Languages detected in PDFBox_1_8_9_20150316_single_thread by language then content type

LANG_ID1_A DETECTED_CONTENT_TYPE_A COUNT
af
application/pdf
10
ar
application/pdf
5
bg
application/pdf
2
bn
application/pdf
560
cs
application/pdf
14
da
application/pdf
26
de
application/pdf
1427
el
application/pdf
18
en
application/pdf
217476
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
959
et
application/pdf
20
fa
application/pdf
1
fi
application/pdf
4
fr
application/pdf
705
he
application/pdf
1
hi
application/pdf
13
hr
application/pdf
38
hu
application/pdf
47
id
application/pdf
59
it
application/pdf
171
ja
application/pdf
4
ko
application/pdf
8
lt
application/pdf
62
lv
application/pdf
6
mk
application/pdf
1
nl
application/pdf
46
no
application/pdf
24
pl
application/pdf
54
pt
application/pdf
161
ro
application/pdf
32
ru
application/pdf
17
sk
application/pdf
24
sl
application/pdf
67
so
application/pdf
66
sq
application/pdf
46
sv
application/pdf
35
sw
application/pdf
18
th
application/pdf
82
tl
application/pdf
60
tr
application/pdf
46
uk
application/pdf
2
ur
application/pdf
2
vi
application/pdf
172
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;