/*
 * Description    : Fuzzy self joins a dataset, DBLP, based on the similarity-jaccard function of its titles' 3-gram tokens.
 *                  DBLP has a 3-gram index on title, and we expect the join to be transformed into an indexed nested-loop join.
 *                  We test the inlining of variables that enable the select to be pushed into the join for subsequent optimization with an index.
 *                  We expect the top-level equi join introduced because of surrogate optimization to be removed, since it is not necessary.
 * 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(title) type ngram(3);

write output to nc1:"rttest/inverted-index-join-noeqjoin_ngram-jaccard-inline.adm";

for $a in dataset('DBLP')
for $b in dataset('DBLP')
let $jacc := similarity-jaccard(gram-tokens($a.title, 3, false), gram-tokens($b.title, 3, false))
where $jacc >= 0.5f and $a.id < $b.id
return {"atitle": $a.title, "btitle": $b.title, "jacc": $jacc}