alexander.behm | c576c60 | 2012-07-06 02:41:15 +0000 | [diff] [blame] | 1 | /* |
Ian Maxon | 857dc13 | 2015-09-25 17:13:19 -0700 | [diff] [blame] | 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 | /* |
alexander.behm | c576c60 | 2012-07-06 02:41:15 +0000 | [diff] [blame] | 20 | * Description : Tests whether an ngram_index is applied to optimize a selection query using the similarity-jaccard-check function on 3-gram tokens. |
| 21 | * The index should be applied. |
| 22 | * Success : Yes |
| 23 | */ |
| 24 | |
| 25 | drop dataverse test if exists; |
| 26 | create dataverse test; |
| 27 | use dataverse test; |
ramangrover29 | a321120 | 2013-05-19 11:56:49 -0700 | [diff] [blame] | 28 | set import-private-functions 'true'; |
alexander.behm | c576c60 | 2012-07-06 02:41:15 +0000 | [diff] [blame] | 29 | |
| 30 | create type DBLPType as closed { |
| 31 | id: int32, |
| 32 | dblpid: string, |
| 33 | title: string, |
| 34 | authors: string, |
| 35 | misc: string |
| 36 | } |
| 37 | |
ramangrover29 | 669d8f6 | 2013-02-11 06:03:32 +0000 | [diff] [blame] | 38 | create dataset DBLP(DBLPType) primary key id; |
alexander.behm | c576c60 | 2012-07-06 02:41:15 +0000 | [diff] [blame] | 39 | |
alexander.behm | c576c60 | 2012-07-06 02:41:15 +0000 | [diff] [blame] | 40 | create index ngram_index on DBLP(title) type ngram(3); |
| 41 | |
| 42 | write output to nc1:"rttest/inverted-index-basic_ngram-jaccard-check.adm"; |
| 43 | |
| 44 | for $o in dataset('DBLP') |
| 45 | where similarity-jaccard-check(gram-tokens($o.title, 3, false), gram-tokens("Transactions for Cooperative Environments", 3, false), 0.5f)[0] |
ramangrover29 | a321120 | 2013-05-19 11:56:49 -0700 | [diff] [blame] | 46 | return $o |