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

/*
 * Description    : Tests whether a keyword is applied to optimize a selection query with ~= using Jaccard on lists.
 *                  The index should be applied.
 * Success        : Yes
 */

drop dataverse test if exists;
create dataverse test;
use dataverse test;

create type AddressType as closed {
  number: int32, 
  street: string,
  city: string
}

create type CustomerType as closed {
  cid: int32, 
  name: string,
  age: int32?,
  address: AddressType?,
  interests: [string],
  children: [ { name: string, age: int32? } ]
}

create dataset Customers(CustomerType) partitioned by key cid;

load dataset Customers 
using "edu.uci.ics.asterix.external.dataset.adapter.NCFileSystemAdapter"
(("path"="nc1://data/semistructured/co1k_olist/customer.adm"),("format"="adm"));

create index interests_index on Customers(interests) type keyword;

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

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

for $c in dataset('Customers')
where $c.interests ~= ["databases", "computers", "wine"]
return $c