rdblue commented on a change in pull request #1122: URL: https://github.com/apache/iceberg/pull/1122#discussion_r443020650
########## File path: spark/src/main/java/org/apache/iceberg/spark/source/BaseWriter.java ########## @@ -0,0 +1,143 @@ +/* + * 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.spark.source; + +import java.io.Closeable; +import java.io.IOException; +import java.util.List; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DataFiles; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.Metrics; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.encryption.EncryptedOutputFile; +import org.apache.iceberg.io.FileAppender; +import org.apache.iceberg.io.FileIO; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.util.Tasks; +import org.apache.spark.sql.catalyst.InternalRow; + +abstract class BaseWriter implements Closeable { + protected static final int ROWS_DIVISOR = 1000; + + private final List<DataFile> completedFiles = Lists.newArrayList(); + private final PartitionSpec spec; + private final FileFormat format; + private final SparkAppenderFactory appenderFactory; + private final OutputFileFactory fileFactory; + private final FileIO io; + private final long targetFileSize; + private PartitionKey currentKey = null; + private FileAppender<InternalRow> currentAppender = null; + private EncryptedOutputFile currentFile = null; + private long currentRows = 0; + + BaseWriter(PartitionSpec spec, FileFormat format, SparkAppenderFactory appenderFactory, + OutputFileFactory fileFactory, FileIO io, long targetFileSize) { + this.spec = spec; + this.format = format; + this.appenderFactory = appenderFactory; + this.fileFactory = fileFactory; + this.io = io; + this.targetFileSize = targetFileSize; + } + + public abstract void write(InternalRow row) throws IOException; Review comment: Yes. The alternative is to have two copies of everything, which I think isn't worth it. This API is unlikely to change between Spark versions because it is relied upon so heavily in Spark. I think it should be fine as long as we have thorough testing to catch any issues. ---------------------------------------------------------------- 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: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
