JAVA 连接 Hbase1.2.3查询

完整程序下载: https://github.com/szxiaokang/hbaseAPI

如果解决了你的问题, 给个Star, 3Q :)

首先说下环境, 在windowns 下安装了三台虚拟机, 网卡桥接的, 每台有独立的ip, 分别为:

10.68.128.215 master
10.68.128.212 slave1
10.68.128.211 slave2

hadoop 版本2.7.1

hbase 版本 1.2.3

zookeeper版本 3.4.9

系统已启动, 切已正常运行. windows 下的hosts文件已经做了绑定

需要的 jar包

hadoop-common-2.7.1.jar
hbase-common-1.2.3.jar
hbase-hadoop-compat-1.2.3.jar
hbase-thrift-1.2.3.jar
zookeeper-3.4.9.jar
commons-codec-1.9.jar
commons-configuration-1.6.jar
hbase-client-1.2.3.jar
hbase-server-1.2.3.jar
slf4j-api-1.7.7.jar
slf4j-log4j12-1.7.5.jar
log4j-1.2-api-2.4.1.jar
log4j-api-2.4.1.jar
log4j-core-2.4.1.jar
log4j-slf4j-impl-2.4.1.jar
log4j-web-2.4.1.jar
commons-logging-1.2.jar
guava-12.0.1.jar
commons-collections-3.2.2.jar
commons-lang-2.6.jar
hadoop-annotations-2.7.1.jar
hadoop-auth-2.7.1.jar
protobuf-java-2.5.0.jar
hbase-protocol-1.2.3.jar
htrace-core-3.1.0-incubating.jar
netty-all-4.0.23.Final.jar
commons-cli-1.2.jar
metrics-core-2.2.0.jar
jackson-core-asl-1.9.13.jar
jackson-jaxrs-1.9.13.jar
jackson-mapper-asl-1.9.13.jar
jackson-xc-1.9.13.jar

都是从hbase与hadoop的lib与share目录下载的

程序如下

/**
 * @ClassName:     Query.java
 * @author         Kang 273030282@qq.com
 * @version        V1.0 
 * @Date           2016-10-26 上午10:52:50
 * @Description:   TODO
 *
 */

package kang.com.cn;

import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;

public class Query {

	public static Configuration configuration;
	public static Connection connection;
	public static Admin admin;

	public static void main(String[] args) throws IOException {
		println("Start...");
		
		listTables();
		
		getData("member", "angelababy");
		
		println("End...");
	}

	/**
	 * 初始化链接
	 */
	public static void init() {
		configuration = HBaseConfiguration.create();
		configuration.set("hbase.zookeeper.property.clientPort", "2181");
		configuration.set("hbase.zookeeper.quorum", "10.68.128.215,10.68.128.211,10.68.128.212");
		configuration.set("hbase.master", "hdfs://10.68.128.215:60000");
		configuration.set("hbase.root.dir", "hdfs://10.68.128.215:9000/hbase");

		try {
			connection = ConnectionFactory.createConnection(configuration);
			admin = connection.getAdmin();
		} catch (IOException e) {
			e.printStackTrace();
		}
	}

	/**
	 * 关闭连接
	 */
	public static void close() {
		try {
			if (null != admin) {
				admin.close();
			}
			if (null != connection) {
				connection.close();
			}
		} catch (IOException e) {
			e.printStackTrace();
		}
	}

	/**
	 * 创建表
	 * 
	 * @param tableName 表名
	 * @param family 列族列表
	 * @throws IOException
	 */
	public static void createTable(String tableName, String[] cols) throws IOException {
		init();
		TableName tName = TableName.valueOf(tableName);
		if (admin.tableExists(tName)) {
			println(tableName + " exists.");
		} else {
			HTableDescriptor hTableDesc = new HTableDescriptor(tName);
			for (String col : cols) {
				HColumnDescriptor hColumnDesc = new HColumnDescriptor(col);
				hTableDesc.addFamily(hColumnDesc);
			}
			admin.createTable(hTableDesc);
		}

		close();
	}

	/**
	 * 删除表
	 * 
	 * @param tableName 表名称
	 * @throws IOException
	 */
	public static void deleteTable(String tableName) throws IOException {
		init();
		TableName tName = TableName.valueOf(tableName);
		if (admin.tableExists(tName)) {
			admin.disableTable(tName);
			admin.deleteTable(tName);
		} else {
			println(tableName + " not exists.");
		}
		close();
	}

	/**
	 * 查看已有表
	 * 
	 * @throws IOException
	 */
	public static void listTables() {
		init();
		HTableDescriptor hTableDescriptors[] = null;
		try {
			hTableDescriptors = admin.listTables();
		} catch (IOException e) {
			// TODO Auto-generated catch block
			e.printStackTrace();
		}
		for (HTableDescriptor hTableDescriptor : hTableDescriptors) {
			println(hTableDescriptor.getNameAsString());
		}
		close();
	}

	/**
	 * 插入单行
	 * 
	 * @param tableName 表名称
	 * @param rowKey RowKey
	 * @param colFamily 列族
	 * @param col 列
	 * @param value 值
	 * @throws IOException
	 */
	public static void insert(String tableName, String rowKey, String colFamily, String col, String value) throws IOException {
		init();
		Table table = connection.getTable(TableName.valueOf(tableName));
		Put put = new Put(Bytes.toBytes(rowKey));
		put.addColumn(Bytes.toBytes(colFamily), Bytes.toBytes(col), Bytes.toBytes(value));
		table.put(put);

		/*
		 * 批量插入 List<Put> putList = new ArrayList<Put>(); puts.add(put); table.put(putList);
		 */

		table.close();
		close();
	}

	public static void delete(String tableName, String rowKey, String colFamily, String col) throws IOException {
		init();

		if (!admin.tableExists(TableName.valueOf(tableName))) {
			println(tableName + " not exists.");
		} else {
			Table table = connection.getTable(TableName.valueOf(tableName));
			Delete del = new Delete(Bytes.toBytes(rowKey));
			if (colFamily != null) {
				del.addFamily(Bytes.toBytes(colFamily));
			}
			if (colFamily != null && col != null) {
				del.addColumn(Bytes.toBytes(colFamily), Bytes.toBytes(col));
			}
			/*
			 * 批量删除 List<Delete> deleteList = new ArrayList<Delete>(); deleteList.add(delete); table.delete(deleteList);
			 */
			table.delete(del);
			table.close();
		}
		close();
	}

	/**
	 * 根据RowKey获取数据
	 * 
	 * @param tableName 表名称
	 * @param rowKey RowKey名称
	 * @param colFamily 列族名称
	 * @param col 列名称
	 * @throws IOException
	 */
	public static void getData(String tableName, String rowKey, String colFamily, String col) throws IOException {
		init();
		Table table = connection.getTable(TableName.valueOf(tableName));
		Get get = new Get(Bytes.toBytes(rowKey));
		if (colFamily != null) {
			get.addFamily(Bytes.toBytes(colFamily));
		}
		if (colFamily != null && col != null) {
			get.addColumn(Bytes.toBytes(colFamily), Bytes.toBytes(col));
		}
		Result result = table.get(get);
		showCell(result);
		table.close();
		close();
	}

	/**
	 * 根据RowKey获取信息
	 * 
	 * @param tableName
	 * @param rowKey
	 * @throws IOException
	 */
	public static void getData(String tableName, String rowKey) throws IOException {
		getData(tableName, rowKey, null, null);
	}

	/**
	 * 格式化输出
	 * 
	 * @param result
	 */
	public static void showCell(Result result) {
		Cell[] cells = result.rawCells();
		for (Cell cell : cells) {
			println("RowName: " + new String(CellUtil.cloneRow(cell)) + " ");
			println("Timetamp: " + cell.getTimestamp() + " ");
			println("column Family: " + new String(CellUtil.cloneFamily(cell)) + " ");
			println("row Name: " + new String(CellUtil.cloneQualifier(cell)) + " ");
			println("value: " + new String(CellUtil.cloneValue(cell)) + " ");
		}
	}

	/**
	 * 打印
	 * 
	 * @param obj 打印对象
	 */
	private static void println(Object obj) {
		System.out.println(obj);
	}
}

Hbase中的数据:

hbase(main):018:0> list
TABLE                                                                                                                     
domain_table                                                                                                              
member                                                                                                                    
2 row(s) in 0.0120 seconds

=> ["domain_table", "member"]
hbase(main):019:0> scan 'member'
ROW                             COLUMN+CELL                                                                               
 angelababy                     column=address:city, timestamp=1477376233811, value=ShangHai                              
 angelababy                     column=address:contry, timestamp=1477376192558, value=China                               
 angelababy                     column=info:age, timestamp=1477375647675, value=27                                        
 angelababy                     column=info:birthday, timestamp=1477375750883, value=1989-2-28                            
 angelababy                     column=info:company, timestamp=1477376154357, value=TaiYangChuanHe                        
 angelababy                     column=info:height, timestamp=1477375972466, value=168cm                                  
 angelababy                     column=info:weight, timestamp=1477376025268, value=45kg                                   
 angelababy                     column=member_id:number, timestamp=1477632132701, value=2                                 
 angelababy                     column=name:chinese, timestamp=1477378496767, value=\xE6\x9D\xA8\xE9\xA2\x96              
 angelababy                     column=name:english, timestamp=1477378538782, value=angelababy                            
 gaoyuanyuan                    column=address:city, timestamp=1477379052063, value=BeiJing                               
 gaoyuanyuan                    column=address:contry, timestamp=1477379037776, value=China                               
 gaoyuanyuan                    column=info:age, timestamp=1477378745014, value=37                                        
 gaoyuanyuan                    column=info:birthday, timestamp=1477378781555, value=1979-10-5                            
 gaoyuanyuan                    column=info:company, timestamp=1477378994114, value=GaoYuanYuanGongZuoShi                 
 gaoyuanyuan                    column=info:height, timestamp=1477378658944, value=165cm                                  
 gaoyuanyuan                    column=info:weight, timestamp=1477378674360, value=48kg                                   
 gaoyuanyuan                    column=member_id:number, timestamp=1477379130831, value=1                                 
 gaoyuanyuan                    column=name:chinese, timestamp=1477378621922, value=\xE9\xAB\x98\xE5\x9C\x86\xE5\x9C\x86  
 gaoyuanyuan                    column=name:english, timestamp=1477378592003, value=Gao YuanYuan                          
2 row(s) in 0.1200 seconds

运行结果:

Start...
15:29:03.806 DEBUG org.apache.hadoop.security.Groups 301 getUserToGroupsMappingService -  Creating new Groups object
15:29:03.846 DEBUG org.apache.hadoop.util.NativeCodeLoader 46 <clinit> - Trying to load the custom-built native-hadoop library...
.....
15:29:04.735 TRACE org.apache.hadoop.io.FastByteComparisons$LexicographicalComparerHolder 93 getBestComparer - Unsafe comparer selected for byte unaligned system architecture
domain_table
member
15:29:04.744 INFO  org.apache.hadoop.hbase.client.ConnectionManager$HConnectionImplementation 2139 closeMasterService - Closing master protocol: MasterService
....
15:29:04.952 TRACE org.apache.hadoop.hbase.client.ScannerCallableWithReplicas 234 updateCurrentlyServingReplica - Setting current scanner as id=-1 associated with replica=0
15:29:04.967 TRACE org.apache.hadoop.hbase.client.MetaCache 175 cacheLocation - Merged cached locations: [region=member,,1477375368907.9ca5604d5939499dc276340d29994208., hostname=slave1,16020,1477617236309, seqNum=47]
15:29:04.994 TRACE org.apache.hadoop.hbase.ipc.AbstractRpcClient 236 callBlockingMethod - Call: Get, callTime: 18ms
RowName: angelababy 
Timetamp: 1477376233811 
column Family: address 
row Name: city 
value: ShangHai 
RowName: angelababy 
Timetamp: 1477376192558 
column Family: address 
row Name: contry 
value: China 
RowName: angelababy 
Timetamp: 1477375647675 
column Family: info 
row Name: age 
value: 27 
RowName: angelababy 
Timetamp: 1477375750883 
column Family: info 
row Name: birthday 
value: 1989-2-28 
RowName: angelababy 
Timetamp: 1477376154357 
column Family: info 
row Name: company 
value: TaiYangChuanHe 
RowName: angelababy 
Timetamp: 1477375972466 
column Family: info 
row Name: height 
value: 168cm 
RowName: angelababy 
Timetamp: 1477376025268 
column Family: info 
row Name: weight 
value: 45kg 
RowName: angelababy 
Timetamp: 1477632132701 
column Family: member_id 
row Name: number 
value: 2 
RowName: angelababy 
Timetamp: 1477378496767 
column Family: name 
row Name: chinese 
value: 杨颖 
RowName: angelababy 
Timetamp: 1477378538782 
column Family: name 
row Name: english 
value: angelababy 
15:29:04.996 INFO  org.apache.hadoop.hbase.client.ConnectionManager$HConnectionImplementation 1710 closeZooKeeperWatcher - Closing zookeeper sessionid=0x158091bd27b000a
.....
15:29:05.016 TRACE org.apache.hadoop.hbase.ipc.RpcClientImpl$Connection 570 run - IPC Client (1375204579) connection to slave1/10.68.128.212:16020 from kangyun: interrupted while waiting for call responses
15:29:05.016 TRACE org.apache.hadoop.hbase.ipc.RpcClientImpl$Connection 1060 markClosed - IPC Client (1375204579) connection to slave1/10.68.128.212:16020 from kangyun: marking at should close, reason: Origin: InterruptedException
15:29:05.017 TRACE org.apache.hadoop.hbase.ipc.RpcClientImpl$Connection 860 close - IPC Client (1375204579) connection to slave1/10.68.128.212:16020 from kangyun: closing ipc connection to slave1/10.68.128.212:16020
15:29:05.017 TRACE org.apache.hadoop.hbase.ipc.RpcClientImpl$Connection 866 close - IPC Client (1375204579) connection to slave1/10.68.128.212:16020 from kangyun: ipc connection to slave1/10.68.128.212:16020 closed
15:29:05.017 TRACE org.apache.hadoop.hbase.ipc.RpcClientImpl$Connection 583 run - IPC Client (1375204579) connection to slave1/10.68.128.212:16020 from kangyun: stopped, connections 0
End...

遇到的问题说下.

第一个问题: 程序运行之后没有反应, 没有日志

此问题是因为没有配置 log4j2.xml (不是log4j.xml)

在包根目录下新建一个 log4j2.xml, 内容如下, 可以根据你的需要修改

<?xml version="1.0" encoding="UTF-8"?>

<configuration status="error">
    <!--先定义所有的appender-->
    <appenders>
        <!--这个输出控制台的配置-->
        <Console name="Console" target="SYSTEM_OUT">
            <!--控制台只输出level及以上级别的信息（onMatch），其他的直接拒绝（onMismatch）-->
            <ThresholdFilter level="trace" onMatch="ACCEPT" onMismatch="DENY"/>
            <!--这个都知道是输出日志的格式-->
            <PatternLayout pattern="%d{HH:mm:ss.SSS} %-5level %class{36} %L %M - %msg%xEx%n"/>
        </Console>
        <!--文件会打印出所有信息，这个log每次运行程序会自动清空，由append属性决定，这个也挺有用的，适合临时测试用
        <File name="log" fileName="log/test.log" append="false">
            <PatternLayout pattern="%d{HH:mm:ss.SSS} %-5level %class{36} %L %M - %msg%xEx%n"/>
        </File>-->

        <!--这个会打印出所有的信息，每次大小超过size，则这size大小的日志会自动存入按年份-月份建立的文件夹下面并进行压缩，作为存档-->
        <RollingFile name="RollingFile" fileName="query.log"
                     filePattern="log/$${date:yyyy-MM}/app-%d{MM-dd-yyyy}-%i.log.gz">
            <PatternLayout pattern="%d{yyyy-MM-dd 'at' HH:mm:ss z} %-5level %class{36} %L %M - %msg%xEx%n"/>
            <SizeBasedTriggeringPolicy size="50MB"/>
        </RollingFile>
    </appenders>
    <!--然后定义logger，只有定义了logger并引入的appender，appender才会生效-->
    <loggers>
        <!--建立一个默认的root的logger-->
        <root level="trace">
            <appender-ref ref="RollingFile"/>
            <appender-ref ref="Console"/>
        </root>

    </loggers>
</configuration>

这样控制台会打印相关的信息, 根据报的错误做相应的修改, 一般都是缺包

第二个问题: 没有查询到预期的信息

运行之后一直没有出来预期的结果, 大概的日志信息长这样:

2016-10-27 at 14:35:46 CST INFO  org.apache.zookeeper.ClientCnxn$SendThread 876 primeConnection - Socket connection established to slave2/10.68.128.211:2181, initiating session
2016-10-27 at 14:35:46 CST DEBUG org.apache.zookeeper.ClientCnxn$SendThread 949 primeConnection - Session establishment request sent on slave2/10.68.128.211:2181
2016-10-27 at 14:35:46 CST TRACE org.apache.zookeeper.ClientCnxnSocket 124 readConnectResult - readConnectResult 37 0x[0,0,0,0,0,0,ffffff9c,40,3,58,3,ffffffb9,ffffffd5,2c,0,c,0,0,0,10,1b,c,3c,60,b,6b,ffffffaf,76,ffffff83,ffffffff,ffffff9c,25,38,fffffff8,32,ffffff82,0,]
2016-10-27 at 14:35:46 CST INFO  org.apache.zookeeper.ClientCnxn$SendThread 1299 onConnected - Session establishment complete on server slave2/10.68.128.211:2181, sessionid = 0x35803b9d52c000c, negotiated timeout = 40000
2016-10-27 at 14:35:46 CST DEBUG org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher 602 process - hconnection-0x31e0fd3d0x0, quorum=master:2181,slave1:2181,slave2:2181, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null
2016-10-27 at 14:35:46 CST DEBUG org.apache.hadoop.hbase.zookeeper.ZooKeeperWatcher 686 connectionEvent - hconnection-0x31e0fd3d-0x35803b9d52c000c connected
2016-10-27 at 14:35:46 CST DEBUG org.apache.zookeeper.ClientCnxn$SendThread 843 readResponse - Reading reply sessionid:0x35803b9d52c000c, packet:: clientPath:null serverPath:null finished:false header:: 1,3  replyHeader:: 1,111669149796,0  request:: '/hbase/hbaseid,F  response:: s{17179869199,111669149705,1475908620421,1477531322314,25,0,0,0,67,0,17179869199} 
2016-10-27 at 14:35:46 CST DEBUG org.apache.zookeeper.ClientCnxn$SendThread 843 readResponse - Reading reply sessionid:0x35803b9d52c000c, packet:: clientPath:null serverPath:null finished:false header:: 2,4  replyHeader:: 2,111669149796,0  request:: '/hbase/hbaseid,F  response:: #ffffffff000146d61737465723a3136303030ffffffe06554104326ffffffc71850425546a2430643365353666652d646631642d343734632d626538322d646536356137353336363632,s{17179869199,111669149705,1475908620421,1477531322314,25,0,0,0,67,0,17179869199} 
2016-10-27 at 14:35:46 CST TRACE org.apache.hadoop.hbase.zookeeper.ZKUtil 1935 logRetrievedMsg - hconnection-0x31e0fd3d-0x35803b9d52c000c, quorum=master:2181,slave1:2181,slave2:2181, baseZNode=/hbase Retrieved 42 byte(s) of data from znode /hbase/hbaseid; data=PBUF\x0A$0d3e56fe-df1d-474c-b...
2016-10-27 at 14:35:46 CST DEBUG org.apache.hadoop.hbase.ipc.AbstractRpcClient 116 <init> - Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@374f910c, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=false, bind address=null
2016-10-27 at 14:35:46 CST DEBUG org.apache.zookeeper.ClientCnxn$SendThread 843 readResponse - Reading reply sessionid:0x35803b9d52c000c, packet:: clientPath:null serverPath:null finished:false header:: 3,3  replyHeader:: 3,111669149796,0  request:: '/hbase,F  response:: s{17179869186,17179869186,1475908611213,1475908611213,0,168,0,0,0,16,111669149727} 
2016-10-27 at 14:35:46 CST DEBUG org.apache.zookeeper.ClientCnxn$SendThread 843 readResponse - Reading reply sessionid:0x35803b9d52c000c, packet:: clientPath:null serverPath:null finished:false header:: 4,4  replyHeader:: 4,111669149796,0  request:: '/hbase/master,F  response:: #ffffffff000146d61737465723a3136303030ffffffcbffffffb7b17ffffffa6ffffffcfffffff96ffffffd650425546a12a66d617374657210ffffff807d18ffffffd4ffffffe9ffffffe9ffffff9dffffff802b10018ffffff8a7d,s{111669149701,111669149701,1477531311006,1477531311006,0,0,0,240946676744585216,54,0,111669149701} 

每隔几秒就会在刷一次, 本人的解决办法是将 程序中配置的 master, slave1, slave2 全部改成ip即可

完整程序下载: https://github.com/szxiaokang/hbaseAPI

如果解决了你的问题, 给个Star, 3Q :)