2024-01-13 04:47:00 -04:00
|
|
|
"""
|
|
|
|
Abstract base classes for rich path objects.
|
|
|
|
|
|
|
|
This module is published as a PyPI package called "pathlib-abc".
|
|
|
|
|
|
|
|
This module is also a *PRIVATE* part of the Python standard library, where
|
|
|
|
it's developed alongside pathlib. If it finds success and maturity as a PyPI
|
|
|
|
package, it could become a public part of the standard library.
|
|
|
|
|
|
|
|
Two base classes are defined here -- PurePathBase and PathBase -- that
|
|
|
|
resemble pathlib's PurePath and Path respectively.
|
|
|
|
"""
|
|
|
|
|
2013-11-22 12:38:12 -04:00
|
|
|
import functools
|
2023-09-30 11:45:01 -03:00
|
|
|
from errno import ENOENT, ENOTDIR, EBADF, ELOOP, EINVAL
|
2013-11-22 12:38:12 -04:00
|
|
|
from stat import S_ISDIR, S_ISLNK, S_ISREG, S_ISSOCK, S_ISBLK, S_ISCHR, S_ISFIFO
|
|
|
|
|
|
|
|
#
|
|
|
|
# Internals
|
|
|
|
#
|
|
|
|
|
2021-04-28 12:50:17 -03:00
|
|
|
_WINERROR_NOT_READY = 21 # drive exists but is not accessible
|
|
|
|
_WINERROR_INVALID_NAME = 123 # fix for bpo-35306
|
|
|
|
_WINERROR_CANT_RESOLVE_FILENAME = 1921 # broken symlink pointing to itself
|
|
|
|
|
2019-05-06 15:57:17 -03:00
|
|
|
# EBADF - guard against macOS `stat` throwing EBADF
|
2021-12-30 03:45:06 -04:00
|
|
|
_IGNORED_ERRNOS = (ENOENT, ENOTDIR, EBADF, ELOOP)
|
2018-08-27 18:33:45 -03:00
|
|
|
|
2019-02-04 03:08:18 -04:00
|
|
|
_IGNORED_WINERRORS = (
|
2021-04-28 12:50:17 -03:00
|
|
|
_WINERROR_NOT_READY,
|
|
|
|
_WINERROR_INVALID_NAME,
|
|
|
|
_WINERROR_CANT_RESOLVE_FILENAME)
|
2019-02-04 03:08:18 -04:00
|
|
|
|
|
|
|
def _ignore_error(exception):
|
2021-12-30 03:45:06 -04:00
|
|
|
return (getattr(exception, 'errno', None) in _IGNORED_ERRNOS or
|
2019-02-04 03:08:18 -04:00
|
|
|
getattr(exception, 'winerror', None) in _IGNORED_WINERRORS)
|
|
|
|
|
|
|
|
|
2023-05-30 17:18:09 -03:00
|
|
|
@functools.cache
|
2023-07-19 14:59:55 -03:00
|
|
|
def _is_case_sensitive(pathmod):
|
|
|
|
return pathmod.normcase('Aa') == 'Aa'
|
2023-05-02 18:51:18 -03:00
|
|
|
|
2013-11-22 12:38:12 -04:00
|
|
|
#
|
|
|
|
# Globbing helpers
|
|
|
|
#
|
|
|
|
|
2023-11-25 13:41:05 -04:00
|
|
|
re = glob = None
|
|
|
|
|
2023-05-30 17:18:09 -03:00
|
|
|
|
2024-01-25 21:12:46 -04:00
|
|
|
@functools.lru_cache(maxsize=512)
|
|
|
|
def _compile_pattern(pat, sep, case_sensitive, recursive=True):
|
2023-06-06 19:50:36 -03:00
|
|
|
"""Compile given glob pattern to a re.Pattern object (observing case
|
2023-11-13 13:15:56 -04:00
|
|
|
sensitivity)."""
|
2023-11-25 13:41:05 -04:00
|
|
|
global re, glob
|
|
|
|
if re is None:
|
|
|
|
import re, glob
|
|
|
|
|
2023-05-18 14:59:31 -03:00
|
|
|
flags = re.NOFLAG if case_sensitive else re.IGNORECASE
|
2024-01-25 21:12:46 -04:00
|
|
|
regex = glob.translate(pat, recursive=recursive, include_hidden=True, seps=sep)
|
2023-11-25 13:41:05 -04:00
|
|
|
return re.compile(regex, flags=flags).match
|
2023-05-30 17:18:09 -03:00
|
|
|
|
|
|
|
|
2024-01-19 22:10:25 -04:00
|
|
|
def _select_special(paths, part):
|
|
|
|
"""Yield special literal children of the given paths."""
|
|
|
|
for path in paths:
|
|
|
|
yield path._make_child_relpath(part)
|
|
|
|
|
|
|
|
|
2023-06-06 19:50:36 -03:00
|
|
|
def _select_children(parent_paths, dir_only, follow_symlinks, match):
|
|
|
|
"""Yield direct children of given paths, filtering by name and type."""
|
|
|
|
if follow_symlinks is None:
|
|
|
|
follow_symlinks = True
|
|
|
|
for parent_path in parent_paths:
|
2016-01-06 13:42:07 -04:00
|
|
|
try:
|
2022-07-20 18:34:13 -03:00
|
|
|
# We must close the scandir() object before proceeding to
|
|
|
|
# avoid exhausting file descriptors when globbing deep trees.
|
2023-06-06 19:50:36 -03:00
|
|
|
with parent_path._scandir() as scandir_it:
|
2020-03-11 13:42:03 -03:00
|
|
|
entries = list(scandir_it)
|
2023-05-10 21:01:39 -03:00
|
|
|
except OSError:
|
|
|
|
pass
|
|
|
|
else:
|
2016-09-07 04:58:05 -03:00
|
|
|
for entry in entries:
|
2023-06-06 19:50:36 -03:00
|
|
|
if dir_only:
|
2020-03-07 13:53:20 -04:00
|
|
|
try:
|
2023-06-06 19:50:36 -03:00
|
|
|
if not entry.is_dir(follow_symlinks=follow_symlinks):
|
2020-03-07 13:53:20 -04:00
|
|
|
continue
|
2023-05-10 21:01:39 -03:00
|
|
|
except OSError:
|
2020-03-07 13:53:20 -04:00
|
|
|
continue
|
2023-12-28 18:23:01 -04:00
|
|
|
if match(entry.name):
|
2024-01-19 22:10:25 -04:00
|
|
|
yield parent_path._make_child_entry(entry)
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2023-05-07 18:12:50 -03:00
|
|
|
|
2023-06-06 19:50:36 -03:00
|
|
|
def _select_recursive(parent_paths, dir_only, follow_symlinks):
|
|
|
|
"""Yield given paths and all their subdirectories, recursively."""
|
|
|
|
if follow_symlinks is None:
|
|
|
|
follow_symlinks = False
|
|
|
|
for parent_path in parent_paths:
|
|
|
|
paths = [parent_path]
|
|
|
|
while paths:
|
|
|
|
path = paths.pop()
|
|
|
|
yield path
|
|
|
|
try:
|
|
|
|
# We must close the scandir() object before proceeding to
|
|
|
|
# avoid exhausting file descriptors when globbing deep trees.
|
|
|
|
with path._scandir() as scandir_it:
|
|
|
|
entries = list(scandir_it)
|
|
|
|
except OSError:
|
|
|
|
pass
|
|
|
|
else:
|
|
|
|
for entry in entries:
|
|
|
|
try:
|
|
|
|
if entry.is_dir(follow_symlinks=follow_symlinks):
|
2024-01-19 22:10:25 -04:00
|
|
|
paths.append(path._make_child_entry(entry))
|
2023-06-06 19:50:36 -03:00
|
|
|
continue
|
|
|
|
except OSError:
|
|
|
|
pass
|
|
|
|
if not dir_only:
|
2023-12-28 18:23:01 -04:00
|
|
|
yield path._make_child_entry(entry)
|
2023-06-06 19:50:36 -03:00
|
|
|
|
|
|
|
|
|
|
|
def _select_unique(paths):
|
|
|
|
"""Yields the given paths, filtering out duplicates."""
|
|
|
|
yielded = set()
|
|
|
|
try:
|
|
|
|
for path in paths:
|
2023-06-07 19:27:06 -03:00
|
|
|
path_str = str(path)
|
|
|
|
if path_str not in yielded:
|
2023-06-06 19:50:36 -03:00
|
|
|
yield path
|
2023-06-07 19:27:06 -03:00
|
|
|
yielded.add(path_str)
|
2023-06-06 19:50:36 -03:00
|
|
|
finally:
|
|
|
|
yielded.clear()
|
2023-05-07 18:12:50 -03:00
|
|
|
|
|
|
|
|
2023-06-22 10:35:51 -03:00
|
|
|
class UnsupportedOperation(NotImplementedError):
|
|
|
|
"""An exception that is raised when an unsupported operation is called on
|
|
|
|
a path object.
|
|
|
|
"""
|
|
|
|
pass
|
|
|
|
|
|
|
|
|
2024-01-14 17:49:53 -04:00
|
|
|
class PathModuleBase:
|
|
|
|
"""Base class for path modules, which do low-level path manipulation.
|
|
|
|
|
|
|
|
Path modules provide a subset of the os.path API, specifically those
|
|
|
|
functions needed to provide PurePathBase functionality. Each PurePathBase
|
|
|
|
subclass references its path module via a 'pathmod' class attribute.
|
|
|
|
|
|
|
|
Every method in this base class raises an UnsupportedOperation exception.
|
|
|
|
"""
|
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def _unsupported(cls, attr):
|
|
|
|
raise UnsupportedOperation(f"{cls.__name__}.{attr} is unsupported")
|
|
|
|
|
|
|
|
@property
|
|
|
|
def sep(self):
|
|
|
|
"""The character used to separate path components."""
|
|
|
|
self._unsupported('sep')
|
|
|
|
|
|
|
|
def join(self, path, *paths):
|
|
|
|
"""Join path segments."""
|
|
|
|
self._unsupported('join()')
|
|
|
|
|
|
|
|
def split(self, path):
|
|
|
|
"""Split the path into a pair (head, tail), where *head* is everything
|
|
|
|
before the final path separator, and *tail* is everything after.
|
|
|
|
Either part may be empty.
|
|
|
|
"""
|
|
|
|
self._unsupported('split()')
|
|
|
|
|
2024-01-14 19:06:04 -04:00
|
|
|
def splitdrive(self, path):
|
|
|
|
"""Split the path into a 2-item tuple (drive, tail), where *drive* is
|
|
|
|
a device name or mount point, and *tail* is everything after the
|
|
|
|
drive. Either part may be empty."""
|
|
|
|
self._unsupported('splitdrive()')
|
2024-01-14 17:49:53 -04:00
|
|
|
|
|
|
|
def normcase(self, path):
|
|
|
|
"""Normalize the case of the path."""
|
|
|
|
self._unsupported('normcase()')
|
|
|
|
|
|
|
|
def isabs(self, path):
|
|
|
|
"""Returns whether the path is absolute, i.e. unaffected by the
|
|
|
|
current directory or drive."""
|
|
|
|
self._unsupported('isabs()')
|
|
|
|
|
|
|
|
|
2023-12-09 11:07:40 -04:00
|
|
|
class PurePathBase:
|
GH-110109: Add `pathlib._PurePathBase` (#110670)
Add private `pathlib._PurePathBase` class: a private superclass of both `PurePath` and `_PathBase`. Unlike `PurePath`, it does not define any of these special methods: `__fspath__`, `__bytes__`, `__reduce__`, `__hash__`, `__eq__`, `__lt__`, `__le__`, `__gt__`, `__ge__`. Its initializer and path joining methods accept only strings, not os.PathLike objects more broadly.
This is important for supporting *virtual paths*: user subclasses of `_PathBase` that provide access to archive files, FTP servers, etc. In these classes, the above methods should be implemented by users only as appropriate, with due consideration for the hash/equality of any backing objects, such as file objects or sockets.
2023-12-08 13:39:04 -04:00
|
|
|
"""Base class for pure path objects.
|
2018-02-18 19:36:32 -04:00
|
|
|
|
GH-110109: Add `pathlib._PurePathBase` (#110670)
Add private `pathlib._PurePathBase` class: a private superclass of both `PurePath` and `_PathBase`. Unlike `PurePath`, it does not define any of these special methods: `__fspath__`, `__bytes__`, `__reduce__`, `__hash__`, `__eq__`, `__lt__`, `__le__`, `__gt__`, `__ge__`. Its initializer and path joining methods accept only strings, not os.PathLike objects more broadly.
This is important for supporting *virtual paths*: user subclasses of `_PathBase` that provide access to archive files, FTP servers, etc. In these classes, the above methods should be implemented by users only as appropriate, with due consideration for the hash/equality of any backing objects, such as file objects or sockets.
2023-12-08 13:39:04 -04:00
|
|
|
This class *does not* provide several magic methods that are defined in
|
|
|
|
its subclass PurePath. They are: __fspath__, __bytes__, __reduce__,
|
|
|
|
__hash__, __eq__, __lt__, __le__, __gt__, __ge__. Its initializer and path
|
|
|
|
joining methods accept only strings, not os.PathLike objects more broadly.
|
2013-11-22 12:38:12 -04:00
|
|
|
"""
|
2023-04-09 14:40:03 -03:00
|
|
|
|
2013-11-22 12:38:12 -04:00
|
|
|
__slots__ = (
|
2024-01-14 17:49:53 -04:00
|
|
|
# The `_raw_path` slot store a joined string path. This is set in the
|
|
|
|
# `__init__()` method.
|
|
|
|
'_raw_path',
|
2023-04-09 14:40:03 -03:00
|
|
|
|
2023-09-30 11:45:01 -03:00
|
|
|
# The '_resolving' slot stores a boolean indicating whether the path
|
2023-12-09 11:07:40 -04:00
|
|
|
# is being processed by `PathBase.resolve()`. This prevents duplicate
|
2023-09-30 11:45:01 -03:00
|
|
|
# work from occurring when `resolve()` calls `stat()` or `readlink()`.
|
|
|
|
'_resolving',
|
2013-11-22 12:38:12 -04:00
|
|
|
)
|
2024-01-14 17:49:53 -04:00
|
|
|
pathmod = PathModuleBase()
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2024-01-14 17:49:53 -04:00
|
|
|
def __init__(self, path, *paths):
|
|
|
|
self._raw_path = self.pathmod.join(path, *paths) if paths else path
|
GH-110109: Add `pathlib._PurePathBase` (#110670)
Add private `pathlib._PurePathBase` class: a private superclass of both `PurePath` and `_PathBase`. Unlike `PurePath`, it does not define any of these special methods: `__fspath__`, `__bytes__`, `__reduce__`, `__hash__`, `__eq__`, `__lt__`, `__le__`, `__gt__`, `__ge__`. Its initializer and path joining methods accept only strings, not os.PathLike objects more broadly.
This is important for supporting *virtual paths*: user subclasses of `_PathBase` that provide access to archive files, FTP servers, etc. In these classes, the above methods should be implemented by users only as appropriate, with due consideration for the hash/equality of any backing objects, such as file objects or sockets.
2023-12-08 13:39:04 -04:00
|
|
|
self._resolving = False
|
|
|
|
|
2023-05-05 16:04:53 -03:00
|
|
|
def with_segments(self, *pathsegments):
|
|
|
|
"""Construct a new path object from any number of path-like objects.
|
|
|
|
Subclasses may override this method to customize how new path objects
|
|
|
|
are created from methods like `iterdir()`.
|
|
|
|
"""
|
|
|
|
return type(self)(*pathsegments)
|
|
|
|
|
2013-11-22 12:38:12 -04:00
|
|
|
def __str__(self):
|
|
|
|
"""Return the string representation of the path, suitable for
|
|
|
|
passing to system calls."""
|
2024-01-13 04:03:21 -04:00
|
|
|
return self._raw_path
|
2013-11-22 12:38:12 -04:00
|
|
|
|
|
|
|
def as_posix(self):
|
|
|
|
"""Return the string representation of the path with forward (/)
|
|
|
|
slashes."""
|
2023-07-19 14:59:55 -03:00
|
|
|
return str(self).replace(self.pathmod.sep, '/')
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2023-04-03 15:57:11 -03:00
|
|
|
@property
|
|
|
|
def drive(self):
|
|
|
|
"""The drive prefix (letter or UNC path), if any."""
|
2024-01-14 19:06:04 -04:00
|
|
|
return self.pathmod.splitdrive(self.anchor)[0]
|
2023-04-03 15:57:11 -03:00
|
|
|
|
|
|
|
@property
|
|
|
|
def root(self):
|
|
|
|
"""The root of the path, if any."""
|
2024-01-14 19:06:04 -04:00
|
|
|
return self.pathmod.splitdrive(self.anchor)[1]
|
2013-11-22 12:38:12 -04:00
|
|
|
|
|
|
|
@property
|
|
|
|
def anchor(self):
|
|
|
|
"""The concatenation of the drive and root, or ''."""
|
2024-01-14 19:06:04 -04:00
|
|
|
return self._stack[0]
|
2013-11-22 12:38:12 -04:00
|
|
|
|
|
|
|
@property
|
|
|
|
def name(self):
|
|
|
|
"""The final path component, if any."""
|
2024-01-14 17:49:53 -04:00
|
|
|
return self.pathmod.split(self._raw_path)[1]
|
2013-11-22 12:38:12 -04:00
|
|
|
|
|
|
|
@property
|
|
|
|
def suffix(self):
|
2019-11-02 13:46:24 -03:00
|
|
|
"""
|
|
|
|
The final component's last suffix, if any.
|
|
|
|
|
|
|
|
This includes the leading period. For example: '.txt'
|
|
|
|
"""
|
2013-11-22 12:38:12 -04:00
|
|
|
name = self.name
|
|
|
|
i = name.rfind('.')
|
|
|
|
if 0 < i < len(name) - 1:
|
|
|
|
return name[i:]
|
|
|
|
else:
|
|
|
|
return ''
|
|
|
|
|
|
|
|
@property
|
|
|
|
def suffixes(self):
|
2019-11-02 13:46:24 -03:00
|
|
|
"""
|
|
|
|
A list of the final component's suffixes, if any.
|
|
|
|
|
|
|
|
These include the leading periods. For example: ['.tar', '.gz']
|
|
|
|
"""
|
2013-11-22 12:38:12 -04:00
|
|
|
name = self.name
|
|
|
|
if name.endswith('.'):
|
|
|
|
return []
|
|
|
|
name = name.lstrip('.')
|
|
|
|
return ['.' + suffix for suffix in name.split('.')[1:]]
|
|
|
|
|
|
|
|
@property
|
|
|
|
def stem(self):
|
|
|
|
"""The final path component, minus its last suffix."""
|
|
|
|
name = self.name
|
|
|
|
i = name.rfind('.')
|
|
|
|
if 0 < i < len(name) - 1:
|
|
|
|
return name[:i]
|
|
|
|
else:
|
|
|
|
return name
|
|
|
|
|
|
|
|
def with_name(self, name):
|
|
|
|
"""Return a new path with the file name changed."""
|
2024-01-14 17:49:53 -04:00
|
|
|
split = self.pathmod.split
|
|
|
|
if split(name)[0]:
|
2023-11-25 13:19:38 -04:00
|
|
|
raise ValueError(f"Invalid name {name!r}")
|
2024-01-14 17:49:53 -04:00
|
|
|
return self.with_segments(split(self._raw_path)[0], name)
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2020-04-19 12:29:49 -03:00
|
|
|
def with_stem(self, stem):
|
|
|
|
"""Return a new path with the stem changed."""
|
|
|
|
return self.with_name(stem + self.suffix)
|
|
|
|
|
2013-11-22 12:38:12 -04:00
|
|
|
def with_suffix(self, suffix):
|
2018-08-03 17:49:42 -03:00
|
|
|
"""Return a new path with the file suffix changed. If the path
|
|
|
|
has no suffix, add given suffix. If the given suffix is an empty
|
|
|
|
string, remove the suffix from the path.
|
|
|
|
"""
|
2023-11-25 13:19:38 -04:00
|
|
|
if not suffix:
|
|
|
|
return self.with_name(self.stem)
|
|
|
|
elif suffix.startswith('.') and len(suffix) > 1:
|
|
|
|
return self.with_name(self.stem + suffix)
|
2013-11-22 12:38:12 -04:00
|
|
|
else:
|
2023-11-25 13:19:38 -04:00
|
|
|
raise ValueError(f"Invalid suffix {suffix!r}")
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2024-01-05 18:56:04 -04:00
|
|
|
def relative_to(self, other, *, walk_up=False):
|
2013-11-22 12:38:12 -04:00
|
|
|
"""Return the relative path to another path identified by the passed
|
|
|
|
arguments. If the operation is not possible (because this is not
|
2022-10-28 20:20:14 -03:00
|
|
|
related to the other path), raise ValueError.
|
|
|
|
|
|
|
|
The *walk_up* parameter controls whether `..` may be used to resolve
|
|
|
|
the path.
|
2013-11-22 12:38:12 -04:00
|
|
|
"""
|
2024-01-05 18:56:04 -04:00
|
|
|
if not isinstance(other, PurePathBase):
|
2023-11-12 18:59:17 -04:00
|
|
|
other = self.with_segments(other)
|
2024-01-09 19:04:14 -04:00
|
|
|
anchor0, parts0 = self._stack
|
|
|
|
anchor1, parts1 = other._stack
|
2024-01-13 04:03:21 -04:00
|
|
|
if isinstance(anchor0, str) != isinstance(anchor1, str):
|
|
|
|
raise TypeError(f"{self._raw_path!r} and {other._raw_path!r} have different types")
|
2024-01-09 19:04:14 -04:00
|
|
|
if anchor0 != anchor1:
|
2024-01-13 04:03:21 -04:00
|
|
|
raise ValueError(f"{self._raw_path!r} and {other._raw_path!r} have different anchors")
|
2024-01-09 19:04:14 -04:00
|
|
|
while parts0 and parts1 and parts0[-1] == parts1[-1]:
|
|
|
|
parts0.pop()
|
|
|
|
parts1.pop()
|
|
|
|
for part in parts1:
|
|
|
|
if not part or part == '.':
|
|
|
|
pass
|
2023-07-26 16:44:55 -03:00
|
|
|
elif not walk_up:
|
2024-01-13 04:03:21 -04:00
|
|
|
raise ValueError(f"{self._raw_path!r} is not in the subpath of {other._raw_path!r}")
|
2024-01-09 19:04:14 -04:00
|
|
|
elif part == '..':
|
2024-01-13 04:03:21 -04:00
|
|
|
raise ValueError(f"'..' segment in {other._raw_path!r} cannot be walked")
|
2024-01-09 19:04:14 -04:00
|
|
|
else:
|
|
|
|
parts0.append('..')
|
|
|
|
return self.with_segments('', *reversed(parts0))
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2024-01-05 18:56:04 -04:00
|
|
|
def is_relative_to(self, other):
|
2019-08-13 16:54:02 -03:00
|
|
|
"""Return True if the path is relative to another path or False.
|
|
|
|
"""
|
2024-01-05 18:56:04 -04:00
|
|
|
if not isinstance(other, PurePathBase):
|
2023-11-12 18:59:17 -04:00
|
|
|
other = self.with_segments(other)
|
2024-01-09 19:04:14 -04:00
|
|
|
anchor0, parts0 = self._stack
|
|
|
|
anchor1, parts1 = other._stack
|
2024-01-13 04:03:21 -04:00
|
|
|
if isinstance(anchor0, str) != isinstance(anchor1, str):
|
|
|
|
raise TypeError(f"{self._raw_path!r} and {other._raw_path!r} have different types")
|
2024-01-09 19:04:14 -04:00
|
|
|
if anchor0 != anchor1:
|
|
|
|
return False
|
|
|
|
while parts0 and parts1 and parts0[-1] == parts1[-1]:
|
|
|
|
parts0.pop()
|
|
|
|
parts1.pop()
|
|
|
|
for part in parts1:
|
|
|
|
if part and part != '.':
|
|
|
|
return False
|
|
|
|
return True
|
2019-08-13 16:54:02 -03:00
|
|
|
|
2013-11-22 12:38:12 -04:00
|
|
|
@property
|
|
|
|
def parts(self):
|
|
|
|
"""An object providing sequence-like access to the
|
|
|
|
components in the filesystem path."""
|
2024-01-09 18:46:50 -04:00
|
|
|
anchor, parts = self._stack
|
|
|
|
if anchor:
|
|
|
|
parts.append(anchor)
|
|
|
|
return tuple(reversed(parts))
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2023-05-05 16:04:53 -03:00
|
|
|
def joinpath(self, *pathsegments):
|
2013-11-22 12:38:12 -04:00
|
|
|
"""Combine this path with one or several arguments, and return a
|
|
|
|
new path representing either a subpath (if all arguments are relative
|
|
|
|
paths) or a totally different path (if one of the arguments is
|
|
|
|
anchored).
|
|
|
|
"""
|
2024-01-14 17:49:53 -04:00
|
|
|
return self.with_segments(self._raw_path, *pathsegments)
|
2013-11-22 12:38:12 -04:00
|
|
|
|
|
|
|
def __truediv__(self, key):
|
2019-08-08 02:41:10 -03:00
|
|
|
try:
|
2024-01-14 17:49:53 -04:00
|
|
|
return self.with_segments(self._raw_path, key)
|
2019-08-08 02:41:10 -03:00
|
|
|
except TypeError:
|
|
|
|
return NotImplemented
|
2013-11-22 12:38:12 -04:00
|
|
|
|
|
|
|
def __rtruediv__(self, key):
|
2019-08-08 02:41:10 -03:00
|
|
|
try:
|
2024-01-14 17:49:53 -04:00
|
|
|
return self.with_segments(key, self._raw_path)
|
2019-08-08 02:41:10 -03:00
|
|
|
except TypeError:
|
|
|
|
return NotImplemented
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2024-01-09 15:50:23 -04:00
|
|
|
@property
|
|
|
|
def _stack(self):
|
|
|
|
"""
|
|
|
|
Split the path into a 2-tuple (anchor, parts), where *anchor* is the
|
|
|
|
uppermost parent of the path (equivalent to path.parents[-1]), and
|
|
|
|
*parts* is a reversed list of parts following the anchor.
|
|
|
|
"""
|
|
|
|
split = self.pathmod.split
|
2024-01-13 04:03:21 -04:00
|
|
|
path = self._raw_path
|
2024-01-09 15:50:23 -04:00
|
|
|
parent, name = split(path)
|
|
|
|
names = []
|
|
|
|
while path != parent:
|
|
|
|
names.append(name)
|
|
|
|
path = parent
|
|
|
|
parent, name = split(path)
|
|
|
|
return path, names
|
|
|
|
|
2013-11-22 12:38:12 -04:00
|
|
|
@property
|
|
|
|
def parent(self):
|
|
|
|
"""The logical parent of the path."""
|
2024-01-13 04:03:21 -04:00
|
|
|
path = self._raw_path
|
2024-01-14 17:49:53 -04:00
|
|
|
parent = self.pathmod.split(path)[0]
|
2024-01-06 17:17:51 -04:00
|
|
|
if path != parent:
|
|
|
|
parent = self.with_segments(parent)
|
|
|
|
parent._resolving = self._resolving
|
|
|
|
return parent
|
|
|
|
return self
|
2013-11-22 12:38:12 -04:00
|
|
|
|
|
|
|
@property
|
|
|
|
def parents(self):
|
|
|
|
"""A sequence of this path's logical parents."""
|
2024-01-14 17:49:53 -04:00
|
|
|
split = self.pathmod.split
|
2024-01-13 04:03:21 -04:00
|
|
|
path = self._raw_path
|
2024-01-14 17:49:53 -04:00
|
|
|
parent = split(path)[0]
|
2024-01-06 17:17:51 -04:00
|
|
|
parents = []
|
|
|
|
while path != parent:
|
|
|
|
parents.append(self.with_segments(parent))
|
|
|
|
path = parent
|
2024-01-14 17:49:53 -04:00
|
|
|
parent = split(path)[0]
|
2024-01-06 17:17:51 -04:00
|
|
|
return tuple(parents)
|
2013-11-22 12:38:12 -04:00
|
|
|
|
|
|
|
def is_absolute(self):
|
|
|
|
"""True if the path is absolute (has both a root and, if applicable,
|
|
|
|
a drive)."""
|
2024-01-14 17:49:53 -04:00
|
|
|
return self.pathmod.isabs(self._raw_path)
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2024-01-19 22:10:25 -04:00
|
|
|
@property
|
|
|
|
def _pattern_stack(self):
|
|
|
|
"""Stack of path components, to be used with patterns in glob()."""
|
|
|
|
anchor, parts = self._stack
|
|
|
|
if anchor:
|
|
|
|
raise NotImplementedError("Non-relative patterns are unsupported")
|
|
|
|
return parts
|
|
|
|
|
2024-01-25 21:12:46 -04:00
|
|
|
@property
|
|
|
|
def _pattern_str(self):
|
|
|
|
"""The path expressed as a string, for use in pattern-matching."""
|
|
|
|
return str(self)
|
|
|
|
|
2023-05-18 14:59:31 -03:00
|
|
|
def match(self, path_pattern, *, case_sensitive=None):
|
2013-11-22 12:38:12 -04:00
|
|
|
"""
|
2024-01-25 21:12:46 -04:00
|
|
|
Return True if this path matches the given pattern. If the pattern is
|
|
|
|
relative, matching is done from the right; otherwise, the entire path
|
|
|
|
is matched. The recursive wildcard '**' is *not* supported by this
|
|
|
|
method.
|
2013-11-22 12:38:12 -04:00
|
|
|
"""
|
2023-12-09 11:07:40 -04:00
|
|
|
if not isinstance(path_pattern, PurePathBase):
|
2023-05-30 17:18:09 -03:00
|
|
|
path_pattern = self.with_segments(path_pattern)
|
2023-05-18 14:59:31 -03:00
|
|
|
if case_sensitive is None:
|
2023-07-19 14:59:55 -03:00
|
|
|
case_sensitive = _is_case_sensitive(self.pathmod)
|
2023-11-13 13:15:56 -04:00
|
|
|
sep = path_pattern.pathmod.sep
|
2024-01-25 21:12:46 -04:00
|
|
|
path_parts = self.parts[::-1]
|
|
|
|
pattern_parts = path_pattern.parts[::-1]
|
|
|
|
if not pattern_parts:
|
2013-11-22 12:38:12 -04:00
|
|
|
raise ValueError("empty pattern")
|
2024-01-25 21:12:46 -04:00
|
|
|
if len(path_parts) < len(pattern_parts):
|
|
|
|
return False
|
|
|
|
if len(path_parts) > len(pattern_parts) and path_pattern.anchor:
|
|
|
|
return False
|
|
|
|
for path_part, pattern_part in zip(path_parts, pattern_parts):
|
|
|
|
match = _compile_pattern(pattern_part, sep, case_sensitive, recursive=False)
|
|
|
|
if match(path_part) is None:
|
|
|
|
return False
|
|
|
|
return True
|
|
|
|
|
|
|
|
def full_match(self, pattern, *, case_sensitive=None):
|
|
|
|
"""
|
|
|
|
Return True if this path matches the given glob-style pattern. The
|
|
|
|
pattern is matched against the entire path.
|
|
|
|
"""
|
|
|
|
if not isinstance(pattern, PurePathBase):
|
|
|
|
pattern = self.with_segments(pattern)
|
|
|
|
if case_sensitive is None:
|
|
|
|
case_sensitive = _is_case_sensitive(self.pathmod)
|
|
|
|
match = _compile_pattern(pattern._pattern_str, pattern.pathmod.sep, case_sensitive)
|
|
|
|
return match(self._pattern_str) is not None
|
2023-05-30 17:18:09 -03:00
|
|
|
|
GH-110109: Add `pathlib._PurePathBase` (#110670)
Add private `pathlib._PurePathBase` class: a private superclass of both `PurePath` and `_PathBase`. Unlike `PurePath`, it does not define any of these special methods: `__fspath__`, `__bytes__`, `__reduce__`, `__hash__`, `__eq__`, `__lt__`, `__le__`, `__gt__`, `__ge__`. Its initializer and path joining methods accept only strings, not os.PathLike objects more broadly.
This is important for supporting *virtual paths*: user subclasses of `_PathBase` that provide access to archive files, FTP servers, etc. In these classes, the above methods should be implemented by users only as appropriate, with due consideration for the hash/equality of any backing objects, such as file objects or sockets.
2023-12-08 13:39:04 -04:00
|
|
|
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2023-12-09 11:07:40 -04:00
|
|
|
class PathBase(PurePathBase):
|
2023-09-30 11:45:01 -03:00
|
|
|
"""Base class for concrete path objects.
|
2018-02-18 19:36:32 -04:00
|
|
|
|
2023-09-30 11:45:01 -03:00
|
|
|
This class provides dummy implementations for many methods that derived
|
|
|
|
classes can override selectively; the default implementations raise
|
|
|
|
UnsupportedOperation. The most basic methods, such as stat() and open(),
|
|
|
|
directly raise UnsupportedOperation; these basic methods are called by
|
|
|
|
other methods such as is_dir() and read_text().
|
|
|
|
|
|
|
|
The Path class derives this class to implement local filesystem paths.
|
|
|
|
Users may derive their own classes to implement virtual filesystem paths,
|
|
|
|
such as paths in archive files or on remote storage systems.
|
2018-02-18 19:36:32 -04:00
|
|
|
"""
|
2021-04-06 21:26:37 -03:00
|
|
|
__slots__ = ()
|
2023-09-30 11:45:01 -03:00
|
|
|
|
2024-01-08 15:31:52 -04:00
|
|
|
# Maximum number of symlinks to follow in resolve()
|
|
|
|
_max_symlinks = 40
|
|
|
|
|
2023-10-01 12:14:02 -03:00
|
|
|
@classmethod
|
|
|
|
def _unsupported(cls, method_name):
|
|
|
|
msg = f"{cls.__name__}.{method_name}() is unsupported"
|
2023-09-30 11:45:01 -03:00
|
|
|
raise UnsupportedOperation(msg)
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2023-05-07 16:07:07 -03:00
|
|
|
def stat(self, *, follow_symlinks=True):
|
|
|
|
"""
|
|
|
|
Return the result of the stat() system call on this path, like
|
|
|
|
os.stat() does.
|
|
|
|
"""
|
2023-09-30 11:45:01 -03:00
|
|
|
self._unsupported("stat")
|
2023-04-03 15:57:11 -03:00
|
|
|
|
2023-05-07 16:07:07 -03:00
|
|
|
def lstat(self):
|
|
|
|
"""
|
|
|
|
Like stat(), except if the path points to a symlink, the symlink's
|
|
|
|
status information is returned, rather than its target's.
|
|
|
|
"""
|
|
|
|
return self.stat(follow_symlinks=False)
|
2013-11-22 12:38:12 -04:00
|
|
|
|
|
|
|
|
2023-05-07 16:07:07 -03:00
|
|
|
# Convenience functions for querying the stat results
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2023-05-07 16:07:07 -03:00
|
|
|
def exists(self, *, follow_symlinks=True):
|
|
|
|
"""
|
|
|
|
Whether this path exists.
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2023-05-07 16:07:07 -03:00
|
|
|
This method normally follows symlinks; to check whether a symlink exists,
|
|
|
|
add the argument follow_symlinks=False.
|
|
|
|
"""
|
|
|
|
try:
|
|
|
|
self.stat(follow_symlinks=follow_symlinks)
|
|
|
|
except OSError as e:
|
|
|
|
if not _ignore_error(e):
|
|
|
|
raise
|
|
|
|
return False
|
|
|
|
except ValueError:
|
|
|
|
# Non-encodable path
|
|
|
|
return False
|
|
|
|
return True
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2023-06-26 13:58:17 -03:00
|
|
|
def is_dir(self, *, follow_symlinks=True):
|
2023-05-07 16:07:07 -03:00
|
|
|
"""
|
|
|
|
Whether this path is a directory.
|
|
|
|
"""
|
|
|
|
try:
|
2023-06-26 13:58:17 -03:00
|
|
|
return S_ISDIR(self.stat(follow_symlinks=follow_symlinks).st_mode)
|
2023-05-07 16:07:07 -03:00
|
|
|
except OSError as e:
|
|
|
|
if not _ignore_error(e):
|
|
|
|
raise
|
|
|
|
# Path doesn't exist or is a broken symlink
|
|
|
|
# (see http://web.archive.org/web/20200623061726/https://bitbucket.org/pitrou/pathlib/issues/12/ )
|
|
|
|
return False
|
|
|
|
except ValueError:
|
|
|
|
# Non-encodable path
|
|
|
|
return False
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2023-06-26 13:58:17 -03:00
|
|
|
def is_file(self, *, follow_symlinks=True):
|
2015-01-12 16:03:41 -04:00
|
|
|
"""
|
2023-05-07 16:07:07 -03:00
|
|
|
Whether this path is a regular file (also True for symlinks pointing
|
|
|
|
to regular files).
|
|
|
|
"""
|
|
|
|
try:
|
2023-06-26 13:58:17 -03:00
|
|
|
return S_ISREG(self.stat(follow_symlinks=follow_symlinks).st_mode)
|
2023-05-07 16:07:07 -03:00
|
|
|
except OSError as e:
|
|
|
|
if not _ignore_error(e):
|
|
|
|
raise
|
|
|
|
# Path doesn't exist or is a broken symlink
|
|
|
|
# (see http://web.archive.org/web/20200623061726/https://bitbucket.org/pitrou/pathlib/issues/12/ )
|
|
|
|
return False
|
|
|
|
except ValueError:
|
|
|
|
# Non-encodable path
|
|
|
|
return False
|
|
|
|
|
|
|
|
def is_mount(self):
|
|
|
|
"""
|
|
|
|
Check if this path is a mount point
|
|
|
|
"""
|
2023-09-30 11:45:01 -03:00
|
|
|
# Need to exist and be a dir
|
|
|
|
if not self.exists() or not self.is_dir():
|
|
|
|
return False
|
|
|
|
|
|
|
|
try:
|
|
|
|
parent_dev = self.parent.stat().st_dev
|
|
|
|
except OSError:
|
|
|
|
return False
|
|
|
|
|
|
|
|
dev = self.stat().st_dev
|
|
|
|
if dev != parent_dev:
|
|
|
|
return True
|
|
|
|
ino = self.stat().st_ino
|
|
|
|
parent_ino = self.parent.stat().st_ino
|
|
|
|
return ino == parent_ino
|
2023-05-07 16:07:07 -03:00
|
|
|
|
|
|
|
def is_symlink(self):
|
|
|
|
"""
|
|
|
|
Whether this path is a symbolic link.
|
|
|
|
"""
|
|
|
|
try:
|
|
|
|
return S_ISLNK(self.lstat().st_mode)
|
|
|
|
except OSError as e:
|
|
|
|
if not _ignore_error(e):
|
|
|
|
raise
|
|
|
|
# Path doesn't exist
|
|
|
|
return False
|
|
|
|
except ValueError:
|
|
|
|
# Non-encodable path
|
|
|
|
return False
|
|
|
|
|
|
|
|
def is_junction(self):
|
|
|
|
"""
|
|
|
|
Whether this path is a junction.
|
|
|
|
"""
|
2023-09-30 11:45:01 -03:00
|
|
|
# Junctions are a Windows-only feature, not present in POSIX nor the
|
|
|
|
# majority of virtual filesystems. There is no cross-platform idiom
|
|
|
|
# to check for junctions (using stat().st_mode).
|
|
|
|
return False
|
2023-05-07 16:07:07 -03:00
|
|
|
|
|
|
|
def is_block_device(self):
|
|
|
|
"""
|
|
|
|
Whether this path is a block device.
|
|
|
|
"""
|
|
|
|
try:
|
|
|
|
return S_ISBLK(self.stat().st_mode)
|
|
|
|
except OSError as e:
|
|
|
|
if not _ignore_error(e):
|
|
|
|
raise
|
|
|
|
# Path doesn't exist or is a broken symlink
|
|
|
|
# (see http://web.archive.org/web/20200623061726/https://bitbucket.org/pitrou/pathlib/issues/12/ )
|
|
|
|
return False
|
|
|
|
except ValueError:
|
|
|
|
# Non-encodable path
|
|
|
|
return False
|
|
|
|
|
|
|
|
def is_char_device(self):
|
|
|
|
"""
|
|
|
|
Whether this path is a character device.
|
|
|
|
"""
|
|
|
|
try:
|
|
|
|
return S_ISCHR(self.stat().st_mode)
|
|
|
|
except OSError as e:
|
|
|
|
if not _ignore_error(e):
|
|
|
|
raise
|
|
|
|
# Path doesn't exist or is a broken symlink
|
|
|
|
# (see http://web.archive.org/web/20200623061726/https://bitbucket.org/pitrou/pathlib/issues/12/ )
|
|
|
|
return False
|
|
|
|
except ValueError:
|
|
|
|
# Non-encodable path
|
|
|
|
return False
|
|
|
|
|
|
|
|
def is_fifo(self):
|
|
|
|
"""
|
|
|
|
Whether this path is a FIFO.
|
|
|
|
"""
|
|
|
|
try:
|
|
|
|
return S_ISFIFO(self.stat().st_mode)
|
|
|
|
except OSError as e:
|
|
|
|
if not _ignore_error(e):
|
|
|
|
raise
|
|
|
|
# Path doesn't exist or is a broken symlink
|
|
|
|
# (see http://web.archive.org/web/20200623061726/https://bitbucket.org/pitrou/pathlib/issues/12/ )
|
|
|
|
return False
|
|
|
|
except ValueError:
|
|
|
|
# Non-encodable path
|
|
|
|
return False
|
|
|
|
|
|
|
|
def is_socket(self):
|
|
|
|
"""
|
|
|
|
Whether this path is a socket.
|
|
|
|
"""
|
|
|
|
try:
|
|
|
|
return S_ISSOCK(self.stat().st_mode)
|
|
|
|
except OSError as e:
|
|
|
|
if not _ignore_error(e):
|
|
|
|
raise
|
|
|
|
# Path doesn't exist or is a broken symlink
|
|
|
|
# (see http://web.archive.org/web/20200623061726/https://bitbucket.org/pitrou/pathlib/issues/12/ )
|
|
|
|
return False
|
|
|
|
except ValueError:
|
|
|
|
# Non-encodable path
|
|
|
|
return False
|
2015-01-12 16:03:41 -04:00
|
|
|
|
2014-05-13 05:50:15 -03:00
|
|
|
def samefile(self, other_path):
|
2015-10-21 21:34:16 -03:00
|
|
|
"""Return whether other_path is the same or not as this file
|
2015-10-21 14:10:24 -03:00
|
|
|
(as returned by os.path.samefile()).
|
2014-05-13 05:50:15 -03:00
|
|
|
"""
|
|
|
|
st = self.stat()
|
|
|
|
try:
|
|
|
|
other_st = other_path.stat()
|
|
|
|
except AttributeError:
|
2023-05-05 16:04:53 -03:00
|
|
|
other_st = self.with_segments(other_path).stat()
|
2023-07-19 14:59:55 -03:00
|
|
|
return (st.st_ino == other_st.st_ino and
|
|
|
|
st.st_dev == other_st.st_dev)
|
2014-05-13 05:50:15 -03:00
|
|
|
|
2023-05-07 16:07:07 -03:00
|
|
|
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.
|
|
|
|
"""
|
2023-09-30 11:45:01 -03:00
|
|
|
self._unsupported("open")
|
2023-05-07 16:07:07 -03:00
|
|
|
|
|
|
|
def read_bytes(self):
|
|
|
|
"""
|
|
|
|
Open the file in bytes mode, read it, and close the file.
|
|
|
|
"""
|
|
|
|
with self.open(mode='rb') as f:
|
|
|
|
return f.read()
|
|
|
|
|
2023-11-21 18:32:38 -04:00
|
|
|
def read_text(self, encoding=None, errors=None, newline=None):
|
2023-05-07 16:07:07 -03:00
|
|
|
"""
|
|
|
|
Open the file in text mode, read it, and close the file.
|
|
|
|
"""
|
2023-11-21 18:32:38 -04:00
|
|
|
with self.open(mode='r', encoding=encoding, errors=errors, newline=newline) as f:
|
2023-05-07 16:07:07 -03:00
|
|
|
return f.read()
|
|
|
|
|
|
|
|
def write_bytes(self, data):
|
|
|
|
"""
|
|
|
|
Open the file in bytes mode, write to it, and close the file.
|
|
|
|
"""
|
|
|
|
# type-check for the buffer interface before truncating the file
|
|
|
|
view = memoryview(data)
|
|
|
|
with self.open(mode='wb') as f:
|
|
|
|
return f.write(view)
|
|
|
|
|
|
|
|
def write_text(self, data, encoding=None, errors=None, newline=None):
|
|
|
|
"""
|
|
|
|
Open the file in text mode, write to it, and close the file.
|
|
|
|
"""
|
|
|
|
if not isinstance(data, str):
|
|
|
|
raise TypeError('data must be str, not %s' %
|
|
|
|
data.__class__.__name__)
|
|
|
|
with self.open(mode='w', encoding=encoding, errors=errors, newline=newline) as f:
|
|
|
|
return f.write(data)
|
|
|
|
|
2013-11-22 12:38:12 -04:00
|
|
|
def iterdir(self):
|
2022-11-09 18:05:07 -04:00
|
|
|
"""Yield path objects of the directory contents.
|
|
|
|
|
|
|
|
The children are yielded in arbitrary order, and the
|
|
|
|
special entries '.' and '..' are not included.
|
2013-11-22 12:38:12 -04:00
|
|
|
"""
|
2023-09-30 11:45:01 -03:00
|
|
|
self._unsupported("iterdir")
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2022-02-02 08:38:25 -04:00
|
|
|
def _scandir(self):
|
2023-09-30 11:45:01 -03:00
|
|
|
# Emulate os.scandir(), which returns an object that can be used as a
|
|
|
|
# context manager. This method is called by walk() and glob().
|
2023-11-25 13:41:05 -04:00
|
|
|
from contextlib import nullcontext
|
|
|
|
return nullcontext(self.iterdir())
|
2022-02-02 08:38:25 -04:00
|
|
|
|
2024-01-19 22:10:25 -04:00
|
|
|
def _make_child_entry(self, entry):
|
2023-12-28 18:23:01 -04:00
|
|
|
# Transform an entry yielded from _scandir() into a path object.
|
|
|
|
return entry
|
|
|
|
|
2023-05-07 16:07:07 -03:00
|
|
|
def _make_child_relpath(self, name):
|
2024-01-09 15:11:17 -04:00
|
|
|
return self.joinpath(name)
|
2023-05-07 16:07:07 -03:00
|
|
|
|
2023-05-29 12:59:52 -03:00
|
|
|
def glob(self, pattern, *, case_sensitive=None, follow_symlinks=None):
|
2013-11-22 12:38:12 -04:00
|
|
|
"""Iterate over this subtree and yield all existing files (of any
|
2019-02-11 06:47:09 -04:00
|
|
|
kind, including directories) matching the given relative pattern.
|
2013-11-22 12:38:12 -04:00
|
|
|
"""
|
2024-01-19 22:10:25 -04:00
|
|
|
if not isinstance(pattern, PurePathBase):
|
|
|
|
pattern = self.with_segments(pattern)
|
2023-06-06 19:50:36 -03:00
|
|
|
if case_sensitive is None:
|
|
|
|
# TODO: evaluate case-sensitivity of each directory in _select_children().
|
2023-07-19 14:59:55 -03:00
|
|
|
case_sensitive = _is_case_sensitive(self.pathmod)
|
2023-06-06 19:50:36 -03:00
|
|
|
|
2024-01-19 22:10:25 -04:00
|
|
|
stack = pattern._pattern_stack
|
|
|
|
specials = ('', '.', '..')
|
|
|
|
filter_paths = False
|
2023-06-06 19:50:36 -03:00
|
|
|
deduplicate_paths = False
|
2023-11-13 13:15:56 -04:00
|
|
|
sep = self.pathmod.sep
|
2024-01-27 15:59:51 -04:00
|
|
|
paths = iter([self] if self.is_dir() else [])
|
2024-01-19 22:10:25 -04:00
|
|
|
while stack:
|
|
|
|
part = stack.pop()
|
|
|
|
if part in specials:
|
|
|
|
paths = _select_special(paths, part)
|
2023-06-06 19:50:36 -03:00
|
|
|
elif part == '**':
|
|
|
|
# Consume adjacent '**' components.
|
2024-01-19 22:10:25 -04:00
|
|
|
while stack and stack[-1] == '**':
|
|
|
|
stack.pop()
|
2023-06-06 19:50:36 -03:00
|
|
|
|
2024-01-19 22:10:25 -04:00
|
|
|
# Consume adjacent non-special components and enable post-walk
|
|
|
|
# regex filtering, provided we're treating symlinks consistently.
|
|
|
|
if follow_symlinks is not None:
|
|
|
|
while stack and stack[-1] not in specials:
|
|
|
|
filter_paths = True
|
|
|
|
stack.pop()
|
2023-06-06 19:50:36 -03:00
|
|
|
|
2024-01-19 22:10:25 -04:00
|
|
|
dir_only = bool(stack)
|
2023-06-06 19:50:36 -03:00
|
|
|
paths = _select_recursive(paths, dir_only, follow_symlinks)
|
|
|
|
if deduplicate_paths:
|
|
|
|
# De-duplicate if we've already seen a '**' component.
|
|
|
|
paths = _select_unique(paths)
|
|
|
|
deduplicate_paths = True
|
|
|
|
elif '**' in part:
|
|
|
|
raise ValueError("Invalid pattern: '**' can only be an entire path component")
|
|
|
|
else:
|
2024-01-19 22:10:25 -04:00
|
|
|
dir_only = bool(stack)
|
2023-11-13 13:15:56 -04:00
|
|
|
match = _compile_pattern(part, sep, case_sensitive)
|
2023-06-06 19:50:36 -03:00
|
|
|
paths = _select_children(paths, dir_only, follow_symlinks, match)
|
2024-01-19 22:10:25 -04:00
|
|
|
if filter_paths:
|
|
|
|
# Filter out paths that don't match pattern.
|
|
|
|
prefix_len = len(str(self._make_child_relpath('_'))) - 1
|
2024-01-25 21:12:46 -04:00
|
|
|
match = _compile_pattern(pattern._pattern_str, sep, case_sensitive)
|
|
|
|
paths = (path for path in paths if match(path._pattern_str, prefix_len))
|
2023-06-06 19:50:36 -03:00
|
|
|
return paths
|
2013-11-22 12:38:12 -04:00
|
|
|
|
2024-01-05 17:41:19 -04:00
|
|
|
def rglob(self, pattern, *, case_sensitive=None, follow_symlinks=None):
|
|
|
|
"""Recursively yield all existing files (of any kind, including
|
|
|
|
directories) matching the given relative pattern, anywhere in
|
|
|
|
this subtree.
|
|
|
|
"""
|
2024-01-19 22:10:25 -04:00
|
|
|
if not isinstance(pattern, PurePathBase):
|
|
|
|
pattern = self.with_segments(pattern)
|
|
|
|
pattern = '**' / pattern
|
|
|
|
return self.glob(pattern, case_sensitive=case_sensitive, follow_symlinks=follow_symlinks)
|
2024-01-05 17:41:19 -04:00
|
|
|
|
2023-05-07 16:07:07 -03:00
|
|
|
def walk(self, top_down=True, on_error=None, follow_symlinks=False):
|
|
|
|
"""Walk the directory tree from this directory, similar to os.walk()."""
|
|
|
|
paths = [self]
|
|
|
|
|
|
|
|
while paths:
|
|
|
|
path = paths.pop()
|
|
|
|
if isinstance(path, tuple):
|
|
|
|
yield path
|
|
|
|
continue
|
|
|
|
|
|
|
|
# We may not have read permission for self, in which case we can't
|
|
|
|
# get a list of the files the directory contains. os.walk()
|
|
|
|
# always suppressed the exception in that instance, rather than
|
|
|
|
# blow up for a minor reason when (say) a thousand readable
|
|
|
|
# directories are still left to visit. That logic is copied here.
|
|
|
|
try:
|
2023-09-30 11:45:01 -03:00
|
|
|
scandir_obj = path._scandir()
|
2023-05-07 16:07:07 -03:00
|
|
|
except OSError as error:
|
|
|
|
if on_error is not None:
|
|
|
|
on_error(error)
|
|
|
|
continue
|
|
|
|
|
2023-09-30 11:45:01 -03:00
|
|
|
with scandir_obj as scandir_it:
|
2023-05-07 16:07:07 -03:00
|
|
|
dirnames = []
|
|
|
|
filenames = []
|
2024-01-19 23:06:00 -04:00
|
|
|
if not top_down:
|
|
|
|
paths.append((path, dirnames, filenames))
|
2023-05-07 16:07:07 -03:00
|
|
|
for entry in scandir_it:
|
|
|
|
try:
|
|
|
|
is_dir = entry.is_dir(follow_symlinks=follow_symlinks)
|
|
|
|
except OSError:
|
|
|
|
# Carried over from os.path.isdir().
|
|
|
|
is_dir = False
|
|
|
|
|
|
|
|
if is_dir:
|
2024-01-19 23:06:00 -04:00
|
|
|
if not top_down:
|
|
|
|
paths.append(path._make_child_entry(entry))
|
2023-05-07 16:07:07 -03:00
|
|
|
dirnames.append(entry.name)
|
|
|
|
else:
|
|
|
|
filenames.append(entry.name)
|
|
|
|
|
|
|
|
if top_down:
|
|
|
|
yield path, dirnames, filenames
|
2024-01-19 23:06:00 -04:00
|
|
|
paths += [path._make_child_relpath(d) for d in reversed(dirnames)]
|
2023-05-07 16:07:07 -03:00
|
|
|
|
2023-09-30 11:45:01 -03:00
|
|
|
def absolute(self):
|
|
|
|
"""Return an absolute version of this path
|
|
|
|
No normalization or symlink resolution is performed.
|
2023-05-07 16:07:07 -03:00
|
|
|
|
2023-09-30 11:45:01 -03:00
|
|
|
Use resolve() to resolve symlinks and remove '..' segments.
|
|
|
|
"""
|
|
|
|
self._unsupported("absolute")
|
2023-05-07 16:07:07 -03:00
|
|
|
|
|
|
|
@classmethod
|
|
|
|
def cwd(cls):
|
|
|
|
"""Return a new path pointing to the current working directory."""
|
|
|
|
# We call 'absolute()' rather than using 'os.getcwd()' directly to
|
|
|
|
# enable users to replace the implementation of 'absolute()' in a
|
|
|
|
# subclass and benefit from the new behaviour here. This works because
|
|
|
|
# os.path.abspath('.') == os.getcwd().
|
2024-01-09 21:12:58 -04:00
|
|
|
return cls('').absolute()
|
2023-05-07 16:07:07 -03:00
|
|
|
|
2023-09-30 11:45:01 -03:00
|
|
|
def expanduser(self):
|
|
|
|
""" Return a new path with expanded ~ and ~user constructs
|
|
|
|
(as returned by os.path.expanduser)
|
|
|
|
"""
|
|
|
|
self._unsupported("expanduser")
|
|
|
|
|
2023-05-07 16:07:07 -03:00
|
|
|
@classmethod
|
|
|
|
def home(cls):
|
2023-09-30 11:45:01 -03:00
|
|
|
"""Return a new path pointing to expanduser('~').
|
2023-05-07 16:07:07 -03:00
|
|
|
"""
|
|
|
|
return cls("~").expanduser()
|
|
|
|
|
2023-09-30 11:45:01 -03:00
|
|
|
def readlink(self):
|
|
|
|
"""
|
|
|
|
Return the path to which the symbolic link points.
|
|
|
|
"""
|
|
|
|
self._unsupported("readlink")
|
|
|
|
readlink._supported = False
|
|
|
|
|
|
|
|
def resolve(self, strict=False):
|
|
|
|
"""
|
|
|
|
Make the path absolute, resolving all symlinks on the way and also
|
|
|
|
normalizing it.
|
|
|
|
"""
|
|
|
|
if self._resolving:
|
|
|
|
return self
|
2024-01-09 15:50:23 -04:00
|
|
|
path_root, parts = self._stack
|
|
|
|
path = self.with_segments(path_root)
|
2023-09-30 11:45:01 -03:00
|
|
|
try:
|
2023-11-17 12:58:17 -04:00
|
|
|
path = path.absolute()
|
2023-09-30 11:45:01 -03:00
|
|
|
except UnsupportedOperation:
|
2024-01-09 15:50:23 -04:00
|
|
|
path_tail = []
|
|
|
|
else:
|
|
|
|
path_root, path_tail = path._stack
|
|
|
|
path_tail.reverse()
|
2023-09-30 11:45:01 -03:00
|
|
|
|
|
|
|
# If the user has *not* overridden the `readlink()` method, then symlinks are unsupported
|
|
|
|
# and (in non-strict mode) we can improve performance by not calling `stat()`.
|
|
|
|
querying = strict or getattr(self.readlink, '_supported', True)
|
|
|
|
link_count = 0
|
|
|
|
while parts:
|
|
|
|
part = parts.pop()
|
2024-01-09 15:50:23 -04:00
|
|
|
if not part or part == '.':
|
|
|
|
continue
|
2023-09-30 11:45:01 -03:00
|
|
|
if part == '..':
|
2024-01-09 15:50:23 -04:00
|
|
|
if not path_tail:
|
|
|
|
if path_root:
|
2023-09-30 11:45:01 -03:00
|
|
|
# Delete '..' segment immediately following root
|
|
|
|
continue
|
2024-01-09 15:50:23 -04:00
|
|
|
elif path_tail[-1] != '..':
|
2023-09-30 11:45:01 -03:00
|
|
|
# Delete '..' segment and its predecessor
|
2024-01-09 15:50:23 -04:00
|
|
|
path_tail.pop()
|
2023-09-30 11:45:01 -03:00
|
|
|
continue
|
2024-01-09 15:50:23 -04:00
|
|
|
path_tail.append(part)
|
2023-09-30 11:45:01 -03:00
|
|
|
if querying and part != '..':
|
2024-01-09 15:50:23 -04:00
|
|
|
path = self.with_segments(path_root + self.pathmod.sep.join(path_tail))
|
|
|
|
path._resolving = True
|
2023-09-30 11:45:01 -03:00
|
|
|
try:
|
2024-01-09 15:50:23 -04:00
|
|
|
st = path.stat(follow_symlinks=False)
|
2023-09-30 11:45:01 -03:00
|
|
|
if S_ISLNK(st.st_mode):
|
|
|
|
# Like Linux and macOS, raise OSError(errno.ELOOP) if too many symlinks are
|
|
|
|
# encountered during resolution.
|
|
|
|
link_count += 1
|
2024-01-08 15:31:52 -04:00
|
|
|
if link_count >= self._max_symlinks:
|
2024-01-13 04:03:21 -04:00
|
|
|
raise OSError(ELOOP, "Too many symbolic links in path", self._raw_path)
|
2024-01-09 15:50:23 -04:00
|
|
|
target_root, target_parts = path.readlink()._stack
|
2023-09-30 11:45:01 -03:00
|
|
|
# If the symlink target is absolute (like '/etc/hosts'), set the current
|
2023-11-17 12:58:17 -04:00
|
|
|
# path to its uppermost parent (like '/').
|
2024-01-09 15:50:23 -04:00
|
|
|
if target_root:
|
|
|
|
path_root = target_root
|
|
|
|
path_tail.clear()
|
|
|
|
else:
|
|
|
|
path_tail.pop()
|
2023-09-30 11:45:01 -03:00
|
|
|
# Add the symlink target's reversed tail parts (like ['hosts', 'etc']) to
|
|
|
|
# the stack of unresolved path parts.
|
|
|
|
parts.extend(target_parts)
|
2023-11-17 12:58:17 -04:00
|
|
|
continue
|
2023-09-30 11:45:01 -03:00
|
|
|
elif parts and not S_ISDIR(st.st_mode):
|
2024-01-13 04:03:21 -04:00
|
|
|
raise NotADirectoryError(ENOTDIR, "Not a directory", self._raw_path)
|
2023-09-30 11:45:01 -03:00
|
|
|
except OSError:
|
|
|
|
if strict:
|
|
|
|
raise
|
|
|
|
else:
|
|
|
|
querying = False
|
2024-01-09 15:50:23 -04:00
|
|
|
return self.with_segments(path_root + self.pathmod.sep.join(path_tail))
|
2023-09-30 11:45:01 -03:00
|
|
|
|
|
|
|
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.
|
|
|
|
"""
|
|
|
|
self._unsupported("symlink_to")
|
|
|
|
|
|
|
|
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.
|
|
|
|
"""
|
|
|
|
self._unsupported("hardlink_to")
|
|
|
|
|
|
|
|
def touch(self, mode=0o666, exist_ok=True):
|
|
|
|
"""
|
|
|
|
Create this file with the given access mode, if it doesn't exist.
|
|
|
|
"""
|
|
|
|
self._unsupported("touch")
|
|
|
|
|
|
|
|
def mkdir(self, mode=0o777, parents=False, exist_ok=False):
|
|
|
|
"""
|
|
|
|
Create a new directory at this given path.
|
|
|
|
"""
|
|
|
|
self._unsupported("mkdir")
|
|
|
|
|
|
|
|
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.
|
|
|
|
"""
|
|
|
|
self._unsupported("rename")
|
|
|
|
|
|
|
|
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.
|
|
|
|
"""
|
|
|
|
self._unsupported("replace")
|
|
|
|
|
|
|
|
def chmod(self, mode, *, follow_symlinks=True):
|
|
|
|
"""
|
|
|
|
Change the permissions of the path, like os.chmod().
|
|
|
|
"""
|
|
|
|
self._unsupported("chmod")
|
|
|
|
|
|
|
|
def lchmod(self, mode):
|
|
|
|
"""
|
|
|
|
Like chmod(), except if the path points to a symlink, the symlink's
|
|
|
|
permissions are changed, rather than its target's.
|
|
|
|
"""
|
|
|
|
self.chmod(mode, follow_symlinks=False)
|
|
|
|
|
|
|
|
def unlink(self, missing_ok=False):
|
|
|
|
"""
|
|
|
|
Remove this file or link.
|
|
|
|
If the path is a directory, use rmdir() instead.
|
|
|
|
"""
|
|
|
|
self._unsupported("unlink")
|
|
|
|
|
|
|
|
def rmdir(self):
|
|
|
|
"""
|
|
|
|
Remove this directory. The directory must be empty.
|
|
|
|
"""
|
|
|
|
self._unsupported("rmdir")
|
|
|
|
|
2023-12-04 15:42:01 -04:00
|
|
|
def owner(self, *, follow_symlinks=True):
|
2023-09-30 11:45:01 -03:00
|
|
|
"""
|
|
|
|
Return the login name of the file owner.
|
|
|
|
"""
|
|
|
|
self._unsupported("owner")
|
|
|
|
|
2023-12-04 15:42:01 -04:00
|
|
|
def group(self, *, follow_symlinks=True):
|
2023-09-30 11:45:01 -03:00
|
|
|
"""
|
|
|
|
Return the group name of the file gid.
|
|
|
|
"""
|
|
|
|
self._unsupported("group")
|
|
|
|
|
2023-10-01 12:14:02 -03:00
|
|
|
@classmethod
|
|
|
|
def from_uri(cls, uri):
|
|
|
|
"""Return a new path from the given 'file' URI."""
|
|
|
|
cls._unsupported("from_uri")
|
|
|
|
|
2023-09-30 11:45:01 -03:00
|
|
|
def as_uri(self):
|
|
|
|
"""Return the path as a URI."""
|
|
|
|
self._unsupported("as_uri")
|