blob: 0f0e99364d5ee40461719c86019cec912183d90a [file] [log] [blame]
drop dataverse fuzzyjoin if exists;
create dataverse fuzzyjoin;
use dataverse fuzzyjoin;
create type DBLPType as open {
id: int32,
dblpid: string,
title: string,
authors: string,
misc: string
}
create type CSXType as open {
id: int32,
csxid: string,
title: string,
authors: string,
misc: string
}
create dataset DBLP(DBLPType) partitioned by key id;
create dataset CSX(CSXType) partitioned by key id;
load dataset DBLP from nc1:'data/pub-small/dblp-small-id.txt' delimited by ':';
load dataset CSX from nc1:'data/pub-small/csx-small-id.txt' delimited by ':';
write output to nc1:'rttest/fuzzyjoin_dblp-csx-aqlplus_3.adm';
set simthreshold '.5f';
for $dblp in dataset('DBLP')
for $csx in dataset('CSX')
where $csx.title ~= $dblp.title
order by $dblp.id, $csx.id
return {'dblp': $dblp, 'csx': $csx}