boneanxs commented on code in PR #8076: URL: https://github.com/apache/hudi/pull/8076#discussion_r1127287138
########## hudi-spark-datasource/hudi-spark-common/src/main/java/org/apache/hudi/commit/DatasetBulkInsertActionExecutor.java: ########## @@ -0,0 +1,91 @@ +/* + * 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.commit; + +import org.apache.hudi.HoodieSparkUtils; +import org.apache.hudi.client.SparkRDDWriteClient; +import org.apache.hudi.client.WriteStatus; +import org.apache.hudi.common.data.HoodieData; +import org.apache.hudi.common.model.WriteOperationType; +import org.apache.hudi.config.HoodieInternalConfig; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.exception.HoodieException; +import org.apache.hudi.internal.DataSourceInternalWriterHelper; +import org.apache.hudi.table.action.HoodieWriteMetadata; +import org.apache.spark.api.java.JavaRDD; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.Row; +import org.apache.spark.sql.SaveMode; + +import java.util.Collections; +import java.util.HashMap; +import java.util.Map; +import java.util.stream.Collectors; + +public class DatasetBulkInsertActionExecutor extends BaseDatasetBulkCommitActionExecutor { + + public DatasetBulkInsertActionExecutor(HoodieWriteConfig config, SparkRDDWriteClient writeClient, String instantTime) { + super(config, writeClient, instantTime); + } + + @Override + protected void preExecute() { + // no op + } + + @Override + protected HoodieData<WriteStatus> doExecute(Dataset<Row> records, boolean arePartitionRecordsSorted) { + Map<String, String> opts = writeConfig.getProps().entrySet().stream().collect(Collectors.toMap( + e -> String.valueOf(e.getKey()), + e -> String.valueOf(e.getValue()))); + Map<String, String> optsOverrides = Collections.singletonMap( + HoodieInternalConfig.BULKINSERT_ARE_PARTITIONER_RECORDS_SORTED, String.valueOf(arePartitionRecordsSorted)); + + String targetFormat; + Map<String, String> customOpts = new HashMap<>(1); + if (HoodieSparkUtils.isSpark2()) { + targetFormat = "org.apache.hudi.internal"; + } else if (HoodieSparkUtils.isSpark3()) { + targetFormat = "org.apache.hudi.spark3.internal"; + customOpts.put(HoodieInternalConfig.BULKINSERT_INPUT_DATA_SCHEMA_DDL.key(), records.schema().json()); + } else { + throw new HoodieException("Bulk insert using row writer is not supported with current Spark version." + + " To use row writer please switch to spark 2 or spark 3"); + } + + records.write().format(targetFormat) Review Comment: Still keep the old behavior here to do the `bulk_insert`, maybe we should also use `HoodieDatasetBulkInsertHelper.bulkInsert` to perform write operation? We can reduce many codes for handling `commit` behavior(Here will add a complete commit, while `HoodieDatasetBulkInsertHelper.bulkInsert` doesn't, we need to handle this differently in `bulkInsertAsRow`) -- 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]
