数据清洗练习4

依然是mapper代码

import net.sf.json.JSONObject;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

public class mappp  extends Mapper <LongWritable, Text,Text, NullWritable>{
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        Text  k=new Text();
        String line=value.toString();
        net.sf.json.JSONObject j = JSONObject.fromObject(line);

        String[] d = new String[5];
        d[1]=j.getString("date");
        d[0]=j.getString("city");
      d[1]=d[1].replace(".","/");
        d[2] = j.getString("temp");
        d[3] = j.getString("wind");
        d[4] = j.getString("weather");
       j.put("date",d[1]);
     j.put("city",d[0]);

        String end = "";
        for (String item: d){
            end = end + item + " ";
        }

        k.set(end);
        context.write(k,NullWritable.get());
    }
}