Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[SPARK-1938] [SQL] ApproxCountDistinctMergeFunction should return Int value. #893

Closed
wants to merge 4 commits into from
Closed

[SPARK-1938] [SQL] ApproxCountDistinctMergeFunction should return Int value. #893

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
fc3ac0f
Fix evaluated value type of ApproxCountDistinctMergeFunction to Int.
ueshin May 27, 2014
cbe7c71
Revert a change.
ueshin May 28, 2014
5ad7ec1
Make dataType for each of CountDistinct, ApproxCountDistinctMerge and…
ueshin May 28, 2014
3970e88
Remove a superfluous line.
ueshin May 28, 2014
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 4 additions & 5 deletions sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/aggregates.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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)
Expand Down Expand Up @@ -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)
}
Expand All @@ -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)
}
Expand All @@ -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 = {
Expand Down Expand Up @@ -391,7 +390,7 @@ 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 {
Expand Down