| /* |
| * Description : Fuzzy joins two datasets, DBLP and CSX, based on the edit-distance-check 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. |
| * 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 type CSXType as closed { |
| id: int32, |
| csxid: string, |
| title: string, |
| authors: string, |
| misc: string |
| } |
| |
| create dataset DBLP(DBLPType) partitioned by key id; |
| |
| create dataset CSX(CSXType) partitioned by key id; |
| |
| load dataset DBLP |
| using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter" |
| (("path"="nc1://data/dblp-small/dblp-small-id.txt"),("format"="delimited-text"),("delimiter"=":")) pre-sorted; |
| |
| load dataset CSX |
| using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter" |
| (("path"="nc1://data/pub-small/csx-small-id.txt"),("format"="delimited-text"),("delimiter"=":")); |
| |
| create index ngram_index on DBLP(authors) type ngram(3); |
| |
| write output to nc1:"rttest/inverted-index-join_ngram-edit-distance-check_01.adm"; |
| |
| for $a in dataset('DBLP') |
| for $b in dataset('CSX') |
| where edit-distance-check($a.authors, $b.authors, 3)[0] and $a.id < $b.id |
| return {"arec": $a, "brec": $b } |