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

/*
 * Description    : Tests whether a keyword is applied to optimize a selection query with ~= using Jaccard on word 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 keyword_index on DBLP(title) type keyword;

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

set simfunction 'jaccard';
set simthreshold '0.5f';

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