| drop dataverse fuzzyjoin if exists; |
| |
| create dataverse fuzzyjoin; |
| |
| use dataverse fuzzyjoin; |
| |
| create type DBLPType as closed { |
| id: int32, |
| dblpid: string, |
| title: string, |
| authors: string, |
| misc: string |
| } |
| |
| create dataset DBLP(DBLPType) partitioned by key id; |
| |
| load dataset DBLP from nc1:'data/pub-small/dblp-small-id.txt' delimited by ':'; |
| |
| write output to nc1:'rttest/fuzzyjoin_dblp-aqlplus_1.adm'; |
| |
| set simthreshold '.5f'; |
| |
| for $dblp in dataset('DBLP') |
| for $dblp2 in dataset('DBLP') |
| where $dblp.title ~= $dblp2.title and $dblp.id < $dblp2.id |
| order by $dblp.id, $dblp2.id |
| return {'dblp': $dblp, 'dblp2': $dblp2} |