language_detector 0.1.0

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.
Files changed (172) hide show
  1. data/README.rdoc +24 -0
  2. data/Rakefile +18 -0
  3. data/VERSION +1 -0
  4. data/lib/language_detector.rb +232 -0
  5. data/lib/model-fm.yml +52504 -0
  6. data/lib/model-tc.yml +53985 -0
  7. data/lib/textcat_ngrams/afrikaans.lm +400 -0
  8. data/lib/textcat_ngrams/albanian.lm +400 -0
  9. data/lib/textcat_ngrams/amharic-utf.lm +400 -0
  10. data/lib/textcat_ngrams/arabic-iso8859_6.lm +400 -0
  11. data/lib/textcat_ngrams/arabic-windows1256.lm +400 -0
  12. data/lib/textcat_ngrams/armenian.lm +400 -0
  13. data/lib/textcat_ngrams/basque.lm +400 -0
  14. data/lib/textcat_ngrams/belarus-windows1251.lm +400 -0
  15. data/lib/textcat_ngrams/bosnian.lm +400 -0
  16. data/lib/textcat_ngrams/breton.lm +400 -0
  17. data/lib/textcat_ngrams/bulgarian-iso8859_5.lm +400 -0
  18. data/lib/textcat_ngrams/catalan.lm +400 -0
  19. data/lib/textcat_ngrams/chinese-big5.lm +400 -0
  20. data/lib/textcat_ngrams/chinese-gb2312.lm +400 -0
  21. data/lib/textcat_ngrams/croatian-ascii.lm +400 -0
  22. data/lib/textcat_ngrams/czech-iso8859_2.lm +400 -0
  23. data/lib/textcat_ngrams/danish.lm +400 -0
  24. data/lib/textcat_ngrams/dutch.lm +400 -0
  25. data/lib/textcat_ngrams/english.lm +400 -0
  26. data/lib/textcat_ngrams/esperanto.lm +400 -0
  27. data/lib/textcat_ngrams/estonian.lm +400 -0
  28. data/lib/textcat_ngrams/finnish.lm +400 -0
  29. data/lib/textcat_ngrams/french.lm +400 -0
  30. data/lib/textcat_ngrams/frisian.lm +400 -0
  31. data/lib/textcat_ngrams/georgian.lm +400 -0
  32. data/lib/textcat_ngrams/german.lm +400 -0
  33. data/lib/textcat_ngrams/greek-iso8859-7.lm +400 -0
  34. data/lib/textcat_ngrams/hebrew-iso8859_8.lm +400 -0
  35. data/lib/textcat_ngrams/hindi.lm +400 -0
  36. data/lib/textcat_ngrams/hungarian.lm +400 -0
  37. data/lib/textcat_ngrams/icelandic.lm +400 -0
  38. data/lib/textcat_ngrams/indonesian.lm +400 -0
  39. data/lib/textcat_ngrams/irish.lm +400 -0
  40. data/lib/textcat_ngrams/italian.lm +400 -0
  41. data/lib/textcat_ngrams/japanese-euc_jp.lm +400 -0
  42. data/lib/textcat_ngrams/japanese-shift_jis.lm +400 -0
  43. data/lib/textcat_ngrams/korean.lm +400 -0
  44. data/lib/textcat_ngrams/latin.lm +400 -0
  45. data/lib/textcat_ngrams/latvian.lm +400 -0
  46. data/lib/textcat_ngrams/lithuanian.lm +400 -0
  47. data/lib/textcat_ngrams/malay.lm +400 -0
  48. data/lib/textcat_ngrams/manx.lm +400 -0
  49. data/lib/textcat_ngrams/marathi.lm +400 -0
  50. data/lib/textcat_ngrams/mingo.lm +400 -0
  51. data/lib/textcat_ngrams/nepali.lm +400 -0
  52. data/lib/textcat_ngrams/norwegian.lm +400 -0
  53. data/lib/textcat_ngrams/persian.lm +400 -0
  54. data/lib/textcat_ngrams/polish.lm +400 -0
  55. data/lib/textcat_ngrams/portuguese.lm +400 -0
  56. data/lib/textcat_ngrams/quechua.lm +400 -0
  57. data/lib/textcat_ngrams/romanian.lm +400 -0
  58. data/lib/textcat_ngrams/rumantsch.lm +400 -0
  59. data/lib/textcat_ngrams/russian-iso8859_5.lm +400 -0
  60. data/lib/textcat_ngrams/russian-koi8_r.lm +400 -0
  61. data/lib/textcat_ngrams/russian-windows1251.lm +400 -0
  62. data/lib/textcat_ngrams/sanskrit.lm +400 -0
  63. data/lib/textcat_ngrams/scots.lm +400 -0
  64. data/lib/textcat_ngrams/scots_gaelic.lm +400 -0
  65. data/lib/textcat_ngrams/serbian-ascii.lm +400 -0
  66. data/lib/textcat_ngrams/slovak-ascii.lm +400 -0
  67. data/lib/textcat_ngrams/slovak-windows1250.lm +400 -0
  68. data/lib/textcat_ngrams/slovenian-ascii.lm +400 -0
  69. data/lib/textcat_ngrams/slovenian-iso8859_2.lm +400 -0
  70. data/lib/textcat_ngrams/spanish.lm +400 -0
  71. data/lib/textcat_ngrams/swahili.lm +400 -0
  72. data/lib/textcat_ngrams/swedish.lm +400 -0
  73. data/lib/textcat_ngrams/tagalog.lm +400 -0
  74. data/lib/textcat_ngrams/tamil.lm +400 -0
  75. data/lib/textcat_ngrams/thai.lm +400 -0
  76. data/lib/textcat_ngrams/turkish.lm +400 -0
  77. data/lib/textcat_ngrams/ukrainian-koi8_u.lm +400 -0
  78. data/lib/textcat_ngrams/vietnamese.lm +400 -0
  79. data/lib/textcat_ngrams/welsh.lm +400 -0
  80. data/lib/textcat_ngrams/yiddish-utf.lm +400 -0
  81. data/lib/training_data/ar-utf8.txt +54 -0
  82. data/lib/training_data/bg-utf8.txt +26 -0
  83. data/lib/training_data/cs-utf8.txt +48 -0
  84. data/lib/training_data/da-utf8.txt +159 -0
  85. data/lib/training_data/de-utf8.txt +569 -0
  86. data/lib/training_data/el-utf8.txt +48 -0
  87. data/lib/training_data/en-utf8.txt +81 -0
  88. data/lib/training_data/es-utf8.txt +185 -0
  89. data/lib/training_data/et-utf8.txt +50 -0
  90. data/lib/training_data/fa-utf8.txt +42 -0
  91. data/lib/training_data/fi-utf8.txt +83 -0
  92. data/lib/training_data/fr-utf8.txt +191 -0
  93. data/lib/training_data/fy-utf8.txt +22 -0
  94. data/lib/training_data/ga-utf8.txt +109 -0
  95. data/lib/training_data/he-utf8.txt +116 -0
  96. data/lib/training_data/hi-utf8.txt +49 -0
  97. data/lib/training_data/hr-utf8.txt +80 -0
  98. data/lib/training_data/hu-utf8.txt +87 -0
  99. data/lib/training_data/io-utf8.txt +41 -0
  100. data/lib/training_data/is-utf8.txt +94 -0
  101. data/lib/training_data/it-utf8.txt +228 -0
  102. data/lib/training_data/ja-utf8.txt +200 -0
  103. data/lib/training_data/ko-utf8.txt +147 -0
  104. data/lib/training_data/nl-utf8.txt +215 -0
  105. data/lib/training_data/no-utf8.txt +281 -0
  106. data/lib/training_data/pl-utf8.txt +120 -0
  107. data/lib/training_data/pt-utf8.txt +214 -0
  108. data/lib/training_data/ro-utf8.txt +66 -0
  109. data/lib/training_data/ru-utf8.txt +310 -0
  110. data/lib/training_data/sl-utf8.txt +263 -0
  111. data/lib/training_data/sv-utf8.txt +174 -0
  112. data/lib/training_data/th-utf8.txt +49 -0
  113. data/lib/training_data/tk-utf8.txt +101 -0
  114. data/lib/training_data/todo/af.txt +114 -0
  115. data/lib/training_data/todo/amharic-utf.txt +95 -0
  116. data/lib/training_data/todo/arabic-windows1256.txt +157 -0
  117. data/lib/training_data/todo/armenian.txt +86 -0
  118. data/lib/training_data/todo/basque.txt +136 -0
  119. data/lib/training_data/todo/belarus-windows1251.txt +97 -0
  120. data/lib/training_data/todo/bosnian.txt +97 -0
  121. data/lib/training_data/todo/breton.txt +159 -0
  122. data/lib/training_data/todo/bulgarian-iso8859_5.txt +115 -0
  123. data/lib/training_data/todo/catalan.txt +93 -0
  124. data/lib/training_data/todo/croatian-ascii.txt +104 -0
  125. data/lib/training_data/todo/esperanto.txt +95 -0
  126. data/lib/training_data/todo/estonian.txt +218 -0
  127. data/lib/training_data/todo/frisian.txt +99 -0
  128. data/lib/training_data/todo/georgian.txt +86 -0
  129. data/lib/training_data/todo/greek-iso8859-7.txt +139 -0
  130. data/lib/training_data/todo/hawaian.txt +108 -0
  131. data/lib/training_data/todo/hebrew-iso8859_8.txt +79 -0
  132. data/lib/training_data/todo/hindi.txt +77 -0
  133. data/lib/training_data/todo/hungarian.txt +102 -0
  134. data/lib/training_data/todo/icelandic.txt +131 -0
  135. data/lib/training_data/todo/indonesian.txt +93 -0
  136. data/lib/training_data/todo/irish.txt +209 -0
  137. data/lib/training_data/todo/latin.txt +120 -0
  138. data/lib/training_data/todo/latvian.txt +126 -0
  139. data/lib/training_data/todo/lithuanian.txt +99 -0
  140. data/lib/training_data/todo/malay.txt +108 -0
  141. data/lib/training_data/todo/manx.txt +78 -0
  142. data/lib/training_data/todo/marathi.txt +100 -0
  143. data/lib/training_data/todo/mf.txt +100 -0
  144. data/lib/training_data/todo/middle_frisian.txt +102 -0
  145. data/lib/training_data/todo/mingo.txt +146 -0
  146. data/lib/training_data/todo/nepali.txt +131 -0
  147. data/lib/training_data/todo/persian.txt +73 -0
  148. data/lib/training_data/todo/quechua.txt +108 -0
  149. data/lib/training_data/todo/romanian.txt +103 -0
  150. data/lib/training_data/todo/rumantsch.txt +110 -0
  151. data/lib/training_data/todo/sanskrit.txt +135 -0
  152. data/lib/training_data/todo/scots.txt +490 -0
  153. data/lib/training_data/todo/scots_gaelic.txt +93 -0
  154. data/lib/training_data/todo/serbian-ascii.txt +121 -0
  155. data/lib/training_data/todo/slovak-ascii.txt +102 -0
  156. data/lib/training_data/todo/slovak-windows1250.txt +115 -0
  157. data/lib/training_data/todo/slovenian-ascii.txt +100 -0
  158. data/lib/training_data/todo/slovenian-iso8859_2.txt +96 -0
  159. data/lib/training_data/todo/sq.txt +110 -0
  160. data/lib/training_data/todo/swahili.txt +120 -0
  161. data/lib/training_data/todo/tagalog.txt +135 -0
  162. data/lib/training_data/todo/tamil.txt +123 -0
  163. data/lib/training_data/todo/turkish.txt +117 -0
  164. data/lib/training_data/todo/ukrainian-koi8_r.txt +214 -0
  165. data/lib/training_data/todo/vietnamese.txt +92 -0
  166. data/lib/training_data/todo/welsh.txt +148 -0
  167. data/lib/training_data/todo/yiddish-utf.txt +83 -0
  168. data/lib/training_data/uk-utf8.txt +75 -0
  169. data/lib/training_data/vi-utf8.txt +47 -0
  170. data/lib/training_data/zh-utf8.txt +228 -0
  171. data/test/language_detector_test.rb +78 -0
  172. metadata +232 -0
@@ -0,0 +1,400 @@
1
+ _ 11636
2
+ � 2659
3
+ � 1629
4
+ � 1578
5
+ � 1458
6
+ � 1397
7
+ � 1299
8
+ � 1118
9
+ � 1005
10
+ � 928
11
+ � 849
12
+ � 840
13
+ _� 809
14
+ � 808
15
+ � 780
16
+ � 773
17
+ � 764
18
+ � 674
19
+ � 640
20
+ � 591
21
+ � 580
22
+ �� 538
23
+ � 526
24
+ � 519
25
+ � 518
26
+ _� 518
27
+ � 506
28
+ � 483
29
+ � 464
30
+ � 463
31
+ � 454
32
+ �� 451
33
+ � 404
34
+ � 395
35
+ � 384
36
+ _� 382
37
+ � 377
38
+ . 374
39
+ � 373
40
+ � 358
41
+ ._ 347
42
+ _� 344
43
+ �� 338
44
+ �_ 333
45
+ �_ 329
46
+ �� 327
47
+ _� 319
48
+ ��_ 317
49
+ ��. 313
50
+ �. 313
51
+ � 308
52
+ � 308
53
+ ��._ 301
54
+ �._ 301
55
+ �_ 299
56
+ _� 291
57
+ � 288
58
+ � 282
59
+ �� 279
60
+ � 278
61
+ � 274
62
+ ��_ 271
63
+ �_ 269
64
+ , 266
65
+ � 266
66
+ �� 261
67
+ �� 258
68
+ ,_ 258
69
+ �� 250
70
+ � 248
71
+ _� 246
72
+ � 245
73
+ �� 244
74
+ �_ 243
75
+ _� 243
76
+ _� 242
77
+ � 238
78
+ � 235
79
+ �� 234
80
+ ��_ 234
81
+ �� 234
82
+ _� 233
83
+ �� 228
84
+ �� 227
85
+ �� 222
86
+ �� 222
87
+ _� 215
88
+ �� 212
89
+ _� 210
90
+ �_ 208
91
+ _� 206
92
+ �_ 206
93
+ �_ 205
94
+ _� 205
95
+ �_ 204
96
+ � 198
97
+ �� 198
98
+ ��_ 194
99
+ ��_ 193
100
+ � 193
101
+ ��_ 193
102
+ ��_ 192
103
+ �� 192
104
+ _�� 190
105
+ �_ 189
106
+ ��_ 189
107
+ _� 189
108
+ �� 188
109
+ �� 188
110
+ ��_ 188
111
+ _� 186
112
+ � 177
113
+ � 175
114
+ � 171
115
+ �� 161
116
+ � 154
117
+ _�� 153
118
+ � 152
119
+ �� 151
120
+ �� 150
121
+ �� 147
122
+ � 147
123
+ �� 145
124
+ �� 143
125
+ � 142
126
+ �� 142
127
+ _� 141
128
+ �� 140
129
+ � 139
130
+ � 138
131
+ � 138
132
+ � 137
133
+ �� 136
134
+ � 134
135
+ �� 134
136
+ _�� 133
137
+ � 132
138
+ �_ 127
139
+ �� 125
140
+ ��_ 123
141
+ �� 122
142
+ ��_ 121
143
+ �� 121
144
+ �� 118
145
+ � 117
146
+ � 116
147
+ �_ 115
148
+ �� 115
149
+ �_ 115
150
+ � 114
151
+ ִ 113
152
+ �� 112
153
+ �� 111
154
+ � 109
155
+ �� 109
156
+ � 108
157
+ � 108
158
+ _� 108
159
+ �� 107
160
+ ��_ 107
161
+ � 107
162
+ � 106
163
+ �ִ 105
164
+ ȸ 103
165
+ �� 101
166
+ �_ 101
167
+ � 100
168
+ _�ִ 100
169
+ õ 100
170
+ ��� 100
171
+ " 98
172
+ ���� 97
173
+ �� 97
174
+ ��� 97
175
+ �� 95
176
+ _�� 94
177
+ �� 94
178
+ �� 94
179
+ _�� 94
180
+ � 94
181
+ �� 94
182
+ �� 92
183
+ �� 92
184
+ _� 91
185
+ � 91
186
+ ϰ 90
187
+ �� 90
188
+ ���_ 90
189
+ � 89
190
+ � 89
191
+ �_ 89
192
+ �_ 89
193
+ ����_ 89
194
+ �� 89
195
+ � 88
196
+ ��� 88
197
+ ��� 88
198
+ ���� 88
199
+ � 87
200
+ ��_ 87
201
+ �� 85
202
+ _� 85
203
+ �_ 84
204
+ �� 84
205
+ ��� 84
206
+ �� 84
207
+ �� 83
208
+ �� 83
209
+ _�� 82
210
+ �ϰ 82
211
+ �� 81
212
+ �� 80
213
+ ����_ 79
214
+ ���_ 79
215
+ ��_ 78
216
+ � 78
217
+ �� 78
218
+ �_ 78
219
+ �� 78
220
+ ' 77
221
+ �� 77
222
+ � 77
223
+ � 77
224
+ �� 77
225
+ �_ 76
226
+ ��_ 76
227
+ � 76
228
+ �_ 75
229
+ ( 74
230
+ ) 74
231
+ �� 74
232
+ �� 74
233
+ �� 73
234
+ _�� 72
235
+ _�� 72
236
+ _�� 72
237
+ - 72
238
+ �� 72
239
+ ִ� 72
240
+ �� 71
241
+ �ִ� 71
242
+ �� 70
243
+ �� 70
244
+ �� 70
245
+ �� 69
246
+ �� 69
247
+ ��_ 69
248
+ _�ִ� 69
249
+ _�� 69
250
+ �_ 69
251
+ ߴ 69
252
+ �� 68
253
+ �� 68
254
+ _� 68
255
+ _�� 68
256
+ �_ 67
257
+ ü 67
258
+ �� 66
259
+ _��_ 66
260
+ �ߴ 66
261
+ �� 65
262
+ � 65
263
+ _� 65
264
+ _�� 65
265
+ �ߴ� 64
266
+ ߴ� 64
267
+ _�� 63
268
+ �� 62
269
+ � 62
270
+ ϴ 62
271
+ �� 62
272
+ ��_ 62
273
+ �� 61
274
+ �� 61
275
+ ϰ� 61
276
+ ̴ 60
277
+ �� 60
278
+ �ϰ� 60
279
+ � 59
280
+ _��_ 59
281
+ _�� 59
282
+ �� 59
283
+ �� 58
284
+ �_ 58
285
+ _�� 58
286
+ �_ 58
287
+ �� 57
288
+ ߴ�. 57
289
+ � 57
290
+ � 57
291
+ �ߴ�. 57
292
+ �� 57
293
+ �� 57
294
+ ִ�. 56
295
+ �_ 56
296
+ �ִ�. 56
297
+ �� 56
298
+ ߴ�._ 56
299
+ �� 56
300
+ �� 55
301
+ �� 55
302
+ �� 55
303
+ Ʈ 55
304
+ �� 55
305
+ �̴ 55
306
+ ִ�._ 54
307
+ _�� 54
308
+ ��_ 53
309
+ �� 53
310
+ � 53
311
+ �� 53
312
+ _�� 53
313
+ �� 53
314
+ �� 53
315
+ ��_ 53
316
+ �� 53
317
+ �� 52
318
+ _�� 52
319
+ �_ 52
320
+ �� 52
321
+ _�� 51
322
+ ��� 51
323
+ �� 51
324
+ �� 51
325
+ ȭ 51
326
+ � 50
327
+ _�� 50
328
+ ��� 50
329
+ ġ 50
330
+ ϰ�_ 49
331
+ �ϰ�_ 49
332
+ _�� 49
333
+ � 49
334
+ � 49
335
+ _" 48
336
+ �� 48
337
+ �� 48
338
+ �̴� 48
339
+ �� 48
340
+ _��� 48
341
+ ̴� 48
342
+ �� 47
343
+ ̴�. 47
344
+ _�� 47
345
+ �̴�. 47
346
+ ��_ 47
347
+ _�� 47
348
+ �� 47
349
+ �� 47
350
+ �_ 46
351
+ �� 46
352
+ �_ 46
353
+ �_ 46
354
+ � 46
355
+ �ϴ 46
356
+ _�� 45
357
+ _�� 45
358
+ _�� 45
359
+ �� 45
360
+ �� 45
361
+ �� 45
362
+ ̴�._ 45
363
+ �� 44
364
+ �� 44
365
+ �� 44
366
+ ��_ 43
367
+ (_ 43
368
+ �� 43
369
+ �� 43
370
+ �_ 43
371
+ �� 42
372
+ �� 42
373
+ �_ 42
374
+ ��_ 42
375
+ _��_ 42
376
+ ��_ 42
377
+ �� 42
378
+ �� 41
379
+ �� 41
380
+ ��� 41
381
+ �� 41
382
+ �� 40
383
+ �õ 40
384
+ �� 40
385
+ � 40
386
+ �� 40
387
+ _�� 40
388
+ �� 40
389
+ �� 40
390
+ _�� 40
391
+ ��_ 39
392
+ _�� 39
393
+ �� 39
394
+ �� 39
395
+ �_ 39
396
+ _�� 39
397
+ �� 38
398
+ ��� 38
399
+ �� 38
400
+ �_ 38
@@ -0,0 +1,400 @@
1
+ _ 20136
2
+ e 6892
3
+ i 5604
4
+ a 5443
5
+ u 4581
6
+ t 4552
7
+ s 4354
8
+ r 3923
9
+ n 3375
10
+ m 3063
11
+ o 2921
12
+ c 2224
13
+ l 1805
14
+ e_ 1625
15
+ s_ 1503
16
+ p 1424
17
+ d 1397
18
+ , 1285
19
+ ,_ 1276
20
+ er 1077
21
+ qu 1028
22
+ q 1028
23
+ a_ 1019
24
+ t_ 1018
25
+ is 942
26
+ _a 921
27
+ re 902
28
+ m_ 891
29
+ v 858
30
+ b 821
31
+ um 808
32
+ _s 773
33
+ us 772
34
+ en 766
35
+ nt 733
36
+ in 729
37
+ ue 727
38
+ te 720
39
+ g 718
40
+ _i 710
41
+ _p 679
42
+ it 676
43
+ _c 669
44
+ et 653
45
+ que 652
46
+ _e 643
47
+ at 643
48
+ ue_ 616
49
+ ra 614
50
+ que_ 611
51
+ f 601
52
+ or 598
53
+ ri 576
54
+ ti 572
55
+ ta 559
56
+ tu 552
57
+ an 551
58
+ ae 527
59
+ _m 513
60
+ am 501
61
+ _t 493
62
+ us_ 488
63
+ is_ 487
64
+ es 479
65
+ em 479
66
+ _f 451
67
+ um_ 443
68
+ _v 442
69
+ ia 442
70
+ li 438
71
+ _d 436
72
+ . 432
73
+ i_ 430
74
+ et_ 429
75
+ ni 412
76
+ ne 409
77
+ h 406
78
+ de 404
79
+ ur 396
80
+ ._ 392
81
+ ar 388
82
+ os 388
83
+ mi 382
84
+ pe 382
85
+ la 376
86
+ st 371
87
+ s, 368
88
+ di 367
89
+ _et 366
90
+ s,_ 365
91
+ _in 363
92
+ on 360
93
+ o_ 359
94
+ _n 351
95
+ _et_ 351
96
+ as 346
97
+ im 336
98
+ na 327
99
+ se 320
100
+ ma 315
101
+ cu 307
102
+ vi 306
103
+ si 303
104
+ ro 303
105
+ r_ 302
106
+ su 299
107
+ un 295
108
+ _l 291
109
+ to 291
110
+ ec 290
111
+ ci 288
112
+ co 287
113
+ _r 287
114
+ ere 286
115
+ ce 284
116
+ tr 280
117
+ re_ 278
118
+ ent 275
119
+ x 275
120
+ ct 274
121
+ ve 271
122
+ ru 259
123
+ ul 256
124
+ me 255
125
+ ui 255
126
+ c_ 252
127
+ _o 250
128
+ ic 249
129
+ ns 247
130
+ _qu 242
131
+ _q 242
132
+ no 241
133
+ ant 235
134
+ am_ 235
135
+ _co 233
136
+ sa 231
137
+ ca 230
138
+ t, 226
139
+ mu 225
140
+ t,_ 225
141
+ _re 223
142
+ el 222
143
+ ib 222
144
+ id 218
145
+ om 212
146
+ _te 211
147
+ al 209
148
+ le 209
149
+ it_ 208
150
+ mo 208
151
+ ol 206
152
+ _u 203
153
+ ; 199
154
+ _h 199
155
+ ac 198
156
+ ;_ 198
157
+ bu 197
158
+ nu 196
159
+ ua 195
160
+ n_ 195
161
+ ll 194
162
+ tis 191
163
+ A 189
164
+ rt 188
165
+ ge 188
166
+ nd 187
167
+ au 187
168
+ lu 186
169
+ iu 185
170
+ squ 185
171
+ per 185
172
+ sq 185
173
+ ter 185
174
+ pa 183
175
+ _A 183
176
+ em_ 183
177
+ ia_ 180
178
+ ed 179
179
+ _pe 178
180
+ m, 176
181
+ sque 175
182
+ _su 175
183
+ ae_ 175
184
+ m,_ 175
185
+ pr 175
186
+ bi 175
187
+ bus 174
188
+ _vi 174
189
+ os_ 173
190
+ ta_ 172
191
+ mqu 171
192
+ mq 171
193
+ ss 170
194
+ sque_ 169
195
+ ibu 167
196
+ ad 166
197
+ ibus 165
198
+ I 164
199
+ nte 163
200
+ ra_ 163
201
+ mque 162
202
+ _de 162
203
+ po 161
204
+ _se 160
205
+ ere_ 160
206
+ nc 160
207
+ qua 159
208
+ T 159
209
+ lo 157
210
+ oc 156
211
+ mque_ 156
212
+ _T 155
213
+ _pa 155
214
+ _pr 155
215
+ tem 154
216
+ bus_ 152
217
+ nti 149
218
+ rum 149
219
+ er_ 149
220
+ ab 148
221
+ ir 148
222
+ da 147
223
+ _ve 146
224
+ ibus_ 146
225
+ ex 146
226
+ ut 145
227
+ pi 145
228
+ tur 145
229
+ _ca 143
230
+ _me 142
231
+ es_ 142
232
+ gi 142
233
+ te_ 141
234
+ _I 141
235
+ vo 141
236
+ do 141
237
+ _si 140
238
+ tus 139
239
+ il 137
240
+ _ar 136
241
+ du 133
242
+ nt_ 133
243
+ uc 133
244
+ fa 132
245
+ as_ 132
246
+ rr 131
247
+ ba 130
248
+ _ad 128
249
+ ne_ 127
250
+ _ma 127
251
+ ens 127
252
+ gn 126
253
+ s. 126
254
+ y 126
255
+ min 125
256
+ ris 124
257
+ in_ 123
258
+ tum 123
259
+ P 123
260
+ _g 123
261
+ mp 123
262
+ e, 122
263
+ io 122
264
+ _P 122
265
+ ea 122
266
+ hi 122
267
+ e,_ 121
268
+ era 120
269
+ sc 120
270
+ _la 120
271
+ qui 120
272
+ unt 120
273
+ fe 119
274
+ _in_ 118
275
+ _no 118
276
+ ore 118
277
+ iam 118
278
+ va 117
279
+ tis_ 117
280
+ s._ 117
281
+ at_ 117
282
+ eri 116
283
+ d_ 116
284
+ con 115
285
+ fu 115
286
+ pu 114
287
+ cum 114
288
+ ub 114
289
+ ng 114
290
+ ine 113
291
+ _au 113
292
+ : 113
293
+ _di 112
294
+ ag 111
295
+ _con 111
296
+ ect 111
297
+ i, 111
298
+ equ 111
299
+ i,_ 111
300
+ be 111
301
+ eq 111
302
+ _po 110
303
+ so 110
304
+ :_ 110
305
+ nis 109
306
+ ha 109
307
+ uo 109
308
+ _fa 108
309
+ na_ 107
310
+ ip 107
311
+ is, 107
312
+ _cu 106
313
+ cr 106
314
+ ate 105
315
+ is,_ 105
316
+ ig 105
317
+ tor 105
318
+ rat 104
319
+ _qua 103
320
+ eg 103
321
+ a, 103
322
+ a,_ 102
323
+ tra 102
324
+ _mo 101
325
+ sp 101
326
+ mis 100
327
+ itu 100
328
+ D 99
329
+ ali 99
330
+ eb 99
331
+ eni 99
332
+ _sa 98
333
+ ie 98
334
+ imu 98
335
+ _ex 97
336
+ _D 96
337
+ res 95
338
+ est 94
339
+ tri 94
340
+ ene 94
341
+ _mi 94
342
+ str 94
343
+ enti 93
344
+ t. 92
345
+ av 92
346
+ _per 91
347
+ ur_ 91
348
+ ora 91
349
+ lt 91
350
+ umqu 90
351
+ _vo 90
352
+ umq 90
353
+ up 89
354
+ t._ 88
355
+ quo 88
356
+ _ne 88
357
+ gen 88
358
+ rum_ 87
359
+ tqu 87
360
+ tq 87
361
+ _fu 86
362
+ ep 86
363
+ ma_ 86
364
+ umque 86
365
+ it,_ 85
366
+ ine_ 85
367
+ it, 85
368
+ men 85
369
+ mus 84
370
+ ort 83
371
+ ven 83
372
+ ina 83
373
+ us,_ 83
374
+ us, 83
375
+ tque 82
376
+ _ge 82
377
+ per_ 82
378
+ mor 82
379
+ inc 82
380
+ are 81
381
+ tus_ 81
382
+ _an 81
383
+ rim 81
384
+ tque_ 81
385
+ ot 81
386
+ ani 80
387
+ H 80
388
+ _tu 80
389
+ ho 80
390
+ tem_ 80
391
+ u_ 80
392
+ ser 79
393
+ um,_ 79
394
+ um, 79
395
+ S 79
396
+ ten 79
397
+ ver 79
398
+ sti 79
399
+ ntu 78
400
+ fer 78