import java.io.IOException;

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 QuChong { /**  * 数据去重 利用并化的的思想  * @author hadoop  *  */ public static class Engine extends Mapper
    
     {      public void map(Object key, Text value, Context context) throws IOException, InterruptedException {      String line = value.toString();      context.write(new Text(line), new Text(""));     }   }      public static class IntSumReducer extends Reducer
     
       {         public void reduce(Text key, Iterable
      
        values, Context context) throws IOException, InterruptedException {     context.write(key, new Text(""));     }   }
      
     
    

   public static void main(String[] args) throws Exception {  //设置引擎配置类，包括引擎地址，引擎输入输出参数（目录）     Configuration conf = new Configuration();     String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();     if (otherArgs.length != 2) {       System.err.println("Usage: wordcount 
    
      
     
      ");       System.exit(2);     }     Job job = new Job(conf, "word count");     job.setJarByClass(QuChong.class);     //设置Map、Combine和Reduce处理类     job.setMapperClass(Engine.class);     job.setCombinerClass(IntSumReducer.class);     job.setReducerClass(IntSumReducer.class);     //设置输出类     job.setOutputKeyClass(Text.class);     job.setOutputValueClass(Text.class);     //设置输入类及输入目录     FileInputFormat.addInputPath(job, new Path(otherArgs[0]));     FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));     System.exit(job.waitForCompletion(true) ? 0 : 1);   }}