blob: ead8e818376601d260c2300bed8bc9b4c3b7aa5a [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 nodegroup group1 if not exists on nc1, nc2;
create dataset DBLP(DBLPType) partitioned by key id on group1;
create dataset CSX(CSXType) partitioned by key id on group1;
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_1.adm';
set simthreshold '.5f';
for $i in dataset('DBLP')
for $j in dataset('CSX')
where $i.title ~= $j.title
order by $i.id, $j.id
return {'dblp': $i, 'csx': $j}