Languages detected in pdfbox_1_8_8 by content type then language

DETECTED_CONTENT_TYPE_A LANG_ID1_A COUNT
application/pdf
en
217500
application/pdf
de
1433
application/pdf
es
957
application/pdf
fr
697
application/pdf
bn
557
application/pdf
vi
180
application/pdf
it
173
application/pdf
pt
168
application/pdf
th
85
application/pdf
sl
62
application/pdf
id
61
application/pdf
lt
61
application/pdf
so
59
application/pdf
pl
59
application/pdf
tl
53
application/pdf
sq
49
application/pdf
tr
46
application/pdf
hu
42
application/pdf
nl
40
application/pdf
sv
35
application/pdf
hr
35
application/pdf
ro
30
application/pdf
da
25
application/pdf
el
21
application/pdf
no
20
application/pdf
et
19
application/pdf
ru
18
application/pdf
sk
17
application/pdf
sw
16
application/pdf
cs
13
application/pdf
hi
13
application/pdf
af
8
application/pdf
ko
7
application/pdf
lv
7
application/pdf
ar
5
application/pdf
ja
4
application/pdf
fi
4
application/pdf
uk
2
application/pdf
ur
2
application/pdf
zh-cn
2
application/pdf
bg
2
application/pdf
zh-tw
2
application/pdf
mk
1
application/pdf
fa
1
application/pdf
he
1
text/html; charset=ISO-8859-1
en
1
text/plain; charset=ISO-8859-8
nl
1
text/plain; charset=windows-1252
en
6
text/plain; charset=windows-1255
en
3




select DETECTED_CONTENT_TYPE_A, LANG_ID1_A, count(1) as COUNT from comparisons where LANG_ID1_A is not null group by DETECTED_CONTENT_TYPE_A, LANG_ID1_A order by DETECTED_CONTENT_TYPE_A, COUNT desc