HBase学习——4.HBase过滤器

其他 2019-04-27 20:14:40 阅读次数: 0

1.过滤器

基础API中的查询操作在面对大量数据的时候是非常苍白的，这里Hbase提供了高级的查询方法：Filter。Filter可以根据簇、列、版本等更多的条件来对数据进行过滤，基于Hbase本身提供的三维有序（主键有序、列有序、版本有序），这些Filter可以高效的完成查询过滤的任务。带有Filter条件的RPC查询请求会把Filter分发到各个RegionServer，是一个服务器端（Server-side）的过滤器，这样也可以降低网络传输的压力。

要完成一个过滤的操作，至少需要两个参数。一个是抽象的操作符，Hbase提供了枚举类型的变量来表示这些抽象的操作符：LESS/LESS_OR_EQUAL/EQUAL/NOT_EUQAL等；另外一个就是具体的比较器（Comparator），代表具体的比较逻辑，如果可以提高字节级的比较、字符串级的比较等。有了这两个参数，我们就可以清晰的定义筛选的条件，过滤数据。

1.1 抽象操作符（比较运算符）

LESS <

LESS_OR_EQUAL <=

EQUAL =

NOT_EQUAL <>

GREATER_OR_EQUAL >=

GREATER >

NO_OP 排除所有

1.2 比较器（指定比较机制）

BinaryComparator 按字节索引顺序比较指定字节数组，采用 Bytes.compareTo(byte[])

BinaryPrefixComparator 跟前面相同，只是比较左端的数据是否相同

NullComparator 判断给定的是否为空

BitComparator 按位比较

RegexStringComparator 提供一个正则的比较器，仅支持 EQUAL 和非 EQUAL

SubstringComparator 判断提供的子串是否出现在 value 中

2.HBase过滤器的分类

2.1 比较过滤器

2.1.1 行键过滤器 RowFilter

Filter rowFilter = new RowFilter(CompareOp.GREATER, new BinaryComparator("95007".getBytes()));

scan.setFilter(rowFilter);

public class HbaseFilterTest {

    private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";

    private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";

    private static Connection conn = null;

    private static Admin admin = null;

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

        Configuration conf = HBaseConfiguration.create();

        conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);

        conn = ConnectionFactory.createConnection(conf);

        admin = conn.getAdmin();

        Table table = conn.getTable(TableName.valueOf("student"));

        Scan scan = new Scan();

        Filter rowFilter = new RowFilter(CompareOp.GREATER, new BinaryComparator("95007".getBytes()));

        scan.setFilter(rowFilter);

        ResultScanner resultScanner = table.getScanner(scan);

        for(Result result : resultScanner) {

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

            for(Cell cell : cells) {

                System.out.println(cell);

            }

        }

    }

}

运行结果部分截图


 

2.1.2 列簇过滤器 FamilyFilter

Filter familyFilter = new FamilyFilter(CompareOp.EQUAL, new BinaryComparator("info".getBytes()));

scan.setFilter(familyFilter);

public class HbaseFilterTest {

    private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";

    private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";

    private static Connection conn = null;

    private static Admin admin = null;

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

        Configuration conf = HBaseConfiguration.create();

        conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);

        conn = ConnectionFactory.createConnection(conf);

        admin = conn.getAdmin();

        Table table = conn.getTable(TableName.valueOf("student"));

        Scan scan = new Scan();

        Filter familyFilter = new FamilyFilter(CompareOp.EQUAL, new BinaryComparator("info".getBytes()));

        scan.setFilter(familyFilter);

        ResultScanner resultScanner = table.getScanner(scan);

        for(Result result : resultScanner) {

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

            for(Cell cell : cells) {

                System.out.println(cell);

            }

        }

    }

}


 

2.1.3 列过滤器 QualifierFilter

Filter qualifierFilter = new QualifierFilter(CompareOp.EQUAL, new BinaryComparator("name".getBytes()));

scan.setFilter(qualifierFilter);

public class HbaseFilterTest {

    private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";

    private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";

    private static Connection conn = null;

    private static Admin admin = null;

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

        Configuration conf = HBaseConfiguration.create();

        conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);

        conn = ConnectionFactory.createConnection(conf);

        admin = conn.getAdmin();

        Table table = conn.getTable(TableName.valueOf("student"));

        Scan scan = new Scan();

        Filter qualifierFilter = new QualifierFilter(CompareOp.EQUAL, new BinaryComparator("name".getBytes()));

        scan.setFilter(qualifierFilter);

        ResultScanner resultScanner = table.getScanner(scan);

        for(Result result : resultScanner) {

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

            for(Cell cell : cells) {

                System.out.println(cell);

            }

        }

    }

}


 

2.1.4 值过滤器 ValueFilter

Filter valueFilter = new ValueFilter(CompareOp.EQUAL, new SubstringComparator("男"));

scan.setFilter(valueFilter);

public class HbaseFilterTest {

    private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";

    private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";

    private static Connection conn = null;

    private static Admin admin = null;

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

        Configuration conf = HBaseConfiguration.create();

        conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);

        conn = ConnectionFactory.createConnection(conf);

        admin = conn.getAdmin();

        Table table = conn.getTable(TableName.valueOf("student"));

        Scan scan = new Scan();

        Filter valueFilter = new ValueFilter(CompareOp.EQUAL, new SubstringComparator("男"));

        scan.setFilter(valueFilter);

        ResultScanner resultScanner = table.getScanner(scan);

        for(Result result : resultScanner) {

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

            for(Cell cell : cells) {

                System.out.println(cell);

            }

        }

    }

}


 

2.1.5 时间戳过滤器 TimestampsFilter

List<Long> list = new ArrayList<>();

list.add(1522469029503l);

TimestampsFilter timestampsFilter = new TimestampsFilter(list);

scan.setFilter(timestampsFilter);

public class HbaseFilterTest {

    private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";

    private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";

    private static Connection conn = null;

    private static Admin admin = null;

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

        Configuration conf = HBaseConfiguration.create();

        conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);

        conn = ConnectionFactory.createConnection(conf);

        admin = conn.getAdmin();

        Table table = conn.getTable(TableName.valueOf("student"));

        Scan scan = new Scan();

        List<Long> list = new ArrayList<>();

        list.add(1522469029503l);

        TimestampsFilter timestampsFilter = new TimestampsFilter(list);

        scan.setFilter(timestampsFilter);

        ResultScanner resultScanner = table.getScanner(scan);

        for(Result result : resultScanner) {

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

            for(Cell cell : cells) {

                System.out.println(Bytes.toString(cell.getRow()) + "\t" + Bytes.toString(cell.getFamily()) + "\t" + Bytes.toString(cell.getQualifier())

                + "\t" + Bytes.toString(cell.getValue()) + "\t" + cell.getTimestamp());

            }

        }

    }

}


 

2.2 专用过滤器

2.2.1 单列值过滤器 SingleColumnValueFilter

会返回满足条件的整行

SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter(

                "info".getBytes(), //列簇

                "name".getBytes(), //列

                CompareOp.EQUAL,

                new SubstringComparator("刘晨"));

//如果不设置为 true，则那些不包含指定 column 的行也会返回

singleColumnValueFilter.setFilterIfMissing(true);

scan.setFilter(singleColumnValueFilter);

public class HbaseFilterTest2 {

    private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";

    private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";

    private static Connection conn = null;

    private static Admin admin = null;

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

        Configuration conf = HBaseConfiguration.create();

        conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);

        conn = ConnectionFactory.createConnection(conf);

        admin = conn.getAdmin();

        Table table = conn.getTable(TableName.valueOf("student"));

        Scan scan = new Scan();

        SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter(

                "info".getBytes(),

                "name".getBytes(),

                CompareOp.EQUAL,

                new SubstringComparator("刘晨"));

        singleColumnValueFilter.setFilterIfMissing(true);

        scan.setFilter(singleColumnValueFilter);

        ResultScanner resultScanner = table.getScanner(scan);

        for(Result result : resultScanner) {

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

            for(Cell cell : cells) {

                System.out.println(Bytes.toString(cell.getRow()) + "\t" + Bytes.toString(cell.getFamily()) + "\t" + Bytes.toString(cell.getQualifier())

                + "\t" + Bytes.toString(cell.getValue()) + "\t" + cell.getTimestamp());

            }

        }

    }

}


 

2.2.2 单列值排除器 SingleColumnValueExcludeFilter

SingleColumnValueExcludeFilter singleColumnValueExcludeFilter = new SingleColumnValueExcludeFilter(

                "info".getBytes(),

                "name".getBytes(),

                CompareOp.EQUAL,

                new SubstringComparator("刘晨"));

singleColumnValueExcludeFilter.setFilterIfMissing(true);

scan.setFilter(singleColumnValueExcludeFilter);

public class HbaseFilterTest2 {

    private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";

    private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";

    private static Connection conn = null;

    private static Admin admin = null;

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

        Configuration conf = HBaseConfiguration.create();

        conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);

        conn = ConnectionFactory.createConnection(conf);

        admin = conn.getAdmin();

        Table table = conn.getTable(TableName.valueOf("student"));

        Scan scan = new Scan();

        SingleColumnValueExcludeFilter singleColumnValueExcludeFilter = new SingleColumnValueExcludeFilter(

                "info".getBytes(),

                "name".getBytes(),

                CompareOp.EQUAL,

                new SubstringComparator("刘晨"));

        singleColumnValueExcludeFilter.setFilterIfMissing(true);

        scan.setFilter(singleColumnValueExcludeFilter);

        ResultScanner resultScanner = table.getScanner(scan);

        for(Result result : resultScanner) {

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

            for(Cell cell : cells) {

                System.out.println(Bytes.toString(cell.getRow()) + "\t" + Bytes.toString(cell.getFamily()) + "\t" + Bytes.toString(cell.getQualifier())

                + "\t" + Bytes.toString(cell.getValue()) + "\t" + cell.getTimestamp());

            }

        }

    }

}


 

2.2.3 前缀过滤器 PrefixFilter----针对行键

PrefixFilter prefixFilter = new PrefixFilter("9501".getBytes());

scan.setFilter(prefixFilter);

public class HbaseFilterTest2 {

    private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";

    private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";

    private static Connection conn = null;

    private static Admin admin = null;

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

        Configuration conf = HBaseConfiguration.create();

        conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);

        conn = ConnectionFactory.createConnection(conf);

        admin = conn.getAdmin();

        Table table = conn.getTable(TableName.valueOf("student"));

        Scan scan = new Scan();

        PrefixFilter prefixFilter = new PrefixFilter("9501".getBytes());

        scan.setFilter(prefixFilter);

        ResultScanner resultScanner = table.getScanner(scan);

        for(Result result : resultScanner) {

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

            for(Cell cell : cells) {

                System.out.println(Bytes.toString(cell.getRow()) + "\t" + Bytes.toString(cell.getFamily()) + "\t" + Bytes.toString(cell.getQualifier())

                + "\t" + Bytes.toString(cell.getValue()) + "\t" + cell.getTimestamp());

            }

        }

    }

}


 

2.2.4 列前缀过滤器 ColumnPrefixFilter

ColumnPrefixFilter columnPrefixFilter = new ColumnPrefixFilter("name".getBytes());

scan.setFilter(columnPrefixFilter);

public class HbaseFilterTest2 {

    private static final String ZK_CONNECT_KEY = "hbase.zookeeper.quorum";

    private static final String ZK_CONNECT_VALUE = "hadoop1:2181,hadoop2:2181,hadoop3:2181";

    private static Connection conn = null;

    private static Admin admin = null;

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

        Configuration conf = HBaseConfiguration.create();

        conf.set(ZK_CONNECT_KEY, ZK_CONNECT_VALUE);

        conn = ConnectionFactory.createConnection(conf);

        admin = conn.getAdmin();

        Table table = conn.getTable(TableName.valueOf("student"));

        Scan scan = new Scan();

        ColumnPrefixFilter columnPrefixFilter = new ColumnPrefixFilter("name".getBytes());

        scan.setFilter(columnPrefixFilter);

        ResultScanner resultScanner = table.getScanner(scan);

        for(Result result : resultScanner) {

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

            for(Cell cell : cells) {

                System.out.println(Bytes.toString(cell.getRow()) + "\t" + Bytes.toString(cell.getFamily()) + "\t" + Bytes.toString(cell.getQualifier())

                + "\t" + Bytes.toString(cell.getValue()) + "\t" + cell.getTimestamp());

            }

        }

    }

}


 

 

猜你喜欢

转载自www.cnblogs.com/importbigdata/p/10779886.html
今日推荐
《美国对全球网络空间安全与发展的威胁和破坏》报告发布
火速冲上 GitHub 热榜 —— 开源编程语言、框架哪有这么可爱？
北京人形机器人创新中心发布全球首个纯电驱拟人奔跑的全尺寸人形机器人“天工”
LFOSSA 源来如此公开课 | 掌握云原生未来：CNCF 认证全面攻略与备考秘籍
周排行
循环神经网络（rnn）讲解
Tigao教程四：单独的关节运动
金蝶K3WISE15.0-注册套打教程
如何在Mac上配置Kubernetes
Android应用结束自身进程的方法
SpringMVC学习 十三 拦截器栈
中国驻洛杉矶总领馆举行新春招待会
HttpClient get post 发送
11 - three.js 笔记 - 绘制三维字体模型
Mysql递归获取某个父节点下面的所有子节点和子节点上的所有父节点
每日归档
更多
2024-05-01(4)
2024-04-30(1)
2024-04-29(40)
2024-04-28(0)
2024-04-27(56)
2024-04-26(39)
2024-04-25(22)
2024-04-24(36)
2024-04-23(26)
2024-04-22(39)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022