123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573 |
- """Common operations on Posix pathnames.
- Instead of importing this module directly, import os and refer to
- this module as os.path. The "os.path" name is an alias for this
- module on Posix systems; on other systems (e.g. Windows),
- os.path provides the same operations in a manner specific to that
- platform, and is an alias to another module (e.g. ntpath).
- Some of this can actually be useful on non-Posix systems too, e.g.
- for manipulation of the pathname component of URLs.
- """
- # Strings representing various path-related bits and pieces.
- # These are primarily for export; internally, they are hardcoded.
- # Should be set before imports for resolving cyclic dependency.
- curdir = '.'
- pardir = '..'
- extsep = '.'
- sep = '/'
- pathsep = ':'
- defpath = '/bin:/usr/bin'
- altsep = None
- devnull = '/dev/null'
- import os
- import sys
- import stat
- import genericpath
- from genericpath import *
- __all__ = ["normcase","isabs","join","splitdrive","splitroot","split","splitext",
- "basename","dirname","commonprefix","getsize","getmtime",
- "getatime","getctime","islink","exists","lexists","isdir","isfile",
- "ismount", "expanduser","expandvars","normpath","abspath",
- "samefile","sameopenfile","samestat",
- "curdir","pardir","sep","pathsep","defpath","altsep","extsep",
- "devnull","realpath","supports_unicode_filenames","relpath",
- "commonpath", "isjunction"]
- def _get_sep(path):
- if isinstance(path, bytes):
- return b'/'
- else:
- return '/'
- # Normalize the case of a pathname. Trivial in Posix, string.lower on Mac.
- # On MS-DOS this may also turn slashes into backslashes; however, other
- # normalizations (such as optimizing '../' away) are not allowed
- # (another function should be defined to do that).
- def normcase(s):
- """Normalize case of pathname. Has no effect under Posix"""
- return os.fspath(s)
- # Return whether a path is absolute.
- # Trivial in Posix, harder on the Mac or MS-DOS.
- def isabs(s):
- """Test whether a path is absolute"""
- s = os.fspath(s)
- sep = _get_sep(s)
- return s.startswith(sep)
- # Join pathnames.
- # Ignore the previous parts if a part is absolute.
- # Insert a '/' unless the first part is empty or already ends in '/'.
- def join(a, *p):
- """Join two or more pathname components, inserting '/' as needed.
- If any component is an absolute path, all previous path components
- will be discarded. An empty last part will result in a path that
- ends with a separator."""
- a = os.fspath(a)
- sep = _get_sep(a)
- path = a
- try:
- if not p:
- path[:0] + sep #23780: Ensure compatible data type even if p is null.
- for b in map(os.fspath, p):
- if b.startswith(sep):
- path = b
- elif not path or path.endswith(sep):
- path += b
- else:
- path += sep + b
- except (TypeError, AttributeError, BytesWarning):
- genericpath._check_arg_types('join', a, *p)
- raise
- return path
- # Split a path in head (everything up to the last '/') and tail (the
- # rest). If the path ends in '/', tail will be empty. If there is no
- # '/' in the path, head will be empty.
- # Trailing '/'es are stripped from head unless it is the root.
- def split(p):
- """Split a pathname. Returns tuple "(head, tail)" where "tail" is
- everything after the final slash. Either part may be empty."""
- p = os.fspath(p)
- sep = _get_sep(p)
- i = p.rfind(sep) + 1
- head, tail = p[:i], p[i:]
- if head and head != sep*len(head):
- head = head.rstrip(sep)
- return head, tail
- # Split a path in root and extension.
- # The extension is everything starting at the last dot in the last
- # pathname component; the root is everything before that.
- # It is always true that root + ext == p.
- def splitext(p):
- p = os.fspath(p)
- if isinstance(p, bytes):
- sep = b'/'
- extsep = b'.'
- else:
- sep = '/'
- extsep = '.'
- return genericpath._splitext(p, sep, None, extsep)
- splitext.__doc__ = genericpath._splitext.__doc__
- # Split a pathname into a drive specification and the rest of the
- # path. Useful on DOS/Windows/NT; on Unix, the drive is always empty.
- def splitdrive(p):
- """Split a pathname into drive and path. On Posix, drive is always
- empty."""
- p = os.fspath(p)
- return p[:0], p
- def splitroot(p):
- """Split a pathname into drive, root and tail. On Posix, drive is always
- empty; the root may be empty, a single slash, or two slashes. The tail
- contains anything after the root. For example:
- splitroot('foo/bar') == ('', '', 'foo/bar')
- splitroot('/foo/bar') == ('', '/', 'foo/bar')
- splitroot('//foo/bar') == ('', '//', 'foo/bar')
- splitroot('///foo/bar') == ('', '/', '//foo/bar')
- """
- p = os.fspath(p)
- if isinstance(p, bytes):
- sep = b'/'
- empty = b''
- else:
- sep = '/'
- empty = ''
- if p[:1] != sep:
- # Relative path, e.g.: 'foo'
- return empty, empty, p
- elif p[1:2] != sep or p[2:3] == sep:
- # Absolute path, e.g.: '/foo', '///foo', '////foo', etc.
- return empty, sep, p[1:]
- else:
- # Precisely two leading slashes, e.g.: '//foo'. Implementation defined per POSIX, see
- # https://pubs.opengroup.org/onlinepubs/9699919799/basedefs/V1_chap04.html#tag_04_13
- return empty, p[:2], p[2:]
- # Return the tail (basename) part of a path, same as split(path)[1].
- def basename(p):
- """Returns the final component of a pathname"""
- p = os.fspath(p)
- sep = _get_sep(p)
- i = p.rfind(sep) + 1
- return p[i:]
- # Return the head (dirname) part of a path, same as split(path)[0].
- def dirname(p):
- """Returns the directory component of a pathname"""
- p = os.fspath(p)
- sep = _get_sep(p)
- i = p.rfind(sep) + 1
- head = p[:i]
- if head and head != sep*len(head):
- head = head.rstrip(sep)
- return head
- # Is a path a junction?
- def isjunction(path):
- """Test whether a path is a junction
- Junctions are not a part of posix semantics"""
- os.fspath(path)
- return False
- # Being true for dangling symbolic links is also useful.
- def lexists(path):
- """Test whether a path exists. Returns True for broken symbolic links"""
- try:
- os.lstat(path)
- except (OSError, ValueError):
- return False
- return True
- # Is a path a mount point?
- # (Does this work for all UNIXes? Is it even guaranteed to work by Posix?)
- def ismount(path):
- """Test whether a path is a mount point"""
- try:
- s1 = os.lstat(path)
- except (OSError, ValueError):
- # It doesn't exist -- so not a mount point. :-)
- return False
- else:
- # A symlink can never be a mount point
- if stat.S_ISLNK(s1.st_mode):
- return False
- path = os.fspath(path)
- if isinstance(path, bytes):
- parent = join(path, b'..')
- else:
- parent = join(path, '..')
- parent = realpath(parent)
- try:
- s2 = os.lstat(parent)
- except (OSError, ValueError):
- return False
- dev1 = s1.st_dev
- dev2 = s2.st_dev
- if dev1 != dev2:
- return True # path/.. on a different device as path
- ino1 = s1.st_ino
- ino2 = s2.st_ino
- if ino1 == ino2:
- return True # path/.. is the same i-node as path
- return False
- # Expand paths beginning with '~' or '~user'.
- # '~' means $HOME; '~user' means that user's home directory.
- # If the path doesn't begin with '~', or if the user or $HOME is unknown,
- # the path is returned unchanged (leaving error reporting to whatever
- # function is called with the expanded path as argument).
- # See also module 'glob' for expansion of *, ? and [...] in pathnames.
- # (A function should also be defined to do full *sh-style environment
- # variable expansion.)
- def expanduser(path):
- """Expand ~ and ~user constructions. If user or $HOME is unknown,
- do nothing."""
- path = os.fspath(path)
- if isinstance(path, bytes):
- tilde = b'~'
- else:
- tilde = '~'
- if not path.startswith(tilde):
- return path
- sep = _get_sep(path)
- i = path.find(sep, 1)
- if i < 0:
- i = len(path)
- if i == 1:
- if 'HOME' not in os.environ:
- try:
- import pwd
- except ImportError:
- # pwd module unavailable, return path unchanged
- return path
- try:
- userhome = pwd.getpwuid(os.getuid()).pw_dir
- except KeyError:
- # bpo-10496: if the current user identifier doesn't exist in the
- # password database, return the path unchanged
- return path
- else:
- userhome = os.environ['HOME']
- else:
- try:
- import pwd
- except ImportError:
- # pwd module unavailable, return path unchanged
- return path
- name = path[1:i]
- if isinstance(name, bytes):
- name = os.fsdecode(name)
- try:
- pwent = pwd.getpwnam(name)
- except KeyError:
- # bpo-10496: if the user name from the path doesn't exist in the
- # password database, return the path unchanged
- return path
- userhome = pwent.pw_dir
- # if no user home, return the path unchanged on VxWorks
- if userhome is None and sys.platform == "vxworks":
- return path
- if isinstance(path, bytes):
- userhome = os.fsencode(userhome)
- root = b'/'
- else:
- root = '/'
- userhome = userhome.rstrip(root)
- return (userhome + path[i:]) or root
- # Expand paths containing shell variable substitutions.
- # This expands the forms $variable and ${variable} only.
- # Non-existent variables are left unchanged.
- _varprog = None
- _varprogb = None
- def expandvars(path):
- """Expand shell variables of form $var and ${var}. Unknown variables
- are left unchanged."""
- path = os.fspath(path)
- global _varprog, _varprogb
- if isinstance(path, bytes):
- if b'$' not in path:
- return path
- if not _varprogb:
- import re
- _varprogb = re.compile(br'\$(\w+|\{[^}]*\})', re.ASCII)
- search = _varprogb.search
- start = b'{'
- end = b'}'
- environ = getattr(os, 'environb', None)
- else:
- if '$' not in path:
- return path
- if not _varprog:
- import re
- _varprog = re.compile(r'\$(\w+|\{[^}]*\})', re.ASCII)
- search = _varprog.search
- start = '{'
- end = '}'
- environ = os.environ
- i = 0
- while True:
- m = search(path, i)
- if not m:
- break
- i, j = m.span(0)
- name = m.group(1)
- if name.startswith(start) and name.endswith(end):
- name = name[1:-1]
- try:
- if environ is None:
- value = os.fsencode(os.environ[os.fsdecode(name)])
- else:
- value = environ[name]
- except KeyError:
- i = j
- else:
- tail = path[j:]
- path = path[:i] + value
- i = len(path)
- path += tail
- return path
- # Normalize a path, e.g. A//B, A/./B and A/foo/../B all become A/B.
- # It should be understood that this may change the meaning of the path
- # if it contains symbolic links!
- try:
- from posix import _path_normpath as normpath
- except ImportError:
- def normpath(path):
- """Normalize path, eliminating double slashes, etc."""
- path = os.fspath(path)
- if isinstance(path, bytes):
- sep = b'/'
- empty = b''
- dot = b'.'
- dotdot = b'..'
- else:
- sep = '/'
- empty = ''
- dot = '.'
- dotdot = '..'
- if path == empty:
- return dot
- _, initial_slashes, path = splitroot(path)
- comps = path.split(sep)
- new_comps = []
- for comp in comps:
- if comp in (empty, dot):
- continue
- if (comp != dotdot or (not initial_slashes and not new_comps) or
- (new_comps and new_comps[-1] == dotdot)):
- new_comps.append(comp)
- elif new_comps:
- new_comps.pop()
- comps = new_comps
- path = initial_slashes + sep.join(comps)
- return path or dot
- def abspath(path):
- """Return an absolute path."""
- path = os.fspath(path)
- if not isabs(path):
- if isinstance(path, bytes):
- cwd = os.getcwdb()
- else:
- cwd = os.getcwd()
- path = join(cwd, path)
- return normpath(path)
- # Return a canonical path (i.e. the absolute location of a file on the
- # filesystem).
- def realpath(filename, *, strict=False):
- """Return the canonical path of the specified filename, eliminating any
- symbolic links encountered in the path."""
- filename = os.fspath(filename)
- path, ok = _joinrealpath(filename[:0], filename, strict, {})
- return abspath(path)
- # Join two paths, normalizing and eliminating any symbolic links
- # encountered in the second path.
- def _joinrealpath(path, rest, strict, seen):
- if isinstance(path, bytes):
- sep = b'/'
- curdir = b'.'
- pardir = b'..'
- else:
- sep = '/'
- curdir = '.'
- pardir = '..'
- if isabs(rest):
- rest = rest[1:]
- path = sep
- while rest:
- name, _, rest = rest.partition(sep)
- if not name or name == curdir:
- # current dir
- continue
- if name == pardir:
- # parent dir
- if path:
- path, name = split(path)
- if name == pardir:
- path = join(path, pardir, pardir)
- else:
- path = pardir
- continue
- newpath = join(path, name)
- try:
- st = os.lstat(newpath)
- except OSError:
- if strict:
- raise
- is_link = False
- else:
- is_link = stat.S_ISLNK(st.st_mode)
- if not is_link:
- path = newpath
- continue
- # Resolve the symbolic link
- if newpath in seen:
- # Already seen this path
- path = seen[newpath]
- if path is not None:
- # use cached value
- continue
- # The symlink is not resolved, so we must have a symlink loop.
- if strict:
- # Raise OSError(errno.ELOOP)
- os.stat(newpath)
- else:
- # Return already resolved part + rest of the path unchanged.
- return join(newpath, rest), False
- seen[newpath] = None # not resolved symlink
- path, ok = _joinrealpath(path, os.readlink(newpath), strict, seen)
- if not ok:
- return join(path, rest), False
- seen[newpath] = path # resolved symlink
- return path, True
- supports_unicode_filenames = (sys.platform == 'darwin')
- def relpath(path, start=None):
- """Return a relative version of a path"""
- if not path:
- raise ValueError("no path specified")
- path = os.fspath(path)
- if isinstance(path, bytes):
- curdir = b'.'
- sep = b'/'
- pardir = b'..'
- else:
- curdir = '.'
- sep = '/'
- pardir = '..'
- if start is None:
- start = curdir
- else:
- start = os.fspath(start)
- try:
- start_list = [x for x in abspath(start).split(sep) if x]
- path_list = [x for x in abspath(path).split(sep) if x]
- # Work out how much of the filepath is shared by start and path.
- i = len(commonprefix([start_list, path_list]))
- rel_list = [pardir] * (len(start_list)-i) + path_list[i:]
- if not rel_list:
- return curdir
- return join(*rel_list)
- except (TypeError, AttributeError, BytesWarning, DeprecationWarning):
- genericpath._check_arg_types('relpath', path, start)
- raise
- # Return the longest common sub-path of the sequence of paths given as input.
- # The paths are not normalized before comparing them (this is the
- # responsibility of the caller). Any trailing separator is stripped from the
- # returned path.
- def commonpath(paths):
- """Given a sequence of path names, returns the longest common sub-path."""
- if not paths:
- raise ValueError('commonpath() arg is an empty sequence')
- paths = tuple(map(os.fspath, paths))
- if isinstance(paths[0], bytes):
- sep = b'/'
- curdir = b'.'
- else:
- sep = '/'
- curdir = '.'
- try:
- split_paths = [path.split(sep) for path in paths]
- try:
- isabs, = set(p[:1] == sep for p in paths)
- except ValueError:
- raise ValueError("Can't mix absolute and relative paths") from None
- split_paths = [[c for c in s if c and c != curdir] for s in split_paths]
- s1 = min(split_paths)
- s2 = max(split_paths)
- common = s1
- for i, c in enumerate(s1):
- if c != s2[i]:
- common = s1[:i]
- break
- prefix = sep if isabs else sep[:0]
- return prefix + sep.join(common)
- except (TypeError, AttributeError):
- genericpath._check_arg_types('commonpath', *paths)
- raise
|