mapreduce-案例-简单的数据清洗案例代码

//1.从Mapper继承
//2.重写map方法
//LongWritable,Text:表示初始输入的键值对格式。LongWritable是键的数据类型，Text是值的数据类型
//Text,LongWritable:表示map函数输出的数据的格式。Text是键的数据类型，LongWritable是值的数据类型
public class WeblogMapper extends Mapper<LongWritable,Text, Text, NullWritable> {
        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

            System.out.println(key);
//1.获取一行数据，使用空格拆分，得到字段组
            String[] words= value.toString().split("\\s+");
            System.out.println(words.length);
            System.out.println("==============================================================");
//2.如果有6个字段，我们就保留这条数据
            if (words.length == 9) {
                context.write(value, NullWritable.get());
            }
        }
}

package com.example.weblog;
//它要做七件事。核心是提交任务给hadoop

import com.example.mapreduce.WordCountMapper;
import com.example.mapreduce.WordCountReducer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;


public class WeblogDriver {
    public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {

//        设置操作集群时的用户名为root
        System.setProperty("HADOOP_USER_NAME", "root");
//        1.获取配置信息，初始化Job
        Configuration conf = new Configuration();

        Job job = Job.getInstance(conf);

//        2.关联Driver类
        job.setJarByClass(WeblogDriver.class);

//        3.关联Mapper和Reducer类
        job.setMapperClass(WeblogMapper.class);


//        4.设置Mapper输出的key和value类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);


        6.设置输入和输出路径：我们要处理的单词所在的文件在哪里？要把最终的结果保存到哪里？
        FileInputFormat.setInputPaths(job, new Path("D://vm//weblogs"));
        FileOutputFormat.setOutputPath(job, new Path("D://vm//weblogs_out123456"));

//        改成集群上的地址。 /cinput:/表示集群的根目
//        FileInputFormat.setInputPaths(job, new Path("/weblog"));
//        FileOutputFormat.setOutputPath(job, new Path("/weblog_out"));

//        7.提交任务
        boolean result = job.waitForCompletion(true);
        System.exit(result ? 0 : 1);
    }
}