hbase數據庫操作

.實驗內容與完成情況：（實驗具體步驟和實驗截圖說明）
（一）編程實現以下指定功能，並用 Hadoop 提供的 HBase Shell 命令完成相同任務：
（1） 列出 HBase 所有的表的相關信息，例如表名；
列出所有數據表：
列出表的結構
查詢表是否存在
查詢表是否可用

 

packagecn.wl.edu.hbase;

import java.io.IOException;

public class ListTables {
    public static Configuration configuration;
    public static Connection connection;
    public static Admin admin;

    public static void listTables() throws IOException {
        init();
        HTableDescriptor[] hTableDescriptors = admin.listTables();
        for (HTableDescriptor hTableDescriptor : hTableDescriptors) {
            System.out.println("table name:"
                    + hTableDescriptor.getNameAsString());

        }
               close();
    }

    public static void init() {
        configuration = HBaseConfiguration.create();
        configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
        try {
            connection = ConnectionFactory.createConnection(configuration);
            admin = connection.getAdmin();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static void close() {
        try {
            if (admin != null) {
                admin.close();
            }
            if (connection != null) {
                connection.close();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static void main(String[] args) {
        try {
            listTables();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

}





（2）在終端打印出指定的表的所有記錄數據；

 

源代碼：
package cn.wl.edu.hbase;

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 java.io.IOException;

public class ListTableData {

    public static Configuration configuration;
    public static Connection connection;
    public static Admin admin;
    
    public static void getData(String tableName)throws IOException{
        init();
        Table table=connection.getTable(TableName.valueOf(tableName));
        Scan scan=new Scan();
        ResultScanner scanner=table.getScanner(scan);
        for(Result result:scanner){
            printRecoder(result);
        }
System.out.println(“finish!”);
        close();
        
    }
    
    public static void printRecoder(Result result)throws IOException{
        for(Cell cell:result.rawCells()){
            System.out.println("行鍵:"+new String(CellUtil.cloneRow(cell)));
              System.out.print("列簇: " + new String(CellUtil.cloneFamily(cell)));
                System.out.print(" 列: " + new String(CellUtil.cloneQualifier(cell)));
                System.out.print(" 值: " + new String(CellUtil.cloneValue(cell)));
                System.out.println("時間戳: " + cell.getTimestamp());
        }
    }
    
    public static void init() {
        configuration = HBaseConfiguration.create();
        configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
        try {
            connection = ConnectionFactory.createConnection(configuration);
            admin = connection.getAdmin();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static void close() {
        try {
            if (admin != null) {
                admin.close();
            }
            if (connection != null) {
                connection.close();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static void main(String[] args) {
        try {
        getData("person");
        } catch (IOException e) {
            e.printStackTrace();
        }
    }


}




（3） 向已經創建好的表添加和刪除指定的列族或列；
添加數據

 

源代碼：
package cn.wl.edu.hbase;

import java.io.IOException;

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 org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Table;

public class InsertRow {
    public static Configuration configuration;
    public static Connection connection;
    public static Admin admin;
    
    public static void insertRow(String tableName,String rowKey,String colFamily,String col,String val)throws IOException{
        
        init();
        Table table=connection.getTable(TableName.valueOf(tableName));
        Put put=new Put(rowKey.getBytes());
        put.addColumn(colFamily.getBytes(),col.getBytes() ,val.getBytes());
        table.put(put);
       System.out.println("insert finish!");
       table.close();
    }
    
    public static void init() {
        configuration = HBaseConfiguration.create();
        configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
        try {
            connection = ConnectionFactory.createConnection(configuration);
            admin = connection.getAdmin();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static void close() {
        try {
            if (admin != null) {
                admin.close();
            }
            if (connection != null) {
                connection.close();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    public static void main(String[] args) {
        try {
        insertRow("student","s002","score","math","100");
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

}



刪除數據

 

源代碼：
package cn.wl.edu.hbase;
import java.io.IOException;

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;

public class DeleteRow {
      public static Configuration configuration;
        public static Connection connection;
        public static Admin admin;

        public static void deleteRow(String tableName, String rowKey, String colFamily, String col) throws IOException {
            init();
            Table table = connection.getTable(TableName.valueOf(tableName));
            Delete delete = new Delete(rowKey.getBytes());
            delete.addFamily(Bytes.toBytes(colFamily));
            delete.addColumn(Bytes.toBytes(colFamily), Bytes.toBytes(col));
            table.delete(delete);
            System.out.println("delete successful!");
            table.close();
            close();
        }

        public static void init() {
            configuration = HBaseConfiguration.create();
            configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
            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("student", "s002", "score", "math");
            } catch (IOException e) {
                e.printStackTrace();
            }

        }

}



（3）清空指定的表的所有記錄數據；

 

源代碼：
package cn.wl.edu.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;
public class TruncateTable {
     public static Configuration configuration;
        public static Connection connection;
        public static Admin admin;

        public static void clearRows(String tableName) throws IOException {
            init();
            TableName tablename = TableName.valueOf(tableName);
            admin.disableTable(tablename);
            admin.truncateTable(tablename, false);
            System.out.println("delete table successful!");
            close();
        }

        public static void init() {
            configuration = HBaseConfiguration.create();
            configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
            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 {
                clearRows("student");
            } catch (IOException e) {
                e.printStackTrace();
            }

        }
}

（5） 統計表的行數。

 

源程序：
package cn.wl.edu.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 java.io.IOException;
public class CountTable {
     public static Configuration configuration;
        public static Connection connection;
        public static Admin admin;

        public static void countTable(String tableName) throws IOException {
            init();
            Table table = connection.getTable(TableName.valueOf(tableName));
            Scan scan = new Scan();
            ResultScanner scanner = table.getScanner(scan);
            int num = 0;
            for (Result result = scanner.next(); result != null; result = scanner
                    .next()) {
                num++;
            }
            System.out.println("行數:" + num);
            scanner.close();
            close();
        }

        public static void init() {
            configuration = HBaseConfiguration.create();
            configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
            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 {
                countTable("student");
            } catch (IOException e) {
                e.printStackTrace();
            }

        }
}




（二） HBase 數據庫操作
1. 現有以下關系型數據庫中的表和數據，要求將其轉換為適合於 HBase 存儲的表並插入數據：

學生表（Student）
學號（S_No）     姓名（S_Name）     性別（S_Sex）     年齡（S_Age）
2015001     Zhangsan     male     23
2015003     Mary     female     22
2015003     Lisi     male     24

課程表（Course）
課程號（C_No）     課程名（C_Name）     學分（C_Credit）
123001     Math     2.0
123002     Computer Science     5.0
123003     English     3.0

選課表（SC）
學號（SC_Sno）     課程號（SC_Cno）     成績（SC_Score）
2015001     123001     86
2015001     123003     69
2015002     123002     77
2015002     123003     99
2015003     123001     98
2015003     123002     95

 

2.請編程實現以下功能：
（1） createTable(String tableName, String[] fields)
創建表，參數 tableName 為表的名稱，字符串數組 fields 為存儲記錄各個字段名稱的數組。
要求當 HBase 已經存在名為 tableName 的表的時候，先刪除原有的表，然后再創建新的表。
package cn.wl.edu.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;

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!");
        }
        HTableDescriptor hTableDescriptor = new HTableDescriptor(tablename);
        for (String str : fields) {
            HColumnDescriptor hColumnDescriptor = new HColumnDescriptor(str);
            hTableDescriptor.addFamily(hColumnDescriptor);
        }
        admin.createTable(hTableDescriptor);
        close();
    }

    public static void init() {
        configuration = HBaseConfiguration.create();
        configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
        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" };
        try {
            createTable("person", fields);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

}


（2）addRecord(String tableName, String row, String[] fields, String[] values
向表 tableName、行 row（用 S_Name 表示）和字符串數組 fields 指定的單元格中添加對
應的數據 values。其中， fields 中每個元素如果對應的列族下還有相應的列限定符的話，用
“columnFamily:column”表示。例如，同時向“Math”、 “Computer Science”、 “English”三列添加
成績時，字符串數組 fields 為{“Score:Math”, ”Score:Computer Science”, ”Score:English”}，數組
values 存儲這三門課的成績。
源代碼：
package cn.wl.edu.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 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://localhost:9000/hbase");
        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("person", "Score", fields, values);
        } catch (IOException e) {
            e.printStackTrace();
        }
    System.out.println("finish!");

    }
}



（3） scanColumn(String tableName, String column)
瀏覽表 tableName 某一列的數據，如果某一行記錄中該列數據不存在，則返回 null。要求
當參數 column 為某一列族名稱時，如果底下有若干個列限定符，則要列出每個列限定符代表
的列的數據；當參數 column 為某一列具體名稱（例如“Score:Math”）時，只需要列出該列的
數據。
源代碼：
package cn.wl.edu.hbase;
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);
            }
           System.out.println("finish!");
            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://localhost:9000/hbase");
            try {
                connection = ConnectionFactory.createConnection(configuration);
                admin = connection.getAdmin();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }

        // 關閉連接
        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("person", "Score");
            } catch (IOException e) {
                e.printStackTrace();
            }

        }
}








（4） modifyData(String tableName, String row, String column)
修改表 tableName，行 row（可以用學生姓名 S_Name 表示），列 column 指定的單元格的
數據。
源代碼：
package cn.wl.edu.hbase;
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);
        System.out.println("modify successful!");
        table.close();
        close();
    }

    public static void init() {
        configuration = HBaseConfiguration.create();
        configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
        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("person", "Score", "Math", "100");
        } catch (IOException e) {
            e.printStackTrace();
        }

    }
}



（5） deleteRow(String tableName, String row)
刪除表 tableName 中 row 指定的行的記錄。 
源代碼：
package cn.wl.edu.hbase;
import java.io.IOException;

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;

public class DeleteRow {
      public static Configuration configuration;
        public static Connection connection;
        public static Admin admin;

        public static void deleteRow(String tableName, String rowKey, String colFamily, String col) throws IOException {
            init();
            Table table = connection.getTable(TableName.valueOf(tableName));
            Delete delete = new Delete(rowKey.getBytes());
            delete.addFamily(Bytes.toBytes(colFamily));
            delete.addColumn(Bytes.toBytes(colFamily), Bytes.toBytes(col));
            table.delete(delete);
            System.out.println("delete successful!");
            table.close();
            close();
        }

        public static void init() {
            configuration = HBaseConfiguration.create();
            configuration.set("hbase.rootdir", "hdfs://localhost:9000/hbase");
            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("student", "s002", "score", "math");
            } catch (IOException e) {
                e.printStackTrace();
            }

        }

}



2.實驗中出現問題：（說明和截圖）
Eclipse運行大多數程序，運行時間特別長，既不報錯也不顯示結果。

3.解決方案：（列出遇到的問題和解決辦法，列出沒有解決的問題）： 
再次對照查看hbase的安裝配置教程，發現自己少了一個步驟。
 在hbase-env.sh文件中添加了這些路徑之后就好了。