blob: 166f305d4bc85afe06b7290e19c57732b3830871 [file] [log] [blame]
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing,
* software distributed under the License is distributed on an
* "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
* KIND, either express or implied. See the License for the
* specific language governing permissions and limitations
* under the License.
*/
/*
* Description : Two-way fuzzy join on DBLP and CSX with a fuzzy join condition on word tokens of their titles.
* Success : Yes
*/
drop dataverse fj-dblp-csx if exists;
create dataverse fj-dblp-csx;
use dataverse fj-dblp-csx;
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 asterix_nc1, asterix_nc2;
create dataset DBLP(DBLPType) primary key id with {"node-group":{"name":"group1"}};
create dataset CSX(CSXType) primary key id with {"node-group":{"name":"group1"}};
write output to asterix_nc1:'rttest/fj-dblp-csx.adm';
for $s in dataset('DBLP')
for $t in dataset('CSX')
where word-tokens($s.title) ~= word-tokens($t.title)
return {"sid": $s.id, "tid": $t.id}