pitrou commented on code in PR #1000: URL: https://github.com/apache/parquet-mr/pull/1000#discussion_r997965979
########## parquet-hadoop/src/main/java/org/apache/parquet/hadoop/codec/NonBlockedCompressor.java: ########## @@ -0,0 +1,186 @@ +/* + * 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.parquet.hadoop.codec; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.io.compress.Compressor; +import org.apache.parquet.Preconditions; + +import java.io.IOException; +import java.nio.ByteBuffer; + +/** + * This class is a wrapper around the underlying compressor. It always consumes + * the entire input in setInput and compresses it as one compressed block. + */ +abstract public class NonBlockedCompressor implements Compressor { + + // Buffer for compressed output. This buffer grows as necessary. + private ByteBuffer outputBuffer = ByteBuffer.allocateDirect(0); + + // Buffer for uncompressed input. This buffer grows as necessary. + private ByteBuffer inputBuffer = ByteBuffer.allocateDirect(0); + + private long bytesRead = 0L; + private long bytesWritten = 0L; + private boolean finishCalled = false; + + /** + * Fills specified buffer with compressed data. Returns actual number + * of bytes of compressed data. A return value of 0 indicates that + * needsInput() should be called in order to determine if more input + * data is required. + * + * @param buffer Buffer for the compressed data + * @param off Start offset of the data + * @param len Size of the buffer + * @return The actual number of bytes of compressed data. + */ + @Override + public synchronized int compress(byte[] buffer, int off, int len) throws IOException { + SnappyUtil.validateBuffer(buffer, off, len); Review Comment: I'm a curious: why does this code call a Snappy-specific API? -- 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: dev-unsubscr...@parquet.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
