leanken commented on a change in pull request #29104:
URL: https://github.com/apache/spark/pull/29104#discussion_r460276191
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala
##########
@@ -896,22 +969,32 @@ private[joins] object LongHashedRelation {
// Create a mapping of key -> rows
var numFields = 0
+ val isOriginalInputEmpty: Boolean = !input.hasNext
+ var allNullColumnKeyExistsInOriginalInput: Boolean = false
while (input.hasNext) {
val unsafeRow = input.next().asInstanceOf[UnsafeRow]
numFields = unsafeRow.numFields()
val rowKey = keyGenerator(unsafeRow)
if (!rowKey.isNullAt(0)) {
+ // LongToUnsafeRowMap can't insert null key
val key = rowKey.getLong(0)
map.append(key, unsafeRow)
+ } else if (!allNullColumnKeyExistsInOriginalInput) {
+ // LongHashedRelation stores single-column key
Review comment:
removed
----------------------------------------------------------------
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.
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
