Hadoop运行hadoop-examples-1.2.1.jar(wordcount)

Hadoop运行hadoop-examples-1.2.1.jar(wordcount)

1  前言

Hadoop 安装参考下列面链接博文

http://blog.chinaunix.net/uid-31429544-id-5759400.html

2  运行hadoop提供的例子

2.1  启动hadoop

    $start-all.sh
    启动过程如下图：

注意：$jps 命令可以看到那些进程已经启动，保证 NameNode、SecondaryNameNode、DataNode 、JobTracker、TaskTracker 都正常启动。

2.2  准备数据

    创建一个本地目录input
    在input创建em1.txt、em2.txt、em3.txt、em4.txt四个文件
    如下图：

2.3  文件复制到hadoop中

    $hadoop dfs
    可以看到hadoop支持的shell命令

    $hadoop dfs –mkdir input

    在hadoop创建目录 input

    $hadoop dfs –ls input

    浏览input下的文件

    $hadoop dfs –put input/* input

    把input目录下的文件从Linux中复制到hadoop中

    过程如下图：

2.4  执行wordcount

    在hadoop的安装目录下面有hadoop-examples-1.2.1.jar，这个jar包中包含了一些在hadoop中执行的例子，hadoop支持执行jar包中的类。执行hadoop-examples-1.2.1.jar中的wordcount类的命令如下：

    $hadoop jar hadoop-examples-1.2.1.jar wordcount input output
    wordcount表示jar包中的类名，表示要执行这个类
    input是输入文件夹
    output是输出文件夹，必须不存在，它由程序自动创建，如果预先存在output文件夹，则会报错。
    执行过程如下图：

    我们可以查看output文件夹的内容来检查程序是否成功创建文件夹，通过查看output文件里面的part-r-00000文件的内容来检查程序执行结果
    执行结果如下图：

3  wordcount 源码

    在hadoop的安装目录下src/examples/org/apache/hadoop/examples中有很多hadoop提供的可以在hadoop上执行的类，可以找到WordCount.java，源码如下：

/**
 * Licensed 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.Text;
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.FileOutputFormat;
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();

    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(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  ");
      System.exit(2);
    }
    Job job = new Job(conf, "word count");
    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]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}