Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/20687#discussion_r174606778
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/ComplexTypes.scala
---
@@ -22,54 +22,34 @@ import
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan
import org.apache.spark.sql.catalyst.rules.Rule
/**
-* push down operations into [[CreateNamedStructLike]].
-*/
-object SimplifyCreateStructOps extends Rule[LogicalPlan] {
- override def apply(plan: LogicalPlan): LogicalPlan = {
- plan.transformExpressionsUp {
- // push down field extraction
+ * Simplify redundant [[CreateNamedStructLike]], [[CreateArray]] and
[[CreateMap]] expressions.
+ */
+object SimplifyExtractValueOps extends Rule[LogicalPlan] {
+ override def apply(plan: LogicalPlan): LogicalPlan = plan transform {
case p =>
+ p.transformExpressionsUp {
--- End diff --
how about `select struct(a, b).a from t group by struct(a, b)`? We may
optimize it to `select a from t group by struct(a, b)`, which is invalid.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
