Github user dongjoon-hyun commented on a diff in the pull request:

    https://github.com/apache/spark/pull/14033#discussion_r69407409
  
    --- Diff: 
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/generators.scala
 ---
    @@ -94,6 +96,61 @@ case class UserDefinedGenerator(
     }
     
     /**
    + * Separate v1, ..., vk into n rows. Each row will have k/n columns. n 
must be constant.
    + * {{{
    + *   SELECT stack(2, 1, 2, 3)) ->
    + *   1      2
    + *   3      NULL
    + * }}}
    + */
    +@ExpressionDescription(
    +  usage = "_FUNC_(n, v1, ..., vk) - Separate v1, ..., vk into n rows.",
    +  extended = "> SELECT _FUNC_(2, 1, 2, 3);\n  [1,2]\n  [3,null]")
    +case class Stack(children: Seq[Expression])
    +    extends Expression with Generator with ImplicitCastInputTypes with 
CodegenFallback {
    +
    +  override def inputTypes: Seq[DataType] =
    +    Seq(IntegerType) ++ Seq.fill(children.length - 
1)(children.tail.head.dataType)
    +
    +  override def checkInputDataTypes(): TypeCheckResult = {
    +    if (children.length <= 1) {
    +      TypeCheckResult.TypeCheckFailure(s"$prettyName requires at least 2 
arguments.")
    +    } else if (!children.head.foldable || 
children.head.eval().asInstanceOf[Int] < 1) {
    +      TypeCheckResult.TypeCheckFailure("The number of rows must be 
positive constant.")
    +    } else if (children.tail.map(_.dataType).distinct.count(_ != NullType) 
> 1) {
    +      TypeCheckResult.TypeCheckFailure(
    +        s"The expressions should all have the same type," +
    +          s" but got $prettyName(${children.map(_.dataType)}).")
    +    } else {
    +      TypeCheckResult.TypeCheckSuccess
    +    }
    +  }
    +
    +  private lazy val numRows = children.head.eval().asInstanceOf[Int]
    +  private lazy val numFields = ((children.length - 1) + numRows - 1) / 
numRows
    +
    +  override def elementSchema: StructType = {
    +    var schema = new StructType()
    +    for (i <- 0 until numFields) {
    +      schema = schema.add(s"col$i", children(1).dataType)
    +    }
    +    schema
    +  }
    +
    +  override def eval(input: InternalRow): TraversableOnce[InternalRow] = {
    +    val values = children.tail.map(_.eval(input))
    +    for (row <- 0 until numRows) yield {
    +      val fields = ArrayBuffer.empty[Any]
    --- End diff --
    
    Right, Good catch! 


---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---

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

Reply via email to