| drop dataverse fuzzyjoin_078 if exists; |
| create dataverse fuzzyjoin_078; |
| use dataverse fuzzyjoin_078; |
| create type DBLPType as open { |
| create nodegroup group1 if not exists on nc1, nc2; |
| create dataset DBLP_fuzzyjoin_078(DBLPType) |
| primary key id on group1; |
| write output to nc1:'rttest/fuzzyjoin_078.adm'; |
| for $paperDBLP in dataset('DBLP_fuzzyjoin_078') |
| let $unrankedTokensDBLP := counthashed-word-tokens($paperDBLP.title) |
| for $token in $unrankedTokensDBLP |
| for $tokenRanked at $i in |
| for $paper in dataset('DBLP_fuzzyjoin_078') |
| for $token in counthashed-word-tokens($paper.title) |
| group by $tokenGroupped := $token with $paper |
| order by count($paper), $tokenGroupped |
| where $token = /*+ bcast */ $tokenRanked |
| return {'id': $paperDBLP.id, 'tokens':$tokensDBLP} |