ueshin commented on a change in pull request #24073: [SPARK-27134][SQL]
array_distinct function does not work correctly with columns containing array
of array
URL: https://github.com/apache/spark/pull/24073#discussion_r265854753
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/collectionOperations.scala
##########
@@ -3112,29 +3112,30 @@ case class ArrayDistinct(child: Expression)
(data: Array[AnyRef]) => new
GenericArrayData(data.distinct.asInstanceOf[Array[Any]])
} else {
(data: Array[AnyRef]) => {
- var foundNullElement = false
- var pos = 0
+ val arrayBuffer = new scala.collection.mutable.ArrayBuffer[Any]
+ var alreadyStoredNull = false
+ var found = false
for (i <- 0 until data.length) {
- if (data(i) == null) {
- if (!foundNullElement) {
- foundNullElement = true
- pos = pos + 1
+ if (data(i) != null) {
+ found = false
+ var j = 0;
+ while (!found && j < arrayBuffer.size) {
+ val va = arrayBuffer(j)
+ found = (va != null) && ordering.equiv(va, data(i))
+ j += 1
}
- } else {
- var j = 0
- var done = false
- while (j <= i && !done) {
- if (data(j) != null && ordering.equiv(data(j), data(i))) {
- done = true
- }
- j = j + 1
+ if (!found) {
+ arrayBuffer += data(i)
}
- if (i == j - 1) {
- pos = pos + 1
+ } else {
+ // De-duplicate the null values.
+ if (!alreadyStoredNull) {
+ arrayBuffer += data(i)
+ alreadyStoredNull = true
}
}
}
- new GenericArrayData(data.slice(0, pos))
Review comment:
Good catch.
Actually I'm not sure how I could miss this.
Thanks!
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
