From 9df86835b60ce587c8b9bd4ad7410eebf59a179d Mon Sep 17 00:00:00 2001
From: Takuya UESHIN <ueshin@happy-camper.st>
Date: Tue, 27 May 2014 22:17:50 -0700
Subject: [PATCH] [SPARK-1938] [SQL] ApproxCountDistinctMergeFunction should
return Int value.
`ApproxCountDistinctMergeFunction` should return `Int` value because the `dataType` of `ApproxCountDistinct` is `IntegerType`.
Author: Takuya UESHIN <ueshin@happy-camper.st>
Closes #893 from ueshin/issues/SPARK-1938 and squashes the following commits:
3970e88 [Takuya UESHIN] Remove a superfluous line.
5ad7ec1 [Takuya UESHIN] Make dataType for each of CountDistinct, ApproxCountDistinctMerge and ApproxCountDistinct LongType.
cbe7c71 [Takuya UESHIN] Revert a change.
fc3ac0f [Takuya UESHIN] Fix evaluated value type of ApproxCountDistinctMergeFunction to Int.
---
.../spark/sql/catalyst/expressions/aggregates.scala | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregates.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregates.scala
index c902433688..01947273b6 100644
--- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregates.scala
+++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregates.scala
@@ -82,7 +82,6 @@ abstract class AggregateFunction
override def dataType = base.dataType
def update(input: Row): Unit
- override def eval(input: Row): Any
// Do we really need this?
override def newInstance() = makeCopy(productIterator.map { case a: AnyRef => a }.toArray)
@@ -166,7 +165,7 @@ case class CountDistinct(expressions: Seq[Expression]) extends AggregateExpressi
override def children = expressions
override def references = expressions.flatMap(_.references).toSet
override def nullable = false
- override def dataType = IntegerType
+ override def dataType = LongType
override def toString = s"COUNT(DISTINCT ${expressions.mkString(",")})"
override def newInstance() = new CountDistinctFunction(expressions, this)
}
@@ -184,7 +183,7 @@ case class ApproxCountDistinctMerge(child: Expression, relativeSD: Double)
extends AggregateExpression with trees.UnaryNode[Expression] {
override def references = child.references
override def nullable = false
- override def dataType = IntegerType
+ override def dataType = LongType
override def toString = s"APPROXIMATE COUNT(DISTINCT $child)"
override def newInstance() = new ApproxCountDistinctMergeFunction(child, this, relativeSD)
}
@@ -193,7 +192,7 @@ case class ApproxCountDistinct(child: Expression, relativeSD: Double = 0.05)
extends PartialAggregate with trees.UnaryNode[Expression] {
override def references = child.references
override def nullable = false
- override def dataType = IntegerType
+ override def dataType = LongType
override def toString = s"APPROXIMATE COUNT(DISTINCT $child)"
override def asPartial: SplitEvaluation = {
@@ -394,7 +393,7 @@ case class CountDistinctFunction(expr: Seq[Expression], base: AggregateExpressio
}
}
- override def eval(input: Row): Any = seen.size
+ override def eval(input: Row): Any = seen.size.toLong
}
case class FirstFunction(expr: Expression, base: AggregateExpression) extends AggregateFunction {
--
GitLab