获取数据的两种方式

package com.shujia;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;

import java.io.BufferedReader;
import java.io.FileReader;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

/*
   HBase的操作分类：
   1.对表结构（元数据）的操作-->Admin对象
   2.对表数据的操作-->Table对象
*/
public class Demo02HBaseJavaAPI {
    Connection conn;
    Admin admin;

    @Before
    public void init() throws IOException {
        //创建HBase的配置
        Configuration conf = HBaseConfiguration.create();
        //配置HBase所属ZK集群的地址
        conf.set("hbase.zookeeper.quorum","master:2181,node1:2181,node2:2181");

        //建立连接
        conn = ConnectionFactory.createConnection(conf);
        //获取所有表的名字,这个操作跟表的数据无关
        admin= conn.getAdmin();
    }

    @Test
    //list 查看所有表
    public void listAllTables() throws IOException {
        //HBase中的表名都以TableName对象形式存在
        TableName[] tableNames = admin.listTableNames();
        for (TableName tableName : tableNames) {
            System.out.println(tableName.getNameAsString());
        }
    }

    @Test
    //创建一张表 tb1 有一个列簇 ttl为10s
    public void createTable() throws IOException {
        //创建一个HTableDescriptor对象,用于描述HBase的表结构
        HTableDescriptor tb1 = new HTableDescriptor(TableName.valueOf("tb1"));
        //添加一个列簇
        //创建一个HColumnDescriptor对象，用于描述列簇的属性
        HColumnDescriptor cf1 = new HColumnDescriptor("cf1");
        cf1.setTimeToLive(10);
        tb1.addFamily(cf1);
        admin.createTable(tb1);
    }

    @Test
    //测试表存不存在
    public void existsTable() throws IOException {
        System.out.println(admin.tableExists(TableName.valueOf("tb1")));
        System.out.println(admin.tableExists(TableName.valueOf("tb10")));
    }

    @Test
    //修改表结构:将tb1的列簇cf1的ttl设置为100秒，并且新加一个列簇cf2
    public void modityTable() throws IOException {
        TableName tb1Name = TableName.valueOf("tb1");
        //获取原有的表结构
        HTableDescriptor tb1 = admin.getTableDescriptor(tb1Name);
        HColumnDescriptor[] columnFamilies = tb1.getColumnFamilies();
        //找到cf1列簇并重新设置ttl
        for (HColumnDescriptor cf : columnFamilies) {
            if("cf1".equals(cf.getNameAsString())){
                System.out.println("cf1原有的ttl为:"+cf.getTimeToLive());
                cf.setTimeToLive(100);
            }
        }
        //添加列簇cf2
        tb1.addFamily(new HColumnDescriptor("cf2"));
        admin.modifyTable(tb1Name,tb1);
    }

    @Test
    //插入数据
    public void put() throws IOException {
        //需要对数据进行操作，所以创建一个Table对象
        Table tb1 = conn.getTable(TableName.valueOf("tb1"));
        Put put = new Put("001".getBytes());
        put.addColumn("cf1".getBytes(),"name".getBytes(),"张三".getBytes());
        put.addColumn("cf1".getBytes(),"age".getBytes(),"22".getBytes());
        put.addColumn("cf1".getBytes(),"clazz".getBytes(),"文科一班".getBytes());
        tb1.put(put);
    }

    @Test
    //获取一条数据 get
    public void getData() throws IOException {
        Table tb1 = conn.getTable(TableName.valueOf("tb1"));
        Get get = new Get("001".getBytes());
        get.addColumn("cf1".getBytes(),"name".getBytes());
        Result rs = tb1.get(get);
        byte[] value = rs.getValue("cf1".getBytes(), "name".getBytes());
        System.out.println(Bytes.toString(value));
    }

    @Test
    //读取students.txt数据并且创建stu表(),将数据写入stu表
    public void putStu() throws IOException {
        TableName stuName = TableName.valueOf("stu");
        //判断表不存在即创建
        if(!admin.tableExists(stuName)) {
            admin.createTable(new HTableDescriptor(stuName).addFamily(new HColumnDescriptor("info")));
            }else{
            System.out.println("表已存在，不需要重复创建");
        }

        Table stu=conn.getTable(stuName);

        //读文件
        BufferedReader br = new BufferedReader(new FileReader("data/students.txt"));
        String line;

        //用于批量插入
        ArrayList<Put> puts = new ArrayList<>();
        //每次插入100条
        int batchSize=99;

        while((line = br.readLine())!=null){
            String[] splits=line.split(",");
            String id=splits[0];
            String name=splits[1];
            String age=splits[2];
            String gender=splits[3];
            String clazz=splits[4];

            //写入数据
            Put put = new Put(id.getBytes());
            put.addColumn("info".getBytes(),"name".getBytes(),name.getBytes());
            put.addColumn("info".getBytes(),"age".getBytes(),age.getBytes());
            put.addColumn("info".getBytes(),"gender".getBytes(),gender.getBytes());
            put.addColumn("info".getBytes(),"clazz".getBytes(),clazz.getBytes());
            //每条数据会调用一次，效率太低
//            stu.put(put);
            //使用批量输入
            puts.add(put);//将每条数据构建好的put对象放入put的list中等待批量插入
            //每100条提交一次
            if (puts.size()==batchSize){
                stu.put(puts);
                //清空put的list
                puts.clear();
            }
        }
        //如果数据的条数不是batchSize的整数倍 put的list中还会有数据未插入
        if(puts.size()!=0){
            stu.put(puts);
        }
    }

    @Test
    //获取一批数据 scan
    public void scanTableData() throws IOException {
        TableName stuName = TableName.valueOf("stu");
        Table stu = conn.getTable(stuName);

        Scan scan = new Scan();
        //配置scan
        scan.withStartRow("1500100001".getBytes());
        scan.withStopRow("1500100030".getBytes(),true);

        scan.setLimit(10);

        ResultScanner rss = stu.getScanner(scan);
        //一个Result对象表示一条数据
        for (Result rs : rss) {
            String id = Bytes.toString(rs.getRow());
            String name = Bytes.toString(rs.getValue("info".getBytes(), "name".getBytes()));
            String age = Bytes.toString(rs.getValue("info".getBytes(), "age".getBytes()));
            String gender = Bytes.toString(rs.getValue("info".getBytes(), "gender".getBytes()));
            String clazz = Bytes.toString(rs.getValue("info".getBytes(), "clazz".getBytes()));

            System.out.println(id+","+name+","+age+","+gender+","+clazz);
        }

        //使用CellUtil获取数据
        //适用于每条数据不一样的情况
        for (Result rs : stu.getScanner(scan)) {
            //获取当前这一行语句包含的所有的Cell
            List<Cell> cells = rs.listCells();
            String id =Bytes.toString(rs.getRow());
            for (Cell cell : cells) {
               //cell就是每一列数据
                String value = Bytes.toString(CellUtil.cloneValue(cell));
                String cf = Bytes.toString(CellUtil.cloneFamily(cell));
                String qua = Bytes.toString(CellUtil.cloneQualifier(cell));
                System.out.println(id+","+cf+":"+qua+","+value);
            }
        }
    }

    @Test
    //删除一条数据
    public void deleteData() throws IOException {
        Table stu = conn.getTable(TableName.valueOf("stu"));
        Delete delete = new Delete("1500100001".getBytes());
//        delete.addColumn("info".getBytes(),"age".getBytes());
        stu.delete(delete);
    }

    @After
    public void close() throws IOException {
        //关闭连接
        admin.close();
        conn.close();
    }
}