新來的一個工程師不懂HBase,java不熟,python還行,我建議他那可以考慮用HBase的thrift調用,完成目前的工作。
首先,安裝thrift
下載thrift,這里,我用的是thrift-0.7.0-dev.tar.gz 這個版本
tar xzf thrift-0.7.0-dev.tar.gz
cd thrift-0.7.0-dev
sudo ./configure --with-cpp=no --with-ruby=no
sudo make
sudo make install
然后,到HBase的源碼包里,找到
src/main/resources/org/apache/hadoop/hbase/thrift/
執行
thrift --gen py Hbase.thrift
mv gen-py/hbase/ /usr/lib/python2.4/site-packages/ (根據python版本可能有不同)
我這里寫了些調用的腳本,供大家參考
from unittest import TestCase, main
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 ColumnDescriptor, Mutation, BatchMutation
class HBaseTester:
def __init__(self, netloc, port, table="staftesttable"):
self.tableName = table
self.transport = TTransport.TBufferedTransport(
TSocket.TSocket(netloc, port))
self.protocol = TBinaryProtocol.TBinaryProtocol(self.transport)
self.client = Hbase.Client(self.protocol)
self.transport.open()
tables = self.client.getTableNames()
if self.tableName not in tables:
self.__createTable()
def __del__(self):
self.transport.close()
def __createTable(self):
name = ColumnDescriptor(name='name')
foo = ColumnDescriptor(name='foo')
self.client.createTable(self.tableName,
[name,foo])
def put(self,key,name,foo):
name = Mutation(column="name:v", value=name)
foo = Mutation(column="foo:v",value=foo)
self.client.mutateRow(self.tablename,key,[name,foo])
def scanner(self,column):
scanner = client.scannerOpen(self.tablename,"",[column])
r = client.scannerGet(scanner)
result= []
while r:
print r[0]
result.append(r[0])
r = client.scannerGet(scanner)
print "Scanner finished"
return result
class TestHBaseTester(TestCase):
def setUp(self):
self.writer = HBaseTester("localhost", 9090)
def tearDown(self):
name = self.writer.tableName
client = self.writer.client
client.disableTable(name)
client.deleteTable(name)
def testCreate(self):
tableName = self.writer.tableName
client = self.writer.client
self.assertTrue(self.writer.tableName in client.getTableNames())
columns =['name:','foo:']
for i in client.getColumnDescriptors(tableName):
self.assertTrue(i in columns)
def testPut(self):
self.writer.put("r1","n1","f1")
self.writer.put("r2","n2","f2")
self.writer.put("r3","n3","")
self.writer.scanner("name:")
if __name__ == "__main__":
main()
以上這篇python 調用HBase的簡單實例就是小編分享給大家的全部內容了,希望能給大家一個參考,也希望大家多多支持腳本之家。
更多文章、技術交流、商務合作、聯系博主
微信掃碼或搜索:z360901061
微信掃一掃加我為好友
QQ號聯系: 360901061
您的支持是博主寫作最大的動力,如果您喜歡我的文章,感覺我的文章對您有幫助,請用微信掃描下面二維碼支持博主2元、5元、10元、20元等您想捐的金額吧,狠狠點擊下面給點支持吧,站長非常感激您!手機微信長按不能支付解決辦法:請將微信支付二維碼保存到相冊,切換到微信,然后點擊微信右上角掃一掃功能,選擇支付二維碼完成支付。
【本文對您有幫助就好】元

