xiarixiaoyao commented on a change in pull request #3193:
URL: https://github.com/apache/hudi/pull/3193#discussion_r665221015
##########
File path:
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/hudi/MergeOnReadSnapshotRelation.scala
##########
@@ -137,11 +136,14 @@ class MergeOnReadSnapshotRelation(val sqlContext:
SQLContext,
}
def buildFileIndex(filters: Array[Filter]): List[HoodieMergeOnReadFileSplit]
= {
-
- val fileStatuses = if (globPaths.isDefined) {
+ // Get all partition paths
+ val partitionPaths = if (globPaths.isDefined) {
// Load files from the global paths if it has defined to be compatible
with the original mode
val inMemoryFileIndex =
HoodieSparkUtils.createInMemoryFileIndex(sqlContext.sparkSession, globPaths.get)
- inMemoryFileIndex.allFiles()
+ val fsView = new HoodieTableFileSystemView(metaClient,
+ metaClient.getActiveTimeline.getCommitsTimeline
+ .filterCompletedInstants, inMemoryFileIndex.allFiles().toArray)
+
fsView.getLatestBaseFiles.iterator().asScala.toList.map(_.getFileStatus.getPath.getParent)
Review comment:
Thank you for your explanation， LGTM
--
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]
