Hbase基础操作Demo（Java版）

一、前置条件

• HBase服务：【快捷部署】023_HBase（2.3.6）
• 开发环境：Java（1.8）、Maven（3）、IDE（Idea 或 Eclipse）

二、相关代码

代码结构如上图中①和②

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.huawei</groupId>
    <artifactId>HbaseAPI</artifactId>
    <version>1.0-SNAPSHOT</version>

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

    <repositories>
        <repository>
            <id>huaweicloud2</id>
            <name>huaweicloud2</name>
            <url>https://mirrors.huaweicloud.com/repository/maven/</url>
        </repository>
        <repository>
            <id>huaweicloud1</id>
            <name>huaweicloud1</name>
            <url>https://repo.huaweicloud.com/repository/maven/huaweicloudsdk/</url>
        </repository>
    </repositories>

    <dependencies>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.8.3</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.8.3</version>
        </dependency>
        <!--hbase-->
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>1.4.13</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>1.4.13</version>
        </dependency>
    </dependencies>

    <build>
        <finalName>HbaseAPI</finalName>
        <plugins>
            <plugin>
                <artifactId>maven-assembly-plugin</artifactId>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                </configuration>
                <executions>
                    <execution>
                        <id>make-assembly</id>
                        <phase>package</phase>
                        <goals>
                            <goal>assembly</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

Config4HBaseDemo（公共配置类）

package com.toc.demo.hbase;
/**
 * 公共配置类
 * @author cxy@toc
 * @date  2024-05-07
 *
 */

public class Config4HBaseDemo {
    public static String zkQuorum = "127.0.0.1";

    public static String getZkQuorum(String[] args) {
        if (args!=null && args.length > 0) {
            System.out.println("接收参数：" + args[0]);
            zkQuorum = args[0];
        }
        return zkQuorum;
    }
}

CreateTable（创建Hbase表）

package com.toc.demo.hbase;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;

import java.io.IOException;

/**
 * 创建Hbase表
 * @author cxy@toc
 * @date  2024-05-07
 *
 */

public class CreateTable {

    public static void main(String[] args) throws IOException {

        //链接hbase
        Configuration conf = HBaseConfiguration.create();
        //这里的zookeeper地址要改为自己集群的zookeeper地址
        conf.set("hbase.zookeeper.quorum",Config4HBaseDemo.getZkQuorum(args));

        conf.set("hbase.zookeeper.property.clientPort", "2181");

        Connection connection = ConnectionFactory.createConnection(conf);
        Admin admin = connection.getAdmin();

        TableName tableName = TableName.valueOf("users");

        if (!admin.tableExists(tableName)){
            //创建表描述器
            HTableDescriptor htd = new HTableDescriptor(tableName);
            htd.addFamily(new HColumnDescriptor("f"));
            admin.createTable(htd);
            System.out.println(tableName+"表创建成功");
        }else {
            System.out.println(tableName+"表已经存在");
        }
    }
}

DeleteData（删除数据）

package com.toc.demo.hbase;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;

import java.io.IOException;

/**
 * 删除数据
 * @author cxy@toc
 * @date  2024-05-07
 *
 */

public class DeleteData {
    public static void main(String[] args) throws IOException {
        //链接hbase
        Configuration conf = HBaseConfiguration.create();
        //这里的zookeeper地址要改为自己集群的zookeeper地址
        conf.set("hbase.zookeeper.quorum",Config4HBaseDemo.getZkQuorum(args));
        conf.set("hbase.zookeeper.property.clientPort", "2181");
        Connection connection = ConnectionFactory.createConnection(conf);

        Table hTable = connection.getTable(TableName.valueOf("users"));

        Delete delete = new Delete(Bytes.toBytes("row5"));
        delete.addColumn(Bytes.toBytes("f"),Bytes.toBytes("id"));
        //直接删除family,将所有row5的信息全部删除
        delete.addFamily(Bytes.toBytes("f"));
        hTable.delete(delete);
        System.out.println("删除成功");
    }
}

DeleteTable（删除表）

package com.toc.demo.hbase;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;

import java.io.IOException;

/**
 * 删除表
 * @author cxy@toc
 * @date  2024-05-07
 *
 */

public class DeleteTable {
    public static void main(String[] args) throws IOException {

        //链接hbase
        Configuration conf = HBaseConfiguration.create();
        //这里的zookeeper地址要改为自己集群的zookeeper地址
        conf.set("hbase.zookeeper.quorum",Config4HBaseDemo.getZkQuorum(args));
        conf.set("hbase.zookeeper.property.clientPort", "2181");

        Connection connection = ConnectionFactory.createConnection(conf);
        Admin hBaseAdmin = connection.getAdmin();

        TableName tableName = TableName.valueOf("users");

        if (hBaseAdmin.tableExists(tableName)) {
            //判断表的状态
            if(hBaseAdmin.isTableAvailable(tableName)) {
                hBaseAdmin.disableTable(tableName);
            }
            hBaseAdmin.deleteTable(tableName);
            System.out.println("删除表"+tableName+"成功");
        }else {
            System.out.println(tableName+"表不存在");
        }
    }
}

DescTable（查看表结构）

package com.toc.demo.hbase;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;

import java.io.IOException;

/**
 * 查看表结构
 * @author cxy@toc
 * @date  2024-05-07
 *
 */
public class DescTable {
    public static void main(String[] args) throws IOException {

        //链接hbase
        Configuration conf = HBaseConfiguration.create();
        //这里的zookeeper地址要改为自己集群的zookeeper地址
        conf.set("hbase.zookeeper.quorum",Config4HBaseDemo.getZkQuorum(args));
        conf.set("hbase.zookeeper.property.clientPort", "2181");

        Connection connection = ConnectionFactory.createConnection(conf);
        Admin hBaseAdmin = connection.getAdmin();

        TableName tableName = TableName.valueOf("users");
        if(hBaseAdmin.tableExists(tableName)) {
            HTableDescriptor htd = hBaseAdmin.getTableDescriptor(tableName);
            System.out.println("查看"+tableName+"表结构");
            System.out.println(htd);
        }else {
            System.out.println(tableName+"表不存在");
        }
    }
}

GetData（获取数据）

package com.toc.demo.hbase;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;

import java.io.IOException;

/**
 * 获取数据
 * @author cxy@toc
 * @date  2024-05-07
 *
 */

public class GetData {
    public static void main(String[] args) throws IOException {
        //链接hbase
        Configuration conf = HBaseConfiguration.create();
        //这里的zookeeper地址要改为自己集群的zookeeper地址
        conf.set("hbase.zookeeper.quorum",Config4HBaseDemo.getZkQuorum(args));
        conf.set("hbase.zookeeper.property.clientPort", "2181");
        Connection connection = ConnectionFactory.createConnection(conf);

        Table hTable = connection.getTable(TableName.valueOf("users"));

        Get get = new Get(Bytes.toBytes("row1"));
        Result result = hTable.get(get);
        byte[] family = Bytes.toBytes("f");
        byte[] buf = result.getValue(family,Bytes.toBytes("id"));
        System.out.println("id="+Bytes.toString(buf));

        buf = result.getValue(family,Bytes.toBytes("age"));
        System.out.println("age="+Bytes.toInt(buf));

        buf = result.getValue(family,Bytes.toBytes("name"));
        System.out.println("name="+Bytes.toString(buf));

        buf = result.getRow();
        System.out.println("rowkey="+Bytes.toString(buf));
    }
}

PutData（插入数据）

package com.toc.demo.hbase;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

/**
 * 插入数据
 * @author cxy@toc
 * @date  2024-05-07
 *
 */

public class PutData {
    public static void main(String[] args) throws IOException {
        //链接hbase
        Configuration conf = HBaseConfiguration.create();
        //这里的zookeeper地址要改为自己集群的zookeeper地址
        conf.set("hbase.zookeeper.quorum",Config4HBaseDemo.getZkQuorum(args));
        conf.set("hbase.zookeeper.property.clientPort", "2181");

        Connection connection = ConnectionFactory.createConnection(conf);

        Table hTable = connection.getTable(TableName.valueOf("users"));

        //插入一条
        Put put= new Put(Bytes.toBytes("row1"));
        put.addColumn(Bytes.toBytes("f"),Bytes.toBytes("id"),Bytes.toBytes("1"));
        put.addColumn(Bytes.toBytes("f"),Bytes.toBytes("name"),Bytes.toBytes("张三"));
        put.addColumn(Bytes.toBytes("f"),Bytes.toBytes("age"),Bytes.toBytes(27));
        put.addColumn(Bytes.toBytes("f"),Bytes.toBytes("phone"),Bytes.toBytes("18600000000"));
        put.addColumn(Bytes.toBytes("f"),Bytes.toBytes("emil"),Bytes.toBytes("123654@163.com"));
        hTable.put(put);
        //插入多个
        Put put1= new Put(Bytes.toBytes("row2"));
        put1.addColumn(Bytes.toBytes("f"),Bytes.toBytes("id"),Bytes.toBytes("2"));
        put1.addColumn(Bytes.toBytes("f"),Bytes.toBytes("name"),Bytes.toBytes("李四"));

        Put put2= new Put(Bytes.toBytes("row3"));
        put2.addColumn(Bytes.toBytes("f"),Bytes.toBytes("id"),Bytes.toBytes("3"));
        put2.addColumn(Bytes.toBytes("f"),Bytes.toBytes("name"),Bytes.toBytes("王五"));

        Put put3= new Put(Bytes.toBytes("row4"));
        put3.addColumn(Bytes.toBytes("f"),Bytes.toBytes("id"),Bytes.toBytes("4"));
        put3.addColumn(Bytes.toBytes("f"),Bytes.toBytes("name"),Bytes.toBytes("赵六"));

        List<Put> list = new ArrayList<Put>();
        list.add(put1);
        list.add(put2);
        list.add(put3);
        hTable.put(list);

        //检测put,条件成功就插入,要求RowKey是一样的
        Put put4 = new Put(Bytes.toBytes("row5"));
        put4.addColumn(Bytes.toBytes("f"),Bytes.toBytes("id"),Bytes.toBytes("5"));
        hTable.checkAndPut(Bytes.toBytes("row5"),Bytes.toBytes("f"),Bytes.toBytes("id"),null,put4);

        System.out.println("插入成功");
    }
}

ScanData（扫描遍历数据）

package com.toc.demo.hbase;


import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.FilterList;
import org.apache.hadoop.hbase.filter.MultipleColumnPrefixFilter;
import org.apache.hadoop.hbase.util.Bytes;

import java.io.IOException;
import java.util.Iterator;
import java.util.Map;
import java.util.NavigableMap;

/**
 * 扫描遍历数据
 * @author cxy@toc
 * @date  2024-05-07
 *
 */

public class ScanData {
    public static void main(String[] args) throws IOException {
        //链接hbase
        Configuration conf = HBaseConfiguration.create();
        //这里的zookeeper地址要改为自己集群的zookeeper地址
        conf.set("hbase.zookeeper.quorum",Config4HBaseDemo.getZkQuorum(args));
        conf.set("hbase.zookeeper.property.clientPort", "2181");
        Connection connection = ConnectionFactory.createConnection(conf);

        Table hTable = connection.getTable(TableName.valueOf("users"));


        Scan scan = new Scan();
        //增加起始rowkey
        scan.withStartRow(Bytes.toBytes("row1"));
        scan.withStopRow(Bytes.toBytes("row5"));

        //增加过滤filter
        FilterList list = new FilterList(FilterList.Operator.MUST_PASS_ALL);
        byte[][] prefixes = new byte[2][];
        prefixes[0] = Bytes.toBytes("id");
        prefixes[1] = Bytes.toBytes("name");
        MultipleColumnPrefixFilter mcpf = new MultipleColumnPrefixFilter(prefixes);
        list.addFilter(mcpf);
        scan.setFilter(list);

        ResultScanner rs = hTable.getScanner(scan);
        Iterator<Result> iter = rs.iterator();
        while (iter.hasNext()){
            Result result = iter.next();
            printResult(result);
        }
    }

    /*
    打印Result对象
     */
    static void printResult(Result result){
        System.out.println("***********"+Bytes.toString(result.getRow()));
        NavigableMap<byte[],NavigableMap<byte[], NavigableMap<Long,byte[]>>> map = result.getMap();
        for(Map.Entry<byte[],NavigableMap<byte[],NavigableMap<Long,byte[]>>> entry: map.entrySet()){
            String family = Bytes.toString(entry.getKey());
            for(Map.Entry<byte[],NavigableMap<Long,byte[]>> columnEntry :entry.getValue().entrySet()){
                String column = Bytes.toString(columnEntry.getKey());
                String value = "";
                if("age".equals(column)){
                    value=""+Bytes.toInt(columnEntry.getValue().firstEntry().getValue());
                }else {
                    value=""+Bytes.toString(columnEntry.getValue().firstEntry().getValue());
                }
                System.out.println(family+":"+column+":"+value);
            }
        }
    }
}

三、如何使用

1. Maven打包
   Eclipse：项目上右键 Run As -> Maven Install进行打包
   Idea：Maven工具栏 -> 生命周期 -> install
   打包好的jar如上图中的③

2. 上传jar到Hadoop(yarn)服务器
   scp 你的target/HbaseAPI-jar-with-dependencies.jar root@xxx.xxx.xxx.xxx:/root

3. 登录到服务器，并查看上传的文件

ssh root@xxx.xxx.xxx.xxx
ls

4. 执行命令，查看效果

# 将{ZK的内网IP}改为zookeeper的ip，如过就是本机可以不写，默认是127.0.0.1
yarn jar HbaseAPI-jar-with-dependencies.jar com.toc.demo.hbase.CreateTable {ZK的内网IP}
yarn jar HbaseAPI-jar-with-dependencies.jar com.toc.demo.hbase.DescTable {ZK的内网IP}
yarn jar HbaseAPI-jar-with-dependencies.jar com.toc.demo.hbase.PutData {ZK的内网IP}
yarn jar HbaseAPI-jar-with-dependencies.jar com.toc.demo.hbase.GetData {ZK的内网IP}
yarn jar HbaseAPI-jar-with-dependencies.jar com.toc.demo.hbase.ScanData {ZK的内网IP}
yarn jar HbaseAPI-jar-with-dependencies.jar com.toc.demo.hbase.DeleteData {ZK的内网IP}
yarn jar HbaseAPI-jar-with-dependencies.jar com.toc.demo.hbase.DeleteTable {ZK的内网IP}

更多详细操作可参见华为云沙箱实验：https://lab.huaweicloud.com/experiment-detail_1779

往期精彩内容推荐

云原生：10分钟了解一下Kubernetes架构
云原生：5分钟了解一下Kubernetes是什么
「快速部署」第二期清单
「快速部署」第一期清单