forked from googleapis/google-api-python-client
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathhttp.py
More file actions
1781 lines (1447 loc) 路 57.4 KB
/
Copy pathhttp.py
File metadata and controls
1781 lines (1447 loc) 路 57.4 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
# Copyright 2014 Google Inc. All Rights Reserved.
#
# 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.
"""Classes to encapsulate a single HTTP request.
The classes implement a command pattern, with every
object supporting an execute() method that does the
actual HTTP request.
"""
from __future__ import absolute_import
import six
from six.moves import http_client
from six.moves import range
__author__ = 'jcgregorio@google.com (Joe Gregorio)'
from six import BytesIO, StringIO
from six.moves.urllib.parse import urlparse, urlunparse, quote, unquote
import base64
import copy
import gzip
import httplib2
import json
import logging
import mimetypes
import os
import random
import socket
import sys
import time
import uuid
# TODO(issue 221): Remove this conditional import jibbajabba.
try:
import ssl
except ImportError:
_ssl_SSLError = object()
else:
_ssl_SSLError = ssl.SSLError
from email.generator import Generator
from email.mime.multipart import MIMEMultipart
from email.mime.nonmultipart import MIMENonMultipart
from email.parser import FeedParser
from googleapiclient import _helpers as util
from googleapiclient import _auth
from googleapiclient.errors import BatchError
from googleapiclient.errors import HttpError
from googleapiclient.errors import InvalidChunkSizeError
from googleapiclient.errors import ResumableUploadError
from googleapiclient.errors import UnexpectedBodyError
from googleapiclient.errors import UnexpectedMethodError
from googleapiclient.model import JsonModel
LOGGER = logging.getLogger(__name__)
DEFAULT_CHUNK_SIZE = 100*1024*1024
MAX_URI_LENGTH = 2048
_TOO_MANY_REQUESTS = 429
DEFAULT_HTTP_TIMEOUT_SEC = 60
_LEGACY_BATCH_URI = 'https://www.googleapis.com/batch'
def _should_retry_response(resp_status, content):
"""Determines whether a response should be retried.
Args:
resp_status: The response status received.
content: The response content body.
Returns:
True if the response should be retried, otherwise False.
"""
# Retry on 5xx errors.
if resp_status >= 500:
return True
# Retry on 429 errors.
if resp_status == _TOO_MANY_REQUESTS:
return True
# For 403 errors, we have to check for the `reason` in the response to
# determine if we should retry.
if resp_status == six.moves.http_client.FORBIDDEN:
# If there's no details about the 403 type, don't retry.
if not content:
return False
# Content is in JSON format.
try:
data = json.loads(content.decode('utf-8'))
if isinstance(data, dict):
reason = data['error']['errors'][0]['reason']
else:
reason = data[0]['error']['errors']['reason']
except (UnicodeDecodeError, ValueError, KeyError):
LOGGER.warning('Invalid JSON content from response: %s', content)
return False
LOGGER.warning('Encountered 403 Forbidden with reason "%s"', reason)
# Only retry on rate limit related failures.
if reason in ('userRateLimitExceeded', 'rateLimitExceeded', ):
return True
# Everything else is a success or non-retriable so break.
return False
def _retry_request(http, num_retries, req_type, sleep, rand, uri, method, *args,
**kwargs):
"""Retries an HTTP request multiple times while handling errors.
If after all retries the request still fails, last error is either returned as
return value (for HTTP 5xx errors) or thrown (for ssl.SSLError).
Args:
http: Http object to be used to execute request.
num_retries: Maximum number of retries.
req_type: Type of the request (used for logging retries).
sleep, rand: Functions to sleep for random time between retries.
uri: URI to be requested.
method: HTTP method to be used.
args, kwargs: Additional arguments passed to http.request.
Returns:
resp, content - Response from the http request (may be HTTP 5xx).
"""
resp = None
content = None
for retry_num in range(num_retries + 1):
if retry_num > 0:
# Sleep before retrying.
sleep_time = rand() * 2 ** retry_num
LOGGER.warning(
'Sleeping %.2f seconds before retry %d of %d for %s: %s %s, after %s',
sleep_time, retry_num, num_retries, req_type, method, uri,
resp.status if resp else exception)
sleep(sleep_time)
try:
exception = None
resp, content = http.request(uri, method, *args, **kwargs)
# Retry on SSL errors and socket timeout errors.
except _ssl_SSLError as ssl_error:
exception = ssl_error
except socket.timeout as socket_timeout:
# It's important that this be before socket.error as it's a subclass
# socket.timeout has no errorcode
exception = socket_timeout
except socket.error as socket_error:
# errno's contents differ by platform, so we have to match by name.
if socket.errno.errorcode.get(socket_error.errno) not in {
'WSAETIMEDOUT', 'ETIMEDOUT', 'EPIPE', 'ECONNABORTED'}:
raise
exception = socket_error
except httplib2.ServerNotFoundError as server_not_found_error:
exception = server_not_found_error
if exception:
if retry_num == num_retries:
raise exception
else:
continue
if not _should_retry_response(resp.status, content):
break
return resp, content
class MediaUploadProgress(object):
"""Status of a resumable upload."""
def __init__(self, resumable_progress, total_size):
"""Constructor.
Args:
resumable_progress: int, bytes sent so far.
total_size: int, total bytes in complete upload, or None if the total
upload size isn't known ahead of time.
"""
self.resumable_progress = resumable_progress
self.total_size = total_size
def progress(self):
"""Percent of upload completed, as a float.
Returns:
the percentage complete as a float, returning 0.0 if the total size of
the upload is unknown.
"""
if self.total_size is not None and self.total_size != 0:
return float(self.resumable_progress) / float(self.total_size)
else:
return 0.0
class MediaDownloadProgress(object):
"""Status of a resumable download."""
def __init__(self, resumable_progress, total_size):
"""Constructor.
Args:
resumable_progress: int, bytes received so far.
total_size: int, total bytes in complete download.
"""
self.resumable_progress = resumable_progress
self.total_size = total_size
def progress(self):
"""Percent of download completed, as a float.
Returns:
the percentage complete as a float, returning 0.0 if the total size of
the download is unknown.
"""
if self.total_size is not None and self.total_size != 0:
return float(self.resumable_progress) / float(self.total_size)
else:
return 0.0
class MediaUpload(object):
"""Describes a media object to upload.
Base class that defines the interface of MediaUpload subclasses.
Note that subclasses of MediaUpload may allow you to control the chunksize
when uploading a media object. It is important to keep the size of the chunk
as large as possible to keep the upload efficient. Other factors may influence
the size of the chunk you use, particularly if you are working in an
environment where individual HTTP requests may have a hardcoded time limit,
such as under certain classes of requests under Google App Engine.
Streams are io.Base compatible objects that support seek(). Some MediaUpload
subclasses support using streams directly to upload data. Support for
streaming may be indicated by a MediaUpload sub-class and if appropriate for a
platform that stream will be used for uploading the media object. The support
for streaming is indicated by has_stream() returning True. The stream() method
should return an io.Base object that supports seek(). On platforms where the
underlying httplib module supports streaming, for example Python 2.6 and
later, the stream will be passed into the http library which will result in
less memory being used and possibly faster uploads.
If you need to upload media that can't be uploaded using any of the existing
MediaUpload sub-class then you can sub-class MediaUpload for your particular
needs.
"""
def chunksize(self):
"""Chunk size for resumable uploads.
Returns:
Chunk size in bytes.
"""
raise NotImplementedError()
def mimetype(self):
"""Mime type of the body.
Returns:
Mime type.
"""
return 'application/octet-stream'
def size(self):
"""Size of upload.
Returns:
Size of the body, or None of the size is unknown.
"""
return None
def resumable(self):
"""Whether this upload is resumable.
Returns:
True if resumable upload or False.
"""
return False
def getbytes(self, begin, end):
"""Get bytes from the media.
Args:
begin: int, offset from beginning of file.
length: int, number of bytes to read, starting at begin.
Returns:
A string of bytes read. May be shorter than length if EOF was reached
first.
"""
raise NotImplementedError()
def has_stream(self):
"""Does the underlying upload support a streaming interface.
Streaming means it is an io.IOBase subclass that supports seek, i.e.
seekable() returns True.
Returns:
True if the call to stream() will return an instance of a seekable io.Base
subclass.
"""
return False
def stream(self):
"""A stream interface to the data being uploaded.
Returns:
The returned value is an io.IOBase subclass that supports seek, i.e.
seekable() returns True.
"""
raise NotImplementedError()
@util.positional(1)
def _to_json(self, strip=None):
"""Utility function for creating a JSON representation of a MediaUpload.
Args:
strip: array, An array of names of members to not include in the JSON.
Returns:
string, a JSON representation of this instance, suitable to pass to
from_json().
"""
t = type(self)
d = copy.copy(self.__dict__)
if strip is not None:
for member in strip:
del d[member]
d['_class'] = t.__name__
d['_module'] = t.__module__
return json.dumps(d)
def to_json(self):
"""Create a JSON representation of an instance of MediaUpload.
Returns:
string, a JSON representation of this instance, suitable to pass to
from_json().
"""
return self._to_json()
@classmethod
def new_from_json(cls, s):
"""Utility class method to instantiate a MediaUpload subclass from a JSON
representation produced by to_json().
Args:
s: string, JSON from to_json().
Returns:
An instance of the subclass of MediaUpload that was serialized with
to_json().
"""
data = json.loads(s)
# Find and call the right classmethod from_json() to restore the object.
module = data['_module']
m = __import__(module, fromlist=module.split('.')[:-1])
kls = getattr(m, data['_class'])
from_json = getattr(kls, 'from_json')
return from_json(s)
class MediaIoBaseUpload(MediaUpload):
"""A MediaUpload for a io.Base objects.
Note that the Python file object is compatible with io.Base and can be used
with this class also.
fh = BytesIO('...Some data to upload...')
media = MediaIoBaseUpload(fh, mimetype='image/png',
chunksize=1024*1024, resumable=True)
farm.animals().insert(
id='cow',
name='cow.png',
media_body=media).execute()
Depending on the platform you are working on, you may pass -1 as the
chunksize, which indicates that the entire file should be uploaded in a single
request. If the underlying platform supports streams, such as Python 2.6 or
later, then this can be very efficient as it avoids multiple connections, and
also avoids loading the entire file into memory before sending it. Note that
Google App Engine has a 5MB limit on request size, so you should never set
your chunksize larger than 5MB, or to -1.
"""
@util.positional(3)
def __init__(self, fd, mimetype, chunksize=DEFAULT_CHUNK_SIZE,
resumable=False):
"""Constructor.
Args:
fd: io.Base or file object, The source of the bytes to upload. MUST be
opened in blocking mode, do not use streams opened in non-blocking mode.
The given stream must be seekable, that is, it must be able to call
seek() on fd.
mimetype: string, Mime-type of the file.
chunksize: int, File will be uploaded in chunks of this many bytes. Only
used if resumable=True. Pass in a value of -1 if the file is to be
uploaded as a single chunk. Note that Google App Engine has a 5MB limit
on request size, so you should never set your chunksize larger than 5MB,
or to -1.
resumable: bool, True if this is a resumable upload. False means upload
in a single request.
"""
super(MediaIoBaseUpload, self).__init__()
self._fd = fd
self._mimetype = mimetype
if not (chunksize == -1 or chunksize > 0):
raise InvalidChunkSizeError()
self._chunksize = chunksize
self._resumable = resumable
self._fd.seek(0, os.SEEK_END)
self._size = self._fd.tell()
def chunksize(self):
"""Chunk size for resumable uploads.
Returns:
Chunk size in bytes.
"""
return self._chunksize
def mimetype(self):
"""Mime type of the body.
Returns:
Mime type.
"""
return self._mimetype
def size(self):
"""Size of upload.
Returns:
Size of the body, or None of the size is unknown.
"""
return self._size
def resumable(self):
"""Whether this upload is resumable.
Returns:
True if resumable upload or False.
"""
return self._resumable
def getbytes(self, begin, length):
"""Get bytes from the media.
Args:
begin: int, offset from beginning of file.
length: int, number of bytes to read, starting at begin.
Returns:
A string of bytes read. May be shorted than length if EOF was reached
first.
"""
self._fd.seek(begin)
return self._fd.read(length)
def has_stream(self):
"""Does the underlying upload support a streaming interface.
Streaming means it is an io.IOBase subclass that supports seek, i.e.
seekable() returns True.
Returns:
True if the call to stream() will return an instance of a seekable io.Base
subclass.
"""
return True
def stream(self):
"""A stream interface to the data being uploaded.
Returns:
The returned value is an io.IOBase subclass that supports seek, i.e.
seekable() returns True.
"""
return self._fd
def to_json(self):
"""This upload type is not serializable."""
raise NotImplementedError('MediaIoBaseUpload is not serializable.')
class MediaFileUpload(MediaIoBaseUpload):
"""A MediaUpload for a file.
Construct a MediaFileUpload and pass as the media_body parameter of the
method. For example, if we had a service that allowed uploading images:
media = MediaFileUpload('cow.png', mimetype='image/png',
chunksize=1024*1024, resumable=True)
farm.animals().insert(
id='cow',
name='cow.png',
media_body=media).execute()
Depending on the platform you are working on, you may pass -1 as the
chunksize, which indicates that the entire file should be uploaded in a single
request. If the underlying platform supports streams, such as Python 2.6 or
later, then this can be very efficient as it avoids multiple connections, and
also avoids loading the entire file into memory before sending it. Note that
Google App Engine has a 5MB limit on request size, so you should never set
your chunksize larger than 5MB, or to -1.
"""
@util.positional(2)
def __init__(self, filename, mimetype=None, chunksize=DEFAULT_CHUNK_SIZE,
resumable=False):
"""Constructor.
Args:
filename: string, Name of the file.
mimetype: string, Mime-type of the file. If None then a mime-type will be
guessed from the file extension.
chunksize: int, File will be uploaded in chunks of this many bytes. Only
used if resumable=True. Pass in a value of -1 if the file is to be
uploaded in a single chunk. Note that Google App Engine has a 5MB limit
on request size, so you should never set your chunksize larger than 5MB,
or to -1.
resumable: bool, True if this is a resumable upload. False means upload
in a single request.
"""
self._filename = filename
fd = open(self._filename, 'rb')
if mimetype is None:
# No mimetype provided, make a guess.
mimetype, _ = mimetypes.guess_type(filename)
if mimetype is None:
# Guess failed, use octet-stream.
mimetype = 'application/octet-stream'
super(MediaFileUpload, self).__init__(fd, mimetype, chunksize=chunksize,
resumable=resumable)
def to_json(self):
"""Creating a JSON representation of an instance of MediaFileUpload.
Returns:
string, a JSON representation of this instance, suitable to pass to
from_json().
"""
return self._to_json(strip=['_fd'])
@staticmethod
def from_json(s):
d = json.loads(s)
return MediaFileUpload(d['_filename'], mimetype=d['_mimetype'],
chunksize=d['_chunksize'], resumable=d['_resumable'])
class MediaInMemoryUpload(MediaIoBaseUpload):
"""MediaUpload for a chunk of bytes.
DEPRECATED: Use MediaIoBaseUpload with either io.TextIOBase or StringIO for
the stream.
"""
@util.positional(2)
def __init__(self, body, mimetype='application/octet-stream',
chunksize=DEFAULT_CHUNK_SIZE, resumable=False):
"""Create a new MediaInMemoryUpload.
DEPRECATED: Use MediaIoBaseUpload with either io.TextIOBase or StringIO for
the stream.
Args:
body: string, Bytes of body content.
mimetype: string, Mime-type of the file or default of
'application/octet-stream'.
chunksize: int, File will be uploaded in chunks of this many bytes. Only
used if resumable=True.
resumable: bool, True if this is a resumable upload. False means upload
in a single request.
"""
fd = BytesIO(body)
super(MediaInMemoryUpload, self).__init__(fd, mimetype, chunksize=chunksize,
resumable=resumable)
class MediaIoBaseDownload(object):
""""Download media resources.
Note that the Python file object is compatible with io.Base and can be used
with this class also.
Example:
request = farms.animals().get_media(id='cow')
fh = io.FileIO('cow.png', mode='wb')
downloader = MediaIoBaseDownload(fh, request, chunksize=1024*1024)
done = False
while done is False:
status, done = downloader.next_chunk()
if status:
print "Download %d%%." % int(status.progress() * 100)
print "Download Complete!"
"""
@util.positional(3)
def __init__(self, fd, request, chunksize=DEFAULT_CHUNK_SIZE):
"""Constructor.
Args:
fd: io.Base or file object, The stream in which to write the downloaded
bytes.
request: googleapiclient.http.HttpRequest, the media request to perform in
chunks.
chunksize: int, File will be downloaded in chunks of this many bytes.
"""
self._fd = fd
self._request = request
self._uri = request.uri
self._chunksize = chunksize
self._progress = 0
self._total_size = None
self._done = False
# Stubs for testing.
self._sleep = time.sleep
self._rand = random.random
self._headers = {}
for k, v in six.iteritems(request.headers):
# allow users to supply custom headers by setting them on the request
# but strip out the ones that are set by default on requests generated by
# API methods like Drive's files().get(fileId=...)
if not k.lower() in ('accept', 'accept-encoding', 'user-agent'):
self._headers[k] = v
@util.positional(1)
def next_chunk(self, num_retries=0):
"""Get the next chunk of the download.
Args:
num_retries: Integer, number of times to retry with randomized
exponential backoff. If all retries fail, the raised HttpError
represents the last request. If zero (default), we attempt the
request only once.
Returns:
(status, done): (MediaDownloadProgress, boolean)
The value of 'done' will be True when the media has been fully
downloaded or the total size of the media is unknown.
Raises:
googleapiclient.errors.HttpError if the response was not a 2xx.
httplib2.HttpLib2Error if a transport error has occured.
"""
headers = self._headers.copy()
headers['range'] = 'bytes=%d-%d' % (
self._progress, self._progress + self._chunksize)
http = self._request.http
resp, content = _retry_request(
http, num_retries, 'media download', self._sleep, self._rand, self._uri,
'GET', headers=headers)
if resp.status in [200, 206]:
if 'content-location' in resp and resp['content-location'] != self._uri:
self._uri = resp['content-location']
self._progress += len(content)
self._fd.write(content)
if 'content-range' in resp:
content_range = resp['content-range']
length = content_range.rsplit('/', 1)[1]
self._total_size = int(length)
elif 'content-length' in resp:
self._total_size = int(resp['content-length'])
if self._total_size is None or self._progress == self._total_size:
self._done = True
return MediaDownloadProgress(self._progress, self._total_size), self._done
else:
raise HttpError(resp, content, uri=self._uri)
class _StreamSlice(object):
"""Truncated stream.
Takes a stream and presents a stream that is a slice of the original stream.
This is used when uploading media in chunks. In later versions of Python a
stream can be passed to httplib in place of the string of data to send. The
problem is that httplib just blindly reads to the end of the stream. This
wrapper presents a virtual stream that only reads to the end of the chunk.
"""
def __init__(self, stream, begin, chunksize):
"""Constructor.
Args:
stream: (io.Base, file object), the stream to wrap.
begin: int, the seek position the chunk begins at.
chunksize: int, the size of the chunk.
"""
self._stream = stream
self._begin = begin
self._chunksize = chunksize
self._stream.seek(begin)
def read(self, n=-1):
"""Read n bytes.
Args:
n, int, the number of bytes to read.
Returns:
A string of length 'n', or less if EOF is reached.
"""
# The data left available to read sits in [cur, end)
cur = self._stream.tell()
end = self._begin + self._chunksize
if n == -1 or cur + n > end:
n = end - cur
return self._stream.read(n)
class HttpRequest(object):
"""Encapsulates a single HTTP request."""
@util.positional(4)
def __init__(self, http, postproc, uri,
method='GET',
body=None,
headers=None,
methodId=None,
resumable=None):
"""Constructor for an HttpRequest.
Args:
http: httplib2.Http, the transport object to use to make a request
postproc: callable, called on the HTTP response and content to transform
it into a data object before returning, or raising an exception
on an error.
uri: string, the absolute URI to send the request to
method: string, the HTTP method to use
body: string, the request body of the HTTP request,
headers: dict, the HTTP request headers
methodId: string, a unique identifier for the API method being called.
resumable: MediaUpload, None if this is not a resumbale request.
"""
self.uri = uri
self.method = method
self.body = body
self.headers = headers or {}
self.methodId = methodId
self.http = http
self.postproc = postproc
self.resumable = resumable
self.response_callbacks = []
self._in_error_state = False
# The size of the non-media part of the request.
self.body_size = len(self.body or '')
# The resumable URI to send chunks to.
self.resumable_uri = None
# The bytes that have been uploaded.
self.resumable_progress = 0
# Stubs for testing.
self._rand = random.random
self._sleep = time.sleep
@util.positional(1)
def execute(self, http=None, num_retries=0):
"""Execute the request.
Args:
http: httplib2.Http, an http object to be used in place of the
one the HttpRequest request object was constructed with.
num_retries: Integer, number of times to retry with randomized
exponential backoff. If all retries fail, the raised HttpError
represents the last request. If zero (default), we attempt the
request only once.
Returns:
A deserialized object model of the response body as determined
by the postproc.
Raises:
googleapiclient.errors.HttpError if the response was not a 2xx.
httplib2.HttpLib2Error if a transport error has occured.
"""
if http is None:
http = self.http
if self.resumable:
body = None
while body is None:
_, body = self.next_chunk(http=http, num_retries=num_retries)
return body
# Non-resumable case.
if 'content-length' not in self.headers:
self.headers['content-length'] = str(self.body_size)
# If the request URI is too long then turn it into a POST request.
# Assume that a GET request never contains a request body.
if len(self.uri) > MAX_URI_LENGTH and self.method == 'GET':
self.method = 'POST'
self.headers['x-http-method-override'] = 'GET'
self.headers['content-type'] = 'application/x-www-form-urlencoded'
parsed = urlparse(self.uri)
self.uri = urlunparse(
(parsed.scheme, parsed.netloc, parsed.path, parsed.params, None,
None)
)
self.body = parsed.query
self.headers['content-length'] = str(len(self.body))
# Handle retries for server-side errors.
resp, content = _retry_request(
http, num_retries, 'request', self._sleep, self._rand, str(self.uri),
method=str(self.method), body=self.body, headers=self.headers)
for callback in self.response_callbacks:
callback(resp)
if resp.status >= 300:
raise HttpError(resp, content, uri=self.uri)
return self.postproc(resp, content)
@util.positional(2)
def add_response_callback(self, cb):
"""add_response_headers_callback
Args:
cb: Callback to be called on receiving the response headers, of signature:
def cb(resp):
# Where resp is an instance of httplib2.Response
"""
self.response_callbacks.append(cb)
@util.positional(1)
def next_chunk(self, http=None, num_retries=0):
"""Execute the next step of a resumable upload.
Can only be used if the method being executed supports media uploads and
the MediaUpload object passed in was flagged as using resumable upload.
Example:
media = MediaFileUpload('cow.png', mimetype='image/png',
chunksize=1000, resumable=True)
request = farm.animals().insert(
id='cow',
name='cow.png',
media_body=media)
response = None
while response is None:
status, response = request.next_chunk()
if status:
print "Upload %d%% complete." % int(status.progress() * 100)
Args:
http: httplib2.Http, an http object to be used in place of the
one the HttpRequest request object was constructed with.
num_retries: Integer, number of times to retry with randomized
exponential backoff. If all retries fail, the raised HttpError
represents the last request. If zero (default), we attempt the
request only once.
Returns:
(status, body): (ResumableMediaStatus, object)
The body will be None until the resumable media is fully uploaded.
Raises:
googleapiclient.errors.HttpError if the response was not a 2xx.
httplib2.HttpLib2Error if a transport error has occured.
"""
if http is None:
http = self.http
if self.resumable.size() is None:
size = '*'
else:
size = str(self.resumable.size())
if self.resumable_uri is None:
start_headers = copy.copy(self.headers)
start_headers['X-Upload-Content-Type'] = self.resumable.mimetype()
if size != '*':
start_headers['X-Upload-Content-Length'] = size
start_headers['content-length'] = str(self.body_size)
resp, content = _retry_request(
http, num_retries, 'resumable URI request', self._sleep, self._rand,
self.uri, method=self.method, body=self.body, headers=start_headers)
if resp.status == 200 and 'location' in resp:
self.resumable_uri = resp['location']
else:
raise ResumableUploadError(resp, content)
elif self._in_error_state:
# If we are in an error state then query the server for current state of
# the upload by sending an empty PUT and reading the 'range' header in
# the response.
headers = {
'Content-Range': 'bytes */%s' % size,
'content-length': '0'
}
resp, content = http.request(self.resumable_uri, 'PUT',
headers=headers)
status, body = self._process_response(resp, content)
if body:
# The upload was complete.
return (status, body)
if self.resumable.has_stream():
data = self.resumable.stream()
if self.resumable.chunksize() == -1:
data.seek(self.resumable_progress)
chunk_end = self.resumable.size() - self.resumable_progress - 1
else:
# Doing chunking with a stream, so wrap a slice of the stream.
data = _StreamSlice(data, self.resumable_progress,
self.resumable.chunksize())
chunk_end = min(
self.resumable_progress + self.resumable.chunksize() - 1,
self.resumable.size() - 1)
else:
data = self.resumable.getbytes(
self.resumable_progress, self.resumable.chunksize())
# A short read implies that we are at EOF, so finish the upload.
if len(data) < self.resumable.chunksize():
size = str(self.resumable_progress + len(data))
chunk_end = self.resumable_progress + len(data) - 1
headers = {
'Content-Range': 'bytes %d-%d/%s' % (
self.resumable_progress, chunk_end, size),
# Must set the content-length header here because httplib can't
# calculate the size when working with _StreamSlice.
'Content-Length': str(chunk_end - self.resumable_progress + 1)
}
for retry_num in range(num_retries + 1):
if retry_num > 0:
self._sleep(self._rand() * 2**retry_num)
LOGGER.warning(
'Retry #%d for media upload: %s %s, following status: %d'
% (retry_num, self.method, self.uri, resp.status))
try:
resp, content = http.request(self.resumable_uri, method='PUT',
body=data,
headers=headers)
except:
self._in_error_state = True
raise
if not _should_retry_response(resp.status, content):
break
return self._process_response(resp, content)
def _process_response(self, resp, content):
"""Process the response from a single chunk upload.
Args:
resp: httplib2.Response, the response object.
content: string, the content of the response.
Returns:
(status, body): (ResumableMediaStatus, object)
The body will be None until the resumable media is fully uploaded.