You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by yi...@apache.org on 2024/05/14 18:48:11 UTC
(hudi) 05/07: [MINOR] Modify filter to allow removal of column stats from metadata table for bootstrap table files (#10238)
This is an automated email from the ASF dual-hosted git repository.
yihua pushed a commit to branch branch-0.x
in repository https://gitbox.apache.org/repos/asf/hudi.git
commit d62b245d9f498a79ea554edff991bc6b623fdf3b
Author: Tim Brown <ti...@onehouse.ai>
AuthorDate: Tue Feb 27 18:55:01 2024 -0800
[MINOR] Modify filter to allow removal of column stats from metadata table for bootstrap table files (#10238)
---
.../main/java/org/apache/hudi/metadata/HoodieTableMetadataUtil.java | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/hudi-common/src/main/java/org/apache/hudi/metadata/HoodieTableMetadataUtil.java b/hudi-common/src/main/java/org/apache/hudi/metadata/HoodieTableMetadataUtil.java
index d364ce77054..4254d2aecd3 100644
--- a/hudi-common/src/main/java/org/apache/hudi/metadata/HoodieTableMetadataUtil.java
+++ b/hudi-common/src/main/java/org/apache/hudi/metadata/HoodieTableMetadataUtil.java
@@ -58,6 +58,7 @@ import org.apache.hudi.common.table.timeline.HoodieTimeline;
import org.apache.hudi.common.table.timeline.TimelineMetadataUtils;
import org.apache.hudi.common.table.view.HoodieTableFileSystemView;
import org.apache.hudi.common.util.CollectionUtils;
+import org.apache.hudi.common.util.ExternalFilePathUtil;
import org.apache.hudi.common.util.FileIOUtils;
import org.apache.hudi.common.util.HoodieRecordUtils;
import org.apache.hudi.common.util.Option;
@@ -667,7 +668,7 @@ public class HoodieTableMetadataUtil {
String partitionPath = deleteFileInfoPair.getLeft();
String filePath = deleteFileInfoPair.getRight();
- if (filePath.endsWith(HoodieFileFormat.PARQUET.getFileExtension())) {
+ if (filePath.endsWith(HoodieFileFormat.PARQUET.getFileExtension()) || ExternalFilePathUtil.isExternallyCreatedFile(filePath)) {
return getColumnStatsRecords(partitionPath, filePath, dataTableMetaClient, columnsToIndex, true).iterator();
}
return Collections.emptyListIterator();