我创建了一个包含其所有实例的类,需要并行化实例化过程,但无法解决将类作为类对象共享的问题。在 python 2.7 中是否可以使用多处理?
OUTPUT_HEADINGS = []
class MyContainer(object):
"""
"""
instances = []
children = []
@classmethod
def export_to_csv(cls):
with open(args.output, "w") as output_file:
f_csv = csv.DictWriter(output_file, fieldnames=OUTPUT_HEADINGS)
f_csv.writeheader()
for instance in cls.instances:
f_csv.writerow(instance.to_dict())
def __new__(cls, dat_file):
try:
tree = ElementTree.parse(dat_file)
cls.children = tree.findall("parent_element/child_element")
except ElementTree.ParseError as err:
logging.exception(err)
if not cls.children:
msg = ("{}: No \"parent_element/child_element\""
" element found".format(os.path.basename(dat_file)))
logging.warning(msg)
cls.children = []
return False
else:
instance = super(MyContainer, cls).__new__(cls, dat_file)
instance.__init__(dat_file)
cls.instances.append(instance)
cls.children = []
return True
def __init__(self, dat_file):
self._name = os.path.basename(dat_file)
self.attr_value_sum = defaultdict(list)
var1 = MyContainer.children[0].find("var1")
var2 = MyContainer.children[0].get("var2")
cat_name = "{}.{}".format(var1, var2)
if cat_name not in OUTPUT_HEADINGS:
OUTPUT_HEADINGS.append(cat_name)
# processing and summarizing of xml data
def to_dict(self):
return output_dict
def main():
i = 0
try:
for f in FILE_LIST:
i += 1
print "{}/{}: {} in progress...".format(i, len(FILE_LIST), f)
print "{}".format("...DONE" if MyContainer(f) else "...SKIPPED")
except Exception as err:
logging.exception(err)
finally:
MyContainer.export_to_csv()
if __name__ == '__main__':
FILE_LIST = []
for d in args.dirs:
FILE_LIST.extend(get_name_defined_files(dir_path=d,
pattern=args.filename,
recursive=args.recursive))
main()
我尝试使用multiprocessing.managers.BaseManager
, 为 MyContainer 类创建代理,但它只能以这种方式创建实例对象。我实际上想并行化MyContainer(dat_file)
调用。