HBase-API

63 阅读 0 评论 42 点赞

我是靠谱客的博主香蕉睫毛，最近开发中收集的这篇文章主要介绍HBase-API，觉得挺不错的，现在分享给大家，希望可以做个参考。

概述

引入的依赖

创建连接

命名空间

表

引入的依赖

    <dependencies>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>2.4.11</version>
            <exclusions>
                <exclusion>
                    <artifactId>javax.el</artifactId>
                    <groupId>org.glassfish</groupId>
                </exclusion>
            </exclusions>
        </dependency>
        <dependency>
            <groupId>org.glassfish</groupId>
            <artifactId>javax.el</artifactId>
            <version>3.0.1-b06</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-common</artifactId>
            <version>2.4.11</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-common</artifactId>
            <version>2.4.11</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.apache.hadoop/hadoop-common -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-common</artifactId>
            <version>2.10.0</version>
        </dependency>
    </dependencies>

创建连接

单线程使用连接

conf.set的配置信息具体跟本地hosts文件中的配置有关

public class HBaseConnection {
    public static void main(String[] args) throws IOException {
        //1.创建连接配置对象
        Configuration conf = new Configuration();
        //2.添加配置参数 zookeeper地址
        conf.set("hbase.zookeeper.quorum","node1,node2,node3");
        //3.创建连接，默认使用同步连接
        Connection connection = ConnectionFactory.createConnection(conf);
        //也可以使用异步连接
        //CompletableFuture<AsyncConnection> asyncConnection = ConnectionFactory.createAsyncConnection();
        //4.使用连接
        System.out.println(connection);
        //5.关闭连接
        connection.close();
    }
}

在创建连接时，由于该连接是重量级的，创建时最好创建一个，所以当多个线程使用连接时，需要只创建一个连接，采用单例的模式

多线程使用连接

public class HBaseConnection2 {
    public static Connection connection = null;
    static {
        //1.创建连接配置对象
        Configuration conf = new Configuration();
        //2.添加配置参数 zookeeper地址
        conf.set("hbase.zookeeper.quorum","node1,node2,node3");
        //3.创建连接，默认使用同步连接
        try {
            connection = ConnectionFactory.createConnection(conf);
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    public static void closeConnection(){
        if(connection != null) {
            try {
                connection.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
    public static void main(String[] args) {
        //4.使用连接
        System.out.println(HBaseConnection2.connection);
        HBaseConnection2.closeConnection();
    }
}

命名空间

public class HBaseDDL {
    public static Connection connection = HBaseConnection2.connection;
    public static void createNameSpace(String namespace) throws IOException {
        //1.获取admin,admin是轻量级，不是线程安全的，不推荐池化或缓存这个连接
        //连接出现问题不属于createNameSpace的问题，应该抛出
        Admin admin = connection.getAdmin();
        //2.调用方法，创建命名空间
        //2.1 创建命名空间描述,利用了建造者模式，拓展丰富了构造器
        NamespaceDescriptor.Builder builder = NamespaceDescriptor.create(namespace);
        //2.2 给命名空间添加需求,就是命名空间的描述
        builder.addConfiguration("user","zz");
        //2.3 使用builder构造出对应的添加完参数的对象  完成创建
        //创建命名空间出现的问题，都属于本方法自身的问题，不应该抛出
        try {
            admin.createNamespace(builder.build());
        } catch (IOException e) {
            System.out.println("命名空间已经存在");
            e.printStackTrace();
        }
        //3关闭admin
        try {
            admin.close();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
    public static void main(String[] args) throws IOException {
        HBaseDDL.createNameSpace("company");
        HBaseConnection2.closeConnection();
    }
}

表

判断表是否存在

//判断表格是否存在
    public static boolean isTableExists(String namespace,String tableName) throws IOException {
        //1.获取admin 连接的异常不属于该方法所以抛出
        Admin admin = connection.getAdmin();
        //2.使用方法判断表格是否存在，该异常是属于该方法，所以try起来
        boolean b = false;
        try {
            b = admin.tableExists(TableName.valueOf(namespace,tableName));
        } catch (IOException e) {
            e.printStackTrace();
        }
        //3.关闭admin
        admin.close();
        //4.返回结果
        return b;
    }
    public static void main(String[] args) throws IOException {
        System.out.println(isTableExists("bigdata","student"));
    }

创建表

//创建表格
    public static void createTable(String namespace,String tableName,String... columnFamilys) throws IOException {
        //判断是否至少有一个列族
        if(columnFamilys.length == 0){
            System.out.println("创建表格至少有一个列族");
            return;
        }
        //判断表格是否存在
        if(isTableExists(namespace,tableName)){
            System.out.println("表格已经存在");
            return;
        }
        //1.获取admin
        Admin admin = connection.getAdmin();
        //2.调用方法创建表格
        //2.1创建表格描述
        TableDescriptorBuilder tableDescriptorBuilder = TableDescriptorBuilder.newBuilder(TableName.valueOf(namespace,tableName));
        //2.2添加参数
        for(String columnFamily : columnFamilys){
            //2.3创建列族描述的建造者
            ColumnFamilyDescriptorBuilder columnFamilyDescriptorBuilder
                    = ColumnFamilyDescriptorBuilder.newBuilder(Bytes.toBytes(columnFamily));
            //2.4对应当前列族添加参数
            columnFamilyDescriptorBuilder.setMaxVersions(5);
            //2.5创建添加完参数的列族描述
            tableDescriptorBuilder.setColumnFamily(columnFamilyDescriptorBuilder.build());
        }
        //2.6创建表格
        try {
            admin.createTable(tableDescriptorBuilder.build());
        } catch (IOException e) {
            System.out.println("表格已经存在");
            e.printStackTrace();
        }
        //3.关闭admin
        admin.close();
    }
    public static void main(String[] args) throws IOException {
        createTable("company","worker","info","msg");
    }

修改表格

    public static void modifyTable(String namespace,String tableName,String columnFamily,int version) throws IOException {
        //判断表格是否存在
        if(!isTableExists(namespace,tableName)){
            System.out.println("表格不存在，无法修改");
            return;
        }
        //1.获取admin
        Admin admin = connection.getAdmin();
        try {
            //2.调用方法修改表格
            //2.1获取之前的表格描述 :先获取描述，再获取建造者，再根据建造者获取表格对象
            TableDescriptor tableDescriptor = admin.getDescriptor(TableName.valueOf(namespace, tableName));
            TableDescriptorBuilder tableDescriptorBuilder = TableDescriptorBuilder.newBuilder(tableDescriptor);
            //2.2获取旧的列族描述
            ColumnFamilyDescriptor columnFamilyDescriptor = tableDescriptor
                    .getColumnFamily(Bytes.toBytes(columnFamily));
            ColumnFamilyDescriptorBuilder columnFamilyDescriptorBuilder = ColumnFamilyDescriptorBuilder
                    .newBuilder(columnFamilyDescriptor);
            //修改对应信息
            columnFamilyDescriptorBuilder.setMaxVersions(version);
            //将修改后的列族赋给旧的表格
            tableDescriptorBuilder.modifyColumnFamily(columnFamilyDescriptorBuilder.build());
            //3.修改版本数
            admin.modifyTable(tableDescriptorBuilder.build());
        } catch (IOException e) {
            e.printStackTrace();
        }
        //4.关闭admin
        admin.close();
    }
    public static void main(String[] args) throws IOException {
        modifyTable("company","worker","info",6);
    }

删除表格

    public static boolean deleteTable(String namespace,String tableName) throws IOException {
        //1.判断表格是否存在
        if(!isTableExists(namespace,tableName)){
            System.out.println("表格不存在，无法删除");
            return false;
        }
        //2.获取admin
        Admin admin = connection.getAdmin();
        //3.调用相关方法
        try {
            //删除表格之前，先标记表格为不可用
            TableName tableName1 = TableName.valueOf(namespace, tableName);
            admin.disableTable(tableName1);
            admin.deleteTable(tableName1);
        } catch (IOException e) {
            e.printStackTrace();
        }
        //4.关闭admin
        admin.close();
        return true;
    }

数据

写入数据

public class HBaseDML {
    public static Connection connection = HBaseConnection2.connection;

    public static void putCell(String namespace,String tableName,
                               String rowKey,String columnFamily,
                               String columnName,String value) throws IOException {
        //1.获取Table
        Table table = connection.getTable(TableName.valueOf(namespace, tableName));
        //2.调用相关方法插入数据
        //2.1创建put对象
        Put put = new Put(Bytes.toBytes(rowKey));
        //2.2给put对象添加数据
        put.addColumn(Bytes.toBytes(columnFamily),Bytes.toBytes(columnName),Bytes.toBytes(value));
        //2.3将对象写入方法
        try {
            table.put(put);
        } catch (IOException e) {
            e.printStackTrace();
        }
        //3.关闭table
        table.close();
    }

    public static void main(String[] args) throws IOException {
        putCell("bigdata","student","1005","info","age","100");
        HBaseConnection2.closeConnection();
    }

读取数据

get

用get读取数据只能读取一行

public static void getCells(String namespace,String tableName,
                                String rowKey,String columnFamily,
                                String columnName) throws IOException {
        //1.获取table
        Table table = connection.getTable(TableName.valueOf(namespace,tableName));
        //2.创建get对象
        Get get = new Get(Bytes.toBytes(rowKey));
        //3.如果直接调用get方法读取数据 此时读取一整行数据
        //如果读取某几列需要增加参数
        get.addColumn(Bytes.toBytes(columnFamily),Bytes.toBytes(columnName));
        //设置读取的版本
        get.readAllVersions();
        Result result = null;
        try {
            //4.获取并处理数据
            result = table.get(get);
            Cell[] cells = result.rawCells();
            for(Cell cell:cells){
                String value = new String(CellUtil.cloneValue(cell));
                System.out.println(value);
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
        //5.关闭table
        table.close();

    }
    public static void main(String[] args) throws IOException {
        getCells("bigdata","student","1005","info","age");
        HBaseConnection2.closeConnection();
    }

scan

    public static void scanRows(String namespace,String tableName,String startRow,String stopRow) throws IOException {
        //1.获取table
        Table table = connection.getTable(TableName.valueOf(namespace,tableName));
        //2.创建scan对象
        Scan scan = new Scan();
        //如果不写这一句就扫描整张表
        scan.withStartRow(Bytes.toBytes(startRow)).withStopRow(Bytes.toBytes(stopRow));
        //3.读取多行数据，Result记录一行数据，ResultScanner记录多行数据，Result是cell的数组，ResultScanner是Result的数据
        ResultScanner resultScanner = null;
        try {
            resultScanner = table.getScanner(scan);
            for (Result result : resultScanner) {
                Cell[] cells = result.rawCells();
                for(Cell cell:cells){
                    System.out.println(new String(CellUtil.cloneRow(cell))+"-"
                            +new String(CellUtil.cloneFamily(cell))+"-"
                            +new String(CellUtil.cloneQualifier(cell))+"-"
                            +new String(CellUtil.cloneValue(cell)));
                }
                System.out.println();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
        //4.关闭table
        table.close();
    }
    public static void main(String[] args) throws IOException {
        scanRows("bigdata","student","1001","1004");
        HBaseConnection2.closeConnection();
    }

scan之单列过滤扫描

输出多行数据的某一列，并且这些行中可以按值去筛选，选中从startRow到stopRow的所有行的columnName的列的内容，再根据value进行筛选

    public static void filterScan(String namespace,String tableName,
                                String startRow,String stopRow,
                                String columnFamily,String columnName,
                                String value) throws IOException {
        //1.获取table
        Table table = connection.getTable(TableName.valueOf(namespace,tableName));
        //2.创建scan对象
        Scan scan = new Scan();
        //如果不写这一句就扫描整张表
        scan.withStartRow(Bytes.toBytes(startRow)).withStopRow(Bytes.toBytes(stopRow));
        //可以添加多个过滤器
        FilterList filterList = new FilterList();
        //创建过滤器
        //(1)结果只保留当前列的数据
        ColumnValueFilter columnValueFilter = new ColumnValueFilter(
                //列族名称
                Bytes.toBytes(columnFamily),
                //列名
                Bytes.toBytes(columnName),
                //比较关系
                CompareOperator.EQUAL,
                //值
                Bytes.toBytes(value)
        );
        filterList.addFilter(columnValueFilter);
        scan.setFilter(filterList);
        //3.读取多行数据，Result记录一行数据，ResultScanner记录多行数据，Result是cell的数组，ResultScanner是Result的数据
        ResultScanner resultScanner = null;
        try {
            resultScanner = table.getScanner(scan);
            for (Result result : resultScanner) {
                Cell[] cells = result.rawCells();
                for(Cell cell:cells){
                    System.out.println(new String(CellUtil.cloneRow(cell))+"-"
                            +new String(CellUtil.cloneFamily(cell))+"-"
                            +new String(CellUtil.cloneQualifier(cell))+"-"
                            +new String(CellUtil.cloneValue(cell)));
                }
                System.out.println();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
        //4.关闭table
        table.close();
    }

    public static void main(String[] args) throws IOException {
        filterScan("bigdata","student",
                "1001","1005",
                "info","name",
                "wangwu");
        HBaseConnection2.closeConnection();
    }

scanf之整行过滤扫描

跟上面过滤的区别是：假设某行数据没有我们指定的columnFamily和columnName，那么该行数据也会作为结果保留下来

    public static void filterScan(String namespace,String tableName,
                                String startRow,String stopRow,
                                String columnFamily,String columnName,
                                String value) throws IOException {
        //1.获取table
        Table table = connection.getTable(TableName.valueOf(namespace,tableName));
        //2.创建scan对象
        Scan scan = new Scan();
        //如果不写这一句就扫描整张表
        scan.withStartRow(Bytes.toBytes(startRow)).withStopRow(Bytes.toBytes(stopRow));
        //可以添加多个过滤器
        FilterList filterList = new FilterList();
        //创建过滤器
        //(1)结果只保留当前列的数据
        ColumnValueFilter columnValueFilter = new ColumnValueFilter(
                //列族名称
                Bytes.toBytes(columnFamily),
                //列名
                Bytes.toBytes(columnName),
                //比较关系
                CompareOperator.EQUAL,
                //值
                Bytes.toBytes(value)
        );
        //(2)结果保留整行数据
        SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter(
                //列族名称
                Bytes.toBytes(columnFamily),
                //列名
                Bytes.toBytes(columnName),
                //比较关系
                CompareOperator.EQUAL,
                //值
                Bytes.toBytes(value)
        );
        filterList.addFilter(singleColumnValueFilter);
        scan.setFilter(filterList);
        //3.读取多行数据，Result记录一行数据，ResultScanner记录多行数据，Result是cell的数组，ResultScanner是Result的数据
        ResultScanner resultScanner = null;
        try {
            resultScanner = table.getScanner(scan);
            for (Result result : resultScanner) {
                Cell[] cells = result.rawCells();
                for(Cell cell:cells){
                    System.out.println(new String(CellUtil.cloneRow(cell))+"-"
                            +new String(CellUtil.cloneFamily(cell))+"-"
                            +new String(CellUtil.cloneQualifier(cell))+"-"
                            +new String(CellUtil.cloneValue(cell)));
                }
                System.out.println();
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
        //4.关闭table
        table.close();
    }

    public static void main(String[] args) throws IOException {
        filterScan("bigdata","student",
                "1001","1005",
                "info","name",
                "wangwu");
        HBaseConnection2.closeConnection();
    }

删除数据

删除某一列数据

    public static void deleteColumn(String namespace,String tableName,
                                    String rowKey,String columnFamily,
                                    String columnName) throws IOException {
        //1.获取table
        Table table = connection.getTable(TableName.valueOf(namespace,tableName));
        //2.获取delete对象
        Delete delete  = new Delete(Bytes.toBytes(rowKey));
        //添加列信息,删除一个版本
        //delete.addColumn(Bytes.toBytes(columnFamily),Bytes.toBytes(columnName));
        //删除所有版本
        delete.addColumns(Bytes.toBytes(columnFamily),Bytes.toBytes(columnName));
        try {
            table.delete(delete);
        } catch (IOException e) {
            e.printStackTrace();
        }
        //3.关闭table
        table.close();
    }
    public static void main(String[] args) throws IOException {
        deleteColumn("bigdata","student","1002","info","name");
        HBaseConnection2.closeConnection();
    }