This repository has been archived by the owner on May 10, 2024. It is now read-only.
/
key.py
1921 lines (1667 loc) · 80.5 KB
/
key.py
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) 2006-2012 Mitch Garnaat http://garnaat.org/
# Copyright (c) 2011, Nexenta Systems Inc.
# Copyright (c) 2012 Amazon.com, Inc. or its affiliates. All Rights Reserved
#
# 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, dis-
# tribute, sublicense, and/or sell copies of the Software, and to permit
# persons to whom the Software is furnished to do so, subject to the fol-
# lowing 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 MERCHANTABIL-
# ITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT
# SHALL THE AUTHOR 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.
import email.utils
import errno
import hashlib
import mimetypes
import os
import re
import base64
import binascii
import math
from hashlib import md5
import boto.utils
from boto.compat import BytesIO, six, urllib, encodebytes
from boto.exception import BotoClientError
from boto.exception import StorageDataError
from boto.exception import PleaseRetryException
from boto.provider import Provider
from boto.s3.keyfile import KeyFile
from boto.s3.user import User
from boto import UserAgent
from boto.utils import compute_md5, compute_hash
from boto.utils import find_matching_headers
from boto.utils import merge_headers_by_name
class Key(object):
"""
Represents a key (object) in an S3 bucket.
:ivar bucket: The parent :class:`boto.s3.bucket.Bucket`.
:ivar name: The name of this Key object.
:ivar metadata: A dictionary containing user metadata that you
wish to store with the object or that has been retrieved from
an existing object.
:ivar cache_control: The value of the `Cache-Control` HTTP header.
:ivar content_type: The value of the `Content-Type` HTTP header.
:ivar content_encoding: The value of the `Content-Encoding` HTTP header.
:ivar content_disposition: The value of the `Content-Disposition` HTTP
header.
:ivar content_language: The value of the `Content-Language` HTTP header.
:ivar etag: The `etag` associated with this object.
:ivar last_modified: The string timestamp representing the last
time this object was modified in S3.
:ivar owner: The ID of the owner of this object.
:ivar storage_class: The storage class of the object. Currently, one of:
STANDARD | REDUCED_REDUNDANCY | GLACIER
:ivar md5: The MD5 hash of the contents of the object.
:ivar size: The size, in bytes, of the object.
:ivar version_id: The version ID of this object, if it is a versioned
object.
:ivar encrypted: Whether the object is encrypted while at rest on
the server.
"""
DefaultContentType = 'application/octet-stream'
RestoreBody = """<?xml version="1.0" encoding="UTF-8"?>
<RestoreRequest xmlns="http://s3.amazonaws.com/doc/2006-03-01">
<Days>%s</Days>
</RestoreRequest>"""
BufferSize = boto.config.getint('Boto', 'key_buffer_size', 8192)
# The object metadata fields a user can set, other than custom metadata
# fields (i.e., those beginning with a provider-specific prefix like
# x-amz-meta).
base_user_settable_fields = set(["cache-control", "content-disposition",
"content-encoding", "content-language",
"content-md5", "content-type",
"x-robots-tag", "expires"])
_underscore_base_user_settable_fields = set()
for f in base_user_settable_fields:
_underscore_base_user_settable_fields.add(f.replace('-', '_'))
# Metadata fields, whether user-settable or not, other than custom
# metadata fields (i.e., those beginning with a provider specific prefix
# like x-amz-meta).
base_fields = (base_user_settable_fields |
set(["last-modified", "content-length", "date", "etag"]))
def __init__(self, bucket=None, name=None):
self.bucket = bucket
self.name = name
self.metadata = {}
self.cache_control = None
self.content_type = self.DefaultContentType
self.content_encoding = None
self.content_disposition = None
self.content_language = None
self.filename = None
self.etag = None
self.is_latest = False
self.last_modified = None
self.owner = None
self._storage_class = None
self.path = None
self.resp = None
self.mode = None
self.size = None
self.version_id = None
self.source_version_id = None
self.delete_marker = False
self.encrypted = None
# If the object is being restored, this attribute will be set to True.
# If the object is restored, it will be set to False. Otherwise this
# value will be None. If the restore is completed (ongoing_restore =
# False), the expiry_date will be populated with the expiry date of the
# restored object.
self.ongoing_restore = None
self.expiry_date = None
self.local_hashes = {}
def __repr__(self):
if self.bucket:
name = u'<Key: %s,%s>' % (self.bucket.name, self.name)
else:
name = u'<Key: None,%s>' % self.name
# Encode to bytes for Python 2 to prevent display decoding issues
if not isinstance(name, str):
name = name.encode('utf-8')
return name
def __iter__(self):
return self
@property
def provider(self):
provider = None
if self.bucket and self.bucket.connection:
provider = self.bucket.connection.provider
return provider
def _get_key(self):
return self.name
def _set_key(self, value):
self.name = value
key = property(_get_key, _set_key);
def _get_md5(self):
if 'md5' in self.local_hashes and self.local_hashes['md5']:
return binascii.b2a_hex(self.local_hashes['md5'])
def _set_md5(self, value):
if value:
self.local_hashes['md5'] = binascii.a2b_hex(value)
elif 'md5' in self.local_hashes:
self.local_hashes.pop('md5', None)
md5 = property(_get_md5, _set_md5);
def _get_base64md5(self):
if 'md5' in self.local_hashes and self.local_hashes['md5']:
md5 = self.local_hashes['md5']
if not isinstance(md5, bytes):
md5 = md5.encode('utf-8')
return binascii.b2a_base64(md5).decode('utf-8').rstrip('\n')
def _set_base64md5(self, value):
if value:
if not isinstance(value, six.string_types):
value = value.decode('utf-8')
self.local_hashes['md5'] = binascii.a2b_base64(value)
elif 'md5' in self.local_hashes:
del self.local_hashes['md5']
base64md5 = property(_get_base64md5, _set_base64md5);
def _get_storage_class(self):
if self._storage_class is None and self.bucket:
# Attempt to fetch storage class
list_items = list(self.bucket.list(self.name.encode('utf-8')))
if len(list_items) and getattr(list_items[0], '_storage_class',
None):
self._storage_class = list_items[0]._storage_class
else:
# Key is not yet saved? Just use default...
self._storage_class = 'STANDARD'
return self._storage_class
def _set_storage_class(self, value):
self._storage_class = value
storage_class = property(_get_storage_class, _set_storage_class)
def get_md5_from_hexdigest(self, md5_hexdigest):
"""
A utility function to create the 2-tuple (md5hexdigest, base64md5)
from just having a precalculated md5_hexdigest.
"""
digest = binascii.unhexlify(md5_hexdigest)
base64md5 = encodebytes(digest)
if base64md5[-1] == '\n':
base64md5 = base64md5[0:-1]
return (md5_hexdigest, base64md5)
def handle_encryption_headers(self, resp):
provider = self.bucket.connection.provider
if provider.server_side_encryption_header:
self.encrypted = resp.getheader(
provider.server_side_encryption_header, None)
else:
self.encrypted = None
def handle_version_headers(self, resp, force=False):
provider = self.bucket.connection.provider
# If the Key object already has a version_id attribute value, it
# means that it represents an explicit version and the user is
# doing a get_contents_*(version_id=<foo>) to retrieve another
# version of the Key. In that case, we don't really want to
# overwrite the version_id in this Key object. Comprende?
if self.version_id is None or force:
self.version_id = resp.getheader(provider.version_id, None)
self.source_version_id = resp.getheader(provider.copy_source_version_id,
None)
if resp.getheader(provider.delete_marker, 'false') == 'true':
self.delete_marker = True
else:
self.delete_marker = False
def handle_restore_headers(self, response):
provider = self.bucket.connection.provider
header = response.getheader(provider.restore_header)
if header is None:
return
parts = header.split(',', 1)
for part in parts:
key, val = [i.strip() for i in part.split('=')]
val = val.replace('"', '')
if key == 'ongoing-request':
self.ongoing_restore = True if val.lower() == 'true' else False
elif key == 'expiry-date':
self.expiry_date = val
def handle_addl_headers(self, headers):
"""
Used by Key subclasses to do additional, provider-specific
processing of response headers. No-op for this base class.
"""
pass
def open_read(self, headers=None, query_args='',
override_num_retries=None, response_headers=None):
"""
Open this key for reading
:type headers: dict
:param headers: Headers to pass in the web request
:type query_args: string
:param query_args: Arguments to pass in the query string
(ie, 'torrent')
:type override_num_retries: int
:param override_num_retries: If not None will override configured
num_retries parameter for underlying GET.
:type response_headers: dict
:param response_headers: A dictionary containing HTTP
headers/values that will override any headers associated
with the stored object in the response. See
http://goo.gl/EWOPb for details.
"""
if self.resp is None:
self.mode = 'r'
provider = self.bucket.connection.provider
self.resp = self.bucket.connection.make_request(
'GET', self.bucket.name, self.name, headers,
query_args=query_args,
override_num_retries=override_num_retries)
if self.resp.status < 199 or self.resp.status > 299:
body = self.resp.read()
raise provider.storage_response_error(self.resp.status,
self.resp.reason, body)
response_headers = self.resp.msg
self.metadata = boto.utils.get_aws_metadata(response_headers,
provider)
for name, value in response_headers.items():
# To get correct size for Range GETs, use Content-Range
# header if one was returned. If not, use Content-Length
# header.
if (name.lower() == 'content-length' and
'Content-Range' not in response_headers):
self.size = int(value)
elif name.lower() == 'content-range':
end_range = re.sub('.*/(.*)', '\\1', value)
self.size = int(end_range)
elif name.lower() in Key.base_fields:
self.__dict__[name.lower().replace('-', '_')] = value
self.handle_version_headers(self.resp)
self.handle_encryption_headers(self.resp)
self.handle_restore_headers(self.resp)
self.handle_addl_headers(self.resp.getheaders())
def open_write(self, headers=None, override_num_retries=None):
"""
Open this key for writing.
Not yet implemented
:type headers: dict
:param headers: Headers to pass in the write request
:type override_num_retries: int
:param override_num_retries: If not None will override configured
num_retries parameter for underlying PUT.
"""
raise BotoClientError('Not Implemented')
def open(self, mode='r', headers=None, query_args=None,
override_num_retries=None):
if mode == 'r':
self.mode = 'r'
self.open_read(headers=headers, query_args=query_args,
override_num_retries=override_num_retries)
elif mode == 'w':
self.mode = 'w'
self.open_write(headers=headers,
override_num_retries=override_num_retries)
else:
raise BotoClientError('Invalid mode: %s' % mode)
closed = False
def close(self, fast=False):
"""
Close this key.
:type fast: bool
:param fast: True if you want the connection to be closed without first
reading the content. This should only be used in cases where subsequent
calls don't need to return the content from the open HTTP connection.
Note: As explained at
http://docs.python.org/2/library/httplib.html#httplib.HTTPConnection.getresponse,
callers must read the whole response before sending a new request to the
server. Calling Key.close(fast=True) and making a subsequent request to
the server will work because boto will get an httplib exception and
close/reopen the connection.
"""
if self.resp and not fast:
self.resp.read()
self.resp = None
self.mode = None
self.closed = True
def next(self):
"""
By providing a next method, the key object supports use as an iterator.
For example, you can now say:
for bytes in key:
write bytes to a file or whatever
All of the HTTP connection stuff is handled for you.
"""
self.open_read()
data = self.resp.read(self.BufferSize)
if not data:
self.close()
raise StopIteration
return data
# Python 3 iterator support
__next__ = next
def read(self, size=0):
self.open_read()
if size == 0:
data = self.resp.read()
else:
data = self.resp.read(size)
if not data:
self.close()
return data
def change_storage_class(self, new_storage_class, dst_bucket=None,
validate_dst_bucket=True):
"""
Change the storage class of an existing key.
Depending on whether a different destination bucket is supplied
or not, this will either move the item within the bucket, preserving
all metadata and ACL info bucket changing the storage class or it
will copy the item to the provided destination bucket, also
preserving metadata and ACL info.
:type new_storage_class: string
:param new_storage_class: The new storage class for the Key.
Possible values are:
* STANDARD
* REDUCED_REDUNDANCY
:type dst_bucket: string
:param dst_bucket: The name of a destination bucket. If not
provided the current bucket of the key will be used.
:type validate_dst_bucket: bool
:param validate_dst_bucket: If True, will validate the dst_bucket
by using an extra list request.
"""
bucket_name = dst_bucket or self.bucket.name
if new_storage_class == 'STANDARD':
return self.copy(bucket_name, self.name,
reduced_redundancy=False, preserve_acl=True,
validate_dst_bucket=validate_dst_bucket)
elif new_storage_class == 'REDUCED_REDUNDANCY':
return self.copy(bucket_name, self.name,
reduced_redundancy=True, preserve_acl=True,
validate_dst_bucket=validate_dst_bucket)
else:
raise BotoClientError('Invalid storage class: %s' %
new_storage_class)
def copy(self, dst_bucket, dst_key, metadata=None,
reduced_redundancy=False, preserve_acl=False,
encrypt_key=False, validate_dst_bucket=True):
"""
Copy this Key to another bucket.
:type dst_bucket: string
:param dst_bucket: The name of the destination bucket
:type dst_key: string
:param dst_key: The name of the destination key
:type metadata: dict
:param metadata: Metadata to be associated with new key. If
metadata is supplied, it will replace the metadata of the
source key being copied. If no metadata is supplied, the
source key's metadata will be copied to the new key.
:type reduced_redundancy: bool
:param reduced_redundancy: If True, this will force the
storage class of the new Key to be REDUCED_REDUNDANCY
regardless of the storage class of the key being copied.
The Reduced Redundancy Storage (RRS) feature of S3,
provides lower redundancy at lower storage cost.
:type preserve_acl: bool
:param preserve_acl: If True, the ACL from the source key will
be copied to the destination key. If False, the
destination key will have the default ACL. Note that
preserving the ACL in the new key object will require two
additional API calls to S3, one to retrieve the current
ACL and one to set that ACL on the new object. If you
don't care about the ACL, a value of False will be
significantly more efficient.
:type encrypt_key: bool
:param encrypt_key: If True, the new copy of the object will
be encrypted on the server-side by S3 and will be stored
in an encrypted form while at rest in S3.
:type validate_dst_bucket: bool
:param validate_dst_bucket: If True, will validate the dst_bucket
by using an extra list request.
:rtype: :class:`boto.s3.key.Key` or subclass
:returns: An instance of the newly created key object
"""
dst_bucket = self.bucket.connection.lookup(dst_bucket,
validate_dst_bucket)
if reduced_redundancy:
storage_class = 'REDUCED_REDUNDANCY'
else:
storage_class = self.storage_class
return dst_bucket.copy_key(dst_key, self.bucket.name,
self.name, metadata,
storage_class=storage_class,
preserve_acl=preserve_acl,
encrypt_key=encrypt_key,
src_version_id=self.version_id)
def startElement(self, name, attrs, connection):
if name == 'Owner':
self.owner = User(self)
return self.owner
else:
return None
def endElement(self, name, value, connection):
if name == 'Key':
self.name = value
elif name == 'ETag':
self.etag = value
elif name == 'IsLatest':
if value == 'true':
self.is_latest = True
else:
self.is_latest = False
elif name == 'LastModified':
self.last_modified = value
elif name == 'Size':
self.size = int(value)
elif name == 'StorageClass':
self.storage_class = value
elif name == 'Owner':
pass
elif name == 'VersionId':
self.version_id = value
else:
setattr(self, name, value)
def exists(self, headers=None):
"""
Returns True if the key exists
:rtype: bool
:return: Whether the key exists on S3
"""
return bool(self.bucket.lookup(self.name, headers=headers))
def delete(self, headers=None):
"""
Delete this key from S3
"""
return self.bucket.delete_key(self.name, version_id=self.version_id,
headers=headers)
def get_metadata(self, name):
return self.metadata.get(name)
def set_metadata(self, name, value):
# Ensure that metadata that is vital to signing is in the correct
# case. Applies to ``Content-Type`` & ``Content-MD5``.
if name.lower() == 'content-type':
self.metadata['Content-Type'] = value
elif name.lower() == 'content-md5':
self.metadata['Content-MD5'] = value
else:
self.metadata[name] = value
if name.lower() in Key.base_user_settable_fields:
self.__dict__[name.lower().replace('-', '_')] = value
def update_metadata(self, d):
self.metadata.update(d)
# convenience methods for setting/getting ACL
def set_acl(self, acl_str, headers=None):
if self.bucket is not None:
self.bucket.set_acl(acl_str, self.name, headers=headers)
def get_acl(self, headers=None):
if self.bucket is not None:
return self.bucket.get_acl(self.name, headers=headers)
def get_xml_acl(self, headers=None):
if self.bucket is not None:
return self.bucket.get_xml_acl(self.name, headers=headers)
def set_xml_acl(self, acl_str, headers=None):
if self.bucket is not None:
return self.bucket.set_xml_acl(acl_str, self.name, headers=headers)
def set_canned_acl(self, acl_str, headers=None):
return self.bucket.set_canned_acl(acl_str, self.name, headers)
def get_redirect(self):
"""Return the redirect location configured for this key.
If no redirect is configured (via set_redirect), then None
will be returned.
"""
response = self.bucket.connection.make_request(
'HEAD', self.bucket.name, self.name)
if response.status == 200:
return response.getheader('x-amz-website-redirect-location')
else:
raise self.provider.storage_response_error(
response.status, response.reason, response.read())
def set_redirect(self, redirect_location, headers=None):
"""Configure this key to redirect to another location.
When the bucket associated with this key is accessed from the website
endpoint, a 301 redirect will be issued to the specified
`redirect_location`.
:type redirect_location: string
:param redirect_location: The location to redirect.
"""
if headers is None:
headers = {}
else:
headers = headers.copy()
headers['x-amz-website-redirect-location'] = redirect_location
response = self.bucket.connection.make_request('PUT', self.bucket.name,
self.name, headers)
if response.status == 200:
return True
else:
raise self.provider.storage_response_error(
response.status, response.reason, response.read())
def make_public(self, headers=None):
return self.bucket.set_canned_acl('public-read', self.name, headers)
def generate_url(self, expires_in, method='GET', headers=None,
query_auth=True, force_http=False, response_headers=None,
expires_in_absolute=False, version_id=None,
policy=None, reduced_redundancy=False, encrypt_key=False):
"""
Generate a URL to access this key.
:type expires_in: int
:param expires_in: How long the url is valid for, in seconds.
:type method: string
:param method: The method to use for retrieving the file
(default is GET).
:type headers: dict
:param headers: Any headers to pass along in the request.
:type query_auth: bool
:param query_auth: If True, signs the request in the URL.
:type force_http: bool
:param force_http: If True, http will be used instead of https.
:type response_headers: dict
:param response_headers: A dictionary containing HTTP
headers/values that will override any headers associated
with the stored object in the response. See
http://goo.gl/EWOPb for details.
:type expires_in_absolute: bool
:param expires_in_absolute:
:type version_id: string
:param version_id: The version_id of the object to GET. If specified
this overrides any value in the key.
:type policy: :class:`boto.s3.acl.CannedACLStrings`
:param policy: A canned ACL policy that will be applied to the
new key in S3.
:type reduced_redundancy: bool
:param reduced_redundancy: If True, this will set the storage
class of the new Key to be REDUCED_REDUNDANCY. The Reduced
Redundancy Storage (RRS) feature of S3, provides lower
redundancy at lower storage cost.
:type encrypt_key: bool
:param encrypt_key: If True, the new copy of the object will
be encrypted on the server-side by S3 and will be stored
in an encrypted form while at rest in S3.
:rtype: string
:return: The URL to access the key
"""
provider = self.bucket.connection.provider
version_id = version_id or self.version_id
if headers is None:
headers = {}
else:
headers = headers.copy()
# add headers accordingly (usually PUT case)
if policy:
headers[provider.acl_header] = policy
if reduced_redundancy:
self.storage_class = 'REDUCED_REDUNDANCY'
if provider.storage_class_header:
headers[provider.storage_class_header] = self.storage_class
if encrypt_key:
headers[provider.server_side_encryption_header] = 'AES256'
headers = boto.utils.merge_meta(headers, self.metadata, provider)
return self.bucket.connection.generate_url(expires_in, method,
self.bucket.name, self.name,
headers, query_auth,
force_http,
response_headers,
expires_in_absolute,
version_id)
def send_file(self, fp, headers=None, cb=None, num_cb=10,
query_args=None, chunked_transfer=False, size=None):
"""
Upload a file to a key into a bucket on S3.
:type fp: file
:param fp: The file pointer to upload. The file pointer must
point at the offset from which you wish to upload.
ie. if uploading the full file, it should point at the
start of the file. Normally when a file is opened for
reading, the fp will point at the first byte. See the
bytes parameter below for more info.
:type headers: dict
:param headers: The headers to pass along with the PUT request
:type num_cb: int
:param num_cb: (optional) If a callback is specified with the
cb parameter this parameter determines the granularity of
the callback by defining the maximum number of times the
callback will be called during the file
transfer. Providing a negative integer will cause your
callback to be called with each buffer read.
:type query_args: string
:param query_args: (optional) Arguments to pass in the query string.
:type chunked_transfer: boolean
:param chunked_transfer: (optional) If true, we use chunked
Transfer-Encoding.
:type size: int
:param size: (optional) The Maximum number of bytes to read
from the file pointer (fp). This is useful when uploading
a file in multiple parts where you are splitting the file
up into different ranges to be uploaded. If not specified,
the default behaviour is to read all bytes from the file
pointer. Less bytes may be available.
"""
self._send_file_internal(fp, headers=headers, cb=cb, num_cb=num_cb,
query_args=query_args,
chunked_transfer=chunked_transfer, size=size)
def _send_file_internal(self, fp, headers=None, cb=None, num_cb=10,
query_args=None, chunked_transfer=False, size=None,
hash_algs=None):
provider = self.bucket.connection.provider
try:
spos = fp.tell()
except IOError:
spos = None
self.read_from_stream = False
# If hash_algs is unset and the MD5 hasn't already been computed,
# default to an MD5 hash_alg to hash the data on-the-fly.
if hash_algs is None and not self.md5:
hash_algs = {'md5': md5}
digesters = dict((alg, hash_algs[alg]()) for alg in hash_algs or {})
def sender(http_conn, method, path, data, headers):
# This function is called repeatedly for temporary retries
# so we must be sure the file pointer is pointing at the
# start of the data.
if spos is not None and spos != fp.tell():
fp.seek(spos)
elif spos is None and self.read_from_stream:
# if seek is not supported, and we've read from this
# stream already, then we need to abort retries to
# avoid setting bad data.
raise provider.storage_data_error(
'Cannot retry failed request. fp does not support seeking.')
# If the caller explicitly specified host header, tell putrequest
# not to add a second host header. Similarly for accept-encoding.
skips = {}
if boto.utils.find_matching_headers('host', headers):
skips['skip_host'] = 1
if boto.utils.find_matching_headers('accept-encoding', headers):
skips['skip_accept_encoding'] = 1
http_conn.putrequest(method, path, **skips)
for key in headers:
http_conn.putheader(key, headers[key])
http_conn.endheaders()
save_debug = self.bucket.connection.debug
self.bucket.connection.debug = 0
# If the debuglevel < 4 we don't want to show connection
# payload, so turn off HTTP connection-level debug output (to
# be restored below).
# Use the getattr approach to allow this to work in AppEngine.
if getattr(http_conn, 'debuglevel', 0) < 4:
http_conn.set_debuglevel(0)
data_len = 0
if cb:
if size:
cb_size = size
elif self.size:
cb_size = self.size
else:
cb_size = 0
if chunked_transfer and cb_size == 0:
# For chunked Transfer, we call the cb for every 1MB
# of data transferred, except when we know size.
cb_count = (1024 * 1024) / self.BufferSize
elif num_cb > 1:
cb_count = int(
math.ceil(cb_size / self.BufferSize / (num_cb - 1.0)))
elif num_cb < 0:
cb_count = -1
else:
cb_count = 0
i = 0
cb(data_len, cb_size)
bytes_togo = size
if bytes_togo and bytes_togo < self.BufferSize:
chunk = fp.read(bytes_togo)
else:
chunk = fp.read(self.BufferSize)
if not isinstance(chunk, bytes):
chunk = chunk.encode('utf-8')
if spos is None:
# read at least something from a non-seekable fp.
self.read_from_stream = True
while chunk:
chunk_len = len(chunk)
data_len += chunk_len
if chunked_transfer:
http_conn.send('%x;\r\n' % chunk_len)
http_conn.send(chunk)
http_conn.send('\r\n')
else:
http_conn.send(chunk)
for alg in digesters:
digesters[alg].update(chunk)
if bytes_togo:
bytes_togo -= chunk_len
if bytes_togo <= 0:
break
if cb:
i += 1
if i == cb_count or cb_count == -1:
cb(data_len, cb_size)
i = 0
if bytes_togo and bytes_togo < self.BufferSize:
chunk = fp.read(bytes_togo)
else:
chunk = fp.read(self.BufferSize)
if not isinstance(chunk, bytes):
chunk = chunk.encode('utf-8')
self.size = data_len
for alg in digesters:
self.local_hashes[alg] = digesters[alg].digest()
if chunked_transfer:
http_conn.send('0\r\n')
# http_conn.send("Content-MD5: %s\r\n" % self.base64md5)
http_conn.send('\r\n')
if cb and (cb_count <= 1 or i > 0) and data_len > 0:
cb(data_len, cb_size)
http_conn.set_debuglevel(save_debug)
self.bucket.connection.debug = save_debug
response = http_conn.getresponse()
body = response.read()
if not self.should_retry(response, chunked_transfer):
raise provider.storage_response_error(
response.status, response.reason, body)
return response
if not headers:
headers = {}
else:
headers = headers.copy()
# Overwrite user-supplied user-agent.
for header in find_matching_headers('User-Agent', headers):
del headers[header]
headers['User-Agent'] = UserAgent
# If storage_class is None, then a user has not explicitly requested
# a storage class, so we can assume STANDARD here
if self._storage_class not in [None, 'STANDARD']:
headers[provider.storage_class_header] = self.storage_class
if find_matching_headers('Content-Encoding', headers):
self.content_encoding = merge_headers_by_name(
'Content-Encoding', headers)
if find_matching_headers('Content-Language', headers):
self.content_language = merge_headers_by_name(
'Content-Language', headers)
content_type_headers = find_matching_headers('Content-Type', headers)
if content_type_headers:
# Some use cases need to suppress sending of the Content-Type
# header and depend on the receiving server to set the content
# type. This can be achieved by setting headers['Content-Type']
# to None when calling this method.
if (len(content_type_headers) == 1 and
headers[content_type_headers[0]] is None):
# Delete null Content-Type value to skip sending that header.
del headers[content_type_headers[0]]
else:
self.content_type = merge_headers_by_name(
'Content-Type', headers)
elif self.path:
self.content_type = mimetypes.guess_type(self.path)[0]
if self.content_type is None:
self.content_type = self.DefaultContentType
headers['Content-Type'] = self.content_type
else:
headers['Content-Type'] = self.content_type
if self.base64md5:
headers['Content-MD5'] = self.base64md5
if chunked_transfer:
headers['Transfer-Encoding'] = 'chunked'
#if not self.base64md5:
# headers['Trailer'] = "Content-MD5"
else:
headers['Content-Length'] = str(self.size)
# This is terrible. We need a SHA256 of the body for SigV4, but to do
# the chunked ``sender`` behavior above, the ``fp`` isn't available to
# the auth mechanism (because closures). Detect if it's SigV4 & embelish
# while we can before the auth calculations occur.
if 'hmac-v4-s3' in self.bucket.connection._required_auth_capability():
kwargs = {'fp': fp, 'hash_algorithm': hashlib.sha256}
if size is not None:
kwargs['size'] = size
headers['_sha256'] = compute_hash(**kwargs)[0]
headers['Expect'] = '100-Continue'
headers = boto.utils.merge_meta(headers, self.metadata, provider)
resp = self.bucket.connection.make_request(
'PUT',
self.bucket.name,
self.name,
headers,
sender=sender,
query_args=query_args
)
self.handle_version_headers(resp, force=True)
self.handle_addl_headers(resp.getheaders())
def should_retry(self, response, chunked_transfer=False):
provider = self.bucket.connection.provider
if not chunked_transfer:
if response.status in [500, 503]:
# 500 & 503 can be plain retries.
return True
if response.getheader('location'):
# If there's a redirect, plain retry.
return True
if 200 <= response.status <= 299:
self.etag = response.getheader('etag')
md5 = self.md5
if isinstance(md5, bytes):
md5 = md5.decode('utf-8')
# If you use customer-provided encryption keys, the ETag value that
# Amazon S3 returns in the response will not be the MD5 of the
# object.
server_side_encryption_customer_algorithm = response.getheader(
'x-amz-server-side-encryption-customer-algorithm', None)
if server_side_encryption_customer_algorithm is None:
if self.etag != '"%s"' % md5:
raise provider.storage_data_error(
'ETag from S3 did not match computed MD5. '
'%s vs. %s' % (self.etag, self.md5))
return True
if response.status == 400:
# The 400 must be trapped so the retry handler can check to
# see if it was a timeout.
# If ``RequestTimeout`` is present, we'll retry. Otherwise, bomb
# out.
body = response.read()
err = provider.storage_response_error(
response.status,
response.reason,
body
)
if err.error_code in ['RequestTimeout']:
raise PleaseRetryException(