Detected extensions in "tika_1_6"
DETECTED_FILE_EXTENSION_A | COUNT |
pdf
| 52024
|
html
| 51030
|
txt
| 31447
|
doc
| 16265
|
jpg
| 14908
|
ppt
| 12063
|
xls
| 7875
|
gif
| 4103
|
ps
| 2484
|
xml
| 2346
|
tgz
| 1596
|
xhtml
| 1454
|
png
| 728
|
eml
| 463
|
bin
| 391
|
rtf
| 246
|
fits
| 86
|
swf
| 78
|
java
| 53
|
zip
| 49
|
kml
| 42
|
| 41
|
pptx
| 35
|
tex
| 26
|
rdf
| 25
|
| 24
|
docx
| 18
|
css
| 17
|
bmp
| 16
|
dwf
| 16
|
rss
| 14
|
bib
| 6
|
emlx
| 6
|
tiff
| 5
|
fm
| 3
|
pbm
| 2
|
wmv
| 2
|
xlr
| 2
|
xlsx
| 2
|
dita
| 1
|
elc
| 1
|
g3
| 1
|
iso
| 1
|
ppm
| 1
|
ppsx
| 1
|
sit
| 1
|
sxi
| 1
|
xps
| 1
|
select DETECTED_FILE_EXTENSION_A, count(1) as COUNT from comparisons group by DETECTED_FILE_EXTENSION_A order by COUNT desc