利用Java连接Hadoop进行编程

目录

• 实验环境
• 实验内容
• 测试Java远程连接hadoop

实验环境

• hadoop版本：3.3.2
• jdk版本：1.8
• hadoop安装系统：ubuntu18.04
• 编程环境：IDEA
• 编程主机：windows

实验内容

测试Java远程连接hadoop

创建maven工程，引入以下依赖：

<dependency>
                <groupId>org.testng</groupId>
                <artifactId>testng</artifactId>
                <version>RELEASE</version>
                <scope>compile</scope>
            </dependency>
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-common</artifactId>
            </dependency>
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-hdfs</artifactId>
                <version>3.3.2</version>
            </dependency>
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-common</artifactId>
                <version>3.3.2</version>
            </dependency>
            <dependency>
                <groupId>org.apache.hadoop</groupId>
                <artifactId>hadoop-core</artifactId>
                <version>1.2.1</version>
            </dependency>

虚拟机的/etc/hosts配置

hdfs-site.xml配置

<configuration>
        <property>
                <name>dfs.replication</name>
                <value>1</value>
        </property>
        <property>
                <name>dfs.namenode.name.dir</name>
                <value>file:/root/rDesk/hadoop-3.3.2/tmp/dfs/name</value>
        </property>
        <property>
                <name>dfs.datanode.http.address</name>
                <value>VM-12-11-ubuntu:50010</value>
        </property>
        <property>
                <name>dfs.client.use.datanode.hostname</name>
                <value>true</value>
        </property>
        <property>
                <name>dfs.datanode.data.dir</name>
                <value>file:/root/rDesk/hadoop-3.3.2/tmp/dfs/data</value>
        </property>
</configuration>

core-site.xml配置

<configuration>
  <property>
          <name>hadoop.tmp.dir</name>
          <value>file:/root/rDesk/hadoop-3.3.2/tmp</value>
          <description>Abase for other temporary directories.</description>
  </property>
  <property>
          <name>fs.defaultFS</name>
          <value>hdfs://VM-12-11-ubuntu:9000</value>
  </property>
</configuration>

启动hadoop

sbin/start-dfs.sh

主机的hosts（C:\Windows\System32\drivers\etc）文件配置

尝试连接到虚拟机的hadoop并读取文件内容，这里我读取hdfs下的/root/iinput文件内容

Java代码：

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hdfs.DistributedFileSystem;
public class TestConnectHadoop {
    public static void main(String[] args) throws Exception {

        String hostname = "VM-12-11-ubuntu";
        String HDFS_PATH = "hdfs://" + hostname + ":9000";
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", HDFS_PATH);
        conf.set("fs.hdfs.impl", DistributedFileSystem.class.getName());
        conf.set("dfs.client.use.datanode.hostname", "true");

        FileSystem fs = FileSystem.get(conf);
        FileStatus[] fileStatuses = fs.listStatus(new Path("/"));
        for (FileStatus fileStatus : fileStatuses) {
            System.out.println(fileStatus.toString());
        }
        FileStatus fileStatus = fs.getFileStatus(new Path("/root/iinput"));
        System.out.println(fileStatus.getOwner());
        System.out.println(fileStatus.getGroup());

        System.out.println(fileStatus.getPath());
        FSDataInputStream open = fs.open(fileStatus.getPath());
        byte[] buf = new byte[1024];
        int n = -1;
        StringBuilder sb = new StringBuilder();
        while ((n = open.read(buf)) > 0) {
            sb.append(new String(buf, 0, n));
        }
        System.out.println(sb);
    }
}

运行结果：

编程实现一个类“MyFSDataInputStream”，该类继承“org.apache.hadoop.fs.FSDataInputStream",要求如下： ①实现按行读取HDFS中指定文件的方法”readLine（）“，如果读到文件末尾，则返回为空，否则返回文件一行的文本

思路：emmm我的思路比较简单，只适用于该要求，仅作参考。
将所有的数据读取出来存储起来，然后根据换行符进行拆分，将拆分的字符串数组存储起来，用于readline返回

Java代码

import org.apache.hadoop.fs.FSDataInputStream;
import java.io.IOException;
import java.io.InputStream;
public class MyFSDataInputStream extends FSDataInputStream {
    private String data = null;
    private String[] lines = null;
    private int count = 0;
    private FSDataInputStream in;
    public MyFSDataInputStream(InputStream in) throws IOException {
        super(in);
        this.in = (FSDataInputStream) in;
        init();
    }
    private void init() throws IOException {
        byte[] buf = new byte[1024];
        int n = -1;
        StringBuilder sb = new StringBuilder();
        while ((n = this.in.read(buf)) > 0) {
            sb.append(new String(buf, 0, n));
        }
        data = sb.toString();
        lines = data.split("\n");
    }
    /**
     * 实现按行读取HDFS中指定文件的方法”readLine（）“，如果读到文件末尾，则返回为空，否则返回文件一行的文本
     */
    public String read_line() {
        return count < lines.length ? lines[count++] : null;
    }

}

测试类：

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hdfs.DistributedFileSystem;
public class TestConnectHadoop {
    public static void main(String[] args) throws Exception {

        String hostname = "VM-12-11-ubuntu";
        String HDFS_PATH = "hdfs://" + hostname + ":9000";
        Configuration conf = new Configuration();
        conf.set("fs.defaultFS", HDFS_PATH);
        conf.set("fs.hdfs.impl", DistributedFileSystem.class.getName());
        conf.set("dfs.client.use.datanode.hostname", "true");
        FileSystem fs = FileSystem.get(conf);
        FileStatus fileStatus = fs.getFileStatus(new Path("/root/iinput"));
        System.out.println(fileStatus.getOwner());
        System.out.println(fileStatus.getGroup());
        System.out.println(fileStatus.getPath());
        FSDataInputStream open = fs.open(fileStatus.getPath());
        MyFSDataInputStream myFSDataInputStream = new MyFSDataInputStream(open);
        String line = null;
        int count = 0;
        while ((line = myFSDataInputStream.read_line()) != null ) {
            System.out.printf("line %d is: %s\n", count++, line);
        }
        System.out.println("end");

    }
}

运行结果：

②实现缓存功能，即利用”MyFSDataInputStream“读取若干字节数据时，首先查找缓存，如果缓存中有所需要数据，则直接由缓存提供，否则从HDFS中读取数据

import org.apache.hadoop.fs.FSDataInputStream;
import java.io.BufferedInputStream;
import java.io.IOException;
import java.io.InputStream;
public class MyFSDataInputStream extends FSDataInputStream {
    private BufferedInputStream buffer;
    private String[] lines = null;
    private int count = 0;
    private FSDataInputStream in;
    public MyFSDataInputStream(InputStream in) throws IOException {
        super(in);
        this.in = (FSDataInputStream) in;
        init();
    }
    private void init() throws IOException {
        byte[] buf = new byte[1024];
        int n = -1;
        StringBuilder sb = new StringBuilder();
        while ((n = this.in.read(buf)) > 0) {
            sb.append(new String(buf, 0, n));
        }
        //缓存数据读取
        buffer = new BufferedInputStream(this.in);
        lines = sb.toString().split("\n");
    }
    /**
     * 实现按行读取HDFS中指定文件的方法”readLine（）“，如果读到文件末尾，则返回为空，否则返回文件一行的文本
     */
    public String read_line() {
        return count < lines.length ? lines[count++] : null;
    }
    @Override
    public int read() throws IOException {
        return this.buffer.read();
    }
    public int readWithBuf(byte[] buf, int offset, int len) throws IOException {
        return this.buffer.read(buf, offset, len);
    }
    public int readWithBuf(byte[] buf) throws IOException {
        return this.buffer.read(buf);
    }
}

到此这篇关于利用Java连接Hadoop进行编程的文章就介绍到这了,更多相关Java连接Hadoop内容请搜索我们以前的文章或继续浏览下面的相关文章希望大家以后多多支持我们！