Repository navigation
Expand file tree
/
Copy pathhelpers.py
More file actions
712 lines (588 loc) · 23.6 KB
/
Copy pathhelpers.py
File metadata and controls
712 lines (588 loc) · 23.6 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
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.
"""
minio.helpers
This module implements all helper functions.
:copyright: (c) 2015, 2016, 2017 by MinIO, Inc.
:license: Apache 2.0, see LICENSE for more details.
"""
from __future__ import absolute_import
# if math.ceil returns an integer and devide two integers returns a float, calculate
# part size will cause errors, so make sure division integers returns a float.
from __future__ import division
from __future__ import unicode_literals
# future_str is unicode or str in both Python 2 and 3
from builtins import str as future_str
import io
import collections
import base64
import hashlib
import re
import os
import errno
import math
from .compat import (urlsplit, urlencode, queryencode,
str, bytes, basestring, _is_py3, _is_py2)
from .error import (InvalidBucketError, InvalidEndpointError,
InvalidArgumentError)
# 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
MAX_POOL_SIZE = 10
MIN_PART_SIZE = 5 * 1024 * 1024 # 5MiB
DEFAULT_PART_SIZE = MIN_PART_SIZE # Currently its 5MiB
_VALID_BUCKETNAME_REGEX = re.compile('^[a-z0-9][a-z0-9\\.\\-]+[a-z0-9]$')
_ALLOWED_HOSTNAME_REGEX = re.compile(
'^((?!-)(?!_)[A-Z_\\d-]{1,63}(?<!-)(?<!_)\\.)*((?!_)(?!-)[A-Z_\\d-]{1,63}(?<!-)(?<!_))$',
re.IGNORECASE)
_EXTRACT_REGION_REGEX = re.compile('s3[.-]?(.+?).amazonaws.com')
def get_s3_region_from_endpoint(endpoint):
"""
Extracts and returns an AWS S3 region from an endpoint
of form `s3-ap-southeast-1.amazonaws.com`
:param endpoint: Endpoint region to be extracted.
"""
# Extract region by regex search.
m = _EXTRACT_REGION_REGEX.search(endpoint)
if m:
# Regex matches, we have found a region.
region = m.group(1)
if region == 'external-1':
# Handle special scenario for us-east-1 URL.
return 'us-east-1'
if region.startswith('dualstack'):
# Handle special scenario for dualstack URL.
return region.split('.')[1]
return region
# No regex matches return None.
return None
def dump_http(method, url, request_headers, response, output_stream):
"""
Dump all headers and response headers into output_stream.
:param request_headers: Dictionary of HTTP request headers.
:param response_headers: Dictionary of HTTP response headers.
:param output_stream: Stream where the request is being dumped at.
"""
# Start header.
output_stream.write('---------START-HTTP---------\n')
# Get parsed url.
parsed_url = urlsplit(url)
# Dump all request headers recursively.
http_path = parsed_url.path
if parsed_url.query:
http_path = http_path + '?' + parsed_url.query
output_stream.write('{0} {1} HTTP/1.1\n'.format(method,
http_path))
for k, v in list(request_headers.items()):
if k is 'authorization':
# Redact signature header value from trace logs.
v = re.sub(r'Signature=([[0-9a-f]+)', 'Signature=*REDACTED*', v)
output_stream.write('{0}: {1}\n'.format(k.title(), v))
# Write a new line.
output_stream.write('\n')
# Write response status code.
output_stream.write('HTTP/1.1 {0}\n'.format(response.status))
# Dump all response headers recursively.
for k, v in list(response.getheaders().items()):
output_stream.write('{0}: {1}\n'.format(k.title(), v))
# For all errors write all the available response body.
if response.status != 200 and \
response.status != 204 and response.status != 206:
output_stream.write('{0}'.format(response.read()))
# End header.
output_stream.write('---------END-HTTP---------\n')
def mkdir_p(path):
"""
Recursively creates parent and sub directories.
:param path:
"""
try:
os.makedirs(path)
except OSError as exc: # Python >2.5
if exc.errno == errno.EEXIST and os.path.isdir(path):
pass
else:
raise
class PartMetadata(object):
"""
Parts manager split parts metadata :class:`PartMetadata <PartMetadata>`.
:param data: Part writer object backed by temporary file.
:param md5_hex: MD5 hash in hex format.
:param sha256_hex: Sha256 hash in hex format.
:param size: Size of the part.
"""
def __init__(self, data, md5_hex, sha256_hex, size):
self.data = data
self.md5_hex = md5_hex
self.sha256_hex = sha256_hex
self.size = size
def read_full(data, size):
"""
read_full reads exactly `size` bytes from reader. returns
`size` bytes.
:param data: Input stream to read from.
:param size: Number of bytes to read from `data`.
:return: Returns :bytes:`part_data`
"""
default_read_size = 32768 # 32KiB per read operation.
chunk = io.BytesIO()
chunk_size = 0
while chunk_size < size:
read_size = default_read_size
if (size - chunk_size) < default_read_size:
read_size = size - chunk_size
current_data = data.read(read_size)
if not current_data or len(current_data) == 0:
break
chunk.write(current_data)
chunk_size+= len(current_data)
return chunk.getvalue()
AWS_S3_ENDPOINT_MAP = {
'us-east-1': 's3.amazonaws.com',
'us-east-2': 's3-us-east-2.amazonaws.com',
'us-west-2': 's3-us-west-2.amazonaws.com',
'us-west-1': 's3-us-west-1.amazonaws.com',
'ca-central-1': 's3.ca-central-1.amazonaws.com',
'eu-west-1': 's3-eu-west-1.amazonaws.com',
'eu-west-2': 's3-eu-west-2.amazonaws.com',
'sa-east-1': 's3-sa-east-1.amazonaws.com',
'eu-central-1': 's3-eu-central-1.amazonaws.com',
'ap-south-1': 's3.ap-south-1.amazonaws.com',
'ap-southeast-1': 's3-ap-southeast-1.amazonaws.com',
'ap-southeast-2': 's3-ap-southeast-2.amazonaws.com',
'ap-northeast-1': 's3-ap-northeast-1.amazonaws.com',
'ap-northeast-2': 's3-ap-northeast-2.amazonaws.com',
'cn-north-1': 's3.cn-north-1.amazonaws.com.cn'
}
def get_s3_endpoint(region):
return AWS_S3_ENDPOINT_MAP.get(region, 's3.amazonaws.com')
def get_target_url(endpoint_url, bucket_name=None, object_name=None,
bucket_region='us-east-1', query=None):
"""
Construct final target url.
:param endpoint_url: Target endpoint url where request is served to.
:param bucket_name: Bucket component for the target url.
:param object_name: Object component for the target url.
:param bucket_region: Bucket region for the target url.
:param query: Query parameters as a *dict* for the target url.
:return: Returns final target url as *str*.
"""
# New url
url = None
# Parse url
parsed_url = urlsplit(endpoint_url)
# Get new host, scheme.
scheme = parsed_url.scheme
host = parsed_url.netloc
# Strip 80/443 ports since curl & browsers do not
# send them in Host header.
if (scheme == 'http' and parsed_url.port == 80) or\
(scheme == 'https' and parsed_url.port == 443):
host = parsed_url.hostname
if 's3.amazonaws.com' in host:
host = get_s3_endpoint(bucket_region)
url = scheme + '://' + host
if bucket_name:
# Save if target url will have buckets which suppport
# virtual host.
is_virtual_host_style = is_virtual_host(endpoint_url,
bucket_name)
if is_virtual_host_style:
url = (scheme + '://' + bucket_name + '.' + host)
else:
url = (scheme + '://' + host + '/' + bucket_name)
url_components = [url]
url_components.append('/')
if object_name:
object_name = encode_object_name(object_name)
url_components.append(object_name)
if query:
ordered_query = collections.OrderedDict(sorted(query.items()))
query_components = []
for component_key in ordered_query:
if isinstance(ordered_query[component_key], list):
for value in ordered_query[component_key]:
query_components.append(component_key+'='+
queryencode(value))
else:
query_components.append(
component_key+'='+
queryencode(ordered_query.get(component_key, '')))
query_string = '&'.join(query_components)
if query_string:
url_components.append('?')
url_components.append(query_string)
return ''.join(url_components)
def is_valid_endpoint(endpoint):
"""
Verify if endpoint is valid.
:type endpoint: string
:param endpoint: An endpoint. Must have at least a scheme and a hostname.
:return: True if the endpoint is valid. Raise :exc:`InvalidEndpointError`
otherwise.
"""
try:
if not '//' in endpoint:
# Having '//' in the beginning of the endpoint enforce
# urlsplit to consider the endpoint as a netloc according
# to this quote in docs.python.org/3/library/urllib.parse.html:
# Following the syntax specifications in RFC 1808, urlparse
# recognizes a netloc only if it is properly introduced by ‘//’.
# Otherwise the input is presumed to be a relative URL and thus
# to start with a path component.
endpoint = '//' + endpoint
u = urlsplit(endpoint)
if u.scheme:
raise InvalidEndpointError('Hostname cannot have a scheme.')
hostname = u.hostname
if hostname is None:
raise InvalidEndpointError('Hostname cannot be empty.')
if len(hostname) > 255:
raise InvalidEndpointError('Hostname cannot be greater than 255.')
if hostname[-1] == '.':
hostname = hostname[:-1]
if not _ALLOWED_HOSTNAME_REGEX.match(hostname):
raise InvalidEndpointError('Hostname does not meet URL standards.')
except AttributeError as error:
raise TypeError(error)
return True
def is_virtual_host(endpoint_url, bucket_name):
"""
Check to see if the ``bucket_name`` can be part of virtual host
style.
:param endpoint_url: Endpoint url which will be used for virtual host.
:param bucket_name: Bucket name to be validated against.
"""
is_valid_bucket_name(bucket_name)
parsed_url = urlsplit(endpoint_url)
# bucket_name can be valid but '.' in the hostname will fail
# SSL certificate validation. So do not use host-style for
# such buckets.
if 'https' in parsed_url.scheme and '.' in bucket_name:
return False
for host in ['s3.amazonaws.com', 'aliyuncs.com']:
if host in parsed_url.netloc:
return True
return False
def is_valid_bucket_name(bucket_name):
"""
Check to see if the ``bucket_name`` complies with the
restricted DNS naming conventions necessary to allow
access via virtual-hosting style.
:param bucket_name: Bucket name in *str*.
:return: True if the bucket is valid. Raise :exc:`InvalidBucketError`
otherwise.
"""
# Verify bucket name length.
if len(bucket_name) < 3:
raise InvalidBucketError('Bucket name cannot be less than'
' 3 characters.')
if len(bucket_name) > 63:
raise InvalidBucketError('Bucket name cannot be more than'
' 63 characters.')
if '..' in bucket_name:
raise InvalidBucketError('Bucket name cannot have successive'
' periods.')
match = _VALID_BUCKETNAME_REGEX.match(bucket_name)
if match is None or match.end() != len(bucket_name):
raise InvalidBucketError('Bucket name does not follow S3 standards.'
' Bucket: {0}'.format(bucket_name))
return True
def is_non_empty_string(input_string):
"""
Validate if non empty string
:param input_string: Input is a *str*.
:return: True if input is string and non empty.
Raise :exc:`Exception` otherwise.
"""
try:
if not input_string.strip():
raise ValueError()
except AttributeError as error:
raise TypeError(error)
return True
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 _is_py3:
string_type = str,
elif _is_py2:
string_type = basestring
if not isinstance(policy, string_type):
raise TypeError('policy can only be of type str')
is_non_empty_string(policy)
return True
def is_valid_bucket_notification_config(notifications):
"""
Validate the notifications config structure
:param notifications: Dictionary with specific structure.
:return: True if input is a valid bucket notifications structure.
Raise :exc:`InvalidArgumentError` otherwise.
"""
# check if notifications is a dict.
if not isinstance(notifications, dict):
raise TypeError('notifications configuration must be a dictionary')
if len(notifications) == 0:
raise InvalidArgumentError(
'notifications configuration may not be empty'
)
VALID_NOTIFICATION_KEYS = set([
"TopicConfigurations",
"QueueConfigurations",
"CloudFunctionConfigurations",
])
VALID_SERVICE_CONFIG_KEYS = set([
'Id',
'Arn',
'Events',
'Filter',
])
NOTIFICATION_EVENTS = set([
's3:ObjectAccessed:*',
's3:ObjectAccessed:Get',
's3:ObjectAccessed:Head',
's3:ReducedRedundancyLostObject',
's3:ObjectCreated:*',
's3:ObjectCreated:Put',
's3:ObjectCreated:Post',
's3:ObjectCreated:Copy',
's3:ObjectCreated:CompleteMultipartUpload',
's3:ObjectRemoved:*',
's3:ObjectRemoved:Delete',
's3:ObjectRemoved:DeleteMarkerCreated',
])
for key, value in notifications.items():
# check if key names are valid
if key not in VALID_NOTIFICATION_KEYS:
raise InvalidArgumentError((
'{} is an invalid key '
'for notifications configuration').format(key))
# check if config values conform
# first check if value is a list
if not isinstance(value, list):
raise InvalidArgumentError((
'The value for key "{}" in the notifications '
'configuration must be a list.').format(key))
for service_config in value:
# check type matches
if not isinstance(service_config, dict):
raise InvalidArgumentError((
'Each service configuration item for "{}" must be a '
'dictionary').format(key))
# check keys are valid
for skey in service_config.keys():
if skey not in VALID_SERVICE_CONFIG_KEYS:
raise InvalidArgumentError((
'{} is an invalid key for a service '
'configuration item').format(skey))
# check for required keys
arn = service_config.get('Arn', '')
if arn == '':
raise InvalidArgumentError(
'Arn key in service config must be present and has to be '
'non-empty string'
)
events = service_config.get('Events', [])
if len(events) < 1:
raise InvalidArgumentError(
'At least one event must be specified in a service config'
)
if not isinstance(events, list):
raise InvalidArgumentError('"Events" must be a list of strings '
'in a service configuration')
# check if 'Id' key is present, it should be string or bytes.
if not isinstance(service_config.get('Id', ''), basestring):
raise InvalidArgumentError('"Id" key must be a string')
for event in events:
if event not in NOTIFICATION_EVENTS:
raise InvalidArgumentError(
'{} is not a valid event. Valid '
'events are: {}'.format(event, NOTIFICATION_EVENTS))
if 'Filter' in service_config:
exception_msg = (
'{} - If a Filter key is given, it must be a '
'dictionary, the dictionary must have the '
'key "Key", and its value must be an object, with '
'a key named "FilterRules" which must be a non-empty list.'
).format(
service_config['Filter']
)
try:
filter_rules = service_config.get('Filter', {}).get(
'Key', {}).get('FilterRules', [])
if not isinstance(filter_rules, list):
raise InvalidArgumentError(exception_msg)
if len(filter_rules) < 1:
raise InvalidArgumentError(exception_msg)
except AttributeError:
raise InvalidArgumentError(exception_msg)
for filter_rule in filter_rules:
try:
name = filter_rule['Name']
value = filter_rule['Value']
except KeyError:
raise InvalidArgumentError((
'{} - a FilterRule dictionary must have "Name" '
'and "Value" keys').format(filter_rule))
if name not in ['prefix', 'suffix']:
raise InvalidArgumentError((
'{} - The "Name" key in a filter rule must be '
'either "prefix" or "suffix"').format(name))
return True
def is_valid_sse_c_object(sse=None):
"""
Validate the SSE object and type
:param sse: SSE object defined.
"""
if sse and sse.type() != "SSE-C":
raise InvalidArgumentError("Required type SSE-C object to be passed")
def is_valid_sse_object(sse):
"""
Validate the SSE object and type
:param sse: SSE object defined.
"""
if sse and sse.type() != "SSE-C" and sse.type() != "SSE-KMS" and sse.type() != "SSE-S3":
raise InvalidArgumentError("unsuported type of sse argument in put_object")
def is_valid_source_sse_object(sse):
"""
Validate the SSE object and type
:param sse: SSE object defined.
"""
if sse and sse.type() != "copy_SSE-C":
raise InvalidArgumentError("Required type copy_SSE-C object to be passed")
def encode_object_name(object_name):
"""
URL encode input object name.
:param object_name: Un-encoded object name.
:return: URL encoded input object name.
"""
is_non_empty_string(object_name)
return urlencode(object_name)
class Hasher(object):
"""
Adaptation of hashlib-based hash functions that
return unicode-encoded hex- and base64-digest
strings.
"""
def __init__(self, data, h):
if data is None:
data = b''
if isinstance(data, str):
data = data.encode('utf-8')
self.h = h(data)
@classmethod
def md5(cls, data=''):
return cls(data, hashlib.md5)
@classmethod
def sha256(cls, data=''):
return cls(data, hashlib.sha256)
def update(self, data):
if isinstance(data, str):
data = data.encode('utf-8')
self.h.update(data)
def hexdigest(self):
r = self.h.hexdigest()
return r.decode('utf-8') if isinstance(r, bytes) else r
def base64digest(self):
r = base64.b64encode(self.h.digest())
return r.decode('utf-8') if isinstance(r, bytes) else r
def get_sha256_hexdigest(content):
"""
Calculate sha256 hexdigest of content.
:param content: Input str or bytes. If the type is `str` we encode
it to UTF8 first.
:return: sha256 digest encoded as hexadecimal `str`.
"""
return Hasher.sha256(content).hexdigest()
def get_md5_base64digest(content):
"""Calculate md5sum and return digest as base64 encoded string.
:param content: Input str or bytes. If the type is `str` we encode
it to UTF8 and calculate md5sum.
:return: md5 digest encoded to base64 `str`.
"""
return Hasher.md5(content).base64digest()
def optimal_part_info(length, part_size):
"""
Calculate optimal part size for multipart uploads.
:param length: Input length to calculate part size of.
:return: Optimal part size.
"""
# object size is '-1' set it to 5TiB.
if length == -1:
length = MAX_MULTIPART_OBJECT_SIZE
if length > MAX_MULTIPART_OBJECT_SIZE:
raise InvalidArgumentError('Input content size is bigger '
' than allowed maximum of 5TiB.')
# honor user configured size
if part_size != MIN_PART_SIZE:
part_size_float = float(part_size)
else:
# Use floats for part size for all calculations to avoid
# overflows during float64 to int64 conversions.
part_size_float = math.ceil(length/MAX_MULTIPART_COUNT)
part_size_float = (math.ceil(part_size_float/part_size)
* part_size)
# Total parts count.
total_parts_count = int(math.ceil(length/part_size_float))
# Part size.
part_size = int(part_size_float)
# Last part size.
last_part_size = length - int(total_parts_count-1)*part_size
return total_parts_count, part_size, last_part_size
# return a new metadata dictionary where user defined metadata keys
# are prefixed by "x-amz-meta-"
def amzprefix_user_metadata(metadata):
m = dict()
for k,v in metadata.items():
# Check if metadata value has US-ASCII encoding since it is
# the only one supported by HTTP headers. This will show a better
# exception message when users pass unsupported characters
# in metadata values.
try:
if isinstance(v, future_str):
v.encode('us-ascii')
except UnicodeEncodeError:
raise ValueError('Metadata supports only US-ASCII characters.')
if is_amz_header(k) or is_supported_header(k) or is_storageclass_header(k):
m[k] = v
else:
m["X-Amz-Meta-" + k] = v
return m
# returns true if amz s3 system defined metadata
def is_amz_header(key):
key = key.lower()
return key.startswith("x-amz-meta") or key == "x-amz-acl" or key.startswith("x-amz-server-side-encryption")
# returns true if a standard supported header
def is_supported_header(key):
## Supported headers for object.
supported_headers = [
"cache-control",
"content-encoding",
"content-type",
"content-disposition",
"content-language",
"x-amz-website-redirect-location",
## Add more supported headers here.
]
return key.lower() in supported_headers
# returns true if header is a storage class header
def is_storageclass_header(key):
return key.lower() == "x-amz-storage-class"