wangyum commented on a change in pull request #28575:
URL: https://github.com/apache/spark/pull/28575#discussion_r432965667
##########
File path:
sql/catalyst/src/test/scala/org/apache/spark/sql/catalyst/optimizer/FilterPushdownSuite.scala
##########
@@ -1230,4 +1233,154 @@ class FilterPushdownSuite extends PlanTest {
comparePlans(Optimize.execute(query.analyze), expected)
}
+
+ test("inner join: rewrite filter predicates to conjunctive normal form") {
+ val x = testRelation.subquery('x)
+ val y = testRelation.subquery('y)
+
+ val originalQuery = {
+ x.join(y)
+ .where(("x.b".attr === "y.b".attr)
+ && (("x.a".attr > 3) && ("y.a".attr > 13) || ("x.a".attr > 1) &&
("y.a".attr > 11)))
+ }
+
+ val optimized = Optimize.execute(originalQuery.analyze)
+ val left = testRelation.where(('a > 3 || 'a > 1)).subquery('x)
+ val right = testRelation.where('a > 13 || 'a > 11).subquery('y)
+ val correctAnswer =
+ left.join(right, condition = Some("x.b".attr === "y.b".attr
+ && (("x.a".attr > 3) && ("y.a".attr > 13) || ("x.a".attr > 1) &&
("y.a".attr > 11))))
+ .analyze
+
+ comparePlans(optimized, correctAnswer)
+ }
+
+ test("inner join: rewrite join predicates to conjunctive normal form") {
+ val x = testRelation.subquery('x)
+ val y = testRelation.subquery('y)
+
+ val originalQuery = {
+ x.join(y, condition = Some(("x.b".attr === "y.b".attr)
+ && (("x.a".attr > 3) && ("y.a".attr > 13) || ("x.a".attr > 1) &&
("y.a".attr > 11))))
+ }
+
+ val optimized = Optimize.execute(originalQuery.analyze)
+ val left = testRelation.where('a > 3 || 'a > 1).subquery('x)
+ val right = testRelation.where('a > 13 || 'a > 11).subquery('y)
+ val correctAnswer =
+ left.join(right, condition = Some("x.b".attr === "y.b".attr
+ && (("x.a".attr > 3) && ("y.a".attr > 13) || ("x.a".attr > 1) &&
("y.a".attr > 11))))
+ .analyze
+
+ comparePlans(optimized, correctAnswer)
Review comment:
Match the `PostgreSQL`'s plan:
```
postgres=# explain select x.* from x join y on (x.b = y.b and ( (x.a > 3 and
y.a > 13 ) or (x.a > 1 and y.a > 11) ));
QUERY PLAN
---------------------------------------------------------------------------
Merge Join (cost=178.36..315.60 rows=3593 width=16)
Merge Cond: (x.b = y.b)
Join Filter: (((x.a > 3) AND (y.a > 13)) OR ((x.a > 1) AND (y.a > 11)))
-> Sort (cost=89.18..91.75 rows=1028 width=16)
Sort Key: x.b
-> Seq Scan on x (cost=0.00..37.75 rows=1028 width=16)
Filter: ((a > 3) OR (a > 1))
-> Sort (cost=89.18..91.75 rows=1028 width=8)
Sort Key: y.b
-> Seq Scan on y (cost=0.00..37.75 rows=1028 width=8)
Filter: ((a > 13) OR (a > 11))
(11 rows)
```
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
