You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by GitBox <gi...@apache.org> on 2022/05/24 03:52:33 UTC
[GitHub] [hudi] codope commented on a diff in pull request #5502: [HUDI-4040]Bulk insert: Add customColumnsSortpartitionerWithRows
codope commented on code in PR #5502:
URL: https://github.com/apache/hudi/pull/5502#discussion_r880032515
##########
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/execution/bulkinsert/CustomColumnsSortPartitionerWithRows.java:
##########
@@ -0,0 +1,60 @@
+/*
+ * 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.config.HoodieWriteConfig;
+import org.apache.hudi.table.BulkInsertPartitioner;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+
+import java.util.Arrays;
+
+/**
+ * A partitioner that does sorting based on specified column values for each spark partitions.
+ */
+public class CustomColumnsSortPartitionerWithRows implements BulkInsertPartitioner<Dataset<Row>> {
Review Comment:
Rename to `RowCustomColumnsSortPartitioner` to be consistent with `RDDCustomColumnsSortPartitioner`?
##########
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/execution/bulkinsert/CustomColumnsSortPartitionerWithRows.java:
##########
@@ -0,0 +1,60 @@
+/*
+ * 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.config.HoodieWriteConfig;
+import org.apache.hudi.table.BulkInsertPartitioner;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+
+import java.util.Arrays;
+
+/**
+ * A partitioner that does sorting based on specified column values for each spark partitions.
+ */
+public class CustomColumnsSortPartitionerWithRows implements BulkInsertPartitioner<Dataset<Row>> {
+
+ private final String[] sortColumnNames;
+
+ public CustomColumnsSortPartitionerWithRows(HoodieWriteConfig config) {
+ this.sortColumnNames = getSortColumnName(config);
+ }
+
+ public CustomColumnsSortPartitionerWithRows(String[] columnNames) {
+ this.sortColumnNames = columnNames;
+ }
+
+ @Override
+ public Dataset<Row> repartitionRecords(Dataset<Row> records, int outputSparkPartitions) {
+ final String[] sortColumns = this.sortColumnNames;
+ return records.coalesce(outputSparkPartitions)
Review Comment:
Does it handle null values?
##########
hudi-client/hudi-spark-client/src/main/java/org/apache/hudi/execution/bulkinsert/CustomColumnsSortPartitionerWithRows.java:
##########
@@ -0,0 +1,60 @@
+/*
+ * 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.config.HoodieWriteConfig;
+import org.apache.hudi.table.BulkInsertPartitioner;
+import org.apache.spark.sql.Dataset;
+import org.apache.spark.sql.Row;
+
+import java.util.Arrays;
+
+/**
+ * A partitioner that does sorting based on specified column values for each spark partitions.
+ */
+public class CustomColumnsSortPartitionerWithRows implements BulkInsertPartitioner<Dataset<Row>> {
+
+ private final String[] sortColumnNames;
+
+ public CustomColumnsSortPartitionerWithRows(HoodieWriteConfig config) {
+ this.sortColumnNames = getSortColumnName(config);
+ }
+
+ public CustomColumnsSortPartitionerWithRows(String[] columnNames) {
+ this.sortColumnNames = columnNames;
+ }
+
+ @Override
+ public Dataset<Row> repartitionRecords(Dataset<Row> records, int outputSparkPartitions) {
+ final String[] sortColumns = this.sortColumnNames;
+ return records.coalesce(outputSparkPartitions)
+ .sortWithinPartitions(HoodieRecord.PARTITION_PATH_METADATA_FIELD, sortColumns);
+ }
+
+ @Override
+ public boolean arePartitionRecordsSorted() {
+ return true;
+ }
+
+ private String[] getSortColumnName(HoodieWriteConfig config) {
+ return Arrays.stream(config.getUserDefinedBulkInsertPartitionerSortColumns().split(","))
+ .map(String::trim).toArray(String[]::new);
Review Comment:
I think would be good to do this change (esp the trim) in `RDDCustomColumnsSortPartitioner`?
--
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: commits-unsubscribe@hudi.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org