| /* |
| * Description : Fuzzy self joins a dataset, DBLP, based on ~= using Jaccard of its titles' word tokens. |
| * DBLP has a keyword index on title, and we expect the join to be transformed into an indexed nested-loop join. |
| * Success : Yes |
| */ |
| |
| drop dataverse test if exists; |
| create dataverse test; |
| use dataverse test; |
| |
| create type DBLPType as closed { |
| id: int32, |
| dblpid: string, |
| title: string, |
| authors: string, |
| misc: string |
| } |
| |
| create dataset DBLP(DBLPType) partitioned by key id; |
| |
| create index keyword_index on DBLP(title) type keyword; |
| |
| write output to nc1:"rttest/inverted-index-join_word-fuzzyeq-jaccard_03.adm"; |
| |
| set simfunction 'jaccard'; |
| set simthreshold '0.5f'; |
| |
| for $a in dataset('DBLP') |
| for $b in dataset('DBLP') |
| where word-tokens($a.title) ~= word-tokens($b.title) and $a.id < $b.id |
| return {"arec": $a, "brec": $b } |