分布式处理框架MapReduce

一.概述

MapReduce源自 Google的MapReduce论文，发表于2004年12月
优点：海量数据离线处理&易开发&易运行
缺点：实时流式运算困难

二.wordcount分词系统案例入门

　　输入通过InputFormat读取，每读一行交由map处理，经过Shuffling分序丢到Reducing上面处理，最后通过OutputFormat把记录输出到文件系统（HDFS）上面去。

　　java源码：

package com.cracker.hadoop.mapreduce;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;

import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import java.io.IOException;

/**
 * 使用MapReduce开发WordCount应用程序
 */
public class WordCountApp {

    /**
     * Map：读取输入的文件
     */
    public static class MyMapper extends Mapper<LongWritable, Text, Text, LongWritable> {

        LongWritable one = new LongWritable(1);

        @Override
        protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

            // 接收到的每一行数据
            String line = value.toString();

            //按照指定分隔符进行拆分
            String[] words = line.split(" ");

            for (String word : words) {
                // 通过上下文把map的处理结果输出
                context.write(new Text(word), one);
            }

        }
    }

    /**
     * Reduce：归并操作
     */
    public static class MyReducer extends Reducer<Text, LongWritable, Text, LongWritable> {

        @Override
        protected void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException,
                InterruptedException {

            long sum = 0;
            for (LongWritable value : values) {
                // 求key出现的次数总和
                sum += value.get();
            }

            // 最终统计结果的输出
            context.write(key, new LongWritable(sum));
        }
    }

    /**
     * 定义Driver：封装了MapReduce作业的所有信息
     */
    public static void main(String[] args) throws Exception {

        //创建Configuration
        Configuration configuration = new Configuration();

        //创建Job
        Job job = Job.getInstance(configuration, "wordcount");

        //设置job的处理类
        job.setJarByClass(WordCountApp.class);

        //设置作业处理的输入路径
        FileInputFormat.setInputPaths(job, new Path(args[0]));

        //设置map相关参数
        job.setMapperClass(MyMapper.class);
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);

        //设置reduce相关参数
        job.setReducerClass(MyReducer.class);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(LongWritable.class);

        //设置作业处理的输出路径
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

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

View Code

　　相关命令

　　本地编译

　　mvn clean package -DskipTests

　　服务器

　　hadoop jar /root/app/hadoop-train-1.0.jar com.cracker.hadoop.mapreduce.WordCountApp hdfs://localhost:8020/hello.txt hdfs://localhost:8020/output/wc