Mapreduce对数据字段格式进行转换

Mapreduce对数据字段格式进行转换

对下如图所示的数据进行部分字段处理，第一列和第二列为Unix时间戳格式，下面利用Mapreduce对数据字段格式进行转换，将其转换为正常日期格式。

自定义类

import org.apache.hadoop.io.WritableComparable;

import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;

public class timeBean implements WritableComparable<timeBean> {
    public String data1;
    public String data2;
    public Double lon1;
    public Double lat1;
    public Double lon2;
    public Double lat2;


    public timeBean() {
        super();
    }

    @Override
    public void write(DataOutput dataOutput) throws IOException {
        dataOutput.writeUTF(data1);
        dataOutput.writeUTF(data2);
        dataOutput.writeDouble(lon1);
        dataOutput.writeDouble(lat1);
        dataOutput.writeDouble(lon2);
        dataOutput.writeDouble(lat2);
    }

    @Override
    public void readFields(DataInput dataInput) throws IOException {
        this.data1 = dataInput.readUTF();
        this.data2 = dataInput.readUTF();
        this.lon1 = dataInput.readDouble();
        this.lat1 = dataInput.readDouble();
        this.lon2 = dataInput.readDouble();
        this.lat2 = dataInput.readDouble();
    }

    public String setTime1(String time1) {
        data1 = TimeStamp2Date(time1);
        return data1;
    }

    public String setTime2(String time2) {
        data2 = TimeStamp2Date(time2);
        return data2;
    }

    @Override
    public String toString() {
        return  data1 + "," + data2 + "," + lon1 + "," + lat1 + "," + lon2 + "," + lat2;
    }

    public void set(String data1, String data2, Double lon1, Double lat1, Double lon2, Double lat2){
        this.data1 = data1;
        this.data2 = data2;
        this.lon1 = lon1;
        this.lat1 = lat1;
        this.lon2 = lon2;
        this.lat2 = lat2;
    }

    public String TimeStamp2Date(String timestampString){
        Long timestamp = Long.parseLong(timestampString)*1000;
        String date = new java.text.SimpleDateFormat("yyyy-MM-dd HH:mm:ss").format(new java.util.Date(timestamp));
        return date;
    }

    @Override
    public int compareTo(timeBean o) {
        return 0;
    }
}

Map阶段

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 timeMapper extends Mapper<LongWritable, Text,timeBean, NullWritable> {
    timeBean v = new timeBean();

        @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //获取一行
        String line = value.toString();

        //切割字段
        String[] fields = line.split(",");

        String data1 = v.setTime1(fields[0]);
        String data2 = v.setTime2(fields[1]);

        Double lon1 = Double.parseDouble(fields[2]);
        Double lat1 = Double.parseDouble(fields[3]);
        Double lon2 = Double.parseDouble(fields[4]);
        Double lat2 = Double.parseDouble(fields[5]);


        v.set(data1,data2,lon1,lat1,lon2,lat2);

        context.write(v,NullWritable.get());
    }

}

无需进行Reduce操作

Driver阶段

import java.io.IOException;

public class timeDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        args = new String[]{"D:/input/timeStamp/20161104","D:/output/timeStamp/20161104"};

        // 1 获取配置信息以及封装任务
        Configuration configuration = new Configuration();
        Job job = Job.getInstance(configuration);

        // 2 设置jar加载路径
        job.setJarByClass(timeDriver.class);

        // 3 设置map,无需reduce类
        job.setMapperClass(timeMapper.class);

        // 4 设置map输出
        job.setMapOutputKeyClass(timeBean.class);
        job.setMapOutputValueClass(NullWritable.class);

        // 5 设置最终输出kv类型
        job.setOutputKeyClass(timeBean.class);
        job.setOutputValueClass(NullWritable.class);

        // 6 设置输入和输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // 7 提交
        boolean result = job.waitForCompletion(true);

        System.exit(result ? 0 : 1);
    }
}

最终可以得到如下图所示的数据