Hbase过滤器（三）：附加过滤器API

 

目录

一：跳转过滤器（SkipFilter）

跳转过滤器包装了一个用户提供的过滤器，当被包装的过滤器遇到一个需要过滤的KeyValue实例时，用户可以拓展并过滤到整行数据。换言之，当过滤器发现某一行中的一列被过滤时，那么整行都会被过滤掉。案例将SkipFilter和ValueFilter组合起来获取不包含空列值的行，同时过滤掉不符合条件的的行。

package appendFilter;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.*;
import org.apache.hadoop.hbase.util.Bytes;
import org.junit.Test;

import java.io.IOException;

public class skipFilter {

    private Configuration configuration = null;
    private Connection connection = null;
    @Test
    public void skipFilter() throws IOException {
        System.out.println("begin");
        configuration = HBaseConfiguration.create();
        connection = ConnectionFactory.createConnection(configuration);
        Table table = connection.getTable(TableName.valueOf("ns1:t1"));
        Filter filter = new ValueFilter(CompareFilter.CompareOp.NOT_EQUAL,new BinaryComparator(Bytes.toBytes("ccc")));
        Scan scan = new Scan();
        scan.setFilter(filter);
        ResultScanner resultScanner = table.getScanner(scan);
        for(Result result:resultScanner){
            for (KeyValue kv : result.raw()) {
                System.out.println("KV: "+kv+",value: "+Bytes.toString(kv.getValue()));
            }
        }
        resultScanner.close();

        System.out.println("-------------------------------------------------");
        Filter filter1 = new SkipFilter(filter);
        Scan scan1 = new Scan();
        scan1.setFilter(filter1);
        ResultScanner resultScanner1 = table.getScanner(scan1);
        for(Result result1:resultScanner1){
            for (KeyValue kv : result1.raw()) {
                System.out.println("KV: "+kv+",value: "+Bytes.toString(kv.getValue()));
            }
        }
        resultScanner1.close();
        table.close();
        System.out.println("end");
    }
}

结果显示：

二：全匹配过滤器（WhileMatchFilter）

全匹配过滤器和跳转过滤器相似，不过当一条数据被过滤掉时，它就会直接放弃这次扫描操作

package appendFilter;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.*;
import org.apache.hadoop.hbase.util.Bytes;
import org.junit.Test;

import java.io.IOException;

public class whileMatchFilter {
    private Configuration configuration = null;
    private Connection connection = null;
    @Test
    public void whileMatchFilter() throws IOException {
        System.out.println("begin");
        configuration = HBaseConfiguration.create();
        connection = ConnectionFactory.createConnection(configuration);
        Table table = connection.getTable(TableName.valueOf("ns1:t1"));
        Filter filter = new RowFilter(CompareFilter.CompareOp.NOT_EQUAL,new BinaryComparator(Bytes.toBytes("row3")));
        Scan scan = new Scan();
        scan.setFilter(filter);
        ResultScanner resultScanner = table.getScanner(scan);
        for(Result result:resultScanner){
            for (KeyValue kv : result.raw()) {
                System.out.println("KV: "+kv+",value: "+Bytes.toString(kv.getValue()));
            }
        }
        resultScanner.close();

        System.out.println("-------------------------------------------------");
        Filter filter1 = new WhileMatchFilter(filter);
        Scan scan1 = new Scan();
        scan1.setFilter(filter1);
        ResultScanner resultScanner1 = table.getScanner(scan1);
        for(Result result1:resultScanner1){
            for (KeyValue kv : result1.raw()) {
                System.out.println("KV: "+kv+",value: "+Bytes.toString(kv.getValue()));
            }
        }
        resultScanner1.close();
        table.close();
        System.out.println("end");
    }
}

结果展示：