4、Intelij+Maven搭建Hadoop项目

1创建工程

点击project——Maven——next

2通过maven导入项目依赖jar包

（1）设置maven自动导入依赖jar包


勾选 Import Maven projects automatically,点击apply
(2)配置pom.xml文件

pom.xml配置文件如下：

<?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.kaikeba.hadoop</groupId>
    <artifactId>com.kaikeba.hadoop</artifactId>
    <version>1.0-SNAPSHOT</version>
    <packaging>jar</packaging>

    <properties>
        <hadoop.version>2.7.3</hadoop.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>commons-cli</groupId>
            <artifactId>commons-cli</artifactId>
            <version>1.2</version>
        </dependency>
        <dependency>
            <groupId>commons-logging</groupId>
            <artifactId>commons-logging</artifactId>
            <version>1.1.3</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-jobclient</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <!-- 3.1.2 -->
        <!--        <dependency>-->
        <!--            <groupId>org.apache.hadoop</groupId>-->
        <!--            <artifactId>hadoop-hdfs-client</artifactId>-->
        <!--            <version>2.8.0</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-hdfs</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-app</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-mapreduce-client-hs</artifactId>
            <version>${hadoop.version}</version>
        </dependency>

        <!--        <dependency>-->
        <!--            <groupId>org.slf4j</groupId>-->
        <!--            <artifactId>slf4j-api</artifactId>-->
        <!--            <version>1.7.25</version>-->
        <!--        </dependency>-->
        <!--        <dependency>-->
        <!--            <groupId>log4j</groupId>-->
        <!--            <artifactId>log4j</artifactId>-->
        <!--            <version>1.2.17</version>-->
        <!--        </dependency>-->
    </dependencies>

</project>

3编写HDFS读写程序

****把本地文件传输到HDFS****
package com.kaikeba.hadoop.hdfs;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;
import java.io.*;
import java.net.URI;
/**
 * 将本地文件系统的文件通过java-API写入到HDFS文件
 */
public class FileCopyFromLocal {

    public static void main(String[] args)  {
        String source  = "E:\\aa.mp4";
        //获取/data的m目录存在（根据自己的环境更改）
        String  destination = "hdfs://122.51.241.109:9000/data/hdfs01.mp4";
        InputStream in  = null;
        try {
            in  = new BufferedInputStream(new FileInputStream(source));
            //HDFS读写的配置文件
            Configuration conf = new Configuration();
            //生成一个文件系统对象
            FileSystem fs = FileSystem.get(URI.create(destination),conf);
            //生成一个输出流
            OutputStream out = fs.create(new Path(destination));
            IOUtils.copyBytes(in, out, 4096, true);
        } catch (FileNotFoundException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

**把HDFS中的文件传输到本地**
package com.kaikeba.hadoop.hdfs;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IOUtils;

import java.io.BufferedOutputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.net.URI;

/**
 * 从HDFS读取文件
 * 打包运行jar包 [bruce@node-01 Desktop]$ hadoop jar com.kaikeba.hadoop-1.0-SNAPSHOT.jar  com.kaikeba.hadoop.hdfs.FileReadFromHdfs
 */
public class FileReadFromHdfs {

    public static void main(String[] args) {
        try {
            //
            String srcFile = "hdfs://122.51.241.109:9000/data/hdfs01.mp4";
            Configuration conf = new Configuration();

            FileSystem fs = FileSystem.get(URI.create(srcFile),conf);
            FSDataInputStream hdfsInStream = fs.open(new Path(srcFile));

            BufferedOutputStream outputStream = new BufferedOutputStream(new FileOutputStream("/opt/hdfs01.mp4"));

            IOUtils.copyBytes(hdfsInStream, outputStream, 4096, true);

        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

4通过运行jar包的方式验证

双击package


生成com.kaikeba.hadoop-1.0-SNAPSHOT.jar，考入到服务器中执行
执行命令：hadoop jar com.kaikeba.hadoop-1.0-SNAPSHOT.jar com.kaikeba.hadoop.hdfs.FileReadFromHdfs
注意： com.kaikeba.hadoop.hdfs.FileReadFromHdfs是全类名，根据自己的项目更改。