大数据课堂测试3——数据清洗（1）

package result;

import java.io.IOException;
import java.util.StringTokenizer;
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.Mapper.Context;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class Result1 {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Job job = Job.getInstance();
        job.setJobName("WordCount");
        job.setJarByClass(Result1.class);
        job.setMapperClass(doMapper.class);
        //job.setReducerClass(doReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        Path in = new Path("hdfs://192.168.187.130:9000/result/result.txt");
        Path out = new Path("hdfs://192.168.187.130:9000/result/out");
        FileInputFormat.addInputPath(job, in);
        FileOutputFormat.setOutputPath(job, out);
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }

    public static class doMapper extends Mapper<Object, Text, Text, IntWritable> {
        public static final IntWritable one = new IntWritable();
        public static Text word = new Text();
        Text outputValue = new Text();

        @Override
        protected void map(Object key, Text value, Context context) throws IOException, InterruptedException {
            String line=value.toString();
            String arr[]=line.split(",");  
            word.set(arr[0]+"    "+arr[1]+"    "+arr[2]+"    "+arr[3]+"   "+arr[4]+"    "+arr[5]);  
            context.write(word,one);
        }
    }
    
}