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：

    4.0.0    com.kaikeba.hadoop    com.kaikeba.hadoop    1.0-SNAPSHOT    jar            2.7.3                            commons-cli            commons-cli            1.2                            commons-logging            commons-logging            1.1.3                            org.apache.hadoop            hadoop-mapreduce-client-jobclient            ${hadoop.version}                            org.apache.hadoop            hadoop-common            ${hadoop.version}                                                                            org.apache.hadoop            hadoop-hdfs            2.7.3                            org.apache.hadoop            hadoop-hdfs            ${hadoop.version}                            org.apache.hadoop            hadoop-mapreduce-client-app            ${hadoop.version}                            org.apache.hadoop            hadoop-mapreduce-client-hs            ${hadoop.version}                                                                                            

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。