hadoop之hbase操作（二）

it2022-05-05 141

标签（空格分隔）： hadoop

hbase的操作

hbase的shell交互操作（常用操作）

入口： $HBASE_HOME/bin/hbase shell 退出： > quit 定义： >create ‘表名’, ‘列族名1’,‘列族名2’,‘列族名N’ 例： create ‘people’,‘student’,‘businessman’ 创建一个人的表列族有学生和商人。

list # 查询所有表 desc ‘people’ 查看表结构 exists ‘people’ 查看表是否存在 is_enabled ‘people’ 启用表 is_disabled ‘people’ 禁用表 #添加修改记录(如果rowkey和列族列名都一致则后者覆盖前者，但前者版本记录还是会有保留默认版本为时间戳) put ‘表名’, ‘rowKey’, ‘列族 : 列’ , ‘值’ put ‘people’,‘stu_123’,‘student:name’,‘zhangsan’ put ‘people’,‘stu_123’,‘student:age’,‘10’ put ‘people’,‘stu_123’,‘businessman:name’,‘lisi’ put ‘people’,‘stu_1234’,‘student:name’,‘wangwu’ 查询记录 get ‘表名’ , ‘rowKey’ # 获取rowkey下的所有数据 get ‘people’,‘stu_123’ count ‘表名’ 注意这里是1条，以rowkey作为条数，虽然是列式的 get ‘表名’,‘rowkey’,‘列族’ # 获取某个列族 get ‘people’,‘stu_123’,‘student’ get ‘表名’,‘rowkey’,‘列族：列’ # 获取某个列由此可以看出要获取的越详细其实就是在后面的多用，间隔子结构即可 get ‘people’,‘stu_123’,‘student:name’ 查询整张表记录 scan “表名” 查看某个表某个列中所有数据 scan “表名” , {COLUMNS=>‘列族名:列名’} 删除记录 delete ‘表名’ ,‘行名’ , ‘列族：列’ delete ‘people’,‘stu_123’,‘student:name’ deleteall ‘表名’,‘rowkey’ 删除郑航 deleteall ‘people’,‘stu_123’ 删除整张表先要屏蔽该表，才能对该表进行删除第一步 disable ‘表名’ ，第二步 drop ‘表名’ 清空表： truncate ‘表名’

hbase的api操作

首先我们来介绍一下相关的api，让我们大体上有个了解，之后再根据这些api来做一下hbase的相关操作。套路一：配置项 HBaseConfiguration与Hdfs的操作一样需要配置类作为操作的相关配置。之后是hbase的核心操作类 HBaseAdmin 该类提供接口提供hbase的相关操作入口 HTableDescriptor 表描述类，包含表和列族的信息，用于表设计既然有表描述类了就必须要有列族信息 HColumnDescriptor 这个是用于做列族信息的定义类以下是做的一些相关hbase操作的javaapi，总结一下就是与命令行是一一对应的关系，在方法和类的命名上。还有如果涉及到定义的话用HbaseAdmin如果涉及到表的数据操作的话用Table类操作。

package com.dinfo.hbase; import org.apache.curator.framework.state.ConnectionStateManager; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.hbase.*; import org.apache.hadoop.hbase.client.*; import org.apache.hadoop.hbase.filter.*; import org.apache.hadoop.hbase.util.Bytes; import org.junit.After; import org.junit.Before; import org.junit.Test; import java.io.IOException; import java.util.ArrayList; import java.util.Arrays; import java.util.List; /** * Created by： luo * date: 2019/7/15. * desc： */ public class HBaseApiOps { Configuration conf = null; Table table = null;//用于做相关表操作的信息 Connection conn =null; @Before public void before() throws IOException { conf = HBaseConfiguration.create(); conf.set("hbase.zookeeper.quorum", "hadoop1,hadoop2,hadoop3"); conf.set("hbase.zookeeper.property.clientPort", "2181"); conn = ConnectionFactory.createConnection(conf); table = conn.getTable(TableName.valueOf("user")); } @Test public void testCreateTable() throws IOException { Admin admin = conn.getAdmin(); TableName tableName = TableName.valueOf("user"); // 表名称 HTableDescriptor desc = new HTableDescriptor(tableName); // 创建列族的描述类 HColumnDescriptor family = new HColumnDescriptor("info"); // 列族 // 将列族添加到表中 desc.addFamily(family); HColumnDescriptor family2 = new HColumnDescriptor("info2"); // 列族 // 将列族添加到表中 desc.addFamily(family2); admin.createTable(desc); } @Test public void testDropTable() throws IOException { Admin admin = conn.getAdmin(); TableName tName = TableName.valueOf("user"); admin.disableTable(tName); admin.deleteTable(tName); } /** * 插入前面定义我们用了hadmin 这里我们dml的时候直接用table就可了 * @throws IOException */ @Test public void testInsertOrUpdate() throws IOException { Put put = new Put(Bytes.toBytes("u_1234")); put.add(Bytes.toBytes("info"), Bytes.toBytes("name"), Bytes.toBytes("zhangsan")); table.put(put); } @Test public void batchInsert() throws IOException { List<Put> puts = new ArrayList<>(); for(int i =0;i<10;i++){ Put put = new Put(Bytes.toBytes("u_123"+i)); put.add(Bytes.toBytes("info"), Bytes.toBytes("name"), Bytes.toBytes("zhangsan" + i)); put.add(Bytes.toBytes("info"), Bytes.toBytes("age"), Bytes.toBytes(i+10)); puts.add(put); } table.put(puts); } /** * 删除一行rowkey * @throws IOException */ @Test public void testDel() throws IOException { //从上面可以知道 table的操作还是比较好记的用table调用put传put对象 delte传delete对象 scan传scan对象我们试下del Delete delete = new Delete(Bytes.toBytes("u_1230")); table.delete(delete); table.flushCommits(); } @Test public void testDelColumnFamily() throws IOException { //删除某个列 Delete del = new Delete(Bytes.toBytes("u_1232")); del.addColumn(Bytes.toBytes("info"),Bytes.toBytes("name")); table.delete(del); } /** * 以下为相关查询的api */ //单条查询 @Test public void testGet() throws IOException { //这里对照命令行的get Get get = new Get(Bytes.toBytes("u_1233")); Result result = table.get(get); Cell[] cells = result.rawCells(); for(Cell ce:cells){ System.out.println("row:"+ new String(ce.getRowArray(),ce.getRowOffset(),ce.getRowLength())); System.out.println("family:"+ new String(ce.getFamilyArray(),ce.getFamilyOffset(),ce.getFamilyLength())); String qualifie = new String(ce.getQualifierArray(),ce.getQualifierOffset(),ce.getQualifierLength()); System.out.println("Qualifier:"+qualifie ); if(qualifie.equals("name")){ System.out.println("value:"+ new String(ce.getValueArray(),ce.getValueOffset(),ce.getValueLength())); }else{ System.out.println("value:"+ Bytes.toInt(ce.getValueArray())); } System.out.println("time:"+ce.getTimestamp()); } } @Test public void testBatchQuery() throws IOException { Scan scan = new Scan(); scan.setStartRow("u_1232".getBytes()); scan.setStopRow("u_1235".getBytes()); ResultScanner result = table.getScanner(scan); printScanResult(result); } private void printScanResult(ResultScanner result) { result.forEach(r -> Arrays.stream(r.rawCells()).forEach( ce -> { System.out.println("row:"+ new String(ce.getRowArray(),ce.getRowOffset(),ce.getRowLength())); System.out.println("family:"+ new String(ce.getFamilyArray(),ce.getFamilyOffset(),ce.getFamilyLength())); String qualifie = new String(ce.getQualifierArray(),ce.getQualifierOffset(),ce.getQualifierLength()); System.out.println("Qualifier:"+qualifie ); if(qualifie.equals("name")){ System.out.println("value:"+ new String(ce.getValueArray(),ce.getValueOffset(),ce.getValueLength())); }else{ System.out.println("value:"+ Bytes.toInt(ce.getValueArray())); } System.out.println("time:"+ce.getTimestamp()); } )); } /** * 全面一种是一行扫描一种是scan扫描接下来这个是过滤扫描 */ @Test public void testSingleFilterQuery() throws IOException { Scan scan = new Scan(); FilterList filterList = new FilterList(FilterList.Operator.MUST_PASS_ONE);//过滤器列表本身也是实现过滤器 filterList.addFilter(new SingleColumnValueFilter(Bytes.toBytes("info"), Bytes.toBytes("name"), CompareFilter.CompareOp.EQUAL,Bytes.toBytes("zhangsan4"))); filterList.addFilter(new SingleColumnValueFilter(Bytes.toBytes("info"), Bytes.toBytes("name"), CompareFilter.CompareOp.EQUAL,Bytes.toBytes("zhangsan3")));//单一列值过滤器 scan.setFilter(filterList); ResultScanner result = table.getScanner(scan); printScanResult(result); //注意：如果过滤器过滤的列在数据表中有的行中不存在，那么这个过滤器对此行无法过滤。 } @Test public void testColumnPreffix() throws IOException { Scan scan = new Scan(); scan.setFilter(new ColumnPrefixFilter("age".getBytes())); ResultScanner result = table.getScanner(scan); printScanResult(result); } //多个列值前缀 @Test public void testMColumnPreffix() throws IOException { Scan scan = new Scan(); byte[][] bys = new byte[][]{Bytes.toBytes("n"),Bytes.toBytes("a")}; scan.setFilter(new MultipleColumnPrefixFilter(bys)); ResultScanner result = table.getScanner(scan); printScanResult(result); } //对rowkey上做文章的过滤器 @Test public void testRowFilter() throws IOException { Scan scan = new Scan(); scan.setFilter(new RowFilter(CompareFilter.CompareOp.EQUAL,new RegexStringComparator("1239$"))); ResultScanner result = table.getScanner(scan); printScanResult(result); } @After public void close() throws IOException { conn.close(); } }

自选删除相关操作，无论是删除还是get对列族啊列啊的设置都差不多，这个api还是很容易上手的。如下图是Delete类的相关设置方法截图。

专利

最新回复(0)