hbase开发实例

时间：2024-01-09 15:53:44

1、put/checkAndPut

 package com.testdata;

 import java.io.IOException;

 import org.apache.hadoop.conf.Configuration;

 import org.apache.hadoop.hbase.HBaseConfiguration;

 import org.apache.hadoop.hbase.client.HConnection;

 import org.apache.hadoop.hbase.client.HConnectionManager;

 import org.apache.hadoop.hbase.client.HTableInterface;

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

 import org.apache.hadoop.hbase.util.Bytes; 

 public class TestPut {

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

         Configuration conf = HBaseConfiguration.create();

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

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

         HConnection conn = HConnectionManager.createConnection(conf);

         HTableInterface table = conn.getTable("testdata");

         Put testput = new Put(Bytes.toBytes("row1"));

         testput.add(Bytes.toBytes("cf"),Bytes.toBytes("col1"),Bytes.toBytes("E"));

         table.put(testput);

         //使用checkAndPut

         table.checkAndPut(Bytes.toBytes("row1"), Bytes.toBytes("cf"),Bytes.toBytes("col5"),Bytes.toBytes("E"),testput);

         table.close();

         conn.close();

     }

 }

使用checkAndPut，需要先对数据进行验证，上面的例子中，向row1中的cf:col1写入数据"E"，而验证的是row1中的cf:col5的值是否为"E"，注意这一点，相当于加了条件。

hbase开发实例

2、使用get读取数据

 package com.testdata;

 import java.io.IOException;

 import java.util.List;

 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.client.Get;

 import org.apache.hadoop.hbase.client.HConnection;

 import org.apache.hadoop.hbase.client.HConnectionManager;

 import org.apache.hadoop.hbase.client.HTableInterface;

 import org.apache.hadoop.hbase.client.Result;

 import org.apache.hadoop.hbase.util.Bytes; 

 public class TestGet {

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

         Configuration conf = HBaseConfiguration.create();

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

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

         HConnection conn = HConnectionManager.createConnection(conf);

         HTableInterface table = conn.getTable("testdata");

         Get testget = new Get(Bytes.toBytes("row1"));

         Result row1 = table.get(testget);

         String value = new String(row1.getValue(Bytes.toBytes("cf"), Bytes.toBytes("col1")));

         System.out.println(value);

         //下面限定到具体的列

         testget.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("col2"));

         Result result = table.get(testget);

         if(result.getValue(Bytes.toBytes("cf"), Bytes.toBytes("col2")) != null){

             String value2 = new String(result.getValue(Bytes.toBytes("cf"), Bytes.toBytes("col2")));

             System.out.println(value2);

         }

         //另外一种读取方式

         List<Cell> cells = row1.listCells();

         for(Cell cell : cells){

             String rowkey = new String(CellUtil.cloneRow(cell));

             String family = new String(CellUtil.cloneFamily(cell));

             String collumn = new String(CellUtil.cloneQualifier(cell));

             String cvalue = new String(CellUtil.cloneValue(cell));

             System.out.println("rowkey:" + rowkey + " family:" + family + " column:" + collumn +" value:" + cvalue);

         }

         //注意要关闭

         table.close();

         conn.close();

     }

 }

参考结果：

hbase开发实例

3、使用scan获取数据

 package com.testdata;

 import java.io.IOException;

 import java.util.List;

 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.client.HConnection;

 import org.apache.hadoop.hbase.client.HConnectionManager;

 import org.apache.hadoop.hbase.client.HTableInterface;

 import org.apache.hadoop.hbase.client.Result;

 import org.apache.hadoop.hbase.client.ResultScanner;

 import org.apache.hadoop.hbase.client.Scan; 

 public class TestScan {

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

         Configuration conf = HBaseConfiguration.create();

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

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

         HConnection conn = HConnectionManager.createConnection(conf);

         HTableInterface table = conn.getTable("testdata");

         Scan testscan =new Scan();

         ResultScanner rs = table.getScanner(testscan);

         for(Result r : rs ){

             List<Cell> cells = r.listCells();

             for(Cell cell : cells){

                 String rowkey = new String(CellUtil.cloneRow(cell));

                 String family = new String(CellUtil.cloneFamily(cell));

                 String collumn = new String(CellUtil.cloneQualifier(cell));

                 String cvalue = new String(CellUtil.cloneValue(cell));

                 System.out.println("rowkey:" + rowkey + " family:" + family + " column:" + collumn +" value:" + cvalue);

             }

         }

         rs.close();

         table.close();

         conn.close();

     }

 }

4、delete/checkAndDelete

 package com.testdata;

 import org.apache.hadoop.conf.Configuration;

 import org.apache.hadoop.hbase.HBaseConfiguration;

 import org.apache.hadoop.hbase.client.Delete;

 import org.apache.hadoop.hbase.client.HConnection;

 import org.apache.hadoop.hbase.client.HConnectionManager;

 import org.apache.hadoop.hbase.client.HTableInterface;

 import java.io.IOException;

 import org.apache.hadoop.hbase.util.Bytes; 

 public class TestDelete {

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

         Configuration conf = HBaseConfiguration.create();

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

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

         HConnection conn = HConnectionManager.createConnection(conf);

         HTableInterface table = conn.getTable("testdata");

         Delete testdelete = new Delete(Bytes.toBytes("row1"));

         testdelete.deleteColumns(Bytes.toBytes("cf"), Bytes.toBytes("col1"));

         //区别只是checkAndDelete需要进行验证，相当于加了前提条件

         //table.delete(testdelete);

         table.checkAndDelete(Bytes.toBytes("row1"), Bytes.toBytes("cf"), Bytes.toBytes("col2"),Bytes.toBytes("BC"), testdelete);

         table.close();

         conn.close();

     }

 }

5、append

 package com.testdata;

 import java.io.IOException;

 import org.apache.hadoop.conf.Configuration;

 import org.apache.hadoop.hbase.HBaseConfiguration;

 import org.apache.hadoop.hbase.client.Append;

 import org.apache.hadoop.hbase.client.HConnection;

 import org.apache.hadoop.hbase.client.HConnectionManager;

 import org.apache.hadoop.hbase.client.HTableInterface;

 import org.apache.hadoop.hbase.util.Bytes; 

 public class TestAppend {

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

         Configuration conf = HBaseConfiguration.create();

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

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

         HConnection conn = HConnectionManager.createConnection(conf);

         HTableInterface table = conn.getTable("testdata");

         Append testappend = new Append(Bytes.toBytes("row1"));

         testappend.add(Bytes.toBytes("cf"),Bytes.toBytes("col1"),Bytes.toBytes("F"));

         table.append(testappend);

         table.close();

         conn.close();

     }

 }

下面是结果，注意append是在原有的值之上附加，先前的值为"E"，现在变为"EF"

hbase开发实例

 6、计数器

计数器可以用于统计用户数，点击量等信息

 package com.testdata;

 import java.io.IOException;

 import org.apache.hadoop.conf.Configuration;

 import org.apache.hadoop.hbase.HBaseConfiguration;

 import org.apache.hadoop.hbase.client.HConnection;

 import org.apache.hadoop.hbase.client.HConnectionManager;

 import org.apache.hadoop.hbase.client.HTableInterface;

 import org.apache.hadoop.hbase.util.Bytes;

 public class TestIncrement {

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

         Configuration conf = HBaseConfiguration.create();

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

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

         HConnection conn = HConnectionManager.createConnection(conf);

         HTableInterface table = conn.getTable("testdata");

         long result = table.incrementColumnValue(Bytes.toBytes("row1"),Bytes.toBytes("cf"),Bytes.toBytes("coli"), 10);

         System.out.println(result);

         table.close();

         conn.close();

     }

 }

注意 long result = table.incrementColumnValue(Bytes.toBytes("row1"),Bytes.toBytes("cf"),Bytes.toBytes("coli"), 10);

最后一个参数，可以为0，意味着读取，也可以是负数。

可以使用get_counter可以获取对应的计数器的值，也可以使用以下命令进行操作

 incr '<table>', '<row>', '<column>', |<increment-value>|

hbase开发实例

7、filter

使用时注意性能

 package com.testdata;

 import java.io.IOException;

 import java.util.List;

 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.client.HConnection;

 import org.apache.hadoop.hbase.client.HConnectionManager;

 import org.apache.hadoop.hbase.client.HTableInterface;

 import org.apache.hadoop.hbase.client.Result;

 import org.apache.hadoop.hbase.client.ResultScanner;

 import org.apache.hadoop.hbase.client.Scan;

 import org.apache.hadoop.hbase.filter.BinaryComparator;

 import org.apache.hadoop.hbase.filter.BinaryPrefixComparator;

 import org.apache.hadoop.hbase.filter.CompareFilter;

 import org.apache.hadoop.hbase.filter.Filter;

 import org.apache.hadoop.hbase.filter.QualifierFilter;

 import org.apache.hadoop.hbase.filter.RowFilter;

 import org.apache.hadoop.hbase.filter.SubstringComparator;

 import org.apache.hadoop.hbase.util.Bytes; 

 public class TestSimplefilter {

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

         Configuration conf = HBaseConfiguration.create();

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

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

         HConnection conn = HConnectionManager.createConnection(conf);

         HTableInterface table = conn.getTable("testdata");

         Scan sc = new Scan();

         sc.setCacheBlocks(false);

         //行过滤器，判断"row1"与行的key是否相等

         //Filter filter = new RowFilter(CompareFilter.CompareOp.EQUAL,new BinaryComparator(Bytes.toBytes("row1")));

         //是否以"row"为前缀

         //Filter filter = new RowFilter(CompareFilter.CompareOp.EQUAL,new BinaryPrefixComparator(Bytes.toBytes("row")));

         //是否包含"row"

         //Filter filter = new RowFilter(CompareFilter.CompareOp.EQUAL,new SubstringComparator("row"));

         //列过滤器，与行类似

         Filter filter = new QualifierFilter(CompareFilter.CompareOp.EQUAL,new BinaryComparator(Bytes.toBytes("col1")));

         sc.setFilter(filter);

         ResultScanner rs = table.getScanner(sc);

         for(Result r : rs ){

             List<Cell> cells = r.listCells();

             for(Cell cell : cells){

                 String rowkey = new String(CellUtil.cloneRow(cell));

                 String family = new String(CellUtil.cloneFamily(cell));

                 String collumn = new String(CellUtil.cloneQualifier(cell));

                 String cvalue = new String(CellUtil.cloneValue(cell));

                 System.out.println("rowkey:" + rowkey + " family:" + family + " column:" + collumn +" value:" + cvalue);

             }

         }

         rs.close();

         table.close();

         conn.close();

     }

 }

使用filterlist

 package com.testdata;

 import java.io.IOException;

 import java.util.ArrayList;

 import java.util.List;

 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.client.HConnection;

 import org.apache.hadoop.hbase.client.HConnectionManager;

 import org.apache.hadoop.hbase.client.HTableInterface;

 import org.apache.hadoop.hbase.client.Result;

 import org.apache.hadoop.hbase.client.ResultScanner;

 import org.apache.hadoop.hbase.client.Scan;

 import org.apache.hadoop.hbase.filter.BinaryComparator;

 import org.apache.hadoop.hbase.filter.BinaryPrefixComparator;

 import org.apache.hadoop.hbase.filter.CompareFilter;

 import org.apache.hadoop.hbase.filter.Filter;

 import org.apache.hadoop.hbase.filter.FilterList;

 import org.apache.hadoop.hbase.filter.QualifierFilter;

 import org.apache.hadoop.hbase.filter.RegexStringComparator;

 import org.apache.hadoop.hbase.filter.RowFilter;

 import org.apache.hadoop.hbase.filter.SingleColumnValueFilter;

 import org.apache.hadoop.hbase.filter.SubstringComparator;

 import org.apache.hadoop.hbase.util.Bytes; 

 public class TestFilterList {

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

         Configuration conf = HBaseConfiguration.create();

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

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

         HConnection conn = HConnectionManager.createConnection(conf);

         HTableInterface table = conn.getTable("testdata");

         Scan sc = new Scan();

         Filter filter1 = new RowFilter(CompareFilter.CompareOp.EQUAL,new BinaryComparator(Bytes.toBytes("row2")));

         SingleColumnValueFilter filter2 = new SingleColumnValueFilter(Bytes.toBytes("cf"),Bytes.toBytes("col1"),CompareFilter.CompareOp.EQUAL,new BinaryPrefixComparator(Bytes.toBytes("B")));

         SingleColumnValueFilter filter3 = new SingleColumnValueFilter(Bytes.toBytes("cf"),Bytes.toBytes("col1"),CompareFilter.CompareOp.EQUAL,new RegexStringComparator("B|C"));

         filter2.setFilterIfMissing(true);

         filter3.setFilterIfMissing(true);

         //List<Filter> filters = new ArrayList<Filter>();

         //filters.add(filter1);

         //filters.add(filter2);

         //FilterList filterlist = new FilterList(filters);

         //也可以这样写,MUST_PASS_ALL标识满足所有的filter,当然也可以使用MUST_PASS_ONE，标识只需要满足一个

         FilterList filterlist = new FilterList(FilterList.Operator.MUST_PASS_ALL);

         filterlist.addFilter(filter1);

         filterlist.addFilter(filter2);

         filterlist.addFilter(filter3);

         sc.addColumn(Bytes.toBytes("cf"),Bytes.toBytes("col1"));

         sc.setFilter(filterlist);

         ResultScanner rs = table.getScanner(sc);

         for(Result r : rs ){

             List<Cell> cells = r.listCells();

             for(Cell cell : cells){

                 String rowkey = new String(CellUtil.cloneRow(cell));

                 String family = new String(CellUtil.cloneFamily(cell));

                 String collumn = new String(CellUtil.cloneQualifier(cell));

                 String cvalue = new String(CellUtil.cloneValue(cell));

                 System.out.println("rowkey:" + rowkey + " family:" + family + " column:" + collumn +" value:" + cvalue);

             }

         }

         rs.close();

         table.close();

         conn.close();

     }

 }

以上一组filter标识了这样的条件，即行的key必须为"row2"，列名必须为"col1"，值必须为"B"

结果参考：

如果没有 sc.addColumn(Bytes.toBytes("cf"),Bytes.toBytes("col1"));这一句，结果会是下面的样子

rowkey:row2 family:cf column:col1 value:B

rowkey:row2 family:cf column:colb value:U

问题出在 SingleColumnValueFilter filter2 = new SingleColumnValueFilter(Bytes.toBytes("cf"),Bytes.toBytes("col1"),CompareFilter.CompareOp.EQUAL,new BinaryPrefixComparator(Bytes.toBytes("B")));这一句，如果打印Bytes.toBytes("B")与Bytes.toBytes("U")，会发现都是以"B"开头的。即使换成BinaryComparator，也不会解决问题。

这里是值得注意的地方，搜索网络可以发现一样的结论，使用时务必使用sc.addColumn(Bytes.toBytes("cf"),Bytes.toBytes("col1"))类似的语句。

rowkey:row2 family:cf column:col1 value:B

相关文章