Languages detected in PDFBox_1_8_9-SNAPSHOT by content type then language

DETECTED_CONTENT_TYPE_B LANG_ID1_B COUNT
application/pdf
en
217489
application/pdf
de
1429
application/pdf
es
957
application/pdf
fr
708
application/pdf
bn
555
application/pdf
vi
180
application/pdf
pt
172
application/pdf
it
167
application/pdf
th
80
application/pdf
sl
64
application/pdf
lt
62
application/pdf
id
60
application/pdf
so
60
application/pdf
pl
60
application/pdf
tl
54
application/pdf
sq
47
application/pdf
tr
43
application/pdf
hu
43
application/pdf
nl
42
application/pdf
hr
40
application/pdf
sv
34
application/pdf
ro
30
application/pdf
da
25
application/pdf
no
24
application/pdf
et
21
application/pdf
el
20
application/pdf
sk
17
application/pdf
sw
17
application/pdf
ru
17
application/pdf
cs
13
application/pdf
hi
13
application/pdf
af
10
application/pdf
ko
8
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_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