/*
 * Description    : Fuzzy self joins a dataset, DBLP, based on the edit-distance-check function of its authors.
 *                  DBLP has a 3-gram index on authors, and we expect the join to be transformed into an indexed nested-loop join.
 * 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;

create index ngram_index on DBLP(authors) type ngram(3);

write output to nc1:"rttest/inverted-index-join_ngram-edit-distance-check_03.adm";

for $a in dataset('DBLP')
for $b in dataset('DBLP')
where edit-distance-check($a.authors, $b.authors, 3)[0] and $a.id < $b.id
return {"arec": $a, "brec": $b }