ygf11 commented on code in PR #5345:
URL: https://github.com/apache/arrow-datafusion/pull/5345#discussion_r1124143715
##########
datafusion/optimizer/src/decorrelate_where_exists.rs:
##########
@@ -670,4 +673,76 @@ mod tests {
assert_plan_eq(&plan, expected)
}
+
+ #[test]
+ fn exists_distinct_subquery() -> Result<()> {
+ let table_scan = test_table_scan()?;
+ let subquery_scan = test_table_scan_with_name("sq")?;
+ let subquery = LogicalPlanBuilder::from(subquery_scan)
+ .filter((lit(1u32) + col("sq.a")).gt(col("test.a") * lit(2u32)))?
+ .project(vec![col("sq.c")])?
+ .distinct()?
+ .build()?;
+ let plan = LogicalPlanBuilder::from(table_scan)
+ .filter(exists(Arc::new(subquery)))?
+ .project(vec![col("test.b")])?
+ .build()?;
+
+ let expected = "Projection: test.b [b:UInt32]\
+ \n LeftSemi Join: Filter: UInt32(1) + sq.a > test.a
* UInt32(2) [a:UInt32, b:UInt32, c:UInt32]\
+ \n TableScan: test [a:UInt32, b:UInt32, c:UInt32]\
+ \n Distinct: [a:UInt32]\
+ \n Projection: sq.a [a:UInt32]\
+ \n TableScan: sq [a:UInt32, b:UInt32,
c:UInt32]";
+
+ assert_plan_eq(&plan, expected)
+ }
+
+ #[test]
+ fn exists_distinct_expr_subquery() -> Result<()> {
+ let table_scan = test_table_scan()?;
+ let subquery_scan = test_table_scan_with_name("sq")?;
+ let subquery = LogicalPlanBuilder::from(subquery_scan)
+ .filter((lit(1u32) + col("sq.a")).gt(col("test.a") * lit(2u32)))?
+ .project(vec![col("sq.b") + col("sq.c")])?
+ .distinct()?
+ .build()?;
+ let plan = LogicalPlanBuilder::from(table_scan)
+ .filter(exists(Arc::new(subquery)))?
+ .project(vec![col("test.b")])?
+ .build()?;
+
+ let expected = "Projection: test.b [b:UInt32]\
+ \n LeftSemi Join: Filter: UInt32(1) + sq.a > test.a
* UInt32(2) [a:UInt32, b:UInt32, c:UInt32]\
+ \n TableScan: test [a:UInt32, b:UInt32, c:UInt32]\
+ \n Distinct: [a:UInt32]\
+ \n Projection: sq.a [a:UInt32]\
+ \n TableScan: sq [a:UInt32, b:UInt32,
c:UInt32]";
+
+ assert_plan_eq(&plan, expected)
+ }
Review Comment:
I find the behaviors of `Distinct` in postgres and spark are not same.
* For postgres, it will not add back the distinct to the optimized result.
* For spark, it will add back the distinct, and will keep the unused project
exprs(`sq.b + sq.c` in the above).
I think `sq.b + sq.c` is not used any more, so remove it.
I am not sure if the way of this pr is appropriate.
I want to hear your advice @mingmwang @alamb @jackwener
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
