nsivabalan commented on a change in pull request #2328: URL: https://github.com/apache/hudi/pull/2328#discussion_r544040384
########## File path: hudi-spark-datasource/hudi-spark3/src/main/java/org/apache/hudi/spark3/internal/DefaultSource.java ########## @@ -0,0 +1,71 @@ +/* + * 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.spark3.internal; + +import org.apache.hudi.DataSourceUtils; +import org.apache.hudi.config.HoodieWriteConfig; + +import org.apache.hadoop.conf.Configuration; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.connector.catalog.Table; +import org.apache.spark.sql.connector.catalog.TableProvider; +import org.apache.spark.sql.connector.expressions.Transform; +import org.apache.spark.sql.types.StructType; +import org.apache.spark.sql.util.CaseInsensitiveStringMap; + +import java.util.Map; + +/** + * DataSource V2 implementation for managing internal write logic. Only called internally. + * This class is only compatible with datasource V2 API in Spark 3. + */ +public class DefaultSource implements TableProvider { + + private SparkSession sparkSession = null; Review comment: do you think we can create "BaseDefaultSource" and move SparkSession, Configuration and getters there. So that spark 3 and spark2 defaultSource can extend from it. ########## File path: hudi-client/hudi-client-common/src/main/java/org/apache/hudi/config/HoodieWriteConfig.java ########## @@ -70,6 +70,7 @@ public static final String INSERT_PARALLELISM = "hoodie.insert.shuffle.parallelism"; public static final String BULKINSERT_PARALLELISM = "hoodie.bulkinsert.shuffle.parallelism"; public static final String BULKINSERT_USER_DEFINED_PARTITIONER_CLASS = "hoodie.bulkinsert.user.defined.partitioner.class"; + public static final String BULKINSERT_INPUT_DATA_SCHEMA_DDL = "hoodie.bulk_insert.schema.ddl"; Review comment: all other configs are named as "bulkinsert". can we fix this one too instead of "bulk_insert". ########## File path: hudi-spark-datasource/hudi-spark3/src/main/java/org/apache/hudi/spark3/internal/HoodieBulkInsertDataInternalWriterFactory.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.spark3.internal; + +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.table.HoodieTable; + +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.connector.write.DataWriter; +import org.apache.spark.sql.connector.write.DataWriterFactory; +import org.apache.spark.sql.types.StructType; + +/** + * Factory to assist in instantiating {@link HoodieBulkInsertDataInternalWriter}. + */ +public class HoodieBulkInsertDataInternalWriterFactory implements DataWriterFactory { Review comment: I assume this is exact replica of HoodieBulkInsertDataInternalWriterFactory in spark2 datasource. ########## File path: hudi-spark-datasource/hudi-spark3/src/main/java/org/apache/hudi/spark3/internal/HoodieBulkInsertDataInternalWriter.java ########## @@ -0,0 +1,116 @@ +/* + * 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.spark3.internal; + +import org.apache.hudi.client.HoodieInternalWriteStatus; +import org.apache.hudi.common.model.HoodieRecord; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.io.HoodieRowCreateHandle; +import org.apache.hudi.table.HoodieTable; + +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.connector.write.DataWriter; +import org.apache.spark.sql.connector.write.WriterCommitMessage; +import org.apache.spark.sql.types.StructType; + +import java.io.IOException; +import java.util.ArrayList; +import java.util.List; +import java.util.UUID; + +/** + * Hoodie's Implementation of {@link DataWriter<InternalRow>}. This is used in data source "hudi.spark3.internal" implementation for bulk insert. + */ +public class HoodieBulkInsertDataInternalWriter implements DataWriter<InternalRow> { Review comment: is there any changes in this class compared to HoodieBulkInsertDataInternalWriter in spark 2 datasource? ########## File path: hudi-spark-datasource/hudi-spark3/src/main/java/org/apache/hudi/spark3/internal/HoodieDataSourceInternalTable.java ########## @@ -0,0 +1,81 @@ +/* + * 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.spark3.internal; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hudi.client.common.HoodieSparkEngineContext; +import org.apache.hudi.common.table.HoodieTableMetaClient; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.table.HoodieSparkTable; +import org.apache.hudi.table.HoodieTable; + +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.connector.catalog.SupportsWrite; +import org.apache.spark.sql.connector.catalog.TableCapability; +import org.apache.spark.sql.connector.write.LogicalWriteInfo; +import org.apache.spark.sql.connector.write.WriteBuilder; +import org.apache.spark.sql.types.StructType; + +import java.util.HashSet; +import java.util.Set; + Review comment: java docs. ########## File path: hudi-spark-datasource/hudi-spark3/src/main/java/org/apache/hudi/spark3/internal/HoodieDataSourceInternalBatchWriter.java ########## @@ -0,0 +1,120 @@ +/* + * 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.spark3.internal; + +import org.apache.hudi.DataSourceUtils; +import org.apache.hudi.client.HoodieInternalWriteStatus; +import org.apache.hudi.client.SparkRDDWriteClient; +import org.apache.hudi.client.common.HoodieSparkEngineContext; +import org.apache.hudi.common.model.HoodieWriteStat; +import org.apache.hudi.common.model.WriteOperationType; +import org.apache.hudi.common.table.HoodieTableMetaClient; +import org.apache.hudi.common.table.timeline.HoodieInstant; +import org.apache.hudi.common.table.timeline.HoodieInstant.State; +import org.apache.hudi.common.table.timeline.HoodieTimeline; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.exception.HoodieException; +import org.apache.hudi.table.HoodieTable; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.connector.write.DataWriterFactory; +import org.apache.spark.sql.connector.write.WriterCommitMessage; +import org.apache.spark.sql.connector.write.BatchWrite; +import org.apache.spark.sql.connector.write.PhysicalWriteInfo; +import org.apache.spark.sql.types.StructType; + +import java.util.Arrays; +import java.util.List; +import java.util.stream.Collectors; + +/** + * Implementation of {@link BatchWrite} for datasource "hudi.spark3.internal" to be used in datasource implementation + * of bulk insert. + */ +public class HoodieDataSourceInternalBatchWriter implements BatchWrite { Review comment: I assume this class is almost exact replica of HoodieDataSourceInternalWriter ########## File path: hudi-spark-datasource/hudi-spark3/src/main/java/org/apache/hudi/spark3/internal/HoodieDataSourceInternalBatchWriter.java ########## @@ -0,0 +1,120 @@ +/* + * 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.spark3.internal; + +import org.apache.hudi.DataSourceUtils; +import org.apache.hudi.client.HoodieInternalWriteStatus; +import org.apache.hudi.client.SparkRDDWriteClient; +import org.apache.hudi.client.common.HoodieSparkEngineContext; +import org.apache.hudi.common.model.HoodieWriteStat; +import org.apache.hudi.common.model.WriteOperationType; +import org.apache.hudi.common.table.HoodieTableMetaClient; +import org.apache.hudi.common.table.timeline.HoodieInstant; +import org.apache.hudi.common.table.timeline.HoodieInstant.State; +import org.apache.hudi.common.table.timeline.HoodieTimeline; +import org.apache.hudi.common.util.Option; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.exception.HoodieException; +import org.apache.hudi.table.HoodieTable; +import org.apache.log4j.LogManager; +import org.apache.log4j.Logger; +import org.apache.spark.api.java.JavaSparkContext; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.connector.write.DataWriterFactory; +import org.apache.spark.sql.connector.write.WriterCommitMessage; +import org.apache.spark.sql.connector.write.BatchWrite; +import org.apache.spark.sql.connector.write.PhysicalWriteInfo; +import org.apache.spark.sql.types.StructType; + +import java.util.Arrays; +import java.util.List; +import java.util.stream.Collectors; + +/** + * Implementation of {@link BatchWrite} for datasource "hudi.spark3.internal" to be used in datasource implementation + * of bulk insert. + */ +public class HoodieDataSourceInternalBatchWriter implements BatchWrite { Review comment: why named it as "...Write**r**" even though interface is called Write. i.e. BatchWrite. ########## File path: hudi-spark-datasource/hudi-spark3/src/main/java/org/apache/hudi/spark3/internal/HoodieDataSourceInternalBatchWriterBuilder.java ########## @@ -0,0 +1,57 @@ +/* + * 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.spark3.internal; + +import org.apache.hudi.common.table.HoodieTableMetaClient; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.table.HoodieTable; +import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.connector.write.BatchWrite; +import org.apache.spark.sql.connector.write.WriteBuilder; +import org.apache.spark.sql.types.StructType; + +/** + * Implementation of {@link WriteBuilder} for datasource "hudi.spark3.internal" to be used in datasource implementation + * of bulk insert. + */ +public class HoodieDataSourceInternalBatchWriterBuilder implements WriteBuilder { Review comment: why suffixed it as "Write**r**Builder" while interface is called "WriteBuilder" ---------------------------------------------------------------- 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]
