LuciferYang commented on a change in pull request #30026:
URL: https://github.com/apache/spark/pull/30026#discussion_r506148242
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/BasicWriteStatsTracker.scala
##########
@@ -139,20 +142,22 @@ class BasicWriteJobStatsTracker(
override def processStats(stats: Seq[WriteTaskStats]): Unit = {
val sparkContext = SparkContext.getActive.get
- var numPartitions: Long = 0L
+ var partitionsSet: mutable.Set[InternalRow] = mutable.HashSet.empty
var numFiles: Long = 0L
var totalNumBytes: Long = 0L
var totalNumOutput: Long = 0L
val basicStats = stats.map(_.asInstanceOf[BasicWriteTaskStats])
basicStats.foreach { summary =>
- numPartitions += summary.numPartitions
+ partitionsSet ++= summary.partitions
Review comment:
ditto, `partitionsSet.addAll(summary.partitions)` can only be used in
Scala 2.13 too.
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/datasources/BasicWriteStatsTracker.scala
##########
@@ -76,7 +79,7 @@ class BasicWriteTaskStatsTracker(hadoopConf: Configuration)
override def newPartition(partitionValues: InternalRow): Unit = {
- numPartitions += 1
+ partitions = partitions :+ partitionValues
Review comment:
`partitions.appended(partitionValues)` can only be used in Scala 2.13
----------------------------------------------------------------
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]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
