nchammas commented on code in PR #45036:
URL: https://github.com/apache/spark/pull/45036#discussion_r1491176098
##########
core/src/test/scala/org/apache/spark/util/collection/OpenHashMapSuite.scala:
##########
@@ -249,4 +249,32 @@ class OpenHashMapSuite extends SparkFunSuite with Matchers
{
map(null) = null
assert(map.get(null) === Some(null))
}
+
+ test("SPARK-45599: 0.0 and -0.0 should count distinctly") {
+ // Exactly these elements provided in roughly this order trigger a
condition where lookups of
+ // 0.0 and -0.0 in the bitset happen to collide, causing their counts to
be merged incorrectly
+ // and inconsistently if `==` is used to check for key equality.
+ val spark45599Repro = Seq(
+ Double.NaN,
+ 2.0,
+ 168.0,
+ Double.NaN,
+ Double.NaN,
+ -0.0,
+ 153.0,
+ 0.0
+ )
+
+ val map1 = new OpenHashMap[Double, Int]()
+ spark45599Repro.foreach(map1.changeValue(_, 1, {_ + 1}))
+ assert(map1(0.0) == 1)
+ assert(map1(-0.0) == 1)
+
+ val map2 = new OpenHashMap[Double, Int]()
+ // Simply changing the order in which the elements are added to the map
should not change the
+ // counts for 0.0 and -0.0.
+ spark45599Repro.reverse.foreach(map2.changeValue(_, 1, {_ + 1}))
+ assert(map2(0.0) == 1)
+ assert(map2(-0.0) == 1)
Review Comment:
Added just below.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
