Languages detected in tika_1_6

LANG_ID1_A	COUNT
en	165169
de	1549
es	1406
fr	749
sq	533
vi	281
it	244
pt	190
pl	175
so	173
hu	135
ro	123
bn	121
da	117
id	107
sw	89
tl	73
sv	53
nl	47
af	41
sl	37
sk	33
et	32
hr	28
zh-cn	26
tr	24
no	21
lt	18
ru	13
cs	8
th	7
hi	4
bg	3
ko	3
fi	2
el	1
he	1
ja	1
mk	1
ne	1

select LANG_ID1_A, count(1) as COUNT from comparisons where LANG_ID1_A is not null group by LANG_ID1_A order by COUNT desc