hadoop MapFileOutputFormat 源码

haddop MapFileOutputFormat 代码

文件路径：/hadoop-mapreduce-project/hadoop-mapreduce-client/hadoop-mapreduce-client-core/src/main/java/org/apache/hadoop/mapred/MapFileOutputFormat.java

/**
 * 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.mapred;

import java.io.IOException;

import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

import org.apache.hadoop.io.MapFile;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.SequenceFile.CompressionType;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.DefaultCodec;
import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.util.Progressable;
import org.apache.hadoop.util.ReflectionUtils;

/** An {@link OutputFormat} that writes {@link MapFile}s.
 */
@InterfaceAudience.Public
@InterfaceStability.Stable
public class MapFileOutputFormat 
extends FileOutputFormat<WritableComparable, Writable> {

  public RecordWriter<WritableComparable, Writable> getRecordWriter(FileSystem ignored, JobConf job,
                                      String name, Progressable progress)
    throws IOException {
    // get the path of the temporary output file 
    Path file = FileOutputFormat.getTaskOutputPath(job, name);
    
    FileSystem fs = file.getFileSystem(job);
    CompressionCodec codec = null;
    CompressionType compressionType = CompressionType.NONE;
    if (getCompressOutput(job)) {
      // find the kind of compression to do
      compressionType = SequenceFileOutputFormat.getOutputCompressionType(job);

      // find the right codec
      Class<? extends CompressionCodec> codecClass = getOutputCompressorClass(job,
	  DefaultCodec.class);
      codec = ReflectionUtils.newInstance(codecClass, job);
    }
    
    // ignore the progress parameter, since MapFile is local
    final MapFile.Writer out =
      new MapFile.Writer(job, fs, file.toString(),
                         job.getOutputKeyClass().asSubclass(WritableComparable.class),
                         job.getOutputValueClass().asSubclass(Writable.class),
                         compressionType, codec,
                         progress);

    return new RecordWriter<WritableComparable, Writable>() {

        public void write(WritableComparable key, Writable value)
          throws IOException {

          out.append(key, value);
        }

        public void close(Reporter reporter) throws IOException { out.close();}
      };
  }

  /** Open the output generated by this format. */
  public static MapFile.Reader[] getReaders(FileSystem ignored, Path dir,
                                            Configuration conf)
      throws IOException {
    return org.apache.hadoop.mapreduce.lib.output.MapFileOutputFormat.
      getReaders(dir, conf);
  }
    
  /** Get an entry from output generated by this class. */
  public static <K extends WritableComparable, V extends Writable>
  Writable getEntry(MapFile.Reader[] readers,
                                  Partitioner<K, V> partitioner,
                                  K key,
                                  V value) throws IOException {
    int readerLength = readers.length;
    int part;
    if (readerLength <= 1) {
      part = 0;
    } else {
      part = partitioner.getPartition(key, value, readers.length);
    }
    return readers[part].get(key, value);
  }

}

相关信息

hadoop 源码目录

相关文章

hadoop AMFeedback 源码

hadoop BackupStore 源码

hadoop BasicTypeSorterBase 源码

hadoop BufferSorter 源码

hadoop CleanupQueue 源码

hadoop Clock 源码

hadoop ClusterStatus 源码

hadoop Counters 源码

hadoop CumulativePeriodicStats 源码

hadoop DeprecatedQueueConfigurationParser 源码