MapReduce之简单的数据清洗----课堂测试 进度2

进行数据清洗首先开启Hadoop

 

然后在eclipse里面创建MapReduce项目

 

 之后写代码：

package 数据清洗hive;

import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.Locale;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;


public class shujuqingxi {
    
    public static class Map extends Mapper<Object,Text,Text,Text>{
          public static final SimpleDateFormat FORMAT = new SimpleDateFormat("d/MMM/yyyy:HH:mm:ss", Locale.ENGLISH); //原时间格式
        public static final SimpleDateFormat dateformat1 = new SimpleDateFormat("yyyy-MM-dd-HH:mm:ss");//现时间格式
        private  static Date parseDateFormat(String string) {         //转换时间格式
            Date parse = null;
            try {
                parse = FORMAT.parse(string);
            } catch (Exception e) {
                e.printStackTrace();
            }
            return parse;
        }
        private static Text newKey = new Text();
        private static Text newvalue = new Text();
        public void map(Object key,Text value,Context context) throws IOException, InterruptedException{
        String line = value.toString();
        System.out.println(line);
        String arr[] = line.split(",");
        newKey.set(arr[0]);
        final int first = arr[1].indexOf("");
        final int last = arr[1].indexOf(" +0800");
        String time = arr[1].substring(first + 1, last).trim();
        Date date = parseDateFormat(time);
       arr[1] = dateformat1.format(date);
        newvalue.set(arr[1]+" "+arr[2]+" "+arr[3]+" "+arr[4]+" "+arr[5]);
        context.write(newKey,newvalue);
        }
    }
        public static class Reduce extends Reducer<Text, Text, Text, Text> {
            protected void reduce(Text key, Iterable<Text> values, Context context)throws IOException, InterruptedException {
                for(Text text : values){
                    context.write(key,text);
                }
            }
        }
    
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        System.out.println("start");
        Job job=Job.getInstance(conf); 
        job.setJobName("filter");
        job.setJarByClass(shujuqingxi.class);
        job.setMapperClass(Map.class);
        job.setReducerClass(Reduce.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);        
        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputFormatClass(TextOutputFormat.class);
        Path in=new Path("hdfs://192.168.57.128:9000/testhdfs1026/result.txt");
        Path out=new Path("hdfs://192.168.57.128:9000/testhdfs1026/result");
        FileInputFormat.addInputPath(job, in);
        FileOutputFormat.setOutputPath(job, out);
        boolean flag = job.waitForCompletion(true);
        System.out.println(flag);
        System.exit(flag? 0 : 1);
    }
}

程序运行成功后：