Github user mn-mikke commented on a diff in the pull request: https://github.com/apache/spark/pull/22013#discussion_r210368929 --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala --- @@ -497,6 +497,62 @@ case class ArrayAggregate( override def prettyName: String = "aggregate" } +/** + * Transform Keys for every entry of the map by applying the transform_keys function. + * Returns map with transformed key entries + */ +@ExpressionDescription( + usage = "_FUNC_(expr, func) - Transforms elements in a map using the function.", + examples = """ + Examples: + > SELECT _FUNC_(map(array(1, 2, 3), array(1, 2, 3)), (k, v) -> k + 1); + map(array(2, 3, 4), array(1, 2, 3)) + > SELECT _FUNC_(map(array(1, 2, 3), array(1, 2, 3)), (k, v) -> k + v); + map(array(2, 4, 6), array(1, 2, 3)) + """, + since = "2.4.0") +case class TransformKeys( + argument: Expression, + function: Expression) + extends MapBasedSimpleHigherOrderFunction with CodegenFallback { + + override def nullable: Boolean = argument.nullable + + @transient lazy val MapType(keyType, valueType, valueContainsNull) = argument.dataType + + override def dataType: DataType = { + MapType(function.dataType, valueType, valueContainsNull) + } + + override def bind(f: (Expression, Seq[(DataType, Boolean)]) => LambdaFunction): TransformKeys = { + copy(function = f(function, (keyType, false) :: (valueType, valueContainsNull) :: Nil)) + } + + @transient lazy val LambdaFunction( + _, (keyVar: NamedLambdaVariable) :: (valueVar: NamedLambdaVariable) :: Nil, _) = function + + + override def nullSafeEval(inputRow: InternalRow, argumentValue: Any): Any = { + val map = argumentValue.asInstanceOf[MapData] + val f = functionForEval --- End diff -- Can't we use ```functionForEval``` directly?
--- --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org