Hadoop-MapReduce-自定义OutputFormat案例实操-连载中

OutputFormat数据输出

1 OutputFormat接口实现类

2 自定义OutputFormat

3 自定义OutputFormat案例实操

1）需求

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

2）需求分析

3）案例实操

（1）编写FilterMapper类

public class LogMapper extends Mapper<LongWritable, Text,Text, NullWritable> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //不做任何处理,直接写出一行log数据
        context.write(value,NullWritable.get());
    }
}

（2）编写FilterReducer类

public class LogReducer extends Reducer<Text, NullWritable,Text, NullWritable> {
    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        //防止有相同的数据,迭代写出
        for (NullWritable value : values) {
            context.write(key,NullWritable.get());
        }
    }
}

（3）自定义一个OutputFormat类

public class LogOutputFormat extends FileOutputFormat<Text, NullWritable> {
    @Override
    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext job) throws IOException, InterruptedException {
        //创建一个自定义的RecordWriter返回
        LogRecordWriter logRecordWriter = new LogRecordWriter(job);
        return logRecordWriter;
    }
}

（4）编写RecordWriter类

public class LogRecordWriter extends RecordWriter<Text, NullWritable> {

    private FSDataOutputStream qinjlOut;
    private FSDataOutputStream otherOut;

    public LogRecordWriter(TaskAttemptContext job) {
        try {
            //获取文件系统对象
            FileSystem fs = FileSystem.get(job.getConfiguration());
            //用文件系统对象创建两个输出流对应不同的目录
            qinjlOut = fs.create(new Path("d:/hadoop/qinjl.txt"));
            otherOut = fs.create(new Path("d:/hadoop/other.txt"));
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    @Override
    public void write(Text key, NullWritable value) throws IOException, InterruptedException {
        String log = key.toString();
        //根据一行的log数据是否包含qinjl,判断两条输出流输出的内容
        if (log.contains("qinjl")) {
            qinjlOut.writeBytes(log + "\n");
        } else {
            otherOut.writeBytes(log + "\n");
        }
    }

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

（5）编写FilterDriver类

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);

        //设置自定义的outputformat
        job.setOutputFormatClass(LogOutputFormat.class);

        FileInputFormat.setInputPaths(job, new Path("D:\\input"));
        //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("D:\\logoutput"));

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