Application of Hadoop counters and data cleaning

package com.atguigu.mapreduce.weblog;
import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
public class LogMapper extends Mapper<LongWritable, Text, Text, NullWritable>{
  Text k = new Text();
  @Override
  protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
   // 1 Get 1 line of data String line = value.toString();
   // 2 Parse log boolean result = parseLog(line,context);
   // 3 Log is illegal and exit if (!result) {
     return;
   }
   // 4 Set key
   k.set(line);
   // 5 Write data context.write(k, NullWritable.get());
  }
  // 2 Parse log private boolean parseLog(String line, Context context) {
   // 1 intercept String[] fields = line.split(" ");
   // 2 Logs with a length greater than 11 are legal if (fields.length > 11) {
     // System counter context.getCounter("map", "true").increment(1);
     return true;
   }else {
     context.getCounter("map", "false").increment(1);
     return false;
   }
  }
}

package com.atguigu.mapreduce.weblog;
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;
public class LogDriver {
  public static void main(String[] args) throws Exception {
// The input and output paths need to be set according to the actual input and output paths on your computer args = new String[] { "e:/input/inputlog", "e:/output1" };
   // 1 Get job information Configuration conf = new Configuration();
   Job job = Job.getInstance(conf);
   // 2 Load the jar package job.setJarByClass(LogDriver.class);
   // 3 associated maps
   job.setMapperClass(LogMapper.class);
   // 4 Set the final output type job.setOutputKeyClass(Text.class);
   job.setOutputValueClass(NullWritable.class);
   // Set the number of reducetask to 0
   job.setNumReduceTasks(0);
   // 5 Set input and output paths FileInputFormat.setInputPaths(job, new Path(args[0]));
   FileOutputFormat.setOutputPath(job, new Path(args[1]));
   // 6 Submit job.waitForCompletion(true);
  }
}