asterix-app/src/test/resources/optimizerts/queries/inverted-index-basic/ngram-fuzzyeq-jaccard.aql

/*
 * Description    : Tests whether an ngram_index is applied to optimize a selection query with ~= using Jaccard on 3-gram tokens.
 *                  The index should be applied.
 * 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(title) type ngram(3);

write output to nc1:"rttest/inverted-index-basic_ngram-fuzzyeq-jaccard.adm";

set simfunction 'jaccard';
set simthreshold '0.8f';

for $o in dataset('DBLP')
where gram-tokens($o.title, 3, false) ~= gram-tokens("Transactions for Cooperative Environments", 3, false)
return $o