sunchao commented on a change in pull request #3250: URL: https://github.com/apache/hadoop/pull/3250#discussion_r683870968
########## File path: hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/io/compress/zlib/BuiltInGzipCompressor.java ########## @@ -0,0 +1,251 @@ +/* + * 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.io.compress.zlib; + +import java.io.IOException; +import java.util.zip.Checksum; +import java.util.zip.Deflater; +import java.util.zip.GZIPOutputStream; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.io.compress.Compressor; +import org.apache.hadoop.io.compress.DoNotPool; +import org.apache.hadoop.util.DataChecksum; + +/** + * A {@link Compressor} based on the popular gzip compressed file format. + * http://www.gzip.org/ + */ +@DoNotPool +public class BuiltInGzipCompressor implements Compressor { + + /** + * Fixed ten-byte gzip header. See {@link GZIPOutputStream}'s source for + * details. + */ + private static final byte[] GZIP_HEADER = new byte[]{ + 0x1f, (byte) 0x8b, 0x08, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; + + // The trailer will be overwritten based on crc and output size. + private byte[] GZIP_TRAILER = new byte[]{0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; + + private final int GZIP_HEADER_LEN = GZIP_HEADER.length; + private final int GZIP_TRAILER_LEN = GZIP_TRAILER.length; + + private Deflater deflater; + + private int headerOff = 0; + private int trailerOff = 0; + + private int numBytesWritten = 0; + + private int currentBufLen = 0; + + private final Checksum crc = DataChecksum.newCrc32(); + + private BuiltInGzipDecompressor.GzipStateLabel state; + + public BuiltInGzipCompressor(Configuration conf) { init(conf); } + + @Override + public boolean finished() { + // Only if the trailer is also written, it is thought as finished. + return deflater.finished() && state == BuiltInGzipDecompressor.GzipStateLabel.FINISHED; + } + + @Override + public boolean needsInput() { + if (state == BuiltInGzipDecompressor.GzipStateLabel.INFLATE_STREAM) { + return deflater.needsInput(); + } + + return (state != BuiltInGzipDecompressor.GzipStateLabel.FINISHED); + } + + @Override + public int compress(byte[] b, int off, int len) throws IOException { + int compressedBytesWritten = 0; + + // If we are not within uncompressed data yet, output the header. + if (state != BuiltInGzipDecompressor.GzipStateLabel.INFLATE_STREAM && Review comment: Ah OK, so the compression can happen on multiple inputs. Then, I'm curious whether we should handle the `FINISHED` state too in this `if` clause. For instance, in the following situation: ```java @Override public void finish() throws IOException { if (!compressor.finished()) { compressor.finish(); while (!compressor.finished()) { compress(); } } } ``` the `CompressorStream` will first set the state to be `FINISHED` and then keep calling `compress` until it is finished. -- 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: common-issues-unsubscr...@hadoop.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: common-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: common-issues-h...@hadoop.apache.org
