[大数据]HBase通过Java利用rowkey简单查询数据

注意事项：操作前要确保HBase已经正常运行而Hbase强依赖于HDFS以及zookeeper，所以在操作之前一定要保证Hbase、Hadoop和zookeeper正常启动。

IDEA：IntelliJ IDEA 2021.1 x64

?

第一步：创建maven工程，导入jar包

新建maven工程

?

在pom.xml文件下写入

<?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>org.example</groupId>
    <artifactId>Hbase</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>16</maven.compiler.source>
        <maven.compiler.target>16</maven.compiler.target>
    </properties>
    <dependencies>
        <!-- https://mvnrepository.com/artifact/org.apache.hbase/hbase-client -->
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>2.0.0</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hbase/hbase-server -->
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>2.0.0</version>
        </dependency>

        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.12</version>
            <scope>test</scope>
        </dependency>
        <dependency>
            <groupId>org.testng</groupId>
            <artifactId>testng</artifactId>
            <version>6.14.3</version>
            <scope>test</scope>
        </dependency>
    </dependencies>

    <build>
        <plugins>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-compiler-plugin</artifactId>
                <version>3.0</version>
                <configuration>
                    <source>1.8</source>
                    <target>1.8</target>
                    <encoding>UTF-8</encoding>
                    <!--    <verbal>true</verbal>-->
                </configuration>
            </plugin>
        </plugins>
    </build>
</project>

等待jar包下载完成

第二步：开发javaAPI操作HBase表数据

?在src下的test下的Java下新建软件包

?在软件包下新建Java类

?在public class HBaseOperate下

public class HBaseOperate{
        

    }

?通过管理员对象创建一张HBase表myuser有两个列族f1 f2

    //创建一张HBase表myuser有两个列族f1 f2
    @Test
    public void createTable() throws IOException {
        //连接HBase集群
        Configuration configuration = HBaseConfiguration.create();
        //指定hbase的zk连接地址
        configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
        Connection connection = ConnectionFactory.createConnection(configuration);
        //获取管理员对象
        Admin admin =connection.getAdmin();
        //通过管理员对象创建表
        HTableDescriptor hTableDescriptor = new HTableDescriptor(TableName.valueOf("myuser"));
        //给表添加列族 f1 f2
        HColumnDescriptor f1 = new HColumnDescriptor("f1");
        HColumnDescriptor f2 = new HColumnDescriptor("f2");
        //将两个列族设置到HTableDescriptor里面去
        hTableDescriptor.addFamily(f1);
        hTableDescriptor.addFamily(f2);
        //创建表
        admin.createTable(hTableDescriptor);
        //关闭管理员对象
        admin.close();
        connection.close();
    }

?在shell终端中用list查看

?myuser表已经创建好

通过管理员对象向myuser表中添加rowkey为0001的数据

/*
    * 向表中添加数据*/
    @Test
    public void addDate() throws IOException {
        //获取连接
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");

        Connection connection = ConnectionFactory.createConnection(configuration);
        //获取表对象
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        //创建put对象，并指定rowkey
        Put put = new Put("0001".getBytes());
        //数据内容
        put.addColumn("f1".getBytes(),"id".getBytes(), Bytes.toBytes(1));//1是整型
        put.addColumn("f1".getBytes(),"name".getBytes(),Bytes.toBytes("张三"));//“张三”是字符串
        put.addColumn("f1".getBytes(),"age".getBytes(),Bytes.toBytes(18));
        put.addColumn("f2".getBytes(),"address".getBytes(),Bytes.toBytes("地球村"));
        put.addColumn("f2".getBytes(),"phone".getBytes(),Bytes.toBytes("10086"));
        //插入数据
        myuser.put(put);
        //关闭表
        myuser.close();
    }

在shell终端中通过

 get 'myuser', '0001'

查看myuser表中rowkey为0001的值

向myuser表中插入rowkey从0002到0007列族有f1和f2

/*
    * 插入大量数据*/
    @Test
    public void insertBatchData() throws IOException {

        //获取连接
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum", "node01:2181,node02:2181");
        Connection connection = ConnectionFactory.createConnection(configuration);
        //获取表
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        //创建put对象，并指定rowkey
        Put put = new Put("0002".getBytes());
        put.addColumn("f1".getBytes(),"id".getBytes(),Bytes.toBytes(1));
        put.addColumn("f1".getBytes(),"name".getBytes(),Bytes.toBytes("曹操"));
        put.addColumn("f1".getBytes(),"age".getBytes(),Bytes.toBytes(30));
        put.addColumn("f2".getBytes(),"sex".getBytes(),Bytes.toBytes("1"));
        put.addColumn("f2".getBytes(),"address".getBytes(),Bytes.toBytes("沛国谯县"));
        put.addColumn("f2".getBytes(),"phone".getBytes(),Bytes.toBytes("16888888888"));
        put.addColumn("f2".getBytes(),"say".getBytes(),Bytes.toBytes("helloworld"));

        Put put2 = new Put("0003".getBytes());
        put2.addColumn("f1".getBytes(),"id".getBytes(),Bytes.toBytes(2));
        put2.addColumn("f1".getBytes(),"name".getBytes(),Bytes.toBytes("刘备"));
        put2.addColumn("f1".getBytes(),"age".getBytes(),Bytes.toBytes(32));
        put2.addColumn("f2".getBytes(),"sex".getBytes(),Bytes.toBytes("1"));
        put2.addColumn("f2".getBytes(),"address".getBytes(),Bytes.toBytes("幽州涿郡涿县"));
        put2.addColumn("f2".getBytes(),"phone".getBytes(),Bytes.toBytes("17888888888"));
        put2.addColumn("f2".getBytes(),"say".getBytes(),Bytes.toBytes("talk is cheap , show me the code"));


        Put put3 = new Put("0004".getBytes());
        put3.addColumn("f1".getBytes(),"id".getBytes(),Bytes.toBytes(3));
        put3.addColumn("f1".getBytes(),"name".getBytes(),Bytes.toBytes("孙权"));
        put3.addColumn("f1".getBytes(),"age".getBytes(),Bytes.toBytes(35));
        put3.addColumn("f2".getBytes(),"sex".getBytes(),Bytes.toBytes("1"));
        put3.addColumn("f2".getBytes(),"address".getBytes(),Bytes.toBytes("下邳"));
        put3.addColumn("f2".getBytes(),"phone".getBytes(),Bytes.toBytes("12888888888"));
        put3.addColumn("f2".getBytes(),"say".getBytes(),Bytes.toBytes("what are you 弄啥嘞！"));

        Put put4 = new Put("0005".getBytes());
        put4.addColumn("f1".getBytes(),"id".getBytes(),Bytes.toBytes(4));
        put4.addColumn("f1".getBytes(),"name".getBytes(),Bytes.toBytes("诸葛亮"));
        put4.addColumn("f1".getBytes(),"age".getBytes(),Bytes.toBytes(28));
        put4.addColumn("f2".getBytes(),"sex".getBytes(),Bytes.toBytes("1"));
        put4.addColumn("f2".getBytes(),"address".getBytes(),Bytes.toBytes("四川隆中"));
        put4.addColumn("f2".getBytes(),"phone".getBytes(),Bytes.toBytes("14888888888"));
        put4.addColumn("f2".getBytes(),"say".getBytes(),Bytes.toBytes("出师表你背了嘛"));

        Put put5 = new Put("0006".getBytes());
        put5.addColumn("f1".getBytes(),"id".getBytes(),Bytes.toBytes(5));
        put5.addColumn("f1".getBytes(),"name".getBytes(),Bytes.toBytes("司马懿"));
        put5.addColumn("f1".getBytes(),"age".getBytes(),Bytes.toBytes(27));
        put5.addColumn("f2".getBytes(),"sex".getBytes(),Bytes.toBytes("1"));
        put5.addColumn("f2".getBytes(),"address".getBytes(),Bytes.toBytes("哪里人有待考究"));
        put5.addColumn("f2".getBytes(),"phone".getBytes(),Bytes.toBytes("15888888888"));
        put5.addColumn("f2".getBytes(),"say".getBytes(),Bytes.toBytes("跟诸葛亮死掐"));


        Put put6 = new Put("0007".getBytes());
        put6.addColumn("f1".getBytes(),"id".getBytes(),Bytes.toBytes(5));
        put6.addColumn("f1".getBytes(),"name".getBytes(),Bytes.toBytes("xiaobubu—吕布"));
        put6.addColumn("f1".getBytes(),"age".getBytes(),Bytes.toBytes(28));
        put6.addColumn("f2".getBytes(),"sex".getBytes(),Bytes.toBytes("1"));
        put6.addColumn("f2".getBytes(),"address".getBytes(),Bytes.toBytes("内蒙人"));
        put6.addColumn("f2".getBytes(),"phone".getBytes(),Bytes.toBytes("15788888888"));
        put6.addColumn("f2".getBytes(),"say".getBytes(),Bytes.toBytes("貂蝉去哪了"));

        List<Put> listPut = new ArrayList<Put>();
        listPut.add(put);
        listPut.add(put2);
        listPut.add(put3);
        listPut.add(put4);
        listPut.add(put5);
        listPut.add(put6);

        myuser.put(listPut);
        //关闭表
        myuser.close();
    }

?在shell终端中通过

scan 'myuser'

查看数据是否写入

?在每次操作前都要获取连接和关闭表，我们创建@BeforeTest和@AfterTest来获取连接和关闭表

/*
    * 初始化操作*/
    @BeforeTest
    public void initTable() throws IOException {
        //获取连接
        configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");

        connection = ConnectionFactory.createConnection(configuration);
        table = connection.getTable(TableName.valueOf("myuser"));
    }

?

 @AfterTest
    public void closeTable() throws IOException {
        table.close();

    }

后续测试都在这两个测试之间进行

查询操作查询rowkey为0003的人，所有的列，通过打开注释可以查询f1列族下面所有列的值和查询f1列族下面id列的值。

 /*
    * 查询操作查询rowkey为0003的人，所有的列*/
    @Test
    public  void getData() throws IOException {
        Get get = new Get("0003".getBytes());

        //查询f1列族下面所有列的值
        //get.addFamily("f1".getBytes());

        //查询f1列族下面id列的值
        //get.addColumn("f1".getBytes(),"id".getBytes());

        //Result是一个对象，封装了所有的结果数据
        Result result = table.get(get);
        //获取0003这条数据所有的cell值
        List<Cell> cells = result.listCells();
        for (Cell cell : cells) {
            //获取列族名称
            String familyName = Bytes.toString(cell.getFamilyArray(), cell.getFamilyOffset(), cell.getFamilyLength());
            //获取列的名称
            String columnName = Bytes.toString(cell.getQualifierArray(), cell.getQualifierOffset(), cell.getQualifierLength());

            if (familyName.equals("f1") && columnName.equals("id") || columnName.equals("age")) {
                int value = Bytes.toInt(cell.getValueArray(),cell.getValueOffset(),cell.getValueLength());
                System.out.println("列族名为" + familyName + "列名为" + columnName + "列的值为" + value);
            }else {
                String value = Bytes.toString(cell.getValueArray(), cell.getValueOffset(), cell.getValueLength());
                System.out.println("列族名为" + familyName + "列名为" + columnName + "列的值为" + value);
            }
        }
    }

查询结果?

?在shell中通过

get 'myuser', '0003'

查询得到

查询rowkey范围是0004到0006

  /*
    * 按照rowkey进行范围值的扫描
    * 扫描rowkey范围是0004到0006*/
    @Test
    public void scanRange() throws IOException {
        Scan scan = new Scan();
        //设置起始和结束的rowkey,范围值扫描包前不包后：只能扫到0005不能扫到0006.没有设置范围将会全局扫描
        scan.setStartRow("0004".getBytes());
        scan.setStopRow("0006".getBytes());
        //返回多条数据结果值都封装在resultScanner里面了
        ResultScanner scanner = table.getScanner(scan);
        for (Result result : scanner){
            List<Cell> cells = result.listCells();
            for (Cell cell : cells){
                String rowkey = Bytes.toString(cell.getRowArray(),cell.getRowOffset(),cell.getRowLength());
                //获取列族名
                String familyName = Bytes.toString(cell.getFamilyArray(),cell.getFamilyOffset(),cell.getFamilyLength());
                //获取列名
                String columnName = Bytes.toString(cell.getQualifierArray(),cell.getQualifierOffset(),cell.getQualifierLength());

                if (familyName.equals("f1") && columnName.equals("id") || columnName.equals("age")) {
                    int value = Bytes.toInt(cell.getValueArray(),cell.getValueOffset(),cell.getValueLength());
                    System.out.println("数据的rowkey为" + rowkey + "列族名为" + familyName + "列名为" + columnName + "列的值为" + value);
                }else {
                    String value = Bytes.toString(cell.getValueArray(), cell.getValueOffset(), cell.getValueLength());
                    System.out.println("数据的rowkey为" + rowkey + "列族名为" + familyName + "列名为" + columnName + "列的值为" + value);
                }
            }
        }
    }

?

?shell中通过

scan 'myuser', {STARTROW => '0004', ENDROW => '0006'}

查询得到?

?