alexeykudinkin commented on a change in pull request #4948:
URL: https://github.com/apache/hudi/pull/4948#discussion_r822164221
##########
File path:
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieFileIndex.scala
##########
@@ -194,77 +192,102 @@ case class HoodieFileIndex(spark: SparkSession,
* @param queryFilters list of original data filters passed down from
querying engine
* @return list of pruned (data-skipped) candidate base-files' names
*/
- private def lookupCandidateFilesInColStatsIndex(queryFilters:
Seq[Expression]): Try[Option[Set[String]]] = Try {
- val indexPath = metaClient.getColumnStatsIndexPath
+ private def lookupCandidateFilesInMetadataTable(queryFilters:
Seq[Expression]): Try[Option[Set[String]]] = Try {
val fs = metaClient.getFs
+ val metadataTablePath =
HoodieTableMetadata.getMetadataTableBasePath(basePath)
Review comment:
Yeah, current bespoke implementation will be removed in a follow-up.
It's currently updated after clustering completes.
##########
File path:
hudi-spark-datasource/hudi-spark-common/src/main/scala/org/apache/hudi/HoodieFileIndex.scala
##########
@@ -194,77 +192,102 @@ case class HoodieFileIndex(spark: SparkSession,
* @param queryFilters list of original data filters passed down from
querying engine
* @return list of pruned (data-skipped) candidate base-files' names
*/
- private def lookupCandidateFilesInColStatsIndex(queryFilters:
Seq[Expression]): Try[Option[Set[String]]] = Try {
- val indexPath = metaClient.getColumnStatsIndexPath
+ private def lookupCandidateFilesInMetadataTable(queryFilters:
Seq[Expression]): Try[Option[Set[String]]] = Try {
val fs = metaClient.getFs
+ val metadataTablePath =
HoodieTableMetadata.getMetadataTableBasePath(basePath)
Review comment:
Yeah, current bespoke implementation will be removed in a follow-up.
It's currently updated only after clustering completes.
--
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]
