pvary commented on code in PR #10179: URL: https://github.com/apache/iceberg/pull/10179#discussion_r1587796859
########## flink/v1.19/flink/src/main/java/org/apache/iceberg/flink/sink/writer/RowDataTaskWriterFactory.java: ########## @@ -0,0 +1,245 @@ +/* + * 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.iceberg.flink.sink.writer; + +import java.util.List; +import java.util.Map; +import java.util.function.Supplier; +import org.apache.flink.table.data.RowData; +import org.apache.flink.table.types.logical.RowType; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.PartitionKey; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Schema; +import org.apache.iceberg.Table; +import org.apache.iceberg.flink.RowDataWrapper; +import org.apache.iceberg.flink.sink.CachingTableSupplier; +import org.apache.iceberg.io.FileAppenderFactory; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.io.OutputFileFactory; +import org.apache.iceberg.io.PartitionedFanoutWriter; +import org.apache.iceberg.io.TaskWriter; +import org.apache.iceberg.io.UnpartitionedWriter; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.types.TypeUtil; +import org.apache.iceberg.util.ArrayUtil; +import org.apache.iceberg.util.SerializableSupplier; + +public class RowDataTaskWriterFactory implements TaskWriterFactory<RowData> { + private final Supplier<Table> tableSupplier; + private final Schema schema; + private final RowType flinkSchema; + private final PartitionSpec spec; + private final long targetFileSizeBytes; + private final FileFormat format; + private final List<Integer> equalityFieldIds; + private final boolean upsert; + private final FileAppenderFactory<RowData> appenderFactory; + + private transient OutputFileFactory outputFileFactory; + + public RowDataTaskWriterFactory( + Table table, + RowType flinkSchema, + long targetFileSizeBytes, + FileFormat format, + Map<String, String> writeProperties, + List<Integer> equalityFieldIds, + boolean upsert) { + this( + () -> table, + flinkSchema, + targetFileSizeBytes, + format, + writeProperties, + equalityFieldIds, + upsert); + } + + public RowDataTaskWriterFactory( + SerializableSupplier<Table> tableSupplier, + RowType flinkSchema, + long targetFileSizeBytes, + FileFormat format, + Map<String, String> writeProperties, + List<Integer> equalityFieldIds, + boolean upsert) { + this.tableSupplier = tableSupplier; + + Table table; + if (tableSupplier instanceof CachingTableSupplier) { Review Comment: I do not get this - we should not read any of the table metadata after the writer has been initialised for now. Let's talk about this. -- 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: issues-unsubscr...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
