apurtell commented on a change in pull request #3691: URL: https://github.com/apache/hbase/pull/3691#discussion_r718669525
########## File path: hbase-compression/hbase-compression-aircompressor/src/main/java/org/apache/hadoop/hbase/io/compress/aircompressor/SnappyCodec.java ########## @@ -0,0 +1,144 @@ +/* + * 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.hadoop.hbase.io.compress.aircompressor; + +import java.io.IOException; +import java.io.InputStream; +import java.io.OutputStream; + +import io.airlift.compress.snappy.SnappyCompressor; +import io.airlift.compress.snappy.SnappyDecompressor; + +import org.apache.hadoop.conf.Configurable; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.CommonConfigurationKeys; +import org.apache.hadoop.io.compress.BlockCompressorStream; +import org.apache.hadoop.io.compress.BlockDecompressorStream; +import org.apache.hadoop.io.compress.CompressionCodec; +import org.apache.hadoop.io.compress.CompressionInputStream; +import org.apache.hadoop.io.compress.CompressionOutputStream; +import org.apache.hadoop.io.compress.Compressor; +import org.apache.hadoop.io.compress.Decompressor; +import org.apache.yetus.audience.InterfaceAudience; + +/** + * Hadoop snappy codec implemented with aircompressor. + * <p> + * This is data format compatible with Hadoop's native snappy codec. + */ [email protected] +public class SnappyCodec implements Configurable, CompressionCodec { + + private Configuration conf; + + public SnappyCodec() { + conf = new Configuration(); + } + + @Override + public Configuration getConf() { + return conf; + } + + @Override + public void setConf(Configuration conf) { + this.conf = conf; + } + + @Override + public Compressor createCompressor() { + return new HadoopSnappyCompressor(); + } + + @Override + public Decompressor createDecompressor() { + return new HadoopSnappyDecompressor(); + } + + @Override + public CompressionInputStream createInputStream(InputStream in) throws IOException { + return createInputStream(in, createDecompressor()); + } + + @Override + public CompressionInputStream createInputStream(InputStream in, Decompressor d) + throws IOException { + return new BlockDecompressorStream(in, d, getBufferSize(conf)); + } + + @Override + public CompressionOutputStream createOutputStream(OutputStream out) throws IOException { + return createOutputStream(out, createCompressor()); + } + + @Override + public CompressionOutputStream createOutputStream(OutputStream out, Compressor c) + throws IOException { + int bufferSize = getBufferSize(conf); + int compressionOverhead = (bufferSize / 6) + 32; + return new BlockCompressorStream(out, c, bufferSize, compressionOverhead); + } + + @Override + public Class<? extends Compressor> getCompressorType() { + return HadoopSnappyCompressor.class; + } + + @Override + public Class<? extends Decompressor> getDecompressorType() { + return HadoopSnappyDecompressor.class; + } + + @Override + public String getDefaultExtension() { + return ".snappy"; + } + + private static int getBufferSize(Configuration conf) { + int size = conf.getInt( + CommonConfigurationKeys.IO_COMPRESSION_CODEC_SNAPPY_BUFFERSIZE_KEY, + CommonConfigurationKeys.IO_COMPRESSION_CODEC_SNAPPY_BUFFERSIZE_DEFAULT); + return size > 0 ? size : 256 * 1024; + } + + @InterfaceAudience.Private Review comment: My understanding is we do it, but I'm also not sure of the best practice. -- 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]
