codope commented on a change in pull request #3139:
URL: https://github.com/apache/hudi/pull/3139#discussion_r663309856
##########
File path:
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/hudi/IncrementalRelation.scala
##########
@@ -96,14 +100,31 @@ class IncrementalRelation(val sqlContext: SQLContext,
val regularFileIdToFullPath = mutable.HashMap[String, String]()
var metaBootstrapFileIdToFullPath = mutable.HashMap[String, String]()
+ // create Replaced file group
+ val replacedTimeline = commitsTimelineToReturn.getCompletedReplaceTimeline
+ val replacedFile =
replacedTimeline.getInstants.collect(Collectors.toList[HoodieInstant]).flatMap
{ instant =>
+ val replaceMetadata = HoodieReplaceCommitMetadata.
+ fromBytes(metaClient.getActiveTimeline.getInstantDetails(instant).get,
classOf[HoodieReplaceCommitMetadata])
+ replaceMetadata.getPartitionToReplaceFileIds.entrySet().flatMap { entry
=>
+ entry.getValue.map { e =>
+ val fullPath = FSUtils.getPartitionPath(basePath,
entry.getKey).toString
+ (e, fullPath)
+ }
+ }
+ }.toMap
+
for (commit <- commitsToReturn) {
val metadata: HoodieCommitMetadata =
HoodieCommitMetadata.fromBytes(commitTimeline.getInstantDetails(commit)
.get, classOf[HoodieCommitMetadata])
if (HoodieTimeline.METADATA_BOOTSTRAP_INSTANT_TS == commit.getTimestamp)
{
- metaBootstrapFileIdToFullPath ++=
metadata.getFileIdAndFullPaths(basePath).toMap
+ metaBootstrapFileIdToFullPath ++=
metadata.getFileIdAndFullPaths(basePath).toMap.filterNot { case (k, v) =>
Review comment:
Can we also cover this scenario of metadata bootstrapping in the test
case?
--
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]
