Github user viirya commented on a diff in the pull request:
https://github.com/apache/spark/pull/21442#discussion_r191338888
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala
---
@@ -219,10 +219,15 @@ object ReorderAssociativeOperator extends
Rule[LogicalPlan] {
object OptimizeIn extends Rule[LogicalPlan] {
def apply(plan: LogicalPlan): LogicalPlan = plan transform {
case q: LogicalPlan => q transformExpressionsDown {
- case In(v, list) if list.isEmpty && !v.nullable => FalseLiteral
+ case In(v, list) if list.isEmpty =>
+ // When v is not nullable, the following expression will be
optimized
+ // to FalseLiteral which is tested in OptimizeInSuite.scala
+ If(IsNotNull(v), FalseLiteral, Literal(null, BooleanType))
case expr @ In(v, list) if expr.inSetConvertible =>
val newList = ExpressionSet(list).toSeq
- if (newList.size > SQLConf.get.optimizerInSetConversionThreshold) {
+ if (newList.length == 1) {
--- End diff --
When `list.length == 1`, we don't need to create `ExpressionSet`.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
