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
|
+
_ 1394
|
2
|
+
� 355
|
3
|
+
� 288
|
4
|
+
� 281
|
5
|
+
� 249
|
6
|
+
� 239
|
7
|
+
� 231
|
8
|
+
� 166
|
9
|
+
� 157
|
10
|
+
� 144
|
11
|
+
� 136
|
12
|
+
� 134
|
13
|
+
� 128
|
14
|
+
� 118
|
15
|
+
� 111
|
16
|
+
� 109
|
17
|
+
� 97
|
18
|
+
�� 95
|
19
|
+
_� 93
|
20
|
+
� 90
|
21
|
+
� 82
|
22
|
+
� 75
|
23
|
+
�� 74
|
24
|
+
�_ 73
|
25
|
+
. 73
|
26
|
+
_� 71
|
27
|
+
�_ 69
|
28
|
+
�_ 69
|
29
|
+
�_ 65
|
30
|
+
�_ 64
|
31
|
+
, 58
|
32
|
+
� 56
|
33
|
+
� 56
|
34
|
+
" 55
|
35
|
+
_� 54
|
36
|
+
�_ 53
|
37
|
+
,_ 53
|
38
|
+
�_ 51
|
39
|
+
_� 51
|
40
|
+
�� 51
|
41
|
+
�� 50
|
42
|
+
� 50
|
43
|
+
_� 48
|
44
|
+
- 48
|
45
|
+
_�� 48
|
46
|
+
._ 47
|
47
|
+
_� 47
|
48
|
+
�� 46
|
49
|
+
��_ 44
|
50
|
+
�� 43
|
51
|
+
� 41
|
52
|
+
_� 39
|
53
|
+
��� 38
|
54
|
+
�� 38
|
55
|
+
�� 38
|
56
|
+
� 38
|
57
|
+
� 37
|
58
|
+
�� 36
|
59
|
+
_�� 36
|
60
|
+
�� 35
|
61
|
+
�� 35
|
62
|
+
_� 33
|
63
|
+
�_ 32
|
64
|
+
� 32
|
65
|
+
� 31
|
66
|
+
�� 31
|
67
|
+
� 30
|
68
|
+
_��� 30
|
69
|
+
�� 29
|
70
|
+
�� 29
|
71
|
+
�� 28
|
72
|
+
� 28
|
73
|
+
�� 27
|
74
|
+
_� 27
|
75
|
+
�� 26
|
76
|
+
��_ 26
|
77
|
+
�� 24
|
78
|
+
�� 24
|
79
|
+
�� 24
|
80
|
+
��_ 24
|
81
|
+
�_ 24
|
82
|
+
��_ 23
|
83
|
+
��_ 23
|
84
|
+
���_ 23
|
85
|
+
�� 23
|
86
|
+
�� 23
|
87
|
+
�� 22
|
88
|
+
�� 22
|
89
|
+
� 22
|
90
|
+
� 22
|
91
|
+
_�� 22
|
92
|
+
�� 21
|
93
|
+
_� 21
|
94
|
+
�� 21
|
95
|
+
_�� 21
|
96
|
+
_�� 21
|
97
|
+
�� 20
|
98
|
+
��� 20
|
99
|
+
�� 20
|
100
|
+
�� 20
|
101
|
+
�� 19
|
102
|
+
�� 19
|
103
|
+
� 19
|
104
|
+
�� 19
|
105
|
+
�� 19
|
106
|
+
_��� 18
|
107
|
+
�� 18
|
108
|
+
��_ 18
|
109
|
+
��� 18
|
110
|
+
�� 18
|
111
|
+
�� 18
|
112
|
+
_�� 18
|
113
|
+
� 18
|
114
|
+
_� 18
|
115
|
+
�_ 17
|
116
|
+
�� 17
|
117
|
+
�� 17
|
118
|
+
_" 17
|
119
|
+
_���_ 17
|
120
|
+
�� 17
|
121
|
+
���_ 17
|
122
|
+
��� 17
|
123
|
+
�� 16
|
124
|
+
�� 16
|
125
|
+
�_ 16
|
126
|
+
�� 16
|
127
|
+
�� 16
|
128
|
+
���_ 15
|
129
|
+
�� 15
|
130
|
+
_���_ 15
|
131
|
+
�� 15
|
132
|
+
��_ 15
|
133
|
+
�� 15
|
134
|
+
�� 15
|
135
|
+
_��_ 15
|
136
|
+
�� 15
|
137
|
+
_�_ 15
|
138
|
+
�� 15
|
139
|
+
�� 15
|
140
|
+
_� 15
|
141
|
+
�� 14
|
142
|
+
_� 14
|
143
|
+
�� 14
|
144
|
+
_�� 14
|
145
|
+
�. 14
|
146
|
+
��� 14
|
147
|
+
�� 14
|
148
|
+
_�� 14
|
149
|
+
�� 14
|
150
|
+
��� 14
|
151
|
+
�� 14
|
152
|
+
���_ 14
|
153
|
+
��_ 14
|
154
|
+
_��� 13
|
155
|
+
�� 13
|
156
|
+
�� 13
|
157
|
+
�� 13
|
158
|
+
�� 13
|
159
|
+
��_ 13
|
160
|
+
�� 13
|
161
|
+
��_ 13
|
162
|
+
�_ 13
|
163
|
+
_�� 12
|
164
|
+
���_ 12
|
165
|
+
�� 12
|
166
|
+
�� 12
|
167
|
+
�� 12
|
168
|
+
��_ 12
|
169
|
+
��� 12
|
170
|
+
�� 12
|
171
|
+
��� 12
|
172
|
+
��_ 12
|
173
|
+
��� 12
|
174
|
+
_��� 12
|
175
|
+
�� 12
|
176
|
+
�� 12
|
177
|
+
_���_ 12
|
178
|
+
��_ 12
|
179
|
+
�� 11
|
180
|
+
��� 11
|
181
|
+
�� 11
|
182
|
+
". 11
|
183
|
+
�� 11
|
184
|
+
��� 11
|
185
|
+
�� 11
|
186
|
+
�� 11
|
187
|
+
�� 11
|
188
|
+
� 11
|
189
|
+
�� 11
|
190
|
+
_��� 10
|
191
|
+
_�� 10
|
192
|
+
�� 10
|
193
|
+
��� 10
|
194
|
+
_�� 10
|
195
|
+
�� 10
|
196
|
+
��_ 10
|
197
|
+
�� 10
|
198
|
+
_��_ 10
|
199
|
+
��� 10
|
200
|
+
��� 10
|
201
|
+
_�� 10
|
202
|
+
�� 10
|
203
|
+
_� 10
|
204
|
+
�� 10
|
205
|
+
_��� 10
|
206
|
+
�� 10
|
207
|
+
��� 10
|
208
|
+
���� 10
|
209
|
+
�. 10
|
210
|
+
_���_ 10
|
211
|
+
��� 10
|
212
|
+
� 10
|
213
|
+
�� 10
|
214
|
+
�� 10
|
215
|
+
_� 10
|
216
|
+
_���� 10
|
217
|
+
_��� 10
|
218
|
+
�� 10
|
219
|
+
�� 10
|
220
|
+
_��� 10
|
221
|
+
�� 10
|
222
|
+
��� 9
|
223
|
+
��� 9
|
224
|
+
� 9
|
225
|
+
�._ 9
|
226
|
+
�� 9
|
227
|
+
�� 9
|
228
|
+
� 9
|
229
|
+
_�� 9
|
230
|
+
", 9
|
231
|
+
��� 9
|
232
|
+
���_ 9
|
233
|
+
� 9
|
234
|
+
��_ 9
|
235
|
+
��� 9
|
236
|
+
��_ 9
|
237
|
+
�� 9
|
238
|
+
�_ 9
|
239
|
+
_� 9
|
240
|
+
_�� 9
|
241
|
+
��� 9
|
242
|
+
���_ 9
|
243
|
+
�� 9
|
244
|
+
���� 9
|
245
|
+
_���_ 9
|
246
|
+
�� 9
|
247
|
+
�� 9
|
248
|
+
_��� 9
|
249
|
+
��� 9
|
250
|
+
",_ 9
|
251
|
+
�� 9
|
252
|
+
_�� 9
|
253
|
+
���_ 9
|
254
|
+
�� 9
|
255
|
+
�� 9
|
256
|
+
���� 9
|
257
|
+
�� 8
|
258
|
+
�._ 8
|
259
|
+
���� 8
|
260
|
+
_�� 8
|
261
|
+
��� 8
|
262
|
+
����� 8
|
263
|
+
�� 8
|
264
|
+
�. 8
|
265
|
+
_���� 8
|
266
|
+
����� 8
|
267
|
+
��_ 8
|
268
|
+
_���� 8
|
269
|
+
_� 8
|
270
|
+
_� 8
|
271
|
+
��� 8
|
272
|
+
��� 8
|
273
|
+
���� 8
|
274
|
+
_��� 8
|
275
|
+
_�� 8
|
276
|
+
�� 8
|
277
|
+
�� 8
|
278
|
+
���� 8
|
279
|
+
�� 8
|
280
|
+
���_ 8
|
281
|
+
�� 8
|
282
|
+
��_ 8
|
283
|
+
�- 8
|
284
|
+
��� 8
|
285
|
+
���� 8
|
286
|
+
����� 8
|
287
|
+
�� 8
|
288
|
+
��� 8
|
289
|
+
�� 8
|
290
|
+
_�� 8
|
291
|
+
��_ 7
|
292
|
+
�, 7
|
293
|
+
�� 7
|
294
|
+
�� 7
|
295
|
+
_��_ 7
|
296
|
+
��_ 7
|
297
|
+
_���_ 7
|
298
|
+
�� 7
|
299
|
+
�� 7
|
300
|
+
��_ 7
|
301
|
+
�� 7
|
302
|
+
���� 7
|
303
|
+
�� 7
|
304
|
+
_���� 7
|
305
|
+
��� 7
|
306
|
+
���_ 7
|
307
|
+
����� 7
|
308
|
+
��� 7
|
309
|
+
��� 7
|
310
|
+
����� 7
|
311
|
+
_� 7
|
312
|
+
����_ 7
|
313
|
+
�� 7
|
314
|
+
_��� 7
|
315
|
+
-� 7
|
316
|
+
�� 7
|
317
|
+
_�� 7
|
318
|
+
���� 7
|
319
|
+
�- 7
|
320
|
+
_��� 7
|
321
|
+
_��� 7
|
322
|
+
��_ 7
|
323
|
+
�� 7
|
324
|
+
�� 7
|
325
|
+
��� 7
|
326
|
+
�_ 7
|
327
|
+
��� 7
|
328
|
+
����_ 6
|
329
|
+
�. 6
|
330
|
+
�� 6
|
331
|
+
_���_ 6
|
332
|
+
�� 6
|
333
|
+
���_ 6
|
334
|
+
_� 6
|
335
|
+
_�� 6
|
336
|
+
_��_ 6
|
337
|
+
_��� 6
|
338
|
+
_�� 6
|
339
|
+
�� 6
|
340
|
+
���_ 6
|
341
|
+
_�� 6
|
342
|
+
�� 6
|
343
|
+
���_ 6
|
344
|
+
_��� 6
|
345
|
+
�,_ 6
|
346
|
+
��_ 6
|
347
|
+
�� 6
|
348
|
+
��_ 6
|
349
|
+
�� 6
|
350
|
+
�� 6
|
351
|
+
��_ 6
|
352
|
+
�� 6
|
353
|
+
��. 6
|
354
|
+
�._ 6
|
355
|
+
�� 6
|
356
|
+
�� 6
|
357
|
+
��� 6
|
358
|
+
�� 6
|
359
|
+
���� 6
|
360
|
+
�� 6
|
361
|
+
���� 6
|
362
|
+
��� 6
|
363
|
+
��� 6
|
364
|
+
; 6
|
365
|
+
�� 6
|
366
|
+
��� 6
|
367
|
+
�,_ 6
|
368
|
+
_� 6
|
369
|
+
��_ 6
|
370
|
+
���_ 6
|
371
|
+
��� 6
|
372
|
+
_��� 6
|
373
|
+
��_ 6
|
374
|
+
�._ 6
|
375
|
+
�� 6
|
376
|
+
����_ 6
|
377
|
+
��� 6
|
378
|
+
_�� 6
|
379
|
+
�� 6
|
380
|
+
�� 6
|
381
|
+
_�._ 6
|
382
|
+
�� 6
|
383
|
+
�� 6
|
384
|
+
�� 6
|
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
|