language_detector 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- data/README.rdoc +24 -0
- data/Rakefile +18 -0
- data/VERSION +1 -0
- data/lib/language_detector.rb +232 -0
- data/lib/model-fm.yml +52504 -0
- data/lib/model-tc.yml +53985 -0
- data/lib/textcat_ngrams/afrikaans.lm +400 -0
- data/lib/textcat_ngrams/albanian.lm +400 -0
- data/lib/textcat_ngrams/amharic-utf.lm +400 -0
- data/lib/textcat_ngrams/arabic-iso8859_6.lm +400 -0
- data/lib/textcat_ngrams/arabic-windows1256.lm +400 -0
- data/lib/textcat_ngrams/armenian.lm +400 -0
- data/lib/textcat_ngrams/basque.lm +400 -0
- data/lib/textcat_ngrams/belarus-windows1251.lm +400 -0
- data/lib/textcat_ngrams/bosnian.lm +400 -0
- data/lib/textcat_ngrams/breton.lm +400 -0
- data/lib/textcat_ngrams/bulgarian-iso8859_5.lm +400 -0
- data/lib/textcat_ngrams/catalan.lm +400 -0
- data/lib/textcat_ngrams/chinese-big5.lm +400 -0
- data/lib/textcat_ngrams/chinese-gb2312.lm +400 -0
- data/lib/textcat_ngrams/croatian-ascii.lm +400 -0
- data/lib/textcat_ngrams/czech-iso8859_2.lm +400 -0
- data/lib/textcat_ngrams/danish.lm +400 -0
- data/lib/textcat_ngrams/dutch.lm +400 -0
- data/lib/textcat_ngrams/english.lm +400 -0
- data/lib/textcat_ngrams/esperanto.lm +400 -0
- data/lib/textcat_ngrams/estonian.lm +400 -0
- data/lib/textcat_ngrams/finnish.lm +400 -0
- data/lib/textcat_ngrams/french.lm +400 -0
- data/lib/textcat_ngrams/frisian.lm +400 -0
- data/lib/textcat_ngrams/georgian.lm +400 -0
- data/lib/textcat_ngrams/german.lm +400 -0
- data/lib/textcat_ngrams/greek-iso8859-7.lm +400 -0
- data/lib/textcat_ngrams/hebrew-iso8859_8.lm +400 -0
- data/lib/textcat_ngrams/hindi.lm +400 -0
- data/lib/textcat_ngrams/hungarian.lm +400 -0
- data/lib/textcat_ngrams/icelandic.lm +400 -0
- data/lib/textcat_ngrams/indonesian.lm +400 -0
- data/lib/textcat_ngrams/irish.lm +400 -0
- data/lib/textcat_ngrams/italian.lm +400 -0
- data/lib/textcat_ngrams/japanese-euc_jp.lm +400 -0
- data/lib/textcat_ngrams/japanese-shift_jis.lm +400 -0
- data/lib/textcat_ngrams/korean.lm +400 -0
- data/lib/textcat_ngrams/latin.lm +400 -0
- data/lib/textcat_ngrams/latvian.lm +400 -0
- data/lib/textcat_ngrams/lithuanian.lm +400 -0
- data/lib/textcat_ngrams/malay.lm +400 -0
- data/lib/textcat_ngrams/manx.lm +400 -0
- data/lib/textcat_ngrams/marathi.lm +400 -0
- data/lib/textcat_ngrams/mingo.lm +400 -0
- data/lib/textcat_ngrams/nepali.lm +400 -0
- data/lib/textcat_ngrams/norwegian.lm +400 -0
- data/lib/textcat_ngrams/persian.lm +400 -0
- data/lib/textcat_ngrams/polish.lm +400 -0
- data/lib/textcat_ngrams/portuguese.lm +400 -0
- data/lib/textcat_ngrams/quechua.lm +400 -0
- data/lib/textcat_ngrams/romanian.lm +400 -0
- data/lib/textcat_ngrams/rumantsch.lm +400 -0
- data/lib/textcat_ngrams/russian-iso8859_5.lm +400 -0
- data/lib/textcat_ngrams/russian-koi8_r.lm +400 -0
- data/lib/textcat_ngrams/russian-windows1251.lm +400 -0
- data/lib/textcat_ngrams/sanskrit.lm +400 -0
- data/lib/textcat_ngrams/scots.lm +400 -0
- data/lib/textcat_ngrams/scots_gaelic.lm +400 -0
- data/lib/textcat_ngrams/serbian-ascii.lm +400 -0
- data/lib/textcat_ngrams/slovak-ascii.lm +400 -0
- data/lib/textcat_ngrams/slovak-windows1250.lm +400 -0
- data/lib/textcat_ngrams/slovenian-ascii.lm +400 -0
- data/lib/textcat_ngrams/slovenian-iso8859_2.lm +400 -0
- data/lib/textcat_ngrams/spanish.lm +400 -0
- data/lib/textcat_ngrams/swahili.lm +400 -0
- data/lib/textcat_ngrams/swedish.lm +400 -0
- data/lib/textcat_ngrams/tagalog.lm +400 -0
- data/lib/textcat_ngrams/tamil.lm +400 -0
- data/lib/textcat_ngrams/thai.lm +400 -0
- data/lib/textcat_ngrams/turkish.lm +400 -0
- data/lib/textcat_ngrams/ukrainian-koi8_u.lm +400 -0
- data/lib/textcat_ngrams/vietnamese.lm +400 -0
- data/lib/textcat_ngrams/welsh.lm +400 -0
- data/lib/textcat_ngrams/yiddish-utf.lm +400 -0
- data/lib/training_data/ar-utf8.txt +54 -0
- data/lib/training_data/bg-utf8.txt +26 -0
- data/lib/training_data/cs-utf8.txt +48 -0
- data/lib/training_data/da-utf8.txt +159 -0
- data/lib/training_data/de-utf8.txt +569 -0
- data/lib/training_data/el-utf8.txt +48 -0
- data/lib/training_data/en-utf8.txt +81 -0
- data/lib/training_data/es-utf8.txt +185 -0
- data/lib/training_data/et-utf8.txt +50 -0
- data/lib/training_data/fa-utf8.txt +42 -0
- data/lib/training_data/fi-utf8.txt +83 -0
- data/lib/training_data/fr-utf8.txt +191 -0
- data/lib/training_data/fy-utf8.txt +22 -0
- data/lib/training_data/ga-utf8.txt +109 -0
- data/lib/training_data/he-utf8.txt +116 -0
- data/lib/training_data/hi-utf8.txt +49 -0
- data/lib/training_data/hr-utf8.txt +80 -0
- data/lib/training_data/hu-utf8.txt +87 -0
- data/lib/training_data/io-utf8.txt +41 -0
- data/lib/training_data/is-utf8.txt +94 -0
- data/lib/training_data/it-utf8.txt +228 -0
- data/lib/training_data/ja-utf8.txt +200 -0
- data/lib/training_data/ko-utf8.txt +147 -0
- data/lib/training_data/nl-utf8.txt +215 -0
- data/lib/training_data/no-utf8.txt +281 -0
- data/lib/training_data/pl-utf8.txt +120 -0
- data/lib/training_data/pt-utf8.txt +214 -0
- data/lib/training_data/ro-utf8.txt +66 -0
- data/lib/training_data/ru-utf8.txt +310 -0
- data/lib/training_data/sl-utf8.txt +263 -0
- data/lib/training_data/sv-utf8.txt +174 -0
- data/lib/training_data/th-utf8.txt +49 -0
- data/lib/training_data/tk-utf8.txt +101 -0
- data/lib/training_data/todo/af.txt +114 -0
- data/lib/training_data/todo/amharic-utf.txt +95 -0
- data/lib/training_data/todo/arabic-windows1256.txt +157 -0
- data/lib/training_data/todo/armenian.txt +86 -0
- data/lib/training_data/todo/basque.txt +136 -0
- data/lib/training_data/todo/belarus-windows1251.txt +97 -0
- data/lib/training_data/todo/bosnian.txt +97 -0
- data/lib/training_data/todo/breton.txt +159 -0
- data/lib/training_data/todo/bulgarian-iso8859_5.txt +115 -0
- data/lib/training_data/todo/catalan.txt +93 -0
- data/lib/training_data/todo/croatian-ascii.txt +104 -0
- data/lib/training_data/todo/esperanto.txt +95 -0
- data/lib/training_data/todo/estonian.txt +218 -0
- data/lib/training_data/todo/frisian.txt +99 -0
- data/lib/training_data/todo/georgian.txt +86 -0
- data/lib/training_data/todo/greek-iso8859-7.txt +139 -0
- data/lib/training_data/todo/hawaian.txt +108 -0
- data/lib/training_data/todo/hebrew-iso8859_8.txt +79 -0
- data/lib/training_data/todo/hindi.txt +77 -0
- data/lib/training_data/todo/hungarian.txt +102 -0
- data/lib/training_data/todo/icelandic.txt +131 -0
- data/lib/training_data/todo/indonesian.txt +93 -0
- data/lib/training_data/todo/irish.txt +209 -0
- data/lib/training_data/todo/latin.txt +120 -0
- data/lib/training_data/todo/latvian.txt +126 -0
- data/lib/training_data/todo/lithuanian.txt +99 -0
- data/lib/training_data/todo/malay.txt +108 -0
- data/lib/training_data/todo/manx.txt +78 -0
- data/lib/training_data/todo/marathi.txt +100 -0
- data/lib/training_data/todo/mf.txt +100 -0
- data/lib/training_data/todo/middle_frisian.txt +102 -0
- data/lib/training_data/todo/mingo.txt +146 -0
- data/lib/training_data/todo/nepali.txt +131 -0
- data/lib/training_data/todo/persian.txt +73 -0
- data/lib/training_data/todo/quechua.txt +108 -0
- data/lib/training_data/todo/romanian.txt +103 -0
- data/lib/training_data/todo/rumantsch.txt +110 -0
- data/lib/training_data/todo/sanskrit.txt +135 -0
- data/lib/training_data/todo/scots.txt +490 -0
- data/lib/training_data/todo/scots_gaelic.txt +93 -0
- data/lib/training_data/todo/serbian-ascii.txt +121 -0
- data/lib/training_data/todo/slovak-ascii.txt +102 -0
- data/lib/training_data/todo/slovak-windows1250.txt +115 -0
- data/lib/training_data/todo/slovenian-ascii.txt +100 -0
- data/lib/training_data/todo/slovenian-iso8859_2.txt +96 -0
- data/lib/training_data/todo/sq.txt +110 -0
- data/lib/training_data/todo/swahili.txt +120 -0
- data/lib/training_data/todo/tagalog.txt +135 -0
- data/lib/training_data/todo/tamil.txt +123 -0
- data/lib/training_data/todo/turkish.txt +117 -0
- data/lib/training_data/todo/ukrainian-koi8_r.txt +214 -0
- data/lib/training_data/todo/vietnamese.txt +92 -0
- data/lib/training_data/todo/welsh.txt +148 -0
- data/lib/training_data/todo/yiddish-utf.txt +83 -0
- data/lib/training_data/uk-utf8.txt +75 -0
- data/lib/training_data/vi-utf8.txt +47 -0
- data/lib/training_data/zh-utf8.txt +228 -0
- data/test/language_detector_test.rb +78 -0
- metadata +232 -0
@@ -0,0 +1,400 @@
|
|
1
|
+
_ 11056
|
2
|
+
� 3428
|
3
|
+
� 3007
|
4
|
+
� 2501
|
5
|
+
� 2490
|
6
|
+
� 2179
|
7
|
+
� 2166
|
8
|
+
� 1596
|
9
|
+
� 1492
|
10
|
+
� 1159
|
11
|
+
�_ 1144
|
12
|
+
� 1093
|
13
|
+
� 918
|
14
|
+
� 803
|
15
|
+
�_ 803
|
16
|
+
�� 724
|
17
|
+
� 720
|
18
|
+
� 702
|
19
|
+
�_ 642
|
20
|
+
� 613
|
21
|
+
_� 577
|
22
|
+
_� 569
|
23
|
+
�_ 556
|
24
|
+
. 537
|
25
|
+
�� 534
|
26
|
+
�� 473
|
27
|
+
._ 467
|
28
|
+
� 462
|
29
|
+
�� 455
|
30
|
+
_� 452
|
31
|
+
_�� 446
|
32
|
+
,_ 440
|
33
|
+
, 440
|
34
|
+
� 439
|
35
|
+
� 432
|
36
|
+
��_ 422
|
37
|
+
� 405
|
38
|
+
� 382
|
39
|
+
�� 376
|
40
|
+
�� 360
|
41
|
+
�� 360
|
42
|
+
� 355
|
43
|
+
_� 353
|
44
|
+
�� 334
|
45
|
+
�� 330
|
46
|
+
�_ 324
|
47
|
+
�� 322
|
48
|
+
_��_ 316
|
49
|
+
�� 310
|
50
|
+
�� 308
|
51
|
+
�� 305
|
52
|
+
�� 303
|
53
|
+
�� 301
|
54
|
+
�� 281
|
55
|
+
_� 278
|
56
|
+
_� 275
|
57
|
+
��� 262
|
58
|
+
�� 262
|
59
|
+
�� 262
|
60
|
+
_� 250
|
61
|
+
��_ 248
|
62
|
+
�� 242
|
63
|
+
�� 236
|
64
|
+
�� 235
|
65
|
+
�� 230
|
66
|
+
_� 226
|
67
|
+
�� 222
|
68
|
+
�� 216
|
69
|
+
� 214
|
70
|
+
�� 210
|
71
|
+
��_ 203
|
72
|
+
�� 198
|
73
|
+
_�_ 196
|
74
|
+
�� 196
|
75
|
+
_�� 195
|
76
|
+
�� 189
|
77
|
+
�� 189
|
78
|
+
���_ 189
|
79
|
+
�_ 186
|
80
|
+
�� 185
|
81
|
+
�� 185
|
82
|
+
_� 184
|
83
|
+
�� 178
|
84
|
+
�� 177
|
85
|
+
� 175
|
86
|
+
�� 175
|
87
|
+
��_ 172
|
88
|
+
�� 171
|
89
|
+
�� 170
|
90
|
+
_� 169
|
91
|
+
_�� 169
|
92
|
+
_� 165
|
93
|
+
�_ 163
|
94
|
+
�� 162
|
95
|
+
� 161
|
96
|
+
�� 160
|
97
|
+
��_ 159
|
98
|
+
�� 156
|
99
|
+
�� 156
|
100
|
+
�� 155
|
101
|
+
�� 154
|
102
|
+
_�_ 152
|
103
|
+
_� 152
|
104
|
+
�� 151
|
105
|
+
�� 151
|
106
|
+
_� 150
|
107
|
+
�� 149
|
108
|
+
� 148
|
109
|
+
_�� 146
|
110
|
+
�� 145
|
111
|
+
�� 143
|
112
|
+
�� 141
|
113
|
+
_� 138
|
114
|
+
�� 137
|
115
|
+
�� 135
|
116
|
+
�� 134
|
117
|
+
�� 133
|
118
|
+
_�� 133
|
119
|
+
�� 131
|
120
|
+
�� 129
|
121
|
+
� 128
|
122
|
+
�� 127
|
123
|
+
_� 126
|
124
|
+
��� 124
|
125
|
+
��� 123
|
126
|
+
�� 123
|
127
|
+
��_ 123
|
128
|
+
�� 122
|
129
|
+
�� 121
|
130
|
+
_�� 120
|
131
|
+
��� 119
|
132
|
+
�� 118
|
133
|
+
�� 116
|
134
|
+
��_ 115
|
135
|
+
�� 113
|
136
|
+
��_ 112
|
137
|
+
� 112
|
138
|
+
- 111
|
139
|
+
��_ 111
|
140
|
+
�� 110
|
141
|
+
���_ 109
|
142
|
+
�� 108
|
143
|
+
_��_ 108
|
144
|
+
�� 108
|
145
|
+
��� 107
|
146
|
+
�� 107
|
147
|
+
�� 107
|
148
|
+
_�� 106
|
149
|
+
��_ 105
|
150
|
+
�� 103
|
151
|
+
_� 103
|
152
|
+
_��_ 101
|
153
|
+
�� 101
|
154
|
+
�� 100
|
155
|
+
_�� 99
|
156
|
+
" 99
|
157
|
+
�� 99
|
158
|
+
�� 99
|
159
|
+
�� 98
|
160
|
+
��� 97
|
161
|
+
��� 97
|
162
|
+
��� 97
|
163
|
+
_�_ 97
|
164
|
+
��� 96
|
165
|
+
��� 96
|
166
|
+
� 93
|
167
|
+
��_ 93
|
168
|
+
�� 92
|
169
|
+
�� 92
|
170
|
+
��� 92
|
171
|
+
�� 92
|
172
|
+
�� 91
|
173
|
+
�� 90
|
174
|
+
�� 90
|
175
|
+
�� 89
|
176
|
+
��� 89
|
177
|
+
��_ 89
|
178
|
+
�� 88
|
179
|
+
���_ 88
|
180
|
+
_� 88
|
181
|
+
�� 88
|
182
|
+
�, 87
|
183
|
+
��� 87
|
184
|
+
�� 87
|
185
|
+
�,_ 87
|
186
|
+
_��_ 85
|
187
|
+
_��_ 83
|
188
|
+
�� 83
|
189
|
+
��� 83
|
190
|
+
��_ 83
|
191
|
+
� 82
|
192
|
+
�� 81
|
193
|
+
�_ 81
|
194
|
+
_�� 81
|
195
|
+
_� 80
|
196
|
+
��� 80
|
197
|
+
��� 79
|
198
|
+
�� 78
|
199
|
+
�� 78
|
200
|
+
���� 78
|
201
|
+
�� 78
|
202
|
+
� 77
|
203
|
+
��� 77
|
204
|
+
��_ 77
|
205
|
+
�� 77
|
206
|
+
��_ 76
|
207
|
+
_�� 76
|
208
|
+
��� 75
|
209
|
+
��� 75
|
210
|
+
�� 75
|
211
|
+
�� 75
|
212
|
+
��� 74
|
213
|
+
�� 73
|
214
|
+
_�� 73
|
215
|
+
�� 73
|
216
|
+
�_ 73
|
217
|
+
��� 73
|
218
|
+
_��� 72
|
219
|
+
�� 72
|
220
|
+
�� 72
|
221
|
+
���� 72
|
222
|
+
��� 72
|
223
|
+
��� 71
|
224
|
+
�� 71
|
225
|
+
�,_ 71
|
226
|
+
����� 71
|
227
|
+
����_ 71
|
228
|
+
��� 71
|
229
|
+
���� 71
|
230
|
+
�_ 71
|
231
|
+
�, 71
|
232
|
+
�� 70
|
233
|
+
�� 70
|
234
|
+
��� 70
|
235
|
+
�� 70
|
236
|
+
��� 70
|
237
|
+
�� 70
|
238
|
+
_�� 70
|
239
|
+
�_ 69
|
240
|
+
�� 68
|
241
|
+
��� 68
|
242
|
+
�� 67
|
243
|
+
�� 67
|
244
|
+
��� 66
|
245
|
+
��� 66
|
246
|
+
���� 66
|
247
|
+
�_ 66
|
248
|
+
�� 66
|
249
|
+
�� 65
|
250
|
+
��� 65
|
251
|
+
��� 64
|
252
|
+
��� 64
|
253
|
+
�� 64
|
254
|
+
��� 64
|
255
|
+
_� 64
|
256
|
+
���� 63
|
257
|
+
��� 63
|
258
|
+
_�� 63
|
259
|
+
_� 62
|
260
|
+
_� 62
|
261
|
+
��_ 62
|
262
|
+
� 62
|
263
|
+
��_ 62
|
264
|
+
_. 62
|
265
|
+
�� 61
|
266
|
+
�� 61
|
267
|
+
�� 61
|
268
|
+
�� 61
|
269
|
+
�� 61
|
270
|
+
_�� 61
|
271
|
+
��� 60
|
272
|
+
��� 60
|
273
|
+
( 60
|
274
|
+
) 60
|
275
|
+
��� 59
|
276
|
+
�� 59
|
277
|
+
�� 59
|
278
|
+
��� 59
|
279
|
+
�� 59
|
280
|
+
�. 58
|
281
|
+
� 58
|
282
|
+
��� 58
|
283
|
+
_( 58
|
284
|
+
_��� 58
|
285
|
+
�� 58
|
286
|
+
�� 58
|
287
|
+
_� 57
|
288
|
+
���_ 57
|
289
|
+
��� 57
|
290
|
+
��� 57
|
291
|
+
��� 56
|
292
|
+
�._ 56
|
293
|
+
�� 56
|
294
|
+
��� 56
|
295
|
+
��� 56
|
296
|
+
_��� 55
|
297
|
+
�� 55
|
298
|
+
��� 55
|
299
|
+
��� 55
|
300
|
+
_�_ 55
|
301
|
+
�� 55
|
302
|
+
_,_ 55
|
303
|
+
_�� 55
|
304
|
+
����� 55
|
305
|
+
��� 55
|
306
|
+
���� 55
|
307
|
+
_, 55
|
308
|
+
��_ 54
|
309
|
+
����� 54
|
310
|
+
� 54
|
311
|
+
���� 54
|
312
|
+
_- 54
|
313
|
+
���� 54
|
314
|
+
-_ 53
|
315
|
+
��� 53
|
316
|
+
�� 53
|
317
|
+
��_ 53
|
318
|
+
����� 53
|
319
|
+
��� 53
|
320
|
+
_�� 53
|
321
|
+
�� 53
|
322
|
+
_�� 52
|
323
|
+
��� 52
|
324
|
+
��� 52
|
325
|
+
_-_ 52
|
326
|
+
�� 51
|
327
|
+
_� 51
|
328
|
+
�� 51
|
329
|
+
�� 51
|
330
|
+
�_ 50
|
331
|
+
_� 50
|
332
|
+
��� 50
|
333
|
+
��� 50
|
334
|
+
�� 50
|
335
|
+
� 50
|
336
|
+
_��� 50
|
337
|
+
_�� 50
|
338
|
+
_" 50
|
339
|
+
�� 49
|
340
|
+
_�� 49
|
341
|
+
�� 49
|
342
|
+
���� 49
|
343
|
+
�� 48
|
344
|
+
��� 48
|
345
|
+
���_ 48
|
346
|
+
��� 48
|
347
|
+
����� 48
|
348
|
+
_�� 48
|
349
|
+
�� 48
|
350
|
+
_._ 48
|
351
|
+
��� 48
|
352
|
+
�� 48
|
353
|
+
���� 48
|
354
|
+
�� 48
|
355
|
+
���� 48
|
356
|
+
��� 47
|
357
|
+
�� 47
|
358
|
+
� 47
|
359
|
+
����� 47
|
360
|
+
_�� 47
|
361
|
+
���� 47
|
362
|
+
��� 47
|
363
|
+
����� 47
|
364
|
+
��� 47
|
365
|
+
���� 47
|
366
|
+
���� 47
|
367
|
+
��� 47
|
368
|
+
��� 47
|
369
|
+
��� 46
|
370
|
+
���� 46
|
371
|
+
_��� 46
|
372
|
+
���_ 46
|
373
|
+
��� 46
|
374
|
+
����� 46
|
375
|
+
_���� 45
|
376
|
+
��� 45
|
377
|
+
��� 45
|
378
|
+
�� 45
|
379
|
+
�� 45
|
380
|
+
���� 45
|
381
|
+
_�� 45
|
382
|
+
�� 45
|
383
|
+
��_ 45
|
384
|
+
�� 45
|
385
|
+
��� 45
|
386
|
+
��� 45
|
387
|
+
���� 44
|
388
|
+
����� 44
|
389
|
+
_��� 44
|
390
|
+
����� 44
|
391
|
+
_���� 44
|
392
|
+
��_ 44
|
393
|
+
���_ 44
|
394
|
+
��� 44
|
395
|
+
��_ 44
|
396
|
+
���� 44
|
397
|
+
� 43
|
398
|
+
���� 43
|
399
|
+
��� 43
|
400
|
+
����� 43
|
@@ -0,0 +1,400 @@
|
|
1
|
+
_ 16604
|
2
|
+
e 5091
|
3
|
+
a 4937
|
4
|
+
s 3120
|
5
|
+
r 3037
|
6
|
+
i 2987
|
7
|
+
l 2747
|
8
|
+
n 2641
|
9
|
+
t 2466
|
10
|
+
o 2274
|
11
|
+
d 1775
|
12
|
+
c 1740
|
13
|
+
u 1515
|
14
|
+
a_ 1460
|
15
|
+
s_ 1416
|
16
|
+
_d 1116
|
17
|
+
e_ 1067
|
18
|
+
p 1014
|
19
|
+
m 995
|
20
|
+
es 985
|
21
|
+
de 972
|
22
|
+
_de 842
|
23
|
+
en 700
|
24
|
+
_l 691
|
25
|
+
re 652
|
26
|
+
_e 637
|
27
|
+
de_ 611
|
28
|
+
el 602
|
29
|
+
_de_ 601
|
30
|
+
_a 600
|
31
|
+
, 599
|
32
|
+
,_ 599
|
33
|
+
er 598
|
34
|
+
la 584
|
35
|
+
ar 583
|
36
|
+
_p 550
|
37
|
+
l_ 547
|
38
|
+
ci 522
|
39
|
+
n_ 518
|
40
|
+
es_ 515
|
41
|
+
an 515
|
42
|
+
ra 499
|
43
|
+
nt 495
|
44
|
+
ta 495
|
45
|
+
b 476
|
46
|
+
_c 452
|
47
|
+
al 450
|
48
|
+
v 440
|
49
|
+
g 428
|
50
|
+
. 420
|
51
|
+
on 420
|
52
|
+
or 404
|
53
|
+
t_ 402
|
54
|
+
at 396
|
55
|
+
._ 377
|
56
|
+
r_ 372
|
57
|
+
i_ 371
|
58
|
+
la_ 368
|
59
|
+
_i 364
|
60
|
+
_la 351
|
61
|
+
_la_ 325
|
62
|
+
f 325
|
63
|
+
le 322
|
64
|
+
te 312
|
65
|
+
' 311
|
66
|
+
_s 308
|
67
|
+
st 308
|
68
|
+
se 305
|
69
|
+
� 302
|
70
|
+
ue 302
|
71
|
+
na 301
|
72
|
+
os 301
|
73
|
+
qu 300
|
74
|
+
q 300
|
75
|
+
el_ 299
|
76
|
+
it 292
|
77
|
+
co 290
|
78
|
+
ri 277
|
79
|
+
ca 277
|
80
|
+
ti 273
|
81
|
+
ac 272
|
82
|
+
in 268
|
83
|
+
ll 264
|
84
|
+
ic 264
|
85
|
+
me 259
|
86
|
+
un 257
|
87
|
+
que 248
|
88
|
+
C 248
|
89
|
+
tr 244
|
90
|
+
ns 242
|
91
|
+
i� 238
|
92
|
+
_i_ 236
|
93
|
+
ad 233
|
94
|
+
ent 232
|
95
|
+
_el 227
|
96
|
+
ne 226
|
97
|
+
_t 223
|
98
|
+
_co 221
|
99
|
+
_m 221
|
100
|
+
_C 217
|
101
|
+
en_ 217
|
102
|
+
li 217
|
103
|
+
ia 212
|
104
|
+
� 212
|
105
|
+
pe 207
|
106
|
+
_a_ 207
|
107
|
+
pr 206
|
108
|
+
ci� 203
|
109
|
+
�_ 203
|
110
|
+
pa 203
|
111
|
+
ro 202
|
112
|
+
o_ 198
|
113
|
+
E 198
|
114
|
+
di 197
|
115
|
+
io 197
|
116
|
+
ls 196
|
117
|
+
h 192
|
118
|
+
_q 192
|
119
|
+
_qu 192
|
120
|
+
_en 187
|
121
|
+
aci 186
|
122
|
+
am 186
|
123
|
+
ec 183
|
124
|
+
to 183
|
125
|
+
as 180
|
126
|
+
om 180
|
127
|
+
ni 180
|
128
|
+
da 179
|
129
|
+
i�_ 179
|
130
|
+
si 178
|
131
|
+
ls_ 176
|
132
|
+
L 175
|
133
|
+
ma 172
|
134
|
+
res 172
|
135
|
+
ur 171
|
136
|
+
_el_ 162
|
137
|
+
rt 162
|
138
|
+
ue_ 160
|
139
|
+
A 160
|
140
|
+
os_ 159
|
141
|
+
_que 159
|
142
|
+
que_ 158
|
143
|
+
_r 158
|
144
|
+
po 157
|
145
|
+
_es 155
|
146
|
+
er_ 155
|
147
|
+
_que_ 155
|
148
|
+
M 155
|
149
|
+
_se 153
|
150
|
+
va 153
|
151
|
+
del 153
|
152
|
+
ci�_ 151
|
153
|
+
_pr 151
|
154
|
+
is 150
|
155
|
+
_en_ 149
|
156
|
+
P 147
|
157
|
+
_pe 146
|
158
|
+
_del 145
|
159
|
+
ts 145
|
160
|
+
lo 145
|
161
|
+
_M 144
|
162
|
+
ct 144
|
163
|
+
_u 144
|
164
|
+
ol 143
|
165
|
+
ve 141
|
166
|
+
_L 140
|
167
|
+
x 140
|
168
|
+
y 140
|
169
|
+
a,_ 139
|
170
|
+
a, 139
|
171
|
+
nc 138
|
172
|
+
men 137
|
173
|
+
al_ 137
|
174
|
+
_f 137
|
175
|
+
_re 137
|
176
|
+
_P 136
|
177
|
+
aci� 136
|
178
|
+
les 136
|
179
|
+
rs 134
|
180
|
+
est 133
|
181
|
+
tu 131
|
182
|
+
_E 130
|
183
|
+
et 130
|
184
|
+
s,_ 129
|
185
|
+
_un 129
|
186
|
+
na_ 129
|
187
|
+
_v 129
|
188
|
+
s, 129
|
189
|
+
ion 127
|
190
|
+
per 126
|
191
|
+
so 125
|
192
|
+
em 125
|
193
|
+
at_ 124
|
194
|
+
no 124
|
195
|
+
j 124
|
196
|
+
br 123
|
197
|
+
nt_ 122
|
198
|
+
ar_ 122
|
199
|
+
sa 121
|
200
|
+
_n 119
|
201
|
+
les_ 118
|
202
|
+
� 118
|
203
|
+
ce 117
|
204
|
+
il 117
|
205
|
+
ell 116
|
206
|
+
_per 114
|
207
|
+
� 114
|
208
|
+
ob 113
|
209
|
+
re_ 113
|
210
|
+
ir 113
|
211
|
+
_A 112
|
212
|
+
ons 112
|
213
|
+
do 112
|
214
|
+
ua 112
|
215
|
+
con 112
|
216
|
+
ment 111
|
217
|
+
gu 111
|
218
|
+
ts_ 110
|
219
|
+
ss 110
|
220
|
+
ns_ 109
|
221
|
+
ant 109
|
222
|
+
ra_ 109
|
223
|
+
Co 109
|
224
|
+
par 108
|
225
|
+
l' 107
|
226
|
+
d' 107
|
227
|
+
_l' 107
|
228
|
+
els 107
|
229
|
+
tat 107
|
230
|
+
sc 106
|
231
|
+
_d' 106
|
232
|
+
an_ 105
|
233
|
+
_Co 105
|
234
|
+
vi 104
|
235
|
+
els_ 104
|
236
|
+
ica 104
|
237
|
+
ran 103
|
238
|
+
ul 102
|
239
|
+
iv 102
|
240
|
+
S 102
|
241
|
+
_del_ 102
|
242
|
+
del_ 102
|
243
|
+
mb 101
|
244
|
+
mi 101
|
245
|
+
ita 101
|
246
|
+
nta 100
|
247
|
+
_pa 99
|
248
|
+
_o 99
|
249
|
+
_con 98
|
250
|
+
aci�_ 97
|
251
|
+
rn 96
|
252
|
+
_in 96
|
253
|
+
ia_ 96
|
254
|
+
z 96
|
255
|
+
im 95
|
256
|
+
rr 95
|
257
|
+
art 94
|
258
|
+
ta_ 93
|
259
|
+
com 93
|
260
|
+
tre 92
|
261
|
+
_h 92
|
262
|
+
s. 91
|
263
|
+
mp 90
|
264
|
+
ie 90
|
265
|
+
J 90
|
266
|
+
s._ 89
|
267
|
+
cio 89
|
268
|
+
_le 89
|
269
|
+
bre 88
|
270
|
+
_ca 88
|
271
|
+
_al 88
|
272
|
+
sta 88
|
273
|
+
_com 88
|
274
|
+
cu 88
|
275
|
+
�_ 87
|
276
|
+
pre 87
|
277
|
+
fe 86
|
278
|
+
ba 86
|
279
|
+
tra 86
|
280
|
+
ge 85
|
281
|
+
pro 85
|
282
|
+
_les 84
|
283
|
+
des 84
|
284
|
+
ter 84
|
285
|
+
_po 84
|
286
|
+
_les_ 84
|
287
|
+
T 84
|
288
|
+
_J 84
|
289
|
+
nd 84
|
290
|
+
cion 84
|
291
|
+
_S 84
|
292
|
+
ura 83
|
293
|
+
nci 82
|
294
|
+
va_ 81
|
295
|
+
ha 81
|
296
|
+
ona 81
|
297
|
+
ent_ 80
|
298
|
+
ues 80
|
299
|
+
oc 80
|
300
|
+
ea 80
|
301
|
+
nte 80
|
302
|
+
�s 80
|
303
|
+
_di 79
|
304
|
+
ui 79
|
305
|
+
as_ 78
|
306
|
+
ut 78
|
307
|
+
ici 78
|
308
|
+
res_ 78
|
309
|
+
us 77
|
310
|
+
ot 77
|
311
|
+
ara 77
|
312
|
+
ip 75
|
313
|
+
rm 75
|
314
|
+
ab 75
|
315
|
+
eg 75
|
316
|
+
_per_ 75
|
317
|
+
ng 75
|
318
|
+
'a 75
|
319
|
+
I 75
|
320
|
+
per_ 75
|
321
|
+
rec 74
|
322
|
+
du 74
|
323
|
+
_tr 74
|
324
|
+
� 73
|
325
|
+
cia 73
|
326
|
+
_no 73
|
327
|
+
b_ 73
|
328
|
+
_par 72
|
329
|
+
ep 72
|
330
|
+
id 72
|
331
|
+
lle 71
|
332
|
+
rc 71
|
333
|
+
_pro 70
|
334
|
+
D 69
|
335
|
+
G 69
|
336
|
+
ga 69
|
337
|
+
fo 69
|
338
|
+
una 68
|
339
|
+
El 68
|
340
|
+
lit 68
|
341
|
+
un_ 68
|
342
|
+
ques 68
|
343
|
+
amb 67
|
344
|
+
ix 67
|
345
|
+
�s_ 67
|
346
|
+
_G 67
|
347
|
+
era 67
|
348
|
+
cr 67
|
349
|
+
) 66
|
350
|
+
da_ 66
|
351
|
+
- 66
|
352
|
+
sp 66
|
353
|
+
y_ 66
|
354
|
+
ada 66
|
355
|
+
tor 66
|
356
|
+
( 66
|
357
|
+
_( 66
|
358
|
+
_T 65
|
359
|
+
ment_ 65
|
360
|
+
B 65
|
361
|
+
_es_ 65
|
362
|
+
Ma 65
|
363
|
+
V 65
|
364
|
+
uc 65
|
365
|
+
ect 65
|
366
|
+
ame 64
|
367
|
+
iu 64
|
368
|
+
_Ma 64
|
369
|
+
orn 64
|
370
|
+
_B 64
|
371
|
+
_D 64
|
372
|
+
Ca 64
|
373
|
+
sti 64
|
374
|
+
_g 63
|
375
|
+
esc 63
|
376
|
+
rd 63
|
377
|
+
una_ 63
|
378
|
+
l� 62
|
379
|
+
" 62
|
380
|
+
ed 62
|
381
|
+
amen 61
|
382
|
+
mo 61
|
383
|
+
ions 61
|
384
|
+
_El 61
|
385
|
+
_Ca 61
|
386
|
+
Jo 61
|
387
|
+
eu 61
|
388
|
+
ari 61
|
389
|
+
lt 61
|
390
|
+
F 61
|
391
|
+
u_ 61
|
392
|
+
ament 60
|
393
|
+
_V 60
|
394
|
+
m_ 60
|
395
|
+
fi 60
|
396
|
+
au 60
|
397
|
+
ev 60
|
398
|
+
La 60
|
399
|
+
itat 59
|
400
|
+
_ha 59
|