我正在尝试使用 Python jaydebeapi 连接到 Impala 数据库。当我两次调用连接类时,我遇到了 JVM 问题。请在下面找到我的连接类和Sql_Query
类。
连接类:
import jaydebeapi
import jpype
import datetime
import ConfigParser
from fileinput import close
config = ConfigParser.RawConfigParser ( )
config.read ( 'ConfigFile.properties' )
def Impala_Connection(sql_query):
conn_impala = None
try:
jars_location = config.get ( 'Jars_info' , 'Jars_Location' )
args = "-Djava.class.path=%s" % jars_location
jvm_path = jpype.getDefaultJVMPath ( )
jpype.startJVM ( jvm_path , args )
except IOError as err:
print('An error occurred trying to read the file:{}".format(e)')
sql_query.close ( )
else:
try:
print "Start executing: " + sql_query + " at " + str (
datetime.datetime.now ( ).strftime ( "%Y-%m-%d %H:%M" ) ) + "\n"
url = config.get ( 'Jars_info' , 'Jdbc_Url' )
Jdbc_Driver_Class = config.get ( 'Jars_info' , 'Jdbc_Driver_Class' )
username = config.get ( 'Jars_info' , 'username' )
password = config.get ( 'Jars_info' , 'password' )
jdbc_jar_location = config.get ( 'Jars_info' , 'Jdbc_Jar_Location' )
conn_impala = jaydebeapi.connect ( Jdbc_Driver_Class , url , {username , password} , jdbc_jar_location )
curs = conn_impala.cursor ( )
sql_execution = curs.execute ( sql_query )
data = curs.fetchall ( sql_execution )
curs.close()
return (data)
except Exception, err:
print("Something went wrong with Impala Connection: {}".format(err))
finally:
close(conn_impala)
jpype.shutdownJVM()
Sql_Query_Class:
from pyspark import SparkConf, SparkContext
from com.my.common_funcitons.Impala_Query_Executor import Impala_Connection
import sys
conf = SparkConf().setAppName("pyspark")
sc = SparkContext(conf=conf)
tbl_name = sys.argv[1]
refid = sys.argv[2]
metadata_Query="SELECT * from Metadata_Table TABLE_NAME='%s' and TEMP.unique_id=%s" %(tbl_name,refid)
metadata_info=Impala_Connection(metadata_Query)
if len(metadata_info) == 0:
new_tbl_name = tbl_name+"_%"
metadata_Query="SELECT * from Metadata_Table TABLE_NAME='%s' and TEMP.unique_id=%s"" (new_tbl_name,refid)
metadata_info=Impala_Connection(metadata_Query)
for row in metadata_info:
metadata_no_of_columns=row[0]
metadata_table_id=row[1]
else:
for row in metadata_info:
metadata_no_of_columns=row[0]
metadata_table_id=row[1]
我有两种类型的表名,例如 table 和 table_000,所以如果我得到空数据,我需要添加 table_% 并要求相同。当我从同一个类调用 Impala 连接时,我遇到了 JVM 问题,请在下面找到错误堆栈:
File "/usr/lib64/python2.7/site-packages/jpype/_core.py", line 50, in startJVM
_jpype.startup(jvm, tuple(args), True)
RuntimeError: Unable to start JVM at native/common/jp_env.cpp:78
我尝试在最后一堂课中添加 JVMshutdown 但仍然面临问题。请建议我一个解决方案。