c27kwan commented on code in PR #37771:
URL: https://github.com/apache/spark/pull/37771#discussion_r961653435
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/ArrayBasedMapData.scala:
##########
@@ -35,6 +37,29 @@ class ArrayBasedMapData(val keyArray: ArrayData, val
valueArray: ArrayData) exte
override def toString: String = {
s"keys: $keyArray, values: $valueArray"
}
+
+ override def equals(obj: Any): Boolean = {
+ if (obj == null && this == null) {
+ return true
+ }
+
+ if (obj == null || !obj.isInstanceOf[ArrayBasedMapData]) {
+ return false
+ }
+
+ val other = obj.asInstanceOf[ArrayBasedMapData]
+
+ keyArray.equals(other.keyArray) && valueArray.equals(other.valueArray)
+ }
+
+ // Hash this class as a Product of two hashCodes. We don't know the DataType
which prevents us
+ // from getting individual rows for hashing as a Map.
+ override def hashCode(): Int = {
+ val seed = MurmurHash3.productSeed
+ val keyHash = scala.util.hashing.MurmurHash3.mix(seed, keyArray.hashCode())
+ val valueHash = scala.util.hashing.MurmurHash3.mix(keyHash,
valueArray.hashCode())
+ scala.util.hashing.MurmurHash3.finalizeHash(valueHash, 2)
+ }
Review Comment:
Hi @cloud-fan , can you take a look? Do you think we need to also add an
explicit `hashCode()` override to `ArrayData` (used by `keyArray` and
`valueArray`)?
--
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]
