yihua commented on a change in pull request #1149:
URL: https://github.com/apache/hudi/pull/1149#discussion_r462703978
##########
File path:
hudi-common/src/test/java/org/apache/hudi/common/testutils/HoodieTestDataGenerator.java
##########
@@ -161,6 +161,17 @@ public static void writePartitionMetadata(FileSystem fs,
String[] partitionPaths
}
}
+ public static List<HoodieRecord> newHoodieRecords(int n, String time) throws
Exception {
Review comment:
I copied this method from the `TestCopyOnWriteActionExecutor` class.
Let me check if I can generalize this.
##########
File path:
hudi-client/src/main/java/org/apache/hudi/execution/bulkinsert/BulkInsertInternalPartitioner.java
##########
@@ -0,0 +1,52 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hudi.execution.bulkinsert;
+
+import org.apache.hudi.common.model.HoodieRecordPayload;
+import org.apache.hudi.exception.HoodieException;
+import org.apache.hudi.table.UserDefinedBulkInsertPartitioner;
+
+/**
+ * Built-in partitioner to repartition input records into at least expected
number of
+ * output spark partitions for bulk insert operation.
+ *
+ * @param <T> HoodieRecordPayload type
+ */
+public abstract class BulkInsertInternalPartitioner<T extends
HoodieRecordPayload> implements
+ UserDefinedBulkInsertPartitioner<T> {
+
+ public static BulkInsertInternalPartitioner get(BulkInsertSortMode sortMode)
{
Review comment:
Yes, good suggestion. Let me do that.
##########
File path:
hudi-client/src/main/java/org/apache/hudi/execution/bulkinsert/RDDPartitionSortPartitioner.java
##########
@@ -0,0 +1,68 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.hudi.execution.bulkinsert;
+
+import org.apache.hudi.common.model.HoodieRecord;
+import org.apache.hudi.common.model.HoodieRecordPayload;
+
+import org.apache.spark.api.java.JavaRDD;
+
+import java.util.ArrayList;
+import java.util.Collections;
+import java.util.List;
+
+import scala.Tuple2;
+
+/**
+ * A built-in partitioner that does local sorting for each RDD partition
+ * after coalesce for bulk insert operation, corresponding to the
+ * {@code BulkInsertSortMode.PARTITION_SORT} mode.
+ *
+ * @param <T> HoodieRecordPayload type
+ */
+public class RDDPartitionSortPartitioner<T extends HoodieRecordPayload>
+ extends BulkInsertInternalPartitioner<T> {
+
+ @Override
+ public JavaRDD<HoodieRecord<T>> repartitionRecords(JavaRDD<HoodieRecord<T>>
records,
+ int
outputSparkPartitions) {
+ return records.coalesce(outputSparkPartitions)
+ .mapToPair(record ->
+ new Tuple2<>(
+ new StringBuilder()
+ .append(record.getPartitionPath())
+ .append("+")
+ .append(record.getRecordKey())
+ .toString(), record))
+ .mapPartitions(partition -> {
+ // Sort locally in partition
+ List<Tuple2<String, HoodieRecord<T>>> recordList = new ArrayList<>();
+ for (; partition.hasNext(); ) {
+ recordList.add(partition.next());
+ }
+ Collections.sort(recordList, (o1, o2) -> o1._1.compareTo(o2._1));
Review comment:
Yes, let's sync offline.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
