| /* |
| * 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' word tokens. |
| * DBLP has a keyword index on title, and we expect the join to be transformed into an indexed nested-loop join. |
| * We test the inlining of variables that enable the select to be pushed into the join for subsequent optimization with an index. |
| * We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary. |
| * Success : Yes |
| */ |
| |
| use test; |
| |
| |
| set `import-private-functions` `true`; |
| |
| select element {'a':a.title,'b':b.title,'jacc':jacc} |
| from DBLP as a, |
| CSX as b |
| with jacc as test.`similarity-jaccard`(test.`word-tokens`(a.title),test.`word-tokens`(b.title)) |
| where ((jacc >= 0.500000f) and (a.id < b.id)) |
| order by jacc,a.id,b.id |
| ; |
