1. 環境準備
- 大數據集羣一套,沒有的可以自己本地搭建一套(參考地址:https://www.jianshu.com/p/2c2ae6490fa0)
- 本地安裝JDK
- 本地安裝IDEA或者Eclipse
2. 創建Maven項目
在IDEA工具中創建一個maven項目,並在pom.xml中添加以下依賴:
<dependencies>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>RELEASE</version>
</dependency>
<dependency>
<groupId>org.apache.logging.log4j</groupId>
<artifactId>log4j-core</artifactId>
<version>2.8.2</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.7.2</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.7.2</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>2.7.2</version>
</dependency>
<dependency>
<groupId>jdk.tools</groupId>
<artifactId>jdk.tools</artifactId>
<version>1.8</version>
<scope>system</scope>
<systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
</dependency>
</dependencies>
3. 編寫代碼
新建名爲HDFSClient的HDFS客戶端操作類,下面是一些基礎的客戶端操作樣例。
package com.lancer.hdfs;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.BlockLocation;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.LocatedFileStatus;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.RemoteIterator;
import org.apache.hadoop.io.IOUtils;
import org.junit.Test;
public class HDFSClient {
/**
* 創建目錄
* @throws Exception
* @throws IOException
* @throws URISyntaxException
*/
@Test
public void mkdir() throws Exception,IOException,URISyntaxException {
Configuration conf = new Configuration();
conf.set("fs.defaultFS", "hdfs://hadoop102:9000");
// 獲取hdfs客戶端對象
//FileSystem fs = FileSystem.get(conf);
FileSystem fs = FileSystem.get(new java.net.URI("hdfs://hadoop102:9000") , conf, "root");
// 在hdfs上創建路徑
fs.mkdirs(new Path("/client/test4"));
// 關閉資源
fs.close();
System.out.println("done");
}
/**
* 上傳文件
* @throws IOException
* @throws InterruptedException
* @throws URISyntaxException
*/
@Test
public void testCopyFromLocalFile() throws IOException, InterruptedException, URISyntaxException {
// 1. 獲取fs對象
FileSystem fs = FileSystem.get(new java.net.URI("hdfs://hadoop102:9000") , new Configuration(), "root");
//2 執行上傳API
fs.copyFromLocalFile(new Path("D:/學習/Hadoop權威指南(第四版).pdf"), new Path("/client/test"));
// 3 關閉資源
fs.close();
}
/**
* 上傳文件,並設置備份數量
* @throws IOException
* @throws InterruptedException
* @throws URISyntaxException
*/
@Test
public void testCopyFromLocalFile2() throws IOException, InterruptedException, URISyntaxException {
// 1 獲取文件系統
Configuration configuration = new Configuration();
//configuration.set("dfs.replication", "2");
FileSystem fs = FileSystem.get(new java.net.URI("hdfs://hadoop102:9000"), configuration, "root");
// 2 上傳文件
fs.copyFromLocalFile(new Path("D:/學習/Hadoop權威指南(第四版).pdf"), new Path("/client/test3"));
// 3 關閉資源
fs.close();
System.out.println("done");
}
/**
* 文件下載
* @throws IOException
* @throws InterruptedException
* @throws URISyntaxException
*/
@Test
public void testCopyToLocalFile() throws IOException, InterruptedException, URISyntaxException{
// 1 獲取文件系統
Configuration configuration = new Configuration();
FileSystem fs = FileSystem.get(new java.net.URI("hdfs://hadoop102:9000"), configuration, "root");
// 2 執行下載操作
// boolean delSrc 指是否將原文件刪除
// Path src 指要下載的文件路徑
// Path dst 指將文件下載到的路徑
// boolean useRawLocalFileSystem 是否開啓文件校驗
fs.copyToLocalFile(false, new Path("/client/test3/Hadoop權威指南(第四版).pdf"), new Path("d:/Hadoop權威指南(第四版).pdf"), true);
// 3 關閉資源
fs.close();
System.out.println("done");
}
/**
* 文件夾刪除
* @throws IOException
* @throws InterruptedException
* @throws URISyntaxException
*/
@Test
public void testDelete() throws IOException, InterruptedException, URISyntaxException{
// 1 獲取文件系統
Configuration configuration = new Configuration();
FileSystem fs = FileSystem.get(new java.net.URI("hdfs://hadoop102:9000"), configuration, "root");
// 2 執行刪除
fs.delete(new Path("/client/"), true);
// 3 關閉資源
fs.close();
System.out.println("done");
}
/**
* 文件名修改
* @throws IOException
* @throws InterruptedException
* @throws URISyntaxException
*/
@Test
public void testRename() throws IOException, InterruptedException, URISyntaxException{
// 1 獲取文件系統
Configuration configuration = new Configuration();
FileSystem fs = FileSystem.get(new java.net.URI("hdfs://hadoop102:9000"), configuration, "root");
// 2 修改文件名稱
fs.rename(new Path("/README.txt"), new Path("/README222.txt"));
// 3 關閉資源
fs.close();
System.out.println("done");
}
@Test
public void testListFiles() throws IOException, InterruptedException, URISyntaxException{
// 1獲取文件系統
Configuration configuration = new Configuration();
FileSystem fs = FileSystem.get(new java.net.URI("hdfs://hadoop102:9000"), configuration, "root");
// 2 獲取文件詳情
RemoteIterator<LocatedFileStatus> listFiles = fs.listFiles(new Path("/"), true);
while(listFiles.hasNext()){
LocatedFileStatus status = listFiles.next();
// 輸出詳情
// 文件名稱
System.out.println("文件名:" + status.getPath().getName());
// 長度
System.out.println("長度:" + status.getLen());
// 權限
System.out.println("權限:" + status.getPermission());
// 分組
System.out.println("分組:" + status.getGroup());
// 獲取存儲的塊信息
BlockLocation[] blockLocations = status.getBlockLocations();
System.out.println("存儲的塊信息:" + status.getGroup());
for (BlockLocation blockLocation : blockLocations) {
// 獲取塊存儲的主機節點
String[] hosts = blockLocation.getHosts();
for (String host : hosts) {
System.out.println(host);
}
}
System.out.println("-----------班長的分割線----------");
}
// 3 關閉資源
fs.close();
System.out.println("done");
}
/**
* HDFS文件和文件夾判斷
* @throws IOException
* @throws InterruptedException
* @throws URISyntaxException
*/
@Test
public void testListStatus() throws IOException, InterruptedException, URISyntaxException{
// 1 獲取文件配置信息
Configuration configuration = new Configuration();
FileSystem fs = FileSystem.get(new java.net.URI("hdfs://hadoop102:9000"), configuration, "root");
// 2 判斷是文件還是文件夾
FileStatus[] listStatus = fs.listStatus(new Path("/"));
for (FileStatus fileStatus : listStatus) {
// 如果是文件
if (fileStatus.isFile()) {
System.out.println("f:"+fileStatus.getPath().getName());
}else {
System.out.println("d:"+fileStatus.getPath().getName());
}
}
// 3 關閉資源
fs.close();
System.out.println("done");
}
/**
* IO操作,上傳文件,不使用封裝好的方法
* @throws IOException
* @throws InterruptedException
* @throws URISyntaxException
*/
@Test
public void putFileToHDFS() throws IOException, InterruptedException, URISyntaxException {
// 1 獲取文件系統
Configuration configuration = new Configuration();
FileSystem fs = FileSystem.get(new URI("hdfs://hadoop102:9000"), configuration, "root");
// 2 創建輸入流
FileInputStream fis = new FileInputStream(new File("D:/學習/Hadoop權威指南(第四版).pdf"));
// 3 獲取輸出流
FSDataOutputStream fos = fs.create(new Path("/Hadoop權威指南(第四版).pdf"));
// 4 流對拷
IOUtils.copyBytes(fis, fos, configuration);
// 5 關閉資源
IOUtils.closeStream(fos);
IOUtils.closeStream(fis);
fs.close();
System.out.println("done");
}
/**
* O操作,文件下載,不使用封裝好的方法
* @throws IOException
* @throws InterruptedException
* @throws URISyntaxException
*/
@Test
public void getFileFromHDFS() throws IOException, InterruptedException, URISyntaxException{
// 1 獲取文件系統
Configuration configuration = new Configuration();
FileSystem fs = FileSystem.get(new URI("hdfs://hadoop102:9000"), configuration, "root");
// 2 獲取輸入流
FSDataInputStream fis = fs.open(new Path("/Hadoop權威指南(第四版).pdf"));
// 3 獲取輸出流
FileOutputStream fos = new FileOutputStream(new File("d:/Hadoop權威指南(第四版)222.pdf"));
// 4 流的對拷
IOUtils.copyBytes(fis, fos, configuration);
// 5 關閉資源
IOUtils.closeStream(fos);
IOUtils.closeStream(fis);
fs.close();
System.out.println("done");
}
/**
* 分塊下載文件,第一塊
* @throws IOException
* @throws InterruptedException
* @throws URISyntaxException
*/
@Test
public void readFileSeek1() throws IOException, InterruptedException, URISyntaxException{
// 1 獲取文件系統
Configuration configuration = new Configuration();
FileSystem fs = FileSystem.get(new URI("hdfs://hadoop102:9000"), configuration, "root");
// 2 獲取輸入流
FSDataInputStream fis = fs.open(new Path("/hadoop-2.7.2.tar.gz"));
// 3 創建輸出流
FileOutputStream fos = new FileOutputStream(new File("d:/hadoop-2.7.2.tar.gz.part1"));
// 4 流的拷貝
byte[] buf = new byte[1024];
for(int i =0 ; i < 1024 * 128; i++){
fis.read(buf);
fos.write(buf);
}
// 5關閉資源
IOUtils.closeStream(fis);
IOUtils.closeStream(fos);
fs.close();
System.out.println("done");
}
/**
* 分塊下載文件,第二塊
* @throws IOException
* @throws InterruptedException
* @throws URISyntaxException
*/
@Test
public void readFileSeek2() throws IOException, InterruptedException, URISyntaxException{
// 1 獲取文件系統
Configuration configuration = new Configuration();
FileSystem fs = FileSystem.get(new URI("hdfs://hadoop102:9000"), configuration, "root");
// 2 打開輸入流
FSDataInputStream fis = fs.open(new Path("/hadoop-2.7.2.tar.gz"));
// 3 定位輸入數據位置
fis.seek(1024*1024*128);
// 4 創建輸出流
FileOutputStream fos = new FileOutputStream(new File("d:/hadoop-2.7.2.tar.gz.part2"));
// 5 流的對拷
IOUtils.copyBytes(fis, fos, configuration);
// 6 關閉資源
IOUtils.closeStream(fis);
IOUtils.closeStream(fos);
System.out.println("done");
/**
*
* 在Window命令窗口中進入到目錄E:\,然後執行如下命令,對數據進行合併
* type hadoop-2.7.2.tar.gz.part2 >> hadoop-2.7.2.tar.gz.part1
* 合併完成後,將hadoop-2.7.2.tar.gz.part1重新命名爲hadoop-2.7.2.tar.gz。解壓發現該tar包非常完整。
*/
}
}