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  public final void readFields(DataInput in) throws IOException {
049    compressed = new byte[in.readInt()];
050    in.readFully(compressed, 0, compressed.length);
051  }
052
053  /** Must be called by all methods which access fields to ensure that the data
054   * has been uncompressed. */
055  protected void ensureInflated() {
056    if (compressed != null) {
057      try {
058        ByteArrayInputStream deflated = new ByteArrayInputStream(compressed);
059        DataInput inflater =
060          new DataInputStream(new InflaterInputStream(deflated));
061        readFieldsCompressed(inflater);
062        compressed = null;
063      } catch (IOException e) {
064        throw new RuntimeException(e);
065      }
066    }
067  }
068
069  /** Subclasses implement this instead of {@link #readFields(DataInput)}. */
070  protected abstract void readFieldsCompressed(DataInput in)
071    throws IOException;
072
073  public final void write(DataOutput out) throws IOException {
074    if (compressed == null) {
075      ByteArrayOutputStream deflated = new ByteArrayOutputStream();
076      Deflater deflater = new Deflater(Deflater.BEST_SPEED);
077      DataOutputStream dout =
078        new DataOutputStream(new DeflaterOutputStream(deflated, deflater));
079      writeCompressed(dout);
080      dout.close();
081      deflater.end();
082      compressed = deflated.toByteArray();
083    }
084    out.writeInt(compressed.length);
085    out.write(compressed);
086  }
087
088  /** Subclasses implement this instead of {@link #write(DataOutput)}. */
089  protected abstract void writeCompressed(DataOutput out) throws IOException;
090
091}