sunchao commented on a change in pull request #3250: URL: https://github.com/apache/hadoop/pull/3250#discussion_r683008770
########## 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}; Review comment: nit: this could be `private static final` ########## File path: hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/io/SequenceFile.java ########## @@ -1180,14 +1180,6 @@ public static Option syncInterval(int value) { new Metadata() : metadataOption.getValue(); this.compress = compressionTypeOption.getValue(); final CompressionCodec codec = compressionTypeOption.getCodec(); - if (codec != null && Review comment: there are a few unused imports in this file. ########## 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; Review comment: nit: these could be `static`. ########## 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 && + state != BuiltInGzipDecompressor.GzipStateLabel.TRAILER_CRC) { + if (currentBufLen <= 0) { + return compressedBytesWritten; + } + + int outputHeaderSize = writeHeader(b, off, len); + numBytesWritten += outputHeaderSize; + + compressedBytesWritten += outputHeaderSize; + + if (outputHeaderSize == len) { + return compressedBytesWritten; + } + + off += outputHeaderSize; + len -= outputHeaderSize; + } + + if (state == BuiltInGzipDecompressor.GzipStateLabel.INFLATE_STREAM) { + // now compress it into b[] + int deflated = deflater.deflate(b, off, len); + + compressedBytesWritten += deflated; + off += deflated; + len -= deflated; + + // All current input are processed. Going to output trailer. + if (deflater.finished()) { + state = BuiltInGzipDecompressor.GzipStateLabel.TRAILER_CRC; + fillTrailer(); + } else { + return compressedBytesWritten; + } + } + + int outputTrailerSize = writeTrailer(b, off, len); + numBytesWritten += outputTrailerSize; + + compressedBytesWritten += outputTrailerSize; + + return compressedBytesWritten; + } + + @Override + public long getBytesRead() { + return deflater.getTotalIn(); + } + + @Override + public long getBytesWritten() { + return numBytesWritten + deflater.getTotalOut(); + } + + @Override + public void end() { + deflater.end(); + } + + @Override + public void finish() { + deflater.finish(); + state = BuiltInGzipDecompressor.GzipStateLabel.FINISHED; + } + + private void init(Configuration conf) { + ZlibCompressor.CompressionLevel level = ZlibFactory.getCompressionLevel(conf); + ZlibCompressor.CompressionStrategy strategy = ZlibFactory.getCompressionStrategy(conf); + + // 'true' (nowrap) => Deflater will handle raw deflate stream only + deflater = new Deflater(level.compressionLevel(), true); + deflater.setStrategy(strategy.compressionStrategy()); + + state = BuiltInGzipDecompressor.GzipStateLabel.HEADER_BASIC; + } + + @Override + public void reinit(Configuration conf) { + init(conf); + crc.reset(); + numBytesWritten = 0; + currentBufLen = 0; + headerOff = trailerOff = 0; + } + + @Override + public void reset() { Review comment: we should reset `numBytesWritten` to 0 here too. BTW I think it might be better to name it `numExtraBytesWritten` or something since this only count header and trailer. ########## 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: nit: maybe just `if (state == BuiltInGzipDecompressor.GzipStateLabel.HEADER_BASIC)`? ########## 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 && + state != BuiltInGzipDecompressor.GzipStateLabel.TRAILER_CRC) { + if (currentBufLen <= 0) { Review comment: nit: maybe move this above line 83? it's a bit strange that this is in the `if` clause. -- 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
