boneanxs commented on code in PR #5723:
URL: https://github.com/apache/hudi/pull/5723#discussion_r902120970
##########
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/MergeOnReadSnapshotRelation.scala:
##########
@@ -104,14 +104,22 @@ class MergeOnReadSnapshotRelation(sqlContext: SQLContext,
val fileSlices = fileIndex.listFileSlices(convertedPartitionFilters)
buildSplits(fileSlices.values.flatten.toSeq)
} else {
- // TODO refactor to avoid iterating over listed files multiple times
- val partitions = listLatestBaseFiles(globPaths,
convertedPartitionFilters, dataFilters)
- val partitionPaths = partitions.keys.toSeq
+ val inMemoryFileIndex = HoodieInMemoryFileIndex.create(sparkSession,
globPaths)
Review Comment:
I'll address this in https://github.com/apache/hudi/pull/5722
--
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]
