Github user mn-mikke commented on a diff in the pull request:
https://github.com/apache/spark/pull/22017#discussion_r209533017
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala
---
@@ -442,3 +442,186 @@ case class ArrayAggregate(
override def prettyName: String = "aggregate"
}
+
+/**
+ * Merges two given maps into a single map by applying function to the
pair of values with
+ * the same key.
+ */
+@ExpressionDescription(
+ usage =
+ """
+ _FUNC_(map1, map2, function) - Merges two given maps into a single
map by applying
+ function to the pair of values with the same key. For keys only
presented in one map,
+ NULL will be passed as the value for the missing key. If an input
map contains duplicated
+ keys, only the first entry of the duplicated key is passed into the
lambda function.
+ """,
+ examples = """
+ Examples:
+ > SELECT _FUNC_(map(1, 'a', 2, 'b'), map(1, 'x', 2, 'y'), (k, v1,
v2) -> concat(v1, v2));
+ {1:"ax",2:"by"}
+ """,
+ since = "2.4.0")
+case class MapZipWith(left: Expression, right: Expression, function:
Expression)
+ extends HigherOrderFunction with CodegenFallback {
+
+ @transient lazy val functionForEval: Expression = functionsForEval.head
+
+ @transient lazy val (leftKeyType, leftValueType, leftValueContainsNull) =
+ HigherOrderFunction.mapKeyValueArgumentType(left.dataType)
+
+ @transient lazy val (rightKeyType, rightValueType,
rightValueContainsNull) =
+ HigherOrderFunction.mapKeyValueArgumentType(right.dataType)
+
+ @transient lazy val keyType =
+ TypeCoercion.findTightestCommonType(leftKeyType,
rightKeyType).getOrElse(NullType)
--- End diff --
Oh, I see. We also need to check the output data type of lambda functions
for the expressions like ```ArrayFilter```.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
