8月1日

今天继续学习hadoop

OutputFormat:

这是在数据输出到文件之前的一步，通过这一步可以设置将数据输入到mysql 文件等

可以根据自己的需求输入到不同的存储中

*******进入reducer 的都是key值相同的集合

学习写了一个写入log文件的案例

Mapper

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，获取到一行数据直接写出
        context.write(value,NullWritable.get());
    }
}

reducer

public class LogReduce extends Reducer<Text, NullWritable,Text, NullWritable> {
    //进入reducer 的都是key值相同的集合
    @Override
    protected void reduce(Text key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {
        //防止相同的网址丢失
        for (NullWritable value : values) {
            context.write(key,NullWritable.get());
        }
    }
}

driver

public class LogDriver {
    public static void main(String[] args) throws ClassNotFoundException, InterruptedException, IOException {
        Configuration conf = new Configuration();
        Job job = Job.getInstance(conf);
        job.setJarByClass(LogDriver.class);
        job.setMapperClass(LogMapper.class);
        job.setReducerClass(LogReduce.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("E:\hadoop\datatest\outputformat"));
        // 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("E:\hadoop\datatest\logoutput"));
        boolean b = job.waitForCompletion(true);
        System.exit(b ? 0 : 1);
    }
}

LogOutPutFormat

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

public class LogRecordWriter extends RecordWriter<Text, NullWritable> {

    private FSDataOutputStream baidu;
    private FSDataOutputStream other;

    public LogRecordWriter(TaskAttemptContext job) {
        //获取两条流
        try {
            FileSystem fs = FileSystem.get(job.getConfiguration());
            baidu = fs.create(new Path("E:\hadoop\datatest\baidu.log"));
            other = fs.create(new Path("E:\hadoop\datatest\other.log"));
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

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

    }

    @Override
    public void close(TaskAttemptContext taskAttemptContext) throws IOException, InterruptedException {
        //关流
        IOUtils.closeStream(baidu);
        IOUtils.closeStream(other);

    }
}

学习时间：13：02到15：34