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
503 lines (407 loc) · 16.6 KB
/
Copy path_fs.pyx
File metadata and controls
503 lines (407 loc) · 16.6 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
# 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
import six
from pyarrow.compat import frombytes, tobytes
from pyarrow.includes.common cimport *
from pyarrow.includes.libarrow cimport PyDateTime_from_TimePoint
from pyarrow.lib import _detect_compression
from pyarrow.lib cimport *
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, six.string_types):
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 class FileStats:
"""FileSystem entry stats"""
def __init__(self):
raise TypeError("FileStats cannot be instantiated directly, use "
"FileSystem.get_target_stats method instead.")
@staticmethod
cdef FileStats wrap(CFileStats stats):
cdef FileStats self = FileStats.__new__(FileStats)
self.stats = stats
return self
def __repr__(self):
def getvalue(attr):
try:
return getattr(self, attr)
except ValueError:
return ''
attrs = ['type', 'path', 'base_name', 'size', 'extension', 'mtime']
attrs = '\n'.join('{}: {}'.format(a, getvalue(a)) for a in attrs)
return '{}\n{}'.format(object.__repr__(self), attrs)
@property
def type(self):
"""Type of the file
The returned enum variants have the following meanings:
- FileType.NonExistent: 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 FileType(<int8_t> self.stats.type())
@property
def path(self):
"""The full file path in the filesystem."""
return frombytes(self.stats.path())
@property
def base_name(self):
"""The file base name
Component after the last directory separator.
"""
return frombytes(self.stats.base_name())
@property
def size(self):
"""The size in bytes, if available
Only regular files are guaranteed to have a size.
"""
if self.stats.type() != CFileType_File:
return None
return self.stats.size()
@property
def extension(self):
"""The file extension"""
return frombytes(self.stats.extension())
@property
def mtime(self):
"""The time of last modification, if available.
Returns
-------
mtime : datetime.datetime
"""
cdef PyObject *out
check_status(PyDateTime_from_TimePoint(self.stats.mtime(), &out))
return PyObject_to_object(out)
cdef class Selector:
"""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_non_existent : 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.
"""
def __init__(self, base_dir, bint allow_non_existent=False,
bint recursive=False):
self.base_dir = base_dir
self.recursive = recursive
self.allow_non_existent = allow_non_existent
@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_non_existent(self):
return self.selector.allow_non_existent
@allow_non_existent.setter
def allow_non_existent(self, bint allow_non_existent):
self.selector.allow_non_existent = allow_non_existent
@property
def recursive(self):
return self.selector.recursive
@recursive.setter
def recursive(self, bint recursive):
self.selector.recursive = recursive
cdef class FileSystem:
"""Abstract file system API"""
def __init__(self):
raise TypeError("FileSystem is an abstract class, instantiate one of "
"the subclasses instead: LocalFileSystem or "
"SubTreeFileSystem")
cdef init(self, const shared_ptr[CFileSystem]& wrapped):
self.wrapped = wrapped
self.fs = wrapped.get()
def get_target_stats(self, paths_or_selector):
"""Get statistics for the given target.
Any symlink is automatically dereferenced, recursively. A non-existing
or unreachable file returns a FileStats object and has a FileType of
value NonExistent. An exception indicates a truly exceptional condition
(low-level I/O error, etc.).
Parameters
----------
paths_or_selector: Selector or list of path-likes
Either a Selector 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_non_existent`.
Returns
-------
file_stats : list of FileStats
"""
cdef:
vector[CFileStats] stats
vector[c_string] paths
CSelector selector
if isinstance(paths_or_selector, Selector):
with nogil:
selector = (<Selector>paths_or_selector).selector
check_status(self.fs.GetTargetStats(selector, &stats))
elif isinstance(paths_or_selector, (list, tuple)):
paths = [_path_as_bytes(s) for s in paths_or_selector]
with nogil:
check_status(self.fs.GetTargetStats(paths, &stats))
else:
raise TypeError('Must pass either paths or a Selector')
return [FileStats.wrap(stat) for stat in stats]
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 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.
"""
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.
"""
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
-------
stram : NativeFile
"""
cdef:
c_string pathstr = _path_as_bytes(path)
NativeFile stream = NativeFile()
shared_ptr[CRandomAccessFile] in_handle
with nogil:
check_status(self.fs.OpenInputFile(pathstr, &in_handle))
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
----------
source: 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
"""
cdef:
c_string pathstr = _path_as_bytes(path)
NativeFile stream = NativeFile()
shared_ptr[CInputStream] in_handle
with nogil:
check_status(self.fs.OpenInputStream(pathstr, &in_handle))
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):
"""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.
Returns
-------
stream : NativeFile
"""
cdef:
c_string pathstr = _path_as_bytes(path)
NativeFile stream = NativeFile()
shared_ptr[COutputStream] out_handle
with nogil:
check_status(self.fs.OpenOutputStream(pathstr, &out_handle))
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):
"""Open an output stream for appending.
If the target doesn't exist, a new empty file is created.
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.
Returns
-------
stream : NativeFile
"""
cdef:
c_string pathstr = _path_as_bytes(path)
NativeFile stream = NativeFile()
shared_ptr[COutputStream] out_handle
with nogil:
check_status(self.fs.OpenAppendStream(pathstr, &out_handle))
stream.set_output_stream(out_handle)
stream.is_writable = True
return self._wrap_output_stream(
stream, path=path, compression=compression, buffer_size=buffer_size
)
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).
"""
def __init__(self):
cdef shared_ptr[CLocalFileSystem] wrapped
wrapped = make_shared[CLocalFileSystem]()
self.init(<shared_ptr[CFileSystem]> wrapped)
cdef init(self, const shared_ptr[CFileSystem]& wrapped):
FileSystem.init(self, wrapped)
self.localfs = <CLocalFileSystem*> wrapped.get()
cdef class SubTreeFileSystem(FileSystem):
"""Delegates to another implementation after prepending a fixed base path.
This is useful to expose a logical view of a subtree of a filesystem,
for example a directory in a LocalFileSystem.
Note, that this makes no security guarantee. For example, symlinks may
allow to "escape" the subtree and access other parts of the underlying
filesystem.
Parameters
----------
base_path: str
The root of the subtree.
base_fs: FileSystem
FileSystem object the operations delegated to.
"""
def __init__(self, base_path, FileSystem base_fs):
cdef:
c_string pathstr
shared_ptr[CSubTreeFileSystem] wrapped
pathstr = _path_as_bytes(base_path)
wrapped = make_shared[CSubTreeFileSystem](pathstr, base_fs.wrapped)
self.init(<shared_ptr[CFileSystem]> wrapped)
cdef init(self, const shared_ptr[CFileSystem]& wrapped):
FileSystem.init(self, wrapped)
self.subtreefs = <CSubTreeFileSystem*> wrapped.get()