Exceptions in "tika_1_6"

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% 




	
ppt

	
11884

	
456

	
3.84% 




	
pps

	
160

	
5

	
3.12% 




	
xml

	
1862

	
45

	
2.42% 




	
xls

	
7868

	
154

	
1.96% 




	
doc

	
16156

	
218

	
1.35% 




	
rtf

	
246

	
1

	
0.41% 




	
html

	
52983

	
63

	
0.12% 




	
pdf

	
52020

	
56

	
0.11% 




	
txt

	
27671

	
4

	
0.01% 




	
jpg

	
14894

	
2

	
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_A is not null group by comparisons.FILE_EXTENSION order by (1.0*ifNull(count(1), 0)/extensions_total.NUM_FILES) desc;