实验三：熟悉常用的HBase操作

实验环境：

(1)操作系统：Linux(建议 Ubuntu 16.04 或 Ubuntu 18.04)。

(2)Hadoop 版本：3.1.3。

(3)HBase 版本：2.2.2。

(4)JDK 版本：1.8。

(5)Java IDE: Eclipse。

实验内容与完成情况：

(1)现有以下关系数据库中的表和数据(见表14-3〜表14-5),要求将其转换为适合于

HBase存储的表并插入数据。

在这里插入图片描述

（1）学生Student表

创建表的HBase Shell命令语句如下：

第二行数据

第三行数据

（2）课程Course表

创建表的HBase Shell命令语句如下：

（3）选课表

创建表的HBase Shell命令语句如下：

(2)编程实现以下功能。

①createTable(String tableName, String]] fields)。

创建表，参数tableName 表的名称，字符串数组fields *存储记录各字段名的数组。 要求当HBase已经存在名为tableName的表时，先删除原有的表，再创建新的表。

Java代码：

package com.xusheng.HBase.shiyan31;
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.*;
import org.apache.hadoop.hbase.util.Bytes;
import java.io.IOException;
public class CreateTable {
    public static Configuration configuration;
    public static Connection connection;
    public static Admin admin;
    public static void createTable(String tableName,String[] fields) throws IOException {
        init();
        TableName tablename = TableName.valueOf(tableName);
        if(admin.tableExists(tablename)){
            System.out.println("table is exists!");
            admin.disableTable(tablename);
            admin.deleteTable(tablename);//删除原来的表
        }
        TableDescriptorBuilder tableDescriptor = TableDescriptorBuilder.newBuilder(tablename);
        for(String str : fields){
            tableDescriptor.setColumnFamily(ColumnFamilyDescriptorBuilder.newBuilder(Bytes.toBytes(str)).build());
            admin.createTable(tableDescriptor.build());
        }
        close();
    }
    //建立连接
    public static void init() {
        configuration = HBaseConfiguration.create();
        //configuration.set("hbase.rootdir", "hdfs://hadoop102:8020/HBase");
        configuration.set("hbase.zookeeper.quorum","hadoop102,hadoop103,hadoop104");
        try {
            connection = ConnectionFactory.createConnection(configuration);
            admin = connection.getAdmin();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    //关闭连接
    public static void close() {
        try {
            if (admin != null) {
                admin.close();
            }
            if (null != connection) {
                connection.close();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    public static void main(String[] args) {
        String[] fields = {"Score"};
        try {
            createTable("person", fields);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

结果：

②addRecord(String tableName, String row, String]] fields, String口 values) 。

向表tableName、行row(用S_Name表示)和字符串数组fields指定的单元格中添加对 应的数据valueso其中,fields中每个元素如果对应的列族下还有相应的列限定符，用 “columnFamily： column"表示。例如，同时向MathComputerEnglish三列添加成绩时，字 符串数组 fields 为( “Score： Math” ," Score: Computer" , “Score： English” ｝，数组 values 存储 这三门课的成绩。

Java代码：

package com.xusheng.HBase.shiyan31;
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 java.io.IOException;
public class addRecord {
    public static Configuration configuration;
    public static Connection connection;
    public static Admin admin;
    public static void addRecord(String tableName, String row, String[] fields, String[] values) throws IOException {
        init();
        Table table = connection.getTable(TableName.valueOf(tableName));
        for (int i = 0; i != fields.length; i++) {
            Put put = new Put(row.getBytes());
            String[] cols = fields[i].split(":");
            put.addColumn(cols[0].getBytes(), cols[1].getBytes(), values[i].getBytes());
            table.put(put);
        }
        table.close();
        close();
    }
    public static void init() {
        configuration = HBaseConfiguration.create();
        //configuration.set("hbase.rootdir", "hdfs://hadoop102:8020/HBase");
        configuration.set("hbase.zookeeper.quorum","hadoop102,hadoop103,hadoop104");
        try {
            connection = ConnectionFactory.createConnection(configuration);
            admin = connection.getAdmin();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    public static void close() {
        try {
            if (admin != null) {
                admin.close();
            }
            if (null != connection) {
                connection.close();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    public static void main(String[] args) {
        String[] fields = {"Score:Math", "Score:Computer Science", "Score:English"};
        String[] values = {"99", "80", "100"};
        try {
            addRecord("tableName", "Score", fields, values);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

结果：

③scanColumn(String tableName, String column) 。

浏览表tableName某列的数据，如果某行记录中该列数据不存在，则返回null。要求 当参数column为某列族名时，如果底下有若干个列限定符，则要列出每个列限定符代表 的列的数据；当参数column为某列具体名(例如“ Score: Math")时，只需要列出该列的 数据。

Java代码：

package com.xusheng.HBase.shiyan31;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
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;
public class scanColumn {
    public static Configuration configuration;
    public static Connection connection;
    public static Admin admin;
    public static void scanColumn(String tableName, String column) throws IOException {
        init();
        Table table = connection.getTable(TableName.valueOf(tableName));
        Scan scan = new Scan();
        scan.addFamily(Bytes.toBytes(column));
        ResultScanner scanner = table.getScanner(scan);
        for (Result result = scanner.next(); result != null; result = scanner.next()) {
            showCell(result);
        }
        table.close();
        close();
    }
    public static void showCell(Result result) {
        Cell[] cells = result.rawCells();
        for (Cell cell : cells) {
            System.out.println("RowName:" + new String(CellUtil.cloneRow(cell)) + " ");
            System.out.println("Timetamp:" + cell.getTimestamp() + " ");
            System.out.println("column Family:" + new String(CellUtil.cloneFamily(cell)) + " ");
            System.out.println("row Name:" + new String(CellUtil.cloneQualifier(cell)) + " ");
            System.out.println("value:" + new String(CellUtil.cloneValue(cell)) + " ");
        }
    }
    public static void init() {
        configuration = HBaseConfiguration.create();
        //configuration.set("hbase.rootdir", "hdfs://hadoop102:8020/HBase");
        configuration.set("hbase.zookeeper.quorum","hadoop102,hadoop103,hadoop104");
        try {
            connection = ConnectionFactory.createConnection(configuration);
            admin = connection.getAdmin();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    // 关闭连接
    public static void close() {
        try {
            if (admin != null) {
                admin.close();
            }
            if (null != connection) {
                connection.close();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    public static void main(String[] args) {
        try {
            scanColumn("tableName", "Score");
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

结果：

④modifyData(String tableName, String row, String column) 。

修改表tableName,即修改行row(可以用学生姓名S_Name表示)、列column指定的 单元格的数据。

Java代码：

package com.xusheng.HBase.shiyan31;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import java.io.IOException;
public class modifyData {
    public static long ts;
    public static Configuration configuration;
    public static Connection connection;
    public static Admin admin;
    public static void modifyData(String tableName, String row, String column, String val) throws IOException {
        init();
        Table table = connection.getTable(TableName.valueOf(tableName));
        Put put = new Put(row.getBytes());
        Scan scan = new Scan();
        ResultScanner resultScanner = table.getScanner(scan);
        for (Result r : resultScanner) {
            for (Cell cell : r.getColumnCells(row.getBytes(), column.getBytes())) {
                ts = cell.getTimestamp();
            }
        }
        put.addColumn(row.getBytes(), column.getBytes(), ts, val.getBytes());
        table.put(put);
        table.close();
        close();
    }
    public static void init() {
        configuration = HBaseConfiguration.create();
        //configuration.set("hbase.rootdir", "hdfs://hadoop102:8020/HBase");
        configuration.set("hbase.zookeeper.quorum","hadoop102,hadoop103,hadoop104");
        try {
            connection = ConnectionFactory.createConnection(configuration);
            admin = connection.getAdmin();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    public static void close() {
        try {
            if (admin != null) {
                admin.close();
            }
            if (null != connection) {
                connection.close();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    public static void main(String[] args) {
        try {
            modifyData("tableName", "Score", "Math", "100");
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

结果：

⑤deleteRow(String tableName, String row)。

删除表tableName中row指定的行的记录。

Java代码：

package com.xusheng.HBase.shiyan31;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
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;
public class deleteRow {
    public static long ts;
    public static Configuration configuration;
    public static Connection connection;
    public static Admin admin;
    public static void deleteRow(String tableName, String row) throws IOException {
        init();
        Table table = connection.getTable(TableName.valueOf(tableName));
        Delete delete=new Delete(row.getBytes());
        table.delete(delete);
        table.close();
        close();
    }
    public static void init() {
        configuration = HBaseConfiguration.create();
        //configuration.set("hbase.rootdir", "hdfs://hadoop102:8020/HBase");
        configuration.set("hbase.zookeeper.quorum","hadoop102,hadoop103,hadoop104");
        try {
            connection = ConnectionFactory.createConnection(configuration);
            admin = connection.getAdmin();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    public static void close() {
        try {
            if (admin != null) {
                admin.close();
            }
            if (null != connection) {
                connection.close();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    public static void main(String[] args) {
        try {
            deleteRow("tableName", "Score");
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

结果：