forked from jaraco/path
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathpath.py
More file actions
1722 lines (1366 loc) · 54.3 KB
/
path.py
File metadata and controls
1722 lines (1366 loc) · 54.3 KB
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
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
#
# Copyright (c) 2010 Mikhail Gusarov
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.
#
"""
path.py - An object representing a path to a file or directory.
https://github.com/jaraco/path.py
Example::
from path import Path
d = Path('/home/guido/bin')
for f in d.files('*.py'):
f.chmod(0o755)
"""
from __future__ import unicode_literals
import sys
import warnings
import os
import fnmatch
import glob
import shutil
import codecs
import hashlib
import errno
import tempfile
import functools
import operator
import re
import contextlib
import io
from distutils import dir_util
import importlib
try:
import win32security
except ImportError:
pass
try:
import pwd
except ImportError:
pass
try:
import grp
except ImportError:
pass
##############################################################################
# Python 2/3 support
PY3 = sys.version_info >= (3,)
PY2 = not PY3
string_types = str,
text_type = str
getcwdu = os.getcwd
def surrogate_escape(error):
"""
Simulate the Python 3 ``surrogateescape`` handler, but for Python 2 only.
"""
chars = error.object[error.start:error.end]
assert len(chars) == 1
val = ord(chars)
val += 0xdc00
return __builtin__.unichr(val), error.end
if PY2:
import __builtin__
string_types = __builtin__.basestring,
text_type = __builtin__.unicode
getcwdu = os.getcwdu
codecs.register_error('surrogateescape', surrogate_escape)
@contextlib.contextmanager
def io_error_compat():
try:
yield
except IOError as io_err:
# On Python 2, io.open raises IOError; transform to OSError for
# future compatibility.
os_err = OSError(*io_err.args)
os_err.filename = getattr(io_err, 'filename', None)
raise os_err
##############################################################################
__all__ = ['Path', 'CaseInsensitivePattern']
LINESEPS = ['\r\n', '\r', '\n']
U_LINESEPS = LINESEPS + ['\u0085', '\u2028', '\u2029']
NEWLINE = re.compile('|'.join(LINESEPS))
U_NEWLINE = re.compile('|'.join(U_LINESEPS))
NL_END = re.compile(r'(?:{0})$'.format(NEWLINE.pattern))
U_NL_END = re.compile(r'(?:{0})$'.format(U_NEWLINE.pattern))
try:
import pkg_resources
__version__ = pkg_resources.require('path.py')[0].version
except Exception:
__version__ = 'unknown'
class TreeWalkWarning(Warning):
pass
# from jaraco.functools
def compose(*funcs):
compose_two = lambda f1, f2: lambda *args, **kwargs: f1(f2(*args, **kwargs))
return functools.reduce(compose_two, funcs)
def simple_cache(func):
"""
Save results for the :meth:'path.using_module' classmethod.
When Python 3.2 is available, use functools.lru_cache instead.
"""
saved_results = {}
def wrapper(cls, module):
if module in saved_results:
return saved_results[module]
saved_results[module] = func(cls, module)
return saved_results[module]
return wrapper
class ClassProperty(property):
def __get__(self, cls, owner):
return self.fget.__get__(None, owner)()
class multimethod(object):
"""
Acts like a classmethod when invoked from the class and like an
instancemethod when invoked from the instance.
"""
def __init__(self, func):
self.func = func
def __get__(self, instance, owner):
return (
functools.partial(self.func, owner) if instance is None
else functools.partial(self.func, owner, instance)
)
class Path(text_type):
"""
Represents a filesystem path.
For documentation on individual methods, consult their
counterparts in :mod:`os.path`.
Some methods are additionally included from :mod:`shutil`.
The functions are linked directly into the class namespace
such that they will be bound to the Path instance. For example,
``Path(src).copy(target)`` is equivalent to
``shutil.copy(src, target)``. Therefore, when referencing
the docs for these methods, assume `src` references `self`,
the Path instance.
"""
module = os.path
""" The path module to use for path operations.
.. seealso:: :mod:`os.path`
"""
def __init__(self, other=''):
if other is None:
raise TypeError("Invalid initial value for path: None")
@classmethod
@simple_cache
def using_module(cls, module):
subclass_name = cls.__name__ + '_' + module.__name__
if PY2:
subclass_name = str(subclass_name)
bases = (cls,)
ns = {'module': module}
return type(subclass_name, bases, ns)
@ClassProperty
@classmethod
def _next_class(cls):
"""
What class should be used to construct new instances from this class
"""
return cls
@classmethod
def _always_unicode(cls, path):
"""
Ensure the path as retrieved from a Python API, such as :func:`os.listdir`,
is a proper Unicode string.
"""
if PY3 or isinstance(path, text_type):
return path
return path.decode(sys.getfilesystemencoding(), 'surrogateescape')
# --- Special Python methods.
def __repr__(self):
return '%s(%s)' % (type(self).__name__, super(Path, self).__repr__())
# Adding a Path and a string yields a Path.
def __add__(self, more):
try:
return self._next_class(super(Path, self).__add__(more))
except TypeError: # Python bug
return NotImplemented
def __radd__(self, other):
if not isinstance(other, string_types):
return NotImplemented
return self._next_class(other.__add__(self))
# The / operator joins Paths.
def __div__(self, rel):
""" fp.__div__(rel) == fp / rel == fp.joinpath(rel)
Join two path components, adding a separator character if
needed.
.. seealso:: :func:`os.path.join`
"""
return self._next_class(self.module.join(self, rel))
# Make the / operator work even when true division is enabled.
__truediv__ = __div__
# The / operator joins Paths the other way around
def __rdiv__(self, rel):
""" fp.__rdiv__(rel) == rel / fp
Join two path components, adding a separator character if
needed.
.. seealso:: :func:`os.path.join`
"""
return self._next_class(self.module.join(rel, self))
# Make the / operator work even when true division is enabled.
__rtruediv__ = __rdiv__
def __enter__(self):
self._old_dir = self.getcwd()
os.chdir(self)
return self
def __exit__(self, *_):
os.chdir(self._old_dir)
@classmethod
def getcwd(cls):
""" Return the current working directory as a path object.
.. seealso:: :func:`os.getcwdu`
"""
return cls(getcwdu())
#
# --- Operations on Path strings.
def abspath(self):
""" .. seealso:: :func:`os.path.abspath` """
return self._next_class(self.module.abspath(self))
def normcase(self):
""" .. seealso:: :func:`os.path.normcase` """
return self._next_class(self.module.normcase(self))
def normpath(self):
""" .. seealso:: :func:`os.path.normpath` """
return self._next_class(self.module.normpath(self))
def realpath(self):
""" .. seealso:: :func:`os.path.realpath` """
return self._next_class(self.module.realpath(self))
def expanduser(self):
""" .. seealso:: :func:`os.path.expanduser` """
return self._next_class(self.module.expanduser(self))
def expandvars(self):
""" .. seealso:: :func:`os.path.expandvars` """
return self._next_class(self.module.expandvars(self))
def dirname(self):
""" .. seealso:: :attr:`parent`, :func:`os.path.dirname` """
return self._next_class(self.module.dirname(self))
def basename(self):
""" .. seealso:: :attr:`name`, :func:`os.path.basename` """
return self._next_class(self.module.basename(self))
def expand(self):
""" Clean up a filename by calling :meth:`expandvars()`,
:meth:`expanduser()`, and :meth:`normpath()` on it.
This is commonly everything needed to clean up a filename
read from a configuration file, for example.
"""
return self.expandvars().expanduser().normpath()
@property
def namebase(self):
""" The same as :meth:`name`, but with one file extension stripped off.
For example,
``Path('/home/guido/python.tar.gz').name == 'python.tar.gz'``,
but
``Path('/home/guido/python.tar.gz').namebase == 'python.tar'``.
"""
base, ext = self.module.splitext(self.name)
return base
@property
def ext(self):
""" The file extension, for example ``'.py'``. """
f, ext = self.module.splitext(self)
return ext
@property
def drive(self):
""" The drive specifier, for example ``'C:'``.
This is always empty on systems that don't use drive specifiers.
"""
drive, r = self.module.splitdrive(self)
return self._next_class(drive)
parent = property(
dirname, None, None,
""" This path's parent directory, as a new Path object.
For example,
``Path('/usr/local/lib/libpython.so').parent ==
Path('/usr/local/lib')``
.. seealso:: :meth:`dirname`, :func:`os.path.dirname`
""")
name = property(
basename, None, None,
""" The name of this file or directory without the full path.
For example,
``Path('/usr/local/lib/libpython.so').name == 'libpython.so'``
.. seealso:: :meth:`basename`, :func:`os.path.basename`
""")
def splitpath(self):
""" p.splitpath() -> Return ``(p.parent, p.name)``.
.. seealso:: :attr:`parent`, :attr:`name`, :func:`os.path.split`
"""
parent, child = self.module.split(self)
return self._next_class(parent), child
def splitdrive(self):
""" p.splitdrive() -> Return ``(p.drive, <the rest of p>)``.
Split the drive specifier from this path. If there is
no drive specifier, :samp:`{p.drive}` is empty, so the return value
is simply ``(Path(''), p)``. This is always the case on Unix.
.. seealso:: :func:`os.path.splitdrive`
"""
drive, rel = self.module.splitdrive(self)
return self._next_class(drive), rel
def splitext(self):
""" p.splitext() -> Return ``(p.stripext(), p.ext)``.
Split the filename extension from this path and return
the two parts. Either part may be empty.
The extension is everything from ``'.'`` to the end of the
last path segment. This has the property that if
``(a, b) == p.splitext()``, then ``a + b == p``.
.. seealso:: :func:`os.path.splitext`
"""
filename, ext = self.module.splitext(self)
return self._next_class(filename), ext
def stripext(self):
""" p.stripext() -> Remove one file extension from the path.
For example, ``Path('/home/guido/python.tar.gz').stripext()``
returns ``Path('/home/guido/python.tar')``.
"""
return self.splitext()[0]
def splitunc(self):
""" .. seealso:: :func:`os.path.splitunc` """
unc, rest = self.module.splitunc(self)
return self._next_class(unc), rest
@property
def uncshare(self):
"""
The UNC mount point for this path.
This is empty for paths on local drives.
"""
unc, r = self.module.splitunc(self)
return self._next_class(unc)
@multimethod
def joinpath(cls, first, *others):
"""
Join first to zero or more :class:`Path` components, adding a separator
character (:samp:`{first}.module.sep`) if needed. Returns a new instance of
:samp:`{first}._next_class`.
.. seealso:: :func:`os.path.join`
"""
if not isinstance(first, cls):
first = cls(first)
return first._next_class(first.module.join(first, *others))
def splitall(self):
r""" Return a list of the path components in this path.
The first item in the list will be a Path. Its value will be
either :data:`os.curdir`, :data:`os.pardir`, empty, or the root
directory of this path (for example, ``'/'`` or ``'C:\\'``). The
other items in the list will be strings.
``path.Path.joinpath(*result)`` will yield the original path.
"""
parts = []
loc = self
while loc != os.curdir and loc != os.pardir:
prev = loc
loc, child = prev.splitpath()
if loc == prev:
break
parts.append(child)
parts.append(loc)
parts.reverse()
return parts
def relpath(self, start='.'):
""" Return this path as a relative path,
based from `start`, which defaults to the current working directory.
"""
cwd = self._next_class(start)
return cwd.relpathto(self)
def relpathto(self, dest):
""" Return a relative path from `self` to `dest`.
If there is no relative path from `self` to `dest`, for example if
they reside on different drives in Windows, then this returns
``dest.abspath()``.
"""
origin = self.abspath()
dest = self._next_class(dest).abspath()
orig_list = origin.normcase().splitall()
# Don't normcase dest! We want to preserve the case.
dest_list = dest.splitall()
if orig_list[0] != self.module.normcase(dest_list[0]):
# Can't get here from there.
return dest
# Find the location where the two paths start to differ.
i = 0
for start_seg, dest_seg in zip(orig_list, dest_list):
if start_seg != self.module.normcase(dest_seg):
break
i += 1
# Now i is the point where the two paths diverge.
# Need a certain number of "os.pardir"s to work up
# from the origin to the point of divergence.
segments = [os.pardir] * (len(orig_list) - i)
# Need to add the diverging part of dest_list.
segments += dest_list[i:]
if len(segments) == 0:
# If they happen to be identical, use os.curdir.
relpath = os.curdir
else:
relpath = self.module.join(*segments)
return self._next_class(relpath)
# --- Listing, searching, walking, and matching
def listdir(self, pattern=None):
""" D.listdir() -> List of items in this directory.
Use :meth:`files` or :meth:`dirs` instead if you want a listing
of just files or just subdirectories.
The elements of the list are Path objects.
With the optional `pattern` argument, this only lists
items whose names match the given pattern.
.. seealso:: :meth:`files`, :meth:`dirs`
"""
if pattern is None:
pattern = '*'
return [
self / child
for child in map(self._always_unicode, os.listdir(self))
if self._next_class(child).fnmatch(pattern)
]
def dirs(self, pattern=None):
""" D.dirs() -> List of this directory's subdirectories.
The elements of the list are Path objects.
This does not walk recursively into subdirectories
(but see :meth:`walkdirs`).
With the optional `pattern` argument, this only lists
directories whose names match the given pattern. For
example, ``d.dirs('build-*')``.
"""
return [p for p in self.listdir(pattern) if p.isdir()]
def files(self, pattern=None):
""" D.files() -> List of the files in this directory.
The elements of the list are Path objects.
This does not walk into subdirectories (see :meth:`walkfiles`).
With the optional `pattern` argument, this only lists files
whose names match the given pattern. For example,
``d.files('*.pyc')``.
"""
return [p for p in self.listdir(pattern) if p.isfile()]
def walk(self, pattern=None, errors='strict'):
""" D.walk() -> iterator over files and subdirs, recursively.
The iterator yields Path objects naming each child item of
this directory and its descendants. This requires that
``D.isdir()``.
This performs a depth-first traversal of the directory tree.
Each directory is returned just before all its children.
The `errors=` keyword argument controls behavior when an
error occurs. The default is ``'strict'``, which causes an
exception. Other allowed values are ``'warn'`` (which
reports the error via :func:`warnings.warn()`), and ``'ignore'``.
`errors` may also be an arbitrary callable taking a msg parameter.
"""
class Handlers:
def strict(msg):
raise
def warn(msg):
warnings.warn(msg, TreeWalkWarning)
def ignore(msg):
pass
if not callable(errors) and errors not in vars(Handlers):
raise ValueError("invalid errors parameter")
errors = vars(Handlers).get(errors, errors)
try:
childList = self.listdir()
except Exception:
exc = sys.exc_info()[1]
tmpl = "Unable to list directory '%(self)s': %(exc)s"
msg = tmpl % locals()
errors(msg)
return
for child in childList:
if pattern is None or child.fnmatch(pattern):
yield child
try:
isdir = child.isdir()
except Exception:
exc = sys.exc_info()[1]
tmpl = "Unable to access '%(child)s': %(exc)s"
msg = tmpl % locals()
errors(msg)
isdir = False
if isdir:
for item in child.walk(pattern, errors):
yield item
def walkdirs(self, pattern=None, errors='strict'):
""" D.walkdirs() -> iterator over subdirs, recursively.
With the optional `pattern` argument, this yields only
directories whose names match the given pattern. For
example, ``mydir.walkdirs('*test')`` yields only directories
with names ending in ``'test'``.
The `errors=` keyword argument controls behavior when an
error occurs. The default is ``'strict'``, which causes an
exception. The other allowed values are ``'warn'`` (which
reports the error via :func:`warnings.warn()`), and ``'ignore'``.
"""
if errors not in ('strict', 'warn', 'ignore'):
raise ValueError("invalid errors parameter")
try:
dirs = self.dirs()
except Exception:
if errors == 'ignore':
return
elif errors == 'warn':
warnings.warn(
"Unable to list directory '%s': %s"
% (self, sys.exc_info()[1]),
TreeWalkWarning)
return
else:
raise
for child in dirs:
if pattern is None or child.fnmatch(pattern):
yield child
for subsubdir in child.walkdirs(pattern, errors):
yield subsubdir
def walkfiles(self, pattern=None, errors='strict'):
""" D.walkfiles() -> iterator over files in D, recursively.
The optional argument `pattern` limits the results to files
with names that match the pattern. For example,
``mydir.walkfiles('*.tmp')`` yields only files with the ``.tmp``
extension.
"""
if errors not in ('strict', 'warn', 'ignore'):
raise ValueError("invalid errors parameter")
try:
childList = self.listdir()
except Exception:
if errors == 'ignore':
return
elif errors == 'warn':
warnings.warn(
"Unable to list directory '%s': %s"
% (self, sys.exc_info()[1]),
TreeWalkWarning)
return
else:
raise
for child in childList:
try:
isfile = child.isfile()
isdir = not isfile and child.isdir()
except:
if errors == 'ignore':
continue
elif errors == 'warn':
warnings.warn(
"Unable to access '%s': %s"
% (self, sys.exc_info()[1]),
TreeWalkWarning)
continue
else:
raise
if isfile:
if pattern is None or child.fnmatch(pattern):
yield child
elif isdir:
for f in child.walkfiles(pattern, errors):
yield f
def fnmatch(self, pattern, normcase=None):
""" Return ``True`` if `self.name` matches the given `pattern`.
`pattern` - A filename pattern with wildcards,
for example ``'*.py'``. If the pattern contains a `normcase`
attribute, it is applied to the name and path prior to comparison.
`normcase` - (optional) A function used to normalize the pattern and
filename before matching. Defaults to :meth:`self.module`, which defaults
to :meth:`os.path.normcase`.
.. seealso:: :func:`fnmatch.fnmatch`
"""
default_normcase = getattr(pattern, 'normcase', self.module.normcase)
normcase = normcase or default_normcase
name = normcase(self.name)
pattern = normcase(pattern)
return fnmatch.fnmatchcase(name, pattern)
def glob(self, pattern):
""" Return a list of Path objects that match the pattern.
`pattern` - a path relative to this directory, with wildcards.
For example, ``Path('/users').glob('*/bin/*')`` returns a list
of all the files users have in their :file:`bin` directories.
.. seealso:: :func:`glob.glob`
"""
cls = self._next_class
return [cls(s) for s in glob.glob(self / pattern)]
#
# --- Reading or writing an entire file at once.
def open(self, *args, **kwargs):
""" Open this file and return a corresponding :class:`file` object.
Keyword arguments work as in :func:`io.open`. If the file cannot be
opened, an :class:`~exceptions.OSError` is raised.
"""
with io_error_compat():
return io.open(self, *args, **kwargs)
def bytes(self):
""" Open this file, read all bytes, return them as a string. """
with self.open('rb') as f:
return f.read()
def chunks(self, size, *args, **kwargs):
""" Returns a generator yielding chunks of the file, so it can
be read piece by piece with a simple for loop.
Any argument you pass after `size` will be passed to :meth:`open`.
:example:
>>> hash = hashlib.md5()
>>> for chunk in Path("path.py").chunks(8192, mode='rb'):
... hash.update(chunk)
This will read the file by chunks of 8192 bytes.
"""
with self.open(*args, **kwargs) as f:
for chunk in iter(lambda: f.read(size) or None, None):
yield chunk
def write_bytes(self, bytes, append=False):
""" Open this file and write the given bytes to it.
Default behavior is to overwrite any existing file.
Call ``p.write_bytes(bytes, append=True)`` to append instead.
"""
if append:
mode = 'ab'
else:
mode = 'wb'
with self.open(mode) as f:
f.write(bytes)
def text(self, encoding=None, errors='strict'):
r""" Open this file, read it in, return the content as a string.
All newline sequences are converted to ``'\n'``. Keyword arguments
will be passed to :meth:`open`.
.. seealso:: :meth:`lines`
"""
with self.open(mode='r', encoding=encoding, errors=errors) as f:
return U_NEWLINE.sub('\n', f.read())
def write_text(self, text, encoding=None, errors='strict',
linesep=os.linesep, append=False):
r""" Write the given text to this file.
The default behavior is to overwrite any existing file;
to append instead, use the `append=True` keyword argument.
There are two differences between :meth:`write_text` and
:meth:`write_bytes`: newline handling and Unicode handling.
See below.
Parameters:
`text` - str/unicode - The text to be written.
`encoding` - str - The Unicode encoding that will be used.
This is ignored if `text` isn't a Unicode string.
`errors` - str - How to handle Unicode encoding errors.
Default is ``'strict'``. See ``help(unicode.encode)`` for the
options. This is ignored if `text` isn't a Unicode
string.
`linesep` - keyword argument - str/unicode - The sequence of
characters to be used to mark end-of-line. The default is
:data:`os.linesep`. You can also specify ``None`` to
leave all newlines as they are in `text`.
`append` - keyword argument - bool - Specifies what to do if
the file already exists (``True``: append to the end of it;
``False``: overwrite it.) The default is ``False``.
--- Newline handling.
``write_text()`` converts all standard end-of-line sequences
(``'\n'``, ``'\r'``, and ``'\r\n'``) to your platform's default
end-of-line sequence (see :data:`os.linesep`; on Windows, for example,
the end-of-line marker is ``'\r\n'``).
If you don't like your platform's default, you can override it
using the `linesep=` keyword argument. If you specifically want
``write_text()`` to preserve the newlines as-is, use ``linesep=None``.
This applies to Unicode text the same as to 8-bit text, except
there are three additional standard Unicode end-of-line sequences:
``u'\x85'``, ``u'\r\x85'``, and ``u'\u2028'``.
(This is slightly different from when you open a file for
writing with ``fopen(filename, "w")`` in C or ``open(filename, 'w')``
in Python.)
--- Unicode
If `text` isn't Unicode, then apart from newline handling, the
bytes are written verbatim to the file. The `encoding` and
`errors` arguments are not used and must be omitted.
If `text` is Unicode, it is first converted to :func:`bytes` using the
specified `encoding` (or the default encoding if `encoding`
isn't specified). The `errors` argument applies only to this
conversion.
"""
if isinstance(text, text_type):
if linesep is not None:
text = U_NEWLINE.sub(linesep, text)
text = text.encode(encoding or sys.getdefaultencoding(), errors)
else:
assert encoding is None
text = NEWLINE.sub(linesep, text)
self.write_bytes(text, append=append)
def lines(self, encoding=None, errors='strict', retain=True):
r""" Open this file, read all lines, return them in a list.
Optional arguments:
`encoding` - The Unicode encoding (or character set) of
the file. The default is ``None``, meaning the content
of the file is read as 8-bit characters and returned
as a list of (non-Unicode) str objects.
`errors` - How to handle Unicode errors; see help(str.decode)
for the options. Default is ``'strict'``.
`retain` - If ``True``, retain newline characters; but all newline
character combinations (``'\r'``, ``'\n'``, ``'\r\n'``) are
translated to ``'\n'``. If ``False``, newline characters are
stripped off. Default is ``True``.
This uses ``'U'`` mode.
.. seealso:: :meth:`text`
"""
if encoding is None and retain:
with self.open('U') as f:
return f.readlines()
else:
return self.text(encoding, errors).splitlines(retain)
def write_lines(self, lines, encoding=None, errors='strict',
linesep=os.linesep, append=False):
r""" Write the given lines of text to this file.
By default this overwrites any existing file at this path.
This puts a platform-specific newline sequence on every line.
See `linesep` below.
`lines` - A list of strings.
`encoding` - A Unicode encoding to use. This applies only if
`lines` contains any Unicode strings.
`errors` - How to handle errors in Unicode encoding. This
also applies only to Unicode strings.
linesep - The desired line-ending. This line-ending is
applied to every line. If a line already has any
standard line ending (``'\r'``, ``'\n'``, ``'\r\n'``,
``u'\x85'``, ``u'\r\x85'``, ``u'\u2028'``), that will
be stripped off and this will be used instead. The
default is os.linesep, which is platform-dependent
(``'\r\n'`` on Windows, ``'\n'`` on Unix, etc.).
Specify ``None`` to write the lines as-is, like
:meth:`file.writelines`.
Use the keyword argument ``append=True`` to append lines to the
file. The default is to overwrite the file.
.. warning ::
When you use this with Unicode data, if the encoding of the
existing data in the file is different from the encoding
you specify with the `encoding=` parameter, the result is
mixed-encoding data, which can really confuse someone trying
to read the file later.
"""
with self.open('ab' if append else 'wb') as f:
for l in lines:
isUnicode = isinstance(l, text_type)
if linesep is not None:
pattern = U_NL_END if isUnicode else NL_END
l = pattern.sub('', l) + linesep
if isUnicode:
l = l.encode(encoding or sys.getdefaultencoding(), errors)
f.write(l)
def read_md5(self):
""" Calculate the md5 hash for this file.
This reads through the entire file.
.. seealso:: :meth:`read_hash`
"""
return self.read_hash('md5')
def _hash(self, hash_name):
""" Returns a hash object for the file at the current path.
`hash_name` should be a hash algo name (such as ``'md5'`` or ``'sha1'``)
that's available in the :mod:`hashlib` module.
"""
m = hashlib.new(hash_name)
for chunk in self.chunks(8192, mode="rb"):
m.update(chunk)
return m
def read_hash(self, hash_name):
""" Calculate given hash for this file.
List of supported hashes can be obtained from :mod:`hashlib` package.
This reads the entire file.
.. seealso:: :meth:`hashlib.hash.digest`
"""
return self._hash(hash_name).digest()
def read_hexhash(self, hash_name):
""" Calculate given hash for this file, returning hexdigest.
List of supported hashes can be obtained from :mod:`hashlib` package.
This reads the entire file.
.. seealso:: :meth:`hashlib.hash.hexdigest`
"""
return self._hash(hash_name).hexdigest()
# --- Methods for querying the filesystem.
# N.B. On some platforms, the os.path functions may be implemented in C
# (e.g. isdir on Windows, Python 3.2.2), and compiled functions don't get
# bound. Playing it safe and wrapping them all in method calls.
def isabs(self):
""" .. seealso:: :func:`os.path.isabs` """
return self.module.isabs(self)
def exists(self):
""" .. seealso:: :func:`os.path.exists` """
return self.module.exists(self)
def isdir(self):
""" .. seealso:: :func:`os.path.isdir` """
return self.module.isdir(self)
def isfile(self):