Files with fewer metadata values in "tika_1_6" than in "tika_1_8_SNAPSHOT" by detected file extension
DETECTED_FILE_EXTENSION_A | COUNT |
| 41
|
| 23
|
bib
| 6
|
bin
| 380
|
bmp
| 16
|
css
| 17
|
doc
| 16046
|
docx
| 18
|
dwf
| 16
|
elc
| 1
|
eml
| 463
|
emlx
| 6
|
fits
| 86
|
fm
| 3
|
g3
| 1
|
gif
| 4103
|
html
| 51027
|
iso
| 1
|
java
| 53
|
jpg
| 14906
|
kml
| 38
|
pbm
| 2
|
pdf
| 51960
|
png
| 728
|
ppm
| 1
|
ppsx
| 1
|
ppt
| 11597
|
pptx
| 32
|
ps
| 2484
|
rdf
| 23
|
rss
| 14
|
rtf
| 245
|
sit
| 1
|
swf
| 78
|
sxi
| 1
|
tex
| 26
|
tgz
| 1596
|
tiff
| 5
|
txt
| 31443
|
wmv
| 2
|
xhtml
| 1454
|
xlr
| 2
|
xls
| 7715
|
xlsx
| 2
|
xml
| 2086
|
xps
| 1
|
zip
| 48
|
SELECT DETECTED_FILE_EXTENSION_A, count(1) as COUNT from comparisons where JSON_EX_A is null and JSON_EX_B is null and SORT_STACK_TRACE_A is null and SORT_STACK_TRACE_B is null and DIFF_NUM_ATTACHMENTS = 0 and DIFF_NUM_METADATA_VALUES > 0 group by DETECTED_FILE_EXTENSION_A