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
|
+
� 18717
|
2
|
+
_ 8282
|
3
|
+
_� 4141
|
4
|
+
י 2236
|
5
|
+
� 2236
|
6
|
+
י� 2028
|
7
|
+
�� 2028
|
8
|
+
� 2000
|
9
|
+
ו 2000
|
10
|
+
ו� 1828
|
11
|
+
�� 1828
|
12
|
+
ה 1399
|
13
|
+
� 1399
|
14
|
+
� 1228
|
15
|
+
ל 1228
|
16
|
+
� 1141
|
17
|
+
ת 1141
|
18
|
+
ר 1133
|
19
|
+
� 1133
|
20
|
+
� 1129
|
21
|
+
א 1129
|
22
|
+
�� 999
|
23
|
+
א� 999
|
24
|
+
מ 944
|
25
|
+
�� 944
|
26
|
+
� 944
|
27
|
+
מ� 944
|
28
|
+
ר� 885
|
29
|
+
�� 885
|
30
|
+
� 832
|
31
|
+
ב 832
|
32
|
+
ל� 791
|
33
|
+
�� 791
|
34
|
+
� 734
|
35
|
+
ש 734
|
36
|
+
�� 706
|
37
|
+
ב� 706
|
38
|
+
ם 674
|
39
|
+
� 674
|
40
|
+
ה_ 660
|
41
|
+
�_ 660
|
42
|
+
_א 657
|
43
|
+
_א� 657
|
44
|
+
� 636
|
45
|
+
ד 636
|
46
|
+
ש� 617
|
47
|
+
�� 617
|
48
|
+
� 610
|
49
|
+
נ 610
|
50
|
+
�� 610
|
51
|
+
נ� 610
|
52
|
+
�_ 569
|
53
|
+
ת_ 569
|
54
|
+
�_ 535
|
55
|
+
ם_ 535
|
56
|
+
�� 534
|
57
|
+
ה� 534
|
58
|
+
� 523
|
59
|
+
ע 523
|
60
|
+
. 522
|
61
|
+
� 507
|
62
|
+
ק 507
|
63
|
+
ק� 499
|
64
|
+
�� 499
|
65
|
+
�� 499
|
66
|
+
ד� 499
|
67
|
+
� 495
|
68
|
+
פ 495
|
69
|
+
�� 495
|
70
|
+
פ� 495
|
71
|
+
ח 470
|
72
|
+
� 470
|
73
|
+
_מ� 461
|
74
|
+
_מ 461
|
75
|
+
�� 460
|
76
|
+
ע� 460
|
77
|
+
�� 441
|
78
|
+
� 441
|
79
|
+
כ 441
|
80
|
+
כ� 441
|
81
|
+
ת� 440
|
82
|
+
�� 440
|
83
|
+
_ב 433
|
84
|
+
ח� 432
|
85
|
+
�� 432
|
86
|
+
._ 423
|
87
|
+
,_ 422
|
88
|
+
, 422
|
89
|
+
ים 417
|
90
|
+
�ם 417
|
91
|
+
_ה 384
|
92
|
+
_ה� 384
|
93
|
+
_ב� 366
|
94
|
+
�ם_ 353
|
95
|
+
ים_ 353
|
96
|
+
� 348
|
97
|
+
ס� 348
|
98
|
+
�� 348
|
99
|
+
ס 348
|
100
|
+
�_ 328
|
101
|
+
ל_ 328
|
102
|
+
�ת 317
|
103
|
+
ות 317
|
104
|
+
ג 309
|
105
|
+
�� 309
|
106
|
+
� 309
|
107
|
+
ג� 309
|
108
|
+
ט 303
|
109
|
+
� 303
|
110
|
+
_ש 302
|
111
|
+
_ש� 302
|
112
|
+
_ל 253
|
113
|
+
_ל� 253
|
114
|
+
�ל 250
|
115
|
+
ול 250
|
116
|
+
�ת_ 243
|
117
|
+
ות_ 243
|
118
|
+
יה 239
|
119
|
+
�ה 239
|
120
|
+
�� 235
|
121
|
+
ט� 235
|
122
|
+
�ו 233
|
123
|
+
לו 233
|
124
|
+
לו� 217
|
125
|
+
�ו� 217
|
126
|
+
_ע� 212
|
127
|
+
_ע 212
|
128
|
+
� 212
|
129
|
+
צ 212
|
130
|
+
_ו 205
|
131
|
+
_ו� 205
|
132
|
+
�י 196
|
133
|
+
�י� 196
|
134
|
+
רי� 196
|
135
|
+
רי 196
|
136
|
+
�ק 194
|
137
|
+
יק 194
|
138
|
+
�ק� 194
|
139
|
+
יק� 194
|
140
|
+
רו 192
|
141
|
+
�ו 192
|
142
|
+
ר_ 188
|
143
|
+
�_ 188
|
144
|
+
�� 184
|
145
|
+
צ� 184
|
146
|
+
רו� 181
|
147
|
+
�ו� 181
|
148
|
+
יה_ 178
|
149
|
+
�ה_ 178
|
150
|
+
בה 175
|
151
|
+
�ה 175
|
152
|
+
�ו 174
|
153
|
+
מו 174
|
154
|
+
י_ 173
|
155
|
+
�_ 173
|
156
|
+
�ל� 172
|
157
|
+
ול� 172
|
158
|
+
�ו 170
|
159
|
+
או 170
|
160
|
+
�י 169
|
161
|
+
די 169
|
162
|
+
�ו 166
|
163
|
+
נו 166
|
164
|
+
�ו� 161
|
165
|
+
נו� 161
|
166
|
+
ית 160
|
167
|
+
�ת 160
|
168
|
+
_כ� 154
|
169
|
+
_כ 154
|
170
|
+
�ו 149
|
171
|
+
�ו� 149
|
172
|
+
יו 149
|
173
|
+
יו� 149
|
174
|
+
� 148
|
175
|
+
ז 148
|
176
|
+
�י� 147
|
177
|
+
די� 147
|
178
|
+
ז� 142
|
179
|
+
�� 142
|
180
|
+
את 141
|
181
|
+
�ו� 141
|
182
|
+
מו� 141
|
183
|
+
�ת 141
|
184
|
+
�י 139
|
185
|
+
ני 139
|
186
|
+
�י 137
|
187
|
+
גי 137
|
188
|
+
�ל 135
|
189
|
+
כל 135
|
190
|
+
�י� 129
|
191
|
+
גי� 129
|
192
|
+
�נ� 128
|
193
|
+
ונ� 128
|
194
|
+
ונ 128
|
195
|
+
�נ 128
|
196
|
+
מה 128
|
197
|
+
�ה 128
|
198
|
+
וג 125
|
199
|
+
וג� 125
|
200
|
+
�ג� 125
|
201
|
+
�ג 125
|
202
|
+
�_ 124
|
203
|
+
ו_ 124
|
204
|
+
ן 122
|
205
|
+
_ת� 122
|
206
|
+
_ת 122
|
207
|
+
� 122
|
208
|
+
�י 121
|
209
|
+
מי 121
|
210
|
+
ית_ 120
|
211
|
+
�ת_ 120
|
212
|
+
שי 118
|
213
|
+
�י 118
|
214
|
+
פי 118
|
215
|
+
_ר� 118
|
216
|
+
�י� 118
|
217
|
+
פי� 118
|
218
|
+
_ר 118
|
219
|
+
�י 118
|
220
|
+
�ם 118
|
221
|
+
אם 118
|
222
|
+
ה. 117
|
223
|
+
�. 117
|
224
|
+
מי� 115
|
225
|
+
�י� 115
|
226
|
+
_בה 114
|
227
|
+
�י� 114
|
228
|
+
ני� 114
|
229
|
+
_את 113
|
230
|
+
�_ 113
|
231
|
+
ד_ 113
|
232
|
+
�י 112
|
233
|
+
לי 112
|
234
|
+
מד 111
|
235
|
+
מד� 111
|
236
|
+
�ד� 111
|
237
|
+
�ד 111
|
238
|
+
וי� 107
|
239
|
+
וי 107
|
240
|
+
_ד� 107
|
241
|
+
�י� 107
|
242
|
+
_ד 107
|
243
|
+
�י 107
|
244
|
+
אח� 105
|
245
|
+
�ח� 105
|
246
|
+
אח 105
|
247
|
+
�ח 105
|
248
|
+
�ה 104
|
249
|
+
קה 104
|
250
|
+
�לו 104
|
251
|
+
�גי 104
|
252
|
+
�וג 104
|
253
|
+
�יה 104
|
254
|
+
על 102
|
255
|
+
�ל 102
|
256
|
+
_ס 101
|
257
|
+
�ו 101
|
258
|
+
ער 101
|
259
|
+
פו 101
|
260
|
+
�ר 101
|
261
|
+
_ס� 101
|
262
|
+
_על 100
|
263
|
+
בי 100
|
264
|
+
אל 100
|
265
|
+
_ג 100
|
266
|
+
�י� 100
|
267
|
+
_ג� 100
|
268
|
+
בי� 100
|
269
|
+
�ל 100
|
270
|
+
�י 100
|
271
|
+
יי 99
|
272
|
+
ה._ 99
|
273
|
+
�י 99
|
274
|
+
�._ 99
|
275
|
+
.� 99
|
276
|
+
_מה 98
|
277
|
+
ן_ 98
|
278
|
+
לי� 98
|
279
|
+
�_ 98
|
280
|
+
�י� 98
|
281
|
+
�ב 97
|
282
|
+
וד 97
|
283
|
+
_אח 97
|
284
|
+
�ד 97
|
285
|
+
רב 97
|
286
|
+
_אם 96
|
287
|
+
�ר 96
|
288
|
+
חר 96
|
289
|
+
דת 96
|
290
|
+
�ת 96
|
291
|
+
�ו� 95
|
292
|
+
שי� 95
|
293
|
+
פו� 95
|
294
|
+
�י� 95
|
295
|
+
_דת 94
|
296
|
+
_או 94
|
297
|
+
ש_ 92
|
298
|
+
ור 92
|
299
|
+
כל� 92
|
300
|
+
בה_ 92
|
301
|
+
�ה_ 92
|
302
|
+
�ל� 92
|
303
|
+
�_ 92
|
304
|
+
�ר 92
|
305
|
+
_ק 91
|
306
|
+
_ק� 91
|
307
|
+
�י 90
|
308
|
+
תי 90
|
309
|
+
קר 90
|
310
|
+
�ר 90
|
311
|
+
�,_ 88
|
312
|
+
רב� 88
|
313
|
+
ה, 88
|
314
|
+
�, 88
|
315
|
+
ה,_ 88
|
316
|
+
�ב� 88
|
317
|
+
או� 88
|
318
|
+
�ו� 88
|
319
|
+
�קה 87
|
320
|
+
יש 87
|
321
|
+
_ח� 87
|
322
|
+
�ש 87
|
323
|
+
_ח 87
|
324
|
+
�ר 86
|
325
|
+
בר 86
|
326
|
+
מה_ 85
|
327
|
+
א_ 85
|
328
|
+
�ה_ 85
|
329
|
+
�י� 85
|
330
|
+
�_ 85
|
331
|
+
יי� 85
|
332
|
+
�י 84
|
333
|
+
הי� 84
|
334
|
+
�י 84
|
335
|
+
הי 84
|
336
|
+
קי 84
|
337
|
+
�י� 84
|
338
|
+
גם 83
|
339
|
+
�ם 83
|
340
|
+
�ל 82
|
341
|
+
�י� 82
|
342
|
+
של 82
|
343
|
+
�מ� 82
|
344
|
+
_המ 82
|
345
|
+
המ 82
|
346
|
+
המ� 82
|
347
|
+
�י 82
|
348
|
+
צי 82
|
349
|
+
צי� 82
|
350
|
+
�מ 82
|
351
|
+
_של 80
|
352
|
+
�י 80
|
353
|
+
_גם 80
|
354
|
+
טי� 80
|
355
|
+
�י� 80
|
356
|
+
טי 80
|
357
|
+
שו� 79
|
358
|
+
ם. 79
|
359
|
+
�_ 79
|
360
|
+
קו 79
|
361
|
+
�. 79
|
362
|
+
אם_ 79
|
363
|
+
�ם_ 79
|
364
|
+
קו� 79
|
365
|
+
�ו� 79
|
366
|
+
�ו 79
|
367
|
+
�ו 79
|
368
|
+
שו 79
|
369
|
+
ב_ 79
|
370
|
+
�ו� 79
|
371
|
+
�י 78
|
372
|
+
_צ 78
|
373
|
+
אי 78
|
374
|
+
אנ� 77
|
375
|
+
�נ 77
|
376
|
+
�נ� 77
|
377
|
+
אנ 77
|
378
|
+
ת. 76
|
379
|
+
�חר 76
|
380
|
+
�. 76
|
381
|
+
ול_ 75
|
382
|
+
יכ 75
|
383
|
+
�ל_ 75
|
384
|
+
יכ� 75
|
385
|
+
�כ 75
|
386
|
+
�פ� 75
|
387
|
+
�פ 75
|
388
|
+
ספ 75
|
389
|
+
�כ� 75
|
390
|
+
ספ� 75
|
391
|
+
�א 74
|
392
|
+
נא 74
|
393
|
+
ופ� 74
|
394
|
+
ופ 74
|
395
|
+
�פ 74
|
396
|
+
�פ� 74
|
397
|
+
עי 73
|
398
|
+
�י 73
|
399
|
+
�ת_ 73
|
400
|
+
�י� 73
|