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
Acrelhuang1 分钟前
安科瑞5G基站直流叠光监控系统-安科瑞黄安南
大数据·数据库·数据仓库·物联网
皓74110 分钟前
服饰电商行业知识管理的创新实践与知识中台的重要性
大数据·人工智能·科技·数据分析·零售
Mephisto.java12 分钟前
【大数据学习 | kafka高级部分】kafka的kraft集群
大数据·sql·oracle·kafka·json·hbase
Mephisto.java14 分钟前
【大数据学习 | kafka高级部分】kafka的文件存储原理
大数据·sql·oracle·kafka·json
十叶知秋44 分钟前
【jmeter】jmeter的线程组功能的详细介绍
数据库·jmeter·性能测试
ycsdn101 小时前
Caused by: org.apache.flink.api.common.io.ParseException: Row too short:
大数据·flink
DolphinScheduler社区2 小时前
Apache DolphinScheduler + OceanBase，搭建分布式大数据调度平台的实践
大数据
瓜牛_gn2 小时前
mysql特性
数据库·mysql
时差9533 小时前
MapReduce 的 Shuffle 过程
大数据·mapreduce
奶糖趣多多3 小时前
Redis知识点
数据库·redis·缓存
热门推荐
01【HarmonyOS】HUAWEI DevEco Studio 下载地址汇总02(欧拉)openEuler系统添加网卡文件配置流程、(欧拉)openEuler系统手动配置ipv6地址流程、(欧拉)openEuler系统网络管理说明03组基轨迹建模 GBTM的介绍与实现（Stata 或 R）04【AIGC】重塑未来的科技巨轮05全面解析：构建基于深度学习的安全帽检测系统（UI界面+YOLO代码+数据集）06【经验分享】Ubuntu22.04安装微信(linux官方版)07基于YOLOv10深度学习的CT扫描图像肾结石智能检测系统【python源码+Pyqt5界面+数据集+训练代码】深度学习实战、目标检测08Ubuntu 20.04使用Livox mid 360 测试 FAST_LIO09RAG 实践- Ollama+RagFlow 部署本地知识库10红米手机使用google play