Python 注解方式实现缓存数据详解

目录 背景 拿来即用 实践过程 通过装饰器类简化代码 总结

背景 每次加载数据都要重新Load，想通过加入的注解方式开发缓存机制，每次缓存不用写代码了 缺点：目前仅支持一个返回值，虽然能弄成字典，但是已经满足个人需求，没动力改(狗头)。

拿来即用 新建文件 Cache.py

class Cache: def init(self, cache_path='.', nocache=False): self.cache_path = cache_path self.cache = not nocache def call(self, func): @wraps(func) def wrapper(args, **kwargs): s = f'{func.code.co_filename}.{func.name}' s += ','.join(list(args[1:]) + [f'{k}={v}' for k, v in kwargs.items()]) md5 = hashlib.md5() md5.update(s.encode('utf-8')) cache_file = f'{self.cache_path}/{md5.hexdigest()}' if self.cache and os.path.exists(cache_file): print('Loading from cache') return pickle.load(open(cache_file, 'rb')) else: if not os.path.exists(self.cache_path): os.makedirs(self.cache_path) data = func(args, **kwargs) pickle.dump(data, file=open(cache_file, 'wb')) print(f'Dump finished {cache_file}') return data return wrapper

from .Cache import Cache @Cache(root_path, nocache=True) def load_data(self, inpath): return 'Wula~a~a~!'

实践过程 第一次，来个简单的继承父类

class Cache(object): def init(self, cache_path=None): self.cache_path = cache_path if cache_path else '.' self.cache_path = f'{self.cache_path}/cache' self.data = self.load_cache() def load_cache(self): if os.path.exists(self.cache_path): print('Loading from cache') return pickle.load(open(self.cache_path, 'rb')) else: return None def save_cache(self): pickle.dump(self.data, file=open(self.cache_path, 'wb')) print(f'Dump finished {self.cache_path}') class Filter4Analyzer(Cache): def init(self, rootpath, datapath): super().init(rootpath) self.root_path = rootpath if self.data is None: self.data = self.load_data(datapath) self.save_cache() Python客栈送红包、纸质书

只要继承Cache类就可以啦，但是有很多局限，例如只能指定某个参数被cache，例如还得在Filter4Analyzer里面写保存的代码。

下一步，python嵌套装饰器来改善这个问题

from functools import wraps import hashlib def cached(cache_path): def wrapperper(func): @wraps(func) def wrapper(args, **kwargs): s = f'{func.code.co_filename}.{func.name}' + ','.join(args[1:]) s += ','.join(list(args[1:]) + [f'{k}={v}' for k, v in kwargs.items()]) md5 = hashlib.md5() md5.update(s.encode('utf-8')) cache_file = f'{cache_path}/{md5.hexdigest()}' if cache_path else './cache' if os.path.exists(cache_file): print('Loading from cache') return pickle.load(open(cache_file, 'rb')) else: if not os.path.exists(cache_path): os.makedirs(cache_path) data = func(args, **kwargs) pickle.dump(data, file=open(cache_file, 'wb')) print(f'Dump finished {cache_file}') return data return wrapper return wrapperper class Tester: @cached(cache_path='./workpath_test') def test(self, data_path): return ['hiahia']

通过装饰器类简化代码

https://studygolang.com/tag/%E5%8D%8E%E7%BA%B3%E5%85%AC%E5%8F%B8%E6%B3%A8%E5%86%8C%E5%BC%80%E6%88%B718313230473

class Cache: def init(self, cache_path='.', nocache=False): self.cache_path = cache_path self.cache = not nocache def call(self, func): @wraps(func) def wrapper(args, **kwargs): s = f'{func.code.co_filename}.{func.name}' s += ','.join(list(args[1:]) + [f'{k}={v}' for k, v in kwargs.items()]) md5 = hashlib.md5() md5.update(s.encode('utf-8')) cache_file = f'{self.cache_path}/{md5.hexdigest()}' if self.cache and os.path.exists(cache_file): print('Loading from cache') return pickle.load(open(cache_file, 'rb')) else: if not os.path.exists(self.cache_path): os.makedirs(self.cache_path) data = func(args, **kwargs) pickle.dump(data, file=open(cache_file, 'wb')) print(f'Dump finished {cache_file}') return data return wrapper