django “如何”系列5：如何编写自定义存储系统

如果你需要提供一个自定义的文件存储-一个常见的例子便是在远程系统上存储文件-你可以通过定义一个自己的存储类来做这件事情，你将通过一下步骤：

你自定义的存储系统一定是django.core.files.storage.Storage的子类

from django.core.files.storage import Storage

class MyStorage(Storage):
...

django必须可以实例化你的存储系统（不使用任何参数），这意味着任何的设置都必须从django.conf.settings中拿

from django.conf import settings
from django.core.files.storage import Storage

class MyStorage(Storage):
def __init__(self, option=None):
if not option:
option = settings.CUSTOM_STORAGE_OPTIONS

你的存储类必须实现_open()和_save()方法，以及其他的和你存储类相关的方法，下面会讲到

另外，如果你的类提供本地文件存储，你必须覆盖path()方法，如果不，可以忽略这个方法

这是基类Storage的源码，我会在源码的注释中讲解一些内容一些要注意的内容

class Storage(object):
"""    存储基类，提供一些默认的行为供其他的存储系统继承或者覆盖（如果需要的话）    """
# 下面的方法代表了私有方法的一个公共接口，除非绝对的需要，这些方法不应该被子类覆盖
def open(self, name, mode='rb'):
"""        从存储中检索特定的文件        """
return self._open(name, mode)

def save(self, name, content):
"""        用给定的文件名保存给定的新内容，内容应该是一个合适的可以从头开始读取的File对象        """
# Get the proper name for the file, as it will actually be saved.
if name is None:
name = content.name

name = self.get_available_name(name)
name = self._save(name, content)

# Store filenames with forward slashes, even on Windows
return force_unicode(name.replace('\\', '/'))

# 这些方法是一部分的公共API（已经实现好的，当然，你可以覆盖）

def get_valid_name(self, name):
"""        Returns a filename, based on the provided filename, that's suitable for
use in the target storage system.        """
return get_valid_filename(name)

def get_available_name(self, name):
"""        Returns a filename that's free on the target storage system, and
available for new content to be written to.        """
dir_name, file_name = os.path.split(name)
file_root, file_ext = os.path.splitext(file_name)
# If the filename already exists, add an underscore and a number (before
# the file extension, if one exists) to the filename until the generated
# filename doesn't exist.
count = itertools.count(1)
while self.exists(name):
# file_ext includes the dot.
name = os.path.join(dir_name, "%s_%s%s" % (file_root, count.next(), file_ext))

return name

def path(self, name):
"""
Returns a local filesystem path where the file can be retrieved using
Python's built-in open() function. Storage systems that can't be
accessed using open() should *not* implement this method.
"""
raise NotImplementedError("This backend doesn't support absolute paths.")

# 下面的这些方法是没有提供默认实现的公共API，子类一定要实现这些方法

def delete(self, name):
"""        Deletes the specified file from the storage system.        """
raise NotImplementedError()

def exists(self, name):
"""        Returns True if a file referened by the given name already exists in the
storage system, or False if the name is available for a new file.        """
raise NotImplementedError()

def listdir(self, path):
"""        Lists the contents of the specified path, returning a 2-tuple of lists;
the first item being directories, the second item being files.        """
raise NotImplementedError()

def size(self, name):
"""        Returns the total size, in bytes, of the file specified by name.        """
raise NotImplementedError()

def url(self, name):
"""        Returns an absolute URL where the file's contents can be accessed
directly by a Web browser.        """
raise NotImplementedError()

def accessed_time(self, name):
"""        Returns the last accessed time (as datetime object) of the file
specified by name.        """
raise NotImplementedError()

def created_time(self, name):
"""        Returns the creation time (as datetime object) of the file
specified by name.        """
raise NotImplementedError()

def modified_time(self, name):
"""        Returns the last modified time (as datetime object) of the file
specified by name.        """
raise NotImplementedError()

看完这个源码，相信你已经知道该如何如写一个自己的存储系统类了（那些方法一定要有的，那些是可以直接用的，那些是一定要写的），下面我们看一下django自带的一个实现吧

class FileSystemStorage(Storage):
"""    Standard filesystem storage    """
def __init__(self, location=None, base_url=None):
if location is None:
location = settings.MEDIA_ROOT
self.base_location = location
self.location = abspathu(self.base_location)
if base_url is None:
base_url = settings.MEDIA_URL
self.base_url = base_url

def _open(self, name, mode='rb'):
return File(open(self.path(name), mode))

def _save(self, name, content):
full_path = self.path(name)

# Create any intermediate directories that do not exist.
# Note that there is a race between os.path.exists and os.makedirs:
# if os.makedirs fails with EEXIST, the directory was created
# concurrently, and we can continue normally. Refs #16082.
directory = os.path.dirname(full_path)
if not os.path.exists(directory):
try:
os.makedirs(directory)
except OSError, e:
if e.errno != errno.EEXIST:
raise
if not os.path.isdir(directory):
raise IOError("%s exists and is not a directory." % directory)

# There's a potential race condition between get_available_name and
# saving the file; it's possible that two threads might return the
# same name, at which point all sorts of fun happens. So we need to
# try to create the file, but if it already exists we have to go back
# to get_available_name() and try again.

while True:
try:
# This file has a file path that we can move.
if hasattr(content, 'temporary_file_path'):
file_move_safe(content.temporary_file_path(), full_path)
content.close()

# This is a normal uploadedfile that we can stream.
else:
# This fun binary flag incantation makes os.open throw an
# OSError if the file already exists before we open it.
fd = os.open(full_path, os.O_WRONLY | os.O_CREAT | os.O_EXCL | getattr(os, 'O_BINARY', 0))
try:
locks.lock(fd, locks.LOCK_EX)
for chunk in content.chunks():
os.write(fd, chunk)
finally:
locks.unlock(fd)
os.close(fd)
except OSError, e:
if e.errno == errno.EEXIST:
# Ooops, the file exists. We need a new file name.
name = self.get_available_name(name)
full_path = self.path(name)
else:
raise
else:
# OK, the file save worked. Break out of the loop.
break

if settings.FILE_UPLOAD_PERMISSIONS is not None:
os.chmod(full_path, settings.FILE_UPLOAD_PERMISSIONS)

return name

def delete(self, name):
name = self.path(name)
# If the file exists, delete it from the filesystem.
# Note that there is a race between os.path.exists and os.remove:
# if os.remove fails with ENOENT, the file was removed
# concurrently, and we can continue normally.
if os.path.exists(name):
try:
os.remove(name)
except OSError, e:
if e.errno != errno.ENOENT:
raise

def exists(self, name):
return os.path.exists(self.path(name))

def listdir(self, path):
path = self.path(path)
directories, files = [], []
for entry in os.listdir(path):
if os.path.isdir(os.path.join(path, entry)):
directories.append(entry)
else:
files.append(entry)
return directories, files

def path(self, name):
try:
path = safe_join(self.location, name)
except ValueError:
raise SuspiciousOperation("Attempted access to '%s' denied." % name)
return os.path.normpath(path)

def size(self, name):
return os.path.getsize(self.path(name))

def url(self, name):
if self.base_url is None:
raise ValueError("This file is not accessible via a URL.")
return urlparse.urljoin(self.base_url, filepath_to_uri(name))

def accessed_time(self, name):
return datetime.fromtimestamp(os.path.getatime(self.path(name)))

def created_time(self, name):
return datetime.fromtimestamp(os.path.getctime(self.path(name)))

def modified_time(self, name):
return datetime.fromtimestamp(os.path.getmtime(self.path(name)))