Restoring existing behavior for Insert Into to deduplicate by default…

… (if pre-combine is specified)
apache · Feb 2, 2023 · 4f2eef7 · 4f2eef7
1 parent 8f4a92b
commit 4f2eef7
Showing 1 changed file with 3 additions and 0 deletions.
diff --git a/...rce/hudi-spark-common/src/main/scala/org/apache/spark/sql/hudi/ProvidesHoodieConfig.scala b/...rce/hudi-spark-common/src/main/scala/org/apache/spark/sql/hudi/ProvidesHoodieConfig.scala
@@ -180,6 +180,9 @@ trait ProvidesHoodieConfig extends Logging {
 
     val defaultOpts = Map(
       PAYLOAD_CLASS_NAME.key -> payloadClassName,
+      // NOTE: By default insert would try to do deduplication in case that pre-combine column is specified
+      //       for the table
+      HoodieWriteConfig.COMBINE_BEFORE_INSERT.key -> String.valueOf(hasPrecombineColumn),
     )
 
     val overridingOpts = Map(