
|
+
_T 26
|
74
|
+
l� 26
|
75
|
+
e 26
|
76
|
+
_d 26
|
77
|
+
m_ 25
|
78
|
+
_g 25
|
79
|
+
� 25
|
80
|
+
� 24
|
81
|
+
_tr 24
|
82
|
+
_l� 24
|
83
|
+
� 24
|
84
|
+
� 24
|
85
|
+
� 23
|
86
|
+
an 23
|
87
|
+
� 23
|
88
|
+
�_ 22
|
89
|
+
�n 22
|
90
|
+
C 22
|
91
|
+
�n 22
|
92
|
+
ܩ 21
|
93
|
+
� 21
|
94
|
+
ph 21
|
95
|
+
�a 20
|
96
|
+
c�a 20
|
97
|
+
_p 20
|
98
|
+
H 20
|
99
|
+
h� 20
|
100
|
+
_ph 20
|
101
|
+
� 20
|
102
|
+
c� 20
|
103
|
+
�i 19
|
104
|
+
l�_ 19
|
105
|
+
_c�a 18
|
106
|
+
ho 18
|
107
|
+
�c 18
|
108
|
+
� 18
|
109
|
+
c�a_ 18
|
110
|
+
�a_ 18
|
111
|
+
_c� 18
|
112
|
+
ha 18
|
113
|
+
�ng 17
|
114
|
+
_r 17
|
115
|
+
_l�_ 17
|
116
|
+
c� 17
|
117
|
+
gi 17
|
118
|
+
c�_ 17
|
119
|
+
�n 17
|
120
|
+
_c� 16
|
121
|
+
� 16
|
122
|
+
_c�_ 16
|
123
|
+
�i_ 16
|
124
|
+
in 16
|
125
|
+
� 16
|
126
|
+
_c�a_ 16
|
127
|
+
� 16
|
128
|
+
" 15
|
129
|
+
i� 15
|
130
|
+
i� 15
|
131
|
+
_gi 15
|
132
|
+
nhi 15
|
133
|
+
q 15
|
134
|
+
uy 15
|
135
|
+
h� 15
|
136
|
+
qu 15
|
137
|
+
h� 15
|
138
|
+
g� 15
|
139
|
+
_C 15
|
140
|
+
� 15
|
141
|
+
�ng_ 15
|
142
|
+
ra 14
|
143
|
+
� 14
|
144
|
+
�n 14
|
145
|
+
� 14
|
146
|
+
_nhi 14
|
147
|
+
h� 14
|
148
|
+
.. 14
|
149
|
+
�t 14
|
150
|
+
gܩi 13
|
151
|
+
�nh 13
|
152
|
+
ܩi 13
|
153
|
+
�u 13
|
154
|
+
ܩi_ 13
|
155
|
+
_qu 13
|
156
|
+
�t_ 13
|
157
|
+
_q 13
|
158
|
+
�n 13
|
159
|
+
gܩ 13
|
160
|
+
� 13
|
161
|
+
v� 13
|
162
|
+
gܩi_ 13
|
163
|
+
�i 13
|
164
|
+
� 13
|
165
|
+
�n_ 13
|
166
|
+
�i_ 13
|
167
|
+
_v� 12
|
168
|
+
h�n 12
|
169
|
+
on 12
|
170
|
+
� 12
|
171
|
+
_N 12
|
172
|
+
i�u 12
|
173
|
+
hi�u 12
|
174
|
+
�u_ 12
|
175
|
+
hi� 12
|
176
|
+
inh 12
|
177
|
+
h�ng 12
|
178
|
+
x 11
|
179
|
+
nhi� 11
|
180
|
+
hi�u_ 11
|
181
|
+
kh� 11
|
182
|
+
kh�n 11
|
183
|
+
nhi�u 11
|
184
|
+
kh�ng 11
|
185
|
+
�n 11
|
186
|
+
c� 11
|
187
|
+
�_ 11
|
188
|
+
�t 11
|
189
|
+
ay 11
|
190
|
+
� 11
|
191
|
+
�o 11
|
192
|
+
sa 11
|
193
|
+
�n_ 11
|
194
|
+
_m� 11
|
195
|
+
m� 11
|
196
|
+
_c� 11
|
197
|
+
_sa 11
|
198
|
+
ܮ 11
|
199
|
+
i�u_ 11
|
200
|
+
� 11
|
201
|
+
_H 11
|
202
|
+
�c_ 10
|
203
|
+
� 10
|
204
|
+
�nh_ 10
|
205
|
+
�n 10
|
206
|
+
i� 10
|
207
|
+
�o_ 10
|
208
|
+
_kh�n 10
|
209
|
+
_m�t_ 10
|
210
|
+
ng� 10
|
211
|
+
�n 10
|
212
|
+
ngܩi 10
|
213
|
+
�ܮ 10
|
214
|
+
_ng� 10
|
215
|
+
�t 10
|
216
|
+
V 10
|
217
|
+
m�t 10
|
218
|
+
ngܩ 10
|
219
|
+
h�ng_ 10
|
220
|
+
�� 10
|
221
|
+
�ng 10
|
222
|
+
�t_ 10
|
223
|
+
_ngܩ 10
|
224
|
+
m�t_ 10
|
225
|
+
� 10
|
226
|
+
�ܮc 10
|
227
|
+
_nhi� 10
|
228
|
+
ܮc 10
|
229
|
+
�n 10
|
230
|
+
_m�t 10
|
231
|
+
_kh� 10
|
232
|
+
h� 10
|
233
|
+
�c 10
|
234
|
+
_x 10
|
235
|
+
_c�c 9
|
236
|
+
� 9
|
237
|
+
nh� 9
|
238
|
+
�_ 9
|
239
|
+
ho_ 9
|
240
|
+
ti 9
|
241
|
+
_�ܮc 9
|
242
|
+
: 9
|
243
|
+
�_ 9
|
244
|
+
inh_ 9
|
245
|
+
ch_ 9
|
246
|
+
_�ܮ 9
|
247
|
+
�ng_ 9
|
248
|
+
�n 9
|
249
|
+
L 9
|
250
|
+
f 9
|
251
|
+
ra_ 9
|
252
|
+
n� 9
|
253
|
+
_V 9
|
254
|
+
an_ 9
|
255
|
+
� 9
|
256
|
+
_�� 9
|
257
|
+
th� 9
|
258
|
+
ܮc_ 9
|
259
|
+
� 9
|
260
|
+
�ܮc_ 9
|
261
|
+
_n� 9
|
262
|
+
h�n 9
|
263
|
+
�c_ 9
|
264
|
+
ay_ 9
|
265
|
+
A 9
|
266
|
+
c�c 9
|
267
|
+
S 9
|
268
|
+
_nh� 9
|
269
|
+
_th� 9
|
270
|
+
�_ 8
|
271
|
+
rong_ 8
|
272
|
+
_cho 8
|
273
|
+
�c 8
|
274
|
+
_s� 8
|
275
|
+
ong_ 8
|
276
|
+
_th�_ 8
|
277
|
+
ro 8
|
278
|
+
ron 8
|
279
|
+
h� 8
|
280
|
+
h�_ 8
|
281
|
+
rong 8
|
282
|
+
p_ 8
|
283
|
+
�� 8
|
284
|
+
�ng_ 8
|
285
|
+
ܧ 8
|
286
|
+
un 8
|
287
|
+
au 8
|
288
|
+
s� 8
|
289
|
+
�_ 8
|
290
|
+
ܩn 8
|
291
|
+
�u 8
|
292
|
+
h� 8
|
293
|
+
��_ 8
|
294
|
+
ong 8
|
295
|
+
G 8
|
296
|
+
ܩng_ 8
|
297
|
+
�n 8
|
298
|
+
�c_ 8
|
299
|
+
th�_ 8
|
300
|
+
_ti 8
|
301
|
+
ta 8
|
302
|
+
ܩng 8
|
303
|
+
hu 8
|
304
|
+
�nh 8
|
305
|
+
M 8
|
306
|
+
�y 8
|
307
|
+
Th 8
|
308
|
+
h�_ 8
|
309
|
+
�_ 8
|
310
|
+
cho 8
|
311
|
+
�n_ 8
|
312
|
+
�ng 8
|
313
|
+
ua 7
|
314
|
+
� 7
|
315
|
+
� 7
|
316
|
+
�n_ 7
|
317
|
+
ao_ 7
|
318
|
+
�ch 7
|
319
|
+
� 7
|
320
|
+
�nh_ 7
|
321
|
+
ar 7
|
322
|
+
� 7
|
323
|
+
i� 7
|
324
|
+
hay 7
|
325
|
+
ao 7
|
326
|
+
�t_ 7
|
327
|
+
�ch_ 7
|
328
|
+
anh 7
|
329
|
+
_L 7
|
330
|
+
_nh�_ 7
|
331
|
+
_Th 7
|
332
|
+
nh�_ 7
|
333
|
+
kh� 7
|
334
|
+
_�� 7
|
335
|
+
cho_ 7
|
336
|
+
vi 7
|
337
|
+
l� 7
|
338
|
+
�n 7
|
339
|
+
� 7
|
340
|
+
ai_ 7
|
341
|
+
_��_ 7
|
342
|
+
? 7
|
343
|
+
Ng 7
|
344
|
+
�n 7
|
345
|
+
re 7
|
346
|
+
_kh� 7
|
347
|
+
�n 7
|
348
|
+
� 7
|
349
|
+
_cho_ 7
|
350
|
+
� 7
|
351
|
+
�i 7
|
352
|
+
... 7
|
353
|
+
_vi 7
|
354
|
+
ai 7
|
355
|
+
_ra_ 6
|
356
|
+
��n 6
|
357
|
+
l�i 6
|
358
|
+
s� 6
|
359
|
+
�n 6
|
360
|
+
_r�t_ 6
|
361
|
+
l�i_ 6
|
362
|
+
_� 6
|
363
|
+
h� 6
|
364
|
+
_th� 6
|
365
|
+
��ng 6
|
366
|
+
_ra 6
|
367
|
+
Nj_ 6
|
368
|
+
trong 6
|
369
|
+
ngu 6
|
370
|
+
h� 6
|
371
|
+
_Nj 6
|
372
|
+
�u_ 6
|
373
|
+
Tr 6
|
374
|
+
_ljn_ 6
|
375
|
+
_r� 6
|
376
|
+
al 6
|
377
|
+
�_ 6
|
378
|
+
d� 6
|
379
|
+
r�t 6
|
380
|
+
� 6
|
381
|
+
ljn_ 6
|
382
|
+
Nj 6
|
383
|
+
lj 6
|
384
|
+
hay_ 6
|
385
|
+
_M 6
|
386
|
+
h�nh_ 6
|
387
|
+
_lj 6
|
388
|
+
�i_ 6
|
389
|
+
� 6
|
390
|
+
_Nj_ 6
|
391
|
+
_s� 6
|
392
|
+
s�_ 6
|
393
|
+
�� 6
|
394
|
+
_r�t 6
|
395
|
+
hi� 6
|
396
|
+
_s�_ 6
|
397
|
+
v�_ 6
|
398
|
+
gu 6
|
399
|
+
ljn 6
|
400
|
+
ia 6
|