2）需求分析
需要在Map阶段对输入的数据根据规则进行过滤清洗。
3）实现代码
（1）编写LogMapper类
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类
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 {
//输入输出路径需要根据自己电脑上实际的输入输出路径设置
args = new String[] { "e:/input/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);
//设置reducetask个数为0
job.setNumReduceTasks(0);
// 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);
}
}