KiteSoar commented on code in PR #20099:
URL: https://github.com/apache/hudi/pull/20099#discussion_r4172551334
##########
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/spark/sql/hudi/command/procedures/ShowCleansProcedure.scala:
##########
@@ -256,6 +266,48 @@ object ShowCleansProcedure {
val NAME = "show_cleans"
def builder: Supplier[ProcedureBuilder] = () => new
ShowCleansProcedure(false)
+
+ private[procedures] def getArchivedCleanTimeline(metaClient:
HoodieTableMetaClient,
+ loadPlans: Boolean,
+ limit: Int = Int.MaxValue):
HoodieTimeline = {
+ val cleanInstants =
metaClient.getArchivedTimeline.getCleanerTimeline.filterCompletedInstants
+ .getReverseOrderedInstants.iterator().asScala.take(limit).toList
+ val contents = new ConcurrentHashMap[String, Array[Byte]]()
+ val factory = metaClient.getTableFormat.getTimelineFactory
+ if (cleanInstants.nonEmpty) {
+ val legacy = metaClient.getTimelineLayoutVersion.getVersion <
TimelineLayoutVersion.VERSION_2
+ val actionField = if (legacy) "actionType" else "action"
+ val contentField = if (legacy) {
+ if (loadPlans) "hoodieCleanerPlan" else "hoodieCleanMetadata"
+ } else {
+ if (loadPlans) "plan" else "metadata"
+ }
+ val loadMode = if (loadPlans) HoodieArchivedTimeline.LoadMode.PLAN else
HoodieArchivedTimeline.LoadMode.METADATA
+ factory.createArchivedTimelineLoader().loadInstants(metaClient,
+ new HoodieArchivedTimeline.ClosedClosedTimeRangeFilter(
+ cleanInstants.last.requestedTime(),
cleanInstants.head.requestedTime()),
+ loadMode,
+ record => HoodieTimeline.CLEAN_ACTION ==
record.get(actionField).toString,
Review Comment:
Done in b231fe4c5612. The V1 loader now receives a null range filter, with
range and selected-instant checks applied in the consumer. Added a V1
regression test with three separate archive files and a commit-only middle
file; both older and newer clean plans and metadata are read successfully.
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
