HDFS的API操作
创建maven工程并导入jar包
-
注意
由于cdh版本的所有的软件涉及版权的问题,所以并没有将所有的jar包托管到maven仓库当中去,而是托管在了CDH自己的服务器上面,所以我们默认去maven的仓库下载不到,需要自己手动的添加repository去CDH仓库进行下载。
要用CDH的jar包,要先添加一个repository:https://www.cloudera.com/documentation/enterprise/release-notes/topics/cdh_vd_cdh5_maven_repo.html
<repositories>
<repository>
<id>cloudera</id>
<url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
</repository>
</repositories>
再从这里找需要的jar包:https://www.cloudera.com/documentation/enterprise/release-notes/topics/cdh_vd_cdh5_maven_repo_514x.html
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.6.0-mr1-cdh5.14.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.6.0-cdh5.14.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>2.6.0-cdh5.14.0</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-mapreduce-client-core</artifactId>
<version>2.6.0-cdh5.14.0</version>
</dependency>
<!-- https://mvnrepository.com/artifact/junit/junit -->
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.11</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.testng</groupId>
<artifactId>testng</artifactId>
<version>RELEASE</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.0</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
<encoding>UTF-8</encoding>
<!-- <verbal>true</verbal>-->
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>2.4.3</version>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<minimizeJar>true</minimizeJar>
</configuration>
</execution>
</executions>
</plugin>
<!-- <plugin>
<artifactId>maven-assembly-plugin </artifactId>
<configuration>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
<archive>
<manifest>
<mainClass>cn.itcast.hadoop.db.DBToHdfs2</mainClass>
</manifest>
</archive>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
</execution>
</executions>
</plugin>-->
</plugins>
</build>
使用URL的方式访问数据(重在了解)
import org.apache.commons.io.IOUtils;
import org.apache.hadoop.fs.FsUrlStreamHandlerFactory;
import org.junit.Test;
import java.io.*;
import java.net.MalformedURLException;
import java.net.URL;
public class demo {
@Test
public void demo1() throws IOException {
//第一步:注册HDFS的URL,让java代码能够识别HDFS的URL形式
URL.setURLStreamHandlerFactory(new FsUrlStreamHandlerFactory());
InputStream inputStream = null;
FileOutputStream outputStream =null;
//URL地址可以在hadoop配置文件core-site.xml中查看
String url = "hdfs://192.168.0.10:8020/test/yum.log";
//打开文件输入流
try {
inputStream =new URL(url).openStream();
outputStream = new FileOutputStream(new File("/Users/zhaozhuang/Downloads/hello.txt"));
IOUtils.copy(inputStream,outputStream);
}catch (IOException e){
e.printStackTrace();
}finally {
IOUtils.closeQuietly(inputStream);
IOUtils.closeQuietly(outputStream);
}
}
}
上述代码中String url的出处
获取FileSystem的几种方式
- 第一种方式获取FileSystem
@Test
public void getFileSystem1() throws IOException {
/*
FileSystem是一个抽象类,获取抽象类的实例有两种方式
第一种,看看这个抽象类有没有提供什么方法,返回它本身
第二种,找子类
*/
Configuration configuration = new Configuration();
//如果这里不加任何配置,这里获取到的就是本地文件系统
configuration.set("fs.defaultFS","hdfs://node01:8020");
FileSystem fileSystem = FileSystem.get(configuration);
System.out.println(fileSystem.toString());
fileSystem.close();
}
- 第二种方式获取FileSystem
@Test
public void getFileSystem2() throws URISyntaxException, IOException {
Configuration configuration = new Configuration();
FileSystem fileSystem = FileSystem.get(new URI("hdfs://node01:8020"), configuration);
System.out.println(fileSystem.toString());
fileSystem.close();
}
- 第三种方式获取FileSystem
@Test
public void getFileSystem3() throws IOException {
Configuration configuration = new Configuration();
configuration.set("fs.defaultFS","hdfs://node01:8020");
FileSystem fileSystem = FileSystem.newInstance(configuration);
System.out.println(fileSystem.toString());
fileSystem.close();
}
- 第四种方式获取FileSystem
@Test
public void getFileSystem4() throws URISyntaxException, IOException {
Configuration configuration = new Configuration();
FileSystem fileSystem = FileSystem.newInstance(new URI("hdfs://node01:8020"), configuration);
System.out.println(fileSystem.toString());
fileSystem.close();
}
递归遍历HDFS的所有文件
- 通过递归遍历hdfs文件系统
@Test
public void getAllFiles() throws URISyntaxException, IOException {
//获取HDFS
FileSystem fileSystem = FileSystem.get(new URI("hdfs://node01:8020"), new Configuration());
//获取文件的状态,可以通过fileStatuses来判断究竟是文件夹还是文件
FileStatus[] fileStatuses = fileSystem.listStatus(new Path("hdfs://node01:8020/"));
/**
循环遍历FileStatus,判断文件究竟是文件夹还是文件
如果是文件,直接输出路径
如果是文件夹,继续遍历
*/
for (FileStatus fileStatus : fileStatuses) {
if (fileStatus.isDirectory()){
//如果是文件夹,继续遍历(需要再写一个方法来获取文件夹中的文件)
getDirFiles(fileStatus.getPath(),fileSystem);
} else {
Path path = fileStatus.getPath();
System.out.println(path.toString());
}
}
}
public void getDirFiles(Path path,FileSystem fileSystem) throws IOException {
//还是先获取文件的状态
FileStatus[] fileStatuses = fileSystem.listStatus(path);
//循环遍历fileStatus
for (FileStatus fileStatus : fileStatuses) {
if (fileStatus.isDirectory()){
getDirFiles(fileStatus.getPath(),fileSystem);
} else {
System.out.println(fileStatus.getPath().toString());
}
}
}
- 官方提供的API直接遍历
/**
* 通过hdfs直接提供的API进行遍历
*/
@Test
public void getAllFiles2() throws URISyntaxException, IOException {
//获取HDFS
FileSystem fileSystem = FileSystem.get(new URI("hdfs://node01:8020"), new Configuration());
//获取RemoteIterator 得到所有的文件或者文件夹,第一个参数指定遍历的路径,第二个参数表示是否要递归遍历
RemoteIterator<LocatedFileStatus> locatedFileStatusRemoteIterator = fileSystem.listFiles(new Path("hdfs://node01:8020/"), true);
//while循环遍历
while (locatedFileStatusRemoteIterator.hasNext()){
LocatedFileStatus next = locatedFileStatusRemoteIterator.next();
System.out.println(next.getPath().toString());
}
fileSystem.close();
}
下载文件到本地
@Test
public void downloadFileToLocal() throws URISyntaxException, IOException {
//获取HDfS
FileSystem fileSystem = FileSystem.get(new URI("hdfs://node01:8020"), new Configuration());
//打开输入流,读取HDfS上的文件
FSDataInputStream inputStream = fileSystem.open(new Path("hdfs://node01:8020/test/yum.log"));
//用输出流,确定下载到本地的路径
FileOutputStream outputStream = new FileOutputStream(new File("/Users/zhaozhuang/Downloads/hello2.txt"));
//用IOUtils把文件下载下来
IOUtils.copy(inputStream,outputStream);
//关闭输入流和输出流
IOUtils.closeQuietly(inputStream);
IOUtils.closeQuietly(outputStream);
fileSystem.close();
}
在HDFS上创建文件夹
@Test
public void mkdirs() throws URISyntaxException, IOException {
//获取HDFS
FileSystem fileSystem = FileSystem.get(new URI("hdfs://node01:8020"), new Configuration());
//创建文件夹
boolean mkdirs = fileSystem.mkdirs(new Path("/hello/mydir/test"));
//关闭系统
fileSystem.close();
}
HDFS文件上传
@Test
public void uploadFileFromLocal() throws URISyntaxException, IOException {
//获取HDfS
FileSystem fileSystem = FileSystem.get(new URI("hdfs://node01:8020"), new Configuration());
//上传文件
fileSystem.copyFromLocalFile(new Path("/Users/zhaozhuang/Downloads/hello2.txt"),new Path("/"));
//关闭系统
fileSystem.close();
}
HDFS权限问题以及伪造用户
- 首先停止hdfs集群,在node01机器上执行以下命令
cd /export/servers/hadoop-2.6.0-cdh5.14.0
stop-dfs.sh
- 修改node01机器上的hdfs-site.xml当中的配置文件
<property>
<name>dfs.permissions</name>
<value>true</value>
</property>
- 修改完成之后配置文件发送到其他机器上面去
scp hdfs-site.xml node02:$PWD
scp hdfs-site.xml node03:$PWD
- 重启hdfs集群
start-dfs.sh
- 随意上传一些文件到我们hadoop集群当中准备测试使用
cd /export/servers/hadoop-2.6.0-cdh5.14.0/etc/hadoop
hdfs dfs -mkdir /config
hdfs dfs -put *.xml /config
hdfs dfs -chmod 600 /config/core-site.xml
- Java伪造root用户下载
@Test
public void getConfig() throws URISyntaxException, IOException, InterruptedException {
//获取HDFS(第三个参数为伪造的用户)
FileSystem fileSystem = FileSystem.get(new URI("hdfs://node01:8020"), new Configuration(),"root");
//下载文件
fileSystem.copyToLocalFile(new Path("/config/core-site.xml"),new Path("/Users/ZhaoZhuang/Downloads/hello3.txt"));
//关闭系统
fileSystem.close();
}
HDFS的小文件合并
- 在linux进行小文件合并
cd /export/servers
hdfs dfs -getmerge /config/*.xml ./hello.xml
- 在java进行小文件合并
@Test
public void mergeFiles() throws URISyntaxException, IOException, InterruptedException {
//获取HDFS
FileSystem fileSystem = FileSystem.get(new URI("hdfs://node01:8020"), new Configuration(), "root");
//创建输出流,在HDFS端创建一个合并文件
FSDataOutputStream outputStream = fileSystem.create(new Path("/bigFile.xml"));
//获取本地文件系统
LocalFileSystem local = FileSystem.getLocal(new Configuration());
//通过本地文件系统获取文件列表,为一个集合
FileStatus[] fileStatuses = local.listStatus(new Path("/Volumes/赵壮备份/大数据离线课程资料/3.大数据离线第三天/上传小文件合并"));
//遍历FileStatus
for (FileStatus fileStatus : fileStatuses) {
FSDataInputStream inputStream = local.open(fileStatus.getPath());
IOUtils.copy(inputStream,outputStream);
IOUtils.closeQuietly(inputStream);
}
IOUtils.closeQuietly(outputStream);
local.close();
fileSystem.close();
}