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
|
+
� 26053
|
2
|
+
� 21638
|
3
|
+
_ 20952
|
4
|
+
� 7004
|
5
|
+
ا 7004
|
6
|
+
_� 5905
|
7
|
+
� 5598
|
8
|
+
ل 5598
|
9
|
+
�� 4328
|
10
|
+
ا� 4328
|
11
|
+
_� 3516
|
12
|
+
ي 3314
|
13
|
+
� 3314
|
14
|
+
ال 3313
|
15
|
+
�ل 3313
|
16
|
+
م 3159
|
17
|
+
� 3159
|
18
|
+
�� 2820
|
19
|
+
ل� 2820
|
20
|
+
_ا 2714
|
21
|
+
� 2654
|
22
|
+
و 2654
|
23
|
+
_ا� 2614
|
24
|
+
_ال 2512
|
25
|
+
ر 2192
|
26
|
+
� 2192
|
27
|
+
ال� 2158
|
28
|
+
�ل� 2158
|
29
|
+
� 2092
|
30
|
+
ن 2092
|
31
|
+
�� 2058
|
32
|
+
ل� 2058
|
33
|
+
�� 2030
|
34
|
+
ا� 2030
|
35
|
+
� 1994
|
36
|
+
ت 1994
|
37
|
+
� 1777
|
38
|
+
ب 1772
|
39
|
+
ي� 1727
|
40
|
+
�� 1727
|
41
|
+
� 1712
|
42
|
+
ة 1712
|
43
|
+
ع 1691
|
44
|
+
� 1691
|
45
|
+
� 1652
|
46
|
+
د 1652
|
47
|
+
�� 1513
|
48
|
+
و� 1513
|
49
|
+
ة_ 1420
|
50
|
+
�_ 1420
|
51
|
+
م� 1353
|
52
|
+
�� 1353
|
53
|
+
م� 1183
|
54
|
+
�� 1183
|
55
|
+
س 1089
|
56
|
+
� 1089
|
57
|
+
_و 1070
|
58
|
+
�ل� 1026
|
59
|
+
ال� 1026
|
60
|
+
ق 1019
|
61
|
+
� 1019
|
62
|
+
� 976
|
63
|
+
ف 976
|
64
|
+
� 950
|
65
|
+
ك 950
|
66
|
+
� 943
|
67
|
+
ه 943
|
68
|
+
�� 938
|
69
|
+
ر� 938
|
70
|
+
� 925
|
71
|
+
ب� 918
|
72
|
+
�� 918
|
73
|
+
� 916
|
74
|
+
ح 916
|
75
|
+
و� 907
|
76
|
+
�� 907
|
77
|
+
ع� 879
|
78
|
+
�� 879
|
79
|
+
أ 874
|
80
|
+
_م 816
|
81
|
+
ي� 811
|
82
|
+
�� 811
|
83
|
+
ت� 810
|
84
|
+
�� 810
|
85
|
+
__ 784
|
86
|
+
. 775
|
87
|
+
�_ 773
|
88
|
+
ن_ 773
|
89
|
+
�� 726
|
90
|
+
ن� 726
|
91
|
+
�� 722
|
92
|
+
ر� 722
|
93
|
+
_و� 700
|
94
|
+
_ب 699
|
95
|
+
�� 696
|
96
|
+
د� 696
|
97
|
+
�� 690
|
98
|
+
ب� 685
|
99
|
+
ي_ 682
|
100
|
+
�_ 682
|
101
|
+
ت� 675
|
102
|
+
�� 675
|
103
|
+
�م 654
|
104
|
+
لم 654
|
105
|
+
� 630
|
106
|
+
ج 630
|
107
|
+
ق� 621
|
108
|
+
�� 621
|
109
|
+
�ة 609
|
110
|
+
ية 609
|
111
|
+
ع� 592
|
112
|
+
�� 592
|
113
|
+
�_ 577
|
114
|
+
ل_ 577
|
115
|
+
س� 554
|
116
|
+
�� 554
|
117
|
+
� 548
|
118
|
+
ط 548
|
119
|
+
�� 546
|
120
|
+
ح� 546
|
121
|
+
�� 539
|
122
|
+
, 537
|
123
|
+
._ 536
|
124
|
+
�_ 532
|
125
|
+
,_ 532
|
126
|
+
ا_ 532
|
127
|
+
م_ 514
|
128
|
+
�_ 514
|
129
|
+
�لم 506
|
130
|
+
أ� 489
|
131
|
+
�� 487
|
132
|
+
ه� 487
|
133
|
+
ر_ 480
|
134
|
+
�_ 480
|
135
|
+
�ا 479
|
136
|
+
وا 479
|
137
|
+
�_ 471
|
138
|
+
ت_ 471
|
139
|
+
ية_ 469
|
140
|
+
�ة_ 469
|
141
|
+
_أ 468
|
142
|
+
د� 454
|
143
|
+
�� 454
|
144
|
+
ف� 448
|
145
|
+
�� 448
|
146
|
+
� 447
|
147
|
+
ص 447
|
148
|
+
_م� 445
|
149
|
+
إ 445
|
150
|
+
� 445
|
151
|
+
ك� 439
|
152
|
+
� 439
|
153
|
+
�� 439
|
154
|
+
ش 439
|
155
|
+
ن� 437
|
156
|
+
�� 437
|
157
|
+
� 434
|
158
|
+
�� 433
|
159
|
+
س� 433
|
160
|
+
_ع 432
|
161
|
+
ز 430
|
162
|
+
�_ 430
|
163
|
+
د_ 430
|
164
|
+
من 427
|
165
|
+
�ن 427
|
166
|
+
�ا 401
|
167
|
+
ما 401
|
168
|
+
_ب� 398
|
169
|
+
�ن 384
|
170
|
+
ان 384
|
171
|
+
ك� 382
|
172
|
+
�� 382
|
173
|
+
�� 381
|
174
|
+
أ� 381
|
175
|
+
�ا 374
|
176
|
+
لا 374
|
177
|
+
لي 368
|
178
|
+
�ي 368
|
179
|
+
ات 366
|
180
|
+
�ت 366
|
181
|
+
�ر 361
|
182
|
+
ار 361
|
183
|
+
_ف 361
|
184
|
+
_ل 355
|
185
|
+
ف� 353
|
186
|
+
�� 353
|
187
|
+
_م� 345
|
188
|
+
خ 343
|
189
|
+
� 343
|
190
|
+
_ت 338
|
191
|
+
� 332
|
192
|
+
ض 332
|
193
|
+
وا� 329
|
194
|
+
�ا� 329
|
195
|
+
، 318
|
196
|
+
� 318
|
197
|
+
في 317
|
198
|
+
�م� 317
|
199
|
+
�ي 317
|
200
|
+
لم� 317
|
201
|
+
� 316
|
202
|
+
ث 316
|
203
|
+
_وا 310
|
204
|
+
ج� 309
|
205
|
+
�� 309
|
206
|
+
ح� 306
|
207
|
+
_و� 306
|
208
|
+
�� 306
|
209
|
+
با 304
|
210
|
+
�ا 304
|
211
|
+
_ف� 303
|
212
|
+
_ب� 301
|
213
|
+
_أ� 300
|
214
|
+
� 293
|
215
|
+
ى 293
|
216
|
+
دي 282
|
217
|
+
�ي 282
|
218
|
+
ّ 281
|
219
|
+
� 281
|
220
|
+
،_ 280
|
221
|
+
�_ 280
|
222
|
+
�ا 276
|
223
|
+
يا 276
|
224
|
+
�� 275
|
225
|
+
�ي 275
|
226
|
+
ري 275
|
227
|
+
ج� 275
|
228
|
+
ه� 273
|
229
|
+
�� 273
|
230
|
+
ات_ 272
|
231
|
+
�ت_ 272
|
232
|
+
ق� 271
|
233
|
+
�ال 271
|
234
|
+
�� 271
|
235
|
+
ى_ 270
|
236
|
+
�_ 270
|
237
|
+
لأ 269
|
238
|
+
�أ 269
|
239
|
+
�ا 261
|
240
|
+
ها 261
|
241
|
+
�ن 256
|
242
|
+
ين 256
|
243
|
+
�ع 255
|
244
|
+
لع 255
|
245
|
+
ام 254
|
246
|
+
�م 254
|
247
|
+
_من 251
|
248
|
+
�م� 248
|
249
|
+
لم� 248
|
250
|
+
_ل� 247
|
251
|
+
�� 246
|
252
|
+
ش� 246
|
253
|
+
_في 244
|
254
|
+
�� 242
|
255
|
+
ط� 242
|
256
|
+
عا 240
|
257
|
+
را 240
|
258
|
+
�ا 240
|
259
|
+
�ا 240
|
260
|
+
_إ 236
|
261
|
+
�لأ 235
|
262
|
+
�ل 234
|
263
|
+
�لع 234
|
264
|
+
ول 234
|
265
|
+
ذ 233
|
266
|
+
إ� 233
|
267
|
+
�� 233
|
268
|
+
� 233
|
269
|
+
ط� 230
|
270
|
+
�� 230
|
271
|
+
�ي_ 229
|
272
|
+
ص� 229
|
273
|
+
�� 229
|
274
|
+
في_ 229
|
275
|
+
_ك 229
|
276
|
+
�� 224
|
277
|
+
خ� 224
|
278
|
+
_ع� 224
|
279
|
+
�ن_ 221
|
280
|
+
من_ 221
|
281
|
+
لك 215
|
282
|
+
�ع� 215
|
283
|
+
لع� 215
|
284
|
+
�ك 215
|
285
|
+
�� 213
|
286
|
+
ز� 213
|
287
|
+
�� 212
|
288
|
+
� 212
|
289
|
+
غ 212
|
290
|
+
إ� 212
|
291
|
+
�س 211
|
292
|
+
لس 211
|
293
|
+
�ي 209
|
294
|
+
بي 209
|
295
|
+
عل 208
|
296
|
+
�ل 208
|
297
|
+
_ع� 208
|
298
|
+
�ل 204
|
299
|
+
مل 204
|
300
|
+
ص� 204
|
301
|
+
�� 204
|
302
|
+
با� 200
|
303
|
+
� 200
|
304
|
+
�ا� 200
|
305
|
+
_ق 197
|
306
|
+
ء 197
|
307
|
+
اد 195
|
308
|
+
�د 195
|
309
|
+
�لس 195
|
310
|
+
ع_ 195
|
311
|
+
�_ 195
|
312
|
+
�د 191
|
313
|
+
ود 191
|
314
|
+
�د 187
|
315
|
+
عد 187
|
316
|
+
_ت� 184
|
317
|
+
_ح 183
|
318
|
+
�_ 181
|
319
|
+
و_ 181
|
320
|
+
لح 180
|
321
|
+
�ح 180
|
322
|
+
�ت 179
|
323
|
+
لت 179
|
324
|
+
ري� 178
|
325
|
+
_ه 178
|
326
|
+
�ي� 178
|
327
|
+
لي� 177
|
328
|
+
�ي� 177
|
329
|
+
لإ 177
|
330
|
+
�إ 177
|
331
|
+
را� 176
|
332
|
+
�ا� 176
|
333
|
+
�ا 174
|
334
|
+
نا 174
|
335
|
+
�� 173
|
336
|
+
ش� 173
|
337
|
+
رب 172
|
338
|
+
�ي 172
|
339
|
+
وي 172
|
340
|
+
�ب 172
|
341
|
+
ها_ 171
|
342
|
+
�ء 171
|
343
|
+
اء 171
|
344
|
+
�ا_ 171
|
345
|
+
يا� 169
|
346
|
+
�ا� 169
|
347
|
+
_أ� 168
|
348
|
+
�ر 166
|
349
|
+
ير 166
|
350
|
+
بل 165
|
351
|
+
�ل 165
|
352
|
+
_با 162
|
353
|
+
�ا 161
|
354
|
+
دا 161
|
355
|
+
دي� 160
|
356
|
+
ه_ 160
|
357
|
+
�ي� 160
|
358
|
+
�_ 160
|
359
|
+
ني 158
|
360
|
+
�ي 158
|
361
|
+
مي 157
|
362
|
+
�ي 157
|
363
|
+
�لح 156
|
364
|
+
ء_ 155
|
365
|
+
�_ 155
|
366
|
+
_ت� 154
|
367
|
+
�لإ 154
|
368
|
+
لا� 153
|
369
|
+
�ا� 153
|
370
|
+
�_ 152
|
371
|
+
ف_ 152
|
372
|
+
�ل� 152
|
373
|
+
مل� 152
|
374
|
+
رة 151
|
375
|
+
�ة 151
|
376
|
+
�ا� 149
|
377
|
+
مع 149
|
378
|
+
�ع 149
|
379
|
+
لا� 149
|
380
|
+
�ال 148
|
381
|
+
لأ� 147
|
382
|
+
�م 147
|
383
|
+
�_ 147
|
384
|
+
تم 147
|
385
|
+
�أ� 147
|
386
|
+
�ى 147
|
387
|
+
لى 147
|
388
|
+
ب_ 147
|
389
|
+
_ي 147
|
390
|
+
ما_ 145
|
391
|
+
�ا_ 145
|
392
|
+
عا� 144
|
393
|
+
_ج 144
|
394
|
+
�ب 144
|
395
|
+
�ا� 144
|
396
|
+
لب 144
|
397
|
+
_ق� 144
|
398
|
+
�س 143
|
399
|
+
سي 143
|
400
|
+
�ي 143
|