dbatomic commented on code in PR #45290:
URL: https://github.com/apache/spark/pull/45290#discussion_r1505922202
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/hash.scala:
##########
@@ -405,11 +405,21 @@ abstract class HashExpression[E] extends Expression {
s"$result = $hasherClassName.hashInt($input.months, $microsecondsHash);"
}
- protected def genHashString(input: String, result: String): String = {
- val baseObject = s"$input.getBaseObject()"
- val baseOffset = s"$input.getBaseOffset()"
- val numBytes = s"$input.numBytes()"
- s"$result = $hasherClassName.hashUnsafeBytes($baseObject, $baseOffset,
$numBytes, $result);"
+ protected def genHashString(
+ ctx: CodegenContext, input: String, result: String, stringType:
StringType): String = {
+ if (stringType.isDefaultCollation) {
+ val baseObject = s"$input.getBaseObject()"
+ val baseOffset = s"$input.getBaseOffset()"
+ val numBytes = s"$input.numBytes()"
+ s"$result = $hasherClassName.hashUnsafeBytes($baseObject, $baseOffset,
$numBytes, $result);"
+ } else {
+ val stringHash = ctx.freshName("stringHash")
+ s"""
+ long $stringHash =
CollationFactory.fetchCollation(${stringType.collationId})
Review Comment:
Right. I will leave this change for another PR.
We need this to make reshuffle working properly btw, but I will make that
change in a separate PR.
--
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: reviews-unsubscr...@spark.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
