Exceptions in "tika_1_6"

Detected content type Number of files Number of files with exceptions Percentage of files with exceptions
application/dita+xml; format=topic
 
1
 
1
 
100.00% 
application/x-tika-msoffice
 
1
 
1
 
100.00% 
application/xml
 
1993
 
260
 
13.05% 
application/vnd.google-earth.kml+xml
 
42
 
4
 
9.52% 
application/rdf+xml
 
25
 
2
 
8.00% 
application/vnd.openxmlformats-officedocument.presentationml.presentation
 
35
 
2
 
5.71% 
application/vnd.ms-powerpoint
 
12063
 
462
 
3.83% 
application/zip
 
49
 
1
 
2.04% 
application/vnd.ms-excel
 
7875
 
154
 
1.96% 
application/msword
 
16265
 
217
 
1.33% 
application/rtf
 
246
 
1
 
0.41% 
application/pdf
 
52024
 
56
 
0.11% 
text/html; charset=utf-8
 
3268
 
2
 
0.06% 
text/plain; charset=ISO-8859-1
 
18086
 
4
 
0.02% 
image/jpeg
 
14908
 
2
 
0.01% 
text/html; charset=windows-1252
 
13654
 
1
 
0.01%




SELECT comparisons.DETECTED_CONTENT_TYPE_A as 'Detected content type', detected_types_A.NUM_FILES as 'Number of files', count(1) as 'Number of files with exceptions', printf("%.2f%% ", (100.0*ifNull(count(1), 0)/detected_types_A.NUM_FILES)) as 'Percentage of files with exceptions' from comparisons left outer join detected_types_A on comparisons.DETECTED_CONTENT_TYPE_A =detected_types_A.DETECTED_CONTENT_TYPE_A where SORT_STACK_TRACE_A is not null group by comparisons.DETECTED_CONTENT_TYPE_A order by (1.0*ifNull(count(1), 0)/detected_types_A.NUM_FILES) desc;