(hudi) branch master updated: [HUDI-7282] Avoid verification failure due to append writing of the cow table with cluster configuration when the index is bucket. (#10475)

[danny0405]

This is an automated email from the ASF dual-hosted git repository.

danny0405 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hudi.git


The following commit(s) were added to refs/heads/master by this push:
     new 4c528029796 [HUDI-7282] Avoid verification failure due to append 
writing of the cow table with cluster configuration when the index is bucket. 
(#10475)
4c528029796 is described below

commit 4c5280297964c5aa3bd4bd7abe893ac36b8ebbcf
Author: akido <37492907+akihito-li...@users.noreply.github.com>
AuthorDate: Fri Jan 12 09:11:30 2024 +0800

    [HUDI-7282] Avoid verification failure due to append writing of the cow 
table with cluster configuration when the index is bucket. (#10475)
---
 .../src/main/java/org/apache/hudi/util/ClusteringUtil.java    |  2 +-
 .../test/java/org/apache/hudi/utils/TestClusteringUtil.java   | 11 +++++++++++
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git 
a/hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/util/ClusteringUtil.java
 
b/hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/util/ClusteringUtil.java
index 75d4ea79815..ac81b4e7af4 100644
--- 
a/hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/util/ClusteringUtil.java
+++ 
b/hudi-flink-datasource/hudi-flink/src/main/java/org/apache/hudi/util/ClusteringUtil.java
@@ -49,7 +49,7 @@ public class ClusteringUtil {
   private static final Logger LOG = 
LoggerFactory.getLogger(ClusteringUtil.class);
 
   public static void validateClusteringScheduling(Configuration conf) {
-    if (OptionsResolver.isBucketIndexType(conf)) {
+    if (!OptionsResolver.isAppendMode(conf) && 
OptionsResolver.isBucketIndexType(conf)) {
       HoodieIndex.BucketIndexEngineType bucketIndexEngineType = 
OptionsResolver.getBucketEngineType(conf);
       switch (bucketIndexEngineType) {
         case SIMPLE:
diff --git 
a/hudi-flink-datasource/hudi-flink/src/test/java/org/apache/hudi/utils/TestClusteringUtil.java
 
b/hudi-flink-datasource/hudi-flink/src/test/java/org/apache/hudi/utils/TestClusteringUtil.java
index e9433d036ca..ca8718289d9 100644
--- 
a/hudi-flink-datasource/hudi-flink/src/test/java/org/apache/hudi/utils/TestClusteringUtil.java
+++ 
b/hudi-flink-datasource/hudi-flink/src/test/java/org/apache/hudi/utils/TestClusteringUtil.java
@@ -32,6 +32,7 @@ import org.apache.hudi.common.util.ClusteringUtils;
 import org.apache.hudi.common.util.Option;
 import org.apache.hudi.configuration.FlinkOptions;
 import org.apache.hudi.exception.HoodieIOException;
+import org.apache.hudi.index.HoodieIndex;
 import org.apache.hudi.table.HoodieFlinkTable;
 import org.apache.hudi.util.ClusteringUtil;
 import org.apache.hudi.util.FlinkTables;
@@ -113,6 +114,16 @@ public class TestClusteringUtil {
         
.stream().map(HoodieInstant::getTimestamp).collect(Collectors.toList());
     assertThat(actualInstants, is(oriInstants));
   }
+  
+  @Test
+  void validateClusteringScheduling() throws Exception {
+    beforeEach();
+    ClusteringUtil.validateClusteringScheduling(this.conf);
+    
+    // validate bucket index
+    this.conf.setString(FlinkOptions.INDEX_TYPE, 
HoodieIndex.IndexType.BUCKET.name());
+    ClusteringUtil.validateClusteringScheduling(this.conf);
+  }
 
   /**
    * Generates a clustering plan on the timeline and returns its instant time.