You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@arrow.apache.org by "ygf11 (via GitHub)" <gi...@apache.org> on 2023/03/03 06:42:58 UTC
[GitHub] [arrow-datafusion] ygf11 commented on a diff in pull request #5345: Refactor DecorrelateWhereExists and add back Distinct if needs
ygf11 commented on code in PR #5345:
URL: https://github.com/apache/arrow-datafusion/pull/5345#discussion_r1113985889
##########
datafusion/optimizer/src/decorrelate_where_exists.rs:
##########
@@ -644,4 +690,102 @@ 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, c:UInt32]\
+ \n Projection: sq.a, sq.c [a:UInt32, c:UInt32]\
+ \n TableScan: sq [a:UInt32, b:UInt32, c:UInt32]";
+
+ assert_plan_eq(&plan, expected)
+ }
+
+ #[test]
+ fn exists_distinct_subquery_with_literal() -> 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![lit(1u32), 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, c:UInt32]\
+ \n Projection: sq.a, sq.c [a:UInt32, c:UInt32]\
+ \n TableScan: sq [a:UInt32, b:UInt32, c:UInt32]";
+
+ assert_plan_eq(&plan, expected)
+ }
+
+ #[test]
+ fn exists_distinct_subquery_dedup_cols() -> Result<()> {
+ let table_scan = test_table_scan()?;
+ let subquery_scan = test_table_scan_with_name("sq")?;
+ // "sq.a" both in projection and filter
+ let subquery = LogicalPlanBuilder::from(subquery_scan)
+ .filter((lit(1u32) + col("sq.a")).gt(col("test.a") * lit(2u32)))?
+ .project(vec![lit("sq.a"), 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, c:UInt32]\
+ \n Projection: sq.a, sq.c [a:UInt32, c:UInt32]\
+ \n TableScan: sq [a:UInt32, b:UInt32, c:UInt32]";
+
+ assert_plan_eq(&plan, expected)
+ }
+
+ #[test]
+ fn exists_subquery_infer_distinct() -> Result<()> {
+ let table_scan = test_table_scan()?;
+ let subquery_scan = test_table_scan_with_name("sq")?;
+
+ let subquery = LogicalPlanBuilder::from(subquery_scan)
+ .filter(col("sq.a").gt(col("test.b")))?
+ .project(vec![col("sq.a"), col("sq.c")])?
+ .aggregate(vec![col("a"), col("c")], Vec::<Expr>::new())?
+ .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: sq.a > test.b [a:UInt32, b:UInt32, c:UInt32]\
+ \n TableScan: test [a:UInt32, b:UInt32, c:UInt32]\
+ \n Aggregate: groupBy=[[sq.a, sq.c]], aggr=[[]] [a:UInt32, c:UInt32]\
+ \n Projection: sq.a, sq.c [a:UInt32, c:UInt32]\
+ \n TableScan: sq [a:UInt32, b:UInt32, c:UInt32]";
+
Review Comment:
The aggregate can be treated as DISTINCT.
##########
datafusion/optimizer/src/decorrelate_where_exists.rs:
##########
@@ -644,4 +690,102 @@ 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, c:UInt32]\
+ \n Projection: sq.a, sq.c [a:UInt32, c:UInt32]\
+ \n TableScan: sq [a:UInt32, b:UInt32, c:UInt32]";
+
+ assert_plan_eq(&plan, expected)
+ }
+
+ #[test]
+ fn exists_distinct_subquery_with_literal() -> 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![lit(1u32), 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, c:UInt32]\
+ \n Projection: sq.a, sq.c [a:UInt32, c:UInt32]\
+ \n TableScan: sq [a:UInt32, b:UInt32, c:UInt32]";
+
Review Comment:
The literal will be removed.
--
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: github-unsubscribe@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org