Jianfeng Jia | 5a2698d | 2016-02-14 00:08:02 -0800 | [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 | * Description : Tests keyword index and the ngram indexe should trigger intersection rule |
| 21 | * Success : Yes |
| 22 | */ |
| 23 | |
| 24 | drop dataverse test if exists; |
| 25 | create dataverse test; |
| 26 | use dataverse test; |
| 27 | |
| 28 | create type tTweet as closed { |
| 29 | id: int32, |
| 30 | message: string, |
| 31 | create_at: datetime, |
| 32 | misc: string |
| 33 | } |
| 34 | |
| 35 | create dataset dsTweet(tTweet) primary key id; |
| 36 | |
| 37 | create index msg_index on dsTweet(message) type ngram(3); |
| 38 | create index msc_index on dsTweet(misc) type keyword; |
| 39 | |
| 40 | for $t in dataset dsTweet |
| 41 | let $ed := edit-distance($t.message, "Suzanna Tilson") |
| 42 | let $jacc := similarity-jaccard-check(word-tokens($t.misc), word-tokens("love like verizon"), 0.2f) |
| 43 | where $jacc[0] and $ed <= 2 |
| 44 | return $t |
| 45 | |