mapreduce基础JOB操作

package cagy.mapreduce.wordcount;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.util.StringUtils;

public class WordCountMapper extends Mapper<LongWritable,Text ,Text, LongWritable>
{
  protected void map(LongWritable key,Text value,Context context) throws IOException, InterruptedException 
  {
    String line =value.toString();
    //切分
    String[] words=StringUtils.split(line,' ');
    //word,1
    for(String word:words)
    {
      context.write(new Text(word),new LongWritable(1));
    }
  }
}

package cagy.mapreduce.wordcount;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.Mapper.Context;
public class WordCountReducer extends Reducer<Text, LongWritable, Text, LongWritable>
{
  protected void reduce(Text key,Iterable<LongWritable> values,Context context) throws IOException, InterruptedException 
  {
    long count=0;
    for(LongWritable value:values)
    {
      count+=value.get();
    }
    //out
    context.write(key,new LongWritable(count));
  }
}

package cagy.mapreduce.wordcount;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

/***
 * 
 * 
 * 初始化JOB
 * 最后丢给hadoop
 * @author Administrator
 *
 */
public class WordCountRunner {

  public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
    // TODO Auto-generated method stub
    Configuration conf=new Configuration();
    Job wcjob=Job.getInstance(conf);
    wcjob.setJarByClass(WordCountRunner.class);//设置JOB
    
    wcjob.setMapperClass(WordCountMapper.class);
    
    wcjob.setReducerClass(WordCountReducer.class);
    //MAP输出的KV数据类型
    wcjob.setMapOutputKeyClass(Text.class);
    wcjob.setMapOutputValueClass(LongWritable.class);
    //reducer输出的KV类型
    wcjob.setOutputKeyClass(Text.class);
    wcjob.setOutputValueClass(LongWritable.class);
    //HDFS路劲
    FileInputFormat.setInputPaths(wcjob, "hdfs://192.168.0.109:9000/wc/data");
    //制定结果输出路劲
    FileOutputFormat.setOutputPath(wcjob, new Path("hdfs://192.168.0.109:9000/wc/output1"));
    boolean res=wcjob.waitForCompletion(true);
    
  //  System.exit(res?0:1);
  }

}

最后导出JAR FILE，上传到HADOOP集群 

 执行命令

hadoop jar wc.jar cagy.mapreduce.wordcount.WordCountRunner