Ian Maxon | 857dc13 | 2015-09-25 17:13:19 -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 | */ |
alexander.behm | c576c60 | 2012-07-06 02:41:15 +0000 | [diff] [blame] | 19 | drop dataverse test if exists; |
| 20 | create dataverse test; |
| 21 | use dataverse test; |
| 22 | |
| 23 | create type DBLPType as closed { |
| 24 | id: int32, |
| 25 | dblpid: string, |
| 26 | title: string, |
| 27 | authors: string, |
| 28 | misc: string |
| 29 | } |
| 30 | |
| 31 | create nodegroup group1 if not exists on nc1, nc2; |
| 32 | |
| 33 | create dataset DBLP(DBLPType) |
ramangrover29 | 669d8f6 | 2013-02-11 06:03:32 +0000 | [diff] [blame] | 34 | primary key id on group1; |
alexander.behm | c576c60 | 2012-07-06 02:41:15 +0000 | [diff] [blame] | 35 | |
| 36 | load dataset DBLP |
Ian Maxon | f18bba2 | 2015-08-21 12:35:14 -0700 | [diff] [blame] | 37 | using "org.apache.asterix.external.dataset.adapter.NCFileSystemAdapter" |
alexander.behm | c576c60 | 2012-07-06 02:41:15 +0000 | [diff] [blame] | 38 | (("path"="nc1://data/dblp-small/dblp-small-id.txt"),("format"="delimited-text"),("delimiter"=":")) pre-sorted; |
| 39 | |
| 40 | write output to nc1:"rttest/consolidate-complex-selects.aql"; |
| 41 | |
| 42 | for $paper in dataset('DBLP') |
| 43 | let $paper_tokens := word-tokens($paper.title) |
| 44 | let $query_tokens := word-tokens("Transactions for Cooperative Environments") |
| 45 | let $jacca := similarity-jaccard-check($paper_tokens, $query_tokens, 0.8f) |
| 46 | let $jaccb := similarity-jaccard-check($paper_tokens, $query_tokens, 0.5f) |
| 47 | let $jaccc := similarity-jaccard-check($paper_tokens, $query_tokens, 0.3f) |
| 48 | where $jacca[0] and $jaccb[0] and $paper.authors = "testauth" and $jaccc |
Ian Maxon | 857dc13 | 2015-09-25 17:13:19 -0700 | [diff] [blame] | 49 | return {"Paper": $paper_tokens, "Query": $query_tokens } |