bvaradar commented on code in PR #7834:
URL: https://github.com/apache/hudi/pull/7834#discussion_r1141157998
##########
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/execution/bulkinsert/RDDBucketIndexPartitioner.java:
##########
@@ -18,15 +18,155 @@
package org.apache.hudi.execution.bulkinsert;
+import org.apache.avro.Schema;
+import org.apache.hudi.avro.HoodieAvroUtils;
+import org.apache.hudi.common.config.SerializableSchema;
+import org.apache.hudi.common.fs.FSUtils;
+import org.apache.hudi.common.model.HoodieKey;
import org.apache.hudi.common.model.HoodieRecord;
+import org.apache.hudi.common.model.HoodieTableType;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.common.util.ValidationUtils;
+import org.apache.hudi.common.util.collection.FlatLists;
+import org.apache.hudi.io.AppendHandleFactory;
+import org.apache.hudi.io.SingleFileHandleCreateFactory;
+import org.apache.hudi.io.WriteHandleFactory;
import org.apache.hudi.table.BulkInsertPartitioner;
+import org.apache.hudi.table.HoodieTable;
+import org.apache.logging.log4j.LogManager;
+import org.apache.logging.log4j.Logger;
+import org.apache.spark.Partitioner;
import org.apache.spark.api.java.JavaRDD;
+import scala.Tuple2;
+
+import java.io.Serializable;
+import java.util.ArrayList;
+import java.util.Arrays;
+import java.util.Comparator;
+import java.util.List;
+
/**
* Abstract of bucket index bulk_insert partitioner
- * TODO implement partitioner for SIMPLE BUCKET INDEX
*/
public abstract class RDDBucketIndexPartitioner<T>
implements BulkInsertPartitioner<JavaRDD<HoodieRecord<T>>> {
+
Review Comment:
@wuwenchi : I agree it was written like that before but wanted to take this
opportunity to correct it as we are bringing in more engines to this specific
use-case. Can you elaborate more why it is convenient to use rdd directly ? One
of the main reason why we introduced these abstractions is to have proper reuse
of core components across engines while being flexible to extend in engine
specific way. Thanks
--
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]
