Fixed ASTERIXDB-1249 and ASTERIXDB-1250: self index-nested-loop join correctly identifies the outer and the inner branch.
The first dataset becomes the outer branch.
The second dataset becomes the inner branch.
The optimizer for index-nested-loop join now only try to use an index from the inner branch.
Change-Id: I0d4291197c2bcfbcdcde998c5952af41960c4ad7
Reviewed-on: https://asterix-gerrit.ics.uci.edu/576
Reviewed-by: Yingyi Bu <buyingyi@gmail.com>
Tested-by: Jenkins <jenkins@fulliautomatix.ics.uci.edu>
diff --git a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-fuzzyeq-jaccard.aql b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-fuzzyeq-jaccard.aql
index 635b331..72e4b69 100644
--- a/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-fuzzyeq-jaccard.aql
+++ b/asterix-app/src/test/resources/optimizerts/queries/inverted-index-join-noeqjoin/ngram-fuzzyeq-jaccard.aql
@@ -29,7 +29,7 @@
set import-private-functions 'true';
create type DBLPType as closed {
- id: int32,
+ id: int32,
dblpid: string,
title: string,
authors: string,
@@ -37,7 +37,7 @@
}
create type CSXType as closed {
- id: int32,
+ id: int32,
csxid: string,
title: string,
authors: string,
@@ -55,7 +55,7 @@
set simfunction 'jaccard';
set simthreshold '0.5f';
-for $a in dataset('DBLP')
for $b in dataset('CSX')
+for $a in dataset('DBLP')
where gram-tokens($a.title, 3, false) ~= gram-tokens($b.title, 3, false) and $a.id < $b.id
return {"atitle": $a.title, "btitle": $b.title}