Languages detected in pdfbox_1_8_8 by language then content type

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




select LANG_ID1_A, DETECTED_CONTENT_TYPE_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 lang_ID1_A, COUNT desc, DETECTED_CONTENT_TYPE_A;