asterix-app/src/test/resources/runtimets/queries/fuzzyjoin/dblp-csx-dblp-aqlplus_1.aql

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) primary key id;
create dataset CSX(CSXType) primary key id;

load dataset DBLP
using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
(("path"="nc1://data/pub-small/dblp-small-id.txt"),("format"="delimited-text"),("delimiter"=":"));

load dataset CSX
using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
(("path"="nc1://data/pub-small/csx-small-id.txt"),("format"="delimited-text"),("delimiter"=":"));

write output to nc1:'rttest/fuzzyjoin_dblp-csx-dblp-aqlplus_1.adm';

set simthreshold '.5f';

for $dblp in dataset('DBLP')
for $csx in dataset('CSX')
for $dblp2 in dataset('DBLP')
where word-tokens($dblp.title) ~= word-tokens($csx.title) and word-tokens($csx.authors) ~= word-tokens($dblp2.authors)
order by $dblp.id, $csx.id, $dblp2.id
return {'dblp': $dblp, 'csx': $csx, 'dblp2': $dblp2}