Hadoop2.6.0: Intellij idea 结合Maven本地运行MapReduce程序 (无需搭载Hadoop和HDFS环境)

环境

JDK 1.8
Intellij Idea 2018.1
Hadoop 2.6.0 (本地未安装Hadoop)
maven 3.5.4

创建word count项目

在idea 中新建maven java项目(配置maven jdk略)

配置pom依赖

pom.xml文件


    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
    </properties>

    <dependencies>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.11</version>
            <scope>test</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>2.6.0</version>
        </dependency>

        <dependency>
            <groupId>commons-cli</groupId>
            <artifactId>commons-cli</artifactId>
            <version>1.2</version>
        </dependency>

        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>1.2.17</version>
        </dependency>

    </dependencies>

创建mapper类

package com.lens.task;

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

import java.io.IOException;
import java.util.StringTokenizer;

/**
 * @author lens
 * @create 2020-02-25 10:24
 */
public class VoteCountMapper extends Mapper<Object, Text, Text, IntWritable> {
    private final static IntWritable one = new IntWritable(1);
    private Text word = new Text();

    @Override
    protected void map(Object key, Text value, Context context) throws IOException, InterruptedException {
        StringTokenizer words = new StringTokenizer(value.toString());
        while (words.hasMoreTokens()) {
            word.set(words.nextToken());
            context.write(word, one);
        }
    }
}

创建reducer类

package com.lens.task;

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

import java.io.IOException;

/**
 * @author lens
 * @create 2020-02-25 10:24
 */
public class VoteCountReducer 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 count = 0;

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

    }
}

创建voteCount 驱动类

package com.lens.task;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
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.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;


/**
 * @author lens
 * @create 2020-02-25 10:22
 */
public class VoteCount extends Configured implements Tool {
    public static void main(String[] args) throws Exception {
        int res = ToolRunner.run(new Configuration(),new VoteCount(),args);
        System.exit(res);
    }


    public int run(String[] args) throws Exception {
        if (args.length !=2){
            System.out.println("Incorrect input, expected: [input] [output]");
            System.exit(-1);
        }

        Configuration conf = this.getConf();
        Job job = new Job(conf, "word count");
        job.setJarByClass(VoteCount.class);

        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(Text.class);

        job.setMapperClass(VoteCountMapper.class);
        job.setReducerClass(VoteCountReducer.class);

        job.setInputFormatClass(TextInputFormat.class);
        job.setOutputValueClass(TextOutputFormat.class);

        job.setMapOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        FileInputFormat.setInputPaths(job, new Path(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));

        job.submit();
        return job.waitForCompletion(true) ? 0 : 1;
    }
}

注意：此处File Format需要导入的是lib下的包

5. 创建wordcount文件输入目录input。文件字符进行计数，输出计数的结果 output。

首先需要配置输入路径，这里在项目下（src同级目录）新建一个文件夹input，并添加一个或多个文本文件到input中（已上传）作为示例。

需要注意：File->Project Structure，在弹出来的对话框中选择Modules项，这里将input文件夹标记为Excluded。

配置运行参数

此处需要配置程序运行时的Main class和VoteCount需要的输入input 输出output路径。

在Intellij菜单栏中选择Run->Edit Configurations，在弹出来的对话框中点击 +，新建一个Application配置。配置Main class为VoteCount（可以点击右边的...选择），Program arguments为input/ output/，即输入路径为创建的input文件夹，输出为output（可以不配）