Question

我的代码中遇到内存错误。我的解析器可以概括为：

# coding=utf-8
#! /usr/bin/env python
import sys
import json
from collections import defaultdict


class MyParserIter(object):

    def _parse_line(self, line):
        for couple in line.split(","):
            key, value = couple.split(':')[0], couple.split(':')[1]
            self.__hash[key].append(value)

    def __init__(self, line):
        # not the real parsing just a example to parse each
        # line to a dict-like obj
        self.__hash = defaultdict(list)
        self._parse_line(line)

    def __iter__(self):
        return iter(self.__hash.values())

    def to_dict(self):
        return self.__hash

    def __getitem__(self, item):
        return self.__hash[item]

    def free(self, item):
        self.__hash[item] = None

    def free_all(self):
        for k in self.__hash:
            self.free(k)

    def to_json(self):
        return json.dumps(self.to_dict())


def parse_file(file_path):
    list_result = []
    with open(file_path) as fin:
        for line in fin:
            parsed_line_obj = MyParserIter(line)
            list_result.append(parsed_line_obj)
    return list_result


def write_to_file(list_obj):
    with open("out.out", "w") as fout:
        for obj in list_obj:
            json_out = obj.to_json()
            fout.write(json_out + "\n")
            obj.free_all()
            obj = None

if __name__ == '__main__':
        result_list = parse_file('test.in')
        print(sys.getsizeof(result_list))
        write_to_file(result_list)
        print(sys.getsizeof(result_list))
        # the same result for memory usage result_list
        print(sys.getsizeof([None] * len(result_list)))
        # the result is not the same :(

目的是解析（大）文件，将每一行转换为将写回文件的json对象。

我的目标是减少占用空间，因为在某些情况下，此代码会引发内存错误。每个fout.write之后我想删除（免费记忆）obj参考。

我尝试将obj设置为无调用方法obj.free_all()，但没有一个释放内存。我还使用了simplejson而不是json，它减少了占用空间，但在某些情况下仍然太大。

test.in看起来像：

test1:OK,test3:OK,...
test1:OK,test3:OK,...
test1:OK,test3:OK,test4:test_again...
....

Answer 1

不要在数组中存储许多类实例，而是将其内联。实施例。

% cat test.in
test1:OK,test3:OK
test1:OK,test3:OK
test1:OK,test3:OK,test4:test_again

% cat test.py 
import json

with open("test.in", "rb") as src:
    with open("out.out", "wb") as dst:
        for line in src:
            pairs, obj = [x.split(":",1) for x in line.rstrip().split(",")], {}
            for k,v in pairs:
                if k not in obj: obj[k] = []
                obj[k].append(v)
            dst.write(json.dumps(obj)+"\n")

% cat out.out
{"test1": ["OK"], "test3": ["OK"]}
{"test1": ["OK"], "test3": ["OK"]}
{"test1": ["OK"], "test3": ["OK"], "test4": ["test_again"]}

如果速度很慢，请不要逐行写入文件，而是将转储的json字符串存储在数组中并执行dst.write("\n".join(array))

Answer 2

为了obj可以自由使用，必须消除对它的所有引用。你的循环没有这样做，因为list_obj中的引用仍然存在。以下将解决这个问题：

def write_to_file(list_obj):
    with open("out.out", "w") as fout:
        for ix in range(list_obj):
            obj = list_obj[ix]
            list_obj[ix] = None
            json_out = obj.to_json()
            fout.write(json_out + "\n")
            obj.free_all()

或者，您可以从list_obj的前面破坏性地弹出元素，但如果必须重新分配list_obj太多次，则可能会导致性能问题。我没有尝试过这个，所以我不太确定。那个版本看起来像这样：

def write_to_file(list_obj):
    with open("out.out", "w") as fout:
        while len(list_obj) > 0:
            obj = list_obj.pop(0)
            json_out = obj.to_json()
            fout.write(json_out + "\n")
            obj.free_all()

循环期间可用内存

2 个答案: