mirror of
https://github.com/python/cpython.git
synced 2025-10-18 12:48:57 +00:00

Change the value of `pathlib._abc.PurePathBase.pathmod` from `os.path` to `posixpath`. User subclasses of `PurePathBase` and `PathBase` previously used the host OS's path syntax, e.g. backslashes as separators on Windows. This is wrong in most use cases, and likely to catch developers out unless they test on both Windows and non-Windows machines. In this patch we change the default to POSIX syntax, regardless of OS. This is somewhat arguable (why not make all aspects of syntax abstract and individually configurable?) but an improvement all the same. This change has no effect on `PurePath`, `Path`, nor their subclasses. Only private APIs are affected.
513 lines
17 KiB
Python
513 lines
17 KiB
Python
"""Object-oriented filesystem paths.
|
|
|
|
This module provides classes to represent abstract paths and concrete
|
|
paths with operations that have semantics appropriate for different
|
|
operating systems.
|
|
"""
|
|
|
|
import io
|
|
import ntpath
|
|
import os
|
|
import posixpath
|
|
|
|
try:
|
|
import pwd
|
|
except ImportError:
|
|
pwd = None
|
|
try:
|
|
import grp
|
|
except ImportError:
|
|
grp = None
|
|
|
|
from . import _abc
|
|
|
|
|
|
__all__ = [
|
|
"UnsupportedOperation",
|
|
"PurePath", "PurePosixPath", "PureWindowsPath",
|
|
"Path", "PosixPath", "WindowsPath",
|
|
]
|
|
|
|
|
|
UnsupportedOperation = _abc.UnsupportedOperation
|
|
|
|
|
|
class PurePath(_abc.PurePathBase):
|
|
"""Base class for manipulating paths without I/O.
|
|
|
|
PurePath represents a filesystem path and offers operations which
|
|
don't imply any actual filesystem I/O. Depending on your system,
|
|
instantiating a PurePath will return either a PurePosixPath or a
|
|
PureWindowsPath object. You can also instantiate either of these classes
|
|
directly, regardless of your system.
|
|
"""
|
|
|
|
__slots__ = (
|
|
# The `_str_normcase_cached` slot stores the string path with
|
|
# normalized case. It is set when the `_str_normcase` property is
|
|
# accessed for the first time. It's used to implement `__eq__()`
|
|
# `__hash__()`, and `_parts_normcase`
|
|
'_str_normcase_cached',
|
|
|
|
# The `_parts_normcase_cached` slot stores the case-normalized
|
|
# string path after splitting on path separators. It's set when the
|
|
# `_parts_normcase` property is accessed for the first time. It's used
|
|
# to implement comparison methods like `__lt__()`.
|
|
'_parts_normcase_cached',
|
|
|
|
# The `_hash` slot stores the hash of the case-normalized string
|
|
# path. It's set when `__hash__()` is called for the first time.
|
|
'_hash',
|
|
)
|
|
pathmod = os.path
|
|
|
|
def __new__(cls, *args, **kwargs):
|
|
"""Construct a PurePath from one or several strings and or existing
|
|
PurePath objects. The strings and path objects are combined so as
|
|
to yield a canonicalized path, which is incorporated into the
|
|
new PurePath object.
|
|
"""
|
|
if cls is PurePath:
|
|
cls = PureWindowsPath if os.name == 'nt' else PurePosixPath
|
|
return object.__new__(cls)
|
|
|
|
def __init__(self, *args):
|
|
paths = []
|
|
for arg in args:
|
|
if isinstance(arg, PurePath):
|
|
if arg.pathmod is ntpath and self.pathmod is posixpath:
|
|
# GH-103631: Convert separators for backwards compatibility.
|
|
paths.extend(path.replace('\\', '/') for path in arg._raw_paths)
|
|
else:
|
|
paths.extend(arg._raw_paths)
|
|
else:
|
|
try:
|
|
path = os.fspath(arg)
|
|
except TypeError:
|
|
path = arg
|
|
if not isinstance(path, str):
|
|
raise TypeError(
|
|
"argument should be a str or an os.PathLike "
|
|
"object where __fspath__ returns a str, "
|
|
f"not {type(path).__name__!r}")
|
|
paths.append(path)
|
|
# Avoid calling super().__init__, as an optimisation
|
|
self._raw_paths = paths
|
|
self._resolving = False
|
|
|
|
def __reduce__(self):
|
|
# Using the parts tuple helps share interned path parts
|
|
# when pickling related paths.
|
|
return (self.__class__, self.parts)
|
|
|
|
def __repr__(self):
|
|
return "{}({!r})".format(self.__class__.__name__, self.as_posix())
|
|
|
|
def __fspath__(self):
|
|
return str(self)
|
|
|
|
def __bytes__(self):
|
|
"""Return the bytes representation of the path. This is only
|
|
recommended to use under Unix."""
|
|
return os.fsencode(self)
|
|
|
|
@property
|
|
def _str_normcase(self):
|
|
# String with normalized case, for hashing and equality checks
|
|
try:
|
|
return self._str_normcase_cached
|
|
except AttributeError:
|
|
if _abc._is_case_sensitive(self.pathmod):
|
|
self._str_normcase_cached = str(self)
|
|
else:
|
|
self._str_normcase_cached = str(self).lower()
|
|
return self._str_normcase_cached
|
|
|
|
def __hash__(self):
|
|
try:
|
|
return self._hash
|
|
except AttributeError:
|
|
self._hash = hash(self._str_normcase)
|
|
return self._hash
|
|
|
|
def __eq__(self, other):
|
|
if not isinstance(other, PurePath):
|
|
return NotImplemented
|
|
return self._str_normcase == other._str_normcase and self.pathmod is other.pathmod
|
|
|
|
@property
|
|
def _parts_normcase(self):
|
|
# Cached parts with normalized case, for comparisons.
|
|
try:
|
|
return self._parts_normcase_cached
|
|
except AttributeError:
|
|
self._parts_normcase_cached = self._str_normcase.split(self.pathmod.sep)
|
|
return self._parts_normcase_cached
|
|
|
|
def __lt__(self, other):
|
|
if not isinstance(other, PurePath) or self.pathmod is not other.pathmod:
|
|
return NotImplemented
|
|
return self._parts_normcase < other._parts_normcase
|
|
|
|
def __le__(self, other):
|
|
if not isinstance(other, PurePath) or self.pathmod is not other.pathmod:
|
|
return NotImplemented
|
|
return self._parts_normcase <= other._parts_normcase
|
|
|
|
def __gt__(self, other):
|
|
if not isinstance(other, PurePath) or self.pathmod is not other.pathmod:
|
|
return NotImplemented
|
|
return self._parts_normcase > other._parts_normcase
|
|
|
|
def __ge__(self, other):
|
|
if not isinstance(other, PurePath) or self.pathmod is not other.pathmod:
|
|
return NotImplemented
|
|
return self._parts_normcase >= other._parts_normcase
|
|
|
|
def as_uri(self):
|
|
"""Return the path as a URI."""
|
|
if not self.is_absolute():
|
|
raise ValueError("relative path can't be expressed as a file URI")
|
|
|
|
drive = self.drive
|
|
if len(drive) == 2 and drive[1] == ':':
|
|
# It's a path on a local drive => 'file:///c:/a/b'
|
|
prefix = 'file:///' + drive
|
|
path = self.as_posix()[2:]
|
|
elif drive:
|
|
# It's a path on a network drive => 'file://host/share/a/b'
|
|
prefix = 'file:'
|
|
path = self.as_posix()
|
|
else:
|
|
# It's a posix path => 'file:///etc/hosts'
|
|
prefix = 'file://'
|
|
path = str(self)
|
|
from urllib.parse import quote_from_bytes
|
|
return prefix + quote_from_bytes(os.fsencode(path))
|
|
|
|
|
|
# Subclassing os.PathLike makes isinstance() checks slower,
|
|
# which in turn makes Path construction slower. Register instead!
|
|
os.PathLike.register(PurePath)
|
|
|
|
|
|
class PurePosixPath(PurePath):
|
|
"""PurePath subclass for non-Windows systems.
|
|
|
|
On a POSIX system, instantiating a PurePath should return this object.
|
|
However, you can also instantiate it directly on any system.
|
|
"""
|
|
pathmod = posixpath
|
|
__slots__ = ()
|
|
|
|
|
|
class PureWindowsPath(PurePath):
|
|
"""PurePath subclass for Windows systems.
|
|
|
|
On a Windows system, instantiating a PurePath should return this object.
|
|
However, you can also instantiate it directly on any system.
|
|
"""
|
|
pathmod = ntpath
|
|
__slots__ = ()
|
|
|
|
|
|
class Path(_abc.PathBase, PurePath):
|
|
"""PurePath subclass that can make system calls.
|
|
|
|
Path represents a filesystem path but unlike PurePath, also offers
|
|
methods to do system calls on path objects. Depending on your system,
|
|
instantiating a Path will return either a PosixPath or a WindowsPath
|
|
object. You can also instantiate a PosixPath or WindowsPath directly,
|
|
but cannot instantiate a WindowsPath on a POSIX system or vice versa.
|
|
"""
|
|
__slots__ = ()
|
|
as_uri = PurePath.as_uri
|
|
|
|
@classmethod
|
|
def _unsupported(cls, method_name):
|
|
msg = f"{cls.__name__}.{method_name}() is unsupported on this system"
|
|
raise UnsupportedOperation(msg)
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
if kwargs:
|
|
import warnings
|
|
msg = ("support for supplying keyword arguments to pathlib.PurePath "
|
|
"is deprecated and scheduled for removal in Python {remove}")
|
|
warnings._deprecated("pathlib.PurePath(**kwargs)", msg, remove=(3, 14))
|
|
super().__init__(*args)
|
|
|
|
def __new__(cls, *args, **kwargs):
|
|
if cls is Path:
|
|
cls = WindowsPath if os.name == 'nt' else PosixPath
|
|
return object.__new__(cls)
|
|
|
|
def stat(self, *, follow_symlinks=True):
|
|
"""
|
|
Return the result of the stat() system call on this path, like
|
|
os.stat() does.
|
|
"""
|
|
return os.stat(self, follow_symlinks=follow_symlinks)
|
|
|
|
def is_mount(self):
|
|
"""
|
|
Check if this path is a mount point
|
|
"""
|
|
return os.path.ismount(self)
|
|
|
|
def is_junction(self):
|
|
"""
|
|
Whether this path is a junction.
|
|
"""
|
|
return os.path.isjunction(self)
|
|
|
|
def open(self, mode='r', buffering=-1, encoding=None,
|
|
errors=None, newline=None):
|
|
"""
|
|
Open the file pointed by this path and return a file object, as
|
|
the built-in open() function does.
|
|
"""
|
|
if "b" not in mode:
|
|
encoding = io.text_encoding(encoding)
|
|
return io.open(self, mode, buffering, encoding, errors, newline)
|
|
|
|
def iterdir(self):
|
|
"""Yield path objects of the directory contents.
|
|
|
|
The children are yielded in arbitrary order, and the
|
|
special entries '.' and '..' are not included.
|
|
"""
|
|
return (self._make_child_relpath(name) for name in os.listdir(self))
|
|
|
|
def _scandir(self):
|
|
return os.scandir(self)
|
|
|
|
def absolute(self):
|
|
"""Return an absolute version of this path
|
|
No normalization or symlink resolution is performed.
|
|
|
|
Use resolve() to resolve symlinks and remove '..' segments.
|
|
"""
|
|
if self.is_absolute():
|
|
return self
|
|
if self.root:
|
|
drive = os.path.splitroot(os.getcwd())[0]
|
|
return self._from_parsed_parts(drive, self.root, self._tail)
|
|
if self.drive:
|
|
# There is a CWD on each drive-letter drive.
|
|
cwd = os.path.abspath(self.drive)
|
|
else:
|
|
cwd = os.getcwd()
|
|
if not self._tail:
|
|
# Fast path for "empty" paths, e.g. Path("."), Path("") or Path().
|
|
# We pass only one argument to with_segments() to avoid the cost
|
|
# of joining, and we exploit the fact that getcwd() returns a
|
|
# fully-normalized string by storing it in _str. This is used to
|
|
# implement Path.cwd().
|
|
result = self.with_segments(cwd)
|
|
result._str = cwd
|
|
return result
|
|
drive, root, rel = os.path.splitroot(cwd)
|
|
if not rel:
|
|
return self._from_parsed_parts(drive, root, self._tail)
|
|
tail = rel.split(self.pathmod.sep)
|
|
tail.extend(self._tail)
|
|
return self._from_parsed_parts(drive, root, tail)
|
|
|
|
def resolve(self, strict=False):
|
|
"""
|
|
Make the path absolute, resolving all symlinks on the way and also
|
|
normalizing it.
|
|
"""
|
|
|
|
return self.with_segments(os.path.realpath(self, strict=strict))
|
|
|
|
if pwd:
|
|
def owner(self, *, follow_symlinks=True):
|
|
"""
|
|
Return the login name of the file owner.
|
|
"""
|
|
uid = self.stat(follow_symlinks=follow_symlinks).st_uid
|
|
return pwd.getpwuid(uid).pw_name
|
|
|
|
if grp:
|
|
def group(self, *, follow_symlinks=True):
|
|
"""
|
|
Return the group name of the file gid.
|
|
"""
|
|
gid = self.stat(follow_symlinks=follow_symlinks).st_gid
|
|
return grp.getgrgid(gid).gr_name
|
|
|
|
if hasattr(os, "readlink"):
|
|
def readlink(self):
|
|
"""
|
|
Return the path to which the symbolic link points.
|
|
"""
|
|
return self.with_segments(os.readlink(self))
|
|
|
|
def touch(self, mode=0o666, exist_ok=True):
|
|
"""
|
|
Create this file with the given access mode, if it doesn't exist.
|
|
"""
|
|
|
|
if exist_ok:
|
|
# First try to bump modification time
|
|
# Implementation note: GNU touch uses the UTIME_NOW option of
|
|
# the utimensat() / futimens() functions.
|
|
try:
|
|
os.utime(self, None)
|
|
except OSError:
|
|
# Avoid exception chaining
|
|
pass
|
|
else:
|
|
return
|
|
flags = os.O_CREAT | os.O_WRONLY
|
|
if not exist_ok:
|
|
flags |= os.O_EXCL
|
|
fd = os.open(self, flags, mode)
|
|
os.close(fd)
|
|
|
|
def mkdir(self, mode=0o777, parents=False, exist_ok=False):
|
|
"""
|
|
Create a new directory at this given path.
|
|
"""
|
|
try:
|
|
os.mkdir(self, mode)
|
|
except FileNotFoundError:
|
|
if not parents or self.parent == self:
|
|
raise
|
|
self.parent.mkdir(parents=True, exist_ok=True)
|
|
self.mkdir(mode, parents=False, exist_ok=exist_ok)
|
|
except OSError:
|
|
# Cannot rely on checking for EEXIST, since the operating system
|
|
# could give priority to other errors like EACCES or EROFS
|
|
if not exist_ok or not self.is_dir():
|
|
raise
|
|
|
|
def chmod(self, mode, *, follow_symlinks=True):
|
|
"""
|
|
Change the permissions of the path, like os.chmod().
|
|
"""
|
|
os.chmod(self, mode, follow_symlinks=follow_symlinks)
|
|
|
|
def unlink(self, missing_ok=False):
|
|
"""
|
|
Remove this file or link.
|
|
If the path is a directory, use rmdir() instead.
|
|
"""
|
|
try:
|
|
os.unlink(self)
|
|
except FileNotFoundError:
|
|
if not missing_ok:
|
|
raise
|
|
|
|
def rmdir(self):
|
|
"""
|
|
Remove this directory. The directory must be empty.
|
|
"""
|
|
os.rmdir(self)
|
|
|
|
def rename(self, target):
|
|
"""
|
|
Rename this path to the target path.
|
|
|
|
The target path may be absolute or relative. Relative paths are
|
|
interpreted relative to the current working directory, *not* the
|
|
directory of the Path object.
|
|
|
|
Returns the new Path instance pointing to the target path.
|
|
"""
|
|
os.rename(self, target)
|
|
return self.with_segments(target)
|
|
|
|
def replace(self, target):
|
|
"""
|
|
Rename this path to the target path, overwriting if that path exists.
|
|
|
|
The target path may be absolute or relative. Relative paths are
|
|
interpreted relative to the current working directory, *not* the
|
|
directory of the Path object.
|
|
|
|
Returns the new Path instance pointing to the target path.
|
|
"""
|
|
os.replace(self, target)
|
|
return self.with_segments(target)
|
|
|
|
if hasattr(os, "symlink"):
|
|
def symlink_to(self, target, target_is_directory=False):
|
|
"""
|
|
Make this path a symlink pointing to the target path.
|
|
Note the order of arguments (link, target) is the reverse of os.symlink.
|
|
"""
|
|
os.symlink(target, self, target_is_directory)
|
|
|
|
if hasattr(os, "link"):
|
|
def hardlink_to(self, target):
|
|
"""
|
|
Make this path a hard link pointing to the same file as *target*.
|
|
|
|
Note the order of arguments (self, target) is the reverse of os.link's.
|
|
"""
|
|
os.link(target, self)
|
|
|
|
def expanduser(self):
|
|
""" Return a new path with expanded ~ and ~user constructs
|
|
(as returned by os.path.expanduser)
|
|
"""
|
|
if (not (self.drive or self.root) and
|
|
self._tail and self._tail[0][:1] == '~'):
|
|
homedir = os.path.expanduser(self._tail[0])
|
|
if homedir[:1] == "~":
|
|
raise RuntimeError("Could not determine home directory.")
|
|
drv, root, tail = self._parse_path(homedir)
|
|
return self._from_parsed_parts(drv, root, tail + self._tail[1:])
|
|
|
|
return self
|
|
|
|
@classmethod
|
|
def from_uri(cls, uri):
|
|
"""Return a new path from the given 'file' URI."""
|
|
if not uri.startswith('file:'):
|
|
raise ValueError(f"URI does not start with 'file:': {uri!r}")
|
|
path = uri[5:]
|
|
if path[:3] == '///':
|
|
# Remove empty authority
|
|
path = path[2:]
|
|
elif path[:12] == '//localhost/':
|
|
# Remove 'localhost' authority
|
|
path = path[11:]
|
|
if path[:3] == '///' or (path[:1] == '/' and path[2:3] in ':|'):
|
|
# Remove slash before DOS device/UNC path
|
|
path = path[1:]
|
|
if path[1:2] == '|':
|
|
# Replace bar with colon in DOS drive
|
|
path = path[:1] + ':' + path[2:]
|
|
from urllib.parse import unquote_to_bytes
|
|
path = cls(os.fsdecode(unquote_to_bytes(path)))
|
|
if not path.is_absolute():
|
|
raise ValueError(f"URI is not absolute: {uri!r}")
|
|
return path
|
|
|
|
|
|
class PosixPath(Path, PurePosixPath):
|
|
"""Path subclass for non-Windows systems.
|
|
|
|
On a POSIX system, instantiating a Path should return this object.
|
|
"""
|
|
__slots__ = ()
|
|
|
|
if os.name == 'nt':
|
|
def __new__(cls, *args, **kwargs):
|
|
raise UnsupportedOperation(
|
|
f"cannot instantiate {cls.__name__!r} on your system")
|
|
|
|
class WindowsPath(Path, PureWindowsPath):
|
|
"""Path subclass for Windows systems.
|
|
|
|
On a Windows system, instantiating a Path should return this object.
|
|
"""
|
|
__slots__ = ()
|
|
|
|
if os.name != 'nt':
|
|
def __new__(cls, *args, **kwargs):
|
|
raise UnsupportedOperation(
|
|
f"cannot instantiate {cls.__name__!r} on your system")
|