Languages detected in pdfbox_1_8_9_20150316 by language then content type

LANG_ID1_B DETECTED_CONTENT_TYPE_B COUNT
af
application/pdf
6
ar
application/pdf
5
bg
application/pdf
2
bn
application/pdf
560
cs
application/pdf
13
da
application/pdf
27
de
application/pdf
1436
el
application/pdf
19
en
application/pdf
217481
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
947
et
application/pdf
20
fa
application/pdf
1
fi
application/pdf
4
fr
application/pdf
711
he
application/pdf
1
hi
application/pdf
14
hr
application/pdf
31
hu
application/pdf
45
id
application/pdf
61
it
application/pdf
170
ja
application/pdf
4
ko
application/pdf
8
lt
application/pdf
63
lv
application/pdf
7
mk
application/pdf
1
nl
application/pdf
41
nl
text/plain; charset=ISO-8859-8
1
no
application/pdf
23
pl
application/pdf
62
pt
application/pdf
164
ro
application/pdf
29
ru
application/pdf
18
sk
application/pdf
18
sl
application/pdf
71
so
application/pdf
63
sq
application/pdf
50
sv
application/pdf
32
sw
application/pdf
18
th
application/pdf
85
tl
application/pdf
56
tr
application/pdf
43
uk
application/pdf
2
ur
application/pdf
2
vi
application/pdf
177
zh-cn
application/pdf
2
zh-tw
application/pdf
2




select LANG_ID1_B, DETECTED_CONTENT_TYPE_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 lang_ID1_B, COUNT desc, DETECTED_CONTENT_TYPE_B;