java api 读取hadoop中hdfs文件系统内的文件

hadoop与hdfs需要自己安装,确保文件存在于hdfs

只有一个main方法

//HdfsTest.java
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;

import java.io.IOException;

public class HdfsTest {

    //列出文件目录
    public static void ls(FileSystem fs, String path){
        FileStatus[] fileStatuses = new FileStatus[0];
        try {
            fileStatuses = fs.listStatus(new Path(path));
        } catch (IOException e) {
            e.printStackTrace();
        }
        for (FileStatus fileStatus : fileStatuses) {
            if (fileStatus.isDirectory()){
                System.out.println("dir:"+fileStatus.getPath());
            }else {
                System.out.println("file:"+fileStatus.getPath());
            }
        }
    }

    //创建目录
    public static void mkdir(FileSystem fs, String path){
        try {
            fs.mkdirs(new Path(path));
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    //写入文件
    public static void writeNewFile(FileSystem fs, String path){

        try {
            FSDataOutputStream hos=fs.create(new Path(path),true) ;
            hos.write("test\n".getBytes());
            hos.flush();
            hos.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static void readFile(FileSystem fs, String path){
        try {
            FSDataInputStream his = fs.open(new Path(path));
            byte[] buff = new byte[1024];
            int length = 0;
            while ((length = his.read(buff)) != -1) {
            System.out.println(new String(buff, 0, length));
        }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static void rm(FileSystem fs, String path){
        try {
            fs.delete(new Path(path),true);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }


    public static void main(String[] args) throws IOException {
        //当远程【写文件】报错没有权限时,设置hadoop的用户
        System.setProperty("HADOOP_USER_NAME","duoduo");
        //创建configuration对象
        Configuration conf = new Configuration();
        //配置在etc/hadoop/core-site.xml   fs.defaultFS
        conf.set("fs.defaultFS","hdfs://192.168.1.210:9000");
        //创建FileSystem对象
        //查看hdfs集群服务器/user/passwd.txt的内容
        FileSystem fs = FileSystem.get(conf);

//        ls(fs,"/");
//        writeNewFile(fs,"hdfs://192.168.1.210:9000/mytest.data"); //需要正确的hadoop用户权限
//        readFile(fs,"hdfs://192.168.1.210:9000/mytest.data");
//        mkdir(fs,"/ddd");
        rm(fs,"/ddd");
    }

}

//pom.xml
<?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.ddddd</groupId>
    <artifactId>hdfs</artifactId>
    <version>1.0</version>

    <properties>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
        <maven.compiler.target>1.8</maven.compiler.target>
        <maven.compiler.source>1.8</maven.compiler.source>
        <hadoop.version>2.7.1</hadoop.version>
    </properties>

    <repositories>
        <repository>
            <id>maven-ali</id>
            <url>http://maven.aliyun.com/nexus/content/groups/public//</url>
            <releases>
                <enabled>true</enabled>
            </releases>
            <snapshots>
                <enabled>true</enabled>
                <updatePolicy>always</updatePolicy>
                <checksumPolicy>fail</checksumPolicy>
            </snapshots>
        </repository>
    </repositories>

    <dependencies>
        <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>
    </dependencies>

</project>
  • 4
    点赞
  • 8
    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