NLineInputFormat的使用

Mapper阶段

import java.io.IOException;

public class NLineMapper extends Mapper<LongWritable, Text,Text, IntWritable> {

    Text k = new Text();
    IntWritable v= new IntWritable(1);

    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //获取一行内容
        String line = value.toString();
        //切割
        String[] split = line.split(" ");

        for(int i=0;i<split.length;i++){
            k.set(split[i]);
            context.write(k,v);
        }
    }
}

Reducer阶段

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

import java.io.IOException;

public class NlineReduce extends Reducer<Text, IntWritable,Text, IntWritable>{
    IntWritable v=new IntWritable();

    @Override
    protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
        int count=0;

        for(IntWritable v:values){
            count+=v.get();
        }
        v.set(count);
        context.write(key,v);
    }
}

Driver调度

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.NLineInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import java.net.URI;


public class NilneDriver {

    public static void main(String[] args) throws Exception {
        System.setProperty("HADOOP_USER_NAME","root");//root权限操作文件

        Configuration configuration=new Configuration();        //你要将Job提交到那个集群
        configuration.set("fs.defaultFS","hdfs://hadoop01:9000");//要获取集群信息
        //获取文件系统
        FileSystem fs=FileSystem.get(new URI("hdfs://hadoop01:9000"),configuration,"root");
        // 定义输入路径
        String INPUT_PATH = "hdfs://hadoop01:9000/input/words.txt";
        // 定义输出路径
        String OUT_PATH = "hdfs://hadoop01:9000/out";

        // 如果输出目录存在，我们就删除
        if (fs.exists(new Path(OUT_PATH)))
            fs.delete(new Path(OUT_PATH), true);

        Job job = Job.getInstance(configuration);// 构造job任务

        //设置一次读取的行数
        NLineInputFormat.setNumLinesPerSplit(job,2);

        //设置处理的记录数
        job.setInputFormatClass(NLineInputFormat.class);

        // 设置job类路径
        job.setJarByClass(NilneDriver.class);

        // 设置map和reduce类
        job.setMapperClass(NLineMapper.class);
        job.setReducerClass(NlineReduce.class);

        // 设置map的k,v类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // 设置reduce的k,v类型
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        //设置inputformat格式
        job.setInputFormatClass(NLineInputFormat.class);

        //指定输出的路径和设置输出的格式化类
        NLineInputFormat.setInputPaths(job , new Path(INPUT_PATH));
        FileOutputFormat.setOutputPath(job , new Path(OUT_PATH));
        // 提交工作
        boolean result = job.waitForCompletion(true);

        System.exit(result?0:1);
    }
}