MapReduce输出压缩格式文件

一，说明

    主要举例说明mapreduce如何输出压缩格式的文件，比较简单，直接上代码。

二，示例代码

/**
 * 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.examples;

import java.io.IOException;
import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.SequenceFile.CompressionType;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.DefaultCodec;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;

import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {

  public static class TokenizerMapper 
       extends Mapper<Object, Text, Text, IntWritable>{
     
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();
      
    public void map(Object key, Text value, Context context
                    ) throws IOException, InterruptedException {
      StringTokenizer itr = new StringTokenizer(value.toString());
      while (itr.hasMoreTokens()) {
        word.set(itr.nextToken());
        context.write(word, one); 
      }
    }
  }
  
  public static class IntSumReducer 
           extends Reducer<Text,IntWritable,Text,IntWritable> {
    private IntWritable result = new IntWritable();
    @SuppressWarnings("unused")
    
    public void reduce(Text key, Iterable<IntWritable> values, 
                       Context context
                       ) throws IOException, InterruptedException {
      int sum = 0;
      for (IntWritable val : values) {
        sum += val.get();
      }
      result.set(sum);
      /*context.write是单文件输出模式*/
      context.write(key, result);
     

    }
  }
  public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
      System.err.println("Usage: wordcount <in> <out>");
      System.exit(2);
    }
    //conf.set("mapreduce.framework.name", "yarn");
    //conf.set("yarn.resourcemanager.address", "192.168.10.225:8032");  
    @SuppressWarnings("deprecation")
	 Job job = new Job(conf, "word count");
    job.setJobName("wordcount");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(TokenizerMapper.class);
    job.setCombinerClass(IntSumReducer.class);
    job.setReducerClass(IntSumReducer.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    //FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
     
    /*以下压缩模式三选一，块压缩，不压缩，记录压缩，*/
    SequenceFileOutputFormat.setOutputCompressionType(job, CompressionType.BLOCK);
    //SequenceFileOutputFormat.setOutputCompressionType(job, CompressionType.NONE);
    //SequenceFileOutputFormat.setOutputCompressionType(job, CompressionType.RECORD);
    
    /*以下压缩算法，DefaultCodec.class，不压缩－－－－GzipCodec.class gzip压缩*/
    //SequenceFileOutputFormat.setOutputCompressorClass(job, DefaultCodec.class);
    SequenceFileOutputFormat.setOutputCompressorClass(job, org.apache.hadoop.io.compress.GzipCodec.class);
    SequenceFileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    
    
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}