Languages detected in pdfbox_1_8_9_20150316 by content type then language

DETECTED_CONTENT_TYPE_B LANG_ID1_B COUNT
application/pdf
en
217481
application/pdf
de
1436
application/pdf
es
947
application/pdf
fr
711
application/pdf
bn
560
application/pdf
vi
177
application/pdf
it
170
application/pdf
pt
164
application/pdf
th
85
application/pdf
sl
71
application/pdf
so
63
application/pdf
lt
63
application/pdf
pl
62
application/pdf
id
61
application/pdf
tl
56
application/pdf
sq
50
application/pdf
hu
45
application/pdf
tr
43
application/pdf
nl
41
application/pdf
sv
32
application/pdf
hr
31
application/pdf
ro
29
application/pdf
da
27
application/pdf
no
23
application/pdf
et
20
application/pdf
el
19
application/pdf
sk
18
application/pdf
sw
18
application/pdf
ru
18
application/pdf
hi
14
application/pdf
cs
13
application/pdf
ko
8
application/pdf
lv
7
application/pdf
af
6
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
he
1
application/pdf
mk
1
application/pdf
fa
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