Languages detected in pdfbox_1_8_8 by language then content type

LANG_ID1_A DETECTED_CONTENT_TYPE_A COUNT
af
application/pdf
5
ar
application/pdf
5
bg
application/pdf
2
bn
application/pdf
560
cs
application/pdf
11
da
application/pdf
23
de
application/pdf
1445
el
application/pdf
20
en
application/pdf
217488
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
961
et
application/pdf
21
fa
application/pdf
1
fi
application/pdf
4
fr
application/pdf
706
hi
application/pdf
14
hr
application/pdf
33
hu
application/pdf
40
id
application/pdf
58
it
application/pdf
173
ja
application/pdf
4
ko
application/pdf
8
lt
application/pdf
58
lv
application/pdf
8
mk
application/pdf
1
nl
application/pdf
47
nl
text/plain; charset=ISO-8859-8
1
no
application/pdf
21
pl
application/pdf
55
pt
application/pdf
165
ro
application/pdf
30
ru
application/pdf
17
sk
application/pdf
14
sl
application/pdf
68
so
application/pdf
62
sq
application/pdf
51
sv
application/pdf
43
sw
application/pdf
17
th
application/pdf
74
tl
application/pdf
57
tr
application/pdf
44
uk
application/pdf
2
ur
application/pdf
2
vi
application/pdf
170
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;