大数据之Hadoop(MapReduce)：自定义OutputFormat案例实操

Posted 2021-06-26 浊酒南街

目录

• 1.需求
• 2.需求分析
• 3.．案例实操

1.需求

过滤输入的log日志，包含jinghang的网站输出到e:/jinghang.log，不包含jinghang的网站输出到e:/other.log。
（1）输入数据

http://www.baidu.com
http://www.google.com
http://cn.bing.com
http://www.jinghang.com
http://www.sohu.com
http://www.sina.com
http://www.sin2a.com
http://www.sin2desa.com
http://www.sindsafa.com

（2）期望输出数据为两个文件
A）jinghang.log : 只存放链接中包含”jinghang”子串的地址
B）other.log : 存放链接中不包含”jinghang”子串的地址其他地址

2.需求分析

3.．案例实操

（1）编写FilterMapper类

package com.jinghang.mapreduce.outputformat;
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 FilterMapper extends Mapper<LongWritable, Text, Text, NullWritable>{
	
	@Override
	protected void map(LongWritable key, Text value, Context context)	throws IOException, InterruptedException {

		// 写出
		context.write(value, NullWritable.get());
	}
}

（2）编写FilterReducer类

package com.jinghang.mapreduce.outputformat;
import java.io.IOException;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class FilterReducer extends Reducer<Text, NullWritable, Text, NullWritable> {

Text k = new Text();

	@Override
	protected void reduce(Text key, Iterable<NullWritable> values, Context context)		throws IOException, InterruptedException {

       // 1 获取一行
		String line = key.toString();

       // 2 拼接
		line = line + "\\r\\n";

       // 3 设置key
       k.set(line);

       // 4 输出
		context.write(k, NullWritable.get());
	}
}

（3）自定义一个OutputFormat类

package com.jinghang.mapreduce.outputformat;
import java.io.IOException;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class FilterOutputFormat extends FileOutputFormat<Text, NullWritable>{

	@Override
	public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job)			throws IOException, InterruptedException {

		// 创建一个RecordWriter
		return new FilterRecordWriter(job);
	}
}

（4）编写RecordWriter类

package com.jinghang.mapreduce.outputformat;
import java.io.IOException;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.RecordWriter;
import org.apache.hadoop.mapreduce.TaskAttemptContext;

public class FilterRecordWriter extends RecordWriter<Text, NullWritable> {

	FSDataOutputStream jinghangOut = null;
	FSDataOutputStream otherOut = null;

	public FilterRecordWriter(TaskAttemptContext job) {

		// 1 获取文件系统
		FileSystem fs;

		try {
			fs = FileSystem.get(job.getConfiguration());

			// 2 创建输出文件路径
			Path jinghangPath = new Path("e:/jinghang.log");
			Path otherPath = new Path("e:/other.log");

			// 3 创建输出流
			jinghangOut = fs.create(jinghangPath);
			otherOut = fs.create(otherPath);
		} catch (IOException e) {
			e.printStackTrace();
		}
	}

	@Override
	public void write(Text key, NullWritable value) throws IOException, InterruptedException {

		// 判断是否包含“jinghang”输出到不同文件
		if (key.toString().contains("jinghang")) {
			jinghangOut.write(key.toString().getBytes());
		} else {
			otherOut.write(key.toString().getBytes());
		}
	}

	@Override
	public void close(TaskAttemptContext context) throws IOException, InterruptedException {

		// 关闭资源
IOUtils.closeStream(jinghangOut);
		IOUtils.closeStream(otherOut);	}
}

（5）编写FilterDriver类

package com.jinghang.mapreduce.outputformat;
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 FilterDriver {

	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/inputoutputformat", "e:/output2" };

		Configuration conf = new Configuration();
		Job job = Job.getInstance(conf);

		job.setJarByClass(FilterDriver.class);
		job.setMapperClass(FilterMapper.class);
		job.setReducerClass(FilterReducer.class);

		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(NullWritable.class);
		
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(NullWritable.class);

		// 要将自定义的输出格式组件设置到job中
		job.setOutputFormatClass(FilterOutputFormat.class);

		FileInputFormat.setInputPaths(job, new Path(args[0]));

		// 虽然我们自定义了outputformat，但是因为我们的outputformat继承自fileoutputformat
		// 而fileoutputformat要输出一个_SUCCESS文件，所以，在这还得指定一个输出目录
		FileOutputFormat.setOutputPath(job, new Path(args[1]));

		boolean result = job.waitForCompletion(true);
		System.exit(result ? 0 : 1);
	}
}