blob: c5b900bef904d3714879312f4d1cf7accd304399 [file] [log] [blame]
use dataverse demo_aql;
declare type DBLPType as open {
id: int32,
dblpid: string,
title: string,
authors: string,
misc: string
}
declare nodegroup group1 on rainbow-01, rainbow-02, rainbow-03, rainbow-04, rainbow-05;
declare dataset DBLP(DBLPType)
partitioned by key id on group1;
write output to rainbow-01:"/home/onose/hyracks-rainbow/results/110-self-join-dblp.adm";
set simthreshold '.8f';
for $k in (
for $i in dataset('DBLP')
for $j in dataset('DBLP')
where $i.title ~= $j.title
order by $i.id, $j.id
return {'dblp1': $i, 'dblp2': $j}
)
where $k.dblp1.id < $k.dblp2.id
return $k