Exercise 25 - HBase CRUD operations

itversity · December 22, 2016, 11:36am

Problem statement

Perform CRUD operations on HBase
Launch HBase shell (hbase shell)
Create namespace
Create table
Insert few rows with several columns
Perform CRUD operations using Java maven
Create dependencies in pom.xml or build.sbt

  <dependency>
  	<groupId>org.apache.hbase</groupId>
  	<artifactId>hbase-client</artifactId>
  	<version>1.1.2</version>
  </dependency>
  <dependency>
  	<groupId>org.apache.hbase</groupId>
  	<artifactId>hbase-common</artifactId>
  	<version>1.1.2</version>
  </dependency>

Write JDBC code using zookeeper quorum

        static Configuration conf = HBaseConfiguration.create();
  conf.set("hbase.zookeeper.quorum", 
  		"nn01.itversity.com,nn02.itversity.com,rm01.itversity.com");
  conf.set("hbase.zookeeper.property.clientPort", "2181");
  
  Connection connection = ConnectionFactory.createConnection(conf);
  Table table = connection.getTable(TableName.valueOf("demo"));

Please provide the following

Hbase shell commands executed
Java code to connect to HBase and get the results

Sumanth_Sharma · December 22, 2016, 12:35pm

hbase code:
create_namespace 'sumanthsharma’
create ‘sumanthsharma:details’,‘name’

python code:
import happybase
connection = happybase.Connection(‘localhost’)

table = connection.table(‘sumanthsharma:details’)
//adding a row

table.put(b’1’, {b’name:first’: b’sumanth’,b’name:last’: b’sharma’})
//retriveing row on row key

row = table.row(b’1’)
//printing desired coloumn

print(row[b’name:first’])
sumanth
//deleting row by row key

row = table.delete(b’1’)
row = table.row(b’1’)
//verifying if row is deleted

print(row[b’name:first’])
Traceback (most recent call last):
File “”, line 1, in
KeyError: ‘name:first’

Farhan_Misarwala · December 22, 2016, 12:42pm

#Hbase shell commands

hbase(main):001:0> create 'employee' , 'cf'
0 row(s) in 0.8190 seconds

=> Hbase::Table - employee
hbase(main):002:0> put 'employee', '1', 'cf:name', 'farhan'
0 row(s) in 0.1000 seconds

hbase(main):003:0> put 'employee', '1', 'cf:age', '24'
0 row(s) in 0.0100 seconds

hbase(main):004:0> put 'employee', '2', 'cf:name', 'saswat'
0 row(s) in 0.0070 seconds

hbase(main):005:0> put 'employee', '2', 'cf:age', '25'
0 row(s) in 0.0080 seconds

hbase(main):006:0> scan 'employee'
ROW                                           COLUMN+CELL                                                                                                                        
 1                                            column=cf:age, timestamp=1482405559573, value=24                                                                                   
 1                                            column=cf:name, timestamp=1482405549318, value=farhan                                                                              
 2                                            column=cf:age, timestamp=1482405592305, value=25                                                                                   
 2                                            column=cf:name, timestamp=1482405579097, value=saswat                                                                              
2 row(s) in 0.0270 seconds

#To connect to HBase and get the results

##Java code

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.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.util.Bytes;

public class OnJava {

	static Configuration conf = HBaseConfiguration.create();

	public static void main(String[] args) throws IOException {

		conf.set("hbase.zookeeper.quorum", "localhost");
		conf.set("hbase.zookeeper.property.clientPort", "2181");

		Connection connection = ConnectionFactory.createConnection(conf);

		Table table = connection.getTable(TableName.valueOf("employee"));

		// Insert data

		Put put = new Put(Bytes.toBytes("3"));

		put.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("name"),
				Bytes.toBytes("kamleshwar"));
		put.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("age"),
				Bytes.toBytes("26"));

		table.put(put);

		// Retrieve Data

		Get get = new Get(Bytes.toBytes("3"));

		Result result = table.get(get);

		byte[] nameByte = result.getValue(Bytes.toBytes("cf"),
				Bytes.toBytes("name"));
		byte[] ageByte = result.getValue(Bytes.toBytes("cf"),
				Bytes.toBytes("age"));

		String nameString = Bytes.toString(nameByte);

		String ageString = Bytes.toString(ageByte);

		System.out.println("Name is " + nameString + ", age is " + ageString);

	}
}

###Output

log4j:WARN No appenders could be found for logger (org.apache.hadoop.metrics2.lib.MutableMetricsFactory).
log4j:WARN Please initialize the log4j system properly.
log4j:WARN See http://logging.apache.org/log4j/1.2/faq.html#noconfig for more info.
Name is kamleshwar, age is 26

##Scala code

import org.apache.hadoop.conf.Configuration
import org.apache.hadoop.hbase.util.HBaseConfTool
import org.apache.hadoop.hbase.HBaseConfiguration
import org.apache.hadoop.hbase.client.Connection
import org.apache.hadoop.hbase.client.ConnectionFactory
import org.apache.hadoop.hbase.TableName
import org.apache.hadoop.hbase.util.Bytes
import org.apache.hadoop.hbase.client.Put
import org.apache.hadoop.hbase.client.Get

object HbaseBasics {

  val conf: Configuration = HBaseConfiguration.create()

  def main(args: Array[String]): Unit = {

    conf.set("hbase.zookeeper.quorum", "localhost")
    conf.set("hbase.zookeeper.property.clientPort", "2181")

    val connection: Connection = ConnectionFactory.createConnection(conf)

    val table = connection.getTable(TableName.valueOf("employee"))

    // Insert data

    val p = new Put(Bytes.toBytes("4"))
    p.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("name"), Bytes.toBytes("arun"))
    p.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("age"), Bytes.toBytes("27"))
    table.put(p)

    //Retreive Data

    for (rowKey <- 1 to 4) {

      val result = table.get(new Get(Bytes.toBytes(rowKey.toString())))

      val nameByte = result.getValue(Bytes.toBytes("cf"), Bytes.toBytes("name"))
      val ageByte = result.getValue(Bytes.toBytes("cf"), Bytes.toBytes("age"))

      val name = Bytes.toString(nameByte)
      val age = Bytes.toString(ageByte)

      println("Name is " + name + ", age is " + age)

    }

  }
}

###Output

log4j:WARN No appenders could be found for logger (org.apache.hadoop.metrics2.lib.MutableMetricsFactory).
log4j:WARN Please initialize the log4j system properly.
log4j:WARN See http://logging.apache.org/log4j/1.2/faq.html#noconfig for more info.
Name is farhan, age is 24
Name is saswat, age is 25
Name is kamleshwar, age is 26
Name is arun, age is 27

Parul · December 23, 2016, 5:48am

create_namespace ‘parulshine92’

create ‘parulshine92:employee’ , ‘colfam’

put ‘parulshine92:employee’ , 3, ‘colfam:deptID’ , '1’
put ‘parulshine92:employee’ , 1, ‘colfam:deptname’ , 'Marketing’
put ‘parulshine92:employee’ , 1, ‘colfam:deptID’ , '1’
0 row(s) in 0.0090 seconds

get ‘parulshine92:employee’ , 3
hbase(main):005:0> scan 'parulshine92:employee’
ROW COLUMN+CELL
1 column=colfam:deptID, timestamp=1482405621803, value=1
1 column=colfam:deptname, timestamp=1482405532762, value=Marketing
2 column=colfam:deptID, timestamp=1482405678618, value=2
2 column=colfam:deptname, timestamp=1482405715457, value=Finance
3 column=colfam:deptID, timestamp=1482404223801, value=1
3 column=colfam:deptname, timestamp=1482404351231, value=revenue
3 row(s) in 0.0180 seconds