学习进度（2）
时间：2020.10.11~2020.10.25
学习了Hbase，zookeeper的安装和Hbase的shell命令，以及通过java API操作HBase数据库
代码量：400行 学习时间：8小时
记录下HBase的DML和DDL操作
对数据的操作：
import java.awt.List; import java.util.ArrayList; import java.util.Iterator; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.hbase.Cell; import org.apache.hadoop.hbase.CellScanner; import org.apache.hadoop.hbase.HBaseConfiguration; import org.apache.hadoop.hbase.TableName; import org.apache.hadoop.hbase.client.Connection; import org.apache.hadoop.hbase.client.ConnectionFactory; import org.apache.hadoop.hbase.client.Delete; import org.apache.hadoop.hbase.client.Get; 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.client.Table; import org.apache.hadoop.hbase.util.Bytes; import org.junit.Before; import org.junit.Test; public class HbaseClientDML { public static Connection getConn() throws Exception{ // 构建一个连接对象 Connection conn = null; Configuration conf = HBaseConfiguration.create(); // 会自动加载hbase-site.xml conf.set("hbase.zookeeper.quorum", "hdp-01:2181,hdp-02:2181,hdp-03:2181"); return conn = ConnectionFactory.createConnection(conf); } /** * 增 * 改:put来覆盖 * @throws Exception */ public void testPut(Connection con) throws Exception{ // 获取一个操作指定表的table对象,进行DML操作 Table table = con.getTable(TableName.valueOf("user_info")); // 构造要插入的数据为一个Put类型(一个put对象只能对应一个rowkey)的对象 Put put = new Put(Bytes.toBytes("001")); put.addColumn(Bytes.toBytes("base_info"), Bytes.toBytes("username"), Bytes.toBytes("张三")); put.addColumn(Bytes.toBytes("base_info"), Bytes.toBytes("age"), Bytes.toBytes("18")); put.addColumn(Bytes.toBytes("extra_info"), Bytes.toBytes("addr"), Bytes.toBytes("北京")); Put put2 = new Put(Bytes.toBytes("002")); put2.addColumn(Bytes.toBytes("base_info"), Bytes.toBytes("username"), Bytes.toBytes("李四")); put2.addColumn(Bytes.toBytes("base_info"), Bytes.toBytes("age"), Bytes.toBytes("28")); put2.addColumn(Bytes.toBytes("extra_info"), Bytes.toBytes("addr"), Bytes.toBytes("上海")); ArrayList puts = new ArrayList(); puts.add(put); puts.add(put2); // 插进去 table.put(puts); table.close(); con.close(); } /** * 循环插入大量数据 * @throws Exception */ public void testManyPuts(Connection con) throws Exception{ Table table = con.getTable(TableName.valueOf("user_info")); ArrayList puts = new ArrayList(); for(int i=0;i<100000;i++){ Put put = new Put(Bytes.toBytes(""+i)); put.addColumn(Bytes.toBytes("base_info"), Bytes.toBytes("username"), Bytes.toBytes("张三"+i)); put.addColumn(Bytes.toBytes("base_info"), Bytes.toBytes("age"), Bytes.toBytes((18+i)+"")); put.addColumn(Bytes.toBytes("extra_info"), Bytes.toBytes("addr"), Bytes.toBytes("北京")); puts.add(put); } table.put(puts); } /** * 删 * @throws Exception */ public void testDelete(Connection con) throws Exception{ Table table = con.getTable(TableName.valueOf("user_info")); // 构造一个对象封装要删除的数据信息 Delete delete1 = new Delete(Bytes.toBytes("001")); Delete delete2 = new Delete(Bytes.toBytes("002")); delete2.addColumn(Bytes.toBytes("extra_info"), Bytes.toBytes("addr")); ArrayList dels = new ArrayList(); dels.add(delete1); dels.add(delete2); table.delete(dels); table.close(); con.close(); } /** * 查 * @throws Exception */ public void testGet(Connection conn ) throws Exception{ Table table = conn.getTable(TableName.valueOf("user_info")); Get get = new Get("002".getBytes()); Result result = table.get(get); // 从结果中取用户指定的某个key的value byte[] value = result.getValue("base_info".getBytes(), "age".getBytes()); System.out.println(new String(value)); System.out.println("-------------------------"); // 遍历整行结果中的所有kv单元格 CellScanner cellScanner = result.cellScanner(); while(cellScanner.advance()){ Cell cell = cellScanner.current(); byte[] rowArray = cell.getRowArray(); //本kv所属的行键的字节数组 byte[] familyArray = cell.getFamilyArray(); //列族名的字节数组 byte[] qualifierArray = cell.getQualifierArray(); //列名的字节数据 byte[] valueArray = cell.getValueArray(); // value的字节数组 System.out.println("行键: "+new String(rowArray,cell.getRowOffset(),cell.getRowLength())); System.out.println("列族名: "+new String(familyArray,cell.getFamilyOffset(),cell.getFamilyLength())); System.out.println("列名: "+new String(qualifierArray,cell.getQualifierOffset(),cell.getQualifierLength())); System.out.println("value: "+new String(valueArray,cell.getValueOffset(),cell.getValueLength())); } table.close(); conn.close(); } /** * 按行键范围查询数据 * @throws Exception */ public void testScan(Connection conn ) throws Exception{ Table table = conn.getTable(TableName.valueOf("user_info")); // 包含起始行键，不包含结束行键,但是如果真的想查询出末尾的那个行键，那么，可以在末尾行键上拼接一个不可见的字节（ 00） Scan scan = new Scan("10".getBytes(), "10000 01".getBytes()); ResultScanner scanner = table.getScanner(scan); Iterator iterator = scanner.iterator(); // ResultScanner resutScanner = table.getScanner(scan); while(iterator.hasNext()){ Result result = (Result) iterator.next(); // 遍历整行结果中的所有kv单元格 CellScanner cellScanner = result.cellScanner(); while(cellScanner.advance()){ Cell cell = cellScanner.current(); byte[] rowArray = cell.getRowArray(); //本kv所属的行键的字节数组 byte[] familyArray = cell.getFamilyArray(); //列族名的字节数组 byte[] qualifierArray = cell.getQualifierArray(); //列名的字节数据 byte[] valueArray = cell.getValueArray(); // value的字节数组 System.out.println("行键: "+new String(rowArray,cell.getRowOffset(),cell.getRowLength())); System.out.println("列族名: "+new String(familyArray,cell.getFamilyOffset(),cell.getFamilyLength())); System.out.println("列名: "+new String(qualifierArray,cell.getQualifierOffset(),cell.getQualifierLength())); System.out.println("value: "+new String(valueArray,cell.getValueOffset(),cell.getValueLength())); } System.out.println("----------------------"); } } public void test(){ String a = "000"; String b = "000 "; System.out.println(a); System.out.println(b); byte[] bytes = a.getBytes(); byte[] bytes2 = b.getBytes(); System.out.println(""); } public static void main(String []args) { } }
对表的操作
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.TableName; import org.apache.hadoop.hbase.client.Admin; import org.apache.hadoop.hbase.client.Connection; import org.apache.hadoop.hbase.client.ConnectionFactory; import org.apache.hadoop.hbase.regionserver.BloomType; import org.junit.Before; import org.junit.Test; /** * * 1、构建连接 * 2、从连接中取到一个表DDL操作工具admin * 3、admin.createTable(表描述对象); * 4、admin.disableTable(表名); 5、admin.deleteTable(表名); 6、admin.modifyTable(表名，表描述对象); * * @author hunter.d * */ public class HbaseClientDDL { Connection conn = null; public void getConn() throws Exception{ // 构建一个连接对象 Configuration conf = HBaseConfiguration.create(); // 会自动加载hbase-site.xml conf.set("hbase.zookeeper.quorum", "hdp-01:2181,hdp-02:2181,hdp-03:2181"); conn = ConnectionFactory.createConnection(conf); } /** * DDL * @throws Exception */ public void testCreateTable() throws Exception{ // 从连接中构造一个DDL操作器 Admin admin = conn.getAdmin(); // 创建一个表定义描述对象 HTableDescriptor hTableDescriptor = new HTableDescriptor(TableName.valueOf("user_info")); // 创建列族定义描述对象 HColumnDescriptor hColumnDescriptor_1 = new HColumnDescriptor("base_info"); hColumnDescriptor_1.setMaxVersions(3); // 设置该列族中存储数据的最大版本数,默认是1 HColumnDescriptor hColumnDescriptor_2 = new HColumnDescriptor("extra_info"); // 将列族定义信息对象放入表定义对象中 hTableDescriptor.addFamily(hColumnDescriptor_1); hTableDescriptor.addFamily(hColumnDescriptor_2); // 用ddl操作器对象：admin 来建表 admin.createTable(hTableDescriptor); // 关闭连接 admin.close(); conn.close(); } /** * 删除表 * @throws Exception */ public void testDropTable() throws Exception{ Admin admin = conn.getAdmin(); // 停用表 admin.disableTable(TableName.valueOf("user_info")); // 删除表 admin.deleteTable(TableName.valueOf("user_info")); admin.close(); conn.close(); } // 修改表定义--添加一个列族 public void testAlterTable() throws Exception{ Admin admin = conn.getAdmin(); // 取出旧的表定义信息 HTableDescriptor tableDescriptor = admin.getTableDescriptor(TableName.valueOf("user_info")); // 新构造一个列族定义 HColumnDescriptor hColumnDescriptor = new HColumnDescriptor("other_info"); hColumnDescriptor.setBloomFilterType(BloomType.ROWCOL); // 设置该列族的布隆过滤器类型 // 将列族定义添加到表定义对象中 tableDescriptor.addFamily(hColumnDescriptor); // 将修改过的表定义交给admin去提交 admin.modifyTable(TableName.valueOf("user_info"), tableDescriptor); admin.close(); conn.close(); } /** * DML -- 数据的增删改查 */ public static void main(String []args) { // Connection conn = null; Configuration conf = HBaseConfiguration.create(); // 会自动加载hbase-site.xml conf.set("hbase.rootdir", "hdfs://localhost:9000/hbase"); try { conn = ConnectionFactory.createConnection(conf); // 从连接中构造一个DDL操作器 Admin admin = conn.getAdmin(); // 创建一个表定义描述对象 HTableDescriptor hTableDescriptor = new HTableDescriptor(TableName.valueOf("result")); // 创建列族定义描述对象 HColumnDescriptor hColumnDescriptor_1 = new HColumnDescriptor("info"); hColumnDescriptor_1.setMaxVersions(3); // 设置该列族中存储数据的最大版本数,默认是1 HColumnDescriptor hColumnDescriptor_2 = new HColumnDescriptor("extra_info"); // 将列族定义信息对象放入表定义对象中 hTableDescriptor.addFamily(hColumnDescriptor_1); //hTableDescriptor.addFamily(hColumnDescriptor_2); // 用ddl操作器对象：admin 来建表 admin.createTable(hTableDescriptor); // 关闭连接 admin.close(); conn.close(); } catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace(); } } }