MapReduce之OutputFormat数据输出以及自定义实例操作

        OutputFormat是MapReduce输出的基类，所有实现MapReduce输出都实现了OutputFormat接口。默认输出格式是TextOutputFormat

        当需要输出数据到MySQL/HBase/Elasticsearch等存储框架时需要自定义OutputFormat。

        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wtite（）

实例：

 （1）编写LogMapper类

/**
 * @author LS
 * @date 2021/12/15 8:37
 * @description
 */
public class LogMapper extends Mapper<LongWritable,Text,Text,NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        context.write(value,NullWritable.get());
    }
}

（2）编写LogReducer类

/**
 * @author LS
 * @date 2021/12/15 8:39
 * @description
 */
public class LogReducer extends Reducer<Text,NullWritable,Text,NullWritable> {
    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        for (NullWritable value : values) {
            context.write(key,NullWritable.get());
        }
    }
}

（3）自定义一个LogOutputFormat类

/**
 * @author LS
 * @date 2021/12/15 8:52
 * @description
 */
public class LogOutputFormat extends FileOutputFormat<Text,NullWritable> {
    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException {
        LogRecordWriter logRecordWriter = new LogRecordWriter(job);
        return logRecordWriter;

    }
}

（4）编写LogRecordWriter类

/**
 * @author LS
 * @date 2021/12/15 8:42
 * @description
 */
public class LogRecordWriter extends RecordWriter<Text,NullWritable> {
    private FSDataOutputStream atguiguout;
    private FSDataOutputStream otherout;

    public LogRecordWriter(TaskAttemptContext job) {
        try {
            FileSystem fs = FileSystem.get(job.getConfiguration());
            atguiguout = fs.create(new Path("F:\\atguigu.log"));
            otherout = fs.create(new Path("F:\\other.log"));
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

    @Override
    public void write(Text text, NullWritable nullWritable) throws IOException, InterruptedException {
        String log = text.toString();

        if (log.contains("atguigu")){
            atguiguout.writeBytes(log+"\n");
        }else{
            otherout.writeBytes(log+"\n");
        }
    }

    @Override
    public void close(TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
        IOUtils.closeStreams(otherout);
        IOUtils.closeStreams(atguiguout);
    }
}

（5）编写LogDriver类

/**
 * @author LS
 * @date 2021/12/15 8:55
 * @description
 */
public class LogDriver {
    public static void main(String[] args) throws IOException, ClassNotFoundException, InterruptedException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);

        job.setJarByClass(LogDriver.class);
        job.setMapperClass(LogMapper.class);
        job.setReducerClass(LogReducer.class);

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

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

        job.setOutputFormatClass(LogOutputFormat.class);

        FileInputFormat.setInputPaths(job,new Path("F:\\inputoutputformat"));
        FileOutputFormat.setOutputPath(job,new Path("F:\\of"));

        job.waitForCompletion(true);
    }

}