Hbase入门API操作和 shell操作

最新推荐文章于 2024-04-30 17:30:34 发布

a2615381

最新推荐文章于 2024-04-30 17:30:34 发布

阅读量1.3k

点赞数

分类专栏： java linux相关 hbase hadoop

本文链接：https://blog.csdn.net/a2615381/article/details/51242594

版权

java 同时被 3 个专栏收录

32 篇文章 0 订阅

订阅专栏

linux相关

18 篇文章 0 订阅

订阅专栏

hadoop

11 篇文章 0 订阅

订阅专栏

package cn.itcast.bigdata.hbase;
import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
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.client.Delete;
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.HTablePool;
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.util.Bytes;

public class HbaseTest {
    // 声明静态配置
    static Configuration conf = null;
    static {
    	conf = HBaseConfiguration.create();
        conf.set("hbase.zookeeper.quorum", "localhost");
    	//	conf.set("hbase.zookeeper.quorum", "weekend05,weekend06,weekend07");
    		System.setProperty("hadoop.home.dir", "E:/hadoop");
    		conf.set("hbase.zookeeper.quorum", "hadoop01:2181,hadoop02:2181,hadoop03:2181");
    }

    /*
     * 创建表
     * 
     * @tableName 表名
     * 
     * @family 列族列表
     */
    public static void creatTable(String tableName, String[] family)
            throws Exception {
        HBaseAdmin admin = new HBaseAdmin(conf);
        HTableDescriptor desc = new HTableDescriptor(tableName);
        for (int i = 0; i < family.length; i++) {
            desc.addFamily(new HColumnDescriptor(family[i]));
        }
        if (admin.tableExists(tableName)) {
            System.out.println("table Exists!");
            System.exit(0);
        } else {
            admin.createTable(desc);
            System.out.println("create table Success!");
        }
    }

    /*
     * 为表添加数据（适合知道有多少列族的固定表）
     * 
     * @rowKey rowKey
     * 
     * @tableName 表名
     * 
     * @column1 第一个列族列表
     * 
     * @value1 第一个列的值的列表
     * 
     * @column2 第二个列族列表
     * 
     * @value2 第二个列的值的列表
     */
    public static void addData(String rowKey, String tableName,
            String[] column1, String[] value1, String[] column2, String[] value2)
            throws IOException {
        Put put = new Put(Bytes.toBytes(rowKey));// 设置rowkey
        HTable table = new HTable(conf, Bytes.toBytes(tableName));// HTabel负责跟记录相关的操作如增删改查等//
                                                                    // 获取表
        HColumnDescriptor[] columnFamilies = table.getTableDescriptor() // 获取所有的列族
                .getColumnFamilies();

        for (int i = 0; i < columnFamilies.length; i++) {
            String familyName = columnFamilies[i].getNameAsString(); // 获取列族名
            if (familyName.equals("article")) { // article列族put数据
                for (int j = 0; j < column1.length; j++) {
                    put.add(Bytes.toBytes(familyName),
                            Bytes.toBytes(column1[j]), Bytes.toBytes(value1[j]));
                }
            }
            if (familyName.equals("author")) { // author列族put数据
                for (int j = 0; j < column2.length; j++) {
                    put.add(Bytes.toBytes(familyName),
                            Bytes.toBytes(column2[j]), Bytes.toBytes(value2[j]));
                }
            }
        }
        table.put(put);
        System.out.println("add data Success!");
    }

    /*
     * 根据rwokey查询
     * 
     * @rowKey rowKey
     * 
     * @tableName 表名
     */
    public static Result getResult(String tableName, String rowKey)
            throws IOException {
        Get get = new Get(Bytes.toBytes(rowKey));
        HTable table = new HTable(conf, Bytes.toBytes(tableName));// 获取表
        Result result = table.get(get);
        for (KeyValue kv : result.list()) {
            System.out.println("family:" + Bytes.toString(kv.getFamily()));
            System.out
                    .println("qualifier:" + Bytes.toString(kv.getQualifier()));
            System.out.println("value:" + Bytes.toString(kv.getValue()));
            System.out.println("Timestamp:" + kv.getTimestamp());
            System.out.println("-------------------------------------------");
        }
        return result;
    }

    /*
     * 遍历查询hbase表
     * 
     * @tableName 表名
     */
    public static void getResultScann(String tableName) throws IOException {
        Scan scan = new Scan();
        ResultScanner rs = null;
        HTable table = new HTable(conf, Bytes.toBytes(tableName));
        try {
            rs = table.getScanner(scan);
            for (Result r : rs) {
                for (KeyValue kv : r.list()) {
                    System.out.println("row:" + Bytes.toString(kv.getRow()));
                    System.out.println("family:"
                            + Bytes.toString(kv.getFamily()));
                    System.out.println("qualifier:"
                            + Bytes.toString(kv.getQualifier()));
                    System.out
                            .println("value:" + Bytes.toString(kv.getValue()));
                    System.out.println("timestamp:" + kv.getTimestamp());
                    System.out
                            .println("-------------------------------------------");
                }
            }
        } finally {
            rs.close();
        }
    }

    /*
     * 遍历查询hbase表
     * 
     * @tableName 表名
     */
    public static void getResultScann(String tableName, String start_rowkey,
            String stop_rowkey) throws IOException {
        Scan scan = new Scan();
        scan.setStartRow(Bytes.toBytes(start_rowkey));
        scan.setStopRow(Bytes.toBytes(stop_rowkey));
        ResultScanner rs = null;
        HTable table = new HTable(conf, Bytes.toBytes(tableName));
        try {
            rs = table.getScanner(scan);
            for (Result r : rs) {
                for (KeyValue kv : r.list()) {
                    System.out.println("row:" + Bytes.toString(kv.getRow()));
                    System.out.println("family:"
                            + Bytes.toString(kv.getFamily()));
                    System.out.println("qualifier:"
                            + Bytes.toString(kv.getQualifier()));
                    System.out
                            .println("value:" + Bytes.toString(kv.getValue()));
                    System.out.println("timestamp:" + kv.getTimestamp());
                    System.out
                            .println("-------------------------------------------");
                }
            }
        } finally {
            rs.close();
        }
    }

    /*
     * 查询表中的某一列
     * 
     * @tableName 表名
     * 
     * @rowKey rowKey
     */
    public static void getResultByColumn(String tableName, String rowKey,
            String familyName, String columnName) throws IOException {
        HTable table = new HTable(conf, Bytes.toBytes(tableName));
        Get get = new Get(Bytes.toBytes(rowKey));
        get.addColumn(Bytes.toBytes(familyName), Bytes.toBytes(columnName)); // 获取指定列族和列修饰符对应的列
        Result result = table.get(get);
        for (KeyValue kv : result.list()) {
            System.out.println("family:" + Bytes.toString(kv.getFamily()));
            System.out
                    .println("qualifier:" + Bytes.toString(kv.getQualifier()));
            System.out.println("value:" + Bytes.toString(kv.getValue()));
            System.out.println("Timestamp:" + kv.getTimestamp());
            System.out.println("-------------------------------------------");
        }
    }

    /*
     * 更新表中的某一列
     * 
     * @tableName 表名
     * 
     * @rowKey rowKey
     * 
     * @familyName 列族名
     * 
     * @columnName 列名
     * 
     * @value 更新后的值
     */
    public static void updateTable(String tableName, String rowKey,
            String familyName, String columnName, String value)
            throws IOException {
        HTable table = new HTable(conf, Bytes.toBytes(tableName));
        Put put = new Put(Bytes.toBytes(rowKey));
        put.add(Bytes.toBytes(familyName), Bytes.toBytes(columnName),
                Bytes.toBytes(value));
        table.put(put);
        System.out.println("update table Success!");
    }

    /*
     * 查询某列数据的多个版本
     * 
     * @tableName 表名
     * 
     * @rowKey rowKey
     * 
     * @familyName 列族名
     * 
     * @columnName 列名
     */
    public static void getResultByVersion(String tableName, String rowKey,
            String familyName, String columnName) throws IOException {
        HTable table = new HTable(conf, Bytes.toBytes(tableName));
        Get get = new Get(Bytes.toBytes(rowKey));
        get.addColumn(Bytes.toBytes(familyName), Bytes.toBytes(columnName));
        get.setMaxVersions(5);
        Result result = table.get(get);
        for (KeyValue kv : result.list()) {
            System.out.println("family:" + Bytes.toString(kv.getFamily()));
            System.out
                    .println("qualifier:" + Bytes.toString(kv.getQualifier()));
            System.out.println("value:" + Bytes.toString(kv.getValue()));
            System.out.println("Timestamp:" + kv.getTimestamp());
            System.out.println("-------------------------------------------");
        }
        /*
         * List<?> results = table.get(get).list(); Iterator<?> it =
         * results.iterator(); while (it.hasNext()) {
         * System.out.println(it.next().toString()); }
         */
    }

    /*
     * 删除指定的列
     * 
     * @tableName 表名
     * 
     * @rowKey rowKey
     * 
     * @familyName 列族名
     * 
     * @columnName 列名
     */
    public static void deleteColumn(String tableName, String rowKey,
            String falilyName, String columnName) throws IOException {
        HTable table = new HTable(conf, Bytes.toBytes(tableName));
        Delete deleteColumn = new Delete(Bytes.toBytes(rowKey));
        deleteColumn.deleteColumns(Bytes.toBytes(falilyName),
                Bytes.toBytes(columnName));
        table.delete(deleteColumn);
        System.out.println(falilyName + ":" + columnName + "is deleted!");
    }

    /*
     * 删除指定的列
     * 
     * @tableName 表名
     * 
     * @rowKey rowKey
     */
    public static void deleteAllColumn(String tableName, String rowKey)
            throws IOException {
        HTable table = new HTable(conf, Bytes.toBytes(tableName));
        Delete deleteAll = new Delete(Bytes.toBytes(rowKey));
        table.delete(deleteAll);
        System.out.println("all columns are deleted!");
    }

    /*
     * 删除表
     * 
     * @tableName 表名
     */
    public static void deleteTable(String tableName) throws IOException {
        HBaseAdmin admin = new HBaseAdmin(conf);
        admin.disableTable(tableName);
        admin.deleteTable(tableName);
        System.out.println(tableName + "is deleted!");
    }

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

        // 创建表
        String tableName = "blog2";
        String[] family = { "article", "author" };
    //      creatTable(tableName, family);

        // 为表添加数据

        String[] column1 = { "title", "content", "tag" };
        String[] value1 = {
                "Head First HBase",
                "HBase is the Hadoop database. Use it when you need random, realtime read/write access to your Big Data.",
                "Hadoop,HBase,NoSQL" };
        String[] column2 = { "name", "nickname" };
        String[] value2 = { "nicholas", "lee" };
//        addData("rowkey1", "blog2", column1, value1, column2, value2);
//        addData("rowkey2", "blog2", column1, value1, column2, value2);
//        addData("rowkey3", "blog2", column1, value1, column2, value2);

        // 遍历查询所有
//         getResultScann("blog2");
        // 根据row key范围遍历查询
  //       getResultScann("blog2", "rowkey1", "rowkey2");//含头不含尾

        // 查询
 //        getResult("blog2", "rowkey1");
//
//        // 查询某一列的值
 //         getResultByColumn("blog2", "rowkey1", "author", "name");
//
//        // 更新列
  //       updateTable("blog2", "rowkey1", "author", "name", "bin");
//
//        // 查询某一列的值
//         getResultByColumn("blog2", "rowkey1", "author", "name");
//
//        // 查询某列的多版本
         getResultByVersion("blog2", "rowkey1", "author", "name");
//
//        // 删除一列
//        deleteColumn("blog2", "rowkey1", "author", "nickname");
//
//        // 删除所有列
//        deleteAllColumn("blog2", "rowkey1");
//
//        // 删除表
//        deleteTable("blog2");

    }
}

Hbase的shell常用操作

进入hbase命令行
./hbase shell

显示hbase中的表
list

创建user表，包含info、data两个列族
create 'user', 'info1', 'data1'
create 'user', {NAME => 'info', VERSIONS => '3'}

向user表中插入信息，row key为rk0001，列族info中添加name列标示符，值为zhangsan
put 'user', 'rk0001', 'info:name', 'zhangsan'

向user表中插入信息，row key为rk0001，列族info中添加gender列标示符，值为female
put 'user', 'rk0001', 'info:gender', 'female'

向user表中插入信息，row key为rk0001，列族info中添加age列标示符，值为20
put 'user', 'rk0001', 'info:age', 20

向user表中插入信息，row key为rk0001，列族data中添加pic列标示符，值为picture
put 'user', 'rk0001', 'data:pic', 'picture'

获取user表中row key为rk0001的所有信息
get 'user', 'rk0001'

获取user表中row key为rk0001，info列族的所有信息
get 'user', 'rk0001', 'info'

获取user表中row key为rk0001，info列族的name、age列标示符的信息
get 'user', 'rk0001', 'info:name', 'info:age'

获取user表中row key为rk0001，info、data列族的信息
get 'user', 'rk0001', 'info', 'data'
get 'user', 'rk0001', {COLUMN => ['info', 'data']}

get 'user', 'rk0001', {COLUMN => ['info:name', 'data:pic']}

获取user表中row key为rk0001，列族为info，版本号最新5个的信息
get 'user', 'rk0001', {COLUMN => 'info', VERSIONS => 2}
get 'user', 'rk0001', {COLUMN => 'info:name', VERSIONS => 5}
get 'user', 'rk0001', {COLUMN => 'info:name', VERSIONS => 5, TIMERANGE => [1392368783980, 1392380169184]}

获取user表中row key为rk0001，cell的值为zhangsan的信息
get 'people', 'rk0001', {FILTER => "ValueFilter(=, 'binary:图片')"}

获取user表中row key为rk0001，列标示符中含有a的信息
get 'people', 'rk0001', {FILTER => "(QualifierFilter(=,'substring:a'))"}

put 'user', 'rk0002', 'info:name', 'fanbingbing'
put 'user', 'rk0002', 'info:gender', 'female'
put 'user', 'rk0002', 'info:nationality', '中国'
get 'user', 'rk0002', {FILTER => "ValueFilter(=, 'binary:中国')"}

查询user表中的所有信息
scan 'user'

查询user表中列族为info的信息
scan 'user', {COLUMNS => 'info'}
scan 'user', {COLUMNS => 'info', RAW => true, VERSIONS => 5}
scan 'persion', {COLUMNS => 'info', RAW => true, VERSIONS => 3}
查询user表中列族为info和data的信息
scan 'user', {COLUMNS => ['info', 'data']}
scan 'user', {COLUMNS => ['info:name', 'data:pic']}

查询user表中列族为info、列标示符为name的信息
scan 'user', {COLUMNS => 'info:name'}

查询user表中列族为info、列标示符为name的信息,并且版本最新的5个
scan 'user', {COLUMNS => 'info:name', VERSIONS => 5}

查询user表中列族为info和data且列标示符中含有a字符的信息
scan 'user', {COLUMNS => ['info', 'data'], FILTER => "(QualifierFilter(=,'substring:a'))"}

查询user表中列族为info，rk范围是[rk0001, rk0003)的数据
scan 'people', {COLUMNS => 'info', STARTROW => 'rk0001', ENDROW => 'rk0003'}

查询user表中row key以rk字符开头的
scan 'user',{FILTER=>"PrefixFilter('rk')"}

查询user表中指定范围的数据
scan 'user', {TIMERANGE => [1392368783980, 1392380169184]}

删除数据
删除user表row key为rk0001，列标示符为info:name的数据
delete 'people', 'rk0001', 'info:name'
删除user表row key为rk0001，列标示符为info:name，timestamp为1392383705316的数据
delete 'user', 'rk0001', 'info:name', 1392383705316

清空user表中的数据
truncate 'people'

修改表结构
首先停用user表（新版本不用）
disable 'user'

添加两个列族f1和f2
alter 'people', NAME => 'f1'
alter 'user', NAME => 'f2'
启用表
enable 'user'

###disable 'user'(新版本不用)
删除一个列族：
alter 'user', NAME => 'f1', METHOD => 'delete' 或 alter 'user', 'delete' => 'f1'

添加列族f1同时删除列族f2
alter 'user', {NAME => 'f1'}, {NAME => 'f2', METHOD => 'delete'}

将user表的f1列族版本号改为5
alter 'people', NAME => 'info', VERSIONS => 5
启用表
enable 'user'

删除表
disable 'user'
drop 'user'

get 'person', 'rk0001', {FILTER => "ValueFilter(=, 'binary:中国')"}
get 'person', 'rk0001', {FILTER => "(QualifierFilter(=,'substring:a'))"}
scan 'person', {COLUMNS => 'info:name'}
scan 'person', {COLUMNS => ['info', 'data'], FILTER => "(QualifierFilter(=,'substring:a'))"}
scan 'person', {COLUMNS => 'info', STARTROW => 'rk0001', ENDROW => 'rk0003'}

scan 'person', {COLUMNS => 'info', STARTROW => '20140201', ENDROW => '20140301'}
scan 'person', {COLUMNS => 'info:name', TIMERANGE => [1395978233636, 1395987769587]}
delete 'person', 'rk0001', 'info:name'

alter 'person', NAME => 'ffff'
alter 'person', NAME => 'info', VERSIONS => 10

get 'user', 'rk0002', {COLUMN => ['info:name', 'data:pic']}