Hbase_java实现过滤器查询

最新推荐文章于 2021-12-08 21:13:04 发布

_WeiA

最新推荐文章于 2021-12-08 21:13:04 发布

阅读量656

点赞数

分类专栏： Hbase 文章标签： hbase 过滤器

本文链接：https://blog.csdn.net/weixin_44449054/article/details/114031941

版权

Hbase 专栏收录该内容

15 篇文章 1 订阅

订阅专栏

标题

1.简述

分类： 比较过滤器，专用过滤器
作用： 在服务端判断数据是否满足条件，然后只将满足条件的数据返回给客户端
hbase过滤器的比较运算符：

LESS  <
LESS_OR_EQUAL <=
EQUAL =
NOT_EQUAL <>
GREATER_OR_EQUAL >=
GREATER >
NO_OP 排除所有

Hbase过滤器的比较器(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.比较过滤器

准备工作：

    private static Connection connection;
    private static Table table;
//初始化连接
    @BeforeAll
    public static void init() throws IOException {
        Configuration configuration = HBaseConfiguration.create();
        configuration.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");

        //获取连接
        connection = ConnectionFactory.createConnection(configuration);
        //获取表连接
        table = connection.getTable(TableName.valueOf("myuser"));
    }

    @AfterAll
    //关闭连接
    public static void close() throws IOException {
        table.close();
        connection.close();
    }

展示所有数据：

    //打印内容
    public void showTable(ResultScanner resultScanner) {
        for (Result result : resultScanner) {
            byte[] row = result.getRow();
            System.out.println("数据的rowKey为" + Bytes.toString(row));

            List<Cell> cells = result.listCells();
            for (Cell cell : cells) {
                byte[] family = cell.getFamily();
                byte[] qualifier = cell.getQualifier();
                byte[] value = cell.getValue();
                //id列和age列是整型数据
                if ("f1".equals(Bytes.toString(family)) && "id".equals(Bytes.toString(qualifier)) || "age".equals(Bytes.toString(value))) {
                    System.out.println("，列族为" + Bytes.toString(family) + "，列名为" + Bytes.toString(qualifier) + "，列值为" + Bytes.toInt(value));
                } else {
                    System.out.println("，列族为" + Bytes.toString(family) + "，列名为" + Bytes.toString(qualifier) + "，列值为" + Bytes.toString(value));
                }
            }
            System.out.println();
        }
    }

1、rowKey过滤器RowFilter
通过RowFilter过滤比rowKey 0003小的所有值出来

/**
     * hbase行键过滤器RowFilter
     */
    @Test
    public  void rowKeyFilter() throws IOException {
        //获取连接
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
		//获取scan
        Scan scan = new Scan();
        //获取拦截器对象
        RowFilter rowFilter = new RowFilter(CompareFilter.CompareOp.LESS_OR_EQUAL, new BinaryComparator(Bytes.toBytes("0003")));

		//设置拦截器
        scan.setFilter(rowFilter);
        ResultScanner resultScanner = myuser.getScanner(scan);
        for (Result result : resultScanner) {
            //获取rowkey
            System.out.println(Bytes.toString(result.getRow()));

            //指定列族以及列打印列当中的数据出来
            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "age".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
        }
    }

2、列族过滤器FamilyFilter
查询比f2列族小的所有的列族内的数据

    @Test
    public  void familyFilter() throws IOException {
        //获取表
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        //获取scan
        Scan scan = new Scan();
        //制作拦截器
        FamilyFilter familyFilter = new FamilyFilter(CompareFilter.CompareOp.LESS, new SubstringComparator("f2"));
        //添加拦截器
        scan.setFilter(familyFilter);
        ResultScanner resultScanner = myuser.getScanner(scan);
        for (Result result : resultScanner) {
            //获取rowkey
            System.out.println(Bytes.toString(result.getRow()));
            //指定列族以及列打印列当中的数据出来
            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "age".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
        }
    }

3、列过滤器QualifierFilter
只查询name列的值

/**
     * hbase列过滤器
     */
    @Test
    public  void qualifierFilter() throws IOException {
    	//获取表
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        //获取scan
        Scan scan = new Scan();
        //制作拦截器
        QualifierFilter qualifierFilter = new QualifierFilter(CompareFilter.CompareOp.EQUAL, new SubstringComparator("name"));
        //设置拦截器
        scan.setFilter(qualifierFilter);
        ResultScanner resultScanner = myuser.getScanner(scan);
        for (Result result : resultScanner) {
            //获取rowkey
            System.out.println(Bytes.toString(result.getRow()));
            //指定列族以及列打印列当中的数据出来
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
        }
    }

4、列值过滤器ValueFilter
查询所有列当中包含8的数据

    @Test
    public  void valueFilter() throws IOException {
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        Scan scan = new Scan();
        ValueFilter valueFilter = new ValueFilter(CompareFilter.CompareOp.EQUAL, new SubstringComparator("8"));

        scan.setFilter(valueFilter);
        ResultScanner resultScanner = myuser.getScanner(scan);
        for (Result result : resultScanner) {
            //获取rowkey
            System.out.println(Bytes.toString(result.getRow()));
            //指定列族以及列打印列当中的数据出来
            //    System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
        }
    }

3.专用过滤器

1、单列值过滤器 SingleColumnValueFilter
SingleColumnValueFilter会返回满足条件的整列值的所有字段

/**
     * 单列值过滤器，返回满足条件的整行数据
     */
    @Test
    public void singleColumnFilter() throws IOException {
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        Scan scan = new Scan();
        SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter("f1".getBytes(), "name".getBytes(), CompareFilter.CompareOp.EQUAL, "刘备".getBytes());
        scan.setFilter(singleColumnValueFilter);
        ResultScanner resultScanner = myuser.getScanner(scan);
        for (Result result : resultScanner) {
            //获取rowkey
            System.out.println(Bytes.toString(result.getRow()));
            //指定列族以及列打印列当中的数据出来
            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
        }
    }

2、列值排除过滤器SingleColumnValueExcludeFilter
与SingleColumnValueFilter相反，会排除掉指定的列，其他的列全部返回

/**
     * 单列值过滤器，返回满足条件的整行数据
     */
    @Test
    public void singleColumnFilter() throws IOException {
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        Scan scan = new Scan();
        SingleColumnValueExcludeFilter singleColumnValueExcludeFilter= new SingleColumnValueExcludeFilter("f1".getBytes(), "name".getBytes(), CompareFilter.CompareOp.EQUAL, "刘备".getBytes());
        scan.setFilter(singleColumnValueExcludeFilter);
        ResultScanner resultScanner = myuser.getScanner(scan);
        for (Result result : resultScanner) {
            //获取rowkey
            System.out.println(Bytes.toString(result.getRow()));
            //指定列族以及列打印列当中的数据出来
            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
        }
    }

3、rowkey前缀过滤器PrefixFilter
查询以00开头的所有前缀的rowkey

/**
     * 行键前缀过滤器
     */
    @Test
    public void preFilter() throws IOException {
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        Scan scan = new Scan();
        PrefixFilter prefixFilter = new PrefixFilter("00".getBytes());
        scan.setFilter(prefixFilter);
        ResultScanner resultScanner = myuser.getScanner(scan);
        for (Result result : resultScanner) {
            //获取rowkey
            System.out.println(Bytes.toString(result.getRow()));
            //指定列族以及列打印列当中的数据出来
            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
        }

    }

4、分页过滤器PageFilter
通过pageFilter实现分页过滤器

@Test
    public void pageFilter2() throws IOException {
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        int pageNum = 3;
        int pageSize = 2;
        Scan scan = new Scan();
        if (pageNum == 1) {
            PageFilter filter = new PageFilter(pageSize);
            scan.setStartRow(Bytes.toBytes(""));
            scan.setFilter(filter);
            scan.setMaxResultSize(pageSize);
            ResultScanner scanner = myuser.getScanner(scan);
            for (Result result : scanner) {
                //获取rowkey
                System.out.println(Bytes.toString(result.getRow()));
                //指定列族以及列打印列当中的数据出来
//            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
                System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
                //System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
            }

        }else{
            String rowKey ="";
            for(int i =pageNum -1;i<=pageNum;i++){
                if(i ==  pageNum){
                    PageFilter filter = new PageFilter(pageSize);
                    scan.setStartRow(Bytes.toBytes(rowKey));
                    scan.setFilter(filter);
                    ResultScanner scanner = myuser.getScanner(scan);
                    for (Result result : scanner) {
                        byte[] row = result.getRow();
                        rowKey = new String(row);
                        System.out.println(rowKey);
                        System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
                    }
                }else{
                    PageFilter filter = new PageFilter((pageNum -1) * pageSize + 1);
                    scan.setStartRow(Bytes.toBytes(rowKey));
                    scan.setFilter(filter);
                    ResultScanner scanner = myuser.getScanner(scan);
                    for (Result result : scanner) {
                        byte[] row = result.getRow();
                        rowKey = new String(row);
                    }
                }
            }
        }
    }

4. 多过滤器综合查询FilterList

需求：使用SingleColumnValueFilter查询f1列族，name为刘备的数据，并且同时满足rowkey的前缀以00开头的数据（PrefixFilter）

/**
     * 多过滤器组合使用
     */
    @Test
    public void manyFilter() throws IOException {
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        Scan scan = new Scan();
        FilterList filterList = new FilterList();

        SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter("f1".getBytes(), "name".getBytes(), CompareFilter.CompareOp.EQUAL, "刘备".getBytes());
        PrefixFilter prefixFilter = new PrefixFilter("00".getBytes());
        filterList.addFilter(singleColumnValueFilter);
        filterList.addFilter(prefixFilter);
        scan.setFilter(filterList);
        ResultScanner scanner = myuser.getScanner(scan);
        for (Result result : scanner) {
            //获取rowkey
            System.out.println(Bytes.toString(result.getRow()));
            //指定列族以及列打印列当中的数据出来
//            System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
            //System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
        }
    }