hbase通过idea操作api

最新推荐文章于 2024-09-26 20:09:57 发布

方兵兵

最新推荐文章于 2024-09-26 20:09:57 发布

阅读量7.2k

点赞数 11

分类专栏：大数据大数据开发入门

本文链接：https://blog.csdn.net/u010800708/article/details/86742516

版权

大数据同时被 2 个专栏收录

36 篇文章 0 订阅

订阅专栏

大数据开发入门

21 篇文章 0 订阅

订阅专栏

1）安装Intellij idea
这款开发工具收费，要注册
http://idea.lanyus.com/
这里找注册码

安装完成后输入注册码，然后需要在本地hosts文件修改
C:\Windows\System32\drivers\etc\hosts
加上这个
0.0.0.0 account.jetbrains.com

2）Intellij idea新建Maven工程

在pom.xml中添加hbase依赖

<dependencies>
    <dependency>
        <groupId>org.apache.hbase</groupId>
        <artifactId>hbase-server</artifactId>
        <version>1.3.1</version>
    </dependency>
    <dependency>
        <groupId>org.apache.hbase</groupId>
        <artifactId>hbase-client</artifactId>
        <version>1.3.1</version>
    </dependency>
</dependencies>

在src/main/resources文件夹下添加三个配置文件
hdfs-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<!--配置元数据存储位子  -->
<property>
	<name>dfs.namenode.name.dir</name>
	<value>/root/hd/dfs/name</value>
</property>
<!-- 配置数据存储的位置-->
<property>
	<name>dfs.datanode.data.dir</name>
	<value>/root/hd/dfs/data</value>
</property>	
<!--备用namenode的节点配置 -->
 <property>
            <name>dfs.namenode.secondary.http-address</name>
	<value>bigdata122:50070</value>
</property>
<!-- block副本的数量配置-->
<property>
            <name>dfs.replication</name>
            <value>3</value>
</property>
	<!-- block大小配置-->
    <property>
            <name>dfs.blocksize</name>
            <value>134217728</value>
    </property>        
</configuration>

core-site.xml

<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
<property>
	<name>fs.defaultFS</name>	
	<value>hdfs://bigdata121:9000</value>
	</property>
</configuration>

hbase-site.xml

<configuration>
<!-- 设置namenode所在位置 通过rootdir设置 也就是设置hdfs中存放的路径 -->
	<property>
		<name>hbase.rootdir</name>
		<value>hdfs://bigdata121:9000/hbase</value>
	</property>
	
	<!-- 是否开启集群 -->
	<property>
		<name>hbase.cluster.distributed</name>
		<value>true</value>
	</property>
	
	<!-- 0.98 后的新变动，之前版本没有.port,默认端口为 60000 -->
	<property>
		<name>hbase.master.port</name>
		<value>16000</value>
	</property>
	
	<!-- zookeeper集群的位置 -->
	<property>
		<name>hbase.zookeeper.quorum</name>
		<value>bigdata121:2181,bigdata122:2181,bigdata123:2181,bigdata124:2181,bigdata125:2181</value>
	</property>
	
	<!-- hbase的元数据信息存储在zookeeper的位置 -->
	<property>
		<name>hbase.zookeeper.property.dataDir</name>
		<value>/root/hd/zookeeper-3.4.10/zkData</value>
	</property>
</configuration>

3）在C:\Windows\System32\drivers\etc\hosts文件中加上hdfs集群的ip

192.168.252.121 bigdata121
192.168.252.122 bigdata122
192.168.252.123 bigdata123
192.168.252.124 bigdata124
192.168.252.125 bigdata125

这样idea才能找到集群

Hbase擅长存储数据，并不擅长计算分析数据
可以结合其他组件（mapreduce/spark）

Hbase官方提供了hbase-api

Hbase-MR操作

官方Hbase-Mapreduce

基本api命名操作如下：

package com.itstaredu.hbase;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.*;
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;


public class HbaseTest {
    //获取配置信息
   public static Configuration conf;

    static{
       conf = HBaseConfiguration.create();
    }

    //1.判断一张表是否存在
    public static boolean isExist(String tableName){
       //对表操作需要使用HbaseAdmin
        try {
            Connection connection = ConnectionFactory.createConnection(conf);
            //管理表
            HBaseAdmin admin = (HBaseAdmin) connection.getAdmin();

            return admin.tableExists(TableName.valueOf(tableName));
        } catch (IOException e) {
            e.printStackTrace();
        }
        return false;
    }

    //2.在hbase创建表
    public static void createTable(String tableName,String... columnfamily){
        try {
            //对表操作需要使用HbaseAdmin
            Connection connection = ConnectionFactory.createConnection(conf);
            //管理表
            HBaseAdmin admin = (HBaseAdmin) connection.getAdmin();

            //1.表如果存在，请输入其他表名
            if(isExist(tableName)){
                System.out.println("表存在，请输入其他表名");
            }else{
                //2.注意:创建表的话，需要创建一个描述器
                HTableDescriptor htd = new HTableDescriptor(TableName.valueOf(tableName));

                //3.创建列族
                for(String cf:columnfamily){
                    htd.addFamily(new HColumnDescriptor(cf));
                }

                //4.创建表
                admin.createTable(htd);
                System.out.println("表已经创建成功！");

            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    //3.删除hbase的表
    public static void deleteTable(String tableName) {
        try {
            //对表操作需要使用HbaseAdmin
            Connection connection = ConnectionFactory.createConnection(conf);
            //管理表
            HBaseAdmin admin = (HBaseAdmin) connection.getAdmin();

            //1.表如果存在，请输入其他表名
            if (!isExist(tableName)) {
                System.out.println("表不存在");
            } else {
                //2.如果表存在，删除
                admin.disableTable(TableName.valueOf(tableName));
                admin.deleteTable(TableName.valueOf(tableName));
                System.out.println("表删除了");
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    //4.添加数据put 'user','rowkey','info:name','tony'
    public static void addRow(String tableName,String rowkey,String cf,String column,String value){
        try {
            //对表操作需要使用HbaseAdmin
            Connection connection = ConnectionFactory.createConnection(conf);
            Table t = connection.getTable(TableName.valueOf(tableName));
            //1.表如果存在，请输入其他表名
            if (!isExist(tableName)) {
                System.out.println("表不存在");
            } else {
                //2.用put方式加入数据
                Put p = new Put(Bytes.toBytes(rowkey));
                //3.加入数据
                p.addColumn(Bytes.toBytes(cf),Bytes.toBytes(column),Bytes.toBytes(value));
                t.put(p);

            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    //5.删除表中一行数据
    public static void deleteRow(String tableName,String rowkey,String cf ){
        try {
            //对表操作需要使用HbaseAdmin
            Connection connection = ConnectionFactory.createConnection(conf);
            Table t = connection.getTable(TableName.valueOf(tableName));
            //1.表如果存在，请输入其他表名
            if (!isExist(tableName)) {
                System.out.println("表不存在");
            } else {
                //1.根据rowkey删除数据
                Delete delete = new Delete(Bytes.toBytes(rowkey));
                //2.删除
                t.delete(delete);
                System.out.println("删除成功");
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    //6.删除多行数据
    public static void deleteAll(String tableName,String... rowkeys){
        try {
            //对表操作需要使用HbaseAdmin
            Connection connection = ConnectionFactory.createConnection(conf);
            Table t = connection.getTable(TableName.valueOf(tableName));
            //1.表如果存在，请输入其他表名
            if (!isExist(tableName)) {
                System.out.println("表不存在");
            } else {
                //1.把delete封装到集合
               List<Delete> list = new ArrayList<Delete>();
               //2.遍历
                for (String row:rowkeys){
                    Delete d = new Delete(Bytes.toBytes(row));
                    list.add(d);
                }
                t.delete(list);
                System.out.println("删除成功");
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    //7.扫描表数据 scan全表扫描
    public static void scanAll(String tableName){
        try {
            //对表操作需要使用HbaseAdmin
            Connection connection = ConnectionFactory.createConnection(conf);
            Table t = connection.getTable(TableName.valueOf(tableName));

            //1.实例scan
            Scan s = new Scan();
            //2.拿到Scanner对象
            ResultScanner rs = t.getScanner(s);

            //3.遍历
            for (Result r:rs){
                Cell[] cells = r.rawCells();
                //遍历具体数据
                for (Cell c : cells){
                    System.out.print("行键为："+Bytes.toString(CellUtil.cloneRow(c))+"  ");
                    System.out.print("列族为："+Bytes.toString(CellUtil.cloneFamily(c))+"  ");
                    System.out.print("列名为："+Bytes.toString(CellUtil.cloneQualifier(c))+"  ");
                    System.out.println("值为："+Bytes.toString(CellUtil.cloneValue(c)));
                }
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static void getRow(String tableName,String rowkey) throws IOException {
        Connection connection = ConnectionFactory.createConnection(conf);
        //拿到表对象
        Table t = connection.getTable(TableName.valueOf(tableName));

        //1.扫描指定数据需要实例对象Get
        Get get = new Get(Bytes.toBytes(rowkey));
        //2.可加过滤条件
        get.addFamily(Bytes.toBytes("info1"));
        Result rs = t.get(get);
        //3.遍历
        Cell[] cells = rs.rawCells();
        for (Cell c : cells){
            System.out.print("行键为："+Bytes.toString(CellUtil.cloneRow(c))+"  ");
            System.out.print("列族为："+Bytes.toString(CellUtil.cloneFamily(c))+"  ");
            System.out.print("列名："+Bytes.toString(CellUtil.cloneQualifier(c))+"  ");
            System.out.println("值为："+Bytes.toString(CellUtil.cloneRow(c))+"  ");
        }
    }

    public static void main(String[] args) throws IOException {
       // System.out.println(isExist("emp"));
        //createTable("yangmi","info");
        //deleteTable("tony");
        //addRow("yangmi","101","info","age","20");
        //deleteRow("yangmi","101","info");
        //deleteAll("emp","1001","1002");
        //scanAll("yangmi");
        getRow("yangmi","1001");
    }
}