Github user ueshin commented on a diff in the pull request:
https://github.com/apache/spark/pull/21045#discussion_r189786894
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
---
@@ -127,6 +127,148 @@ case class MapKeys(child: Expression)
override def prettyName: String = "map_keys"
}
+@ExpressionDescription(
+ usage = """_FUNC_(a1, a2, ...) - Returns a merged array containing in
the N-th position the
+ N-th value of each array given.""",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(array(1, 2, 3), array(2, 3, 4));
+ [[1, 2], [2, 3], [3, 4]]
+ > SELECT _FUNC_(array(1, 2), array(2, 3), array(3, 4));
+ [[1, 2, 3], [2, 3, 4]]
+ """,
+ since = "2.4.0")
+case class Zip(children: Seq[Expression]) extends Expression with
ExpectsInputTypes {
+
+ override def inputTypes: Seq[AbstractDataType] =
Seq.fill(children.length)(ArrayType)
+
+ override def dataType: DataType = ArrayType(mountSchema)
+
+ override def prettyName: String = "zip"
+
+ override def nullable: Boolean = children.forall(_.nullable)
+
+ lazy val numberOfArrays: Int = children.length
+
+ private lazy val arrayTypes =
children.map(_.dataType.asInstanceOf[ArrayType])
+
+ private lazy val arrayElementTypes = arrayTypes.map(_.elementType)
+
+ def mountSchema: StructType = {
+ val fields = arrayTypes.zipWithIndex.foldRight(List[StructField]()) {
case ((arr, idx), list) =>
+ StructField(s"_$idx", arr.elementType, children(idx).nullable ||
arr.containsNull) :: list
--- End diff --
The `nullable` should always be `true` for the case the array is shorter
than other arrays, regardless of the related nullabilities?
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
