相信大家通過之前的做法都已經搭建起了一個hadoop的開發環境。今天帶大家通過java api來訪問hdfs檔案系統
首先啟動hadoop叢集
start-dfs.sh
或者
start-all.sh //一鍵啟動hadoop叢集和yarn叢集
複製程式碼開啟idea
在pom.xml檔案里加入hadoop的依賴，我這裡使用的是我搭建的一樣版本的依賴
hadoop 2.7.3
<properties>
<hadoop.version>2.7.3</hadoop.version>
</properties>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>${hadoop.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>${hadoop.version}</version>
</dependency>
複製程式碼Java api在hdfs上建立一個檔案目錄
//建立配置檔案
Configuration conf = new Configuration();
//windows下無法找到對應的環境變數，需要設定。把hadoop解壓下來的根目錄
System.setProperty("hadoop.home.dir", "F:\\linux\\hadoop-2.7.3");
// 指定hadoop fs的地址
conf.set("fs.defaultFS", "hdfs://master:9000");
//定義訪問的根目錄
String userRootPath = "/userSpace"
//拿到檔案操作物件
FileSystem fs = FileSystem.get(conf);
//建立一個path物件，hdfs上的目錄都需要用path物件來訪問
Path dir = new Path(userRootPath); //表示根目錄下的 userSpace目錄
boolean result = fs.mkdirs(dir);
if(result){
System.out.println("建立目錄成功！");
}
複製程式碼其實就和java訪問檔案一樣的操作類似，非常簡單，不過操作hdfs主要是通過FileSystem類。下面給大家貼一下完整程式碼
package com.mmcc.springboothadoop.hadoop;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import org.apache.hadoop.io.IOUtils;
import java.io.ByteArrayOutputStream;
import java.io.IOException;
public class HdfsUtils {
private static Configuration conf = new Configuration();
public static String userRootPath = "/userSpace";
static {
//windows下無法找到對應的環境變數，需要設定
System.setProperty("hadoop.home.dir", "F:\\linux\\hadoop-2.7.3");
// 指定hadoop fs的地址
conf.set("fs.defaultFS", "hdfs://master:9000");
}
//判斷路徑是否存在
public static boolean exists(String path) throws IOException {
FileSystem fileSystem = FileSystem.get(conf);
return fileSystem.exists(new Path(path));
}
//建立檔案
public static void createFile(String filePath, byte[] contents) throws IOException {
FileSystem fileSystem = FileSystem.get(conf);
Path path = new Path(filePath);
FSDataOutputStream fdo = fileSystem.create(path);
fdo.write(contents);
fdo.close();
fileSystem.close();
}
/**
* 建立檔案
*
* @param filePath
* @param fileContent
* @throws IOException
*/
public static void createFile(String filePath, String fileContent)
throws IOException {
createFile(filePath, fileContent.getBytes());
}
//從本地複製到hdfs上
public static void copyFromLocalFile(String localFilePath, String remoteFilePath) throws IOException {
FileSystem fs = FileSystem.get(conf);
Path localPath = new Path(localFilePath);
Path remotePath = new Path(remoteFilePath);
fs.copyFromLocalFile(false, true, localPath, remotePath);
fs.close();
}
/**
* 刪除目錄或檔案
*
* @param remoteFilePath
* @param recursive
* @return
* @throws IOException
*/
public static boolean deleteFile(String remoteFilePath, boolean recursive)
throws IOException {
FileSystem fs = FileSystem.get(conf);
boolean result = fs.delete(new Path(remoteFilePath), recursive);
fs.close();
return result;
}
/**
* 刪除目錄或檔案(如果有子目錄,則級聯刪除)
*
* @param remoteFilePath
* @return
* @throws IOException
*/
public static boolean deleteFile(String remoteFilePath) throws IOException {
return deleteFile(remoteFilePath, true);
}
/**
* 檔案重新命名
*
* @param oldFileName
* @param newFileName
* @return
* @throws IOException
*/
public static boolean renameFile(String oldFileName, String newFileName)
throws IOException {
FileSystem fs = FileSystem.get(conf);
Path oldPath = new Path(oldFileName);
Path newPath = new Path(newFileName);
boolean result = fs.rename(oldPath, newPath);
fs.close();
return result;
}
/**
* 建立目錄
*
* @param dirName
* @return
* @throws IOException
*/
public static boolean createDirectory(String dirName) throws IOException {
FileSystem fs = FileSystem.get(conf);
Path dir = new Path(dirName);
boolean result = false;
if (!fs.exists(dir)) {
result = fs.mkdirs(dir);
}
fs.close();
return result;
}
//列出指定路徑下的檔案
public static RemoteIterator<LocatedFileStatus> listFiles(String dirPath,boolean recursive) throws IOException {
FileSystem fs = FileSystem.get(conf);
RemoteIterator<LocatedFileStatus> listFiles = fs.listFiles(new Path(dirPath), recursive);//不進行遞迴
fs.close();
return listFiles;
}
/**
* 列出指定路徑下的檔案（非遞迴）
*
* @param basePath
* @return
* @throws IOException
*/
public static RemoteIterator<LocatedFileStatus> listFiles(String basePath)
throws IOException {
FileSystem fs = FileSystem.get(conf);
RemoteIterator<LocatedFileStatus> remoteIterator = fs.listFiles(
new Path(basePath), false);
fs.close();
return remoteIterator;
}
/**
* 列出指定目錄下的檔案\子目錄資訊（非遞迴）
*
* @param dirPath
* @return
* @throws IOException
*/
public static FileStatus[] listStatus(String dirPath) throws IOException {
FileSystem fs = FileSystem.get(conf);
FileStatus[] fileStatuses = fs.listStatus(new Path(dirPath));
fs.close();
return fileStatuses;
}
//讀取檔案內容
public static byte[] readFile(String filePath) throws IOException {
byte[] fileContent = null;
FileSystem fs = FileSystem.get(conf);
Path path = new Path(filePath);
if (fs.exists(path)){
FSDataInputStream fsin = fs.open(path);
ByteArrayOutputStream bos = new ByteArrayOutputStream();
IOUtils.copyBytes(fsin,bos,conf);
fileContent = bos.toByteArray();
}
return fileContent;
}
//下載hdfs上的檔案
public static void download(String remote,String local) throws IOException {
FileSystem fs = FileSystem.get(conf);
//遠端hdfs上的檔案
Path remotePath = new Path(remote);
//本地的檔案
Path localPath = new Path(local);
fs.copyToLocalFile(remotePath,localPath);
fs.close();
}
}
複製程式碼