| * Description : Fuzzy joins two datasets, DBLP and CSX, based on the edit-distance-contains function of their authors. |
| * DBLP has a 3-gram index on authors, and we expect the join to be transformed into an indexed nested-loop join. |
| drop dataverse test if exists; |
| create type DBLPType as closed { |
| create type CSXType as closed { |
| create dataset DBLP(DBLPType) primary key id; |
| create dataset CSX(CSXType) primary key id; |
| create index ngram_index on DBLP(authors) type ngram(3); |
| write output to nc1:"rttest/inverted-index-join_ngram-edit-distance-contains.adm"; |
| for $a in dataset('DBLP') |
| where edit-distance-contains($a.authors, $b.authors, 3)[0] and $a.id < $b.id |
| return {"arec": $a, "brec": $b } |