Hadoop的使用

Hadoop WordCount

wordCount 是Hadoop里面最经典的入门程序。

我们可以先写一个Word Count.java的程序:

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;

public class WordCount {

  public static class TokenizerMapper
       extends Mapper<Object, Text, Text, IntWritable>{
    
    private final static IntWritable one = new IntWritable(1);// 输出的value类型
    private Text word = new Text();// 输出的key类型
    
    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();
    Job job = Job.getInstance(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(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
  }
}

TokenizerMapper:

IntSumReducer:

main函数中：

Job设置了6个类，首先是处理改作业的类，然后是设置负责Map，combine，reduce的类，以及输出的key，value的类。最后执行了一下。

打包执行

首先添加编译的环境变量:

export HADOOP_CLASSPATH=${JAVA_HOME}/lib/tools.jar

然后编译打包（在正确的目录下）：

root@huchi:/home/huchi/install_package/hadoop/hadoop-2.9.1# bin/hadoop com.sun.tools.javac.Main WordCount.java
root@huchi:/home/huchi/install_package/hadoop/hadoop-2.9.1# jar cf wc.jar WordCount*.class

生成了具体的文件后，我们就可以用了，不过我们要准备两个txt文件先上传到节点上。

hadoop fs -put file /

file 里面有几个txt.

root@huchi:/home/huchi/install_package/hadoop/hadoop-2.9.1# hadoop fs -cat /file/file1.txt
Hello huchi
Hello hadoop
Hello world
Hello guys
Hello nobody