hadoop-15 OutputFormat

OutputFormat是MapReduce输出的基类，所有实现MapReduce输出都实现了OutputFormat接口

OutputFormat实现类

默认输出格式TextOutFormat

自定义OutputFormat

自定义类继承FileOutFormat
改写RecordWriter，具体改写数据的输出方法write()
LogOutPutFormat.java

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;

import java.io.IOException;

public class LogOutPutFormat extends FileOutputFormat<Text, NullWritable> {
    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException {
        LogRecordWriter lrw = new LogRecordWriter(job);
        return lrw;
    }
}

LogRecordWriter.java

import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
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 java.io.IOException;

public class LogRecordWriter extends RecordWriter<Text, NullWritable> {

    private  FSDataOutputStream atguiguOut;
    private  FSDataOutputStream otherOut;

    public LogRecordWriter(TaskAttemptContext job) {
        // 创建两条流
        try {
            FileSystem fs = FileSystem.get(job.getConfiguration());
            atguiguOut = fs.create(new Path("E:\\hadoop\\logoutput\\atguigu.log"));
            otherOut = fs.create(new Path("E:\\hadoop\\logoutput\\other.log"));
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    @Override
    public void write(Text key, NullWritable value) throws IOException, InterruptedException {
        // 具体写
        String log = key.toString();
        if (log.contains("atguigu")) {
            atguiguOut.writeBytes(log + "\n");
        } else {
            otherOut.writeBytes(log + "\n");
        }
    }

    @Override
    public void close(TaskAttemptContext context) throws IOException, InterruptedException {
        // 关流
        IOUtils.closeStream(atguiguOut);
        IOUtils.closeStream(otherOut);
    }
}

LogMapper.java

import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

import java.io.IOException;

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());
    }
}

LogReducer.java

import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

import java.io.IOException;

public class LogReducer extends Reducer<Text, NullWritable, Text, NullWritable> {
    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        // 防止相同数据丢数据
        for (NullWritable value : values) {
            context.write(key, NullWritable.get());
        }
    }
}

LogDriver.java

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;

import java.io.IOException;

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.setMapOutputValueClass(NullWritable.class);

        // 设置OutPutFormat
        job.setOutputFormatClass(LogOutPutFormat.class);

        FileInputFormat.setInputPaths(job, new Path("E:\\hadoop\\loginput\\"));
        // 虽然我们定义了outputformat但是因为我们的outputformat继承自fileoutputformat
        // 而fileoutputformat要输出一个_SUCCESS文件，所以这里还得指定一个输出目录
        FileOutputFormat.setOutputPath(job, new Path("E:\\hadoop\\logoutput"));

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

Blog

hadoop-15 OutputFormat