Posted by
GitBox on
Dec 07, 2020; 7:16am
URL: http://apache-carbondata-dev-mailing-list-archive.168.s1.nabble.com/GitHub-carbondata-QiangCai-opened-a-new-pull-request-4044-CARBONDATA-4062-Refactor-clean-files-featue-tp104338p104433.html
QiangCai commented on a change in pull request #4044:
URL:
https://github.com/apache/carbondata/pull/4044#discussion_r537278197##########
File path: integration/spark/src/main/scala/org/apache/spark/sql/secondaryindex/events/CleanFilesPostEventListener.scala
##########
@@ -48,30 +50,61 @@ class CleanFilesPostEventListener extends OperationEventListener with Logging {
event match {
case cleanFilesPostEvent: CleanFilesPostEvent =>
LOGGER.info("Clean files post event listener called")
- val carbonTable = cleanFilesPostEvent.carbonTable
- val indexTables = CarbonIndexUtil
- .getIndexCarbonTables(carbonTable, cleanFilesPostEvent.sparkSession)
- val isForceDelete = cleanFilesPostEvent.ifForceDelete
- val inProgressSegmentsClean = cleanFilesPostEvent.cleanStaleInProgress
- indexTables.foreach { indexTable =>
- val partitions: Option[Seq[PartitionSpec]] = CarbonFilters.getPartitions(
- Seq.empty[Expression],
- cleanFilesPostEvent.sparkSession,
- indexTable)
- SegmentStatusManager.deleteLoadsAndUpdateMetadata(
- indexTable, isForceDelete, partitions.map(_.asJava).orNull, inProgressSegmentsClean,
- true)
- CarbonUpdateUtil.cleanUpDeltaFiles(indexTable, true)
- cleanUpUnwantedSegmentsOfSIAndUpdateMetadata(indexTable, carbonTable)
- }
+ cleanFilesForIndex(
+ cleanFilesPostEvent.sparkSession,
+ cleanFilesPostEvent.carbonTable,
+ cleanFilesPostEvent.options.getOrElse("force", "false").toBoolean,
+ cleanFilesPostEvent.options.getOrElse("stale_inprogress", "false").toBoolean)
+
+ cleanFilesForMv(
+ cleanFilesPostEvent.sparkSession,
+ cleanFilesPostEvent.carbonTable,
+ cleanFilesPostEvent.options)
+ }
+ }
+
+ private def cleanFilesForIndex(
+ sparkSession: SparkSession,
+ carbonTable: CarbonTable,
+ isForceDelete: Boolean,
+ cleanStaleInProgress: Boolean
+ ): Unit = {
+ val indexTables = CarbonIndexUtil
+ .getIndexCarbonTables(carbonTable, sparkSession)
+ indexTables.foreach { indexTable =>
+ val partitions: Option[Seq[PartitionSpec]] = CarbonFilters.getPartitions(
+ Seq.empty[Expression],
+ sparkSession,
+ indexTable)
+ SegmentStatusManager.deleteLoadsAndUpdateMetadata(
+ indexTable, isForceDelete, partitions.map(_.asJava).orNull, cleanStaleInProgress,
+ true)
+ cleanUpUnwantedSegmentsOfSIAndUpdateMetadata(indexTable, carbonTable)
+ }
+ }
+
+ private def cleanFilesForMv(
+ sparkSession: SparkSession,
+ carbonTable: CarbonTable,
+ options: Map[String, String]
+ ): Unit = {
+ val viewSchemas = MVManagerInSpark.get(sparkSession).getSchemasOnTable(carbonTable)
+ if (!viewSchemas.isEmpty) {
+ viewSchemas.asScala.map { schema =>
Review comment:
fixed, the following command is using the wrong table, changed it to use this variable: schema
----------------------------------------------------------------
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:
[hidden email]