HDFS java API操作

HDFS的javaAPI操作

     目标:掌握如何使用APIHDFS上的目录和数据进行增、删、改、查操作。

1.idea创建maven工程

2.修改pom.xml文件如下:

(需要下载jar包,时间可能稍长)

<?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</groupId>           <!-- 自己的组名 -->
    <artifactId>aa</artifactId>      <!-- 自己的项目名 -->
    <version>1.0-SNAPSHOT</version>

    <repositories>
        <repository>
            <id>cloudera</id>
            <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
        </repository>
    </repositories>
    <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>
        <dependency>
            <groupId>org.apache.zookeeper</groupId>
            <artifactId>zookeeper</artifactId>
            <version>3.4.9</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>

        </plugins>
    </build>


</project>

3.下载完成后编写java类     可一个一个尝试

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

import java.net.URI;

public class HDFSDemo {
    public static void main(String[] args) throws Exception {

        /*
        //创建文件夹
        Configuration configuration = new Configuration();
        FileSystem fs=FileSystem.get(new URI("hdfs://192.168.10.101:8020"),configuration);
        boolean b = fs.mkdirs(new Path("/003"));
        if (b){
            System.out.println("成功!");
        }else {
            System.out.println("失败!");
        }
        */

       /*
        //删除文件夹
        Configuration configuration = new Configuration();
        configuration.set("fs.defaultFS","hdfs://192.168.10.101:8020");
        FileSystem fs = FileSystem.newInstance(new URI("/"), configuration);
        boolean b = fs.delete(new Path("/003"), true);
        if (b){
            System.out.println("成功!");
        }else {
            System.out.println("失败!");
        }
        */

       /*
       //修改文件夹
        Configuration configuration = new Configuration();
        FileSystem fs= FileSystem.get(new URI("hdfs://192.168.10.101:8020"),configuration);
        boolean b = fs.rename(new Path("/002"),new Path("/003"));
        if (b){
            System.out.println("成功!");
        }else {
            System.out.println("失败!");
        }
        */

        /*
       //查看文件夹
        Configuration configuration = new Configuration();
        FileSystem fs= FileSystem.get(new URI("hdfs://192.168.10.101:8020"),configuration);
        FileStatus[] fi = fs.listStatus(new Path("/"));
        for (FileStatus f : fi) {
            System.out.println("path:"+f.getPath());
            System.out.println("name:"+f.getPath().getName());

        }
        */

       /*
        //上传数据
        Configuration configuration = new Configuration();
        FileSystem fs= FileSystem.get(new URI("hdfs://192.168.10.101:8020"),configuration);
        fs.copyFromLocalFile(new Path(""),new Path("/"));
        fs.close();
        */


        //下载数据
        Configuration configuration = new Configuration();
        FileSystem fs = FileSystem.get(new URI("hdfs://192.168.10.101:8020"), configuration);
        fs.copyToLocalFile(new Path(""), new Path("/"));
        fs.close();
    }
}

如果执行出现以下错误,也可以不用理会,不会影响程序的执行。配置hadoo环境变量之后重启开发工具就可以了

获取FileSystem的几种方式 

  1.  第一种:
    @Test
    public void getFileSystem() throws URISyntaxException, IOException {
       Configuration configuration = new Configuration();
        FileSystem fileSystem = FileSystem.get(new URI("hdfs://192.168.52.100:8020"), configuration);
        System.out.println(fileSystem.toString());
    }
    
  2.  第二种:
    @Test
    public void getFileSystem2() throws URISyntaxException, IOException {
        Configuration configuration = new Configuration();
        configuration.set("fs.defaultFS","hdfs://192.168.52.100:8020");
        FileSystem fileSystem = FileSystem.get(new URI("/"), configuration);
        System.out.println(fileSystem.toString());
    }
    

    3. 第三种:

    @Test
    public void getFileSystem3() throws URISyntaxException, IOException {
        Configuration configuration = new Configuration();
        FileSystem fileSystem = FileSystem.newInstance(new URI("hdfs://192.168.52.100:8020"), configuration);
        System.out.println(fileSystem.toString());
    }
    

     4.第四种:

    @Test
    public void getFileSystem4() throws  Exception{
        Configuration configuration = new Configuration();
        configuration.set("fs.defaultFS","hdfs://192.168.52.100:8020");
        FileSystem fileSystem = FileSystem.newInstance(configuration);
        System.out.println(fileSystem.toString());
    }
    

     递归遍历文件系统当中的所有文件

通过递归遍历hdfs文件系统

@Test
public void listFile() throws Exception{
    FileSystem fileSystem = FileSystem.get(new URI("hdfs://192.168.52.100:8020"), new Configuration());
    FileStatus[] fileStatuses = fileSystem.listStatus(new Path("/"));
    for (FileStatus fileStatus : fileStatuses) {
        if(fileStatus.isDirectory()){
            Path path = fileStatus.getPath();
            listAllFiles(fileSystem,path);
        }else{
            System.out.println("文件路径为"+fileStatus.getPath().toString());

        }
    }
}
public void listAllFiles(FileSystem fileSystem,Path path) throws  Exception{
    FileStatus[] fileStatuses = fileSystem.listStatus(path);
    for (FileStatus fileStatus : fileStatuses) {
        if(fileStatus.isDirectory()){
            listAllFiles(fileSystem,fileStatus.getPath());
        }else{
            Path path1 = fileStatus.getPath();
            System.out.println("文件路径为"+path1);
        }
    }
}

官方提供的API直接遍历

/**
 * 递归遍历官方提供的API版本
 * @throws Exception
 */
@Test
public void listMyFiles()throws Exception{
    //获取fileSystem类
    FileSystem fileSystem = FileSystem.get(new URI("hdfs://192.168.52.100:8020"), 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("/"), true);
    while (locatedFileStatusRemoteIterator.hasNext()){
        LocatedFileStatus next = locatedFileStatusRemoteIterator.next();
        System.out.println(next.getPath().toString());
    }
    fileSystem.close();
}

  • 2
    点赞
  • 12
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值