forked from apache/arrow
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy path_fs.pyx
More file actions
1623 lines (1306 loc) · 51.2 KB
/
Copy path_fs.pyx
File metadata and controls
1623 lines (1306 loc) · 51.2 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
# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements. See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership. The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License. You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied. See the License for the
# specific language governing permissions and limitations
# under the License.
# cython: language_level = 3
from cpython.datetime cimport datetime, PyDateTime_DateTime
from pyarrow.includes.common cimport *
from pyarrow.includes.libarrow_python cimport PyDateTime_to_TimePoint
from pyarrow.lib import _detect_compression, frombytes, tobytes
from pyarrow.lib cimport *
from pyarrow.util import _stringify_path
from abc import ABC, abstractmethod
from datetime import datetime, timezone
import os
import pathlib
import sys
cdef _init_ca_paths():
cdef CFileSystemGlobalOptions options
import ssl
paths = ssl.get_default_verify_paths()
if paths.cafile:
options.tls_ca_file_path = os.fsencode(paths.cafile)
if paths.capath:
options.tls_ca_dir_path = os.fsencode(paths.capath)
check_status(CFileSystemsInitialize(options))
if sys.platform == 'linux':
# ARROW-9261: On Linux, we may need to fixup the paths to TLS CA certs
# (especially in manylinux packages) since the values hardcoded at
# compile-time in libcurl may be wrong.
_init_ca_paths()
cdef inline c_string _path_as_bytes(path) except *:
# handle only abstract paths, not bound to any filesystem like pathlib is,
# so we only accept plain strings
if not isinstance(path, (bytes, str)):
raise TypeError('Path must be a string')
# tobytes always uses utf-8, which is more or less ok, at least on Windows
# since the C++ side then decodes from utf-8. On Unix, os.fsencode may be
# better.
return tobytes(path)
cdef object _wrap_file_type(CFileType ty):
return FileType(<int8_t> ty)
cdef CFileType _unwrap_file_type(FileType ty) except *:
if ty == FileType.Unknown:
return CFileType_Unknown
elif ty == FileType.NotFound:
return CFileType_NotFound
elif ty == FileType.File:
return CFileType_File
elif ty == FileType.Directory:
return CFileType_Directory
assert 0
def _file_type_to_string(ty):
# Python 3.11 changed str(IntEnum) to return the string representation
# of the integer value: https://github.com/python/cpython/issues/94763
return f"{ty.__class__.__name__}.{ty._name_}"
cdef class FileInfo(_Weakrefable):
"""
FileSystem entry info.
Parameters
----------
path : str
The full path to the filesystem entry.
type : FileType
The type of the filesystem entry.
mtime : datetime or float, default None
If given, the modification time of the filesystem entry.
If a float is given, it is the number of seconds since the
Unix epoch.
mtime_ns : int, default None
If given, the modification time of the filesystem entry,
in nanoseconds since the Unix epoch.
`mtime` and `mtime_ns` are mutually exclusive.
size : int, default None
If given, the filesystem entry size in bytes. This should only
be given if `type` is `FileType.File`.
Examples
--------
Generate a file:
>>> from pyarrow import fs
>>> local = fs.LocalFileSystem()
>>> path_fs = local_path + '/pyarrow-fs-example.dat'
>>> with local.open_output_stream(path_fs) as stream:
... stream.write(b'data')
4
Get FileInfo object using ``get_file_info()``:
>>> file_info = local.get_file_info(path_fs)
>>> file_info
<FileInfo for '.../pyarrow-fs-example.dat': type=FileType.File, size=4>
Inspect FileInfo attributes:
>>> file_info.type
<FileType.File: 2>
>>> file_info.is_file
True
>>> file_info.path
'/.../pyarrow-fs-example.dat'
>>> file_info.base_name
'pyarrow-fs-example.dat'
>>> file_info.size
4
>>> file_info.extension
'dat'
>>> file_info.mtime # doctest: +SKIP
datetime.datetime(2022, 6, 29, 7, 56, 10, 873922, tzinfo=datetime.timezone.utc)
>>> file_info.mtime_ns # doctest: +SKIP
1656489370873922073
"""
def __init__(self, path, FileType type=FileType.Unknown, *,
mtime=None, mtime_ns=None, size=None):
self.info.set_path(tobytes(path))
self.info.set_type(_unwrap_file_type(type))
if mtime is not None:
if mtime_ns is not None:
raise TypeError("Only one of mtime and mtime_ns "
"can be given")
if isinstance(mtime, datetime):
self.info.set_mtime(PyDateTime_to_TimePoint(
<PyDateTime_DateTime*> mtime))
else:
self.info.set_mtime(TimePoint_from_s(mtime))
elif mtime_ns is not None:
self.info.set_mtime(TimePoint_from_ns(mtime_ns))
if size is not None:
self.info.set_size(size)
@staticmethod
cdef wrap(CFileInfo info):
cdef FileInfo self = FileInfo.__new__(FileInfo)
self.info = move(info)
return self
cdef inline CFileInfo unwrap(self) nogil:
return self.info
@staticmethod
cdef CFileInfo unwrap_safe(obj):
if not isinstance(obj, FileInfo):
raise TypeError("Expected FileInfo instance, got {0}"
.format(type(obj)))
return (<FileInfo> obj).unwrap()
def __repr__(self):
def getvalue(attr):
try:
return getattr(self, attr)
except ValueError:
return ''
s = (f'<FileInfo for {self.path!r}: '
f'type={_file_type_to_string(self.type)}')
if self.is_file:
s += f', size={self.size}'
s += '>'
return s
@property
def type(self):
"""
Type of the file.
The returned enum values can be the following:
- FileType.NotFound: target does not exist
- FileType.Unknown: target exists but its type is unknown (could be a
special file such as a Unix socket or character device, or
Windows NUL / CON / ...)
- FileType.File: target is a regular file
- FileType.Directory: target is a regular directory
Returns
-------
type : FileType
"""
return _wrap_file_type(self.info.type())
@property
def is_file(self):
"""
"""
return self.type == FileType.File
@property
def path(self):
"""
The full file path in the filesystem.
Examples
--------
>>> file_info = local.get_file_info(path)
>>> file_info.path
'/.../pyarrow-fs-example.dat'
"""
return frombytes(self.info.path())
@property
def base_name(self):
"""
The file base name.
Component after the last directory separator.
Examples
--------
>>> file_info = local.get_file_info(path)
>>> file_info.base_name
'pyarrow-fs-example.dat'
"""
return frombytes(self.info.base_name())
@property
def size(self):
"""
The size in bytes, if available.
Only regular files are guaranteed to have a size.
Returns
-------
size : int or None
"""
cdef int64_t size
size = self.info.size()
return (size if size != -1 else None)
@property
def extension(self):
"""
The file extension.
Examples
--------
>>> file_info = local.get_file_info(path)
>>> file_info.extension
'dat'
"""
return frombytes(self.info.extension())
@property
def mtime(self):
"""
The time of last modification, if available.
Returns
-------
mtime : datetime.datetime or None
Examples
--------
>>> file_info = local.get_file_info(path)
>>> file_info.mtime # doctest: +SKIP
datetime.datetime(2022, 6, 29, 7, 56, 10, 873922, tzinfo=datetime.timezone.utc)
"""
cdef int64_t nanoseconds
nanoseconds = TimePoint_to_ns(self.info.mtime())
return (datetime.fromtimestamp(nanoseconds / 1.0e9, timezone.utc)
if nanoseconds != -1 else None)
@property
def mtime_ns(self):
"""
The time of last modification, if available, expressed in nanoseconds
since the Unix epoch.
Returns
-------
mtime_ns : int or None
Examples
--------
>>> file_info = local.get_file_info(path)
>>> file_info.mtime_ns # doctest: +SKIP
1656489370873922073
"""
cdef int64_t nanoseconds
nanoseconds = TimePoint_to_ns(self.info.mtime())
return (nanoseconds if nanoseconds != -1 else None)
cdef class FileSelector(_Weakrefable):
"""
File and directory selector.
It contains a set of options that describes how to search for files and
directories.
Parameters
----------
base_dir : str
The directory in which to select files. Relative paths also work, use
'.' for the current directory and '..' for the parent.
allow_not_found : bool, default False
The behavior if `base_dir` doesn't exist in the filesystem.
If false, an error is returned.
If true, an empty selection is returned.
recursive : bool, default False
Whether to recurse into subdirectories.
Examples
--------
List the contents of a directory and subdirectories:
>>> selector_1 = fs.FileSelector(local_path, recursive=True)
>>> local.get_file_info(selector_1) # doctest: +SKIP
[<FileInfo for 'tmp/alphabet/example.dat': type=FileType.File, size=4>,
<FileInfo for 'tmp/alphabet/subdir': type=FileType.Directory>,
<FileInfo for 'tmp/alphabet/subdir/example_copy.dat': type=FileType.File, size=4>]
List only the contents of the base directory:
>>> selector_2 = fs.FileSelector(local_path)
>>> local.get_file_info(selector_2) # doctest: +SKIP
[<FileInfo for 'tmp/alphabet/example.dat': type=FileType.File, size=4>,
<FileInfo for 'tmp/alphabet/subdir': type=FileType.Directory>]
Return empty selection if the directory doesn't exist:
>>> selector_not_found = fs.FileSelector(local_path + '/missing',
... recursive=True,
... allow_not_found=True)
>>> local.get_file_info(selector_not_found)
[]
"""
def __init__(self, base_dir, bint allow_not_found=False,
bint recursive=False):
self.base_dir = base_dir
self.recursive = recursive
self.allow_not_found = allow_not_found
@staticmethod
cdef FileSelector wrap(CFileSelector wrapped):
cdef FileSelector self = FileSelector.__new__(FileSelector)
self.selector = move(wrapped)
return self
cdef inline CFileSelector unwrap(self) nogil:
return self.selector
@property
def base_dir(self):
return frombytes(self.selector.base_dir)
@base_dir.setter
def base_dir(self, base_dir):
self.selector.base_dir = _path_as_bytes(base_dir)
@property
def allow_not_found(self):
return self.selector.allow_not_found
@allow_not_found.setter
def allow_not_found(self, bint allow_not_found):
self.selector.allow_not_found = allow_not_found
@property
def recursive(self):
return self.selector.recursive
@recursive.setter
def recursive(self, bint recursive):
self.selector.recursive = recursive
def __repr__(self):
return ("<FileSelector base_dir={0.base_dir!r} "
"recursive={0.recursive}>".format(self))
cdef class FileSystem(_Weakrefable):
"""
Abstract file system API.
"""
def __init__(self):
raise TypeError("FileSystem is an abstract class, instantiate one of "
"the subclasses instead: LocalFileSystem or "
"SubTreeFileSystem")
@staticmethod
def from_uri(uri):
"""
Create a new FileSystem from URI or Path.
Recognized URI schemes are "file", "mock", "s3fs", "gs", "gcs", "hdfs" and "viewfs".
In addition, the argument can be a pathlib.Path object, or a string
describing an absolute local path.
Parameters
----------
uri : string
URI-based path, for example: file:///some/local/path.
Returns
-------
tuple of (FileSystem, str path)
With (filesystem, path) tuple where path is the abstract path
inside the FileSystem instance.
Examples
--------
Create a new FileSystem subclass from a URI:
>>> uri = 'file:///{}/pyarrow-fs-example.dat'.format(local_path)
>>> local_new, path_new = fs.FileSystem.from_uri(uri)
>>> local_new
<pyarrow._fs.LocalFileSystem object at ...
>>> path_new
'/.../pyarrow-fs-example.dat'
Or from a s3 bucket:
>>> fs.FileSystem.from_uri("s3://usgs-landsat/collection02/")
(<pyarrow._s3fs.S3FileSystem object at ...>, 'usgs-landsat/collection02')
"""
cdef:
c_string c_path
c_string c_uri
CResult[shared_ptr[CFileSystem]] result
if isinstance(uri, pathlib.Path):
# Make absolute
uri = uri.resolve().absolute()
c_uri = tobytes(_stringify_path(uri))
with nogil:
result = CFileSystemFromUriOrPath(c_uri, &c_path)
return FileSystem.wrap(GetResultValue(result)), frombytes(c_path)
cdef init(self, const shared_ptr[CFileSystem]& wrapped):
self.wrapped = wrapped
self.fs = wrapped.get()
@staticmethod
cdef wrap(const shared_ptr[CFileSystem]& sp):
cdef FileSystem self
typ = frombytes(sp.get().type_name())
if typ == 'local':
self = LocalFileSystem.__new__(LocalFileSystem)
elif typ == 'mock':
self = _MockFileSystem.__new__(_MockFileSystem)
elif typ == 'subtree':
self = SubTreeFileSystem.__new__(SubTreeFileSystem)
elif typ == 's3':
from pyarrow._s3fs import S3FileSystem
self = S3FileSystem.__new__(S3FileSystem)
elif typ == 'gcs':
from pyarrow._gcsfs import GcsFileSystem
self = GcsFileSystem.__new__(GcsFileSystem)
elif typ == 'hdfs':
from pyarrow._hdfs import HadoopFileSystem
self = HadoopFileSystem.__new__(HadoopFileSystem)
elif typ.startswith('py::'):
self = PyFileSystem.__new__(PyFileSystem)
else:
raise TypeError('Cannot wrap FileSystem pointer')
self.init(sp)
return self
cdef inline shared_ptr[CFileSystem] unwrap(self) nogil:
return self.wrapped
def equals(self, FileSystem other):
return self.fs.Equals(other.unwrap())
def __eq__(self, other):
try:
return self.equals(other)
except TypeError:
return NotImplemented
@property
def type_name(self):
"""
The filesystem's type name.
"""
return frombytes(self.fs.type_name())
def get_file_info(self, paths_or_selector):
"""
Get info for the given files.
Any symlink is automatically dereferenced, recursively. A non-existing
or unreachable file returns a FileStat object and has a FileType of
value NotFound. An exception indicates a truly exceptional condition
(low-level I/O error, etc.).
Parameters
----------
paths_or_selector : FileSelector, path-like or list of path-likes
Either a selector object, a path-like object or a list of
path-like objects. The selector's base directory will not be
part of the results, even if it exists. If it doesn't exist,
use `allow_not_found`.
Returns
-------
FileInfo or list of FileInfo
Single FileInfo object is returned for a single path, otherwise
a list of FileInfo objects is returned.
Examples
--------
>>> local
<pyarrow._fs.LocalFileSystem object at ...>
>>> local.get_file_info("/{}/pyarrow-fs-example.dat".format(local_path))
<FileInfo for '/.../pyarrow-fs-example.dat': type=FileType.File, size=4>
"""
cdef:
CFileInfo info
c_string path
vector[CFileInfo] infos
vector[c_string] paths
CFileSelector selector
if isinstance(paths_or_selector, FileSelector):
with nogil:
selector = (<FileSelector>paths_or_selector).selector
infos = GetResultValue(self.fs.GetFileInfo(selector))
elif isinstance(paths_or_selector, (list, tuple)):
paths = [_path_as_bytes(s) for s in paths_or_selector]
with nogil:
infos = GetResultValue(self.fs.GetFileInfo(paths))
elif isinstance(paths_or_selector, (bytes, str)):
path =_path_as_bytes(paths_or_selector)
with nogil:
info = GetResultValue(self.fs.GetFileInfo(path))
return FileInfo.wrap(info)
else:
raise TypeError('Must pass either path(s) or a FileSelector')
return [FileInfo.wrap(info) for info in infos]
def create_dir(self, path, *, bint recursive=True):
"""
Create a directory and subdirectories.
This function succeeds if the directory already exists.
Parameters
----------
path : str
The path of the new directory.
recursive : bool, default True
Create nested directories as well.
"""
cdef c_string directory = _path_as_bytes(path)
with nogil:
check_status(self.fs.CreateDir(directory, recursive=recursive))
def delete_dir(self, path):
"""
Delete a directory and its contents, recursively.
Parameters
----------
path : str
The path of the directory to be deleted.
"""
cdef c_string directory = _path_as_bytes(path)
with nogil:
check_status(self.fs.DeleteDir(directory))
def delete_dir_contents(self, path, *,
bint accept_root_dir=False,
bint missing_dir_ok=False):
"""
Delete a directory's contents, recursively.
Like delete_dir, but doesn't delete the directory itself.
Parameters
----------
path : str
The path of the directory to be deleted.
accept_root_dir : boolean, default False
Allow deleting the root directory's contents
(if path is empty or "/")
missing_dir_ok : boolean, default False
If False then an error is raised if path does
not exist
"""
cdef c_string directory = _path_as_bytes(path)
if accept_root_dir and directory.strip(b"/") == b"":
with nogil:
check_status(self.fs.DeleteRootDirContents())
else:
with nogil:
check_status(self.fs.DeleteDirContents(directory,
missing_dir_ok))
def move(self, src, dest):
"""
Move / rename a file or directory.
If the destination exists:
- if it is a non-empty directory, an error is returned
- otherwise, if it has the same type as the source, it is replaced
- otherwise, behavior is unspecified (implementation-dependent).
Parameters
----------
src : str
The path of the file or the directory to be moved.
dest : str
The destination path where the file or directory is moved to.
Examples
--------
Create a new folder with a file:
>>> local.create_dir('/tmp/other_dir')
>>> local.copy_file(path,'/tmp/move_example.dat')
Move the file:
>>> local.move('/tmp/move_example.dat',
... '/tmp/other_dir/move_example_2.dat')
Inspect the file info:
>>> local.get_file_info('/tmp/other_dir/move_example_2.dat')
<FileInfo for '/tmp/other_dir/move_example_2.dat': type=FileType.File, size=4>
>>> local.get_file_info('/tmp/move_example.dat')
<FileInfo for '/tmp/move_example.dat': type=FileType.NotFound>
Delete the folder:
>>> local.delete_dir('/tmp/other_dir')
"""
cdef:
c_string source = _path_as_bytes(src)
c_string destination = _path_as_bytes(dest)
with nogil:
check_status(self.fs.Move(source, destination))
def copy_file(self, src, dest):
"""
Copy a file.
If the destination exists and is a directory, an error is returned.
Otherwise, it is replaced.
Parameters
----------
src : str
The path of the file to be copied from.
dest : str
The destination path where the file is copied to.
Examples
--------
>>> local.copy_file(path,
... local_path + '/pyarrow-fs-example_copy.dat')
Inspect the file info:
>>> local.get_file_info(local_path + '/pyarrow-fs-example_copy.dat')
<FileInfo for '/.../pyarrow-fs-example_copy.dat': type=FileType.File, size=4>
>>> local.get_file_info(path)
<FileInfo for '/.../pyarrow-fs-example.dat': type=FileType.File, size=4>
"""
cdef:
c_string source = _path_as_bytes(src)
c_string destination = _path_as_bytes(dest)
with nogil:
check_status(self.fs.CopyFile(source, destination))
def delete_file(self, path):
"""
Delete a file.
Parameters
----------
path : str
The path of the file to be deleted.
"""
cdef c_string file = _path_as_bytes(path)
with nogil:
check_status(self.fs.DeleteFile(file))
def _wrap_input_stream(self, stream, path, compression, buffer_size):
if buffer_size is not None and buffer_size != 0:
stream = BufferedInputStream(stream, buffer_size)
if compression == 'detect':
compression = _detect_compression(path)
if compression is not None:
stream = CompressedInputStream(stream, compression)
return stream
def _wrap_output_stream(self, stream, path, compression, buffer_size):
if buffer_size is not None and buffer_size != 0:
stream = BufferedOutputStream(stream, buffer_size)
if compression == 'detect':
compression = _detect_compression(path)
if compression is not None:
stream = CompressedOutputStream(stream, compression)
return stream
def open_input_file(self, path):
"""
Open an input file for random access reading.
Parameters
----------
path : str
The source to open for reading.
Returns
-------
stream : NativeFile
Examples
--------
Print the data from the file with `open_input_file()`:
>>> with local.open_input_file(path) as f:
... print(f.readall())
b'data'
"""
cdef:
c_string pathstr = _path_as_bytes(path)
NativeFile stream = NativeFile()
shared_ptr[CRandomAccessFile] in_handle
with nogil:
in_handle = GetResultValue(self.fs.OpenInputFile(pathstr))
stream.set_random_access_file(in_handle)
stream.is_readable = True
return stream
def open_input_stream(self, path, compression='detect', buffer_size=None):
"""
Open an input stream for sequential reading.
Parameters
----------
path : str
The source to open for reading.
compression : str optional, default 'detect'
The compression algorithm to use for on-the-fly decompression.
If "detect" and source is a file path, then compression will be
chosen based on the file extension.
If None, no compression will be applied. Otherwise, a well-known
algorithm name must be supplied (e.g. "gzip").
buffer_size : int optional, default None
If None or 0, no buffering will happen. Otherwise the size of the
temporary read buffer.
Returns
-------
stream : NativeFile
Examples
--------
Print the data from the file with `open_input_stream()`:
>>> with local.open_input_stream(path) as f:
... print(f.readall())
b'data'
"""
cdef:
c_string pathstr = _path_as_bytes(path)
NativeFile stream = NativeFile()
shared_ptr[CInputStream] in_handle
with nogil:
in_handle = GetResultValue(self.fs.OpenInputStream(pathstr))
stream.set_input_stream(in_handle)
stream.is_readable = True
return self._wrap_input_stream(
stream, path=path, compression=compression, buffer_size=buffer_size
)
def open_output_stream(self, path, compression='detect',
buffer_size=None, metadata=None):
"""
Open an output stream for sequential writing.
If the target already exists, existing data is truncated.
Parameters
----------
path : str
The source to open for writing.
compression : str optional, default 'detect'
The compression algorithm to use for on-the-fly compression.
If "detect" and source is a file path, then compression will be
chosen based on the file extension.
If None, no compression will be applied. Otherwise, a well-known
algorithm name must be supplied (e.g. "gzip").
buffer_size : int optional, default None
If None or 0, no buffering will happen. Otherwise the size of the
temporary write buffer.
metadata : dict optional, default None
If not None, a mapping of string keys to string values.
Some filesystems support storing metadata along the file
(such as "Content-Type").
Unsupported metadata keys will be ignored.
Returns
-------
stream : NativeFile
Examples
--------
>>> local = fs.LocalFileSystem()
>>> with local.open_output_stream(path) as stream:
... stream.write(b'data')
4
"""
cdef:
c_string pathstr = _path_as_bytes(path)
NativeFile stream = NativeFile()
shared_ptr[COutputStream] out_handle
shared_ptr[const CKeyValueMetadata] c_metadata
if metadata is not None:
c_metadata = pyarrow_unwrap_metadata(KeyValueMetadata(metadata))
with nogil:
out_handle = GetResultValue(
self.fs.OpenOutputStream(pathstr, c_metadata))
stream.set_output_stream(out_handle)
stream.is_writable = True
return self._wrap_output_stream(
stream, path=path, compression=compression, buffer_size=buffer_size
)
def open_append_stream(self, path, compression='detect',
buffer_size=None, metadata=None):
"""
Open an output stream for appending.
If the target doesn't exist, a new empty file is created.
.. note::
Some filesystem implementations do not support efficient
appending to an existing file, in which case this method will
raise NotImplementedError.
Consider writing to multiple files (using e.g. the dataset layer)
instead.
Parameters
----------
path : str
The source to open for writing.
compression : str optional, default 'detect'
The compression algorithm to use for on-the-fly compression.
If "detect" and source is a file path, then compression will be
chosen based on the file extension.
If None, no compression will be applied. Otherwise, a well-known
algorithm name must be supplied (e.g. "gzip").
buffer_size : int optional, default None
If None or 0, no buffering will happen. Otherwise the size of the
temporary write buffer.
metadata : dict optional, default None
If not None, a mapping of string keys to string values.
Some filesystems support storing metadata along the file
(such as "Content-Type").
Unsupported metadata keys will be ignored.
Returns
-------
stream : NativeFile
Examples
--------
Append new data to a FileSystem subclass with nonempty file:
>>> with local.open_append_stream(path) as f:
... f.write(b'+newly added')
12
Print out the content fo the file:
>>> with local.open_input_file(path) as f:
... print(f.readall())
b'data+newly added'
"""
cdef:
c_string pathstr = _path_as_bytes(path)
NativeFile stream = NativeFile()
shared_ptr[COutputStream] out_handle
shared_ptr[const CKeyValueMetadata] c_metadata
if metadata is not None:
c_metadata = pyarrow_unwrap_metadata(KeyValueMetadata(metadata))
with nogil:
out_handle = GetResultValue(
self.fs.OpenAppendStream(pathstr, c_metadata))
stream.set_output_stream(out_handle)
stream.is_writable = True
return self._wrap_output_stream(
stream, path=path, compression=compression, buffer_size=buffer_size
)
def normalize_path(self, path):
"""
Normalize filesystem path.
Parameters
----------
path : str
The path to normalize
Returns
-------
normalized_path : str
The normalized path
"""
cdef:
c_string c_path = _path_as_bytes(path)
c_string c_path_normalized
c_path_normalized = GetResultValue(self.fs.NormalizePath(c_path))
return frombytes(c_path_normalized)
cdef class LocalFileSystem(FileSystem):
"""
A FileSystem implementation accessing files on the local machine.
Details such as symlinks are abstracted away (symlinks are always followed,
except when deleting an entry).
Parameters
----------
use_mmap : bool, default False
Whether open_input_stream and open_input_file should return
a mmap'ed file or a regular file.
Examples
--------
Create a FileSystem object with LocalFileSystem constructor:
>>> from pyarrow import fs
>>> local = fs.LocalFileSystem()
>>> local
<pyarrow._fs.LocalFileSystem object at ...>
and write data on to the file:
>>> with local.open_output_stream('/tmp/local_fs.dat') as stream:
... stream.write(b'data')
4
>>> with local.open_input_stream('/tmp/local_fs.dat') as stream:
... print(stream.readall())
b'data'