Hbase的客户端有原生java客户端,Hbase Shell,Thrift,Rest,Mapreduce,WebUI等等。java
下面是这几种客户端的常见用法。python
原生java客户端是hbase最主要,最高效的客户端。c++
涵盖了增删改查等API,还实现了建立,删除,修改表等DDL操做。web
Java链接HBase须要两个类:shell
HBaseConfiguration
ConnectionFactory
首先,配置一个hbase链接:apache
好比zookeeper的地址端口
hbase.zookeeper.quorum
hbase.zookeeper.property.clientPort复制代码
更通用的作法是编写hbase-site.xml文件,实现配置文件的加载:bootstrap
hbase-site.xml示例:数组
<configuration>
<property>
<name>hbase.master</name>
<value>hdfs://host1:60000</value>
</property>
<property>
<name>hbase.zookeeper.quorum</name>
<value>host1,host2,host3</value>
</property>
<property>
<name>hbase.zookeeper.property.clientPort</name>
<value>2181</value>
</property>
</configuration>复制代码
随后咱们加载配置文件,建立链接:ruby
config.addResource(new Path(System.getenv("HBASE_CONF_DIR"), "hbase-site.xml"));
Connection connection = ConnectionFactory.createConnection(config);复制代码
要建立表咱们须要首先建立一个Admin
对象服务器
Admin admin = connection.getAdmin(); //使用链接对象获取Admin对象
TableName tableName = TableName.valueOf("test");//定义表名
HTableDescriptor htd = new HTableDescriptor(tableName);//定义表对象
HColumnDescriptor hcd = new HColumnDescriptor("data");//定义列族对象
htd.addFamily(hcd); //添加
admin.createTable(htd);//建立表复制代码
HBase2.X 的版本中建立表使用了新的 API
TableName tableName = TableName.valueOf("test");//定义表名
//TableDescriptor对象经过TableDescriptorBuilder构建;
TableDescriptorBuilder tableDescriptor = TableDescriptorBuilder.newBuilder(tableName);
ColumnFamilyDescriptor family = ColumnFamilyDescriptorBuilder.newBuilder(Bytes.toBytes("data")).build();//构建列族对象
tableDescriptor.setColumnFamily(family);//设置列族
admin.createTable(tableDescriptor.build());//建立表复制代码
Table table = connection.getTable(tableName);//获取Table对象
try {
byte[] row = Bytes.toBytes("row1"); //定义行
Put put = new Put(row); //建立Put对象
byte[] columnFamily = Bytes.toBytes("data"); //列
byte[] qualifier = Bytes.toBytes(String.valueOf(1)); //列族修饰词
byte[] value = Bytes.toBytes("张三丰"); //值
put.addColumn(columnFamily, qualifier, value);
table.put(put); //向表中添加数据
} finally {
//使用完了要释放资源
table.close();
}复制代码
//获取数据
Get get = new Get(Bytes.toBytes("row1")); //定义get对象
Result result = table.get(get); //经过table对象获取数据
System.out.println("Result: " + result);
//不少时候咱们只须要获取“值” 这里表示获取 data:1 列族的值
byte[] valueBytes = result.getValue(Bytes.toBytes("data"), Bytes.toBytes("1")); //获取到的是字节数组
//将字节转成字符串
String valueStr = new String(valueBytes,"utf-8");
System.out.println("value:" + valueStr);复制代码
Scan scan = new Scan();
ResultScanner scanner = table.getScanner(scan);
try {
for (Result scannerResult: scanner) {
System.out.println("Scan: " + scannerResult);
byte[] row = scannerResult.getRow();
System.out.println("rowName:" + new String(row,"utf-8"));
}
} finally {
scanner.close();
}复制代码
TableName tableName = TableName.valueOf("test");
admin.disableTable(tableName); //禁用表
admin.deleteTable(tableName); //删除表复制代码
Hbase Java API表DDL完整示例:
package com.example.hbase.admin;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HConstants;
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.io.compress.Compression.Algorithm;
public class Example {
private static final String TABLE_NAME = "MY_TABLE_NAME_TOO";
private static final String CF_DEFAULT = "DEFAULT_COLUMN_FAMILY";
public static void createOrOverwrite(Admin admin, HTableDescriptor table) throws IOException {
if (admin.tableExists(table.getTableName())) {
admin.disableTable(table.getTableName());
admin.deleteTable(table.getTableName());
}
admin.createTable(table);
}
public static void createSchemaTables(Configuration config) throws IOException {
try (Connection connection = ConnectionFactory.createConnection(config);
Admin admin = connection.getAdmin()) {
HTableDescriptor table = new HTableDescriptor(TableName.valueOf(TABLE_NAME));
table.addFamily(new HColumnDescriptor(CF_DEFAULT).setCompressionType(Algorithm.NONE));
System.out.print("Creating table. ");
createOrOverwrite(admin, table);
System.out.println(" Done.");
}
}
public static void modifySchema (Configuration config) throws IOException {
try (Connection connection = ConnectionFactory.createConnection(config);
Admin admin = connection.getAdmin()) {
TableName tableName = TableName.valueOf(TABLE_NAME);
if (!admin.tableExists(tableName)) {
System.out.println("Table does not exist.");
System.exit(-1);
}
HTableDescriptor table = admin.getTableDescriptor(tableName);
// 更新表格
HColumnDescriptor newColumn = new HColumnDescriptor("NEWCF");
newColumn.setCompactionCompressionType(Algorithm.GZ);
newColumn.setMaxVersions(HConstants.ALL_VERSIONS);
admin.addColumn(tableName, newColumn);
// 更新列族
HColumnDescriptor existingColumn = new HColumnDescriptor(CF_DEFAULT);
existingColumn.setCompactionCompressionType(Algorithm.GZ);
existingColumn.setMaxVersions(HConstants.ALL_VERSIONS);
table.modifyFamily(existingColumn);
admin.modifyTable(tableName, table);
// 禁用表格
admin.disableTable(tableName);
// 删除列族
admin.deleteColumn(tableName, CF_DEFAULT.getBytes("UTF-8"));
// 删除表格(需提早禁用)
admin.deleteTable(tableName);
}
}
public static void main(String... args) throws IOException {
Configuration config = HBaseConfiguration.create();
//添加必要配置文件(hbase-site.xml, core-site.xml)
config.addResource(new Path(System.getenv("HBASE_CONF_DIR"), "hbase-site.xml"));
config.addResource(new Path(System.getenv("HADOOP_CONF_DIR"), "core-site.xml"));
createSchemaTables(config);
modifySchema(config);
}
}复制代码
在 HBase 安装目录 bin/ 目录下使用hbase shell
命令链接正在运行的 HBase 实例。
$ ./bin/hbase shell
hbase(main):001:0>复制代码
输入help
并回车, 能够看到 HBase Shell 的基本信息和一些示例命令.
使用 create
建立一个表 必须指定一个表名和列族名
hbase(main):001:0> create 'test', 'cf'
0 row(s) in 0.4170 seconds
=> Hbase::Table - test复制代码
使用 list
查看存在表
hbase(main):002:0> list 'test'
TABLE
test
1 row(s) in 0.0180 seconds
=> ["test"]复制代码
describe
查看表细节及配置hbase(main):003:0> describe 'test'
Table test is ENABLED
test
COLUMN FAMILIES DESCRIPTION
{NAME => 'cf', VERSIONS => '1', EVICT_BLOCKS_ON_CLOSE => 'false', NEW_VERSION_BEHAVIOR => 'false', KEEP_DELETED_CELLS => 'FALSE', CACHE_DATA_ON_WRITE =>
'false', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', CACHE_INDEX_ON_WRITE => 'f
alse', IN_MEMORY => 'false', CACHE_BLOOMS_ON_WRITE => 'false', PREFETCH_BLOCKS_ON_OPEN => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE
=> '65536'}
1 row(s)
Took 0.9998 seconds复制代码
使用 put
插入数据
hbase(main):003:0> put 'test', 'row1', 'cf:a', 'value1'
0 row(s) in 0.0850 seconds
hbase(main):004:0> put 'test', 'row2', 'cf:b', 'value2'
0 row(s) in 0.0110 seconds
hbase(main):005:0> put 'test', 'row3', 'cf:c', 'value3'
0 row(s) in 0.0100 seconds复制代码
从 HBase 获取数据的途径之一就是 scan
。使用 scan 命令扫描表数据。你能够对扫描作限制。
hbase(main):006:0> scan 'test'
ROW COLUMN+CELL
row1 column=cf:a, timestamp=1421762485768, value=value1
row2 column=cf:b, timestamp=1421762491785, value=value2
row3 column=cf:c, timestamp=1421762496210, value=value3
3 row(s) in 0.0230 seconds复制代码
使用 get
命令一次获取一条数据
hbase(main):007:0> get 'test', 'row1'
COLUMN CELL
cf:a timestamp=1421762485768, value=value1
1 row(s) in 0.0350 seconds复制代码
使用 disable
命令禁用表
hbase(main):008:0> disable 'test'
0 row(s) in 1.1820 seconds
hbase(main):009:0> enable 'test'
0 row(s) in 0.1770 seconds复制代码
使用 enable
命令启用表
hbase(main):010:0> disable 'test'
0 row(s) in 1.1820 seconds复制代码
hbase(main):011:0> drop 'test'
0 row(s) in 0.1370 seconds复制代码
使用quit
命令退出命令行并从集群断开链接。
因为Hbase是用Java写的,所以它原生地提供了Java接口,对非Java程序人员,怎么办呢?幸亏它提供了thrift接口服务器,所以也能够采用其余语言来编写Hbase的客户端,这里是经常使用的Hbase python接口的介绍。其余语言也相似。
要使用Hbase的thrift接口,必须将它的服务启动,启动Hbase的thrift-server进程以下:
cd /app/zpy/hbase/bin
./hbase-daemon.sh start thrift
执行jps命令检查:
34533 ThriftServer复制代码
thrift默认端口是9090,启动成功后能够查看端口是否起来。
(1)安装依赖
yum install automake libtool flex bison pkgconfig gcc-c++ boost-devel libevent-devel zlib-devel python-devel ruby-devel openssl-devel
(2)安装boost
wget http://sourceforge.net/projects/boost/files/boost/1.53.0/boost_1_53_0.tar.gz
tar xvf boost_1_53_0.tar.gz
cd boost_1_53_0
./bootstrap.sh
./b2 install复制代码
官网下载 thrift-0.11.0.tar.gz,解压并安装
wget http://mirrors.hust.edu.cn/apache/thrift/0.11.0/thrift-0.11.0.tar.gz
tar xzvf thrift-0.11.0.tar.gz
cd thrift-0.11.0
mkdir /app/zpy/thrift
./configure --prefix=/app/zpy/thrift
make
make install复制代码
make可能报错以下:
g++: error: /usr/lib64/libboost_unit_test_framework.a: No such file or directory
解决:
find / -name libboost_unit_test_framework.*
cp /usr/local/lib/libboost_unit_test_framework.a /usr/lib64/复制代码
安装所需包
pip install thrift
pip install hbase-thrift复制代码
python 脚本以下:
from thrift import Thrift
from thrift.transport import TSocket
from thrift.transport import TTransport
from thrift.protocol import TBinaryProtocol
from hbase import Hbase
from hbase.ttypes import *
transport = TSocket.TSocket('localhost', 9090)
protocol = TBinaryProtocol.TBinaryProtocol(transport)
client = Hbase.Client(protocol)
transport.open()
a = client.getTableNames()
print(a)复制代码
a.启动一个非守护进程模式的REST服务器(ctrl+c 终止)
bin/hbase rest start
b.启动守护进程模式的REST服务器
bin/hbase-daemon.sh start rest
默认启动的是8080端口(可使用参数在启动时指定端口),能够被访问。curl http://
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Get;
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.rest.client.Client;
import org.apache.hadoop.hbase.rest.client.Cluster;
import org.apache.hadoop.hbase.rest.client.RemoteHTable;
import org.apache.hadoop.hbase.util.Bytes;
import util.HBaseHelper;
import java.io.IOException;
/**
* Created by root on 15-1-9.
*/
public class RestExample {
public static void main(String[] args) throws IOException {
Configuration conf = HBaseConfiguration.create();
HBaseHelper helper = HBaseHelper.getHelper(conf);
helper.dropTable("testtable");
helper.createTable("testtable", "colfam1");
System.out.println("Adding rows to table...");
helper.fillTable("testtable", 1, 10, 5, "colfam1");
Cluster cluster=new Cluster();
cluster.add("hadoop",8080);
Client client=new Client(cluster);
Get get = new Get(Bytes.toBytes("row-30"));
get.addColumn(Bytes.toBytes("colfam1"), Bytes.toBytes("col-3"));
Result result1 = table.get(get);
System.out.println("Get result1: " + result1);
Scan scan = new Scan();
scan.setStartRow(Bytes.toBytes("row-10"));
scan.setStopRow(Bytes.toBytes("row-15"));
scan.addColumn(Bytes.toBytes("colfam1"), Bytes.toBytes("col-5"));
ResultScanner scanner = table.getScanner(scan);
for (Result result2 : scanner) {
System.out.println("Scan row[" + Bytes.toString(result2.getRow()) +
"]: " + result2);
}
}
}复制代码
Apache MapReduce 是Hadoop提供的软件框架,用来进行大规模数据分析.
mapred
and mapreduce
与 MapReduce 同样,在 HBase 中也有 2 种 mapreduce API 包.org.apache.hadoop.hbase.mapred and org.apache.hadoop.hbase.mapreduce.前者使用旧式风格的 API,后者采用新的模式.相比于前者,后者更加灵活。
HBase MapReduce 读示例
Configuration config = HBaseConfiguration.create();
Job job = new Job(config, "ExampleRead");
job.setJarByClass(MyReadJob.class); // class that contains mapper
Scan scan = new Scan();
scan.setCaching(500); // 1 is the default in Scan, which will be bad for MapReduce jobs
scan.setCacheBlocks(false); // don't set to true for MR jobs
// set other scan attrs
...
TableMapReduceUtil.initTableMapperJob(
tableName, // input HBase table name
scan, // Scan instance to control CF and attribute selection
MyMapper.class, // mapper
null, // mapper output key
null, // mapper output value
job);
job.setOutputFormatClass(NullOutputFormat.class); // because we aren't emitting anything from mapper
boolean b = job.waitForCompletion(true);
if (!b) {
throw new IOException("error with job!");
}复制代码
public static class MyMapper extends TableMapper<Text, Text> {
public void map(ImmutableBytesWritable row, Result value, Context context) throws InterruptedException, IOException {
// process data for the row from the Result instance.
}
}复制代码
HBase MapReduce 读写示例
Configuration config = HBaseConfiguration.create();
Job job = new Job(config,"ExampleReadWrite");
job.setJarByClass(MyReadWriteJob.class); // class that contains mapper
Scan scan = new Scan();
scan.setCaching(500); // 1 is the default in Scan, which will be bad for MapReduce jobs
scan.setCacheBlocks(false); // don't set to true for MR jobs
// set other scan attrs
TableMapReduceUtil.initTableMapperJob(
sourceTable, // input table
scan, // Scan instance to control CF and attribute selection
MyMapper.class, // mapper class
null, // mapper output key
null, // mapper output value
job);
TableMapReduceUtil.initTableReducerJob(
targetTable, // output table
null, // reducer class
job);
job.setNumReduceTasks(0);
boolean b = job.waitForCompletion(true);
if (!b) {
throw new IOException("error with job!");
}复制代码
Hbase提供了一种Web方式的用户接口,用户能够经过Web界面查看Hbase集群的属性等状态信息,web页面分为:Master状态界面,和Zookeeper统计信息页面。
默认访问地址分别是:
ip:60010
ip::60030
ip:60010/zk.jsp
Master状态界面会看到Master状态的详情。
该页面大概分HBase集群信息,任务信息,表信息,RegionServer信息。每一部分又包含了一些具体的属性。
RegionServer状态界面会看到RegionServer状态的详情。
RegionServer的节点属性信息,任务信息和Region信息。
Zookeeper统计信息页面是很是简单的半结构化文本打印信息。
更多实时计算,Hbase,Flink,Kafka等相关技术博文,欢迎关注实时流式计算
本文由博客一文多发平台 OpenWrite 发布!