| use dataverse fuzzy1; |
| |
| declare type DBLPType as open { |
| id: int32, |
| dblpid: string, |
| title: string, |
| authors: string, |
| misc: string |
| } |
| |
| declare nodegroup group1 on nc1, nc2; |
| |
| declare dataset DBLP(DBLPType) |
| partitioned by key id on group1; |
| |
| write output to nc1:'/tmp/dblp.adm'; |
| |
| set simthreshold '.5'; |
| |
| for $paperR in dataset('DBLP') |
| for $paperS in dataset('DBLP') |
| where $paperR.title ~= $paperS.title and $paperR.id < $paperS.id |
| return { 'R': { 'dblpid': $paperR.dblpid, 'title': $paperR.title }, |
| 'S': { 'dblpid': $paperS.dblpid, 'title': $paperS.title }} |