danny0405 commented on code in PR #11947:
URL: https://github.com/apache/hudi/pull/11947#discussion_r1798655419
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/MergeOnReadIncrementalRelation.scala:
##########
@@ -201,55 +199,42 @@ trait HoodieIncrementalRelationTrait extends
HoodieBaseRelation {
val fallbackToFullTableScan =
optParams.getOrElse(DataSourceReadOptions.INCREMENTAL_FALLBACK_TO_FULL_TABLE_SCAN.key,
DataSourceReadOptions.INCREMENTAL_FALLBACK_TO_FULL_TABLE_SCAN.defaultValue).toBoolean
- fallbackToFullTableScan && (startInstantArchived || endInstantArchived
+ fallbackToFullTableScan && (startInstantArchived
|| affectedFilesInCommits.asScala.exists(fileStatus =>
!metaClient.getStorage.exists(fileStatus.getPath)))
}
- protected lazy val includedCommits: immutable.Seq[HoodieInstant] = {
- if (!startInstantArchived || !endInstantArchived) {
- // If endTimestamp commit is not archived, will filter instants
- // before endTimestamp.
- if (hollowCommitHandling == USE_TRANSITION_TIME) {
- super.timeline.findInstantsInRangeByCompletionTime(startTimestamp,
endTimestamp).getInstants.asScala.toList
- } else {
- super.timeline.findInstantsInRange(startTimestamp,
endTimestamp).getInstants.asScala.toList
- }
- } else {
- super.timeline.getInstants.asScala.toList
- }
- }
+ protected lazy val queryContext: IncrementalQueryAnalyzer.QueryContext =
+ IncrementalQueryAnalyzer.builder()
+ .metaClient(metaClient)
+ .startTime(optParams(DataSourceReadOptions.BEGIN_INSTANTTIME.key))
+ .endTime(optParams.getOrElse(DataSourceReadOptions.END_INSTANTTIME.key,
null))
+ .rangeType(InstantRange.RangeType.OPEN_CLOSED)
Review Comment:
Why the start instant is hard coded to be ignored.
--
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]
