nastra commented on code in PR #14859:
URL: https://github.com/apache/iceberg/pull/14859#discussion_r2626457189


##########
spark/v4.0/spark/src/main/java/org/apache/iceberg/spark/actions/RewriteTablePathSparkAction.java:
##########
@@ -662,18 +663,27 @@ private void rewritePositionDeletes(Set<DeleteFile> 
toRewrite) {
       return;
     }
 
+    Set<DeleteFile> uniqueDeleteFiles = 
deduplicateDeleteFilesByLocation(toRewrite);
     Encoder<DeleteFile> deleteFileEncoder = 
Encoders.javaSerialization(DeleteFile.class);
     Dataset<DeleteFile> deleteFileDs =
-        spark().createDataset(Lists.newArrayList(toRewrite), 
deleteFileEncoder);
+        spark().createDataset(Lists.newArrayList(uniqueDeleteFiles), 
deleteFileEncoder);
 
     PositionDeleteReaderWriter posDeleteReaderWriter = new 
SparkPositionDeleteReaderWriter();
     deleteFileDs
-        .repartition(toRewrite.size())
+        .repartition(uniqueDeleteFiles.size())
         .foreach(
             rewritePositionDelete(
                 tableBroadcast(), sourcePrefix, targetPrefix, stagingDir, 
posDeleteReaderWriter));
   }
 
+  @VisibleForTesting
+  Set<DeleteFile> deduplicateDeleteFilesByLocation(Set<DeleteFile> 
deleteFiles) {

Review Comment:
   this diff should be enough:
   
   ```
   --- 
a/spark/v4.0/spark/src/main/java/org/apache/iceberg/spark/actions/RewriteTablePathSparkAction.java
   +++ 
b/spark/v4.0/spark/src/main/java/org/apache/iceberg/spark/actions/RewriteTablePathSparkAction.java
   @@ -72,6 +72,7 @@ import 
org.apache.iceberg.relocated.com.google.common.collect.Lists;
    import org.apache.iceberg.relocated.com.google.common.collect.Sets;
    import org.apache.iceberg.spark.JobGroupInfo;
    import org.apache.iceberg.spark.source.SerializableTableWithSize;
   +import org.apache.iceberg.util.DeleteFileSet;
    import org.apache.iceberg.util.Pair;
    import org.apache.spark.api.java.function.ForeachFunction;
    import org.apache.spark.api.java.function.MapFunction;
   @@ -301,7 +302,7 @@ public class RewriteTablePathSparkAction extends 
BaseSparkAction<RewriteTablePat
            rewriteManifestResult.toRewrite().stream()
                .filter(e -> e instanceof DeleteFile)
                .map(e -> (DeleteFile) e)
   -            .collect(Collectors.toSet());
   +            .collect(Collectors.toCollection(DeleteFileSet::create));
        rewritePositionDeletes(deleteFiles);
   ```



-- 
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]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to