asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-edit-distance-panic.aql

/*
 * Description    : Tests whether an ngram_index is applied to optimize a selection query using the edit-distance 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-panic.adm";

// This query cannot be optimized with an index, based on the high edit distance.
for $o in dataset('DBLP')
where edit-distance($o.authors, "Amihay Motro") <= 5
return $o