我正在创建一些类来处理各种类型的文件共享(nfs,afp,s3,本地磁盘)等中的文件名。当用户输入时,会得到一个标识数据源(即"nfs://192.168.1.3"或"s3://mybucket/data")的字符串。
"nfs://192.168.1.3"
"s3://mybucket/data"
我从具有通用代码的基类中继承特定文件系统。我感到困惑的是对象创建。我有以下内容:
import os class FileSystem(object): class NoAccess(Exception): pass def __new__(cls,path): if cls is FileSystem: if path.upper().startswith('NFS://'): return super(FileSystem,cls).__new__(Nfs) else: return super(FileSystem,cls).__new__(LocalDrive) else: return super(FileSystem,cls).__new__(cls,path) def count_files(self): raise NotImplementedError class Nfs(FileSystem): def __init__ (self,path): pass def count_files(self): pass class LocalDrive(FileSystem): def __init__(self,path): if not os.access(path, os.R_OK): raise FileSystem.NoAccess('Cannot read directory') self.path = path def count_files(self): return len([x for x in os.listdir(self.path) if os.path.isfile(os.path.join(self.path, x))]) data1 = FileSystem('nfs://192.168.1.18') data2 = FileSystem('/var/log') print type(data1) print type(data2) print data2.count_files()
我以为这会很好用,__new__但我读过的大多数文章都劝阻它。有没有更公认的方法来解决此问题?
__new__
我 不 认为用__new__()做你想要的东西是不正确的。换句话说,我不同意这个问题)的公认答案,该观点认为工厂功能始终是“最佳方法”。
__new__()
如果您真的想避免使用它,则唯一的选择是元类或单独的工厂函数/方法。考虑到可用的选择,将__new__()方法设置为一种(因为默认情况下是静态的)是一种完全明智的方法。
也就是说,以下是我认为是代码的改进版本。我添加了几个类方法来帮助自动查找所有子类。它们支持更好的最重要方法- 现在添加子类不需要修改__new__()方法。这意味着它现在很容易扩展,因为它有效地支持了所谓的 虚拟构造函数 。
也可以使用类似的实现将实例的创建从__new__()方法中移到单独的(静态)工厂方法中- 因此,从某种意义上说,无论使用什么名称,所示技术都是一种相对简单的编码可扩展通用工厂函数的方法它给出了。
# Works in Python 2 and 3. import os import re class FileSystem(object): class NoAccess(Exception): pass class Unknown(Exception): pass # Regex for matching "xxx://" where x is any non-whitespace character except for ":". _PATH_PREFIX_PATTERN = re.compile(r'\s*([^:]+)://') @classmethod def _get_all_subclasses(cls): """ Recursive generator of all class' subclasses. """ for subclass in cls.__subclasses__(): yield subclass for subclass in subclass._get_all_subclasses(): yield subclass @classmethod def _get_prefix(cls, s): """ Extract any file system prefix at beginning of string s and return a lowercase version of it or None when there isn't one. """ match = cls._PATH_PREFIX_PATTERN.match(s) return match.group(1).lower() if match else None def __new__(cls, path): """ Create instance of appropriate subclass using path prefix. """ path_prefix = cls._get_prefix(path) for subclass in cls._get_all_subclasses(): if subclass.prefix == path_prefix: # Using "object" base class method avoids recursion here. return object.__new__(subclass) else: # No subclass with matching prefix found (& no default defined) raise FileSystem.Unknown( 'path "{}" has no known file system prefix'.format(path)) def count_files(self): raise NotImplementedError class Nfs(FileSystem): prefix = 'nfs' def __init__ (self, path): pass def count_files(self): pass class LocalDrive(FileSystem): prefix = None # Default when no file system prefix is found. def __init__(self, path): if not os.access(path, os.R_OK): raise FileSystem.NoAccess('Cannot read directory') self.path = path def count_files(self): return sum(os.path.isfile(os.path.join(self.path, filename)) for filename in os.listdir(self.path)) if __name__ == '__main__': data1 = FileSystem('nfs://192.168.1.18') data2 = FileSystem('c:/') # Change as necessary for testing. print(type(data1).__name__) # -> Nfs print(type(data2).__name__) # -> LocalDrive print(data2.count_files()) # -> <some number>
上面的代码可在Python 2和3.x中使用。但是,在Python 3.6中,object为named添加了一个新的类方法,__init_subclass__()该方法通过使用子类自动创建子类的“注册表”来简化子类的查找,而不必像上述_get_all_subclasses()方法那样递归地检查每个子类。
object
__init_subclass__()
_get_all_subclasses()
# Requires Python 3.6+ import os import re class FileSystem(object): class NoAccess(Exception): pass class Unknown(Exception): pass # Regex for matching "xxx://" where x is any non-whitespace character except for ":". _PATH_PREFIX_PATTERN = re.compile(r'\s*([^:]+)://') _registry = {} # Registered subclasses. @classmethod def __init_subclass__(cls, /, path_prefix, **kwargs): super().__init_subclass__(**kwargs) cls._registry[path_prefix] = cls # Add class to registry. @classmethod def _get_prefix(cls, s): """ Extract any file system prefix at beginning of string s and return a lowercase version of it or None when there isn't one. """ match = cls._PATH_PREFIX_PATTERN.match(s) return match.group(1).lower() if match else None def __new__(cls, path): """ Create instance of appropriate subclass. """ path_prefix = cls._get_prefix(path) subclass = FileSystem._registry.get(path_prefix) if subclass: # Using "object" base class method avoids recursion here. return object.__new__(subclass) else: # No subclass with matching prefix found (and no default). raise FileSystem.Unknown( f'path "{path}" has no known file system prefix') def count_files(self): raise NotImplementedError class Nfs(FileSystem, path_prefix='nfs'): def __init__ (self, path): pass def count_files(self): pass class LocalDrive(FileSystem, path_prefix=None): # Default file system. def __init__(self, path): if not os.access(path, os.R_OK): raise FileSystem.NoAccess('Cannot read directory') self.path = path def count_files(self): return sum(os.path.isfile(os.path.join(self.path, filename)) for filename in os.listdir(self.path)) if __name__ == '__main__': data1 = FileSystem('nfs://192.168.1.18') data2 = FileSystem('c:/') # Change as necessary for testing. print(type(data1).__name__) # -> Nfs print(type(data2).__name__) # -> LocalDrive print(data2.count_files()) # -> <some number> try: data3 = FileSystem('foobar://42') # Unregistered path prefix. except FileSystem.Unknown as exc: print(str(exc), '- raised as expected') else: raise RuntimeError( "Unregistered path prefix should have raised Exception!")