asterixdb/asterix-app/src/test/resources/optimizerts/queries_sqlpp/fj-phase2-with-hints.sqlpp

/*
 * 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.
 */

drop  dataverse fuzzyjoin_078 if exists;
create  dataverse fuzzyjoin_078;

use fuzzyjoin_078;


create type fuzzyjoin_078.DBLPType as
{
  id : int32,
  dblpid : string,
  title : string,
  authors : string,
  misc : string
}

create  nodegroup group1 if not exists  on
    asterix_nc1,
    asterix_nc2
;
create  dataset DBLP_fuzzyjoin_078(DBLPType) primary key id on group1;

write output to asterix_nc1:"rttest/fuzzyjoin_078.adm"
select element {'id':paperDBLP.id,'tokens':tokensDBLP}
from  DBLP_fuzzyjoin_078 as paperDBLP
with  unrankedTokensDBLP as fuzzyjoin_078.`counthashed-word-tokens`(paperDBLP.title),
      tokensDBLP as (
      select element i
      from  unrankedTokensDBLP as token,
            (
          select element tokenGroupped
          from  DBLP_fuzzyjoin_078 as paper,
                fuzzyjoin_078.`counthashed-word-tokens`(paper.title) as token
          /* +hash */
          group by token as tokenGroupped
          order by count(paper),tokenGroupped
      ) as tokenRanked at i
      where (token = tokenRanked)
      order by i
  )
order by paperDBLP.id
;