import urllib
import pathlib
def file_uri_to_path(file_uri, path_class=pathlib.PurePath):
"""
This function returns a pathlib.PurePath object for the supplied file URI.
:param str file_uri: The file URI ...
:param class path_class: The type of path in the file_uri. By default it uses
the system specific path pathlib.PurePath, to force a specific type of path
pass pathlib.PureWindowsPath or pathlib.PurePosixPath
:returns: the pathlib.PurePath object
:rtype: pathlib.PurePath
"""
windows_path = isinstance(path_class(),pathlib.PureWindowsPath)
file_uri_parsed = urllib.parse.urlparse(file_uri)
file_uri_path_unquoted = urllib.parse.unquote(file_uri_parsed.path)
if windows_path and file_uri_path_unquoted.startswith("/"):
result = path_class(file_uri_path_unquoted[1:])
else:
result = path_class(file_uri_path_unquoted)
if result.is_absolute() == False:
raise ValueError("Invalid file uri {} : resulting path {} not absolute".format(
file_uri, result))
return result
The "host" is the fully qualified domain name of the system on which
the file is accessible. This allows a client on another system to
know that it cannot access the file system, or perhaps that it needs
to use some other local mechanism to access the file.
函数的验证(pytest):
import os
import pytest
def validate(file_uri, expected_windows_path, expected_posix_path):
if expected_windows_path is not None:
expected_windows_path_object = pathlib.PureWindowsPath(expected_windows_path)
if expected_posix_path is not None:
expected_posix_path_object = pathlib.PurePosixPath(expected_posix_path)
if expected_windows_path is not None:
if os.name == "nt":
assert file_uri_to_path(file_uri) == expected_windows_path_object
assert file_uri_to_path(file_uri, pathlib.PureWindowsPath) == expected_windows_path_object
if expected_posix_path is not None:
if os.name != "nt":
assert file_uri_to_path(file_uri) == expected_posix_path_object
assert file_uri_to_path(file_uri, pathlib.PurePosixPath) == expected_posix_path_object
def test_some_paths():
validate(pathlib.PureWindowsPath(r"C:\Windows\System32\Drivers\etc\hosts").as_uri(),
expected_windows_path=r"C:\Windows\System32\Drivers\etc\hosts",
expected_posix_path=r"/C:/Windows/System32/Drivers/etc/hosts")
validate(pathlib.PurePosixPath(r"/C:/Windows/System32/Drivers/etc/hosts").as_uri(),
expected_windows_path=r"C:\Windows\System32\Drivers\etc\hosts",
expected_posix_path=r"/C:/Windows/System32/Drivers/etc/hosts")
validate(pathlib.PureWindowsPath(r"C:\some dir\some file").as_uri(),
expected_windows_path=r"C:\some dir\some file",
expected_posix_path=r"/C:/some dir/some file")
validate(pathlib.PurePosixPath(r"/C:/some dir/some file").as_uri(),
expected_windows_path=r"C:\some dir\some file",
expected_posix_path=r"/C:/some dir/some file")
def test_invalid_url():
with pytest.raises(ValueError) as excinfo:
validate(r"file://C:/test/doc.txt",
expected_windows_path=r"test\doc.txt",
expected_posix_path=r"/test/doc.txt")
assert "is not absolute" in str(excinfo.value)
def test_escaped():
validate(r"file:///home/user/some%20file.txt",
expected_windows_path=None,
expected_posix_path=r"/home/user/some file.txt")
validate(r"file:///C:/some%20dir/some%20file.txt",
expected_windows_path="C:\some dir\some file.txt",
expected_posix_path=r"/C:/some dir/some file.txt")
def test_no_authority():
validate(r"file:c:/path/to/file",
expected_windows_path=r"c:\path\to\file",
expected_posix_path=None)
validate(r"file:/path/to/file",
expected_windows_path=None,
expected_posix_path=r"/path/to/file")
使用^{} 从URI获取路径:
@Jakob Bowyer的解决方案不会将URL encoded characters转换为常规的UTF-8字符。为此,您需要使用^{} 。
要使用python将文件uri转换为路径(特定于3,如果有人真的需要,我可以使用python 2):
urllib.parse.urlparse
解析uri用
urllib.parse.unquote
然后。。。
a.如果path是一个windows路径,并且以
/
开头:去掉未引用的path组件的第一个字符(路径组件file:///C:/some/file.txt
是/C:/some/file.txt
,它不被pathlib.PureWindowsPath
解释为等同于C:\some\file.txt
)b.否则,只需按原样使用未引用的路径组件。
下面是一个函数:
使用示例(在linux上运行):
此函数适用于windows和posix文件uri,它将在没有权限部分的情况下处理文件uri。但是,它不会验证URI的权限,因此不会遵守:
IETF RFC 8089: The "file" URI Scheme / 2. Syntax
函数的验证(pytest):
此贡献是根据Zero-Clause BSD License (0BSD)许可证授权的(除了可能适用的任何其他许可证之外)
允许任何人使用、复制、修改和/或分发本软件 特此批准,无论是否收费。
本软件按“原样”提供,作者不作任何保证 关于本软件,包括 适销性和适用性。在任何情况下,作者都不承担责任 任何特殊的、直接的、间接的或间接的损害或任何损害 任何由于使用、数据或利润损失而导致的,无论是 因下列原因引起的合同诉讼、疏忽或其他侵权诉讼 或与本软件的使用或性能有关。
在法律允许的范围内,Iwan Aucamp放弃了对stackexchange贡献的所有版权和相关或相邻权利。这部作品发表于:挪威。
相关问题 更多 >
编程相关推荐