Yingyi Bu | 391f09e | 2015-10-29 13:49:39 -0700 | [diff] [blame] | 1 | /* |
| 2 | * Licensed to the Apache Software Foundation (ASF) under one |
| 3 | * or more contributor license agreements. See the NOTICE file |
| 4 | * distributed with this work for additional information |
| 5 | * regarding copyright ownership. The ASF licenses this file |
| 6 | * to you under the Apache License, Version 2.0 (the |
| 7 | * "License"); you may not use this file except in compliance |
| 8 | * with the License. You may obtain a copy of the License at |
| 9 | * |
| 10 | * http://www.apache.org/licenses/LICENSE-2.0 |
| 11 | * |
| 12 | * Unless required by applicable law or agreed to in writing, |
| 13 | * software distributed under the License is distributed on an |
| 14 | * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY |
| 15 | * KIND, either express or implied. See the License for the |
| 16 | * specific language governing permissions and limitations |
| 17 | * under the License. |
| 18 | */ |
| 19 | |
| 20 | drop database fuzzyjoin_078 if exists; |
| 21 | create database fuzzyjoin_078; |
| 22 | |
| 23 | use fuzzyjoin_078; |
| 24 | |
| 25 | |
| 26 | create type fuzzyjoin_078.DBLPType as |
| 27 | { |
| 28 | id : int32, |
| 29 | dblpid : string, |
| 30 | title : string, |
| 31 | authors : string, |
| 32 | misc : string |
| 33 | } |
| 34 | |
| 35 | create nodegroup group1 if not exists on |
Ian Maxon | f7b6453 | 2015-12-09 17:28:18 -0800 | [diff] [blame] | 36 | asterix_nc1, |
| 37 | asterix_nc2 |
Yingyi Bu | 391f09e | 2015-10-29 13:49:39 -0700 | [diff] [blame] | 38 | ; |
| 39 | create table DBLP_fuzzyjoin_078(DBLPType) primary key id on group1; |
| 40 | |
Ian Maxon | f7b6453 | 2015-12-09 17:28:18 -0800 | [diff] [blame] | 41 | write output to asterix_nc1:"rttest/fuzzyjoin_078.adm" |
Yingyi Bu | 391f09e | 2015-10-29 13:49:39 -0700 | [diff] [blame] | 42 | select element {'id':paperDBLP.id,'tokens':tokensDBLP} |
| 43 | from DBLP_fuzzyjoin_078 as paperDBLP |
| 44 | with unrankedTokensDBLP as fuzzyjoin_078."counthashed-word-tokens"(paperDBLP.title), |
| 45 | tokensDBLP as ( |
| 46 | select element i |
| 47 | from unrankedTokensDBLP as token, |
| 48 | ( |
| 49 | select element tokenGroupped |
| 50 | from DBLP_fuzzyjoin_078 as paper, |
| 51 | fuzzyjoin_078."counthashed-word-tokens"(paper.title) as token |
| 52 | /* +hash */ |
| 53 | group by token as tokenGroupped |
Yingyi Bu | 3dd80ec | 2016-04-01 10:31:53 -0700 | [diff] [blame^] | 54 | order by count(paper),tokenGroupped |
Yingyi Bu | 391f09e | 2015-10-29 13:49:39 -0700 | [diff] [blame] | 55 | ) as tokenRanked at i |
| 56 | where (token = tokenRanked) |
| 57 | order by i |
| 58 | ) |
| 59 | order by paperDBLP.id |
| 60 | ; |