HDFS自定义处理类实现

1、新建interface： ImoocMapper.java

package com.imooc.bigdata.hadoop.hdfs;

/*
 *自定义Mapper
 */

public interface ImoocMapper {

    /*
     * 先放一个接口
     * line 读取到的每一行数据
     * context 上下文/缓存
     */
    public void map(String line, ImoocContext context);
}

2、新建class：WordCountMapper.java

package com.imooc.bigdata.hadoop.hdfs;

/*
 * 自定义WordCount实现类
 */

public class WordCountMapper implements ImoocMapper {

    @Override
    public void map(String line, ImoocContext context) {
        String[] words = line.split("\t");

        for (String word : words){
            Object value = context.get(word);
            if (value == null){
                context.write(word, 1);
            } else {
                int v = Integer.parseInt(value.toString());
                context.write(word, v+1);//去除单词对应的次数+1
            }
        }
    }
}