HBase过滤器

简要介绍

HBase中的过滤器类似于SQL中的where条件。过滤器可以在HBase中的多个维度上进行数据的筛选操作。筛选器筛选的数据能够细化到具体的一个存储单元格上（行键、列族、列限定符）

过滤器的参数

过滤器中至少需要使用两类参数：抽象的运算符和比较器

抽象的运算符：

运算符	含义
LESS	小于
LESS_OR_EQUAL	小于等于
EQUAL	等于
NOT_EQUAL	不等于
GREATER	大于
GREATER_OR_EQUAL	大于等于
NO_OP	无操作

比较器

用于处理具体的比较逻辑。例如：字节级的比较、字符串级的比较等

比较器	含义
BinaryComparator	二进制比较器。用于按字典顺序比较Byte数据值，采用Bytes.compareTo(Bytes[])进行比较
BinaryPrefixComparator	前缀二进制比较器。与二进制比较器不同的是：只比较前缀是否相同
NullComparator	空值比较器。判断给定的值是否为空
RegexStringComparator	正则比较器，仅支持EQUAL和NOT_EQUAL
SubstringComparator	字符串包含比较器。用于监测一个字符串是否存在于值中，并且不区分大小写

过滤案例

行键过滤器

package Filter;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.CompareOperator;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.BinaryComparator;
import org.apache.hadoop.hbase.filter.RowFilter;
import org.apache.hadoop.hbase.util.Bytes;

import java.io.IOException;

public class Rowkey {
    public static void main(String[] args) throws IOException {
        Configuration conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum","192.168.1.100:2181," +
                "192.168.1.101:2181,192.168.1.102:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        Table t1 = connection.getTable(TableName.valueOf("t1")); 
        // 创建一个查询指定表的数据
        Scan scan = new Scan();
        // 创建一个行键过滤器
        RowFilter filter = new RowFilter(CompareOperator.EQUAL, new BinaryComparator(Bytes.toBytes("row1")));
        scan.setFilter(filter);
        ResultScanner scanner = t1.getScanner(scan);
        // 实际生成中，会将查询之后的结果转换成map，添加到list集合中
        // 最后转换为JSON格式的数据返回给前端
    }
}

列族过滤器

```java
package Filter;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.CompareOperator;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.RegionTooBusyException;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.BinaryComparator;
import org.apache.hadoop.hbase.filter.FamilyFilter;
import org.apache.hadoop.hbase.util.Bytes;

import java.io.IOException;

public class Family {
    public static void main(String[] args) throws IOException {
        Configuration conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum","192.168.1.100:2181," +
                "192.168.1.101:2181,192.168.1.102:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        Table t1 = connection.getTable(TableName.valueOf("t1"));
        Scan scan = new Scan();
        FamilyFilter f1 = new FamilyFilter(CompareOperator.EQUAL, new BinaryComparator(Bytes.toBytes("f1")));
        scan.setFilter(f1);
        ResultScanner scanner = t1.getScanner(scan);

    }
}

列过滤器

package Filter;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.CompareOperator;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.BinaryComparator;
import org.apache.hadoop.hbase.filter.QualifierFilter;
import org.apache.hadoop.hbase.util.Bytes;

import java.io.IOException;

public class Qualifier {
    public static void main(String[] args) throws IOException {
        Configuration conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum","192.168.1.100:2181," +
                "192.168.1.101:2181,192.168.1.102:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        Table t1 = connection.getTable(TableName.valueOf("t1"));
        Scan scan = new Scan();
        QualifierFilter name = new QualifierFilter(CompareOperator.EQUAL, new BinaryComparator(Bytes.toBytes("name")));
        scan.setFilter(name);
        ResultScanner res = t1.getScanner(scan);


    }
}

值过滤器

package Filter;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.CompareOperator;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.SubstringComparator;
import org.apache.hadoop.hbase.filter.ValueFilter;

import java.io.IOException;

public class Value {
    public static void main(String[] args) throws IOException {
        Configuration conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum","192.168.1.100:2181," +
                "192.168.1.101:2181,192.168.1.102:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        Table t1 = connection.getTable(TableName.valueOf("t1"));
        Scan scan = new Scan();
        ValueFilter valueFilter = new ValueFilter(CompareOperator.EQUAL, new SubstringComparator("xiaoming"));
        scan.setFilter(valueFilter);
        ResultScanner res = t1.getScanner(scan);
    }
}

单列值过滤器

package Filter;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.CompareOperator;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.SingleColumnValueFilter;
import org.apache.hadoop.hbase.filter.SubstringComparator;
import org.apache.hadoop.hbase.util.Bytes;

import java.io.IOException;

public class SingleColumnValue {
    public static void main(String[] args) throws IOException {
        Configuration conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum","192.168.1.100:2181," +
                "192.168.1.101:2181,192.168.1.102:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        Table t1 = connection.getTable(TableName.valueOf("t1"));
        Scan scan = new Scan();
        SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter(Bytes.toBytes("f1"), Bytes.toBytes("name"),
                CompareOperator.NOT_EQUAL, new SubstringComparator("xiaoming"));
        // 如果name列不存在，则被过滤掉，设置为false，则不过滤
        singleColumnValueFilter.setFilterIfMissing(true);
        scan.setFilter(singleColumnValueFilter);
        ResultScanner res = t1.getScanner(scan);
    }
}

多条件过滤器

package Filter;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.CompareOperator;
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.Scan;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.filter.*;
import org.apache.hadoop.hbase.util.Bytes;

import java.io.IOException;

public class MulConditionFilter {
    public static void main(String[] args) throws IOException {
        Configuration conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum", "192.168.1.100:2181," +
                "192.168.1.101:2181,192.168.1.102:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        Table t1 = connection.getTable(TableName.valueOf("t1"));
        Scan scan = new Scan();
        SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter(Bytes.toBytes("f1"), Bytes.toBytes("name"),
                CompareOperator.NOT_EQUAL, new SubstringComparator("xiaoming"));
        // 如果name列不存在，则被过滤掉，设置为false，则不过滤
        singleColumnValueFilter.setFilterIfMissing(true);
        FamilyFilter familyFilter = new FamilyFilter(CompareOperator.EQUAL, new BinaryComparator(Bytes.toBytes("f1")));

        // 创建过滤器集合对象
        FilterList filterList = new FilterList();
        // 添加多个过滤器到过滤器集合对象中
        filterList.addFilter(singleColumnValueFilter);
        filterList.addFilter(familyFilter);

        // 设置查询过滤器
        scan.setFilter(filterList);
    }
}