check null value count for only null value column

Author: pengbo

sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/AggregateEstimation.scala

@@ -39,8 +39,16 @@ object AggregateEstimation {
       // Multiply distinct counts of group-by columns. This is an upper bound, which assumes
       // the data contains all combinations of distinct values of group-by columns.
       var outputRows: BigInt = agg.groupingExpressions.foldLeft(BigInt(1))(
-        (res, expr) => res *
-          childStats.attributeStats(expr.asInstanceOf[Attribute]).distinctCount.get.max(BigInt(1)))
+        (res, expr) => {
+          val columnStat = childStats.attributeStats(expr.asInstanceOf[Attribute])
+          val distinctValue: BigInt = if (columnStat.distinctCount.get == 0 &&
+            columnStat.nullCount.get > 0) {
+            1
+          } else {
+            columnStat.distinctCount.get
+          }
+          res * distinctValue
+        })
 
       outputRows = if (agg.groupingExpressions.isEmpty) {
         // If there's no group-by columns, the output is a single row containing values of aggregate