asterix-app/src/test/resources/optimizerts/queries/inverted-index-complex/ngram-jaccard-check-multi-let.aql

/*
 * Description    : Tests whether an ngram_index is applied to optimize a selection query using the similarity-jaccard-check function on 3-gram tokens.
 *                  Tests that the optimizer rule correctly drills through the let clauses.
 *                  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-complex_ngram-jaccard-check-multi-let.adm";

// This test is complex because we have three assigns to drill into.
for $paper in dataset('DBLP')
let $paper_tokens := gram-tokens($paper.title, 3, false)
let $query_tokens := gram-tokens("Transactions for Cooperative Environments", 3, false)
let $jacc := similarity-jaccard-check($paper_tokens, $query_tokens, 0.5f)
where $jacc[0]
return {"Paper": $paper_tokens, "Query": $query_tokens }