ambari安裝集群下python連接hbase之安裝thrift

簡介：　　

　　python連接hbase是需要通過thrift連進行連接的，ambari安裝的服務中貌似沒有自帶安裝hbase的thrift，我是看配置hbase的配置名稱里面沒有thrift，cdh版本的就有，所以我就自己安裝了thrift。

一、thrift安裝：

1、下載thrift依賴的東西 

yum install automake libtool flex bison pkgconfig gcc-c++ boost-devel libevent-devel zlib-devel python-devel ruby-devel openssl-devel

2、安裝boost_1_53_0.tar.gz

[root@master ~]# wget http://sourceforge.net/projects/boost/files/boost/1.53.0/boost_1_53_0.tar.gz
[root@master ~]# tar xvf boost_1_53_0.tar.gz
[root@master ~]# cd boost_1_53_0
[root@master boost_1_53_0]# ./bootstrap.sh
[root@master boost_1_53_0]# ./b2 install
[root@master boost_1_53_0]# cp /usr/local/lib/libboost_unit_test_framework.a /usr/lib64/
[root@master boost_1_53_0]# make
[root@master boost_1_53_0]# make install

3、下載最新版本thrift，網址：http://thrift.apache.org
 
4、移動到默認安裝目錄，並解壓

[root@master ~]# mv thrift-0.11.0.tar.gz /usr/local
[root@master ~]# cd /usr/local
[root@master local]# tar -zxvf thrift-0.11.0.tar.gz
[root@master local]# mv thrift-0.11.0 thrift
[root@master local]# cd thrift
[root@master local]# ./configure --libdir=/usr/lib --without-java --without-python --without-c_glib
[root@master local]# make
[root@master local]# make install

 二、啟動thrift

1、找到hbase的bin執行文件夾，我執行的位置是ambari默認安裝的文件夾下面/usr/hdp/2.6.3.0-235/hbase/bin

2、啟動thrift，默認端口是9090

[root@master ~]# cd /usr/hdp/2.6.3.0-235/hbase/bin
[root@master bin]# bin/hbase-daemon.sh start thrift

三、使用python連接hbase

1、安裝python依賴包

pip install thrift
pip install hbase-thrift

2、demo程序

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)

transport = TTransport.TBufferedTransport(transport)
protocol = TBinaryProtocol.TBinaryProtocol(transport)

client = Hbase.Client(protocol)
transport.open()

contents = ColumnDescriptor(name='cf:', maxVersions=1)
# client.deleteTable('test')
client.createTable('test', [contents])

print client.getTableNames()

# insert data
transport.open()

row = 'row-key1'

mutations = [Mutation(column="cf:a", value="1")]
client.mutateRow('test', row, mutations)

# get one row
tableName = 'test'
rowKey = 'row-key1'

result = client.getRow(tableName, rowKey)
print result
for r in result:
    print 'the row is ', r.row
    print 'the values is ', r.columns.get('cf:a').value
transport.close()