Hi, all:
I wrote this guild to tell how to start to program with hbase. Please give
a review to
check if there are any errors or improvements.
Attachment is an example.
Getting start with hbase-based program.
This guild is for those who are fresh to hbase. It can teach you to
get involved with basic hbase operations about in 30 minutes, including:
--connect to hbase
--create/delete tables
--add/read/modify/delete columns
--add/read/modify/delete values
For more details, please refer to hbase java doc. And also, hbase test
example is your good teacher.
== Before Start ==
Before start, be sure that you already have your hadoop and hbase run.
Please follow "hbase in ten minutes" for details.
== Connect to hbase ==
Steps to connect to hbase:
1. Read configuration file.
2. Get HBaseAdmin. HBaseAdmin is the entry to access hbase tables.
...
//configuration file
HBaseConfiguration hbaseConf = new HBaseConfiguration();
//connect to hbase.
HBaseAdmin hbaseAdmin = new HBaseAdmin(hbaseConf);
...
== Create tables ==
Steps to create tables:
1. Decide table name.
2. Decide column families.
3. Create tables
//table name
Text tableName = new Text(TABLENAME);
//column family
Text columnFamily = new Text (COLUMNFAMILY);
//column descriptor
HColumnDescriptor column = new HColumnDescriptor(
columnFamily.toString());
//table descriptor
HTableDescriptor table = new HTableDescriptor(tableName.toString());
//add column into table
table.addFamily(column);
//create table
try {
hbaseAdmin.createTable(table);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
== get all table names ==
Use method listTables() in class org.apache.hadoop.hbase.HBaseAdmin.
== delete table ==
You can delte a table by simply giving a table name.
hbaseAdmin.deleteTable(table);
== read all column names ==
Step to get all column names:
1. Get table descriptor by table name.
2. Get column family set.
Set<Text> colNames = null;
//get table descriptor by table name
HTableDescriptor tableDesc = null;
HTableDescriptor[] tableDescs = hbaseAdmin.listTables();
for (HTableDescriptor t : tableDescs) {
if (t.getName().toString().equals(TABLENAME))
tableDesc = t;
}
//get all column names
colNames = tableDesc.getFamilies().keySet();
== add/delete/modify column ==
Please refer to method addColumn(), deleteColumn(), modifyColumn() in
class org.apache.hadoop.hbase.HBaseAdmin.
Note that you need to disable table by call hbaseAdmin.disableTable()
method before the operation and hbaseAdmin.enableTable() after.
== insert/update data in table ==
Step to add data into table:
1. Get HTable by table name.
2. Start atomic insert/update
3. Perform insert/update
4. Commit
//get HTable by name
HTable table = new HTable (hbaseConf, TABLENAME);
//start insert
long lockid = table.startUpdate(ROW);
//insert
byte[] value = VALUE.toString().getBytes("UTF-8");
table.put(lockid, COLUMNFAMILY1, value);
//commit
table.commit(lockid);
== read column values ==
HashMap<Text, TreeMap<Text,byte[]>> results = new HashMap();
//get table
HTable table = new HTable (hbaseConf, TABLENAME);
//get scanner
HScannerInterface scanner = table.obtainScanner(new
Text[]{COLUMNFAMILY1}, new Text(""));
//scan table
HStoreKey key = new HStoreKey();
TreeMap<Text, byte[]> resultOfRow = new TreeMap<Text, byte[]>();
while(scanner.next(key, resultOfRow)) {
results.put(key.getRow(), resultOfRow);
key = new HStoreKey();
resultOfRow = new TreeMap<Text, byte[]>();
}
--
[EMAIL PROTECTED]
Institute of Computing Technology, Chinese Academy of Sciences, Beijing.
package cn.ac.ict.hla;
import java.io.IOException;
import java.util.HashMap;
import java.util.Set;
import java.util.TreeMap;
import org.apache.hadoop.hbase.HBaseAdmin;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HScannerInterface;
import org.apache.hadoop.hbase.HStoreKey;
import org.apache.hadoop.hbase.HTable;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.MasterNotRunningException;
import org.apache.hadoop.io.Text;
/**
* This class demonstrates the basic hbase operations, including:
* --connect to hbase
* --create/delete tables
* --insert/modify/delete columns
* --insert/modify/delete values
* @author [EMAIL PROTECTED]
*
*/
public class HTableTest {
//table name
public static final Text TABLENAME = new Text("testtable");
//column family 1
public static final Text COLUMNFAMILY1= new Text ("testinfo1:");
//column family 2
public static final Text COLUMNFAMILY2 = new Text("testinfo2:");
//row
public static final Text ROW = new Text("row");
//value
public static final Text VALUE = new Text("value");
/** read configuration file*/
private HBaseConfiguration hbaseConf = null;
/** HBaseAdmin is the key to access hbase tables */
private HBaseAdmin hbaseAdmin = null;
/**
* connect to hbase master.
*/
public HTableTest () {
this.hbaseConf = new HBaseConfiguration ();
try {
//connect to hbase master.
this.hbaseAdmin = new HBaseAdmin(hbaseConf);
} catch (MasterNotRunningException e) {
e.printStackTrace();
}
}
/**
* @return HBaseAdmin
*/
public HBaseAdmin getAdmin () {
return this.hbaseAdmin;
}
/**
* create table which is named TABLENAME with conlumn COLUMNFAMILY1
* @throws IOException
*/
public void createTable() throws IOException{
//column descriptor
HColumnDescriptor column = new HColumnDescriptor(COLUMNFAMILY1.toString());
//table descriptor
HTableDescriptor table = new HTableDescriptor(TABLENAME.toString());
//add column into table
table.addFamily(column);
//create table
createTable(table);
}
/**
* create table
* @param tableDes table descriptor
* @throws IOException
*/
public void createTable(HTableDescriptor tableDes) throws IOException {
this.hbaseAdmin.createTable(tableDes);
}
/**
* delete table
* @throws IOException
*/
public void deleteTable() throws IOException{
this.hbaseAdmin.deleteTable(TABLENAME);
}
/**
* add a column family
* @throws IOException
*/
public void addColumn() throws IOException {
this.hbaseAdmin.disableTable(TABLENAME);
HColumnDescriptor colDesc = new HColumnDescriptor (COLUMNFAMILY2.toString());
this.hbaseAdmin.addColumn(TABLENAME, colDesc);
this.hbaseAdmin.enableTable(TABLENAME);
}
/**
* delete a column family
* @throws IOException
*/
public void deleteColumn() throws IOException{
this.hbaseAdmin.disableTable(TABLENAME);
this.hbaseAdmin.deleteColumn(TABLENAME, COLUMNFAMILY1);
this.hbaseAdmin.enableTable(TABLENAME);
}
/**
* modify column family name from COLUMNFAMILY1 to COLUMNFAMILY2
* @throws IOException
*/
public void modifyColumn() throws IOException {
this.hbaseAdmin.disableTable(TABLENAME);
HColumnDescriptor colDesc = new HColumnDescriptor(COLUMNFAMILY1.toString());
this.hbaseAdmin.modifyColumn(TABLENAME, COLUMNFAMILY2, colDesc);
this.hbaseAdmin.enableTable(TABLENAME);
}
/**
* read all column family names
* @return A Set<Text> with family names.
* @throws IOException
*/
public Set<Text> readAllColNames() throws IOException {
Set<Text> colNames = null;
//get table descriptor
HTableDescriptor tableDesc = null;
HTableDescriptor[] tableDescs = hbaseAdmin.listTables();
for (HTableDescriptor t : tableDescs) {
if (t.getName().toString().equals(TABLENAME.toString()))
tableDesc = t;
else {
throw new IOException("No such table:" + TABLENAME);
}
}
//get all column names
colNames = tableDesc.getFamilies().keySet();
return colNames;
}
/**
* add data into table.
* @throws IOException
*/
public void addDataIntoTable() throws IOException {
//get HTable by name
HTable table = new HTable (hbaseConf, TABLENAME);
//start insert values into row "row".
//if you want to insert/update multiple rows,
//remember give different row name for each row.
long lockid = table.startUpdate(ROW);
//insert
byte[] value = VALUE.toString().getBytes("UTF-8");
table.put(lockid, COLUMNFAMILY1, value);
//commit
table.commit(lockid);
}
/**
* read all value from table TABLENAME
* @return a HashMap of row->(column->value)
* @throws IOException
*/
public HashMap<Text, TreeMap<Text,byte[]>> getAllValues () throws IOException {
HashMap<Text, TreeMap<Text,byte[]>> results = new HashMap();
//get table
HTable table = new HTable (hbaseConf, TABLENAME);
//get scanner
HScannerInterface scanner = table.obtainScanner(new Text[]{COLUMNFAMILY1}, new Text(""));
//scan table
HStoreKey key = new HStoreKey();
TreeMap<Text, byte[]> resultOfRow = new TreeMap<Text, byte[]>();
while(scanner.next(key, resultOfRow)) {
results.put(key.getRow(), resultOfRow);
key = new HStoreKey();
resultOfRow = new TreeMap<Text, byte[]>();
}
return results;
}
}
