前提:

eclipse与hadoop的配置成功

总结:

1.创建一个hadoop项目

  导入hadoop包: hadoop-0.20.2-core.jar hadoop-0.20.2-ant.jar hadoop-0.20.2-tools.jar

2.创建一个WordCount.java

源码

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.LongWritable;

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<LongWritable, Text, Text, IntWritable>

 {

  private final static IntWritable one = new IntWritable(1);

  private Text word = new Text();

  public void map(LongWritable 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();

  if (args.length != 2) {

   System.err.println("Usage: wordcount  ");

   System.exit(2);

   }

  conf.set("hadoop.job.ugi", "root,chenbo");

  conf.set("mapred.system.dir", "/hadoopdata/mapred/system");

  Job job = new Job(conf, "word count");

  job.setJarByClass(WordCount.class);

  job.setMapperClass(TokenizerMapper.class);

  job.setReducerClass(IntSumReducer.class);

  job.setMapOutputKeyClass(Text.class);

  job.setMapOutputValueClass(IntWritable.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);

  }

 }

3.编译WordCount.java

  javac -classpath /jz/hadoop-0.20.2/hadoop-0.20.2-core.jar WordCount.java -d /Home/chenbo/code/WordCount

  生成三个class文件 WordCount.class，WordCount$Map.class，WordCount$Reduce.class

4.生成WordCount.jar

  进入/Home/chenbo/code/WordCount目录

  jar cvf WordCount.jar *.class

5.引用WordCount

   Hadoop jar WordCount.jar WordCount in out

 

今天有收获，GO ON！