Exceptions in "tika_1_8_SNAPSHOT"

FILE_EXTENSION Number of files Number of files with exceptions Percentage of files with exceptions

	
1

	
1

	
100.00% 




	
log

	
830

	
158

	
19.04% 




	
kml

	
42

	
4

	
9.52% 




	
sgml

	
15

	
1

	
6.67% 




	
pptx

	
35

	
2

	
5.71% 




	
xml

	
1862

	
45

	
2.42% 




	
ppt

	
11884

	
256

	
2.15% 




	
pps

	
160

	
3

	
1.87% 




	
doc

	
16156

	
215

	
1.33% 




	
unk

	
879

	
11

	
1.25% 




	
xls

	
7868

	
65

	
0.83% 




	
rtf

	
246

	
1

	
0.41% 




	
html

	
52983

	
63

	
0.12% 




	
pdf

	
52020

	
20

	
0.04% 




	
jpg

	
14894

	
2

	
0.01% 




	
txt

	
27671

	
3

	
0.01% 













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