1、需求：将file1和file2合并后按行去重。

file1:
2012-3-1 a
2012-3-2 b
2012-3-3 c
2012-3-4 d
2012-3-5 a
2012-3-6 b
2012-3-7 c
2012-3-3 c

file2:
2012-3-1 b
2012-3-2 a
2012-3-3 b
2012-3-4 d
2012-3-5 a
2012-3-6 c
2012-3-7 d
2012-3-3 c

2、代码实现

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 Dedup {
    //map  将输入中的value  复制到  输出数据的key上，并直接输出
    public static class Map extends Mapper<Object,Text,Text,Text>{
        private static Text line=new Text();//每行数据
        //实现map函数
        public void map(Object key,Text value,Context context) throws IOException,InterruptedException{
            line=value;
            context.write(line, new Text(""));
        }
    }
    
    //reduce  将输入中的key  复制到  输出数据的key上，并直接输出
    public static class Reduce extends Reducer<Text,Text,Text,Text>{
        //实现reduce函数
        public void reduce(Text key,Iterable<Text> values,Context context) throws IOException,InterruptedException{
            context.write(key, new Text(""));
        }
    }

    
    public static void main(String[] args) throws Exception{
//      权限问题 设置hadoop用户
//      System.setProperty("HADOOP_USER_NAME", "root");
//      创建配置对象
        Configuration conf = new Configuration();
//      这句话很关键
//      conf.set("mapred.job.tracker", "192.168.1.2:9001");
        
//      设置输入输出参数
        String[] ioArgs=new String[]{"dedup_in","dedup_out"};
//      设置其它参数
        String[] otherArgs = new GenericOptionsParser(conf, ioArgs).getRemainingArgs();
//      校验输入参数
        if (otherArgs.length != 2) {
            System.err.println("Usage: Data Deduplication <in> <out>");
            System.exit(2);
        }
        
//      创建Job对象
        Job job = Job.getInstance(conf, "Data Deduplication");
//      Job job = new Job(conf, "Data Deduplication");
//      指定reduce数量
        job.setNumReduceTasks(1);
//      设置运行job的类
        job.setJarByClass(Dedup.class);
//      设置Map、Combine和Reduce处理类
        job.setMapperClass(Map.class);
        job.setCombinerClass(Reduce.class);
        job.setReducerClass(Reduce.class);
//      设置map输出的key value
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);
//      设置reduce输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);
//      设置输入和输出目录
//      FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
//      FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
        FileInputFormat.addInputPath(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
//      提交job
        System.exit(job.waitForCompletion(true) ? 0 : 1);
     }

}

3、输出结果

2012-3-1 a
2012-3-1 b
2012-3-2 a
2012-3-2 b
2012-3-3 b
2012-3-3 c
2012-3-4 d
2012-3-5 a
2012-3-6 b
2012-3-6 c
2012-3-7 c
2012-3-7 d