Github user cloud-fan commented on a diff in the pull request:
https://github.com/apache/spark/pull/18113#discussion_r150083215
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/typedaggregators.scala
---
@@ -26,43 +26,64 @@ import org.apache.spark.sql.expressions.Aggregator
// This file defines internal implementations for aggregators.
////////////////////////////////////////////////////////////////////////////////////////////////////
+class TypedSumDouble[IN](val f: IN => Double)
+ extends Aggregator[IN, java.lang.Double, java.lang.Double] {
+
+ override def zero: java.lang.Double = null
+ override def reduce(b: java.lang.Double, a: IN): java.lang.Double =
+ if (b == null) f(a) else b + f(a)
+
+ override def merge(b1: java.lang.Double, b2: java.lang.Double):
java.lang.Double = {
+ if (b1 == null) {
+ b2
+ } else if (b2 == null) {
+ b1
+ } else {
+ b1 + b2
+ }
+ }
+ override def finish(reduction: java.lang.Double): java.lang.Double =
reduction
-class TypedSumDouble[IN](val f: IN => Double) extends Aggregator[IN,
Double, Double] {
- override def zero: Double = 0.0
--- End diff --
so we will return 0.0 for empty input, let's not change this behavior
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
