blob: 67475bc72ead44d94a22cf7754350bc3ad7d7d0f [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.
*/
drop dataverse fuzzyjoin if exists;
create dataverse fuzzyjoin;
use fuzzyjoin;
create type fuzzyjoin.DBLPType as
closed {
id : int32,
dblpid : string,
title : string,
authors : string,
misc : string
}
create type fuzzyjoin.TOKENSRANKEDADMType as
closed {
token : int32,
rank : int32
}
create nodegroup group1 if not exists on
asterix_nc1,
asterix_nc2
;
create dataset DBLP(DBLPType) primary key id on group1;
create dataset TOKENSRANKEDADM(TOKENSRANKEDADMType) primary key rank on group1;
write output to asterix_nc1:"rttest/unnest_list_in_subplan.adm"
select element {'id':idDBLP,'tokens':tokensDBLP}
from DBLP as paperDBLP
with idDBLP as paperDBLP.id,
tokensUnrankedDBLP as fuzzyjoin.`counthashed-word-tokens`(paperDBLP.title),
tokensDBLP as (
select element tokenRanked.rank
from tokensUnrankedDBLP as tokenUnranked,
TOKENSRANKEDADM as tokenRanked
where (tokenUnranked = tokenRanked.token)
order by tokenRanked.rank
)
;