001/**
002 * Licensed to the Apache Software Foundation (ASF) under one
003 * or more contributor license agreements.  See the NOTICE file
004 * distributed with this work for additional information
005 * regarding copyright ownership.  The ASF licenses this file
006 * to you under the Apache License, Version 2.0 (the
007 * "License"); you may not use this file except in compliance
008 * with the License.  You may obtain a copy of the License at
009 *
010 *     http://www.apache.org/licenses/LICENSE-2.0
011 *
012 * Unless required by applicable law or agreed to in writing, software
013 * distributed under the License is distributed on an "AS IS" BASIS,
014 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
015 * See the License for the specific language governing permissions and
016 * limitations under the License.
017 */
018
019package org.apache.hadoop.io;
020
021import java.io.IOException;
022import java.io.DataInput;
023import java.io.DataOutput;
024import java.io.DataOutputStream;
025import java.io.DataInputStream;
026import java.io.ByteArrayOutputStream;
027import java.io.ByteArrayInputStream;
028import java.util.zip.Deflater;
029import java.util.zip.DeflaterOutputStream;
030import java.util.zip.InflaterInputStream;
031
032import org.apache.hadoop.classification.InterfaceAudience;
033import org.apache.hadoop.classification.InterfaceStability;
034
035/** A base-class for Writables which store themselves compressed and lazily
036 * inflate on field access.  This is useful for large objects whose fields are
037 * not be altered during a map or reduce operation: leaving the field data
038 * compressed makes copying the instance from one file to another much
039 * faster. */
040@InterfaceAudience.Public
041@InterfaceStability.Stable
042public abstract class CompressedWritable implements Writable {
043  // if non-null, the compressed field data of this instance.
044  private byte[] compressed;
045
046  public CompressedWritable() {}
047
048  @Override
049  public final void readFields(DataInput in) throws IOException {
050    compressed = new byte[in.readInt()];
051    in.readFully(compressed, 0, compressed.length);
052  }
053
054  /** Must be called by all methods which access fields to ensure that the data
055   * has been uncompressed. */
056  protected void ensureInflated() {
057    if (compressed != null) {
058      try {
059        ByteArrayInputStream deflated = new ByteArrayInputStream(compressed);
060        DataInput inflater =
061          new DataInputStream(new InflaterInputStream(deflated));
062        readFieldsCompressed(inflater);
063        compressed = null;
064      } catch (IOException e) {
065        throw new RuntimeException(e);
066      }
067    }
068  }
069
070  /** Subclasses implement this instead of {@link #readFields(DataInput)}. */
071  protected abstract void readFieldsCompressed(DataInput in)
072    throws IOException;
073
074  @Override
075  public final void write(DataOutput out) throws IOException {
076    if (compressed == null) {
077      ByteArrayOutputStream deflated = new ByteArrayOutputStream();
078      Deflater deflater = new Deflater(Deflater.BEST_SPEED);
079      DataOutputStream dout =
080        new DataOutputStream(new DeflaterOutputStream(deflated, deflater));
081      writeCompressed(dout);
082      dout.close();
083      deflater.end();
084      compressed = deflated.toByteArray();
085    }
086    out.writeInt(compressed.length);
087    out.write(compressed);
088  }
089
090  /** Subclasses implement this instead of {@link #write(DataOutput)}. */
091  protected abstract void writeCompressed(DataOutput out) throws IOException;
092
093}