Github user HyukjinKwon commented on a diff in the pull request:
https://github.com/apache/spark/pull/20938#discussion_r179969902
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
---
@@ -287,3 +289,165 @@ case class ArrayContains(left: Expression, right:
Expression)
override def prettyName: String = "array_contains"
}
+
+/**
+ * Transforms an array of arrays into a single array.
+ */
+@ExpressionDescription(
+ usage = "_FUNC_(arrayOfArrays) - Transforms an array of arrays into a
single array.",
+ examples = """
+ Examples:
+ > SELECT _FUNC_(array(array(1, 2), array(3, 4));
+ [1,2,3,4]
+ """)
+case class Flatten(child: Expression) extends UnaryExpression {
+
+ override def nullable: Boolean = child.nullable || dataType.containsNull
+
+ override def dataType: ArrayType = {
+ child
+ .dataType.asInstanceOf[ArrayType]
+ .elementType.asInstanceOf[ArrayType]
+ }
+
+ override def checkInputDataTypes(): TypeCheckResult = {
+ if (
+ ArrayType.acceptsType(child.dataType) &&
+
ArrayType.acceptsType(child.dataType.asInstanceOf[ArrayType].elementType)
+ ) {
--- End diff --
How about this?
```scala
child.dataType match {
case _: ArrayType(_: ArrayType, _) =>
TypeCheckResult.TypeCheckSuccess
case _: =>
TypeCheckResult.TypeCheckFailure(
"The argument should be an array of arrays, " +
s"but '${child.sql}' is of ${child.dataType.simpleString} type.")
}
```
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
