r"""OS routines for NT or Posix depending on what system we're on.
- all functions from posix or nt, e.g. unlink, stat, etc.
- os.path is either posixpath or ntpath
- os.name is either 'posix' or 'nt'
- os.curdir is a string representing the current directory (always '.')
- os.pardir is a string representing the parent directory (always '..')
- os.sep is the (or a most common) pathname separator ('/' or '\\')
- os.extsep is the extension separator (always '.')
- os.altsep is the alternate pathname separator (None or '/')
- os.pathsep is the component separator used in $PATH etc
- os.linesep is the line separator in text files ('\r' or '\n' or '\r\n')
- os.defpath is the default search path for executables
- os.devnull is the file path of the null device ('/dev/null', etc.)
Programs that import and use 'os' stand a better chance of being
portable between different platforms. Of course, they must then
only use functions that are defined by all platforms (e.g., unlink
and opendir), and leave all pathname manipulation to os.path
_names = sys.builtin_module_names
# Note: more names are added to __all__ later.
__all__ = ["altsep", "curdir", "pardir", "sep", "pathsep", "linesep",
"defpath", "name", "path", "devnull", "SEEK_SET", "SEEK_CUR",
"SEEK_END", "fsencode", "fsdecode", "get_exec_path", "fdopen",
def _get_exports_list(module):
return list(module.__all__)
return [n for n in dir(module) if n[0] != '_']
# Any new dependencies of the os module and/or changes in path separator
# requires updating importlib as well.
from posix import _have_functions
__all__.extend(_get_exports_list(posix))
__all__.extend(_get_exports_list(nt))
from nt import _have_functions
raise ImportError('no os specific module found')
sys.modules['os.path'] = path
from os.path import (curdir, pardir, sep, pathsep, defpath, extsep, altsep,
if _exists("_have_functions"):
if (fn in _globals) and (str in _have_functions):
_add("HAVE_FACCESSAT", "access")
_add("HAVE_FCHMODAT", "chmod")
_add("HAVE_FCHOWNAT", "chown")
_add("HAVE_FSTATAT", "stat")
_add("HAVE_FUTIMESAT", "utime")
_add("HAVE_LINKAT", "link")
_add("HAVE_MKDIRAT", "mkdir")
_add("HAVE_MKFIFOAT", "mkfifo")
_add("HAVE_MKNODAT", "mknod")
_add("HAVE_OPENAT", "open")
_add("HAVE_READLINKAT", "readlink")
_add("HAVE_RENAMEAT", "rename")
_add("HAVE_SYMLINKAT", "symlink")
_add("HAVE_UNLINKAT", "unlink")
_add("HAVE_UNLINKAT", "rmdir")
_add("HAVE_UTIMENSAT", "utime")
_add("HAVE_FACCESSAT", "access")
supports_effective_ids = _set
_add("HAVE_FCHDIR", "chdir")
_add("HAVE_FCHMOD", "chmod")
_add("HAVE_FCHOWN", "chown")
_add("HAVE_FDOPENDIR", "listdir")
_add("HAVE_FEXECVE", "execve")
_set.add(stat) # fstat always works
_add("HAVE_FTRUNCATE", "truncate")
_add("HAVE_FUTIMENS", "utime")
_add("HAVE_FUTIMES", "utime")
_add("HAVE_FPATHCONF", "pathconf")
if _exists("statvfs") and _exists("fstatvfs"): # mac os x10.3
_add("HAVE_FSTATVFS", "statvfs")
_add("HAVE_FACCESSAT", "access")
# Some platforms don't support lchmod(). Often the function exists
# anyway, as a stub that always returns ENOSUP or perhaps EOPNOTSUPP.
# (No, I don't know why that's a good design.) ./configure will detect
# this and reject it--so HAVE_LCHMOD still won't be defined on such
# platforms. This is Very Helpful.
# However, sometimes platforms without a working lchmod() *do* have
# fchmodat(). (Examples: Linux kernel 3.2 with glibc 2.15,
# OpenIndiana 3.x.) And fchmodat() has a flag that theoretically makes
# it behave like lchmod(). So in theory it would be a suitable
# replacement for lchmod(). But when lchmod() doesn't work, fchmodat()'s
# flag doesn't work *either*. Sadly ./configure isn't sophisticated
# enough to detect this condition--it only determines whether or not
# fchmodat() minimally works.
# Therefore we simply ignore fchmodat() when deciding whether or not
# os.chmod supports follow_symlinks. Just checking lchmod() is
# sufficient. After all--if you have a working fchmodat(), your
# lchmod() almost certainly works too.
# _add("HAVE_FCHMODAT", "chmod")
_add("HAVE_FCHOWNAT", "chown")
_add("HAVE_FSTATAT", "stat")
_add("HAVE_LCHFLAGS", "chflags")
_add("HAVE_LCHMOD", "chmod")
if _exists("lchown"): # mac os x10.3
_add("HAVE_LCHOWN", "chown")
_add("HAVE_LINKAT", "link")
_add("HAVE_LUTIMES", "utime")
_add("HAVE_LSTAT", "stat")
_add("HAVE_FSTATAT", "stat")
_add("HAVE_UTIMENSAT", "utime")
_add("MS_WINDOWS", "stat")
supports_follow_symlinks = _set
# Python uses fixed values for the SEEK_ constants; they are mapped
# to native constants if necessary in posixmodule.c
# Other possible SEEK values are directly imported from posixmodule.c
# Super directory utilities.
# (Inspired by Eric Raymond; the doc strings are mostly his)
def makedirs(name, mode=0o777, exist_ok=False):
"""makedirs(name [, mode=0o777][, exist_ok=False])
Super-mkdir; create a leaf directory and all intermediate ones. Works like
mkdir, except that any intermediate path segment (not just the rightmost)
will be created if it does not exist. If the target directory already
exists, raise an OSError if exist_ok is False. Otherwise no exception is
raised. This is recursive.
head, tail = path.split(name)
head, tail = path.split(head)
if head and tail and not path.exists(head):
makedirs(head, mode, exist_ok)
# Defeats race condition when another thread created the path
if isinstance(tail, bytes):
cdir = bytes(curdir, 'ASCII')
if tail == cdir: # xxx/newdir/. exists if xxx/newdir exists
# 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 path.isdir(name):
Super-rmdir; remove a leaf directory and all empty intermediate
ones. Works like rmdir except that, if the leaf directory is
successfully removed, directories corresponding to rightmost path
segments will be pruned away until either the whole path is
consumed or an error occurs. Errors during this latter phase are
ignored -- they generally mean that a directory was not empty.
head, tail = path.split(name)
head, tail = path.split(head)
head, tail = path.split(head)
Super-rename; create directories as necessary and delete any left
empty. Works like rename, except creation of any intermediate
directories needed to make the new pathname good is attempted
first. After the rename, directories corresponding to rightmost
path segments of the old name will be pruned until either the
whole path is consumed or a nonempty directory is found.
Note: this function can fail with the new directory structure made
if you lack permissions needed to unlink the leaf directory or
head, tail = path.split(new)
if head and tail and not path.exists(head):
head, tail = path.split(old)
__all__.extend(["makedirs", "removedirs", "renames"])
def walk(top, topdown=True, onerror=None, followlinks=False):
"""Directory tree generator.
For each directory in the directory tree rooted at top (including top
itself, but excluding '.' and '..'), yields a 3-tuple
dirpath, dirnames, filenames
dirpath is a string, the path to the directory. dirnames is a list of
the names of the subdirectories in dirpath (excluding '.' and '..').
filenames is a list of the names of the non-directory files in dirpath.
Note that the names in the lists are just names, with no path components.
To get a full path (which begins with top) to a file or directory in
dirpath, do os.path.join(dirpath, name).
If optional arg 'topdown' is true or not specified, the triple for a
directory is generated before the triples for any of its subdirectories
(directories are generated top down). If topdown is false, the triple
for a directory is generated after the triples for all of its
subdirectories (directories are generated bottom up).
When topdown is true, the caller can modify the dirnames list in-place
(e.g., via del or slice assignment), and walk will only recurse into the
subdirectories whose names remain in dirnames; this can be used to prune the
search, or to impose a specific order of visiting. Modifying dirnames when
topdown is false is ineffective, since the directories in dirnames have
already been generated by the time dirnames itself is generated. No matter
the value of topdown, the list of subdirectories is retrieved before the
tuples for the directory and its subdirectories are generated.
By default errors from the os.scandir() call are ignored. If
optional arg 'onerror' is specified, it should be a function; it
will be called with one argument, an OSError instance. It can
report the error to continue with the walk, or raise the exception
to abort the walk. Note that the filename is available as the
filename attribute of the exception object.
By default, os.walk does not follow symbolic links to subdirectories on
systems that support them. In order to get this functionality, set the
optional argument 'followlinks' to true.
Caution: if you pass a relative pathname for top, don't change the
current working directory between resumptions of walk. walk never
changes the current directory, and assumes that the client doesn't
from os.path import join, getsize
for root, dirs, files in os.walk('python/Lib/email'):
print(root, "consumes", end="")
print(sum([getsize(join(root, name)) for name in files]), end="")
print("bytes in", len(files), "non-directory files")
dirs.remove('CVS') # don't visit CVS directories
# We may not have read permission for top, in which case we can't
# get a list of the files the directory contains. os.walk
# always suppressed the exception then, rather than blow up for a
# minor reason when (say) a thousand readable directories are still
# left to visit. That logic is copied here.
# Note that scandir is global in this module due
scandir_it = scandir(top)
# If is_dir() raises an OSError, consider that the entry is not
# a directory, same behaviour than os.path.isdir().
nondirs.append(entry.name)
if not topdown and is_dir:
# Bottom-up: recurse into sub-directory, but exclude symlinks to
# directories if followlinks is False
is_symlink = entry.is_symlink()
# If is_symlink() raises an OSError, consider that the
# entry is not a symbolic link, same behaviour than
walk_into = not is_symlink
walk_dirs.append(entry.path)
# Yield before recursion if going top down
# Recurse into sub-directories
islink, join = path.islink, path.join
new_path = join(top, dirname)
# Issue #23605: os.path.islink() is used instead of caching
# entry.is_symlink() result during the loop on os.scandir() because
# the caller can replace the directory entry during the "yield"
if followlinks or not islink(new_path):
yield from walk(new_path, topdown, onerror, followlinks)
# Recurse into sub-directories
for new_path in walk_dirs:
yield from walk(new_path, topdown, onerror, followlinks)
# Yield after recursion if going bottom up
if {open, stat} <= supports_dir_fd and {listdir, stat} <= supports_fd:
def fwalk(top=".", topdown=True, onerror=None, *, follow_symlinks=False, dir_fd=None):
"""Directory tree generator.
This behaves exactly like walk(), except that it yields a 4-tuple
dirpath, dirnames, filenames, dirfd
`dirpath`, `dirnames` and `filenames` are identical to walk() output,
and `dirfd` is a file descriptor referring to the directory `dirpath`.
The advantage of fwalk() over walk() is that it's safe against symlink
races (when follow_symlinks is False).
If dir_fd is not None, it should be a file descriptor open to a directory,
and top should be relative; top will then be relative to that directory.
(dir_fd is always supported for fwalk.)
Since fwalk() yields file descriptors, those are only valid until the
next iteration step, so you should dup() them if you want to keep them
for root, dirs, files, rootfd in os.fwalk('python/Lib/email'):
print(root, "consumes", end="")
print(sum([os.stat(name, dir_fd=rootfd).st_size for name in files]),
print("bytes in", len(files), "non-directory files")
dirs.remove('CVS') # don't visit CVS directories
if not isinstance(top, int) or not hasattr(top, '__index__'):
# Note: To guard against symlink races, we use the standard
# lstat()/open()/fstat() trick.
orig_st = stat(top, follow_symlinks=False, dir_fd=dir_fd)
topfd = open(top, O_RDONLY, dir_fd=dir_fd)
if (follow_symlinks or (st.S_ISDIR(orig_st.st_mode) and
path.samestat(orig_st, stat(topfd)))):
yield from _fwalk(topfd, top, topdown, onerror, follow_symlinks)
def _fwalk(topfd, toppath, topdown, onerror, follow_symlinks):
# Note: This uses O(depth of the directory tree) file descriptors: if
# necessary, it can be adapted to only require O(1) FDs, see issue
# Here, we don't use AT_SYMLINK_NOFOLLOW to be consistent with
# walk() which reports symlinks to directories as directories.
# We do however check for symlinks before recursing into
if st.S_ISDIR(stat(name, dir_fd=topfd).st_mode):
# Add dangling symlinks, ignore disappeared files
if st.S_ISLNK(stat(name, dir_fd=topfd, follow_symlinks=False)
yield toppath, dirs, nondirs, topfd
orig_st = stat(name, dir_fd=topfd, follow_symlinks=follow_symlinks)
dirfd = open(name, O_RDONLY, dir_fd=topfd)