diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala index 899227674f2acc4d23a9025f724d4fe07986f6e8..ac9693e079f51d28b6a02549d69c0b0d18fc9757 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/CheckAnalysis.scala @@ -73,9 +73,9 @@ trait CheckAnalysis extends PredicateHelper { s"invalid cast from ${c.child.dataType.simpleString} to ${c.dataType.simpleString}") case g: Grouping => - failAnalysis(s"grouping() can only be used with GroupingSets/Cube/Rollup") + failAnalysis("grouping() can only be used with GroupingSets/Cube/Rollup") case g: GroupingID => - failAnalysis(s"grouping_id() can only be used with GroupingSets/Cube/Rollup") + failAnalysis("grouping_id() can only be used with GroupingSets/Cube/Rollup") case w @ WindowExpression(AggregateExpression(_, _, true, _), _) => failAnalysis(s"Distinct window functions are not supported: $w") diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala index 1f4ff9c4b184ead52f447db53087d6841a4236bd..ac2cefaddcf5925a3ce431b88c1c3dae0ea2faf3 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregate/collect.scala @@ -20,6 +20,7 @@ package org.apache.spark.sql.catalyst.expressions.aggregate import scala.collection.generic.Growable import scala.collection.mutable +import org.apache.spark.sql.catalyst.analysis.TypeCheckResult import org.apache.spark.sql.catalyst.expressions._ import org.apache.spark.sql.catalyst.util.GenericArrayData import org.apache.spark.sql.catalyst.InternalRow @@ -107,6 +108,14 @@ case class CollectSet( def this(child: Expression) = this(child, 0, 0) + override def checkInputDataTypes(): TypeCheckResult = { + if (!child.dataType.existsRecursively(_.isInstanceOf[MapType])) { + TypeCheckResult.TypeCheckSuccess + } else { + TypeCheckResult.TypeCheckFailure("collect_set() cannot have map type data") + } + } + override def withNewMutableAggBufferOffset(newMutableAggBufferOffset: Int): ImperativeAggregate = copy(mutableAggBufferOffset = newMutableAggBufferOffset) diff --git a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala index 69a990789bcfd16e670f921b0f10f393b50afabf..92aa7b95434dcac3a735fa412dc0daa00bfa0705 100644 --- a/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala +++ b/sql/core/src/test/scala/org/apache/spark/sql/DataFrameAggregateSuite.scala @@ -457,6 +457,16 @@ class DataFrameAggregateSuite extends QueryTest with SharedSQLContext { ) } + test("collect_set functions cannot have maps") { + val df = Seq((1, 3, 0), (2, 3, 0), (3, 4, 1)) + .toDF("a", "x", "y") + .select($"a", map($"x", $"y").as("b")) + val error = intercept[AnalysisException] { + df.select(collect_set($"a"), collect_set($"b")) + } + assert(error.message.contains("collect_set() cannot have map type data")) + } + test("SPARK-14664: Decimal sum/avg over window should work.") { checkAnswer( spark.sql("select sum(a) over () from values 1.0, 2.0, 3.0 T(a)"),