OutputFormat接口实现类

OutputFormat是MapReduce输出的基类，所有实现MapReduce输出都实现了 OutputFormat接口。下面我们介绍几种常见的OutputFormat实现类。

1. 文本输出TextOutputFormat
   默认的输出格式是TextOutputFormat，它把每条记录写为文本行。它的键和值可以是任意类型，因为TextOutputFormat调用toString()方法把它们转换为字符串
2. SequenceFileOutputFormat
   将SequenceFileOutputFormat输出作为后续 MapReduce任务的输入，这便是一种好的输出格式，因为它的格式紧凑，很容易被压缩
3. 自定义OutputFormat
   根据用户需求，自定义实现输出

自定义OutputFormat使用场景及步骤

1. 使用场景
   为了实现控制最终文件的输出路径和输出格式，可以自定义OutputFormat
   例如：要在一个MapReduce程序中根据数据的不同输出两类结果到不同目录，这类灵活的输出需求可以通过自定义OutputFormat来实现。
2. 自定义OutputFormat步骤
   1）自定义一个类继承FileOutputFormat
   2）改写RecordWriter，具体改写输出数据的方法write()

自定义OutputFormat案例实操

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

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

案例实操

1）编写FilterMapper类

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

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

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

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 liujhOut = 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 liujhPath = new Path("e:/liujh.log");
            Path otherPath = new Path("e:/other.log");

            // 3 创建输出流
            liujhOut = fs.create(liujhPath);
            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“liujh”输出到不同文件
        if (key.toString().contains("liujh")) {
            liujhOut.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(liujhOut);
        IOUtils.closeStream(otherOut);  }
}

5）编写FilterDriver类

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);
    }
}

关注微信公众号
简书：https://www.jianshu.com/u/0278602aea1d
CSDN：https://blog.csdn.net/u012387141