欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页

HDFS Java api操作

程序员文章站 2024-03-23 08:01:21
...

新建一个maven工程

HDFS Java api操作

HDFS Java api操作

在pom.xml中添加相关依赖

<?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.lzc.hadoop</groupId>
  <artifactId>hadoop-api</artifactId>
  <version>1.0-SNAPSHOT</version>

  <name>hadoop-api</name>
  <!-- FIXME change it to the project's website -->
  <url>http://www.example.com</url>

  <properties>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    <maven.compiler.source>1.7</maven.compiler.source>
    <maven.compiler.target>1.7</maven.compiler.target>
    <hadoop.version>2.6.0-cdh5.7.0</hadoop.version>
  </properties>

    <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>${hadoop.version}</version>
    </dependency>

    <dependency>
      <groupId>junit</groupId>
      <artifactId>junit</artifactId>
      <version>4.10</version>
      <scope>test</scope>
    </dependency>
  </dependencies>

</project>

基本操作

package com.lzc.hadoop.hdfs;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.*;
import org.apache.hadoop.io.IOUtils;
import org.apache.hadoop.util.Progressable;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;

import java.io.*;
import java.net.URI;

/**
 * hadoop hdfs java api操作
 */
public class HDFSApp {

    public static final String HDFS_PATH = "hdfs://192.168.126.129:8020";

    FileSystem fileSystem = null;
    Configuration configuration = null;

    @Before
    public void setUp() throws Exception {
        System.out.println("HDFSApp.setUp");
        configuration = new Configuration();
        configuration.set("dfs.replication", "1"); // 设置hdfs副本,如果不设置,默认采用的是hadoop自己的副本系数
        fileSystem = FileSystem.get(new URI(HDFS_PATH), configuration, "root");
    }

    @After
    public void tearDown() {
        configuration = null;
        fileSystem = null;
        System.out.println("HDFSApp.tearDown");
    }

    /**
     * 创建hdfs目录
     */
    @Test
    public void mkdir() throws Exception {
        fileSystem.mkdirs(new Path("/hdfsapi/"));
    }

    /**
     *创建文件
     */
    @Test
    public void create() throws Exception {
        FSDataOutputStream outputStream =  fileSystem.create(new Path("/hdfsapi/lzc.txt"));
        outputStream.write("lzc hello".getBytes());
        outputStream.flush();
        outputStream.close();
    }

    /**
     *查看hdfs文件内容
     */
    @Test
    public void cat() throws Exception {
        FSDataInputStream inputStream = fileSystem.open(new Path("/hdfsapi/test.txt"));
        IOUtils.copyBytes(inputStream, System.out, 1024);
        inputStream.close();
    }

    /**
     * 重命名文件
     * @throws Exception
     */
    @Test
    public void rename() throws Exception {
        Path oldPath = new Path("/hdfsapi/lzc.txt");
        Path newPath = new Path("/hdfsapi/lizhencheng.txt");
        fileSystem.rename(oldPath, newPath);
    }

    /**
     *上传文件到hdfs
     * @throws Exception
     */
    @Test
    public void copyFromLocal() throws Exception {
        Path localPath = new Path("F:\\test.txt");
        Path hdfsPath = new Path("/hdfsapi/");
        fileSystem.copyFromLocalFile(localPath,hdfsPath);
    }

    /**
     *上传文件到hdfs
     * @throws Exception
     */
    @Test
    public void copyFromLocalWithProgress() throws Exception {
        InputStream in = new BufferedInputStream(new FileInputStream(new File("F:\\jdk-8u162-windows-x64.exe")));
        FSDataOutputStream output =  fileSystem.create(new Path("/hdfsapi/jdk.exe"), new Progressable() {
            @Override
            public void progress() {
                System.out.print("=>");
            }
        });
        IOUtils.copyBytes(in, output, 4096);
    }

    /**
     *下载hdfs文件
     * @throws Exception
     */
    @Test
    public void copyToLocalFile() throws Exception {
        Path localPath = new Path("F:\\hh.txt");
        Path hdfsPath = new Path("/hdfsapi/test.txt");
        fileSystem.copyToLocalFile(false, hdfsPath, localPath, true);
    }

    /**
     *查看hdfs某个目录下的所有文件
     * @throws Exception
     */
    @Test
    public void listFiles() throws Exception {
        FileStatus[] fileStatus = fileSystem.listStatus(new Path("/"));
        for (FileStatus f : fileStatus) {
            String isDir = f.isDirectory()? "文件夹":"文件";
            short replication = f.getReplication();
            long len = f.getLen();
            String path = f.getPath().toString();
            System.out.println(isDir + "\t" + replication + "\t" + len + "\t" + path);
        }
    }

    /**
     *查看hdfs某个目录下的所有文件
     * @throws Exception
     */
    @Test
    public void delete() throws Exception {
        fileSystem.delete(new Path("/hdfsapi/jdk.exe"), true);
    }


}

 

上一篇: java操作hdfs

下一篇: HDFS java API操作