Hbase的过滤器查询

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过滤器的比较运算符：

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。

Ⅰ、比较过滤器

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
     */

    public static void rowKeyFilter() throws IOException {
        //获取连接
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        Table myuser = connection.getTable(TableName.valueOf("myuser"));

        Scan scan = new Scan();
        RowFilter rowFilter = new RowFilter(CompareFilter.CompareOp.LESS_OR_EQUAL, new BinaryComparator(Bytes.toBytes("0003")));

        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())));
        }
        myuser.close();

    }

②、列族过滤器FamilyFilter

查询比f2列族小的所有的列族内的数据

 /**
     * hbase列族过滤器FamilyFilter
     */

    public static void familyFilter() throws IOException {
        //获取连接
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        Scan scan = new Scan();
        FamilyFilter familyFilter = new FamilyFilter(CompareFilter.CompareOp.LESS, new SubstringComparator("f2"));
        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())));
        }
        myuser.close();
    }

③、列过滤器QualifierFilter

只查询name列的值

/**
     * hbase列过滤器
     */
     
    public static void qualifierFilter() throws IOException {
        //获取连接
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        Table myuser = connection.getTable(TableName.valueOf("myuser"));
        Scan scan = new Scan();
        QualifierFilter qualifierFilter = new QualifierFilter(CompareFilter.CompareOp.EQUAL, new SubstringComparator("name"));
        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.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
            System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
        }
        myuser.close();
    }

④列值过滤器ValueFilter

查询所有列当中包含8的数据

/**
     * hbase值过滤器
     * 查询包含8的列值
     */

    public static void valueFilter() throws IOException {
        //获取连接
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        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())));
        }
        myuser.close();
    }

Ⅱ、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
     */

    public static void singleColumnFilter() throws IOException {
        //获取连接
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        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())));
        }
        myuser.close();
    }

②、列值排除过滤器SingleColumnValueExcludeFilter

与单列值过滤器SingleColumnValueFilter相反，会排除掉指定的列，其他的列全部返回

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
     */

    public static void preFilter() throws IOException {

        //获取连接
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        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())));
        }
        myuser.close();

    }

④、分页过滤器PageFilter

通过pageFilter实现分页过滤器

 public static void pageFilter2() throws IOException {
        //获取连接
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        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 startRowKey = "";
            PageFilter filter = new PageFilter((pageNum - 1) * pageSize + 1);
            scan.setStartRow(startRowKey.getBytes());
            scan.setMaxResultSize((pageNum - 1) * pageSize + 1);
            scan.setFilter(filter);
            ResultScanner scanner = myuser.getScanner(scan);
            for (Result result : scanner) {
                byte[] row = result.getRow();
                startRowKey = new String(row);
            }
            Scan scan2 = new Scan();
            scan2.setStartRow(startRowKey.getBytes());
            scan2.setMaxResultSize(Long.valueOf(pageSize));
            PageFilter filter2 = new PageFilter(pageSize);
            scan2.setFilter(filter2);

            ResultScanner scanner1 = myuser.getScanner(scan2);
            for (Result result : scanner1) {
                byte[] row = result.getRow();
                System.out.println(new String(row));
            }
        }
        myuser.close();
    }

⑤、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
     */

    public static void manyFilter() throws IOException {
        //获取连接
        Configuration conf = new Configuration();
        conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
        Connection connection = ConnectionFactory.createConnection(conf);
        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())));
        }
        myuser.close();

    }