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
|
+
� 1569
|
2
|
+
_ 1212
|
3
|
+
�� 367
|
4
|
+
�_ 269
|
5
|
+
� 181
|
6
|
+
�� 130
|
7
|
+
� 129
|
8
|
+
� 128
|
9
|
+
� 127
|
10
|
+
� 125
|
11
|
+
�� 123
|
12
|
+
� 116
|
13
|
+
� 113
|
14
|
+
. 108
|
15
|
+
� 107
|
16
|
+
� 106
|
17
|
+
� 105
|
18
|
+
�� 98
|
19
|
+
�� 98
|
20
|
+
��� 97
|
21
|
+
�� 97
|
22
|
+
� 96
|
23
|
+
� 95
|
24
|
+
��_ 95
|
25
|
+
� 93
|
26
|
+
� 88
|
27
|
+
� 87
|
28
|
+
� 86
|
29
|
+
�_ 82
|
30
|
+
�� 81
|
31
|
+
� 80
|
32
|
+
�� 78
|
33
|
+
�� 77
|
34
|
+
�� 75
|
35
|
+
_� 74
|
36
|
+
�� 71
|
37
|
+
��� 70
|
38
|
+
� 66
|
39
|
+
�� 66
|
40
|
+
�� 63
|
41
|
+
�� 63
|
42
|
+
�� 60
|
43
|
+
�� 58
|
44
|
+
��_ 57
|
45
|
+
�� 50
|
46
|
+
� 49
|
47
|
+
� 49
|
48
|
+
�� 49
|
49
|
+
_� 48
|
50
|
+
� 47
|
51
|
+
�� 47
|
52
|
+
._ 47
|
53
|
+
�� 47
|
54
|
+
_�� 46
|
55
|
+
��� 44
|
56
|
+
���_ 42
|
57
|
+
�� 42
|
58
|
+
�� 42
|
59
|
+
�� 41
|
60
|
+
_� 41
|
61
|
+
��� 41
|
62
|
+
_�� 41
|
63
|
+
_� 40
|
64
|
+
��_ 40
|
65
|
+
_� 40
|
66
|
+
.. 39
|
67
|
+
�� 38
|
68
|
+
� 37
|
69
|
+
� 36
|
70
|
+
��� 36
|
71
|
+
_� 36
|
72
|
+
_�� 33
|
73
|
+
��� 33
|
74
|
+
� 33
|
75
|
+
... 33
|
76
|
+
��� 32
|
77
|
+
�_ 32
|
78
|
+
� 31
|
79
|
+
_�� 31
|
80
|
+
��� 31
|
81
|
+
�� 30
|
82
|
+
��� 30
|
83
|
+
��_ 29
|
84
|
+
_� 29
|
85
|
+
�� 29
|
86
|
+
�� 29
|
87
|
+
�� 28
|
88
|
+
�� 28
|
89
|
+
_� 28
|
90
|
+
� 27
|
91
|
+
.... 27
|
92
|
+
�� 27
|
93
|
+
�� 27
|
94
|
+
� 26
|
95
|
+
__ 26
|
96
|
+
��� 26
|
97
|
+
��� 25
|
98
|
+
_� 25
|
99
|
+
_�� 25
|
100
|
+
��� 25
|
101
|
+
_� 25
|
102
|
+
���� 24
|
103
|
+
_�� 24
|
104
|
+
� 24
|
105
|
+
_��� 24
|
106
|
+
�� 23
|
107
|
+
�� 23
|
108
|
+
��� 23
|
109
|
+
�_ 23
|
110
|
+
���� 23
|
111
|
+
�� 23
|
112
|
+
���_ 22
|
113
|
+
�� 22
|
114
|
+
��� 21
|
115
|
+
..... 21
|
116
|
+
��� 21
|
117
|
+
��� 21
|
118
|
+
���� 20
|
119
|
+
��_ 20
|
120
|
+
��� 20
|
121
|
+
��� 20
|
122
|
+
��� 20
|
123
|
+
��� 20
|
124
|
+
��� 20
|
125
|
+
���_ 20
|
126
|
+
�_ 20
|
127
|
+
, 19
|
128
|
+
�� 19
|
129
|
+
� 19
|
130
|
+
��� 19
|
131
|
+
�� 19
|
132
|
+
��� 19
|
133
|
+
��_ 19
|
134
|
+
,_ 19
|
135
|
+
�� 19
|
136
|
+
���� 19
|
137
|
+
� 18
|
138
|
+
��� 18
|
139
|
+
��� 18
|
140
|
+
���� 17
|
141
|
+
��_ 17
|
142
|
+
�� 17
|
143
|
+
�� 17
|
144
|
+
��� 17
|
145
|
+
� 17
|
146
|
+
����_ 17
|
147
|
+
��_ 17
|
148
|
+
�_ 17
|
149
|
+
��� 17
|
150
|
+
_�� 17
|
151
|
+
��� 16
|
152
|
+
� 16
|
153
|
+
��� 16
|
154
|
+
�� 16
|
155
|
+
���� 16
|
156
|
+
_� 16
|
157
|
+
�� 16
|
158
|
+
�. 16
|
159
|
+
�� 16
|
160
|
+
�. 16
|
161
|
+
�� 16
|
162
|
+
��� 16
|
163
|
+
�� 15
|
164
|
+
_�� 15
|
165
|
+
_��� 15
|
166
|
+
��� 15
|
167
|
+
�_ 15
|
168
|
+
���� 15
|
169
|
+
���� 15
|
170
|
+
� 15
|
171
|
+
_���� 15
|
172
|
+
' 15
|
173
|
+
��� 15
|
174
|
+
��_ 15
|
175
|
+
��� 15
|
176
|
+
� 15
|
177
|
+
��� 15
|
178
|
+
��� 14
|
179
|
+
��� 14
|
180
|
+
�._ 14
|
181
|
+
�. 14
|
182
|
+
��� 14
|
183
|
+
���� 14
|
184
|
+
�� 14
|
185
|
+
�� 14
|
186
|
+
'_ 14
|
187
|
+
_� 14
|
188
|
+
_��� 14
|
189
|
+
_���� 14
|
190
|
+
_�� 14
|
191
|
+
_� 14
|
192
|
+
�� 14
|
193
|
+
�� 14
|
194
|
+
��� 13
|
195
|
+
_��� 13
|
196
|
+
� 13
|
197
|
+
��� 13
|
198
|
+
_��� 13
|
199
|
+
��� 13
|
200
|
+
���� 13
|
201
|
+
_�� 13
|
202
|
+
����_ 13
|
203
|
+
��� 13
|
204
|
+
�� 13
|
205
|
+
���� 13
|
206
|
+
_� 13
|
207
|
+
_��� 12
|
208
|
+
_�� 12
|
209
|
+
_�� 12
|
210
|
+
���� 12
|
211
|
+
_�� 12
|
212
|
+
�� 12
|
213
|
+
_� 12
|
214
|
+
���� 12
|
215
|
+
��� 12
|
216
|
+
_� 12
|
217
|
+
��� 12
|
218
|
+
��� 12
|
219
|
+
�� 11
|
220
|
+
� 11
|
221
|
+
��� 11
|
222
|
+
_� 11
|
223
|
+
_'_ 11
|
224
|
+
���_ 11
|
225
|
+
��� 11
|
226
|
+
� 11
|
227
|
+
��_ 11
|
228
|
+
��� 11
|
229
|
+
� 11
|
230
|
+
�� 11
|
231
|
+
���� 11
|
232
|
+
����_ 11
|
233
|
+
_' 11
|
234
|
+
�� 11
|
235
|
+
�._ 11
|
236
|
+
����� 10
|
237
|
+
_�� 10
|
238
|
+
��� 10
|
239
|
+
�_ 10
|
240
|
+
�,_ 10
|
241
|
+
�� 10
|
242
|
+
���_ 10
|
243
|
+
����� 10
|
244
|
+
�� 10
|
245
|
+
���� 10
|
246
|
+
��� 10
|
247
|
+
���� 10
|
248
|
+
�� 10
|
249
|
+
��� 10
|
250
|
+
�, 10
|
251
|
+
��_ 10
|
252
|
+
��_ 10
|
253
|
+
���� 10
|
254
|
+
� 10
|
255
|
+
��_ 10
|
256
|
+
��� 10
|
257
|
+
��� 10
|
258
|
+
_��� 10
|
259
|
+
_��� 10
|
260
|
+
��� 10
|
261
|
+
�� 10
|
262
|
+
_� 10
|
263
|
+
���� 10
|
264
|
+
�� 10
|
265
|
+
_��� 9
|
266
|
+
�� 9
|
267
|
+
_�� 9
|
268
|
+
���� 9
|
269
|
+
��� 9
|
270
|
+
���� 9
|
271
|
+
����� 9
|
272
|
+
�� 9
|
273
|
+
����� 9
|
274
|
+
���_ 9
|
275
|
+
���_ 9
|
276
|
+
�� 9
|
277
|
+
���_ 9
|
278
|
+
���� 9
|
279
|
+
��� 9
|
280
|
+
�� 9
|
281
|
+
�. 9
|
282
|
+
�� 9
|
283
|
+
_�� 9
|
284
|
+
���� 9
|
285
|
+
���_ 9
|
286
|
+
� 9
|
287
|
+
���� 9
|
288
|
+
_���� 9
|
289
|
+
���� 9
|
290
|
+
��� 9
|
291
|
+
�� 9
|
292
|
+
_���� 9
|
293
|
+
_�� 9
|
294
|
+
��� 9
|
295
|
+
�._ 9
|
296
|
+
��� 9
|
297
|
+
����_ 9
|
298
|
+
���_ 9
|
299
|
+
�� 9
|
300
|
+
��� 9
|
301
|
+
��� 9
|
302
|
+
�� 9
|
303
|
+
��� 9
|
304
|
+
���� 9
|
305
|
+
�� 9
|
306
|
+
����_ 9
|
307
|
+
� 9
|
308
|
+
_��� 9
|
309
|
+
_� 9
|
310
|
+
���_ 9
|
311
|
+
����� 9
|
312
|
+
�� 8
|
313
|
+
��� 8
|
314
|
+
����. 8
|
315
|
+
�� 8
|
316
|
+
����. 8
|
317
|
+
_��� 8
|
318
|
+
��. 8
|
319
|
+
��� 8
|
320
|
+
���. 8
|
321
|
+
_��� 8
|
322
|
+
� 8
|
323
|
+
��� 8
|
324
|
+
��. 8
|
325
|
+
�� 8
|
326
|
+
�� 8
|
327
|
+
_�� 8
|
328
|
+
���� 8
|
329
|
+
��� 8
|
330
|
+
��� 8
|
331
|
+
�� 8
|
332
|
+
���. 8
|
333
|
+
��� 8
|
334
|
+
��� 8
|
335
|
+
��� 7
|
336
|
+
_���_ 7
|
337
|
+
_��� 7
|
338
|
+
����� 7
|
339
|
+
��� 7
|
340
|
+
��_ 7
|
341
|
+
�� 7
|
342
|
+
�� 7
|
343
|
+
� 7
|
344
|
+
� 7
|
345
|
+
_�� 7
|
346
|
+
��. 7
|
347
|
+
��� 7
|
348
|
+
��� 7
|
349
|
+
���� 7
|
350
|
+
_�� 7
|
351
|
+
���_ 7
|
352
|
+
���� 7
|
353
|
+
��. 7
|
354
|
+
����� 7
|
355
|
+
�� 7
|
356
|
+
_� 7
|
357
|
+
�� 7
|
358
|
+
��� 7
|
359
|
+
����_ 7
|
360
|
+
��� 7
|
361
|
+
_�� 7
|
362
|
+
��._ 7
|
363
|
+
����_ 7
|
364
|
+
���� 7
|
365
|
+
���� 7
|
366
|
+
��� 7
|
367
|
+
��._ 7
|
368
|
+
���� 7
|
369
|
+
_� 7
|
370
|
+
���� 7
|
371
|
+
�� 7
|
372
|
+
�� 7
|
373
|
+
���._ 7
|
374
|
+
� 7
|
375
|
+
_��� 7
|
376
|
+
�._ 7
|
377
|
+
��� 7
|
378
|
+
����_ 7
|
379
|
+
��_ 7
|
380
|
+
���� 7
|
381
|
+
�� 7
|
382
|
+
����� 7
|
383
|
+
_��� 7
|
384
|
+
ť 7
|
385
|
+
����� 6
|
386
|
+
� 6
|
387
|
+
��� 6
|
388
|
+
���._ 6
|
389
|
+
��� 6
|
390
|
+
�� 6
|
391
|
+
���_ 6
|
392
|
+
��� 6
|
393
|
+
��. 6
|
394
|
+
���_ 6
|
395
|
+
��� 6
|
396
|
+
�� 6
|
397
|
+
����� 6
|
398
|
+
��� 6
|
399
|
+
��� 6
|
400
|
+
��._ 6
|