yihua commented on code in PR #12772: URL: https://github.com/apache/hudi/pull/12772#discussion_r2076289756
########## hudi-spark-datasource/hudi-spark4-common/src/main/java/org/apache/hudi/spark4/internal/HoodieBulkInsertDataInternalWriter.java: ########## @@ -0,0 +1,79 @@ +/* + * 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.spark4.internal; + +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.index.HoodieIndex; +import org.apache.hudi.table.HoodieTable; +import org.apache.hudi.table.action.commit.BucketBulkInsertDataInternalWriterHelper; +import org.apache.hudi.table.action.commit.BulkInsertDataInternalWriterHelper; +import org.apache.hudi.table.action.commit.ConsistentBucketBulkInsertDataInternalWriterHelper; + +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; + +/** + * Hoodie's Implementation of {@link DataWriter<InternalRow>}. This is used in data source "hudi.spark4.internal" implementation for bulk insert. + */ +public class HoodieBulkInsertDataInternalWriter implements DataWriter<InternalRow> { Review Comment: Similarly for row writer with Datasource V2 implementation, let's see if they can be move to a common module, since the minimum Spark version supported for Hudi is Spark 3.3. ########## hudi-spark-datasource/hudi-spark4-common/src/main/java/org/apache/hudi/spark4/internal/DefaultSource.java: ########## @@ -0,0 +1,70 @@ +/* + * 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.spark4.internal; + +import org.apache.hudi.DataSourceUtils; +import org.apache.hudi.common.table.HoodieTableConfig; +import org.apache.hudi.config.HoodieInternalConfig; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.internal.BaseDefaultSource; +import org.apache.hudi.internal.DataSourceInternalWriterHelper; + +import org.apache.spark.sql.HoodieDataTypeUtils; +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.HashMap; +import java.util.Map; + +import static org.apache.spark.sql.HoodieDataTypeUtils.tryOverrideParquetWriteLegacyFormatProperty; + +/** + * DataSource V2 implementation for managing internal write logic. Only called internally. + * This class is only compatible with datasource V2 API in Spark 3. Review Comment: Update comment ########## hudi-spark-datasource/hudi-spark4-common/pom.xml: ########## @@ -0,0 +1,258 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + 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. +--> +<project xmlns="http://maven.apache.org/POM/4.0.0"; + xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"; + xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd";> + <parent> + <artifactId>hudi-spark-datasource</artifactId> + <groupId>org.apache.hudi</groupId> + <version>1.1.0-SNAPSHOT</version> + </parent> + <modelVersion>4.0.0</modelVersion> + + <artifactId>hudi-spark4-common</artifactId> Review Comment: We could take this in a separate prerequisite PR so it makes this PR easy. ########## hudi-spark-datasource/hudi-spark4-common/src/main/java/org/apache/hudi/spark4/internal/DefaultSource.java: ########## @@ -0,0 +1,70 @@ +/* + * 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.spark4.internal; + +import org.apache.hudi.DataSourceUtils; +import org.apache.hudi.common.table.HoodieTableConfig; +import org.apache.hudi.config.HoodieInternalConfig; +import org.apache.hudi.config.HoodieWriteConfig; +import org.apache.hudi.internal.BaseDefaultSource; +import org.apache.hudi.internal.DataSourceInternalWriterHelper; + +import org.apache.spark.sql.HoodieDataTypeUtils; +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.HashMap; +import java.util.Map; + +import static org.apache.spark.sql.HoodieDataTypeUtils.tryOverrideParquetWriteLegacyFormatProperty; + +/** + * 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 extends BaseDefaultSource implements TableProvider { Review Comment: Same here. This class looks exactly the same as Spark3's `DefaultSource`. ########## hudi-spark-datasource/hudi-spark4-common/pom.xml: ########## @@ -0,0 +1,258 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + 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. +--> +<project xmlns="http://maven.apache.org/POM/4.0.0"; + xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"; + xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd";> + <parent> + <artifactId>hudi-spark-datasource</artifactId> + <groupId>org.apache.hudi</groupId> + <version>1.1.0-SNAPSHOT</version> + </parent> + <modelVersion>4.0.0</modelVersion> + + <artifactId>hudi-spark4-common</artifactId> Review Comment: Do we need a separate `hudi-spark4-common` module? If almost all classes are shared with Spark 3 (`hudi-spark3-common`), it's better to move the shared classes to `hudi-spark-common` and move the rest to Spark 4.0 module. ########## hudi-spark-datasource/hudi-spark4-common/pom.xml: ########## @@ -0,0 +1,258 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- + 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. +--> +<project xmlns="http://maven.apache.org/POM/4.0.0"; + xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"; + xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd";> + <parent> + <artifactId>hudi-spark-datasource</artifactId> + <groupId>org.apache.hudi</groupId> + <version>1.1.0-SNAPSHOT</version> + </parent> + <modelVersion>4.0.0</modelVersion> + + <artifactId>hudi-spark4-common</artifactId> Review Comment: Right now there are many duplicated classes which will make the maintenance Hudi Spark integration much harder. -- 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]
