diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala index 765327c474e692a0de77ffad106d84e12cdcd074..d3163dcd4db94083710a4418a70ba8bc4e428e6d 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/Analyzer.scala @@ -224,10 +224,15 @@ class Analyzer( case other => Alias(other, other.toString)() } - // TODO: We need to use bitmasks to determine which grouping expressions need to be - // set as nullable. For example, if we have GROUPING SETS ((a,b), a), we do not need - // to change the nullability of a. - val attributeMap = groupByAliases.map(a => (a -> a.toAttribute.withNullability(true))).toMap + val nonNullBitmask = x.bitmasks.reduce(_ & _) + + val attributeMap = groupByAliases.zipWithIndex.map { case (a, idx) => + if ((nonNullBitmask & 1 << idx) == 0) { + (a -> a.toAttribute.withNullability(true)) + } else { + (a -> a.toAttribute) + } + }.toMap val aggregations: Seq[NamedExpression] = x.aggregations.map { // If an expression is an aggregate (contains a AggregateExpression) then we dont change