Repository navigation
Expand file tree
/
Copy pathhelpers.py
More file actions
712 lines (577 loc) · 21.9 KB
/
Copy pathhelpers.py
File metadata and controls
712 lines (577 loc) · 21.9 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
# -*- coding: utf-8 -*-
# MinIO Python Library for Amazon S3 Compatible Cloud Storage, (C)
# 2015, 2016, 2017 MinIO, Inc.
#
# Licensed 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.
"""Helper functions."""
from __future__ import absolute_import, division, unicode_literals
import base64
import errno
import hashlib
import math
import os
import re
import urllib.parse
from queue import Queue
from threading import BoundedSemaphore, Thread
from .sse import Sse, SseCustomerKey
from .time import to_iso8601utc
# Constants
MAX_MULTIPART_COUNT = 10000 # 10000 parts
MAX_MULTIPART_OBJECT_SIZE = 5 * 1024 * 1024 * 1024 * 1024 # 5TiB
MAX_PART_SIZE = 5 * 1024 * 1024 * 1024 # 5GiB
MIN_PART_SIZE = 5 * 1024 * 1024 # 5MiB
_VALID_BUCKETNAME_REGEX = re.compile(
'^[A-Za-z0-9][A-Za-z0-9\\.\\-\\_\\:]{1,61}[A-Za-z0-9]$')
_VALID_BUCKETNAME_STRICT_REGEX = re.compile(
'^[a-z0-9][a-z0-9\\.\\-]{1,61}[a-z0-9]$')
_VALID_IP_ADDRESS = re.compile(
r'^(\d+\.){3}\d+$')
_ALLOWED_HOSTNAME_REGEX = re.compile(
'^((?!-)(?!_)[A-Z_\\d-]{1,63}(?<!-)(?<!_)\\.)*((?!_)(?!-)' +
'[A-Z_\\d-]{1,63}(?<!-)(?<!_))$',
re.IGNORECASE)
_EXTRACT_REGION_REGEX = re.compile('s3[.-]?(.+?).amazonaws.com')
def quote(resource, safe='/', encoding=None, errors=None):
"""
Wrapper to urllib.parse.quote() replacing back to '~' for older python
versions.
"""
return urllib.parse.quote(
resource,
safe=safe,
encoding=encoding,
errors=errors,
).replace("%7E", "~")
def queryencode(query, safe='', encoding=None, errors=None):
"""Encode query parameter value."""
return quote(query, safe, encoding, errors)
def headers_to_strings(headers, titled_key=False):
"""Convert HTTP headers to multi-line string."""
def _get_key(key):
return key.title() if titled_key else key
def _get_value(value):
return re.sub(
r"Credential=([^/]+)",
"Credential=*REDACTED*",
re.sub(
r"Signature=([0-9a-f]+)",
"Signature=*REDACTED*",
value if isinstance(value, str) else str(value),
),
) if titled_key else value
return "\n".join(
[
f"{_get_key(key)}: {_get_value(value)}"
for key, value in headers.items()
]
)
def _validate_sizes(object_size, part_size):
"""Validate object and part size."""
if part_size > 0:
if part_size < MIN_PART_SIZE:
raise ValueError(
f"part size {part_size} is not supported; minimum allowed 5MiB",
)
if part_size > MAX_PART_SIZE:
raise ValueError(
f"part size {part_size} is not supported; minimum allowed 5GiB",
)
if object_size >= 0:
if object_size > MAX_MULTIPART_OBJECT_SIZE:
raise ValueError(
f"object size {object_size} is not supported; "
f"maximum allowed 5TiB"
)
elif part_size <= 0:
raise ValueError(
"valid part size must be provided when object size is unknown",
)
def _get_part_info(object_size, part_size):
"""Compute part information for object and part size."""
_validate_sizes(object_size, part_size)
if object_size < 0:
return part_size, -1
if part_size > 0:
part_size = min(part_size, object_size)
return part_size, math.ceil(object_size / part_size) if part_size else 1
part_size = math.ceil(
math.ceil(object_size / MAX_MULTIPART_COUNT) / MIN_PART_SIZE,
) * MIN_PART_SIZE
return part_size, math.ceil(object_size / part_size) if part_size else 1
def get_part_info(object_size, part_size):
"""Compute part information for object and part size."""
part_size, part_count = _get_part_info(object_size, part_size)
if part_count > MAX_MULTIPART_COUNT:
raise ValueError(
f"object size {object_size} and part size {part_size} "
f"make more than {MAX_MULTIPART_COUNT} parts for upload"
)
return part_size, part_count
def read_part_data(stream, size, part_data=b'', progress=None):
"""Read part data of given size from stream."""
size -= len(part_data)
while size:
data = stream.read(size)
if not data:
break # EOF reached
if not isinstance(data, bytes):
raise ValueError("read() must return 'bytes' object")
part_data += data
size -= len(data)
if progress:
progress.update(len(data))
return part_data
def makedirs(path):
"""Wrapper of os.makedirs() ignores errno.EEXIST."""
try:
if path:
os.makedirs(path)
except OSError as exc: # Python >2.5
if exc.errno != errno.EEXIST:
raise
if not os.path.isdir(path):
raise ValueError(f"path {path} is not a directory") from exc
def check_bucket_name(bucket_name, strict=False):
"""Check whether bucket name is valid optional with strict check or not."""
# Verify bucket name is not empty
bucket_name = str(bucket_name).strip()
if not bucket_name:
raise ValueError('Bucket name cannot be empty.')
# Verify bucket name length.
if len(bucket_name) < 3:
raise ValueError('Bucket name cannot be less than'
' 3 characters.')
if len(bucket_name) > 63:
raise ValueError('Bucket name cannot be greater than'
' 63 characters.')
match = _VALID_IP_ADDRESS.match(bucket_name)
if match:
raise ValueError('Bucket name cannot be an ip address')
unallowed_successive_chars = ['..', '.-', '-.']
if any(x in bucket_name for x in unallowed_successive_chars):
raise ValueError('Bucket name contains invalid '
'successive chars '
+ str(unallowed_successive_chars) + '.')
if strict:
match = _VALID_BUCKETNAME_STRICT_REGEX.match(bucket_name)
if (not match) or match.end() != len(bucket_name):
raise ValueError('Bucket name contains invalid '
'characters (strictly enforced).')
match = _VALID_BUCKETNAME_REGEX.match(bucket_name)
if (not match) or match.end() != len(bucket_name):
raise ValueError(
f"Bucket name does not follow S3 standards. Bucket: {bucket_name}",
)
def check_non_empty_string(string):
"""Check whether given string is not empty."""
try:
if not string.strip():
raise ValueError()
except AttributeError as exc:
raise TypeError() from exc
def is_valid_policy_type(policy):
"""
Validate if policy is type str
:param policy: S3 style Bucket policy.
:return: True if policy parameter is of a valid type, 'string'.
Raise :exc:`TypeError` otherwise.
"""
if not isinstance(policy, (str, bytes)):
raise TypeError("policy must be str or bytes type")
check_non_empty_string(policy)
return True
def check_ssec(sse):
"""Check sse is SseCustomerKey type or not."""
if sse and not isinstance(sse, SseCustomerKey):
raise ValueError("SseCustomerKey type is required")
def check_sse(sse):
"""Check sse is Sse type or not."""
if sse and not isinstance(sse, Sse):
raise ValueError("Sse type is required")
def md5sum_hash(data):
"""Compute MD5 of data and return hash as Base64 encoded value."""
if data is None:
return None
hasher = hashlib.md5()
hasher.update(data.encode() if isinstance(data, str) else data)
md5sum = base64.b64encode(hasher.digest())
return md5sum.decode() if isinstance(md5sum, bytes) else md5sum
def sha256_hash(data):
"""Compute SHA-256 of data and return hash as hex encoded value."""
data = data or b""
hasher = hashlib.sha256()
hasher.update(data.encode() if isinstance(data, str) else data)
sha256sum = hasher.hexdigest()
return sha256sum.decode() if isinstance(sha256sum, bytes) else sha256sum
def url_replace(
url, scheme=None, netloc=None, path=None, query=None, fragment=None
):
"""Return new URL with replaced properties in given URL."""
return urllib.parse.SplitResult(
scheme if scheme is not None else url.scheme,
netloc if netloc is not None else url.netloc,
path if path is not None else url.path,
query if query is not None else url.query,
fragment if fragment is not None else url.fragment,
)
def _metadata_to_headers(metadata):
"""Convert user metadata to headers."""
def normalize_key(key):
if not key.lower().startswith("x-amz-meta-"):
key = "X-Amz-Meta-" + key
return key
def to_string(value):
value = str(value)
try:
value.encode("us-ascii")
except UnicodeEncodeErro
10BC8
r as exc:
raise ValueError(
f"unsupported metadata value {value}; "
f"only US-ASCII encoded characters are supported"
) from exc
return value
def normalize_value(values):
if not isinstance(values, (list, tuple)):
values = [values]
return [to_string(value) for value in values]
return {
normalize_key(key): normalize_value(value)
for key, value in (metadata or {}).items()
}
def normalize_headers(headers):
"""Normalize headers by prefixing 'X-Amz-Meta-' for user metadata."""
headers = {str(key): value for key, value in (headers or {}).items()}
def guess_user_metadata(key):
key = key.lower()
return not (
key.startswith("x-amz-") or
key in [
"cache-control",
"content-encoding",
"content-type",
"content-disposition",
"content-language",
]
)
user_metadata = {
key: value for key, value in headers.items()
if guess_user_metadata(key)
}
# Remove guessed user metadata.
_ = [headers.pop(key) for key in user_metadata]
headers.update(_metadata_to_headers(user_metadata))
return headers
def genheaders(headers, sse, tags, retention, legal_hold):
"""Generate headers for given parameters."""
headers = normalize_headers(headers)
headers.update(sse.headers() if sse else {})
tagging = "&".join(
[
queryencode(key) + "=" + queryencode(value)
for key, value in (tags or {}).items()
],
)
if tagging:
headers["x-amz-tagging"] = tagging
if retention and retention.mode:
headers["x-amz-object-lock-mode"] = retention.mode
headers["x-amz-object-lock-retain-until-date"] = (
to_iso8601utc(retention.retain_until_date)
)
if legal_hold:
headers["x-amz-object-lock-legal-hold"] = "ON"
return headers
def _extract_region(host):
"""Extract region from Amazon S3 host."""
tokens = host.split(".")
token = tokens[1]
# If token is "dualstack", then region might be in next token.
if token == "dualstack":
token = tokens[2]
# If token is equal to "amazonaws", region is not passed in the host.
if token == "amazonaws":
return None
# Return token as region.
return token
class BaseURL:
"""Base URL of S3 endpoint."""
def __init__(self, endpoint, region):
url = urllib.parse.urlsplit(endpoint)
host = url.hostname
if url.scheme.lower() not in ["http", "https"]:
raise ValueError("scheme in endpoint must be http or https")
url = url_replace(url, scheme=url.scheme.lower())
if url.path and url.path != "/":
raise ValueError("path in endpoint is not allowed")
url = url_replace(url, path="")
if url.query:
raise ValueError("query in endpoint is not allowed")
if url.fragment:
raise ValueError("fragment in endpoint is not allowed")
try:
url.port
except ValueError as exc:
raise ValueError("invalid port") from exc
if url.username:
raise ValueError("username in endpoint is not allowed")
if url.password:
raise ValueError("password in endpoint is not allowed")
if (
(url.scheme == "http" and url.port == 80) or
(url.scheme == "https" and url.port == 443)
):
url = url_replace(url, netloc=host)
self._accelerate_host_flag = host.startswith("s3-accelerate.")
self._is_aws_host = (
(
host.startswith("s3.") or self._accelerate_host_flag
) and
(
host.endswith(".amazonaws.com") or
host.endswith(".amazonaws.com.cn")
)
)
self._virtual_style_flag = (
self._is_aws_host or host.endswith("aliyuncs.com")
)
region_in_host = None
if self._is_aws_host:
is_aws_china_host = host.endswith(".cn")
url = url_replace(
url,
netloc=(
"amazonaws.com.cn"
if is_aws_china_host else "amazonaws.com"
),
)
region_in_host = _extract_region(host)
if is_aws_china_host and not region_in_host and not region:
raise ValueError(
f"region missing in Amazon S3 China endpoint {endpoint}",
)
self._dualstack_host_flag = ".dualstack." in host
else:
self._accelerate_host_flag = False
self._url = url
self._region = region or region_in_host
@property
def region(self):
"""Get region."""
return self._region
@property
def is_https(self):
"""Check if scheme is HTTPS."""
return self._url.scheme == "https"
@property
def host(self):
"""Get hostname."""
return self._url.netloc
@property
def is_aws_host(self):
"""Check if URL points to AWS host."""
return self._is_aws_host
@property
def accelerate_host_flag(self):
"""Check if URL points to AWS accelerate host."""
return self._accelerate_host_flag
@accelerate_host_flag.setter
def accelerate_host_flag(self, flag):
"""Check if URL points to AWS accelerate host."""
if self._is_aws_host:
self._accelerate_host_flag = flag
@property
def dualstack_host_flag(self):
"""Check if URL points to AWS dualstack host."""
return self._dualstack_host_flag
@dualstack_host_flag.setter
def dualstack_host_flag(self, flag):
"""Check to use virtual style or not."""
if self._is_aws_host:
self._dualstack_host_flag = flag
@property
def virtual_style_flag(self):
"""Check to use virtual style or not."""
return self._virtual_style_flag
@virtual_style_flag.setter
def virtual_style_flag(self, flag):
"""Check to use virtual style or not."""
self._virtual_style_flag = flag
def build(
self, method, region,
bucket_name=None, object_name=None, query_params=None,
):
"""Build URL for given information."""
if not bucket_name and object_name:
raise ValueError(
f"empty bucket name for object name {object_name}",
)
query = []
for key, values in sorted((query_params or {}).items()):
values = values if isinstance(values, (list, tuple)) else [values]
query += [
f"{queryencode(key)}={queryencode(value)}"
for value in sorted(values)
]
url = url_replace(self._url, query="&".join(query))
host = self._url.netloc
if not bucket_name:
url = url_replace(url, path="/")
return (
url_replace(url, netloc="s3." + region + "." + host)
if self._is_aws_host else url
)
enforce_path_style = (
# CreateBucket API requires path style in Amazon AWS S3.
(method == "PUT" and not object_name and not query_params) or
# GetBucketLocation API requires path style in Amazon AWS S3.
(query_params and "location" in query_params) or
# Use path style for bucket name containing '.' which causes
# SSL certificate validation error.
("." in bucket_name and self._url.scheme == "https")
)
if self._is_aws_host:
s3_domain = "s3."
if self._accelerate_host_flag:
if "." in bucket_name:
raise ValueError(
f"bucket name '{bucket_name}' with '.' is not allowed "
f"for accelerated endpoint"
)
if not enforce_path_style:
s3_domain = "s3-accelerate."
dual_stack = "dualstack." if self._dualstack_host_flag else ""
endpoint = s3_domain + dual_stack
if enforce_path_style or not self._accelerate_host_flag:
endpoint += region + "."
host = endpoint + host
if enforce_path_style or not self._virtual_style_flag:
url = url_replace(url, netloc=host)
url = url_replace(url, path="/" + bucket_name)
else:
url = url_replace(
url,
netloc=bucket_name + "." + host,
path="/",
)
if object_name:
path = url.path
path += ("" if path.endswith("/") else "/") + quote(object_name)
url = url_replace(url, path=path)
return url
class ObjectWriteResult:
"""Result class of any APIs doing object creation."""
def __init__(
self, bucket_name, object_name, version_id, etag, http_headers,
last_modified=None, location=None,
):
self._bucket_name = bucket_name
self._object_name = object_name
self._version_id = version_id
self._etag = etag
self._http_headers = http_headers
self._last_modified = last_modified
self._location = location
@property
def bucket_name(self):
"""Get bucket name."""
return self._bucket_name
@property
def object_name(self):
"""Get object name."""
return self._object_name
@property
def version_id(self):
"""Get version ID."""
return self._version_id
@property
def etag(self):
"""Get etag."""
return self._etag
@property
def http_headers(self):
"""Get HTTP headers."""
return self._http_headers
@property
def last_modified(self):
"""Get last-modified time."""
return self._last_modified
@property
def location(self):
"""Get location."""
return self._location
class Worker(Thread):
""" Thread executing tasks from a given tasks queue """
def __init__(self, tasks_queue, results_queue, exceptions_queue):
Thread.__init__(self, daemon=True)
self._tasks_queue = tasks_queue
self._results_queue = results_queue
self._exceptions_queue = exceptions_queue
self.start()
def run(self):
""" Continously receive tasks and execute them """
while True:
task = self._tasks_queue.get()
if not task:
self._tasks_queue.task_done()
break
# No exception detected in any thread,
# continue the execution.
if self._exceptions_queue.empty():
# Execute the task
func, args, kargs, cleanup_func = task
try:
result = func(*args, **kargs)
self._results_queue.put(result)
except Exception as ex: # pylint: disable=broad-except
self._exceptions_queue.put(ex)
finally:
cleanup_func()
# Mark this task as done, whether an exception happened or not
self._tasks_queue.task_done()
class ThreadPool:
""" Pool of threads consuming tasks from a queue """
def __init__(self, num_threads):
self._results_queue = Queue()
self._exceptions_queue = Queue()
self._tasks_queue = Queue()
self._sem = BoundedSemaphore(num_threads)
self._num_threads = num_threads
def add_task(self, func, *args, **kargs):
"""
Add a task to the queue. Calling this function can block
until workers have a room for processing new tasks. Blocking
the caller also prevents the latter from allocating a lot of
memory while workers are still busy running their assigned tasks.
"""
self._sem.acquire() # pylint: disable=consider-using-with
cleanup_func = self._sem.release
self._tasks_queue.put((func, args, kargs, cleanup_func))
def start_parallel(self):
""" Prepare threads to run tasks"""
for _ in range(self._num_threads):
Worker(
self._tasks_queue, self._results_queue, self._exceptions_queue,
)
def result(self):
""" Stop threads and return the result of all called tasks """
# Send None to all threads to cleanly stop them
for _ in range(self._num_threads):
self._tasks_queue.put(None)
# Wait for completion of all the tasks in the queue
self._tasks_queue.join()
# Check if one of the thread raised an exception, if yes
# raise it here in the function
if not self._exceptions_queue.empty():
raise self._exceptions_queue.get()
return self._results_queue