Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/22029#discussion_r229700708
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/expressions.scala
---
@@ -212,27 +212,34 @@ object ReorderAssociativeOperator extends
Rule[LogicalPlan] {
* 1. Converts the predicate to false when the list is empty and
* the value is not nullable.
* 2. Removes literal repetitions.
- * 3. Replaces [[In (value, seq[Literal])]] with optimized version
- * [[InSet (value, HashSet[Literal])]] which is much faster.
+ * 3. Replaces [[In (values, seq[Literal])]] with optimized version
+ * [[InSet (values, HashSet[Literal])]] which is much faster.
*/
object OptimizeIn extends Rule[LogicalPlan] {
def apply(plan: LogicalPlan): LogicalPlan = plan transform {
case q: LogicalPlan => q transformExpressionsDown {
- case In(v, list) if list.isEmpty =>
- // When v is not nullable, the following expression will be
optimized
+ case i @ In(values, list) if list.isEmpty =>
+ // When values are 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 isNotNull = if (SQLConf.get.inFalseForNullField) {
+ IsNotNull(i.value)
+ } else {
+ val valuesNotNull: Seq[Expression] = values.map(IsNotNull)
+ valuesNotNull.tail.foldLeft(valuesNotNull.head)(And)
--- End diff --
nit: `values.map(IsNotNull).reduce(And)`
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
