| /* |
| * Description : Tests whether an ngram_index is applied to optimize a selection query using the edit-distance-check function on strings. |
| * The index should *not* be applied (see below). |
| * 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; |
| |
| 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; |
| |
| create index ngram_index on DBLP(authors) type ngram(3); |
| |
| write output to nc1:"rttest/inverted-index-basic_ngram-edit-distance-check-panic.adm"; |
| |
| // This query cannot be optimized with an index, based on the high edit distance. |
| for $o in dataset('DBLP') |
| let $ed := edit-distance-check($o.authors, "Amihay Motro", 5) |
| where $ed[0] |
| return $o |