Hadoop入门之--Helloword（Hadoop分布式文件系统(HDFS)和Map-Reduce框架）

前言

现在才打开 Hadoop 之门是不是有点晚 😌？

一个理论实现起来很比较容易的事情，提出这整套理论才是技术发展的根本因素，多学习多动脑也许你不只是新技术的学习者，也不只是理论的实践者，而是理论的提出者！

有高超的运用能力，不如创造能力，不如理论能力，最终还要归于物理，归于数学，归于哲学，到顶也就是神学了😄。

 

搭建简单 Hadoop 环境

创建 Maven 项目

略.....

在 POM 中增加依赖

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <groupId>com.ihiss</groupId>
    <artifactId>hi</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.5.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-hdfs</artifactId>
            <version>2.5.1</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.5.1</version>
        </dependency>
    </dependencies>

</project>

相关代码

package com.ihiss.hi;

import java.io.IOException;

import java.util.StringTokenizer;

import org.apache.hadoop.conf.Configuration;

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.Mapper;

import org.apache.hadoop.mapreduce.Reducer;

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

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

import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {

    public static class TokenizerMapper

            extends Mapper<Object, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);

        private Text word = new Text();


        public void map(Object key, Text value, Context context)

                throws IOException, InterruptedException {

            StringTokenizer itr = new StringTokenizer(value.toString());

            while (itr.hasMoreTokens()) {

                word.set(itr.nextToken());

                context.write(word, one);

            }

        }

    }

    public static class IntSumReducer

            extends Reducer<Text, IntWritable, Text, IntWritable> {

        private IntWritable result = new IntWritable();

        public void reduce(Text key, Iterable<IntWritable> values, Context context)

                throws IOException, InterruptedException {

            int sum = 0;

            for (IntWritable val : values) {

                sum += val.get();

            }

            result.set(sum);

            context.write(key, result);

        }

    }


    public static void main(String[] args) throws Exception {

        Configuration conf = new Configuration();

        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();

        if (otherArgs.length != 2) {

            System.err.println("Usage: wordcount <in> <out>");

            System.exit(2);

        }

        Job job = new Job(conf, "word count");

        job.setJarByClass(WordCount.class);

        job.setMapperClass(TokenizerMapper.class);

        job.setCombinerClass(IntSumReducer.class);

        job.setReducerClass(IntSumReducer.class);

        job.setOutputKeyClass(Text.class);

        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));

        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

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

    }

}