0

我正在尝试在内存排序中实现，即基于编号进行排序。的计数。我面临以下问题，在 Reduce 类的 close 方法中 output.collect 中出现 null pinter 异常。请帮忙！

我的编码逻辑正确吗？我将来自 reduce 方法的不同实例的标记保存在内存中。请帮我！我想要一个基于 TCounts 的排序输出。

package com.a;

import java.io.IOException;
import java.util.ArrayList;
import java.util.StringTokenizer;

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reporter;


public class Map1 extends MapReduceBase implements Mapper<LongWritable, Text, Text, 
Text >{
    public void map(LongWritable key, Text value, OutputCollector<Text, Text> output,
            Reporter reporter) throws IOException {

        StringTokenizer tokenizer = new StringTokenizer(value.toString());

        String tk = tokenizer.nextToken();
        String id = tokenizer.nextToken();
        String name = tokenizer.nextToken();

        StringTokenizer tkz = new StringTokenizer(name, ",");


        ArrayList<String> al = new ArrayList<String>();

        while(tkz.hasMoreTokens())
        {
            name = tkz.nextToken();
            al.add(name);
        }

        for(int i = 0; i<al.size(); i++)
        {
            output.collect(new Text(t+" "+al.get(i)), new Text("1"));
            System.out.println("out key:----->"+t+" "+al.get(i));
        }

    }

}



public class Reduce1 extends MapReduceBase implements Reducer<Text, Text, Text, Text>{
    //  @SuppressWarnings("unchecked")

    ArrayList<TCount> al = new ArrayList<TCount>();
    String key_str = null;
    private OutputCollector<Text, Text> output;



    public void reduce (Text key, Iterator<Text> values, OutputCollector<Text,
            Text> output, Reporter reporter) throws IOException {

        int sum = 0;

        while(values.hasNext())
        {
            String val = values.next().toString();
            sum = sum+Integer.parseInt(val);;

        }

        String str_val = String.valueOf(sum);
        key_str = key.toString();
        //output.collect(key, new Text(str_val));
        TCount tc = new TCount(key.toString(), sum);
        al.add(tc);


    }

    private Text t = new Text();
    private Text txt_key = new Text();


    public void close() throws IOException {
        Collections.sort(al);

        for(int i = 0; i<al.size(); i++)
        {

            String tkn = al.get(i).getT();
            System.out.println("token:-------------------> "+tkn);

            System.out.println("output: "+output);
            txt_key = new Text(t);
            txt = new Text(String.valueOf(al.get(i).getCount()));
            output.collect(txt_key, t);

        }
    }
}
4

1 回答 1

1

在 Reduce1 类中，您要声明输出对象：

private OutputCollector<Text, Text> output;

没有初始化它->所以此时它为空。

同样在方法中，reduce()您传递相同类型的参数 ( OutputCollector<Text, Text> output) -> 所以在此方法中，我猜您想说：

this.output=output;
// if the object is null, initialize it if you wanna use it

问题是，只要您的对象未初始化（实例化），您就会得到一个空指针异常。

于 2012-10-05T05:17:38.383 回答