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
|
+
_ 21836
|
2
|
+
� 5818
|
3
|
+
� 4506
|
4
|
+
� 4258
|
5
|
+
� 3769
|
6
|
+
� 3394
|
7
|
+
� 3254
|
8
|
+
� 2594
|
9
|
+
� 2470
|
10
|
+
� 2346
|
11
|
+
� 2227
|
12
|
+
� 1798
|
13
|
+
� 1709
|
14
|
+
� 1673
|
15
|
+
� 1638
|
16
|
+
� 1377
|
17
|
+
, 1187
|
18
|
+
,_ 1172
|
19
|
+
�_ 1160
|
20
|
+
� 1059
|
21
|
+
� 1024
|
22
|
+
� 1006
|
23
|
+
�_ 966
|
24
|
+
� 945
|
25
|
+
_� 937
|
26
|
+
� 910
|
27
|
+
_� 907
|
28
|
+
�_ 896
|
29
|
+
�� 878
|
30
|
+
� 856
|
31
|
+
_� 828
|
32
|
+
_� 818
|
33
|
+
�_ 801
|
34
|
+
� 795
|
35
|
+
. 789
|
36
|
+
._ 761
|
37
|
+
�� 655
|
38
|
+
�� 617
|
39
|
+
_� 616
|
40
|
+
�� 575
|
41
|
+
� 568
|
42
|
+
� 565
|
43
|
+
�� 549
|
44
|
+
�� 526
|
45
|
+
�� 524
|
46
|
+
�_ 522
|
47
|
+
_� 521
|
48
|
+
_� 497
|
49
|
+
_� 496
|
50
|
+
� 484
|
51
|
+
_�� 477
|
52
|
+
_� 477
|
53
|
+
�� 472
|
54
|
+
�� 470
|
55
|
+
�_ 461
|
56
|
+
�� 456
|
57
|
+
�� 454
|
58
|
+
�� 452
|
59
|
+
�� 432
|
60
|
+
�� 431
|
61
|
+
�� 425
|
62
|
+
� 413
|
63
|
+
�� 403
|
64
|
+
�� 402
|
65
|
+
_� 396
|
66
|
+
_� 396
|
67
|
+
�� 395
|
68
|
+
�� 388
|
69
|
+
��_ 384
|
70
|
+
�_ 383
|
71
|
+
_�� 378
|
72
|
+
_�_ 375
|
73
|
+
�� 369
|
74
|
+
�� 367
|
75
|
+
_�� 365
|
76
|
+
�_ 364
|
77
|
+
�� 363
|
78
|
+
�� 357
|
79
|
+
�_ 357
|
80
|
+
�� 353
|
81
|
+
�� 352
|
82
|
+
�� 350
|
83
|
+
�� 344
|
84
|
+
�� 344
|
85
|
+
�_ 343
|
86
|
+
�� 338
|
87
|
+
�� 337
|
88
|
+
�� 334
|
89
|
+
�� 330
|
90
|
+
�� 328
|
91
|
+
�� 326
|
92
|
+
�� 326
|
93
|
+
�� 323
|
94
|
+
- 322
|
95
|
+
�� 320
|
96
|
+
�� 317
|
97
|
+
� 312
|
98
|
+
�� 308
|
99
|
+
�� 308
|
100
|
+
�_ 302
|
101
|
+
_� 299
|
102
|
+
�_ 296
|
103
|
+
�� 292
|
104
|
+
��_ 292
|
105
|
+
�� 291
|
106
|
+
�� 291
|
107
|
+
_� 291
|
108
|
+
�� 286
|
109
|
+
�� 283
|
110
|
+
�� 283
|
111
|
+
_�� 274
|
112
|
+
�� 264
|
113
|
+
�� 263
|
114
|
+
�_ 260
|
115
|
+
�� 253
|
116
|
+
_- 245
|
117
|
+
_� 245
|
118
|
+
�_ 244
|
119
|
+
�� 240
|
120
|
+
��_ 238
|
121
|
+
�� 235
|
122
|
+
_��_ 235
|
123
|
+
�� 233
|
124
|
+
�� 229
|
125
|
+
-_ 225
|
126
|
+
�� 219
|
127
|
+
_�_ 217
|
128
|
+
�� 217
|
129
|
+
�� 215
|
130
|
+
�� 215
|
131
|
+
�� 211
|
132
|
+
�� 211
|
133
|
+
�� 211
|
134
|
+
�� 209
|
135
|
+
��_ 209
|
136
|
+
�� 208
|
137
|
+
_� 206
|
138
|
+
� 206
|
139
|
+
�� 205
|
140
|
+
� 205
|
141
|
+
��� 203
|
142
|
+
�� 203
|
143
|
+
�� 202
|
144
|
+
_-_ 202
|
145
|
+
_�� 199
|
146
|
+
_��� 199
|
147
|
+
�� 197
|
148
|
+
�� 197
|
149
|
+
��_ 197
|
150
|
+
_� 195
|
151
|
+
�� 192
|
152
|
+
_� 191
|
153
|
+
�� 190
|
154
|
+
�� 190
|
155
|
+
�� 188
|
156
|
+
�� 188
|
157
|
+
�� 185
|
158
|
+
_�� 184
|
159
|
+
_� 183
|
160
|
+
�� 182
|
161
|
+
_�� 181
|
162
|
+
�� 175
|
163
|
+
� 174
|
164
|
+
_�� 172
|
165
|
+
�� 170
|
166
|
+
_� 169
|
167
|
+
��_ 168
|
168
|
+
! 168
|
169
|
+
���_ 165
|
170
|
+
�� 165
|
171
|
+
��_ 164
|
172
|
+
�� 164
|
173
|
+
�_ 164
|
174
|
+
�� 163
|
175
|
+
��� 163
|
176
|
+
� 162
|
177
|
+
_���_ 162
|
178
|
+
_�� 159
|
179
|
+
�� 158
|
180
|
+
�� 157
|
181
|
+
�� 156
|
182
|
+
�� 154
|
183
|
+
�� 154
|
184
|
+
��� 153
|
185
|
+
�� 153
|
186
|
+
�� 153
|
187
|
+
�� 153
|
188
|
+
�� 152
|
189
|
+
�� 150
|
190
|
+
_��_ 149
|
191
|
+
�_ 148
|
192
|
+
�� 148
|
193
|
+
_�� 146
|
194
|
+
��_ 146
|
195
|
+
��_ 146
|
196
|
+
_� 144
|
197
|
+
��� 143
|
198
|
+
�� 141
|
199
|
+
�_ 141
|
200
|
+
��_ 141
|
201
|
+
!_ 139
|
202
|
+
�� 139
|
203
|
+
�� 139
|
204
|
+
�� 137
|
205
|
+
��� 136
|
206
|
+
��� 136
|
207
|
+
���_ 135
|
208
|
+
_�� 134
|
209
|
+
_�� 131
|
210
|
+
�� 131
|
211
|
+
��� 130
|
212
|
+
��_ 129
|
213
|
+
�, 128
|
214
|
+
_�� 128
|
215
|
+
�,_ 127
|
216
|
+
�� 127
|
217
|
+
�� 126
|
218
|
+
�� 126
|
219
|
+
_�� 126
|
220
|
+
�� 125
|
221
|
+
�� 125
|
222
|
+
� 124
|
223
|
+
�� 123
|
224
|
+
�� 122
|
225
|
+
_�� 122
|
226
|
+
_�� 121
|
227
|
+
_�� 120
|
228
|
+
��� 120
|
229
|
+
�� 120
|
230
|
+
�� 120
|
231
|
+
_� 119
|
232
|
+
��� 119
|
233
|
+
��� 119
|
234
|
+
�� 118
|
235
|
+
� 117
|
236
|
+
_��� 117
|
237
|
+
�, 115
|
238
|
+
�� 115
|
239
|
+
_�� 115
|
240
|
+
��_ 114
|
241
|
+
_� 114
|
242
|
+
�,_ 114
|
243
|
+
_� 113
|
244
|
+
_� 113
|
245
|
+
�� 112
|
246
|
+
��� 112
|
247
|
+
��� 110
|
248
|
+
�� 110
|
249
|
+
_�� 110
|
250
|
+
�� 109
|
251
|
+
�� 109
|
252
|
+
��� 109
|
253
|
+
_��� 109
|
254
|
+
_�� 108
|
255
|
+
��� 108
|
256
|
+
�� 107
|
257
|
+
�� 107
|
258
|
+
�� 107
|
259
|
+
�� 106
|
260
|
+
�, 106
|
261
|
+
� 106
|
262
|
+
�� 105
|
263
|
+
��� 105
|
264
|
+
�� 105
|
265
|
+
_�� 105
|
266
|
+
_��� 104
|
267
|
+
�� 104
|
268
|
+
��_ 104
|
269
|
+
�� 104
|
270
|
+
�� 104
|
271
|
+
� 103
|
272
|
+
�,_ 103
|
273
|
+
�� 103
|
274
|
+
�� 102
|
275
|
+
��� 102
|
276
|
+
_�� 102
|
277
|
+
_� 101
|
278
|
+
��� 101
|
279
|
+
�� 101
|
280
|
+
��� 101
|
281
|
+
�_ 101
|
282
|
+
��� 100
|
283
|
+
_�_ 100
|
284
|
+
�, 100
|
285
|
+
��_ 100
|
286
|
+
��� 100
|
287
|
+
�� 100
|
288
|
+
�� 100
|
289
|
+
�� 100
|
290
|
+
_� 100
|
291
|
+
_� 99
|
292
|
+
�, 99
|
293
|
+
�� 99
|
294
|
+
��� 99
|
295
|
+
��_ 99
|
296
|
+
_�� 99
|
297
|
+
�� 98
|
298
|
+
�� 98
|
299
|
+
_�� 98
|
300
|
+
���_ 98
|
301
|
+
� 97
|
302
|
+
��� 97
|
303
|
+
�� 97
|
304
|
+
_� 97
|
305
|
+
�,_ 97
|
306
|
+
�� 96
|
307
|
+
_�� 96
|
308
|
+
�,_ 96
|
309
|
+
�� 96
|
310
|
+
�� 96
|
311
|
+
��_ 95
|
312
|
+
�� 95
|
313
|
+
�� 94
|
314
|
+
��_ 94
|
315
|
+
_�� 94
|
316
|
+
�� 94
|
317
|
+
��� 93
|
318
|
+
�� 93
|
319
|
+
��_ 92
|
320
|
+
_��� 91
|
321
|
+
�� 91
|
322
|
+
�� 90
|
323
|
+
�� 90
|
324
|
+
_�� 90
|
325
|
+
? 90
|
326
|
+
��� 89
|
327
|
+
��� 89
|
328
|
+
_�_ 89
|
329
|
+
�� 89
|
330
|
+
�, 89
|
331
|
+
�� 88
|
332
|
+
� 88
|
333
|
+
_��� 88
|
334
|
+
�� 88
|
335
|
+
�� 88
|
336
|
+
��_ 87
|
337
|
+
��� 87
|
338
|
+
�,_ 87
|
339
|
+
��_ 86
|
340
|
+
�, 86
|
341
|
+
�,_ 86
|
342
|
+
��� 86
|
343
|
+
��� 86
|
344
|
+
��� 86
|
345
|
+
�� 86
|
346
|
+
� 86
|
347
|
+
�� 85
|
348
|
+
��_ 85
|
349
|
+
��� 85
|
350
|
+
�� 84
|
351
|
+
_��_ 84
|
352
|
+
_��� 84
|
353
|
+
�� 84
|
354
|
+
_��� 84
|
355
|
+
_� 84
|
356
|
+
�_ 83
|
357
|
+
�� 83
|
358
|
+
�� 83
|
359
|
+
� 83
|
360
|
+
��� 82
|
361
|
+
��_ 82
|
362
|
+
" 82
|
363
|
+
��� 82
|
364
|
+
���_ 81
|
365
|
+
��� 81
|
366
|
+
��� 81
|
367
|
+
�� 81
|
368
|
+
�� 81
|
369
|
+
��� 81
|
370
|
+
��� 81
|
371
|
+
��� 80
|
372
|
+
��_ 79
|
373
|
+
��� 79
|
374
|
+
��� 79
|
375
|
+
���� 79
|
376
|
+
��� 79
|
377
|
+
��� 79
|
378
|
+
��� 79
|
379
|
+
_�� 78
|
380
|
+
��� 78
|
381
|
+
_�� 78
|
382
|
+
�. 77
|
383
|
+
_�� 77
|
384
|
+
�._ 76
|
385
|
+
�. 76
|
386
|
+
_�� 76
|
387
|
+
�� 76
|
388
|
+
�� 76
|
389
|
+
�� 76
|
390
|
+
��� 76
|
391
|
+
�, 75
|
392
|
+
� 75
|
393
|
+
��_ 75
|
394
|
+
�,_ 75
|
395
|
+
��_ 75
|
396
|
+
�� 74
|
397
|
+
_�� 74
|
398
|
+
��� 74
|
399
|
+
�� 74
|
400
|
+
�� 74
|
@@ -0,0 +1,400 @@
|
|
1
|
+
a 15017
|
2
|
+
_ 14975
|
3
|
+
h 5028
|
4
|
+
i 3820
|
5
|
+
t 2976
|
6
|
+
s 2788
|
7
|
+
r 2599
|
8
|
+
| 2437
|
9
|
+
n 2432
|
10
|
+
aa 2276
|
11
|
+
ha 2007
|
12
|
+
m 1982
|
13
|
+
a_ 1802
|
14
|
+
v 1799
|
15
|
+
d 1768
|
16
|
+
u 1629
|
17
|
+
y 1599
|
18
|
+
_| 1470
|
19
|
+
|_ 1470
|
20
|
+
e 1403
|
21
|
+
k 1371
|
22
|
+
sh 1330
|
23
|
+
ra 1243
|
24
|
+
p 1213
|
25
|
+
va 1152
|
26
|
+
A 1134
|
27
|
+
ya 1120
|
28
|
+
ma 1097
|
29
|
+
na 1091
|
30
|
+
ar 1080
|
31
|
+
ta 1054
|
32
|
+
M 1050
|
33
|
+
. 1047
|
34
|
+
am 1037
|
35
|
+
an 1006
|
36
|
+
|| 967
|
37
|
+
||_ 965
|
38
|
+
_|| 965
|
39
|
+
_||_ 963
|
40
|
+
at 962
|
41
|
+
M_ 946
|
42
|
+
as 910
|
43
|
+
_s 882
|
44
|
+
o 848
|
45
|
+
b 844
|
46
|
+
i_ 827
|
47
|
+
aM 764
|
48
|
+
aM_ 685
|
49
|
+
c 630
|
50
|
+
ch 629
|
51
|
+
sa 623
|
52
|
+
N 616
|
53
|
+
ad 612
|
54
|
+
H 601
|
55
|
+
pa 595
|
56
|
+
H_ 584
|
57
|
+
g 580
|
58
|
+
_n 579
|
59
|
+
l 554
|
60
|
+
bh 552
|
61
|
+
hi 547
|
62
|
+
ka 542
|
63
|
+
it 536
|
64
|
+
ii 535
|
65
|
+
ama 519
|
66
|
+
_|_ 505
|
67
|
+
e_ 477
|
68
|
+
_p 475
|
69
|
+
dh 475
|
70
|
+
av 469
|
71
|
+
ak 445
|
72
|
+
aH 444
|
73
|
+
da 440
|
74
|
+
aH_ 439
|
75
|
+
ay 437
|
76
|
+
j 437
|
77
|
+
_na 432
|
78
|
+
ana 430
|
79
|
+
hh 428
|
80
|
+
ti 426
|
81
|
+
ara 425
|
82
|
+
aa_ 410
|
83
|
+
_k 394
|
84
|
+
shh 389
|
85
|
+
_v 388
|
86
|
+
_sa 381
|
87
|
+
.h 379
|
88
|
+
ah 369
|
89
|
+
_b 368
|
90
|
+
h_ 363
|
91
|
+
.h_ 363
|
92
|
+
cha 362
|
93
|
+
haa 361
|
94
|
+
_t 358
|
95
|
+
ri 352
|
96
|
+
sha 345
|
97
|
+
ap 333
|
98
|
+
vi 330
|
99
|
+
is 329
|
100
|
+
^ 321
|
101
|
+
o_ 321
|
102
|
+
_m 320
|
103
|
+
ai 311
|
104
|
+
_d 311
|
105
|
+
la 302
|
106
|
+
na_ 301
|
107
|
+
.n 298
|
108
|
+
ava 295
|
109
|
+
al 294
|
110
|
+
_sh 291
|
111
|
+
ja 288
|
112
|
+
a. 280
|
113
|
+
aan 277
|
114
|
+
ish 274
|
115
|
+
aN 273
|
116
|
+
aya 273
|
117
|
+
ash 266
|
118
|
+
ha_ 265
|
119
|
+
ga 264
|
120
|
+
st 255
|
121
|
+
ni 255
|
122
|
+
ii_ 254
|
123
|
+
hu 253
|
124
|
+
Na 253
|
125
|
+
R 248
|
126
|
+
R^ 248
|
127
|
+
^i 247
|
128
|
+
R^i 247
|
129
|
+
a.n 243
|
130
|
+
th 241
|
131
|
+
_c 240
|
132
|
+
_ch 239
|
133
|
+
maa 238
|
134
|
+
bha 237
|
135
|
+
vaa 233
|
136
|
+
ab 228
|
137
|
+
ir 226
|
138
|
+
\ 226
|
139
|
+
ita 223
|
140
|
+
uu 222
|
141
|
+
dha 220
|
142
|
+
har 218
|
143
|
+
_a 216
|
144
|
+
_bh 216
|
145
|
+
nam 212
|
146
|
+
u_ 212
|
147
|
+
he 212
|
148
|
+
m.h_ 211
|
149
|
+
m. 211
|
150
|
+
m.h 211
|
151
|
+
ur 210
|
152
|
+
es 209
|
153
|
+
ata 208
|
154
|
+
te 206
|
155
|
+
yaa 205
|
156
|
+
_ma 204
|
157
|
+
esh 202
|
158
|
+
aka 200
|
159
|
+
id 199
|
160
|
+
pr 199
|
161
|
+
aha 198
|
162
|
+
hy 198
|
163
|
+
T 197
|
164
|
+
aat 197
|
165
|
+
_OM_ 196
|
166
|
+
OM 196
|
167
|
+
_O 196
|
168
|
+
_OM 196
|
169
|
+
OM_ 196
|
170
|
+
O 196
|
171
|
+
ti_ 195
|
172
|
+
ari 194
|
173
|
+
raa 193
|
174
|
+
ag 192
|
175
|
+
_y 192
|
176
|
+
aas 190
|
177
|
+
_ta 190
|
178
|
+
_j 189
|
179
|
+
I 189
|
180
|
+
_na_ 187
|
181
|
+
am.h_ 185
|
182
|
+
am.h 185
|
183
|
+
am. 185
|
184
|
+
_pa 183
|
185
|
+
iv 182
|
186
|
+
de 182
|
187
|
+
ada 178
|
188
|
+
nd 178
|
189
|
+
_cha 177
|
190
|
+
_h 176
|
191
|
+
ati 175
|
192
|
+
taa 173
|
193
|
+
ev 172
|
194
|
+
nt 171
|
195
|
+
rii 171
|
196
|
+
ishh 170
|
197
|
+
ya_ 168
|
198
|
+
_vi 166
|
199
|
+
ast 165
|
200
|
+
tr 164
|
201
|
+
abh 164
|
202
|
+
kh 162
|
203
|
+
ala 160
|
204
|
+
tha 160
|
205
|
+
apa 160
|
206
|
+
asa 158
|
207
|
+
naa 158
|
208
|
+
_nam 156
|
209
|
+
ru 156
|
210
|
+
A_ 155
|
211
|
+
_ka 154
|
212
|
+
aar 153
|
213
|
+
_pr 152
|
214
|
+
_g 151
|
215
|
+
pra 150
|
216
|
+
ham 150
|
217
|
+
hha 149
|
218
|
+
aana 149
|
219
|
+
di 149
|
220
|
+
ra_ 147
|
221
|
+
ik 146
|
222
|
+
.a 144
|
223
|
+
yat 143
|
224
|
+
ks 143
|
225
|
+
hA 143
|
226
|
+
hya 143
|
227
|
+
ksh 143
|
228
|
+
ut 142
|
229
|
+
sy 141
|
230
|
+
nama 140
|
231
|
+
_va 140
|
232
|
+
.\ 140
|
233
|
+
paa 140
|
234
|
+
han 139
|
235
|
+
eva 138
|
236
|
+
U 138
|
237
|
+
mi 138
|
238
|
+
_r 136
|
239
|
+
_ja 136
|
240
|
+
asy 135
|
241
|
+
hr 135
|
242
|
+
sya 134
|
243
|
+
cha_ 132
|
244
|
+
rv 132
|
245
|
+
tv 130
|
246
|
+
asya 130
|
247
|
+
kar 130
|
248
|
+
ho 129
|
249
|
+
yo 129
|
250
|
+
in 128
|
251
|
+
adh 127
|
252
|
+
yA 127
|
253
|
+
va_ 126
|
254
|
+
su 125
|
255
|
+
_ya 125
|
256
|
+
shha 124
|
257
|
+
pu 124
|
258
|
+
R^it 123
|
259
|
+
sta 123
|
260
|
+
mu 123
|
261
|
+
^it 123
|
262
|
+
ty 123
|
263
|
+
_nama 121
|
264
|
+
ac 120
|
265
|
+
rii_ 120
|
266
|
+
ach 120
|
267
|
+
aNa 119
|
268
|
+
tas 119
|
269
|
+
shi 119
|
270
|
+
iva 119
|
271
|
+
hav 119
|
272
|
+
tra 118
|
273
|
+
var 118
|
274
|
+
par 118
|
275
|
+
haM 117
|
276
|
+
aad 117
|
277
|
+
kaa 117
|
278
|
+
hch 117
|
279
|
+
mas 117
|
280
|
+
ai_ 117
|
281
|
+
hc 117
|
282
|
+
sar 116
|
283
|
+
aam 116
|
284
|
+
_bha 115
|
285
|
+
_pra 114
|
286
|
+
et 114
|
287
|
+
haM_ 113
|
288
|
+
aay 113
|
289
|
+
aj 113
|
290
|
+
ye 113
|
291
|
+
o. 113
|
292
|
+
An 111
|
293
|
+
arii 111
|
294
|
+
t.h 110
|
295
|
+
t. 110
|
296
|
+
ath 110
|
297
|
+
t.h_ 109
|
298
|
+
man 109
|
299
|
+
te_ 108
|
300
|
+
o.a 108
|
301
|
+
hara 108
|
302
|
+
rA 108
|
303
|
+
rva 108
|
304
|
+
tva 108
|
305
|
+
asta 108
|
306
|
+
up 108
|
307
|
+
shr 107
|
308
|
+
daa 104
|
309
|
+
me 104
|
310
|
+
dr 104
|
311
|
+
ram 104
|
312
|
+
arii_ 102
|
313
|
+
_ni 102
|
314
|
+
arv 102
|
315
|
+
iH 102
|
316
|
+
hit 101
|
317
|
+
ras 101
|
318
|
+
aga 101
|
319
|
+
Am 101
|
320
|
+
mA 101
|
321
|
+
ba 101
|
322
|
+
amas 100
|
323
|
+
tu 100
|
324
|
+
yaM 100
|
325
|
+
ant 99
|
326
|
+
ud 99
|
327
|
+
uk 98
|
328
|
+
iH_ 98
|
329
|
+
yaM_ 98
|
330
|
+
kha 98
|
331
|
+
au 98
|
332
|
+
ira 97
|
333
|
+
shhT 97
|
334
|
+
rah 97
|
335
|
+
hT 97
|
336
|
+
hhT 97
|
337
|
+
D 96
|
338
|
+
_sar 96
|
339
|
+
re 96
|
340
|
+
eshh 95
|
341
|
+
sarv 94
|
342
|
+
amaa 94
|
343
|
+
and 94
|
344
|
+
arva 94
|
345
|
+
_ra 93
|
346
|
+
_dh 93
|
347
|
+
tt 92
|
348
|
+
tad 92
|
349
|
+
hm 92
|
350
|
+
raM_ 91
|
351
|
+
dev 91
|
352
|
+
raM 91
|
353
|
+
C 91
|
354
|
+
ani 91
|
355
|
+
_sarv 90
|
356
|
+
atha 89
|
357
|
+
Ad 89
|
358
|
+
chi 89
|
359
|
+
tA 88
|
360
|
+
sarva 88
|
361
|
+
avi 88
|
362
|
+
taM 87
|
363
|
+
hava 87
|
364
|
+
anaa 86
|
365
|
+
vA 86
|
366
|
+
dd 86
|
367
|
+
nA 85
|
368
|
+
Ar 85
|
369
|
+
hv 85
|
370
|
+
taM_ 85
|
371
|
+
dhi 84
|
372
|
+
ksha 84
|
373
|
+
ip 84
|
374
|
+
ma_ 84
|
375
|
+
_sha 84
|
376
|
+
ati_ 83
|
377
|
+
yai 83
|
378
|
+
vat 83
|
379
|
+
At 83
|
380
|
+
kR 82
|
381
|
+
kR^ 82
|
382
|
+
bhi 82
|
383
|
+
_shr 82
|
384
|
+
to 82
|
385
|
+
ta_ 82
|
386
|
+
br 82
|
387
|
+
ek 82
|
388
|
+
kR^i 82
|
389
|
+
tat 81
|
390
|
+
nta 81
|
391
|
+
hma 81
|
392
|
+
aaya 80
|
393
|
+
tam 80
|
394
|
+
en 80
|
395
|
+
us 79
|
396
|
+
bra 79
|
397
|
+
ke 79
|
398
|
+
kt 79
|
399
|
+
ddh 79
|
400
|
+
mo 79
|