openinx commented on a change in pull request #1213: URL: https://github.com/apache/iceberg/pull/1213#discussion_r459196795
########## File path: core/src/main/java/org/apache/iceberg/taskio/BaseTaskWriter.java ########## @@ -0,0 +1,141 @@ +/* + * 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.taskio; + +import java.io.IOException; +import java.util.Collections; +import java.util.List; +import java.util.function.Supplier; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DataFiles; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.Metrics; +import org.apache.iceberg.PartitionKey; +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.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.util.Tasks; + +abstract class BaseTaskWriter<T> implements TaskWriter<T> { + protected static final int ROWS_DIVISOR = 1000; + + private final List<DataFile> completedFiles = Lists.newArrayList(); + private final PartitionSpec spec; + private final FileFormat format; + private final FileAppenderFactory<T> appenderFactory; + private final OutputFileFactory fileFactory; + private final FileIO io; + private final long targetFileSize; + + protected BaseTaskWriter(PartitionSpec spec, FileFormat format, FileAppenderFactory<T> 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; + } + + @Override + public void abort() throws IOException { + close(); + + // clean up files created by this writer + Tasks.foreach(completedFiles) + .throwFailureWhenFinished() + .noRetry() + .run(file -> io.deleteFile(file.path().toString())); + } + + @Override + public List<DataFile> pollCompleteFiles() { + if (completedFiles.size() > 0) { + List<DataFile> dataFiles = ImmutableList.copyOf(completedFiles); + completedFiles.clear(); + return dataFiles; + } else { + return Collections.emptyList(); + } + } + + protected OutputFileFactory outputFileFactory() { + return this.fileFactory; + } + + WrappedFileAppender createWrappedFileAppender(PartitionKey partitionKey, + Supplier<EncryptedOutputFile> outputFileSupplier) { + EncryptedOutputFile outputFile = outputFileSupplier.get(); + FileAppender<T> appender = appenderFactory.newAppender(outputFile.encryptingOutputFile(), format); + return new WrappedFileAppender(partitionKey, outputFile, appender); + } + + class WrappedFileAppender { Review comment: I created this class because in fanout writer we will have several opening writers and when building the `DataFile`, we will need all the informations for the given FileAppender, such as partitionKey, EncryptedOutputFile etc. The previous spark implementations won't need the class because all of the context information are maintained inside the PartitionedWriter (currentXXX ), that's not work for fanout writer. It will be better to have such a class to hold those infos to build `DataFile`. > It would make sense to keep this class if it completely encapsulated the logic of rolling new files Good point. Make the WrappedFileAppender to accomplish all the rolling things, let me refactor this. ########## File path: core/src/main/java/org/apache/iceberg/taskio/BaseTaskWriter.java ########## @@ -0,0 +1,141 @@ +/* + * 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.taskio; + +import java.io.IOException; +import java.util.Collections; +import java.util.List; +import java.util.function.Supplier; +import org.apache.iceberg.DataFile; +import org.apache.iceberg.DataFiles; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.Metrics; +import org.apache.iceberg.PartitionKey; +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.ImmutableList; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.iceberg.util.Tasks; + +abstract class BaseTaskWriter<T> implements TaskWriter<T> { + protected static final int ROWS_DIVISOR = 1000; + + private final List<DataFile> completedFiles = Lists.newArrayList(); + private final PartitionSpec spec; + private final FileFormat format; + private final FileAppenderFactory<T> appenderFactory; + private final OutputFileFactory fileFactory; + private final FileIO io; + private final long targetFileSize; + + protected BaseTaskWriter(PartitionSpec spec, FileFormat format, FileAppenderFactory<T> 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; + } + + @Override + public void abort() throws IOException { + close(); + + // clean up files created by this writer + Tasks.foreach(completedFiles) + .throwFailureWhenFinished() + .noRetry() + .run(file -> io.deleteFile(file.path().toString())); + } + + @Override + public List<DataFile> pollCompleteFiles() { + if (completedFiles.size() > 0) { + List<DataFile> dataFiles = ImmutableList.copyOf(completedFiles); + completedFiles.clear(); + return dataFiles; + } else { + return Collections.emptyList(); + } + } + + protected OutputFileFactory outputFileFactory() { + return this.fileFactory; + } + + WrappedFileAppender createWrappedFileAppender(PartitionKey partitionKey, + Supplier<EncryptedOutputFile> outputFileSupplier) { + EncryptedOutputFile outputFile = outputFileSupplier.get(); + FileAppender<T> appender = appenderFactory.newAppender(outputFile.encryptingOutputFile(), format); + return new WrappedFileAppender(partitionKey, outputFile, appender); + } + + class WrappedFileAppender { Review comment: I created this class because in fanout writer we will have several opening writers and when building the `DataFile`, we will need all the informations for the given FileAppender, such as partitionKey, EncryptedOutputFile etc. The previous spark implementations won't need the class because all of the context information are maintained inside the PartitionedWriter (currentXXX ), that's not work for fanout writer. It will be better to have such a class to hold those infos to build `DataFile`. > It would make sense to keep this class if it completely encapsulated the logic of rolling new files Good point. Make the WrappedFileAppender to accomplish all the rolling things, let me refactor 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. 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
