Languages detected in pdfbox_1_8_9_20150316 by language then content type

LANG_ID1_B DETECTED_CONTENT_TYPE_B COUNT
af
application/pdf
5
ar
application/pdf
5
bg
application/pdf
2
bn
application/pdf
557
cs
application/pdf
12
da
application/pdf
25
de
application/pdf
1440
el
application/pdf
20
en
application/pdf
217492
en
text/plain; charset=windows-1252
6
en
text/plain; charset=windows-1255
3
en
text/html; charset=ISO-8859-1
1
en
text/plain; charset=ISO-8859-8
1
es
application/pdf
946
et
application/pdf
20
fa
application/pdf
1
fi
application/pdf
4
fr
application/pdf
707
hi
application/pdf
13
hr
application/pdf
33
hu
application/pdf
45
id
application/pdf
59
it
application/pdf
168
ja
application/pdf
4
ko
application/pdf
8
lt
application/pdf
64
lv
application/pdf
10
mk
application/pdf
1
nl
application/pdf
43
no
application/pdf
24
pl
application/pdf
56
pt
application/pdf
164
ro
application/pdf
30
ru
application/pdf
17
sk
application/pdf
17
sl
application/pdf
68
so
application/pdf
66
sq
application/pdf
47
sv
application/pdf
29
sw
application/pdf
17
th
application/pdf
84
tl
application/pdf
57
tr
application/pdf
44
uk
application/pdf
3
ur
application/pdf
2
vi
application/pdf
182
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;