课堂测试-数据清洗

package org.apache.hadoop.examples;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
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.output.FileOutputFormat;
public class WordCount2{
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Job job = Job.getInstance();
job.setJobName("WordCount2");
job.setJarByClass(WordCount2.class);
job.setMapperClass(doMapper.class);
job.setReducerClass(doReducer.class);
job.setoutputKeyClass(Text.class);
job.setoutputValueClass(NullWritable.class);
Path in = new Path("hdfs://localhost:9000/user/hadoop/output2/part-r-00000");
Path out = new Path("hdfs://localhost:9000/user/hadoop/output3");
FileInputFormat.addInputPath(job, in);
FileOutputFormat.setoutputPath(job, out);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
public static class doMapper extends Mapper<Object, Text, Text,  NullWritable>{
public static Text word = new Text();
@Override
protected void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
    int i=0;
    String line = value.toString();
    String arr[] = line.split("  ");
    String arrtime[]=arr[1].split("/");
    String arrtimedate[]=arrtime[2].split(":");
    String arr2[]=arrtimedate[3].split(" ");
    if(arrtime[1].equals("Nov")){
         i=11;
    }
    String time=arrtimedate[0]+"-"+i+"-"+arrtime[0]+" "+arrtimedate[1]+":"+arrtimedate[2]+":"+arr2[0];
    String[] type=arr[3].split("/");
word.set(arr[0]+"  "+time+"  "+arrtime[0]+"  "+arr[2]+"  "+type[0]+"  "+type[1]);
context.write(word,  NullWritable.get());
}
}
public static class doReducer 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());
}
}
}

运行结果：

 

 

package org.apache.hadoop.examples;
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.NullWritable;
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.output.FileOutputFormat;
public class WordCount3{
public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
Job job = Job.getInstance();
job.setJobName("WordCount3");
job.setJarByClass(WordCount3.class);
job.setMapperClass(doMapper.class);
job.setReducerClass(doReducer.class);
job.setoutputKeyClass(Text.class);
job.setoutputValueClass(NullWritable.class);
Path in = new Path("hdfs://localhost:9000/user/hadoop/output3/part-r-00000");
Path out = new Path("hdfs://localhost:9000/user/hadoop/output3");
FileInputFormat.addInputPath(job, in);
FileOutputFormat.setoutputPath(job, out);
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
public static class doMapper extends Mapper<Object, Text, Text,  NullWritable>{
public static Text word = new Text();
@Override
protected void map(Object key, Text value, Context context)
throws IOException, InterruptedException {
    int i=0;
    String line = value.toString();
    String arr[] = line.split("  ");
    String arrtime[]=arr[1].split("/");
    String arrtimedate[]=arrtime[2].split(":");
    String arr2[]=arrtimedate[3].split(" ");
    if(arrtime[1].equals("Nov")){
         i=11;
    }
    String time=arrtimedate[0]+"-"+i+"-"+arrtime[0]+" "+arrtimedate[1]+":"+arrtimedate[2]+":"+arr2[0];
    String[] type=arr[3].split("/");
word.set(arr[0]+"  "+time+"  "+arrtime[0]+"  "+arr[2]+"  "+type[0]+"  "+type[1]);
context.write(word,  NullWritable.get());
}
}
public static class doReducer 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());
}
}
}

运行结果：