黑猴子的家：MapReduce 日志清洗 简单解析版

1、需求：

去除日志中字段长度小于等于11的日志

2、输入数据

data -> GitHub
数据过长，放不下，我就放在GitHub上了
https://github.com/liufengji/hadoop_data.git

3、实现代码

（1）编写LogMapper

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{
    
    Text k = new Text();
    
    @Override
    protected void map(LongWritable key, Text value, Context context)
            throws IOException, InterruptedException {
        
        // 1 获取1行数据
        String line = value.toString();
        
        // 2 解析日志
        boolean result = parseLog(line,context);
        
        // 3 日志不合法退出
        if (!result) {
            return;
        }
        
        // 4 设置key
        k.set(line);
        
        // 5 写出数据
        context.write(k, NullWritable.get());
    }

    // 2 解析日志
    private boolean parseLog(String line, Context context) {
        // 1 截取
        String[] fields = line.split(" ");
        
        // 2 日志长度大于11的为合法
        if (fields.length > 11) {
            // 系统计数器
            context.getCounter("map", "true").increment(1);
            return true;
        }else {
            context.getCounter("map", "false").increment(1);
            return false;
        }
    }
}

（2）编写LogDriver

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 {

        args = new String[] { "e:/inputlog", "e:/output1" };

        // 1 获取job信息
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        // 2 加载jar包
        job.setJarByClass(LogDriver.class);

        // 3 关联map
        job.setMapperClass(LogMapper.class);

        // 4 设置最终输出类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(NullWritable.class);

        // 5 设置输入和输出路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        // 6 提交
        job.waitForCompletion(true);
    }
}

4、Code -> GitHub

https://github.com/liufengji/hadoop_mapreduce.git