blob: 3bf85c664a59f5b796fb6ff7291a957753419db0 [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 : Fuzzy joins two datasets, DBLP and CSX, based on the similarity-jaccard function of their titles' 3-gram tokens.
* DBLP has a 3-gram index on title, and we expect the join to be transformed into an indexed nested-loop join.
* We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
* Success : Yes
*/
drop dataverse test if exists;
create dataverse test;
use dataverse test;
set import-private-functions 'true';
create type DBLPType as closed {
id: int32,
dblpid: string,
title: string,
authors: string,
misc: string
}
create type CSXType as closed {
id: int32,
csxid: string,
title: string,
authors: string,
misc: string
}
create dataset DBLP(DBLPType) primary key id;
create dataset CSX(CSXType) primary key id;
create index ngram_index on DBLP(title) type ngram(3);
write output to nc1:"rttest/inverted-index-join-noeqjoin_ngram-jaccard.adm";
for $a in dataset('DBLP')
for $b in dataset('CSX')
where similarity-jaccard(gram-tokens($a.title, 3, false), gram-tokens($b.title, 3, false)) >= 0.5f
and $a.id < $b.id
return {"atitle": $a.title, "btitle": $b.title}