summaryrefslogtreecommitdiffstats
path: root/Lib/posixpath.py
blob: bc76c90dde42857f2ffaea1ac65ad2ee66e038fa (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
"""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. Mac, Windows),
os.path provides the same operations in a manner specific to that
platform, and is an alias to another module (e.g. macpath, ntpath).

Some of this can actually be useful on non-Posix systems too, e.g.
for manipulation of the pathname component of URLs.
"""

import os
import sys
import stat
import genericpath
from genericpath import *

__all__ = ["normcase","isabs","join","splitdrive","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"]

# Strings representing various path-related bits and pieces.
# These are primarily for export; internally, they are hardcoded.
curdir = '.'
pardir = '..'
extsep = '.'
sep = '/'
pathsep = ':'
defpath = ':/bin:/usr/bin'
altsep = None
devnull = '/dev/null'

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"""
    # TODO: on Mac OS X, this should really return s.lower().
    if not isinstance(s, (bytes, str)):
        raise TypeError("normcase() argument must be str or bytes, "
                        "not '{}'".format(s.__class__.__name__))
    return 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"""
    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."""
    sep = _get_sep(a)
    path = a
    try:
        for b in p:
            if b.startswith(sep):
                path = b
            elif not path or path.endswith(sep):
                path += b
            else:
                path += sep + b
    except TypeError:
        valid_types = all(isinstance(s, (str, bytes, bytearray))
                          for s in (a, ) + p)
        if valid_types:
            # Must have a mixture of text and binary data
            raise TypeError("Can't mix strings and bytes in path components.")
        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."""
    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):
    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."""
    return p[:0], p


# Return the tail (basename) part of a path, same as split(path)[1].

def basename(p):
    """Returns the final component of a pathname"""
    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"""
    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 symbolic link?
# This will always return false on systems where os.lstat doesn't exist.

def islink(path):
    """Test whether a path is a symbolic link"""
    try:
        st = os.lstat(path)
    except (os.error, AttributeError):
        return False
    return stat.S_ISLNK(st.st_mode)

# 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 os.error:
        return False
    return True


# Are two filenames really pointing to the same file?

def samefile(f1, f2):
    """Test whether two pathnames reference the same actual file"""
    s1 = os.stat(f1)
    s2 = os.stat(f2)
    return samestat(s1, s2)


# Are two open files really referencing the same file?
# (Not necessarily the same file descriptor!)

def sameopenfile(fp1, fp2):
    """Test whether two open file objects reference the same file"""
    s1 = os.fstat(fp1)
    s2 = os.fstat(fp2)
    return samestat(s1, s2)


# Are two stat buffers (obtained from stat, fstat or lstat)
# describing the same file?

def samestat(s1, s2):
    """Test whether two stat buffers reference the same file"""
    return s1.st_ino == s2.st_ino and \
           s1.st_dev == s2.st_dev


# 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"""
    if islink(path):
        # A symlink can never be a mount point
        return False
    try:
        s1 = os.lstat(path)
        if isinstance(path, bytes):
            parent = join(path, b'..')
        else:
            parent = join(path, '..')
        s2 = os.lstat(parent)
    except os.error:
        return False # It doesn't exist -- so not a mount point :-)
    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."""
    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:
            import pwd
            userhome = pwd.getpwuid(os.getuid()).pw_dir
        else:
            userhome = os.environ['HOME']
    else:
        import pwd
        name = path[1:i]
        if isinstance(name, bytes):
            name = str(name, 'ASCII')
        try:
            pwent = pwd.getpwnam(name)
        except KeyError:
            return path
        userhome = pwent.pw_dir
    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 ${var}.  Unknown variables
    are left unchanged."""
    global _varprog, _varprogb
    if isinstance(path, bytes):
        if b'$' not in path:
            return path
        if not _varprogb:
            import re
            _varprogb = re.compile(br'\$(\w+|\{[^}]*\})', re.ASCII)
        search = _varprogb.search
        start = b'{'
        end = b'}'
    else:
        if '$' not in path:
            return path
        if not _varprog:
            import re
            _varprog = re.compile(r'\$(\w+|\{[^}]*\})', re.ASCII)
        search = _varprog.search
        start = '{'
        end = '}'
    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]
        if isinstance(name, bytes):
            name = str(name, 'ASCII')
        if name in os.environ:
            tail = path[j:]
            value = os.environ[name]
            if isinstance(path, bytes):
                value = value.encode('ASCII')
            path = path[:i] + value
            i = len(path)
            path += tail
        else:
            i = j
    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!

def normpath(path):
    """Normalize path, eliminating double slashes, etc."""
    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.startswith(sep)
    # POSIX allows one or two initial slashes, but treats three or more
    # as single slash.
    if (initial_slashes and
        path.startswith(sep*2) and not path.startswith(sep*3)):
        initial_slashes = 2
    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 = sep.join(comps)
    if initial_slashes:
        path = sep*initial_slashes + path
    return path or dot


def abspath(path):
    """Return an absolute 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):
    """Return the canonical path of the specified filename, eliminating any
symbolic links encountered in the path."""
    path, ok = _joinrealpath(filename[:0], filename, {})
    return abspath(path)

# Join two paths, normalizing ang eliminating any symbolic links
# encountered in the second path.
def _joinrealpath(path, rest, 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)
        if not islink(newpath):
            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.
            # 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), 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")

    if isinstance(path, bytes):
        curdir = b'.'
        sep = b'/'
        pardir = b'..'
    else:
        curdir = '.'
        sep = '/'
        pardir = '..'

    if start is None:
        start = curdir

    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)