asterix-app/src/test/resources/optimizerts/queries/similarity/fuzzyeq-to-jaccard-check.aql

/*
 * Description    : Tests that the FuzzyEqRule rewrites ~= using Jaccard 
 *                  into edit-distance-check.
 * 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;

write output to nc1:"rttest/similarity_fuzzyeq-to-jaccard-check.adm";

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

// Tests two rules: FuzzyEqRule and SimilarityCheckRule
for $paper in dataset('DBLP')
where word-tokens($paper.title) ~= word-tokens("Transactions for Cooperative Environments")
return $paper