HBase的javaApi一个应用（创建删除表等）

本文为传智播客hadoop八天——第六天学习笔记

目的：使用HBase提供的api在eclipse中创建表，删除表，查询数据，使用过滤器有选择的查询数据

在启动HBase之前一定要启动Hadoop和Zookeeper！！今天调了一上午的错，竟然是因为没启动Zookeeper。o（╥﹏╥）o

以下为java代码。

package cn.bigdata;

import java.util.ArrayList;
import java.util.List;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.HBaseAdmin;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.ResultScanner;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.filter.BinaryComparator;
import org.apache.hadoop.hbase.filter.BinaryPrefixComparator;
import org.apache.hadoop.hbase.filter.ByteArrayComparable;
import org.apache.hadoop.hbase.filter.ColumnPrefixFilter;
import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp;
import org.apache.hadoop.hbase.filter.FamilyFilter;
import org.apache.hadoop.hbase.filter.Filter;
import org.apache.hadoop.hbase.filter.MultipleColumnPrefixFilter;
import org.apache.hadoop.hbase.filter.PrefixFilter;
import org.apache.hadoop.hbase.filter.QualifierFilter;
import org.apache.hadoop.hbase.filter.RegexStringComparator;
import org.apache.hadoop.hbase.filter.RowFilter;
import org.apache.hadoop.hbase.filter.SingleColumnValueFilter;
import org.apache.hadoop.hbase.filter.SubstringComparator;
import org.apache.hadoop.hbase.util.Bytes;
import org.junit.Before;
import org.junit.Test;

public class HbaseDao {

    private Configuration conf;
    private HTable testDemo;

    @Before
    public void init() throws Exception {
        conf = HBaseConfiguration.create();
        //设置Hbase所依赖的Zookeeper集群，我使用的是伪分布模式，所以只有一个节点
        conf.set("hbase.zookeeper.quorum", "localhost:2181");
        //表名
        testDemo = new HTable(conf, "testDemo01");
    }

    /**
     * 根据键名插入数据
     * 
     * @throws Exception
     */
    @Test
    public void testInsert() throws Exception {
        //键名
        Put name = new Put(Bytes.toBytes("rk0002"));
        name.add(Bytes.toBytes("base_info"), Bytes.toBytes("name"),
                Bytes.toBytes("天使"));

        Put age = new Put(Bytes.toBytes("rk0002"));
        age.add(Bytes.toBytes("base_info"), Bytes.toBytes("age"),
                Bytes.toBytes("28"));

        ArrayList<Put> puts = new ArrayList<Put>();
        puts.add(name);
        puts.add(age);

        testDemo.put(puts);

    }

    /**
     * 删除表
     * 
     * @throws Exception
     */
    @Test
    public void testDrop() throws Exception {
        //创建表和删除表都需要HBaseAdmin
        HBaseAdmin admin = new HBaseAdmin(conf);
        admin.disableTable("testDemo01");
        admin.deleteTable("testDemo01");
        admin.close();

    }

    /**
     * 根据键名取出数据
     * 
     * @throws Exception
     */
    @Test
    public void testGet() throws Exception {
        Get get = new Get(Bytes.toBytes("rk0002"));
        get.setMaxVersions(5);
        Result result = testDemo.get(get);
        List<Cell> cell = result.listCells();

        for (KeyValue kv : result.list()) {
            String family = new String(kv.getFamily());
            System.out.println(family);
            String qualifier = new String(kv.getQualifier());
            System.out.println(qualifier);
            System.out.println(new String(kv.getValue()));

        }

    }


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

        Configuration conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum", "localhost:2181");

        HBaseAdmin admin = new HBaseAdmin(conf);
        //表名
        TableName name = TableName.valueOf("testDemo01");

        HTableDescriptor desc = new HTableDescriptor(name);
        //列族
        HColumnDescriptor base_info = new HColumnDescriptor("base_info");
        HColumnDescriptor extra_info = new HColumnDescriptor("base_info");
        //版本数
        base_info.setMaxVersions(5);

        desc.addFamily(base_info);
        desc.addFamily(extra_info);

        admin.createTable(desc);

    }

}

HBase提供了很多筛选的过滤器，用于scan方法

    /**
     * 多种过滤条件的使用方法
     * @throws Exception
     */
    @Test
    public void testScan() throws Exception{
        HTable table = new HTable(conf, "person_info".getBytes());
        Scan scan = new Scan(Bytes.toBytes("person_rk_bj_zhang_000001"), Bytes.toBytes("person_rk_bj_zhang_000002"));
        // 前缀过滤器----针对行键
        Filter filter = new PrefixFilter(Bytes.toBytes("rk"));

        // 行过滤器
        ByteArrayComparable rowComparator = new BinaryComparator(
                Bytes.toBytes("person_rk_bj_zhang_000001"));
        RowFilter rf = new RowFilter(CompareOp.LESS_OR_EQUAL, rowComparator);

        /**
         * 假设rowkey格式为：创建日期_发布日期_ID_TITLE 目标：查找 发布日期 为 2014-12-21 的数据
         */
        rf = new RowFilter(CompareOp.EQUAL, new SubstringComparator(
                "_2014-12-21_"));

        // 单值过滤器 1 完整匹配字节数组
        new SingleColumnValueFilter("base_info".getBytes(), "name".getBytes(),
                CompareOp.EQUAL, "zhangsan".getBytes());
        // 单值过滤器2 匹配正则表达式
        ByteArrayComparable comparator = new RegexStringComparator("zhang.");
        new SingleColumnValueFilter("info".getBytes(), "NAME".getBytes(),
                CompareOp.EQUAL, comparator);

        // 单值过滤器2 匹配是否包含子串,大小写不敏感
        comparator = new SubstringComparator("wu");
        new SingleColumnValueFilter("info".getBytes(), "NAME".getBytes(),
                CompareOp.EQUAL, comparator);

        // 键值对元数据过滤-----family过滤----字节数组完整匹配
        FamilyFilter ff = new FamilyFilter(CompareOp.EQUAL,
                new BinaryComparator(Bytes.toBytes("base_info")) // 表中不存在inf列族，过滤结果为空
        );
        // 键值对元数据过滤-----family过滤----字节数组前缀匹配
        ff = new FamilyFilter(CompareOp.EQUAL, new BinaryPrefixComparator(
                Bytes.toBytes("inf")) // 表中存在以inf打头的列族info，过滤结果为该列族所有行
        );

        // 键值对元数据过滤-----qualifier过滤----字节数组完整匹配

        filter = new QualifierFilter(CompareOp.EQUAL, new BinaryComparator(
                Bytes.toBytes("na")) // 表中不存在na列，过滤结果为空
        );
        filter = new QualifierFilter(CompareOp.EQUAL,
                new BinaryPrefixComparator(Bytes.toBytes("na")) // 表中存在以na打头的列name，过滤结果为所有行的该列数据
        );

        // 基于列名(即Qualifier)前缀过滤数据的ColumnPrefixFilter
        filter = new ColumnPrefixFilter("na".getBytes());

        // 基于列名(即Qualifier)多个前缀过滤数据的MultipleColumnPrefixFilter
        byte[][] prefixes = new byte[][] { Bytes.toBytes("na"),
                Bytes.toBytes("me") };
        filter = new MultipleColumnPrefixFilter(prefixes);

        // 为查询设置过滤条件
        scan.setFilter(filter);

        scan.addFamily(Bytes.toBytes("base_info"));
        ResultScanner scanner = testDemo.getScanner(scan);
        for (Result r : scanner) {

            // 直接从result中取到某个特定的value
            byte[] value = r.getValue(Bytes.toBytes("base_info"),
                    Bytes.toBytes("name"));
            System.out.println(new String(value));
        }
        testDemo.close();
    }