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.
- 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
|
+
_ 14926
|
|
2
|
+
� 7221
|
|
3
|
+
� 5780
|
|
4
|
+
� 4137
|
|
5
|
+
� 2966
|
|
6
|
+
� 2908
|
|
7
|
+
� 2607
|
|
8
|
+
� 2372
|
|
9
|
+
� 2260
|
|
10
|
+
� 2080
|
|
11
|
+
� 2078
|
|
12
|
+
� 2005
|
|
13
|
+
� 1598
|
|
14
|
+
� 1383
|
|
15
|
+
� 1363
|
|
16
|
+
�_ 1248
|
|
17
|
+
�_ 1149
|
|
18
|
+
� 1145
|
|
19
|
+
�� 1009
|
|
20
|
+
� 974
|
|
21
|
+
_� 965
|
|
22
|
+
�_ 964
|
|
23
|
+
�� 912
|
|
24
|
+
�� 901
|
|
25
|
+
�� 897
|
|
26
|
+
� 820
|
|
27
|
+
. 813
|
|
28
|
+
�� 767
|
|
29
|
+
" 762
|
|
30
|
+
._ 735
|
|
31
|
+
, 720
|
|
32
|
+
,_ 718
|
|
33
|
+
�� 684
|
|
34
|
+
_� 669
|
|
35
|
+
� 653
|
|
36
|
+
�� 631
|
|
37
|
+
�� 622
|
|
38
|
+
�� 575
|
|
39
|
+
�� 570
|
|
40
|
+
�� 567
|
|
41
|
+
� 551
|
|
42
|
+
_� 550
|
|
43
|
+
� 542
|
|
44
|
+
_� 526
|
|
45
|
+
� 518
|
|
46
|
+
�� 517
|
|
47
|
+
�� 485
|
|
48
|
+
�� 479
|
|
49
|
+
�� 478
|
|
50
|
+
_� 474
|
|
51
|
+
�� 468
|
|
52
|
+
_� 436
|
|
53
|
+
�� 435
|
|
54
|
+
�� 420
|
|
55
|
+
�� 419
|
|
56
|
+
�� 418
|
|
57
|
+
�� 416
|
|
58
|
+
�� 412
|
|
59
|
+
��_ 407
|
|
60
|
+
_�� 404
|
|
61
|
+
��_ 393
|
|
62
|
+
�� 384
|
|
63
|
+
�� 382
|
|
64
|
+
� 376
|
|
65
|
+
_" 374
|
|
66
|
+
��_ 371
|
|
67
|
+
� 369
|
|
68
|
+
�� 364
|
|
69
|
+
�� 360
|
|
70
|
+
�� 358
|
|
71
|
+
�� 353
|
|
72
|
+
�� 349
|
|
73
|
+
� 349
|
|
74
|
+
�� 342
|
|
75
|
+
� 341
|
|
76
|
+
�� 335
|
|
77
|
+
�� 334
|
|
78
|
+
�� 332
|
|
79
|
+
�� 326
|
|
80
|
+
_� 322
|
|
81
|
+
�� 321
|
|
82
|
+
�� 319
|
|
83
|
+
_� 319
|
|
84
|
+
_� 319
|
|
85
|
+
�� 317
|
|
86
|
+
_�� 316
|
|
87
|
+
�� 316
|
|
88
|
+
�� 306
|
|
89
|
+
�_ 299
|
|
90
|
+
_� 288
|
|
91
|
+
�� 279
|
|
92
|
+
��� 273
|
|
93
|
+
�� 271
|
|
94
|
+
� 270
|
|
95
|
+
�_ 267
|
|
96
|
+
�� 267
|
|
97
|
+
_�� 266
|
|
98
|
+
�� 263
|
|
99
|
+
�� 260
|
|
100
|
+
�_ 256
|
|
101
|
+
��� 255
|
|
102
|
+
�� 238
|
|
103
|
+
�� 238
|
|
104
|
+
�� 234
|
|
105
|
+
�� 233
|
|
106
|
+
�� 230
|
|
107
|
+
�� 229
|
|
108
|
+
_� 227
|
|
109
|
+
"_ 225
|
|
110
|
+
��� 224
|
|
111
|
+
: 224
|
|
112
|
+
:_ 223
|
|
113
|
+
�. 221
|
|
114
|
+
_��_ 217
|
|
115
|
+
� 215
|
|
116
|
+
�� 213
|
|
117
|
+
�, 213
|
|
118
|
+
�,_ 212
|
|
119
|
+
_� 211
|
|
120
|
+
�_ 209
|
|
121
|
+
_�� 208
|
|
122
|
+
��� 208
|
|
123
|
+
�� 206
|
|
124
|
+
_�� 204
|
|
125
|
+
�� 203
|
|
126
|
+
��� 203
|
|
127
|
+
�� 203
|
|
128
|
+
�._ 201
|
|
129
|
+
�. 200
|
|
130
|
+
- 193
|
|
131
|
+
�� 192
|
|
132
|
+
��� 192
|
|
133
|
+
�_ 189
|
|
134
|
+
�� 188
|
|
135
|
+
� 188
|
|
136
|
+
�� 187
|
|
137
|
+
�_ 185
|
|
138
|
+
��� 183
|
|
139
|
+
�� 179
|
|
140
|
+
�._ 177
|
|
141
|
+
�_ 177
|
|
142
|
+
�� 174
|
|
143
|
+
�� 174
|
|
144
|
+
�� 173
|
|
145
|
+
�� 172
|
|
146
|
+
_�� 172
|
|
147
|
+
�� 172
|
|
148
|
+
��� 171
|
|
149
|
+
_�� 170
|
|
150
|
+
��_ 170
|
|
151
|
+
_�� 170
|
|
152
|
+
_� 169
|
|
153
|
+
�� 166
|
|
154
|
+
�� 166
|
|
155
|
+
_� 165
|
|
156
|
+
��_ 165
|
|
157
|
+
��_ 163
|
|
158
|
+
�� 162
|
|
159
|
+
_�� 160
|
|
160
|
+
�� 158
|
|
161
|
+
_� 155
|
|
162
|
+
�� 154
|
|
163
|
+
��� 153
|
|
164
|
+
� 151
|
|
165
|
+
�_ 149
|
|
166
|
+
��� 148
|
|
167
|
+
�,_ 147
|
|
168
|
+
�, 147
|
|
169
|
+
�� 147
|
|
170
|
+
�� 145
|
|
171
|
+
���� 145
|
|
172
|
+
�� 143
|
|
173
|
+
��� 143
|
|
174
|
+
�� 143
|
|
175
|
+
��� 142
|
|
176
|
+
�� 142
|
|
177
|
+
��� 141
|
|
178
|
+
�� 140
|
|
179
|
+
�� 139
|
|
180
|
+
���_ 139
|
|
181
|
+
�� 139
|
|
182
|
+
�� 138
|
|
183
|
+
_� 136
|
|
184
|
+
��_ 135
|
|
185
|
+
��� 133
|
|
186
|
+
��_ 132
|
|
187
|
+
��� 131
|
|
188
|
+
�� 130
|
|
189
|
+
�� 130
|
|
190
|
+
�� 130
|
|
191
|
+
��� 128
|
|
192
|
+
�� 125
|
|
193
|
+
�� 125
|
|
194
|
+
�� 125
|
|
195
|
+
�_ 124
|
|
196
|
+
��� 124
|
|
197
|
+
��_ 124
|
|
198
|
+
��� 123
|
|
199
|
+
_�� 123
|
|
200
|
+
��� 122
|
|
201
|
+
_�� 121
|
|
202
|
+
�� 121
|
|
203
|
+
_� 120
|
|
204
|
+
�� 120
|
|
205
|
+
�� 116
|
|
206
|
+
_� 114
|
|
207
|
+
��� 113
|
|
208
|
+
��� 113
|
|
209
|
+
��� 113
|
|
210
|
+
�� 112
|
|
211
|
+
�� 112
|
|
212
|
+
�� 112
|
|
213
|
+
�� 112
|
|
214
|
+
��� 111
|
|
215
|
+
�� 111
|
|
216
|
+
�� 109
|
|
217
|
+
�� 109
|
|
218
|
+
�� 107
|
|
219
|
+
��_ 107
|
|
220
|
+
��_ 107
|
|
221
|
+
��� 107
|
|
222
|
+
���_ 106
|
|
223
|
+
�� 106
|
|
224
|
+
��_ 106
|
|
225
|
+
_�� 105
|
|
226
|
+
� 104
|
|
227
|
+
��� 104
|
|
228
|
+
_�� 104
|
|
229
|
+
��� 103
|
|
230
|
+
_�� 103
|
|
231
|
+
��� 103
|
|
232
|
+
��� 103
|
|
233
|
+
_� 103
|
|
234
|
+
�� 102
|
|
235
|
+
_� 102
|
|
236
|
+
��� 102
|
|
237
|
+
��� 102
|
|
238
|
+
�� 102
|
|
239
|
+
_��� 101
|
|
240
|
+
_��� 101
|
|
241
|
+
�� 100
|
|
242
|
+
_���� 100
|
|
243
|
+
��� 99
|
|
244
|
+
�� 99
|
|
245
|
+
�� 99
|
|
246
|
+
�� 99
|
|
247
|
+
�� 97
|
|
248
|
+
�� 97
|
|
249
|
+
��� 96
|
|
250
|
+
�� 94
|
|
251
|
+
�� 94
|
|
252
|
+
_�� 94
|
|
253
|
+
�,_ 93
|
|
254
|
+
�� 93
|
|
255
|
+
�� 93
|
|
256
|
+
_�� 93
|
|
257
|
+
�, 93
|
|
258
|
+
_�� 93
|
|
259
|
+
�� 93
|
|
260
|
+
�� 92
|
|
261
|
+
��� 92
|
|
262
|
+
��_ 92
|
|
263
|
+
�� 91
|
|
264
|
+
��� 91
|
|
265
|
+
�� 91
|
|
266
|
+
�� 90
|
|
267
|
+
��_ 90
|
|
268
|
+
��� 89
|
|
269
|
+
���� 89
|
|
270
|
+
�� 89
|
|
271
|
+
��� 89
|
|
272
|
+
��� 89
|
|
273
|
+
�� 89
|
|
274
|
+
�" 89
|
|
275
|
+
�. 88
|
|
276
|
+
�� 88
|
|
277
|
+
��� 88
|
|
278
|
+
��_ 87
|
|
279
|
+
_��� 87
|
|
280
|
+
�� 87
|
|
281
|
+
��� 87
|
|
282
|
+
��� 87
|
|
283
|
+
�� 87
|
|
284
|
+
��� 87
|
|
285
|
+
��� 85
|
|
286
|
+
��_ 85
|
|
287
|
+
��� 85
|
|
288
|
+
�� 85
|
|
289
|
+
�� 85
|
|
290
|
+
_� 84
|
|
291
|
+
��. 84
|
|
292
|
+
_�� 83
|
|
293
|
+
�._ 83
|
|
294
|
+
_� 83
|
|
295
|
+
_��� 83
|
|
296
|
+
��� 83
|
|
297
|
+
��._ 82
|
|
298
|
+
��� 82
|
|
299
|
+
��_ 82
|
|
300
|
+
��� 82
|
|
301
|
+
�� 81
|
|
302
|
+
��_ 81
|
|
303
|
+
"� 81
|
|
304
|
+
�� 80
|
|
305
|
+
_"� 80
|
|
306
|
+
��� 80
|
|
307
|
+
_��_ 79
|
|
308
|
+
_�� 79
|
|
309
|
+
�� 79
|
|
310
|
+
�� 79
|
|
311
|
+
���� 79
|
|
312
|
+
��_ 79
|
|
313
|
+
��� 79
|
|
314
|
+
��� 78
|
|
315
|
+
��, 78
|
|
316
|
+
�� 78
|
|
317
|
+
�� 78
|
|
318
|
+
���� 78
|
|
319
|
+
��� 78
|
|
320
|
+
��,_ 78
|
|
321
|
+
��� 78
|
|
322
|
+
�� 78
|
|
323
|
+
_��_ 77
|
|
324
|
+
�� 77
|
|
325
|
+
�� 77
|
|
326
|
+
����� 77
|
|
327
|
+
_�� 77
|
|
328
|
+
��� 77
|
|
329
|
+
��� 77
|
|
330
|
+
���� 77
|
|
331
|
+
�� 76
|
|
332
|
+
��_ 75
|
|
333
|
+
_�� 75
|
|
334
|
+
�� 75
|
|
335
|
+
�� 75
|
|
336
|
+
��_ 75
|
|
337
|
+
��� 75
|
|
338
|
+
���� 74
|
|
339
|
+
���� 74
|
|
340
|
+
����� 74
|
|
341
|
+
���_ 74
|
|
342
|
+
�� 73
|
|
343
|
+
�� 73
|
|
344
|
+
�� 73
|
|
345
|
+
�� 73
|
|
346
|
+
�� 73
|
|
347
|
+
����� 73
|
|
348
|
+
�� 73
|
|
349
|
+
��� 72
|
|
350
|
+
�� 72
|
|
351
|
+
_� 72
|
|
352
|
+
�� 71
|
|
353
|
+
��_ 71
|
|
354
|
+
�� 71
|
|
355
|
+
�� 71
|
|
356
|
+
�� 71
|
|
357
|
+
��� 71
|
|
358
|
+
����� 71
|
|
359
|
+
��� 70
|
|
360
|
+
��_ 70
|
|
361
|
+
�� 69
|
|
362
|
+
��_ 69
|
|
363
|
+
�� 69
|
|
364
|
+
_��� 67
|
|
365
|
+
� 67
|
|
366
|
+
��� 67
|
|
367
|
+
��� 67
|
|
368
|
+
��� 67
|
|
369
|
+
����� 67
|
|
370
|
+
�� 67
|
|
371
|
+
���� 66
|
|
372
|
+
_���� 66
|
|
373
|
+
�� 66
|
|
374
|
+
��� 66
|
|
375
|
+
���� 66
|
|
376
|
+
��� 66
|
|
377
|
+
���� 66
|
|
378
|
+
_��� 66
|
|
379
|
+
��� 65
|
|
380
|
+
�� 65
|
|
381
|
+
��� 65
|
|
382
|
+
�� 65
|
|
383
|
+
���_ 65
|
|
384
|
+
��� 65
|
|
385
|
+
�� 65
|
|
386
|
+
_�� 64
|
|
387
|
+
�_ 63
|
|
388
|
+
�� 63
|
|
389
|
+
", 63
|
|
390
|
+
�� 63
|
|
391
|
+
��� 63
|
|
392
|
+
�� 63
|
|
393
|
+
�� 63
|
|
394
|
+
�� 62
|
|
395
|
+
�" 62
|
|
396
|
+
��� 62
|
|
397
|
+
? 62
|
|
398
|
+
",_ 62
|
|
399
|
+
! 62
|
|
400
|
+
_�� 62
|
|
@@ -0,0 +1,400 @@
|
|
|
1
|
+
_ 31586
|
|
2
|
+
e 15008
|
|
3
|
+
n 9058
|
|
4
|
+
i 7299
|
|
5
|
+
r 6830
|
|
6
|
+
t 5662
|
|
7
|
+
s 5348
|
|
8
|
+
a 4618
|
|
9
|
+
h 4176
|
|
10
|
+
d 4011
|
|
11
|
+
er 3415
|
|
12
|
+
en 3412
|
|
13
|
+
u 3341
|
|
14
|
+
l 3266
|
|
15
|
+
n_ 2848
|
|
16
|
+
c 2636
|
|
17
|
+
ch 2460
|
|
18
|
+
g 2407
|
|
19
|
+
o 2376
|
|
20
|
+
e_ 2208
|
|
21
|
+
r_ 2128
|
|
22
|
+
m 2077
|
|
23
|
+
_d 1948
|
|
24
|
+
de 1831
|
|
25
|
+
en_ 1786
|
|
26
|
+
ei 1718
|
|
27
|
+
er_ 1570
|
|
28
|
+
in 1568
|
|
29
|
+
te 1505
|
|
30
|
+
ie 1505
|
|
31
|
+
b 1458
|
|
32
|
+
t_ 1425
|
|
33
|
+
f 1306
|
|
34
|
+
k 1176
|
|
35
|
+
ge 1144
|
|
36
|
+
s_ 1137
|
|
37
|
+
un 1113
|
|
38
|
+
, 1104
|
|
39
|
+
,_ 1099
|
|
40
|
+
w 1099
|
|
41
|
+
z 1060
|
|
42
|
+
nd 1039
|
|
43
|
+
he 1004
|
|
44
|
+
st 989
|
|
45
|
+
_s 952
|
|
46
|
+
_de 949
|
|
47
|
+
. 909
|
|
48
|
+
_e 906
|
|
49
|
+
ne 906
|
|
50
|
+
der 880
|
|
51
|
+
._ 847
|
|
52
|
+
be 841
|
|
53
|
+
es 829
|
|
54
|
+
ic 796
|
|
55
|
+
_a 791
|
|
56
|
+
ie_ 779
|
|
57
|
+
is 769
|
|
58
|
+
ich 763
|
|
59
|
+
an 755
|
|
60
|
+
re 749
|
|
61
|
+
di 732
|
|
62
|
+
ein 730
|
|
63
|
+
se 730
|
|
64
|
+
" 720
|
|
65
|
+
ng 709
|
|
66
|
+
_i 706
|
|
67
|
+
sc 683
|
|
68
|
+
sch 681
|
|
69
|
+
it 673
|
|
70
|
+
der_ 652
|
|
71
|
+
h_ 651
|
|
72
|
+
ch_ 642
|
|
73
|
+
S 630
|
|
74
|
+
le 609
|
|
75
|
+
p 609
|
|
76
|
+
� 607
|
|
77
|
+
� 603
|
|
78
|
+
au 603
|
|
79
|
+
v 602
|
|
80
|
+
che 599
|
|
81
|
+
_w 596
|
|
82
|
+
d_ 585
|
|
83
|
+
die 576
|
|
84
|
+
_di 572
|
|
85
|
+
m_ 562
|
|
86
|
+
_die 559
|
|
87
|
+
el 548
|
|
88
|
+
_S 540
|
|
89
|
+
_der 529
|
|
90
|
+
li 527
|
|
91
|
+
_der_ 523
|
|
92
|
+
si 515
|
|
93
|
+
al 514
|
|
94
|
+
ns 507
|
|
95
|
+
on 501
|
|
96
|
+
or 495
|
|
97
|
+
ti 490
|
|
98
|
+
ten 487
|
|
99
|
+
ht 486
|
|
100
|
+
die_ 485
|
|
101
|
+
_die_ 483
|
|
102
|
+
D 479
|
|
103
|
+
rt 478
|
|
104
|
+
nd_ 476
|
|
105
|
+
_u 470
|
|
106
|
+
nt 468
|
|
107
|
+
A 466
|
|
108
|
+
in_ 464
|
|
109
|
+
den 461
|
|
110
|
+
cht 447
|
|
111
|
+
und 443
|
|
112
|
+
me 440
|
|
113
|
+
_z 429
|
|
114
|
+
ung 426
|
|
115
|
+
ll 423
|
|
116
|
+
_un 421
|
|
117
|
+
_ei 419
|
|
118
|
+
_n 415
|
|
119
|
+
hr 412
|
|
120
|
+
ine 412
|
|
121
|
+
_A 408
|
|
122
|
+
_ein 405
|
|
123
|
+
ar 404
|
|
124
|
+
ra 403
|
|
125
|
+
_v 400
|
|
126
|
+
_g 400
|
|
127
|
+
as 395
|
|
128
|
+
zu 392
|
|
129
|
+
et 389
|
|
130
|
+
em 385
|
|
131
|
+
_D 380
|
|
132
|
+
eine 376
|
|
133
|
+
gen 376
|
|
134
|
+
g_ 376
|
|
135
|
+
da 368
|
|
136
|
+
we 366
|
|
137
|
+
K 365
|
|
138
|
+
lt 360
|
|
139
|
+
B 354
|
|
140
|
+
_" 353
|
|
141
|
+
nde 349
|
|
142
|
+
ni 347
|
|
143
|
+
und_ 345
|
|
144
|
+
E 345
|
|
145
|
+
ur 345
|
|
146
|
+
_m 342
|
|
147
|
+
ri 341
|
|
148
|
+
ha 340
|
|
149
|
+
eh 339
|
|
150
|
+
ten_ 338
|
|
151
|
+
es_ 336
|
|
152
|
+
_K 336
|
|
153
|
+
_und 335
|
|
154
|
+
ig 335
|
|
155
|
+
_b 335
|
|
156
|
+
hen 334
|
|
157
|
+
_und_ 332
|
|
158
|
+
_au 329
|
|
159
|
+
_B 327
|
|
160
|
+
_da 325
|
|
161
|
+
_zu 324
|
|
162
|
+
_in 322
|
|
163
|
+
at 321
|
|
164
|
+
us 318
|
|
165
|
+
wi 307
|
|
166
|
+
n, 305
|
|
167
|
+
n,_ 304
|
|
168
|
+
nn 304
|
|
169
|
+
te_ 301
|
|
170
|
+
eit 301
|
|
171
|
+
_h 300
|
|
172
|
+
ter 299
|
|
173
|
+
M 298
|
|
174
|
+
n. 295
|
|
175
|
+
� 294
|
|
176
|
+
ng_ 289
|
|
177
|
+
sche 289
|
|
178
|
+
- 283
|
|
179
|
+
rs 282
|
|
180
|
+
den_ 282
|
|
181
|
+
_si 280
|
|
182
|
+
G 280
|
|
183
|
+
im 278
|
|
184
|
+
_ge 277
|
|
185
|
+
chen 276
|
|
186
|
+
rd 273
|
|
187
|
+
_E 273
|
|
188
|
+
n._ 270
|
|
189
|
+
icht 270
|
|
190
|
+
rn 268
|
|
191
|
+
uf 267
|
|
192
|
+
isch 264
|
|
193
|
+
isc 264
|
|
194
|
+
nen 263
|
|
195
|
+
_in_ 262
|
|
196
|
+
_M 260
|
|
197
|
+
_er 257
|
|
198
|
+
ich_ 255
|
|
199
|
+
ac 253
|
|
200
|
+
lic 252
|
|
201
|
+
_G 252
|
|
202
|
+
ber 252
|
|
203
|
+
la 251
|
|
204
|
+
vo 251
|
|
205
|
+
eb 250
|
|
206
|
+
ke 249
|
|
207
|
+
F 248
|
|
208
|
+
as_ 248
|
|
209
|
+
hen_ 248
|
|
210
|
+
ach 245
|
|
211
|
+
en, 244
|
|
212
|
+
ung_ 243
|
|
213
|
+
lich 243
|
|
214
|
+
ste 243
|
|
215
|
+
en,_ 243
|
|
216
|
+
_k 241
|
|
217
|
+
ben 241
|
|
218
|
+
_f 241
|
|
219
|
+
en. 241
|
|
220
|
+
_be 239
|
|
221
|
+
it_ 239
|
|
222
|
+
L 238
|
|
223
|
+
_se 237
|
|
224
|
+
mi 236
|
|
225
|
+
ve 236
|
|
226
|
+
na 236
|
|
227
|
+
on_ 236
|
|
228
|
+
P 235
|
|
229
|
+
ss 234
|
|
230
|
+
ist 234
|
|
231
|
+
� 234
|
|
232
|
+
ht_ 233
|
|
233
|
+
ru 233
|
|
234
|
+
st_ 229
|
|
235
|
+
_F 229
|
|
236
|
+
ts 227
|
|
237
|
+
ab 226
|
|
238
|
+
W 226
|
|
239
|
+
ol 225
|
|
240
|
+
_eine 225
|
|
241
|
+
hi 225
|
|
242
|
+
so 224
|
|
243
|
+
em_ 223
|
|
244
|
+
"_ 223
|
|
245
|
+
ren 222
|
|
246
|
+
en._ 221
|
|
247
|
+
chen_ 221
|
|
248
|
+
R 221
|
|
249
|
+
ta 221
|
|
250
|
+
ere 220
|
|
251
|
+
ische 219
|
|
252
|
+
ers 218
|
|
253
|
+
ert 217
|
|
254
|
+
_P 217
|
|
255
|
+
tr 217
|
|
256
|
+
ed 215
|
|
257
|
+
ze 215
|
|
258
|
+
eg 215
|
|
259
|
+
ens 215
|
|
260
|
+
�r 213
|
|
261
|
+
ah 212
|
|
262
|
+
_vo 212
|
|
263
|
+
ne_ 211
|
|
264
|
+
cht_ 210
|
|
265
|
+
uc 209
|
|
266
|
+
_wi 209
|
|
267
|
+
nge 208
|
|
268
|
+
lle 208
|
|
269
|
+
fe 207
|
|
270
|
+
_L 207
|
|
271
|
+
ver 206
|
|
272
|
+
hl 205
|
|
273
|
+
V 204
|
|
274
|
+
ma 203
|
|
275
|
+
wa 203
|
|
276
|
+
auf 201
|
|
277
|
+
H 198
|
|
278
|
+
_W 195
|
|
279
|
+
T 195
|
|
280
|
+
nte 193
|
|
281
|
+
uch 193
|
|
282
|
+
l_ 192
|
|
283
|
+
sei 192
|
|
284
|
+
nen_ 190
|
|
285
|
+
u_ 189
|
|
286
|
+
_den 189
|
|
287
|
+
_al 189
|
|
288
|
+
_V 188
|
|
289
|
+
t. 188
|
|
290
|
+
lte 187
|
|
291
|
+
ut 186
|
|
292
|
+
ent 184
|
|
293
|
+
sich 183
|
|
294
|
+
sic 183
|
|
295
|
+
il 183
|
|
296
|
+
ier 182
|
|
297
|
+
am 181
|
|
298
|
+
gen_ 180
|
|
299
|
+
sen 179
|
|
300
|
+
f� 178
|
|
301
|
+
um 178
|
|
302
|
+
t._ 177
|
|
303
|
+
f_ 174
|
|
304
|
+
he_ 174
|
|
305
|
+
ner 174
|
|
306
|
+
nst 174
|
|
307
|
+
ls 174
|
|
308
|
+
_sei 173
|
|
309
|
+
ro 173
|
|
310
|
+
ir 173
|
|
311
|
+
ebe 173
|
|
312
|
+
mm 173
|
|
313
|
+
ag 172
|
|
314
|
+
ern 169
|
|
315
|
+
t,_ 169
|
|
316
|
+
t, 169
|
|
317
|
+
eu 169
|
|
318
|
+
ft 168
|
|
319
|
+
icht_ 167
|
|
320
|
+
hre 167
|
|
321
|
+
Be 166
|
|
322
|
+
nz 165
|
|
323
|
+
nder 165
|
|
324
|
+
_T 164
|
|
325
|
+
_den_ 164
|
|
326
|
+
iche 163
|
|
327
|
+
tt 163
|
|
328
|
+
zu_ 162
|
|
329
|
+
and 162
|
|
330
|
+
J 161
|
|
331
|
+
rde 160
|
|
332
|
+
rei 160
|
|
333
|
+
_we 159
|
|
334
|
+
_H 159
|
|
335
|
+
ige 159
|
|
336
|
+
_Be 158
|
|
337
|
+
rte 157
|
|
338
|
+
hei 156
|
|
339
|
+
das 155
|
|
340
|
+
aus 155
|
|
341
|
+
che_ 154
|
|
342
|
+
_das 154
|
|
343
|
+
_zu_ 154
|
|
344
|
+
tz 154
|
|
345
|
+
_ni 153
|
|
346
|
+
das_ 153
|
|
347
|
+
_R 153
|
|
348
|
+
N 153
|
|
349
|
+
des 153
|
|
350
|
+
_ve 153
|
|
351
|
+
_J 152
|
|
352
|
+
I 152
|
|
353
|
+
_das_ 152
|
|
354
|
+
men 151
|
|
355
|
+
_so 151
|
|
356
|
+
_ver 151
|
|
357
|
+
_auf 150
|
|
358
|
+
ine_ 150
|
|
359
|
+
_ha 150
|
|
360
|
+
rg 149
|
|
361
|
+
ind 148
|
|
362
|
+
eben 148
|
|
363
|
+
kt 147
|
|
364
|
+
mit 147
|
|
365
|
+
_an 147
|
|
366
|
+
her 146
|
|
367
|
+
Ge 146
|
|
368
|
+
Sc 145
|
|
369
|
+
_sich 145
|
|
370
|
+
U 145
|
|
371
|
+
Sch 145
|
|
372
|
+
_sic 145
|
|
373
|
+
end 145
|
|
374
|
+
Di 144
|
|
375
|
+
abe 143
|
|
376
|
+
ck 143
|
|
377
|
+
sse 142
|
|
378
|
+
�r_ 142
|
|
379
|
+
ell 142
|
|
380
|
+
ik 141
|
|
381
|
+
o_ 141
|
|
382
|
+
nic 141
|
|
383
|
+
nich 141
|
|
384
|
+
sa 141
|
|
385
|
+
_f� 140
|
|
386
|
+
hn 140
|
|
387
|
+
zi 140
|
|
388
|
+
no 140
|
|
389
|
+
nicht 140
|
|
390
|
+
im_ 139
|
|
391
|
+
von_ 139
|
|
392
|
+
von 139
|
|
393
|
+
_nic 139
|
|
394
|
+
_nich 139
|
|
395
|
+
eine_ 139
|
|
396
|
+
oc 138
|
|
397
|
+
wei 138
|
|
398
|
+
io 138
|
|
399
|
+
schen 138
|
|
400
|
+
gt 138
|