HBase使用java代码基础练习 - 陕西小楞娃

创建maven项目

依赖

    <dependencies>
        <!-- https://mvnrepository.com/artifact/org.apache.hbase/hbase-client -->
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>2.0.5</version>
        </dependency>

    </dependencies>

创建类HBaseDemo

公共信息

    Configuration conf = null;
    Connection conn = null;
    // 表的管理对象
    Admin admin = null;
    Table table = null;
    // 创建表的对象
    TableName tableName = TableName.valueOf("666");

初始化信息

    @Before
    public void init() throws  IOException{
        // 创建配置文件对象
        conf = HBaseConfiguration.create();
        // 加载zookeeper配置
        conf.set("hbase.zookeeper.quorum","node02,node03,node04");
        // 获取连接
        conn = ConnectionFactory.createConnection(conf);
        // 获取对象
        admin = conn.getAdmin();
        // 获取数据操作对象
        table = conn.getTable(tableName);
    }

创建一张表

    @Test
    public void createTable() throws IOException{
        // 定义表描述对象
        TableDescriptorBuilder tableDescriptorBuilder = TableDescriptorBuilder.newBuilder(tableName);
        // 定义列族对象
        ColumnFamilyDescriptorBuilder columnFamilyDescriptorBuilder = ColumnFamilyDescriptorBuilder.newBuilder("cf".getBytes());
        // 添加列族信息给表
        tableDescriptorBuilder.setColumnFamily(columnFamilyDescriptorBuilder.build());

        if(admin.tableExists(tableName)){
            //禁用表
            admin.disableTable(tableName);
            admin.deleteTable(tableName);
        }
        //创建表
        admin.createTable(tableDescriptorBuilder.build());
    }

给表中插入一行数据

    @Test
    public void insert() throws IOException {
        Put put = new Put(Bytes.toBytes("row2222"));
        put.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("name"), Bytes.toBytes("lisi"));
        put.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("age"), Bytes.toBytes("341"));
        put.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("sex"), Bytes.toBytes("women"));
        table.put(put);
    }

查看一行row数据

 /**
     * Hbase 可以插入十亿行 和百万列, 所以查询需要克服io，如下减少io
     * 查看一行row
     * @throws IOException
     */
    @Test
    public void get() throws IOException{

        Get get = new Get(Bytes.toBytes("row2222"));

        // 在服务端做数据过滤，挑选出符合需求的列,也就是百万列，我只要这三个，其他的不查也就不走io
        get.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("name"));
        get.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("age"));
        get.addColumn(Bytes.toBytes("cf"), Bytes.toBytes("sex"));

        Result result = table.get(get);
        Cell cell1 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("name"));
        Cell cell2 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("age"));
        Cell cell3 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("sex"));

        String name = Bytes.toString(CellUtil.cloneValue(cell1));
        String age = Bytes.toString(CellUtil.cloneValue(cell2));
        String sex = Bytes.toString(CellUtil.cloneValue(cell3));

        System.out.println(name);
        System.out.println(age);
        System.out.println(sex);
    }

查看所有行数据

    /**
     * Hbase 可以插入十亿行 和百万列, 所以查询需要克服io，如下减少io
     * 查看所有行row, 公司一般禁止使用，相当于mysql的select * from
     * @throws IOException
     */
    @Test
    public void scan() throws IOException{

        Scan scan = new Scan();
        ResultScanner scanner = table.getScanner(scan);
        for (Result result : scanner) {
            Cell cell1 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("name"));
            Cell cell2 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("age"));
            Cell cell3 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("sex"));

            String name = Bytes.toString(CellUtil.cloneValue(cell1));
            String age = Bytes.toString(CellUtil.cloneValue(cell2));
            String sex = Bytes.toString(CellUtil.cloneValue(cell3));
            System.out.println(name);
            System.out.println(age);
            System.out.println(sex);
        }
    }

需求：

你要查询手机的通话记录，你怎么设计row_key

通话内容有: 我的手机号、 别人的手机号码、通话时间、 通话时长、通话类型

创建数据：

假设有10个用户，每个用户一年产生10000条记录

    @Test
    public void insertMangerData() throws Exception{
        List<Put> puts = new ArrayList<Put>();
        for (int i = 0; i < 10; i++) {
            String myNumber = getNumber("177");
            for (int j = 0; j < 10000; j++) {
                // 模拟数据 别人的手机号码、通话时长、通话时间、通话类型
                String otherNumber = getNumber("177");
                String length = String.valueOf(random.nextInt(100));
                String date = getDate("2019");
                String type = String.valueOf(random.nextInt(2));

                // rowkey 设计为我的手机号码 + 时间戳反转(也可以将手机号码倒过来进行数据分散)
                String rowkey = myNumber+"_"+(Long.MAX_VALUE-sdf.parse(date).getTime());
                Put put = new Put(Bytes.toBytes(rowkey));
                put.addColumn(Bytes.toBytes("cf"),Bytes.toBytes("otherNumber"),Bytes.toBytes(otherNumber));
                put.addColumn(Bytes.toBytes("cf"),Bytes.toBytes("length"),Bytes.toBytes(length));
                put.addColumn(Bytes.toBytes("cf"),Bytes.toBytes("date"),Bytes.toBytes(date));
                put.addColumn(Bytes.toBytes("cf"),Bytes.toBytes("type"),Bytes.toBytes(type));
                puts.add(put);
            }
        }
        table.put(puts);
    }

    SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMddHHmmss");
    private String getDate(String s) {
        return s+String.format("%02d%02d%02d%02d%02d",random.nextInt(12)+1,random.nextInt(31),random.nextInt(24),random.nextInt(60),random.nextInt(60));
    }

    Random random = new Random();
    private String getNumber(String s) {
        return s + String.format("%08d", random.nextInt(99999999));
    }

获取本机手机号码的所有通话记录，假设17733292236是我的手机号码

    /**
     * 获取本机手机号码的所有通话记录
     * @throws Exception
     */
    @Test
    public void scanByCondition()  throws Exception{
        Scan scan = new Scan();
        scan.setRowPrefixFilter(Bytes.toBytes("17733292236"));
        ResultScanner scanner = table.getScanner(scan);
        for (Result result : scanner) {
            Cell cell1 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("otherNumber"));
            Cell cell2 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("length"));
            Cell cell3 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("type"));
            Cell cell4 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("date"));

            String otherNumber = Bytes.toString(CellUtil.cloneValue(cell1));
            String length = Bytes.toString(CellUtil.cloneValue(cell2));
            String type = Bytes.toString(CellUtil.cloneValue(cell3));
            String date = Bytes.toString(CellUtil.cloneValue(cell4));

            System.out.print(otherNumber + " - ");
            System.out.print(length + " - ");
            System.out.print(type + " - ");
            System.out.println(date);
        }

    }

查询某一个用户3月份的通话记录

    /**
     * 查询某一个用户3月份的通话记录
     */
    @Test
    public void scanByCondition2() throws Exception {
        Scan scan = new Scan();
        String startRow = "17733292236_"+(Long.MAX_VALUE-sdf.parse("20190331000000").getTime());
        String stopRow = "17733292236_"+(Long.MAX_VALUE-sdf.parse("20190301000000").getTime());
        scan.withStartRow(Bytes.toBytes(startRow));
        scan.withStopRow(Bytes.toBytes(stopRow));
        ResultScanner rss = table.getScanner(scan);
        for (Result result:rss) {
            Cell cell1 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("otherNumber"));
            Cell cell2 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("length"));
            Cell cell3 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("type"));
            Cell cell4 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("date"));

            String otherNumber = Bytes.toString(CellUtil.cloneValue(cell1));
            String length = Bytes.toString(CellUtil.cloneValue(cell2));
            String type = Bytes.toString(CellUtil.cloneValue(cell3));
            String date = Bytes.toString(CellUtil.cloneValue(cell4));

            System.out.print(otherNumber + " - ");
            System.out.print(length + " - ");
            System.out.print(type + " - ");
            System.out.println(date);
        }
    }

根据列族中的字段来进行查询，需要使用拦截器，例如查询row手机号码为17733292236，通话类型为1的

 @Test
    public void getType() throws IOException{
        Scan scan = new Scan();
        //创建过滤器集合
        FilterList filters = new FilterList(FilterList.Operator.MUST_PASS_ALL);
        //创建过滤器
        SingleColumnValueFilter filter1 = new SingleColumnValueFilter(Bytes.toBytes("cf"), Bytes.toBytes("type"), CompareOperator.EQUAL, Bytes.toBytes("1"));
        filters.addFilter(filter1);
        //前缀过滤器
        PrefixFilter filter2 = new PrefixFilter(Bytes.toBytes("17733292236"));
        filters.addFilter(filter2);
        scan.setFilter(filters);
        ResultScanner rss = table.getScanner(scan);
        for (Result result:rss) {
            Cell cell1 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("otherNumber"));
            Cell cell2 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("length"));
            Cell cell3 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("type"));
            Cell cell4 = result.getColumnLatestCell(Bytes.toBytes("cf"), Bytes.toBytes("date"));

            String otherNumber = Bytes.toString(CellUtil.cloneValue(cell1));
            String length = Bytes.toString(CellUtil.cloneValue(cell2));
            String type = Bytes.toString(CellUtil.cloneValue(cell3));
            String date = Bytes.toString(CellUtil.cloneValue(cell4));

            System.out.print(otherNumber + " - ");
            System.out.print(length + " - ");
            System.out.print(type + " - ");
            System.out.println(date);
        }

    }

删除一行数据

    @Test
    public void delete() throws Exception{
        Delete delete = new Delete("row2222".getBytes());
        table.delete(delete);

关闭连接

    @After
    public void destory(){
        try {
            table.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
        try {
            admin.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
        try {
            conn.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

代码地址: https://gitee.com/Xiaokeworksveryhard/big-data.git

posted on 2020-11-21 13:52 陕西小楞娃阅读(224) 评论(0) 编辑收藏举报

会员力量，点亮园子希望

刷新页面返回顶部