[GitHub] spark pull request #22031: [SPARK-23932][SQL] Higher order function zip_with

[techaddict <gi...@git.apache.org>]

Github user techaddict commented on a diff in the pull request:

    https://github.com/apache/spark/pull/22031#discussion_r210452329
  
    --- Diff: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/higherOrderFunctions.scala ---
    @@ -442,3 +442,91 @@ case class ArrayAggregate(
     
       override def prettyName: String = "aggregate"
     }
    +
    +// scalastyle:off line.size.limit
    +@ExpressionDescription(
    +  usage = "_FUNC_(left, right, func) - Merges the two given arrays, element-wise, into a single array using function. If one array is shorter, nulls are appended at the end to match the length of the longer array, before applying function.",
    +  examples = """
    +    Examples:
    +      > SELECT _FUNC_(array(1, 2, 3), array('a', 'b', 'c'), (x, y) -> (y, x));
    +       array(('a', 1), ('b', 3), ('c', 5))
    +      > SELECT _FUNC_(array(1, 2), array(3, 4), (x, y) -> x + y));
    +       array(4, 6)
    +      > SELECT _FUNC_(array('a', 'b', 'c'), array('d', 'e', 'f'), (x, y) -> concat(x, y));
    +       array('ad', 'be', 'cf')
    +  """,
    +  since = "2.4.0")
    +// scalastyle:on line.size.limit
    +case class ArraysZipWith(
    +    left: Expression,
    +    right: Expression,
    +    function: Expression)
    +  extends HigherOrderFunction with CodegenFallback with ExpectsInputTypes {
    +
    +  override def inputs: Seq[Expression] = List(left, right)
    +
    +  override def functions: Seq[Expression] = List(function)
    +
    +  def expectingFunctionType: AbstractDataType = AnyDataType
    +  @transient lazy val functionForEval: Expression = functionsForEval.head
    +
    +  override def inputTypes: Seq[AbstractDataType] = Seq(ArrayType, ArrayType, expectingFunctionType)
    +
    +  override def nullable: Boolean = inputs.exists(_.nullable)
    +
    +  override def dataType: ArrayType = ArrayType(function.dataType, function.nullable)
    +
    +  override def bind(f: (Expression, Seq[(DataType, Boolean)]) => LambdaFunction): ArraysZipWith = {
    +    val (leftElementType, leftContainsNull) = left.dataType match {
    +      case ArrayType(elementType, containsNull) => (elementType, containsNull)
    +      case _ =>
    +        val ArrayType(elementType, containsNull) = ArrayType.defaultConcreteType
    +        (elementType, containsNull)
    +    }
    +    val (rightElementType, rightContainsNull) = right.dataType match {
    +      case ArrayType(elementType, containsNull) => (elementType, containsNull)
    +      case _ =>
    +        val ArrayType(elementType, containsNull) = ArrayType.defaultConcreteType
    +        (elementType, containsNull)
    +    }
    +    copy(function = f(function,
    +      (leftElementType, leftContainsNull) :: (rightElementType, rightContainsNull) :: Nil))
    --- End diff --
    
    @mn-mikke @ueshin "both arrays must be the same length" was how zip_with in presto used to work, they've moved to appending nulls and process regardless.


---

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org