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