/*
 * 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 `fj-dblp-csx` if exists;
create  dataverse `fj-dblp-csx`;

use `fj-dblp-csx`;


create type `fj-dblp-csx`.DBLPType as
{
  id : int32,
  dblpid : string,
  title : string,
  authors : string,
  misc : string
}

create type `fj-dblp-csx`.CSXType as
{
  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 on group1;

create  dataset CSX(CSXType) primary key id on group1;

write output to asterix_nc1:"rttest/fj-dblp-csx.adm"
select element {'idDBLP':idDBLP,'idCSX':idCSX}
from  DBLP as paperDBLP,
      tokensDBLP as prefixTokenDBLP,
      CSX as paperCSX,
      tokensCSX as prefixTokenCSX
with  idDBLP as paperDBLP.id,
      unrankedTokensDBLP as `fj-dblp-csx`.`counthashed-word-tokens`(paperDBLP.title),
      tokensDBLP as (
      select element i
      from  unrankedTokensDBLP as token,
            (
          select element paper.title
          from  DBLP as paper
      ) as tokenRanked at i
      where (token = tokenRanked)
      order by i
  ),
      idCSX as paperCSX.id,
      unrankedTokensCSX as `fj-dblp-csx`.`counthashed-word-tokens`(paperCSX.title),
      tokensCSX as (
      select element i
      from  unrankedTokensCSX as token,
            (
          select element paper.title
          from  DBLP as paper
      ) as tokenRanked at i
      where (token = tokenRanked)
      order by i
  )
where (prefixTokenDBLP = prefixTokenCSX)
group by idDBLP as idDBLP,idCSX as idCSX
order by idDBLP,idCSX
;