| use dataverse fuzzyjoin; | |
| // | |
| // -- - Stage 2 - -- | |
| // | |
| for $paperDBLP in dataset('DBLP') | |
| let $tokensDBLP := | |
| for $tokenUnranked in counthashed-word-tokens($paperDBLP.title) | |
| for $tokenRanked at $i in | |
| // | |
| // -- - Stage 1 - -- | |
| // | |
| for $paper in dataset('DBLP') | |
| let $id := $paper.id | |
| for $token in counthashed-word-tokens($paper.title) | |
| group by $tokenGroupped := $token with $id | |
| order by count($id), $tokenGroupped | |
| return $tokenGroupped | |
| where $tokenUnranked = $tokenRanked | |
| order by $i | |
| return $i | |
| for $prefixTokenDBLP in subset-collection( | |
| $tokensDBLP, | |
| 0, | |
| prefix-len-jaccard(len($tokensDBLP), .5f)) | |
| for $paperCSX in dataset('CSX') | |
| let $tokensCSX := | |
| for $tokenUnranked in counthashed-word-tokens($paperCSX.title) | |
| for $tokenRanked at $i in | |
| // | |
| // -- - Stage 1 - -- | |
| // | |
| for $paper in dataset('DBLP') | |
| let $id := $paper.id | |
| for $token in counthashed-word-tokens($paper.title) | |
| group by $tokenGroupped := $token with $id | |
| order by count($id), $tokenGroupped | |
| return $tokenGroupped | |
| where $tokenUnranked = $tokenRanked | |
| order by $i | |
| return $i | |
| for $prefixTokenCSX in subset-collection( | |
| $tokensCSX, | |
| 0, | |
| prefix-len-jaccard(len($tokensCSX), .5f)) | |
| where $prefixTokenDBLP = $prefixTokenCSX | |
| let $sim := similarity-jaccard-prefix( | |
| len(counthashed-word-tokens($paperDBLP.title)), | |
| $tokensDBLP, | |
| len(counthashed-word-tokens($paperCSX.title)), | |
| $tokensCSX, | |
| $prefixTokenDBLP, | |
| .5f) | |
| where $sim >= .5f | |
| group by $idDBLP := $paperDBLP.id, $idCSX := $paperCSX.id, $sim := $sim with $sim | |
| order by $idDBLP, $idCSX | |
| return {'idDBLP': $idDBLP, 'idCSX': $idCSX, 'sim': $sim[0]} |