0
我进入DW测试并需要比较源数据到目标数据。源数据存储在hive/RDBMS中,而目标数据加载到Hbase中。我是Hbase的新手。任何人都可以帮助我采取我可以采取的方法。我正在寻找的是与“MINUS”类似的功能。可能吗 ?Hive与表中数据的比较
我进入DW测试并需要比较源数据到目标数据。源数据存储在hive/RDBMS中,而目标数据加载到Hbase中。我是Hbase的新手。任何人都可以帮助我采取我可以采取的方法。我正在寻找的是与“MINUS”类似的功能。可能吗 ?Hive与表中数据的比较
你应该写Java文件中,可以组合:
HBase:
import java.io.IOException;
// HBASE
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.util.Bytes;
public class RetriveData{
public static void main(String[] args) throws IOException, Exception{
// Instantiating Configuration class
Configuration config = HBaseConfiguration.create();
// Instantiating HTable class
HTable table = new HTable(config, "emp");
// Instantiating Get class
Get g = new Get(Bytes.toBytes("row1"));
// Reading the data
Result result = table.get(g);
// Reading values from Result class object
byte [] value = result.getValue(Bytes.toBytes("personal"),Bytes.toBytes("name"));
byte [] value1 = result.getValue(Bytes.toBytes("personal"),Bytes.toBytes("city"));
// Printing the values
String name = Bytes.toString(value);
String city = Bytes.toString(value1);
**// CALL THE HIVE CLASS(HiveQLOrderBy)...YOU CAN COMPARE**
System.out.println("name: " + name + " city: " + city);
}
}
//HIVE
import java.sql.SQLException;
import java.sql.Connection;
import java.sql.ResultSet;
import java.sql.Statement;
import java.sql.DriverManager;
public class HiveQLOrderBy {
private static String driverName = "org.apache.hadoop.hive.jdbc.HiveDriver";
public static void main(String[] args) throws SQLException {
// Register driver and create driver instance
Class.forName(driverName);
// get connection
Connection con = DriverManager.getConnection("jdbc:hive://localhost:10000/userdb", "", "");
// create statement
Statement stmt = con.createStatement();
// execute statement
Resultset res = stmt.executeQuery("SELECT * FROM employee ORDER BY DEPT;");
System.out.println(" ID \t Name \t Salary \t Designation \t Dept ");
while (res.next()) {
System.out.println(res.getInt(1) + " " + res.getString(2) + " " + res.getDouble(3) + " " + res.getString(4) + " " + res.getString(5));
}
con.close();
}
}
感谢@R Palanivel,但我从上面的Java文件不解的是,它会单独打印从HBase的表和蜂巢结果那么将不得不手动比较它。如果我错了,请纠正我。到目前为止,我还没能实现它。请建议。 –