Hbase布隆过滤器

难以触及的高度2024-06-12 18:02

Hbase布隆过滤器

小白的Hbase学习笔记

目录

Hbase布隆过滤器

[1.过滤表中所有Value中 >23 的内容](#1.过滤表中所有Value中 >23 的内容)

2.获取表中age列大于23的所有RowKey值（1的改进）

3.比较以某个Value值开头的列

[4.按前缀 准确值 后缀查找](#4.按前缀 准确值 后缀查找)

5.获取RowKey中包含15001000的所有RowKey（速度更快）

6.过滤列族名称以2结尾的RowKey数据

[7.获取列名称以 na 开头的所有RowKey](#7.获取列名称以 na 开头的所有RowKey)

[8.对学生表中的信息进行过滤 条件有：1.所有性别为男性 2.所有文科班 3.年龄大于23岁](#8.对学生表中的信息进行过滤 条件有：1.所有性别为男性 2.所有文科班 3.年龄大于23岁)

1.过滤表中所有Value中 >23 的内容

java 复制代码 
package com.shujia.comparator;

import org.apache.hadoop.conf.Configuration;
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.CompareFilter;
import org.apache.hadoop.hbase.filter.ValueFilter;
import org.apache.hadoop.hbase.util.Bytes;

import java.io.IOException;
//过滤器

/**
 * 需求：
 *      过滤表中所有Value中 >23 的内容
 */
public class Code01ComparatorValue {
    public static void main(String[] args) throws IOException {

        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum","node1,node2,master");
        Connection conn = ConnectionFactory.createConnection(conf);

        Table table = conn.getTable(TableName.valueOf("jan:tbl1"));
        Scan scan=new Scan();
        /**
         * (CompareOp valueCompareOp, ByteArrayComparable valueComparator)
         */
        //创建字节比较器 参数传入具体比较的值
        BinaryComparator binaryComparator = new BinaryComparator(Bytes.toBytes("23"));

        //该过滤器是针对于当前表中所有的值进行过滤 只要满足则返回一行 并且 如果不满足返回NULL
        //put 'jan:tbl1','1001','info:name','25'

        ValueFilter filter = new ValueFilter(CompareFilter.CompareOp.GREATER, binaryComparator);
        //设置过滤器
        scan.setFilter(filter);

        //获取扫描器对象
        ResultScanner scanner = table.getScanner(scan);
        for (Result result : scanner) {
            String rowKey = Bytes.toString(result.getRow());
            String name = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("name")));
            String age = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("age")));
            String gender = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("gender")));
            String clazz = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("clazz")));
            System.out.println(rowKey+","+name+","+age+","+gender+","+clazz);
        }

        table.close();
        conn.close();

    }
}

2.获取表中age列大于23的所有RowKey值（1的改进）

java 复制代码 
package com.shujia.comparator;

//需求：获取表中age列大于23的所有RowKey值
//01的改进代码
import org.apache.hadoop.conf.Configuration;
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.CompareFilter;
import org.apache.hadoop.hbase.filter.SingleColumnValueFilter;
import org.apache.hadoop.hbase.filter.ValueFilter;
import org.apache.hadoop.hbase.util.Bytes;

import java.io.IOException;

public class Code02ComparatorSingleColumns {
    public static void main(String[] args) throws IOException {
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum","node1,node2,master");
        Connection conn = ConnectionFactory.createConnection(conf);

        Table table = conn.getTable(TableName.valueOf("jan:tbl1"));
        Scan scan=new Scan();
        /**
         * 单列过滤器：
         *      用于过滤单列值
         *      返回的数据是满足条件的所有RowKey
         *注意：
         *      如果一条RowKey用于比较的列不存在 那么该RowKey也会被返回
         */
        SingleColumnValueFilter filter = new SingleColumnValueFilter(
                Bytes.toBytes("info"),
                Bytes.toBytes("age"),
                CompareFilter.CompareOp.GREATER,
                Bytes.toBytes(23));
        //设置过滤器
        scan.setFilter(filter);

        //获取扫描器对象
        ResultScanner scanner = table.getScanner(scan);
        for (Result result : scanner) {
            String rowKey = Bytes.toString(result.getRow());
            String name = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("name")));
            String age = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("age")));
            String gender = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("gender")));
            String clazz = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("clazz")));
            System.out.println(rowKey+","+name+","+age+","+gender+","+clazz);
        }

        table.close();
        conn.close();

    }
}

3.比较以某个Value值开头的列

java 复制代码 
package com.shujia.comparator;

//该比较器用于比较以某个Value值开头的列
import org.apache.hadoop.conf.Configuration;
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 java.io.IOException;

public class Code03ComparatorSingleColumns {
    public static void main(String[] args) throws IOException {
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum","node1,node2,master");
        Connection conn = ConnectionFactory.createConnection(conf);

        Table table = conn.getTable(TableName.valueOf("jan:tbl1"));
        Scan scan=new Scan();
        /**
         * 单列过滤器：
         *      用于过滤单列值
         *      返回的数据是满足条件的所有RowKey
         *注意：
         *      如果一条RowKey用于比较的列不存在 那么该RowKey也会被返回
         */
        SingleColumnValueFilter filter = new SingleColumnValueFilter(
                Bytes.toBytes("info"),
                Bytes.toBytes("clazz"),
                CompareFilter.CompareOp.EQUAL,
                //该比较器用于比较以某个Value值开头的列
                new BinaryPrefixComparator(Bytes.toBytes("文科")));//二进制前缀比较器
                //new BinaryPrefixComparator(Bytes.toBytes("文科六")));


        //设置过滤器
        scan.setFilter(filter);

        //获取扫描器对象
        ResultScanner scanner = table.getScanner(scan);
        for (Result result : scanner) {
            String rowKey = Bytes.toString(result.getRow());
            String name = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("name")));
            String age = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("age")));
            String gender = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("gender")));
            String clazz = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("clazz")));
            System.out.println(rowKey+","+name+","+age+","+gender+","+clazz);
        }

        table.close();
        conn.close();

    }
}

4.按前缀 准确值 后缀查找

java 复制代码 
package com.shujia.comparator;

//需求：获取RowKey中包含15001000的所有RowKey

import org.apache.hadoop.conf.Configuration;
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 java.io.IOException;

public class Code04ComparatorRowKey {
    public static void main(String[] args) throws IOException {
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum","node1,node2,master");
        Connection conn = ConnectionFactory.createConnection(conf);

        Table table = conn.getTable(TableName.valueOf("jan:tbl1"));
        Scan scan=new Scan();

        RowFilter filter = new RowFilter(
                CompareFilter.CompareOp.EQUAL
                //RowKey中的值以15001000为开头的
                , new BinaryPrefixComparator(Bytes.toBytes("15001000"))
                //如果我们想按照准确的信息查找
                //, new BinaryComparator(Bytes.toBytes("1500100001"))

                //通过RegexStringComparator的正则表达式过滤以98为结尾的内容
                //,new RegexStringComparator(".*02$")
        );

        //设置过滤器
        scan.setFilter(filter);

        //获取扫描器对象
        ResultScanner scanner = table.getScanner(scan);
        for (Result result : scanner) {
            String rowKey = Bytes.toString(result.getRow());
            String name = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("name")));
            String age = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("age")));
            String gender = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("gender")));
            String clazz = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("clazz")));
            System.out.println(rowKey+","+name+","+age+","+gender+","+clazz);
        }

        table.close();
        conn.close();

    }
}

5.获取RowKey中包含15001000的所有RowKey（速度更快）

java 复制代码 
package com.shujia.comparator;

//需求：获取RowKey中包含15001000的所有RowKey

import org.apache.hadoop.conf.Configuration;
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 java.io.IOException;

public class Code05ComparatorPrefix {
    public static void main(String[] args) throws IOException {
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum","node1,node2,master");
        Connection conn = ConnectionFactory.createConnection(conf);

        Table table = conn.getTable(TableName.valueOf("jan:tbl1"));
        Scan scan=new Scan();

        /**
         *相比于在RowFilter中添加 BinaryComparator(Bytes.toBytes("15001000"))
         * PrefixFilter 执行速度更快 效率更高
         */

        PrefixFilter filter = new PrefixFilter(Bytes.toBytes("15001000"));
        //设置过滤器
        scan.setFilter(filter);

        //获取扫描器对象
        ResultScanner scanner = table.getScanner(scan);
        for (Result result : scanner) {
            String rowKey = Bytes.toString(result.getRow());
            String name = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("name")));
            String age = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("age")));
            String gender = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("gender")));
            String clazz = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("clazz")));
            System.out.println(rowKey+","+name+","+age+","+gender+","+clazz);
        }

        table.close();
        conn.close();

    }
}

6.过滤列族名称以2结尾的RowKey数据

java 复制代码 
package com.shujia.comparator;

//需求：获取RowKey中包含15001000的所有RowKey

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
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 java.io.IOException;
import java.util.List;

//需求：
//      过滤列族名称以2结尾的RowKey数据

public class Code06ComparatorFamily {
    public static void main(String[] args) throws IOException {
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum","node1,node2,master");
        Connection conn = ConnectionFactory.createConnection(conf);

        Table table = conn.getTable(TableName.valueOf("jan:tbl1"));
        Scan scan=new Scan();

        FamilyFilter filter = new FamilyFilter(
                CompareFilter.CompareOp.EQUAL
                , new RegexStringComparator(".*2$")
        );
        //desc 'jan:tbl1'
        //添加列族 alter 'jan:tbl1',{NAME => 'info2',VERSIONS => 1}
        //put 'jan:tbl1','1001','info2:name','zhangsan'
        //put 'jan:tbl1','1002','info2:name','zhangsan'

        //设置过滤器
        scan.setFilter(filter);

        //获取扫描器对象
        ResultScanner scanner = table.getScanner(scan);

        for (Result result : scanner) {
            List<Cell> cells = result.listCells();
            String rowKey = Bytes.toString(result.getRow());
            for (Cell cell : cells) {
                String family = Bytes.toString(CellUtil.cloneFamily(cell));
                String qualifier = Bytes.toString(CellUtil.cloneQualifier(cell));
                String value = Bytes.toString(CellUtil.cloneValue(cell));
                System.out.println(rowKey+","+family+","+qualifier+","+value);
            }

        }

        table.close();
        conn.close();

    }
}

7.获取列名称以 na 开头的所有RowKey

java 复制代码 
package com.shujia.comparator;

//需求：获取RowKey中包含15001000的所有RowKey

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
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 java.io.IOException;
import java.util.List;

//需求：
//      获取列名称以 na 开头的所有RowKey

public class Code07ComparatorColumns {
    public static void main(String[] args) throws IOException {
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum","node1,node2,master");
        Connection conn = ConnectionFactory.createConnection(conf);

        Table table = conn.getTable(TableName.valueOf("jan:tbl1"));
        Scan scan=new Scan();

        ColumnPrefixFilter filter = new ColumnPrefixFilter(Bytes.toBytes("na"));

        //设置过滤器
        scan.setFilter(filter);

        //获取扫描器对象
        ResultScanner scanner = table.getScanner(scan);

        for (Result result : scanner) {
            List<Cell> cells = result.listCells();
            String rowKey = Bytes.toString(result.getRow());
            for (Cell cell : cells) {
                String family = Bytes.toString(CellUtil.cloneFamily(cell));
                String qualifier = Bytes.toString(CellUtil.cloneQualifier(cell));
                String value = Bytes.toString(CellUtil.cloneValue(cell));
                System.out.println(rowKey+","+family+","+qualifier+","+value);
            }

        }

        table.close();
        conn.close();

    }
}

8.对学生表中的信息进行过滤 条件有：1.所有性别为男性 2.所有文科班 3.年龄大于23岁

java 复制代码 
package com.shujia.comparator;

//需求：
//      对学生表中的信息进行过滤 条件有：1.所有性别为男性 2.所有文科班 3.年龄大于23岁

import com.sun.xml.internal.bind.v2.runtime.unmarshaller.XsiNilLoader;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
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 java.io.IOException;
import java.util.ArrayList;
import java.util.List;

//需求：
//      获取列名称以 na 开头的所有RowKey

public class Code08Comparator {
    public static void main(String[] args) throws IOException {
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum","node1,node2,master");
        Connection conn = ConnectionFactory.createConnection(conf);

        Table table = conn.getTable(TableName.valueOf("jan:tbl1"));
        Scan scan=new Scan();

        //1.所有性别为男性
        SingleColumnValueFilter filter1 = new SingleColumnValueFilter(
                Bytes.toBytes("info")
                , Bytes.toBytes("gender")
                , CompareFilter.CompareOp.EQUAL
                , new BinaryPrefixComparator(Bytes.toBytes("男"))
        );
        //2.所有文科班
        SingleColumnValueFilter filter2 = new SingleColumnValueFilter(
                Bytes.toBytes("info")
                , Bytes.toBytes("clazz")
                , CompareFilter.CompareOp.EQUAL
                , new BinaryPrefixComparator(Bytes.toBytes("文科"))
        );
        //3.年龄大于23岁
        SingleColumnValueFilter filter3 = new SingleColumnValueFilter(
                Bytes.toBytes("info")
                , Bytes.toBytes("age")
                , CompareFilter.CompareOp.GREATER
                , new BinaryPrefixComparator(Bytes.toBytes("23"))
        );

        List<Filter> filters = new ArrayList<>();
        filters.add(filter1);
        filters.add(filter2);
        filters.add(filter3);


        FilterList filter = new FilterList(filters);

        //设置过滤器
        scan.setFilter(filter);

        //获取扫描器对象
        ResultScanner scanner = table.getScanner(scan);

        for (Result result : scanner) {
                String rowKey = Bytes.toString(result.getRow());
                String name = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("name")));
                String age = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("age")));
                String gender = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("gender")));
                String clazz = Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("clazz")));
                System.out.println(rowKey+","+name+","+age+","+gender+","+clazz);

        }

        table.close();
        conn.close();

    }
}
相关推荐
廿一夏4 小时前
MySql存储引擎与索引
数据库·sql·mysql
商业模式源码开发4 小时前
实体门店低获客成本增长案例：3 人转介绍模型 + 消费返还机制落地分析
大数据·商业模式·私域流量
元拓数智6 小时前
智能分析落地卡壳？先补好「数据关系+语义治理」这层技术基建
大数据·分布式·ai·spark·数据关系·语义治理
lzhdim6 小时前
SQL 入门 15：SQL 事务：从 ACID 到四种常见的并发问题
数据库·sql
瀚高PG实验室7 小时前
瀚高企业版V9.1.1在pg_restore还原备份文件时提示extract函数语法问题
数据库·瀚高数据库
TDengine （老段）7 小时前
TDengine Tag 设计哲学与 Schema 变更机制
大数据·数据库·物联网·时序数据库·iot·tdengine·涛思数据
sxgzzn7 小时前
新能源场站数智化转型：基于数字孪生与AI的智慧运维管理平台解析
大数据·运维·人工智能
YOU OU8 小时前
Spring IoC&DI
java·数据库·spring
Muscleheng9 小时前
Navicat连接postgresql时出现‘datlastsysoid does not exist‘报错
数据库·postgresql
清平乐的技术专栏9 小时前
【Flink学习】（二）Flink 本地环境搭建，运行第一个入门程序
大数据·flink
热门推荐
01GitHub 镜像站点02Codex 接入 DeepSeek API 完整配置文档03装上就回不去了：CodeGraph 让 AI 编程效率飙升 92%，它到底做了什么？04【踩坑记录 | 第一篇】微软商店无法使用时，如何手动安装 OpenAI Codex？附`.msix`文件系统错误解决方法05裂开！ChatGPT 居然开始要手机号验证，附详细解决方法06CC-Switch & Claude 基于 Linux 服务器安装使用指南07几个好用的ip纯净度检测网站08【AI】2026 年具身智能模型和世界模型总结09用了半年 OpenRouter，我换到了 Ofox.ai — 两个 AI API 聚合平台的真实对比10codex app每次打开重连5次Reconnecting问题解决