charlesconnell commented on code in PR #8541: URL: https://github.com/apache/hbase/pull/8541#discussion_r3737879858
########## hbase-common/src/main/java/org/apache/hadoop/hbase/io/compress/GzipByteBuffDecompressor.java: ########## @@ -0,0 +1,220 @@ +/* + * 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; + +import edu.umd.cs.findbugs.annotations.Nullable; +import java.io.IOException; +import java.util.zip.CRC32; +import java.nio.ByteBuffer; +import java.util.zip.DataFormatException; +import java.util.zip.Inflater; +import org.apache.hadoop.hbase.nio.ByteBuff; +import org.apache.hadoop.hbase.nio.SingleByteBuff; +import org.apache.hadoop.io.compress.zlib.ZlibDecompressor; +import org.apache.yetus.audience.InterfaceAudience; + +/** + * Glue for ByteBuffDecompressor on top of Hadoop's native + * {@link ZlibDecompressor.ZlibDirectDecompressor}. + */ [email protected] +public class GzipByteBuffDecompressor implements ByteBuffDecompressor { + + private static final int GZIP_HEADER_LENGTH = 10; + private static final int GZIP_TRAILER_LENGTH = 8; + + @Nullable + private final ZlibDecompressor.ZlibDirectDecompressor decompressor; + + private final Inflater inflater = new Inflater(true); + + private final CRC32 crc32 = new CRC32(); + + private boolean allowByteBuffDecompression; + + GzipByteBuffDecompressor(boolean nativeZlibLoaded) { + decompressor = nativeZlibLoaded + ? new ZlibDecompressor.ZlibDirectDecompressor(ZlibDecompressor.CompressionHeader.GZIP_FORMAT, + 0) + : null; + allowByteBuffDecompression = true; + } + + @Override + public boolean canDecompress(ByteBuff output, ByteBuff input) { + if (!allowByteBuffDecompression) { + return false; + } + if (!(output instanceof SingleByteBuff) || !(input instanceof SingleByteBuff)) { + return false; + } + boolean inputDirect = input.nioByteBuffers()[0].isDirect(); + boolean outputDirect = output.nioByteBuffers()[0].isDirect(); + if (inputDirect && outputDirect) { + return decompressor != null; + } + return !inputDirect && !outputDirect; + } + + @Override + public int decompress(ByteBuff output, ByteBuff input, int inputLen) throws IOException { + if (!(output instanceof SingleByteBuff) || !(input instanceof SingleByteBuff)) { + throw new IllegalStateException( + "At least one buffer is not a SingleByteBuff, this is not supported"); + } + if (inputLen < GZIP_HEADER_LENGTH + GZIP_TRAILER_LENGTH) { + throw new IOException("Input of length " + inputLen + " is too short to be a gzip member"); + } + + ByteBuffer nioInput = input.nioByteBuffers()[0]; + ByteBuffer nioOutput = output.nioByteBuffers()[0]; + boolean inputDirect = nioInput.isDirect(); + boolean outputDirect = nioOutput.isDirect(); + + if (inputDirect && outputDirect) { + if (decompressor == null) { + throw new IllegalStateException( + "GzipByteBuffDecompressor#decompress() was called with direct buffers but Hadoop's " + + "native zlib library is not loaded, this should never happen since " + + "canDecompress() would have returned false"); + } + return decompressOffHeap(nioInput, nioOutput, inputLen); + } + return decompressOnHeap(nioInput, nioOutput, inputLen); + } + + private int decompressOffHeap(ByteBuffer nioInput, ByteBuffer nioOutput, int inputLen) + throws IOException { + int inputStart = nioInput.position(); + int outputStart = nioOutput.position(); + + ByteBuffer gzipMember = nioInput.duplicate(); + gzipMember.limit(inputStart + inputLen); + + decompressor.reset(); + while (!decompressor.finished()) { + int outputRemainingBefore = nioOutput.remaining(); + try { + decompressor.decompress(gzipMember, nioOutput); + } catch (IOException e) { + throw new IOException("Invalid gzip stream: " + e.getMessage(), e); + } + if (nioOutput.remaining() == outputRemainingBefore && !decompressor.finished()) { + if (!nioOutput.hasRemaining()) { + throw new IOException("Output buffer is too small for the decompressed gzip stream"); + } + throw new IOException("Unexpected end of gzip stream"); + } + } Review Comment: Is there a reason this needs to loop? Why would the decompressor need multiple attempts? ########## hbase-common/src/main/java/org/apache/hadoop/hbase/io/compress/GzipByteBuffDecompressor.java: ########## @@ -0,0 +1,220 @@ +/* + * 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; + +import edu.umd.cs.findbugs.annotations.Nullable; +import java.io.IOException; +import java.util.zip.CRC32; +import java.nio.ByteBuffer; +import java.util.zip.DataFormatException; +import java.util.zip.Inflater; +import org.apache.hadoop.hbase.nio.ByteBuff; +import org.apache.hadoop.hbase.nio.SingleByteBuff; +import org.apache.hadoop.io.compress.zlib.ZlibDecompressor; +import org.apache.yetus.audience.InterfaceAudience; + +/** + * Glue for ByteBuffDecompressor on top of Hadoop's native + * {@link ZlibDecompressor.ZlibDirectDecompressor}. + */ [email protected] +public class GzipByteBuffDecompressor implements ByteBuffDecompressor { + + private static final int GZIP_HEADER_LENGTH = 10; + private static final int GZIP_TRAILER_LENGTH = 8; + + @Nullable + private final ZlibDecompressor.ZlibDirectDecompressor decompressor; + + private final Inflater inflater = new Inflater(true); Review Comment: For consistency, I suggest you use the top-level ZlibDecompressor to handle on-heap ########## hbase-common/src/test/java/org/apache/hadoop/hbase/io/compress/TestGzipByteBuffDecompressor.java: ########## @@ -0,0 +1,511 @@ +/* + * 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; + +import static org.junit.jupiter.api.Assertions.assertEquals; +import static org.junit.jupiter.api.Assertions.assertFalse; +import static org.junit.jupiter.api.Assertions.assertTrue; +import static org.junit.jupiter.api.Assertions.fail; +import static org.junit.jupiter.api.Assumptions.assumeTrue; + +import java.io.IOException; +import java.nio.ByteBuffer; +import java.util.Arrays; +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.hbase.nio.ByteBuff; +import org.apache.hadoop.hbase.nio.MultiByteBuff; +import org.apache.hadoop.hbase.nio.SingleByteBuff; +import org.apache.hadoop.hbase.testclassification.SmallTests; +import org.apache.hadoop.hbase.util.Bytes; +import org.apache.hadoop.util.NativeCodeLoader; +import org.junit.jupiter.api.Tag; +import org.junit.jupiter.api.Test; + +@Tag(SmallTests.TAG) +public class TestGzipByteBuffDecompressor { + + /* + * "HBase is fun to use and very fast" compressed as a single gzip member via GZIPOutputStream, + * matching the framing that ReusableStreamGzipCodec produces on the compression side. + */ Review Comment: Are there are situations where a gzip input payload would contain multiple members? -- 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]
