scylla 0.7.0 → 0.7.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- data/lib/scylla/classifier.rb +3 -4
- data/lib/scylla/generator.rb +4 -7
- data/lib/scylla/lms/afrikaans.lm +280 -280
- data/lib/scylla/lms/arabic.lm +225 -225
- data/lib/scylla/lms/bulgarian.lm +208 -208
- data/lib/scylla/lms/catalan.lm +212 -212
- data/lib/scylla/lms/chinese.lm +201 -201
- data/lib/scylla/lms/danish.lm +155 -155
- data/lib/scylla/lms/english.lm +207 -207
- data/lib/scylla/lms/finnish.lm +259 -259
- data/lib/scylla/lms/french.lm +203 -203
- data/lib/scylla/lms/german.lm +280 -280
- data/lib/scylla/lms/greek.lm +276 -276
- data/lib/scylla/lms/hebrew.lm +170 -170
- data/lib/scylla/lms/hindi.lm +241 -241
- data/lib/scylla/lms/icelandic.lm +264 -264
- data/lib/scylla/lms/indonesian.lm +272 -272
- data/lib/scylla/lms/italian.lm +283 -283
- data/lib/scylla/lms/japanese.lm +105 -105
- data/lib/scylla/lms/korean.lm +400 -400
- data/lib/scylla/lms/norwegian.lm +235 -235
- data/lib/scylla/lms/polish.lm +264 -264
- data/lib/scylla/lms/portuguese.lm +269 -269
- data/lib/scylla/lms/romanian.lm +278 -278
- data/lib/scylla/lms/russian.lm +127 -127
- data/lib/scylla/lms/slovak.lm +281 -281
- data/lib/scylla/lms/slovenian.lm +276 -276
- data/lib/scylla/lms/spanish.lm +190 -190
- data/lib/scylla/lms/swedish.lm +195 -195
- data/lib/scylla/lms/tagalog.lm +282 -282
- data/lib/scylla/lms/thai.lm +257 -257
- data/lib/scylla/lms/turkish.lm +300 -300
- data/lib/scylla/lms/vietnamese.lm +277 -277
- data/lib/scylla/lms/welsh.lm +271 -271
- data/scylla.gemspec +3 -22
- data/source_texts/korean.txt +219 -134
- metadata +15 -14
- data/scylla-0.6.0.gem +0 -0
data/lib/scylla/lms/arabic.lm
CHANGED
@@ -1,400 +1,400 @@
|
|
1
1
|
� 26053
|
2
2
|
� 21638
|
3
|
-
_
|
3
|
+
_ 20044
|
4
4
|
� 7004
|
5
5
|
ا 7004
|
6
|
-
_�
|
7
|
-
� 5598
|
6
|
+
_� 6209
|
8
7
|
ل 5598
|
9
|
-
|
10
|
-
��
|
11
|
-
|
8
|
+
� 5598
|
9
|
+
�� 4325
|
10
|
+
ا� 4325
|
11
|
+
_� 3698
|
12
12
|
� 3314
|
13
13
|
ي 3314
|
14
|
-
ال 3313
|
15
14
|
�ل 3313
|
15
|
+
ال 3313
|
16
16
|
م 3159
|
17
17
|
� 3159
|
18
|
-
|
19
|
-
��
|
20
|
-
|
18
|
+
_ا 2826
|
19
|
+
�� 2819
|
20
|
+
ل� 2819
|
21
|
+
_ا� 2724
|
21
22
|
� 2654
|
22
23
|
و 2654
|
23
|
-
_
|
24
|
-
_ال 2527
|
24
|
+
_ال 2621
|
25
25
|
ر 2192
|
26
26
|
� 2192
|
27
|
-
�ل� 2158
|
28
27
|
ال� 2158
|
28
|
+
�ل� 2158
|
29
29
|
� 2092
|
30
30
|
ن 2092
|
31
|
-
|
32
|
-
|
33
|
-
ا�
|
34
|
-
��
|
35
|
-
� 1994
|
31
|
+
�� 2056
|
32
|
+
ل� 2056
|
33
|
+
ا� 2028
|
34
|
+
�� 2028
|
36
35
|
ت 1994
|
36
|
+
� 1994
|
37
37
|
� 1777
|
38
38
|
ب 1772
|
39
|
-
��
|
40
|
-
ي�
|
41
|
-
� 1712
|
39
|
+
�� 1721
|
40
|
+
ي� 1721
|
42
41
|
ة 1712
|
43
|
-
|
42
|
+
� 1712
|
44
43
|
� 1691
|
45
|
-
|
44
|
+
ع 1691
|
46
45
|
� 1652
|
46
|
+
د 1652
|
47
47
|
�� 1513
|
48
48
|
و� 1513
|
49
|
-
|
50
|
-
|
51
|
-
|
52
|
-
|
53
|
-
|
54
|
-
|
49
|
+
ة_ 1491
|
50
|
+
�_ 1491
|
51
|
+
م� 1350
|
52
|
+
�� 1350
|
53
|
+
م� 1179
|
54
|
+
�� 1179
|
55
|
+
_و 1115
|
55
56
|
س 1089
|
56
57
|
� 1089
|
57
|
-
_و 1080
|
58
|
-
ال� 1026
|
59
58
|
�ل� 1026
|
59
|
+
ال� 1026
|
60
60
|
ق 1019
|
61
61
|
� 1019
|
62
|
-
� 976
|
63
62
|
ف 976
|
63
|
+
� 976
|
64
64
|
ك 950
|
65
65
|
� 950
|
66
66
|
� 943
|
67
67
|
ه 943
|
68
|
-
|
69
|
-
|
68
|
+
�� 936
|
69
|
+
ر� 936
|
70
70
|
� 925
|
71
|
-
�� 918
|
72
|
-
ب� 918
|
73
|
-
ح 916
|
74
71
|
� 916
|
75
|
-
|
72
|
+
ح 916
|
73
|
+
�� 915
|
74
|
+
ب� 915
|
76
75
|
و� 907
|
76
|
+
�� 907
|
77
|
+
_م 898
|
77
78
|
ع� 879
|
78
79
|
�� 879
|
79
80
|
أ 874
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
|
84
|
-
|
85
|
-
|
86
|
-
�_ 776
|
87
|
-
ن_ 776
|
81
|
+
�� 806
|
82
|
+
ي� 806
|
83
|
+
ت� 804
|
84
|
+
�� 804
|
85
|
+
�_ 786
|
86
|
+
ن_ 786
|
88
87
|
. 772
|
89
|
-
|
90
|
-
|
91
|
-
�� 722
|
92
|
-
|
93
|
-
_ب
|
94
|
-
|
88
|
+
._ 762
|
89
|
+
ن� 722
|
90
|
+
�� 722
|
91
|
+
_و� 721
|
92
|
+
_ب 720
|
93
|
+
ر� 719
|
94
|
+
�� 719
|
95
|
+
ي_ 703
|
96
|
+
�_ 703
|
95
97
|
د� 696
|
96
98
|
�� 696
|
97
|
-
��
|
98
|
-
ب�
|
99
|
-
|
100
|
-
|
101
|
-
|
102
|
-
|
103
|
-
�م 654
|
104
|
-
لم 654
|
99
|
+
�� 689
|
100
|
+
ب� 684
|
101
|
+
ت� 674
|
102
|
+
�� 674
|
103
|
+
لم 652
|
104
|
+
�م 652
|
105
105
|
ج 630
|
106
106
|
� 630
|
107
|
-
ق� 621
|
108
107
|
�� 621
|
108
|
+
ق� 621
|
109
|
+
ل_ 611
|
110
|
+
�_ 611
|
109
111
|
ية 609
|
110
112
|
�ة 609
|
111
|
-
ع� 592
|
112
113
|
�� 592
|
113
|
-
|
114
|
-
|
115
|
-
س�
|
116
|
-
�� 556
|
117
|
-
ط 548
|
114
|
+
ع� 592
|
115
|
+
�� 554
|
116
|
+
س� 554
|
118
117
|
� 548
|
119
|
-
|
120
|
-
|
118
|
+
ط 548
|
119
|
+
ح� 545
|
120
|
+
�� 545
|
121
|
+
�_ 541
|
122
|
+
ا_ 541
|
121
123
|
�� 539
|
122
|
-
._ 539
|
123
124
|
, 537
|
124
|
-
�_ 533
|
125
|
-
ا_ 533
|
126
125
|
,_ 532
|
127
|
-
|
128
|
-
|
126
|
+
م_ 524
|
127
|
+
�_ 524
|
129
128
|
�لم 506
|
129
|
+
�ة_ 505
|
130
|
+
ية_ 505
|
131
|
+
�_ 490
|
132
|
+
ر_ 490
|
130
133
|
أ� 489
|
131
134
|
�� 487
|
132
135
|
ه� 487
|
133
|
-
|
134
|
-
|
135
|
-
|
136
|
+
_أ 485
|
137
|
+
ت_ 480
|
138
|
+
�_ 480
|
139
|
+
_م� 480
|
136
140
|
�ا 479
|
137
|
-
|
138
|
-
|
139
|
-
|
140
|
-
|
141
|
-
|
142
|
-
�� 456
|
143
|
-
د� 456
|
144
|
-
�� 448
|
145
|
-
ف� 448
|
146
|
-
_م� 448
|
141
|
+
وا 479
|
142
|
+
_ع 474
|
143
|
+
د� 449
|
144
|
+
�� 449
|
145
|
+
�� 447
|
147
146
|
� 447
|
147
|
+
ف� 447
|
148
148
|
ص 447
|
149
|
-
إ 445
|
150
149
|
� 445
|
151
|
-
|
152
|
-
ك� 441
|
150
|
+
إ 445
|
153
151
|
� 439
|
154
152
|
ش 439
|
155
|
-
��
|
156
|
-
|
157
|
-
_
|
153
|
+
�� 439
|
154
|
+
ك� 439
|
155
|
+
د_ 437
|
156
|
+
�_ 437
|
158
157
|
� 434
|
159
|
-
|
158
|
+
�� 434
|
159
|
+
ن� 434
|
160
160
|
�� 433
|
161
|
+
س� 433
|
161
162
|
ز 430
|
162
|
-
د_ 430
|
163
|
-
�_ 430
|
164
163
|
�ن 427
|
165
164
|
من 427
|
166
|
-
|
167
|
-
|
168
|
-
ما
|
169
|
-
|
170
|
-
�ا 398
|
171
|
-
ان 384
|
165
|
+
_ب� 413
|
166
|
+
�ا 400
|
167
|
+
ما 400
|
168
|
+
_م� 392
|
172
169
|
�ن 384
|
173
|
-
|
170
|
+
ان 384
|
174
171
|
ك� 382
|
175
|
-
��
|
172
|
+
�� 382
|
176
173
|
أ� 381
|
177
|
-
|
174
|
+
�� 381
|
175
|
+
_ت 378
|
176
|
+
لا 373
|
177
|
+
�ا 373
|
178
178
|
لي 368
|
179
|
-
|
179
|
+
�ي 368
|
180
|
+
_ف 368
|
180
181
|
ات 366
|
181
|
-
|
182
|
+
�ت 366
|
183
|
+
_ل 366
|
182
184
|
ار 361
|
183
185
|
�ر 361
|
184
|
-
|
185
|
-
ف�
|
186
|
-
�� 353
|
187
|
-
_ت 352
|
188
|
-
_م� 352
|
189
|
-
خ 343
|
186
|
+
�� 352
|
187
|
+
ف� 352
|
190
188
|
� 343
|
191
|
-
|
189
|
+
خ 343
|
192
190
|
� 332
|
191
|
+
ض 332
|
193
192
|
�ا� 329
|
194
193
|
وا� 329
|
195
|
-
|
194
|
+
_و� 326
|
196
195
|
� 318
|
197
|
-
|
198
|
-
لم� 317
|
199
|
-
�م� 317
|
196
|
+
، 318
|
200
197
|
في 317
|
201
|
-
|
198
|
+
�ي 317
|
199
|
+
لم� 316
|
200
|
+
�م� 316
|
202
201
|
ث 316
|
203
|
-
|
204
|
-
_وا
|
205
|
-
|
206
|
-
|
207
|
-
|
202
|
+
� 316
|
203
|
+
_وا 312
|
204
|
+
_أ� 311
|
205
|
+
�� 307
|
206
|
+
ج� 307
|
207
|
+
_ب� 307
|
208
|
+
_ف� 306
|
208
209
|
ح� 306
|
209
|
-
|
210
|
-
�ا
|
211
|
-
|
212
|
-
_ب� 301
|
213
|
-
_أ� 301
|
214
|
-
ى 293
|
210
|
+
�� 306
|
211
|
+
�ا 303
|
212
|
+
با 303
|
215
213
|
� 293
|
216
|
-
|
214
|
+
ى 293
|
217
215
|
دي 282
|
216
|
+
�ي 282
|
218
217
|
ّ 281
|
219
218
|
� 281
|
220
219
|
�_ 280
|
221
220
|
،_ 280
|
222
|
-
|
223
|
-
|
224
|
-
ري 275
|
225
|
-
ج� 275
|
221
|
+
ات_ 277
|
222
|
+
�ت_ 277
|
226
223
|
�ي 275
|
224
|
+
ري 275
|
227
225
|
�� 275
|
226
|
+
ج� 275
|
228
227
|
�� 273
|
229
228
|
ه� 273
|
230
|
-
|
231
|
-
|
229
|
+
�ا 272
|
230
|
+
يا 272
|
231
|
+
�ال 271
|
232
232
|
�� 271
|
233
|
+
_من 271
|
233
234
|
ق� 271
|
234
|
-
�ال 271
|
235
235
|
�_ 270
|
236
|
-
�أ 270
|
237
|
-
لأ 270
|
238
236
|
ى_ 270
|
237
|
+
لأ 269
|
238
|
+
�أ 269
|
239
239
|
ها 261
|
240
240
|
�ا 261
|
241
241
|
�ن 256
|
242
|
+
_ل� 256
|
242
243
|
ين 256
|
243
|
-
لع 255
|
244
244
|
�ع 255
|
245
|
-
|
246
|
-
ام
|
247
|
-
|
248
|
-
|
249
|
-
�م� 248
|
250
|
-
_ل� 247
|
251
|
-
ش� 246
|
245
|
+
لع 255
|
246
|
+
ام 251
|
247
|
+
�م 251
|
248
|
+
_في 247
|
252
249
|
�� 246
|
253
|
-
|
254
|
-
|
250
|
+
لم� 246
|
251
|
+
�م� 246
|
252
|
+
ش� 246
|
253
|
+
_ع� 245
|
255
254
|
�� 242
|
256
|
-
|
257
|
-
|
255
|
+
ط� 242
|
256
|
+
_إ 241
|
258
257
|
عا 240
|
259
|
-
�ا 240
|
260
|
-
|
258
|
+
�ا 240
|
259
|
+
�ا 239
|
260
|
+
را 239
|
261
|
+
_ك 236
|
261
262
|
�لأ 235
|
262
|
-
�لع 234
|
263
263
|
�ل 234
|
264
|
+
�لع 234
|
264
265
|
ول 234
|
265
|
-
إ� 233
|
266
266
|
� 233
|
267
267
|
�� 233
|
268
268
|
ذ 233
|
269
|
-
|
269
|
+
إ� 233
|
270
270
|
ط� 230
|
271
|
+
�� 230
|
271
272
|
في_ 229
|
272
273
|
ص� 229
|
273
274
|
�� 229
|
274
275
|
�ي_ 229
|
275
|
-
_
|
276
|
-
_ع� 224
|
276
|
+
_ع� 229
|
277
277
|
�� 224
|
278
278
|
خ� 224
|
279
|
-
�ن_
|
280
|
-
من_
|
279
|
+
�ن_ 222
|
280
|
+
من_ 222
|
281
281
|
�ع� 215
|
282
|
-
لع� 215
|
283
282
|
لك 215
|
284
283
|
�ك 215
|
284
|
+
لع� 215
|
285
285
|
�� 213
|
286
286
|
ز� 213
|
287
287
|
إ� 212
|
288
|
-
�� 212
|
289
288
|
غ 212
|
290
289
|
� 212
|
291
|
-
|
292
|
-
|
290
|
+
�� 212
|
291
|
+
_ت� 212
|
293
292
|
�س 211
|
294
|
-
|
295
|
-
|
296
|
-
�ل 208
|
293
|
+
لس 211
|
294
|
+
�ي 208
|
297
295
|
عل 208
|
296
|
+
�ل 208
|
297
|
+
بي 208
|
298
|
+
_ق 205
|
298
299
|
�� 204
|
299
300
|
ص� 204
|
300
301
|
مل 204
|
301
302
|
�ل 204
|
302
|
-
_ق 201
|
303
|
-
�ا� 200
|
304
303
|
� 200
|
305
|
-
با�
|
304
|
+
با� 199
|
305
|
+
�ا� 199
|
306
306
|
ء 197
|
307
|
-
_ت� 197
|
308
|
-
ع_ 195
|
309
|
-
�_ 195
|
310
307
|
�د 195
|
308
|
+
�_ 195
|
311
309
|
اد 195
|
310
|
+
ع_ 195
|
312
311
|
�لس 195
|
313
312
|
�د 191
|
314
313
|
ود 191
|
315
|
-
|
314
|
+
_ح 188
|
316
315
|
�د 187
|
317
|
-
|
318
|
-
|
319
|
-
�_
|
316
|
+
عد 187
|
317
|
+
_ه 183
|
318
|
+
�_ 182
|
319
|
+
و_ 182
|
320
320
|
لح 180
|
321
|
-
�ت 180
|
322
|
-
لي� 180
|
323
|
-
�ي� 180
|
324
|
-
لت 180
|
325
321
|
�ح 180
|
326
|
-
|
327
|
-
|
322
|
+
�ت 179
|
323
|
+
لت 179
|
328
324
|
�ي� 178
|
325
|
+
ري� 178
|
329
326
|
لإ 177
|
330
|
-
�ا� 177
|
331
|
-
لا� 177
|
332
327
|
�إ 177
|
333
328
|
�ا� 176
|
334
329
|
را� 176
|
335
|
-
|
336
|
-
|
330
|
+
لي� 176
|
331
|
+
�ي� 176
|
332
|
+
_أ� 174
|
333
|
+
�ا_ 174
|
334
|
+
ها_ 174
|
337
335
|
�� 173
|
338
|
-
رب 173
|
339
|
-
�ب 173
|
340
336
|
ش� 173
|
341
|
-
|
337
|
+
�ب 172
|
338
|
+
رب 172
|
342
339
|
�ي 172
|
343
|
-
|
344
|
-
|
345
|
-
�ا_ 171
|
340
|
+
وي 172
|
341
|
+
�ا 171
|
346
342
|
�ء 171
|
347
|
-
|
348
|
-
|
349
|
-
|
350
|
-
|
343
|
+
اء 171
|
344
|
+
نا 171
|
345
|
+
_ج 168
|
346
|
+
�ا� 168
|
347
|
+
يا� 168
|
351
348
|
ير 166
|
349
|
+
�ر 166
|
350
|
+
_ت� 166
|
352
351
|
�ل 165
|
353
352
|
بل 165
|
354
353
|
_با 165
|
355
|
-
�ا 162
|
356
|
-
دا 162
|
357
|
-
ه_ 160
|
358
|
-
دي� 160
|
359
354
|
�_ 160
|
360
|
-
|
361
|
-
|
362
|
-
|
355
|
+
ه_ 160
|
356
|
+
_ي 160
|
357
|
+
دا 159
|
358
|
+
�ا 159
|
359
|
+
ء_ 158
|
360
|
+
�_ 158
|
361
|
+
ني 157
|
362
|
+
�ي 157
|
363
|
+
�ي� 157
|
364
|
+
دي� 157
|
363
365
|
مي 157
|
366
|
+
ف_ 157
|
364
367
|
�ي 157
|
368
|
+
�_ 157
|
365
369
|
�لح 156
|
366
|
-
ء_ 155
|
367
|
-
�_ 155
|
368
|
-
_ت� 155
|
369
370
|
�لإ 154
|
370
|
-
|
371
|
-
ف_ 153
|
372
|
-
�ل� 152
|
371
|
+
�ا� 152
|
373
372
|
مل� 152
|
373
|
+
لا� 152
|
374
|
+
�ل� 152
|
374
375
|
رة 151
|
375
376
|
�ة 151
|
376
|
-
|
377
|
+
ب_ 151
|
378
|
+
�_ 151
|
377
379
|
لا� 149
|
378
|
-
�ع 149
|
379
380
|
�ا� 149
|
380
|
-
|
381
|
-
|
382
|
-
|
383
|
-
|
381
|
+
مع 149
|
382
|
+
�ع 149
|
383
|
+
_ق� 148
|
384
|
+
�ال 147
|
384
385
|
�م 147
|
385
386
|
لى 147
|
386
387
|
�ى 147
|
387
|
-
|
388
|
+
لأ� 147
|
389
|
+
�أ� 147
|
388
390
|
تم 147
|
389
|
-
_ي 147
|
390
391
|
�ا_ 146
|
392
|
+
ان_ 146
|
393
|
+
�ن_ 146
|
391
394
|
ما_ 146
|
392
|
-
_
|
393
|
-
_ج 146
|
395
|
+
_ك� 145
|
394
396
|
�ا� 144
|
395
|
-
�ب 144
|
396
|
-
لب 144
|
397
397
|
عا� 144
|
398
|
+
لب 144
|
399
|
+
�ب 144
|
398
400
|
اس 143
|
399
|
-
سي 143
|
400
|
-
�س 143
|