blob: 3271c8adc1fc9099ba04f2a1949c235fe990d8ff [file] [log] [blame]
alexander.behmc576c602012-07-06 02:41:15 +00001/*
Ian Maxon857dc132015-09-25 17:13:19 -07002 * 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/*
alexander.behmc576c602012-07-06 02:41:15 +000020 * Description : Tests whether an ngram_index is applied to optimize a selection query using the similarity-jaccard-check function on 3-gram tokens.
21 * Tests that the optimizer rule correctly drills through the let clauses.
22 * The index should be applied.
23 * Success : Yes
24 */
25
26drop dataverse test if exists;
27create dataverse test;
28use dataverse test;
ramangrover29a3211202013-05-19 11:56:49 -070029set import-private-functions 'true';
alexander.behmc576c602012-07-06 02:41:15 +000030
31create type DBLPType as closed {
32 id: int32,
33 dblpid: string,
34 title: string,
35 authors: string,
36 misc: string
37}
38
ramangrover29669d8f62013-02-11 06:03:32 +000039create dataset DBLP(DBLPType) primary key id;
alexander.behmc576c602012-07-06 02:41:15 +000040
alexander.behmc576c602012-07-06 02:41:15 +000041create index ngram_index on DBLP(title) type ngram(3);
42
Ian Maxonf7b64532015-12-09 17:28:18 -080043write output to asterix_nc1:"rttest/inverted-index-complex_ngram-jaccard-check-let.adm";
alexander.behmc576c602012-07-06 02:41:15 +000044
45for $o in dataset('DBLP')
46let $jacc := similarity-jaccard-check(gram-tokens($o.title, 3, false), gram-tokens("Transactions for Cooperative Environments", 3, false), 0.5f)
47where $jacc[0]
ramangrover29a3211202013-05-19 11:56:49 -070048return $o