Github user dongjoon-hyun commented on a diff in the pull request:
https://github.com/apache/spark/pull/14033#discussion_r69596328
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/generators.scala
---
@@ -94,6 +94,63 @@ 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 CodegenFallback {
+
+ private lazy val numRows = children.head.eval().asInstanceOf[Int]
+ private lazy val numFields = ((children.length - 1) + numRows - 1) /
numRows
+
+ override def checkInputDataTypes(): TypeCheckResult = {
+ if (children.length <= 1) {
+ TypeCheckResult.TypeCheckFailure(s"$prettyName requires at least 2
arguments.")
+ } else if (children.head.dataType != IntegerType ||
!children.head.foldable || numRows < 1) {
+ TypeCheckResult.TypeCheckFailure("The number of rows must be a
positive constant integer.")
+ } else {
+ for (i <- 1 until children.length) {
+ val j = (i - 1) % numFields
+ if (children(i).dataType != elementSchema.fields(j).dataType) {
+ return TypeCheckResult.TypeCheckFailure(
+ s"Argument ${j + 1} (${elementSchema.fields(j).dataType}) != "
+
+ s"Argument $i (${children(i).dataType})")
+ }
+ }
+ TypeCheckResult.TypeCheckSuccess
+ }
+ }
+
+ override def elementSchema: StructType = {
+ var schema = new StructType()
+ val types = children.tail.take(numFields).map(_.dataType)
+ for (i <- 0 until numFields) {
+ schema = schema.add(s"col$i", types(i))
+ }
+ schema
+ }
+
+ override def eval(input: InternalRow): TraversableOnce[InternalRow] = {
+ val values = children.tail.map(_.eval(input))
+ for (row <- 0 until numRows) yield {
+ val fields = new Array[Any](numFields)
+ for (col <- 0 until numFields) {
+ val index = (row % numRows) * numFields + col
--- End diff --
Absolutely, it's unnecessary.
---
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
