条件,假设配置好了hadoop和hive,并可以正常运行
首先,要外部查询hive,你需要安装thrift和fb303,或许有别的办法,但我实际应用过程中看来,这是最简单的途径。hive本身提供了thrift的接口。文件在hive解压缩后如下路径中
hive/hive-0.7.1/src/service/if/hive_service.thrift
然后复制四个文件
metastore/if/hive_metastore.thrift
src/service/if/hive_service.thrift
ql/if/queryplan.thrift
和
thrift源码下fb303中的fb303.thrift。
编辑hive_service.thrift,将其中include其他三个文件的路径修改为正确的路径。保存退出,运行thrift
#thrift -r --gen python hive_service.thrift
将生成的python放入/usr/lib/python/site-packages下,然后编写如下脚本
#!/usr/bin/python
#-*-coding:UTF-8 -*-
import sys
import os
import string
import re
import MySQLdb
from hive_service import ThriftHive
from hive_service.ttypes import HiveServerException
from thrift import Thrift
from thrift.transport import TSocket
from thrift.transport import TTransport
from thrift.protocol import TBinaryProtocol
def hiveExe(hsql,dbname):
#定义hive查询函数
try:
transport = TSocket.TSocket('192.168.10.1', 10000)
transport = TTransport.TBufferedTransport(transport)
protocol = TBinaryProtocol.TBinaryProtocol(transport)
client = ThriftHive.Client(protocol)
transport.open()
client.execute('ADD jar /opt/modules/hive/hive-0.7.1/lib/hive-contrib-0.7.1.jar')
client.execute("use "+dbname)
row = client.fetchOne()
#使用库名,只需一次fetch,用fetchOne
client.execute(hsql)
return client.fetchAll()
#查询所有数据,用fetchAll()
transport.close()
except Thrift.TException, tx:
print '%s' % (tx.message)
def mysqlExe(sql):
try:
conn = MySQLdb.connect(user="test",passwd="test123",host="127.0.0.1",db="active2_ip",port=5029)
except Exception,data:
print "Could not connect to MySQL server.:",data
try:
cursor = conn.cursor()
cursor.execute(sql)
return row
cursor.commit()
cursor.close()
conn.close()
except Exception,data:
print "Could not Fetch anything:",data
dbname = "active2"
date = os.popen("date -d '1 day ago' +%Y%m%d").read().strip()
#shell方式取昨天日期,读取并去前后\n
date.close()
sql = "create table IF NOT EXISTS "+dbname+"_group_ip_"+date+" like "+dbname+"_group_ip;load data infile '/tmp/"+dbname+"_"+date+".csv' into table "+dbname+"_group_ip_"+date+" FIELDS TERMINATED BY ','"
#以模板表创建日期表,并load data到该表中
hsql = "insert overwrite local directory '/tmp/"+dbname+"_"+date+"' select count(version) as vc,stat_hour,type,version,province,city,isp from "+dbname+"_"+date+" group by province,city,version,type,stat_hour,isp"
#hive查询,并将查询结果导出到本地/tmp/active2_20111129目录下,可能生成多个文件
hiveExe(hsql, dbname)
#执行查询
os.system("sudo cat /tmp/"+dbname+"_"+date+"/* > /tmp/tmplog ")
#将多个文件通过shell合并为一个文件tmplog
file1 = open("/tmp/tmplog", 'r')
#打开合并后的临时文件
file2 = open("/tmp/"+dbname+"_"+date+".csv",'w')
#打开另一个文件,做文字替换。因为hive导出结果,其分隔符为特殊字符。所以需要做替换,格式为csv,故用逗号分隔
sep = ','
for line in file1:
tmp = line[:-1].split('\x01')
#hive导出文件分隔符为ascii中的001,\x01是16进制,但其实也就是十进制的1
replace = sep.join(tmp)
file2.write(replace+"\n")
file1.close()
file2.close()
os.system("sudo rm -f /tmp/tmplog")
#删除临时的tmplog
mysqlExe(sql)
#执行mysql查询,创建表和加载数据。
os.system("sudo rm -f /tmp/"+dbname+"_"+date)
#-*-coding:UTF-8 -*-
import sys
import os
import string
import re
import MySQLdb
from hive_service import ThriftHive
from hive_service.ttypes import HiveServerException
from thrift import Thrift
from thrift.transport import TSocket
from thrift.transport import TTransport
from thrift.protocol import TBinaryProtocol
def hiveExe(hsql,dbname):
#定义hive查询函数
try:
transport = TSocket.TSocket('192.168.10.1', 10000)
transport = TTransport.TBufferedTransport(transport)
protocol = TBinaryProtocol.TBinaryProtocol(transport)
client = ThriftHive.Client(protocol)
transport.open()
client.execute('ADD jar /opt/modules/hive/hive-0.7.1/lib/hive-contrib-0.7.1.jar')
client.execute("use "+dbname)
row = client.fetchOne()
#使用库名,只需一次fetch,用fetchOne
client.execute(hsql)
return client.fetchAll()
#查询所有数据,用fetchAll()
transport.close()
except Thrift.TException, tx:
print '%s' % (tx.message)
def mysqlExe(sql):
try:
conn = MySQLdb.connect(user="test",passwd="test123",host="127.0.0.1",db="active2_ip",port=5029)
except Exception,data:
print "Could not connect to MySQL server.:",data
try:
cursor = conn.cursor()
cursor.execute(sql)
return row
cursor.commit()
cursor.close()
conn.close()
except Exception,data:
print "Could not Fetch anything:",data
dbname = "active2"
date = os.popen("date -d '1 day ago' +%Y%m%d").read().strip()
#shell方式取昨天日期,读取并去前后\n
date.close()
sql = "create table IF NOT EXISTS "+dbname+"_group_ip_"+date+" like "+dbname+"_group_ip;load data infile '/tmp/"+dbname+"_"+date+".csv' into table "+dbname+"_group_ip_"+date+" FIELDS TERMINATED BY ','"
#以模板表创建日期表,并load data到该表中
hsql = "insert overwrite local directory '/tmp/"+dbname+"_"+date+"' select count(version) as vc,stat_hour,type,version,province,city,isp from "+dbname+"_"+date+" group by province,city,version,type,stat_hour,isp"
#hive查询,并将查询结果导出到本地/tmp/active2_20111129目录下,可能生成多个文件
hiveExe(hsql, dbname)
#执行查询
os.system("sudo cat /tmp/"+dbname+"_"+date+"/* > /tmp/tmplog ")
#将多个文件通过shell合并为一个文件tmplog
file1 = open("/tmp/tmplog", 'r')
#打开合并后的临时文件
file2 = open("/tmp/"+dbname+"_"+date+".csv",'w')
#打开另一个文件,做文字替换。因为hive导出结果,其分隔符为特殊字符。所以需要做替换,格式为csv,故用逗号分隔
sep = ','
for line in file1:
tmp = line[:-1].split('\x01')
#hive导出文件分隔符为ascii中的001,\x01是16进制,但其实也就是十进制的1
replace = sep.join(tmp)
file2.write(replace+"\n")
file1.close()
file2.close()
os.system("sudo rm -f /tmp/tmplog")
#删除临时的tmplog
mysqlExe(sql)
#执行mysql查询,创建表和加载数据。
os.system("sudo rm -f /tmp/"+dbname+"_"+date)
其实难点主要是如何通过thrift来查询hive。还有就是hive在dump数据时,如果写insert overwrite directory,会dump到hdfs里,必须写insert overwrite local directory,才会dump到当前工作机。
再一个就是注意导出文件内容中的分隔符,其他都跟正常数据库操作是一样的。
PS:我是个python新手,刚用时间不长,所以用了很多命令行去获取当前状态值,这个熟悉python的人可以改一下。