合并去重MapReduce

去重合并【全】

import java.io.IOException;
import java.util.Iterator;
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 MyUnion {
    public MyUnion() {
    }
    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: myunion <in> [<in>...] <out>");
            System.exit(2);
        }
        Job job = Job.getInstance(conf, "my union");        //设置环境参数
        job.setJarByClass(MyUnion.class);                //设置整个程序的类名
        job.setMapperClass(MyUnion.TokenizerMapper.class); //添加Mapper类
        job.setReducerClass(MyUnion.QuChongReducer.class);  //添加Reducer类
        job.setOutputKeyClass(Text.class);                  //设置输出类型
        job.setOutputValueClass(Text.class);             //设置输出类型 
        for(int i = 0; i < otherArgs.length - 1; ++i) {
            FileInputFormat.addInputPath(job, new Path(otherArgs[i]));  //设置输入文件(路径)
        }
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));//设置输出文件
        System.exit(job.waitForCompletion(true)?0:1);
    }
    public static class TokenizerMapper extends Mapper<Object, Text, Text, Text> {
        private Text text = new Text(); 
        public TokenizerMapper() {
        }
        public void map(Object key, Text value, Mapper<Object, Text, Text, Text>.Context context) throws IOException, InterruptedException {
		text = value;
		context.write(text, new Text(""));
        }
    }
   public static class QuChongReducer extends Reducer<Text, Text, Text, Text> {
        public QuChongReducer() {
        }
        public void reduce(Text key, Iterable<Text> values, Reducer<Text, Text, Text, Text>.Context context) throws IOException, InterruptedException {
            context.write(key, new Text(""));
        }
    }

}