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
|
+
� 17815
|
2
|
+
_ 14534
|
3
|
+
�� 4035
|
4
|
+
�_ 3087
|
5
|
+
� 2180
|
6
|
+
� 1762
|
7
|
+
�� 1669
|
8
|
+
� 1654
|
9
|
+
� 1534
|
10
|
+
� 1480
|
11
|
+
�� 1433
|
12
|
+
� 1342
|
13
|
+
� 1289
|
14
|
+
� 1237
|
15
|
+
� 1163
|
16
|
+
� 1158
|
17
|
+
� 1153
|
18
|
+
��_ 1133
|
19
|
+
� 1099
|
20
|
+
� 1084
|
21
|
+
� 1062
|
22
|
+
� 1059
|
23
|
+
�_ 1054
|
24
|
+
�� 1054
|
25
|
+
�� 1050
|
26
|
+
��� 1039
|
27
|
+
�� 989
|
28
|
+
� 983
|
29
|
+
�� 968
|
30
|
+
� 965
|
31
|
+
� 949
|
32
|
+
_� 936
|
33
|
+
. 936
|
34
|
+
�� 915
|
35
|
+
�� 859
|
36
|
+
�� 842
|
37
|
+
�� 838
|
38
|
+
�� 836
|
39
|
+
�� 769
|
40
|
+
�� 764
|
41
|
+
� 710
|
42
|
+
�� 710
|
43
|
+
�� 684
|
44
|
+
��� 681
|
45
|
+
._ 670
|
46
|
+
��_ 637
|
47
|
+
� 609
|
48
|
+
�� 578
|
49
|
+
_� 578
|
50
|
+
_�� 569
|
51
|
+
_� 543
|
52
|
+
�� 530
|
53
|
+
_� 530
|
54
|
+
�� 524
|
55
|
+
_� 523
|
56
|
+
� 511
|
57
|
+
� 504
|
58
|
+
�_ 495
|
59
|
+
��_ 477
|
60
|
+
��� 476
|
61
|
+
�� 474
|
62
|
+
_� 474
|
63
|
+
_� 457
|
64
|
+
_�� 447
|
65
|
+
_�� 447
|
66
|
+
���_ 446
|
67
|
+
�� 444
|
68
|
+
� 438
|
69
|
+
�� 423
|
70
|
+
��� 422
|
71
|
+
�� 409
|
72
|
+
�� 388
|
73
|
+
�� 387
|
74
|
+
��� 381
|
75
|
+
�_ 366
|
76
|
+
��� 359
|
77
|
+
� 339
|
78
|
+
��� 334
|
79
|
+
_�� 332
|
80
|
+
�� 331
|
81
|
+
�� 324
|
82
|
+
��� 320
|
83
|
+
_�� 320
|
84
|
+
��� 318
|
85
|
+
� 315
|
86
|
+
_� 315
|
87
|
+
��_ 314
|
88
|
+
� 313
|
89
|
+
�� 306
|
90
|
+
��_ 303
|
91
|
+
�� 301
|
92
|
+
�� 297
|
93
|
+
� 297
|
94
|
+
��� 295
|
95
|
+
�� 284
|
96
|
+
�� 280
|
97
|
+
� 274
|
98
|
+
�_ 272
|
99
|
+
��� 270
|
100
|
+
��� 268
|
101
|
+
���_ 268
|
102
|
+
�� 264
|
103
|
+
�� 264
|
104
|
+
�� 263
|
105
|
+
, 258
|
106
|
+
���� 256
|
107
|
+
���� 256
|
108
|
+
���_ 256
|
109
|
+
,_ 255
|
110
|
+
��� 255
|
111
|
+
� 249
|
112
|
+
��� 247
|
113
|
+
��� 243
|
114
|
+
��� 241
|
115
|
+
_� 234
|
116
|
+
_�� 233
|
117
|
+
��� 232
|
118
|
+
�� 232
|
119
|
+
�� 231
|
120
|
+
��_ 231
|
121
|
+
��� 230
|
122
|
+
��� 228
|
123
|
+
� 227
|
124
|
+
� 226
|
125
|
+
��� 225
|
126
|
+
�_ 223
|
127
|
+
��� 221
|
128
|
+
�� 220
|
129
|
+
_� 220
|
130
|
+
�� 219
|
131
|
+
��_ 218
|
132
|
+
��� 217
|
133
|
+
�. 216
|
134
|
+
�� 215
|
135
|
+
_�� 213
|
136
|
+
.. 209
|
137
|
+
_��� 209
|
138
|
+
���� 205
|
139
|
+
��� 205
|
140
|
+
���� 204
|
141
|
+
� 204
|
142
|
+
��� 203
|
143
|
+
����_ 202
|
144
|
+
�_ 202
|
145
|
+
��� 201
|
146
|
+
� 198
|
147
|
+
_� 198
|
148
|
+
�� 193
|
149
|
+
_� 191
|
150
|
+
��� 190
|
151
|
+
�._ 189
|
152
|
+
��� 188
|
153
|
+
�� 188
|
154
|
+
���� 187
|
155
|
+
� 186
|
156
|
+
�� 186
|
157
|
+
� 185
|
158
|
+
��_ 180
|
159
|
+
��_ 180
|
160
|
+
_�� 180
|
161
|
+
�� 179
|
162
|
+
� 178
|
163
|
+
_��� 176
|
164
|
+
_��� 175
|
165
|
+
_���� 175
|
166
|
+
�� 175
|
167
|
+
_�� 175
|
168
|
+
��� 174
|
169
|
+
��� 171
|
170
|
+
�� 170
|
171
|
+
_� 170
|
172
|
+
... 168
|
173
|
+
��� 167
|
174
|
+
��� 166
|
175
|
+
_� 164
|
176
|
+
��� 164
|
177
|
+
��� 163
|
178
|
+
���� 163
|
179
|
+
�� 162
|
180
|
+
��� 162
|
181
|
+
_��� 162
|
182
|
+
����_ 161
|
183
|
+
�� 160
|
184
|
+
��_ 159
|
185
|
+
���� 159
|
186
|
+
��� 157
|
187
|
+
��� 154
|
188
|
+
�� 154
|
189
|
+
_�� 154
|
190
|
+
_� 154
|
191
|
+
�� 153
|
192
|
+
��� 153
|
193
|
+
�� 151
|
194
|
+
��� 151
|
195
|
+
_� 151
|
196
|
+
���� 150
|
197
|
+
�� 150
|
198
|
+
�� 150
|
199
|
+
�. 149
|
200
|
+
_���� 149
|
201
|
+
�� 148
|
202
|
+
��� 148
|
203
|
+
�� 147
|
204
|
+
�� 147
|
205
|
+
ţ 146
|
206
|
+
���_ 146
|
207
|
+
_�� 145
|
208
|
+
�._ 145
|
209
|
+
��� 144
|
210
|
+
�� 143
|
211
|
+
� 142
|
212
|
+
� 140
|
213
|
+
���� 140
|
214
|
+
��� 139
|
215
|
+
�� 139
|
216
|
+
��� 137
|
217
|
+
��� 136
|
218
|
+
_�� 136
|
219
|
+
�� 136
|
220
|
+
_�� 135
|
221
|
+
�. 135
|
222
|
+
��� 135
|
223
|
+
' 135
|
224
|
+
�ţ 134
|
225
|
+
_�� 132
|
226
|
+
���� 131
|
227
|
+
����_ 131
|
228
|
+
��� 129
|
229
|
+
'_ 129
|
230
|
+
_��� 129
|
231
|
+
�._ 128
|
232
|
+
�� 127
|
233
|
+
.... 127
|
234
|
+
� 127
|
235
|
+
�� 126
|
236
|
+
��� 125
|
237
|
+
_�� 124
|
238
|
+
��_ 123
|
239
|
+
���� 123
|
240
|
+
� 122
|
241
|
+
; 122
|
242
|
+
_�� 121
|
243
|
+
_��� 119
|
244
|
+
� 118
|
245
|
+
��� 115
|
246
|
+
��� 114
|
247
|
+
��_ 114
|
248
|
+
��� 113
|
249
|
+
���� 113
|
250
|
+
��� 113
|
251
|
+
b 113
|
252
|
+
��� 112
|
253
|
+
_' 112
|
254
|
+
s 111
|
255
|
+
& 111
|
256
|
+
��� 111
|
257
|
+
��� 111
|
258
|
+
���� 111
|
259
|
+
p 111
|
260
|
+
� 111
|
261
|
+
_� 110
|
262
|
+
����� 110
|
263
|
+
bs 109
|
264
|
+
�� 109
|
265
|
+
n 109
|
266
|
+
� 109
|
267
|
+
_��� 108
|
268
|
+
&n 107
|
269
|
+
bsp; 107
|
270
|
+
nbsp; 107
|
271
|
+
sp; 107
|
272
|
+
nb 107
|
273
|
+
bsp 107
|
274
|
+
nbs 107
|
275
|
+
sp 107
|
276
|
+
nbsp 107
|
277
|
+
&nb 107
|
278
|
+
  107
|
279
|
+
p; 107
|
280
|
+
&nbs 107
|
281
|
+
���� 106
|
282
|
+
_'_ 106
|
283
|
+
��� 106
|
284
|
+
��� 106
|
285
|
+
��� 106
|
286
|
+
���_ 105
|
287
|
+
��� 104
|
288
|
+
��� 104
|
289
|
+
�� 104
|
290
|
+
�� 104
|
291
|
+
_�� 103
|
292
|
+
���� 103
|
293
|
+
�� 103
|
294
|
+
��� 102
|
295
|
+
���� 101
|
296
|
+
���� 100
|
297
|
+
���� 99
|
298
|
+
�, 99
|
299
|
+
_� 98
|
300
|
+
�,_ 98
|
301
|
+
_�ţ 98
|
302
|
+
��� 98
|
303
|
+
����_ 98
|
304
|
+
_��� 97
|
305
|
+
;& 97
|
306
|
+
_��� 97
|
307
|
+
���� 97
|
308
|
+
_���� 96
|
309
|
+
�� 96
|
310
|
+
����� 96
|
311
|
+
��� 96
|
312
|
+
� 96
|
313
|
+
;&nb 95
|
314
|
+
p;&nb 95
|
315
|
+
;&n 95
|
316
|
+
p;& 95
|
317
|
+
;&nbs 95
|
318
|
+
bsp;& 95
|
319
|
+
..... 95
|
320
|
+
��_ 95
|
321
|
+
sp;&n 95
|
322
|
+
sp;& 95
|
323
|
+
p;&n 95
|
324
|
+
� 94
|
325
|
+
_� 94
|
326
|
+
� 94
|
327
|
+
����_ 94
|
328
|
+
���� 93
|
329
|
+
��� 93
|
330
|
+
���_ 93
|
331
|
+
��_ 93
|
332
|
+
��� 93
|
333
|
+
_� 92
|
334
|
+
�� 92
|
335
|
+
_��� 92
|
336
|
+
���_ 92
|
337
|
+
��� 92
|
338
|
+
���_ 91
|
339
|
+
�� 91
|
340
|
+
��_ 90
|
341
|
+
_��� 90
|
342
|
+
_��� 90
|
343
|
+
����� 90
|
344
|
+
� 90
|
345
|
+
���� 90
|
346
|
+
�� 89
|
347
|
+
�� 89
|
348
|
+
���� 89
|
349
|
+
���_ 89
|
350
|
+
�� 89
|
351
|
+
��� 89
|
352
|
+
���� 89
|
353
|
+
�� 89
|
354
|
+
��� 89
|
355
|
+
_�� 88
|
356
|
+
�� 88
|
357
|
+
����� 88
|
358
|
+
_�� 88
|
359
|
+
_��� 88
|
360
|
+
���� 87
|
361
|
+
�� 87
|
362
|
+
�� 87
|
363
|
+
����� 87
|
364
|
+
_� 87
|
365
|
+
�� 87
|
366
|
+
���� 87
|
367
|
+
���� 86
|
368
|
+
���_ 86
|
369
|
+
_��� 85
|
370
|
+
��� 85
|
371
|
+
�� 85
|
372
|
+
_� 85
|
373
|
+
��� 85
|
374
|
+
_���� 84
|
375
|
+
�� 84
|
376
|
+
���� 83
|
377
|
+
��� 83
|
378
|
+
��� 83
|
379
|
+
�� 83
|
380
|
+
��� 83
|
381
|
+
���_ 83
|
382
|
+
_� 82
|
383
|
+
_���� 82
|
384
|
+
����_ 82
|
385
|
+
���_ 82
|
386
|
+
����� 82
|
387
|
+
���� 82
|
388
|
+
���_ 82
|
389
|
+
_�� 82
|
390
|
+
���_ 82
|
391
|
+
���_ 81
|
392
|
+
�� 81
|
393
|
+
�._ 80
|
394
|
+
��� 80
|
395
|
+
_��� 80
|
396
|
+
�. 80
|
397
|
+
�� 79
|
398
|
+
_�� 79
|
399
|
+
����_ 79
|
400
|
+
� 79
|
@@ -0,0 +1,400 @@
|
|
1
|
+
_ 3156
|
2
|
+
' 991
|
3
|
+
a 829
|
4
|
+
t 788
|
5
|
+
k 788
|
6
|
+
n 752
|
7
|
+
e 640
|
8
|
+
h 602
|
9
|
+
� 551
|
10
|
+
s 495
|
11
|
+
w 466
|
12
|
+
� 422
|
13
|
+
y 403
|
14
|
+
u 397
|
15
|
+
'_ 368
|
16
|
+
_n 330
|
17
|
+
i 269
|
18
|
+
. 269
|
19
|
+
._ 240
|
20
|
+
e' 238
|
21
|
+
� 219
|
22
|
+
a' 209
|
23
|
+
ne 209
|
24
|
+
e_ 194
|
25
|
+
_ne 184
|
26
|
+
wa 172
|
27
|
+
_k 164
|
28
|
+
kw 162
|
29
|
+
� 154
|
30
|
+
e'_ 146
|
31
|
+
_t 145
|
32
|
+
't 141
|
33
|
+
" 141
|
34
|
+
�' 134
|
35
|
+
� 132
|
36
|
+
_h 131
|
37
|
+
� 129
|
38
|
+
ak 129
|
39
|
+
ne_ 126
|
40
|
+
ta 123
|
41
|
+
_ne_ 123
|
42
|
+
at 121
|
43
|
+
u' 121
|
44
|
+
hu 118
|
45
|
+
_u 108
|
46
|
+
ka 107
|
47
|
+
� 106
|
48
|
+
n� 105
|
49
|
+
N 103
|
50
|
+
�' 100
|
51
|
+
hs 95
|
52
|
+
ha 95
|
53
|
+
te 94
|
54
|
+
ya 93
|
55
|
+
_� 92
|
56
|
+
kh 90
|
57
|
+
'k 86
|
58
|
+
� 85
|
59
|
+
� 84
|
60
|
+
ni 84
|
61
|
+
'. 84
|
62
|
+
w� 83
|
63
|
+
ny 83
|
64
|
+
sh 80
|
65
|
+
_N 80
|
66
|
+
'._ 76
|
67
|
+
�_ 76
|
68
|
+
k� 72
|
69
|
+
_" 71
|
70
|
+
�n 70
|
71
|
+
th 69
|
72
|
+
yu 66
|
73
|
+
_w 66
|
74
|
+
�h 66
|
75
|
+
t_ 66
|
76
|
+
�_ 66
|
77
|
+
Ne 65
|
78
|
+
Ne' 65
|
79
|
+
's 64
|
80
|
+
ne' 64
|
81
|
+
"_ 64
|
82
|
+
_. 63
|
83
|
+
_._ 61
|
84
|
+
Ne'_ 61
|
85
|
+
, 60
|
86
|
+
ne'_ 58
|
87
|
+
n� 58
|
88
|
+
kwa 57
|
89
|
+
_ne' 57
|
90
|
+
�t 57
|
91
|
+
a't 57
|
92
|
+
ek 56
|
93
|
+
s_ 56
|
94
|
+
�t 55
|
95
|
+
i' 55
|
96
|
+
_hu 54
|
97
|
+
T 54
|
98
|
+
�_ 54
|
99
|
+
_s 54
|
100
|
+
_Ne 53
|
101
|
+
t� 53
|
102
|
+
t� 53
|
103
|
+
_Ne' 53
|
104
|
+
_ne'_ 53
|
105
|
+
ht 53
|
106
|
+
- 53
|
107
|
+
ts 52
|
108
|
+
ya' 52
|
109
|
+
�'_ 51
|
110
|
+
_wa 51
|
111
|
+
_Ne'_ 51
|
112
|
+
'� 50
|
113
|
+
�y 50
|
114
|
+
_ka 50
|
115
|
+
as 50
|
116
|
+
n� 49
|
117
|
+
un 49
|
118
|
+
�_ 49
|
119
|
+
ty 48
|
120
|
+
hu_ 48
|
121
|
+
ke 48
|
122
|
+
u_ 48
|
123
|
+
,_ 47
|
124
|
+
y� 46
|
125
|
+
he 46
|
126
|
+
ye 46
|
127
|
+
k� 45
|
128
|
+
si 45
|
129
|
+
n� 44
|
130
|
+
khu 44
|
131
|
+
a'k 44
|
132
|
+
_a 43
|
133
|
+
�k 43
|
134
|
+
wat 42
|
135
|
+
'� 42
|
136
|
+
n�' 42
|
137
|
+
w� 42
|
138
|
+
aw 41
|
139
|
+
an 41
|
140
|
+
we 41
|
141
|
+
�t 41
|
142
|
+
i_ 41
|
143
|
+
_kh 41
|
144
|
+
tak 41
|
145
|
+
_te 41
|
146
|
+
ik 41
|
147
|
+
_khu 40
|
148
|
+
�s 40
|
149
|
+
y� 40
|
150
|
+
k_ 39
|
151
|
+
khu_ 39
|
152
|
+
yu' 38
|
153
|
+
h� 38
|
154
|
+
w�n 38
|
155
|
+
n- 38
|
156
|
+
�hs 38
|
157
|
+
_ha 38
|
158
|
+
wa' 38
|
159
|
+
_n- 37
|
160
|
+
sa 37
|
161
|
+
? 37
|
162
|
+
_T 37
|
163
|
+
�' 37
|
164
|
+
_un 36
|
165
|
+
h� 36
|
166
|
+
w� 36
|
167
|
+
ah 36
|
168
|
+
_khu_ 35
|
169
|
+
iy 35
|
170
|
+
�k 35
|
171
|
+
ut 35
|
172
|
+
�k 35
|
173
|
+
�h 35
|
174
|
+
te' 35
|
175
|
+
u'_ 35
|
176
|
+
_k� 34
|
177
|
+
y�_ 34
|
178
|
+
ha' 34
|
179
|
+
st 34
|
180
|
+
ti 34
|
181
|
+
ta' 34
|
182
|
+
u't 33
|
183
|
+
ya't 33
|
184
|
+
't_ 33
|
185
|
+
'�_ 33
|
186
|
+
akw 33
|
187
|
+
�k 33
|
188
|
+
n�y 32
|
189
|
+
'ta 32
|
190
|
+
ku 32
|
191
|
+
ui 32
|
192
|
+
_sh 32
|
193
|
+
aa 31
|
194
|
+
�n 31
|
195
|
+
ay 31
|
196
|
+
�n� 31
|
197
|
+
� 30
|
198
|
+
se 30
|
199
|
+
tw 30
|
200
|
+
y� 30
|
201
|
+
(_ 29
|
202
|
+
_(_ 29
|
203
|
+
_)_ 29
|
204
|
+
us 29
|
205
|
+
_�hs 29
|
206
|
+
( 29
|
207
|
+
k� 29
|
208
|
+
_�h 29
|
209
|
+
ae 29
|
210
|
+
h� 29
|
211
|
+
_) 29
|
212
|
+
)_ 29
|
213
|
+
_( 29
|
214
|
+
sy 29
|
215
|
+
) 29
|
216
|
+
�� 28
|
217
|
+
�n 28
|
218
|
+
sk 28
|
219
|
+
t� 28
|
220
|
+
t� 28
|
221
|
+
tk 28
|
222
|
+
�n 28
|
223
|
+
k�_ 28
|
224
|
+
a_ 28
|
225
|
+
�n 27
|
226
|
+
_huik 27
|
227
|
+
�n 27
|
228
|
+
_hui 27
|
229
|
+
kw� 27
|
230
|
+
huik 27
|
231
|
+
�k 27
|
232
|
+
hui 27
|
233
|
+
uik 27
|
234
|
+
_na 27
|
235
|
+
na 27
|
236
|
+
a'_ 26
|
237
|
+
uik� 26
|
238
|
+
_ni 26
|
239
|
+
." 26
|
240
|
+
�� 26
|
241
|
+
wi 26
|
242
|
+
huik� 26
|
243
|
+
ik� 26
|
244
|
+
nya 25
|
245
|
+
."_ 25
|
246
|
+
?" 25
|
247
|
+
t�' 25
|
248
|
+
�yu 25
|
249
|
+
aw� 25
|
250
|
+
sn 25
|
251
|
+
n�_ 24
|
252
|
+
�'_ 24
|
253
|
+
ik�_ 24
|
254
|
+
ekh 24
|
255
|
+
'ke 24
|
256
|
+
uik�_ 24
|
257
|
+
?"_ 24
|
258
|
+
tek 24
|
259
|
+
�t 24
|
260
|
+
', 24
|
261
|
+
"N 23
|
262
|
+
_ta 23
|
263
|
+
'a 23
|
264
|
+
hk 23
|
265
|
+
t� 23
|
266
|
+
tsi 23
|
267
|
+
w� 23
|
268
|
+
yu'_ 23
|
269
|
+
_"N 23
|
270
|
+
�yu' 23
|
271
|
+
n�yu 23
|
272
|
+
a'ta 23
|
273
|
+
�' 23
|
274
|
+
n�yu' 23
|
275
|
+
sh� 22
|
276
|
+
w�n� 22
|
277
|
+
kwa' 22
|
278
|
+
�n� 22
|
279
|
+
kw� 22
|
280
|
+
_u' 22
|
281
|
+
ey 22
|
282
|
+
�n�yu 22
|
283
|
+
K 22
|
284
|
+
ai 22
|
285
|
+
_sh� 22
|
286
|
+
�w 22
|
287
|
+
a� 22
|
288
|
+
�ht 22
|
289
|
+
�n�y 22
|
290
|
+
kwe 22
|
291
|
+
w�n�y 22
|
292
|
+
_he 22
|
293
|
+
_te' 21
|
294
|
+
�n 21
|
295
|
+
s. 21
|
296
|
+
n�h 21
|
297
|
+
�� 21
|
298
|
+
_�k 21
|
299
|
+
'sh 21
|
300
|
+
k�' 21
|
301
|
+
ht� 21
|
302
|
+
H 21
|
303
|
+
ata 21
|
304
|
+
U 20
|
305
|
+
'h 20
|
306
|
+
_ha' 20
|
307
|
+
��' 20
|
308
|
+
ae_ 20
|
309
|
+
a'ke 20
|
310
|
+
�ny 20
|
311
|
+
un� 20
|
312
|
+
we' 20
|
313
|
+
w�' 20
|
314
|
+
i'_ 20
|
315
|
+
k�s 20
|
316
|
+
ya'ta 19
|
317
|
+
es 19
|
318
|
+
aw�n� 19
|
319
|
+
h�_ 19
|
320
|
+
uk 19
|
321
|
+
aw�n 19
|
322
|
+
hw 19
|
323
|
+
�'. 19
|
324
|
+
�' 19
|
325
|
+
t�' 19
|
326
|
+
s� 19
|
327
|
+
�'� 19
|
328
|
+
�'._ 19
|
329
|
+
'�� 19
|
330
|
+
hkw 19
|
331
|
+
-a 19
|
332
|
+
twa 19
|
333
|
+
'kw 18
|
334
|
+
he_ 18
|
335
|
+
_K 18
|
336
|
+
n�t 18
|
337
|
+
hsa 18
|
338
|
+
hsi 18
|
339
|
+
�ni 18
|
340
|
+
aya 18
|
341
|
+
is 18
|
342
|
+
��' 18
|
343
|
+
k� 18
|
344
|
+
skw 18
|
345
|
+
uw 18
|
346
|
+
',_ 18
|
347
|
+
e't 18
|
348
|
+
k�� 18
|
349
|
+
ka' 18
|
350
|
+
nae 17
|
351
|
+
sh�_ 17
|
352
|
+
sat 17
|
353
|
+
niy 17
|
354
|
+
�ts 17
|
355
|
+
ath 17
|
356
|
+
ye' 17
|
357
|
+
�_ 17
|
358
|
+
'��' 17
|
359
|
+
'u 17
|
360
|
+
_�t 17
|
361
|
+
�s_ 17
|
362
|
+
_k�s 17
|
363
|
+
_y 17
|
364
|
+
kak 17
|
365
|
+
�'� 17
|
366
|
+
kat 17
|
367
|
+
_th 17
|
368
|
+
'�_ 17
|
369
|
+
�t 17
|
370
|
+
u'k 17
|
371
|
+
_H 17
|
372
|
+
tekh 17
|
373
|
+
s._ 17
|
374
|
+
w� 17
|
375
|
+
_nae 17
|
376
|
+
kw� 17
|
377
|
+
_sh�_ 17
|
378
|
+
y� 17
|
379
|
+
�te 16
|
380
|
+
sha 16
|
381
|
+
ke_ 16
|
382
|
+
k. 16
|
383
|
+
si' 16
|
384
|
+
h�' 16
|
385
|
+
y� 16
|
386
|
+
hta 16
|
387
|
+
kn 16
|
388
|
+
_nae_ 16
|
389
|
+
hse 16
|
390
|
+
k� 16
|
391
|
+
�'�_ 16
|
392
|
+
un� 16
|
393
|
+
nya' 16
|
394
|
+
nae_ 16
|
395
|
+
n� 16
|
396
|
+
�' 16
|
397
|
+
�s 16
|
398
|
+
t� 16
|
399
|
+
a's 16
|
400
|
+
a'u 16
|