asterix-app/src/test/resources/runtimets/queries/index-selection/fuzzy-inverted-index-ngram-jaccard.aql

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 nodegroup group1 if not exists on nc1, nc2;

create dataset DBLP(DBLPType) 
  partitioned by key id on group1;

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 fuzzy ngram(3);

write output to nc1:"rttest/index-selection_fuzzy-inverted-index-ngram-jaccard.adm";

for $o in dataset('DBLP')
let $jacc := similarity-jaccard-check(gram-tokens($o.title, 3, false), gram-tokens("Transactions for Cooperative Environments", 3, false), 0.5f)
where $jacc[0]
return $o