Languages detected in pdfbox_1_8_9_20150316 by content type then language

DETECTED_CONTENT_TYPE_B LANG_ID1_B COUNT
application/pdf
en
217492
application/pdf
de
1440
application/pdf
es
946
application/pdf
fr
707
application/pdf
bn
557
application/pdf
vi
182
application/pdf
it
168
application/pdf
pt
164
application/pdf
th
84
application/pdf
sl
68
application/pdf
so
66
application/pdf
lt
64
application/pdf
id
59
application/pdf
tl
57
application/pdf
pl
56
application/pdf
sq
47
application/pdf
hu
45
application/pdf
tr
44
application/pdf
nl
43
application/pdf
hr
33
application/pdf
ro
30
application/pdf
sv
29
application/pdf
da
25
application/pdf
no
24
application/pdf
el
20
application/pdf
et
20
application/pdf
sk
17
application/pdf
sw
17
application/pdf
ru
17
application/pdf
hi
13
application/pdf
cs
12
application/pdf
lv
10
application/pdf
ko
8
application/pdf
af
5
application/pdf
ar
5
application/pdf
ja
4
application/pdf
fi
4
application/pdf
uk
3
application/pdf
ur
2
application/pdf
zh-tw
2
application/pdf
zh-cn
2
application/pdf
bg
2
application/pdf
mk
1
application/pdf
fa
1
text/html; charset=ISO-8859-1
en
1
text/plain; charset=ISO-8859-8
en
1
text/plain; charset=windows-1252
en
6
text/plain; charset=windows-1255
en
3




select DETECTED_CONTENT_TYPE_B, LANG_ID1_B, count(1) as COUNT from comparisons where LANG_ID1_B is not null group by DETECTED_CONTENT_TYPE_B, LANG_ID1_B order by DETECTED_CONTENT_TYPE_B, COUNT desc