alexeykudinkin commented on code in PR #5722:
URL: https://github.com/apache/hudi/pull/5722#discussion_r906326302
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/MergeOnReadSnapshotRelation.scala:
##########
@@ -104,24 +104,8 @@ class MergeOnReadSnapshotRelation(sqlContext: SQLContext,
val fileSlices = fileIndex.listFileSlices(convertedPartitionFilters)
buildSplits(fileSlices.values.flatten.toSeq)
} else {
- val inMemoryFileIndex = HoodieInMemoryFileIndex.create(sparkSession,
globPaths)
- val partitionDirs = inMemoryFileIndex.listFiles(partitionFilters,
dataFilters)
-
- val fsView = new HoodieTableFileSystemView(metaClient, timeline,
partitionDirs.flatMap(_.files).toArray)
- val partitionPaths = fsView.getPartitionPaths.asScala
-
- if (partitionPaths.isEmpty || latestInstant.isEmpty) {
- // If this an empty table OR it has no completed commits yet, return
- List.empty[HoodieMergeOnReadFileSplit]
- } else {
- val queryTimestamp = this.queryTimestamp.get
-
- val fileSlices = partitionPaths.flatMap { partitionPath =>
- val relativePath = getRelativePartitionPath(new Path(basePath),
partitionPath)
- fsView.getLatestMergedFileSlicesBeforeOrOn(relativePath,
queryTimestamp).iterator().asScala.toSeq
- }
- buildSplits(fileSlices)
- }
+ val fileSlices = listLatestFileSlices(globPaths, partitionFilters,
dataFilters)
Review Comment:
SG, will do
--
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]
