ulysses-you commented on code in PR #38047:
URL: https://github.com/apache/spark/pull/38047#discussion_r1005435590
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/analysis/TypeCoercion.scala:
##########
@@ -751,6 +753,49 @@ abstract class TypeCoercionBase {
}
}
+ /**
+ * Casts types according to bucket info for Equality expression.
+ */
+ object EqualityTypeCasts extends TypeCoercionRule {
+
+ private def isIntegralTypes(exprs: Seq[Expression]): Boolean = {
+ exprs.map(_.dataType).forall {
+ case _: IntegralType => true
+ case DecimalType.Fixed(_, 0) => true
+ case _ => false
+ }
+ }
+
+ override val transform: PartialFunction[Expression, Expression] = {
+ case b @ Equality(l: Attribute, r: Attribute)
+ if b.childrenResolved && l.dataType != r.dataType &&
isIntegralTypes(b.children) =>
+ // The result type is:
+ // 1. The attribute data type with larger bucket number.
+ // 2. The attribute data type with larger default size if it is not
bucketed attribute.
Review Comment:
good point ! the value is equivalent but the hash code can be different
according to the data type
--
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]
