cloud-fan commented on code in PR #47503:
URL: https://github.com/apache/spark/pull/47503#discussion_r1701074034
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/HyperLogLogPlusPlusHelper.scala:
##########
@@ -93,6 +94,8 @@ class HyperLogLogPlusPlusHelper(relativeSD: Double) extends
Serializable {
val value = dataType match {
case FloatType => FLOAT_NORMALIZER.apply(_value)
case DoubleType => DOUBLE_NORMALIZER.apply(_value)
+ case st: StringType if !st.supportsBinaryEquality &&
_value.isInstanceOf[UTF8String] =>
Review Comment:
StringType values must be `UTF8String`. The entire the SQL execution
framework takes this assumption.
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/util/HyperLogLogPlusPlusHelper.scala:
##########
@@ -93,6 +94,8 @@ class HyperLogLogPlusPlusHelper(relativeSD: Double) extends
Serializable {
val value = dataType match {
case FloatType => FLOAT_NORMALIZER.apply(_value)
case DoubleType => DOUBLE_NORMALIZER.apply(_value)
+ case st: StringType if !st.supportsBinaryEquality &&
_value.isInstanceOf[UTF8String] =>
Review Comment:
StringType values must be `UTF8String`. The entire SQL execution framework
takes this assumption.
--
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]
