借助Maven搭建Hadoop开发环境的最详细教程分享

介绍

在开发Hadoop应用程序时，使用Maven来管理依赖项和构建过程是很方便的。本文将介绍如何在MacOS上使用Maven搭建Hadoop开发环境。

前置条件

安装Java
安装Maven
下载安装文件：hadoop-x.x.x.tar.gz

步骤

步骤一：解压hadoop安装文件

在命令行中进入到下载好的hadoop-x.x.x.tar.gz所在的目录下，输入以下命令进行解压：

tar -xzvf hadoop-x.x.x.tar.gz

解压完成后，进入到hadoop-x.x.x目录中。

步骤二：配置环境变量

编辑.bashrc文件，在文件末尾加入以下内容：

export HADOOP_HOME=/path/to/hadoop-x.x.x
export PATH=$PATH:$HADOOP_HOME/bin
export HADOOP_CONF_DIR=$HADOOP_HOME/etc/hadoop

其中，/path/to/hadoop-x.x.x是指hadoop-x.x.x所在的目录路径。

为了使修改立即生效，可以输入以下命令：

source ~/.bashrc

步骤三：设置Maven依赖项

在Maven工程中，需要使用hadoop-common、hadoop-hdfs、hadoop-mapreduce-client-core等jar包。需要在pom.xml文件中加入以下依赖项：

<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-common</artifactId>
    <version>2.7.3</version>
</dependency>

<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-hdfs</artifactId>
    <version>2.7.3</version>
</dependency>

<dependency>
    <groupId>org.apache.hadoop</groupId>
    <artifactId>hadoop-mapreduce-client-core</artifactId>
    <version>2.7.3</version>
</dependency>

步骤四：使用Maven构建Hadoop项目

在Maven工程的根目录下运行以下命令来构建项目：

mvn clean package

例一：WordCount示例

创建一个WordCount类，用于统计文件中的单词数量。

import java.nio.file.FileSystem;
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.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;

public class WordCount {

    public static class TokenizerMapper extends Mapper<LongWritable, Text, Text, IntWritable> {

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

        public void map(LongWritable 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();
        Job job = Job.getInstance(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(args[0]));
        FileOutputFormat.setOutputPath(job, new Path(args[1]));
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}

例二：HDFS示例

在HDFS上读取和写入文件，创建一个HdfsClient类。

import java.io.InputStream;
import java.net.URI;
import java.nio.file.FileSystem;
import java.nio.file.FileSystems;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class HdfsClient {

    private static Configuration conf = new Configuration();
    private static String uri = "hdfs://localhost:9000";
    private static org.apache.hadoop.fs.FileSystem hdfs;

    public static void main(String[] args) throws Exception {
        hdfs = FileSystem.get(new URI(uri), conf);

        // 读取文件
        Path readPath = new Path("/test/file");
        InputStream in = hdfs.open(readPath);
        byte[] data = new byte[1024];
        int length;
        while ((length = in.read(data)) > 0) {
            System.out.println(new String(data, 0, length));
        }

        // 写入文件
        String content = "Hello, Hadoop!";
        Path writePath = new Path("/test/result.txt");
        FSDataOutputStream os = hdfs.create(writePath);
        os.write(content.getBytes("UTF-8"));
        os.close();

        hdfs.close();
    }
}