MapReducer清洗实操——更改日期格式

需求

源数据举例

{“date”:“2020-02-03”,“city”:“beijing”}

处理后的数据

{“date”:“2020/02/03”,“city”:“beijing”}

Mapper部分

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 WeatherDataMap3 extends Mapper<LongWritable, Text,Text, NullWritable>{
    Text k = new Text();
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        String line = value.toString();
        line=line.replace("-","/");//方法一
//        line=line.replaceAll("\\-","/");//正则表达式("\\"="\")//方法二
        k.set(line);
        context.write(k,NullWritable.get());
    }
}

Reducer部分

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;


import java.io.IOException;

public class WeatherDataReduce3 extends Reducer<Text, NullWritable,Text,NullWritable> {

    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        context.write(key,NullWritable.get());
    }
}

Driver部分

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
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 WeatherDataDriver3 {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        conf.set("hadoop.tmp.dir","D:\\file\\hdfs_temp");
        //创建job
        Job job = Job.getInstance(conf);
        //设置jar存储位置
        job.setJarByClass(WeatherDataDriver3.class);
        //关联map和reduce
//        job.setMapperClass(WeatherDataMap3.class);
        job.setMapperClass(WeatherDataMap3_4.class);
        job.setReducerClass(WeatherDataReduce3.class);
        //map阶段输出key和value
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(NullWritable.class);
        //最后阶段输出
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);
        //输入输出路径
        Path p =setPath(job);
        p.getFileSystem(conf).delete(p,true);
        boolean result = job.waitForCompletion(true);
        System.out.println(result);
        System.exit(result?0:1);


    }
    public static Path setPath(Job job) throws IOException {
        Path inPath = new Path("D:\\file\\source\\weatherdata3.txt");
        Path outPath = new Path("D:\\file\\output");
        FileInputFormat.addInputPath(job,inPath);
        FileOutputFormat.setOutputPath(job,outPath);
        return outPath;


    }
}