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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
|
# -*- coding: utf-8 -*-
"""
werkzeug.http
~~~~~~~~~~~~~
Werkzeug comes with a bunch of utilities that help Werkzeug to deal with
HTTP data. Most of the classes and functions provided by this module are
used by the wrappers, but they are useful on their own, too, especially if
the response and request objects are not used.
This covers some of the more HTTP centric features of WSGI, some other
utilities such as cookie handling are documented in the `werkzeug.utils`
module.
:copyright: 2007 Pallets
:license: BSD-3-Clause
"""
import base64
import re
import warnings
from datetime import datetime
from datetime import timedelta
from hashlib import md5
from time import gmtime
from time import time
from ._compat import integer_types
from ._compat import iteritems
from ._compat import PY2
from ._compat import string_types
from ._compat import text_type
from ._compat import to_bytes
from ._compat import to_unicode
from ._compat import try_coerce_native
from ._internal import _cookie_parse_impl
from ._internal import _cookie_quote
from ._internal import _make_cookie_domain
try:
from email.utils import parsedate_tz
except ImportError:
from email.Utils import parsedate_tz
try:
from urllib.request import parse_http_list as _parse_list_header
from urllib.parse import unquote_to_bytes as _unquote
except ImportError:
from urllib2 import parse_http_list as _parse_list_header
from urllib2 import unquote as _unquote
_cookie_charset = "latin1"
_basic_auth_charset = "utf-8"
# for explanation of "media-range", etc. see Sections 5.3.{1,2} of RFC 7231
_accept_re = re.compile(
r"""
( # media-range capturing-parenthesis
[^\s;,]+ # type/subtype
(?:[ \t]*;[ \t]* # ";"
(?: # parameter non-capturing-parenthesis
[^\s;,q][^\s;,]* # token that doesn't start with "q"
| # or
q[^\s;,=][^\s;,]* # token that is more than just "q"
)
)* # zero or more parameters
) # end of media-range
(?:[ \t]*;[ \t]*q= # weight is a "q" parameter
(\d*(?:\.\d+)?) # qvalue capturing-parentheses
[^,]* # "extension" accept params: who cares?
)? # accept params are optional
""",
re.VERBOSE,
)
_token_chars = frozenset(
"!#$%&'*+-.0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ^_`abcdefghijklmnopqrstuvwxyz|~"
)
_etag_re = re.compile(r'([Ww]/)?(?:"(.*?)"|(.*?))(?:\s*,\s*|$)')
_unsafe_header_chars = set('()<>@,;:"/[]?={} \t')
_option_header_piece_re = re.compile(
r"""
;\s*,?\s* # newlines were replaced with commas
(?P<key>
"[^"\\]*(?:\\.[^"\\]*)*" # quoted string
|
[^\s;,=*]+ # token
)
(?:\*(?P<count>\d+))? # *1, optional continuation index
\s*
(?: # optionally followed by =value
(?: # equals sign, possibly with encoding
\*\s*=\s* # * indicates extended notation
(?: # optional encoding
(?P<encoding>[^\s]+?)
'(?P<language>[^\s]*?)'
)?
|
=\s* # basic notation
)
(?P<value>
"[^"\\]*(?:\\.[^"\\]*)*" # quoted string
|
[^;,]+ # token
)?
)?
\s*
""",
flags=re.VERBOSE,
)
_option_header_start_mime_type = re.compile(r",\s*([^;,\s]+)([;,]\s*.+)?")
_entity_headers = frozenset(
[
"allow",
"content-encoding",
"content-language",
"content-length",
"content-location",
"content-md5",
"content-range",
"content-type",
"expires",
"last-modified",
]
)
_hop_by_hop_headers = frozenset(
[
"connection",
"keep-alive",
"proxy-authenticate",
"proxy-authorization",
"te",
"trailer",
"transfer-encoding",
"upgrade",
]
)
HTTP_STATUS_CODES = {
100: "Continue",
101: "Switching Protocols",
102: "Processing",
200: "OK",
201: "Created",
202: "Accepted",
203: "Non Authoritative Information",
204: "No Content",
205: "Reset Content",
206: "Partial Content",
207: "Multi Status",
226: "IM Used", # see RFC 3229
300: "Multiple Choices",
301: "Moved Permanently",
302: "Found",
303: "See Other",
304: "Not Modified",
305: "Use Proxy",
307: "Temporary Redirect",
308: "Permanent Redirect",
400: "Bad Request",
401: "Unauthorized",
402: "Payment Required", # unused
403: "Forbidden",
404: "Not Found",
405: "Method Not Allowed",
406: "Not Acceptable",
407: "Proxy Authentication Required",
408: "Request Timeout",
409: "Conflict",
410: "Gone",
411: "Length Required",
412: "Precondition Failed",
413: "Request Entity Too Large",
414: "Request URI Too Long",
415: "Unsupported Media Type",
416: "Requested Range Not Satisfiable",
417: "Expectation Failed",
418: "I'm a teapot", # see RFC 2324
421: "Misdirected Request", # see RFC 7540
422: "Unprocessable Entity",
423: "Locked",
424: "Failed Dependency",
426: "Upgrade Required",
428: "Precondition Required", # see RFC 6585
429: "Too Many Requests",
431: "Request Header Fields Too Large",
449: "Retry With", # proprietary MS extension
451: "Unavailable For Legal Reasons",
500: "Internal Server Error",
501: "Not Implemented",
502: "Bad Gateway",
503: "Service Unavailable",
504: "Gateway Timeout",
505: "HTTP Version Not Supported",
507: "Insufficient Storage",
510: "Not Extended",
}
def wsgi_to_bytes(data):
"""coerce wsgi unicode represented bytes to real ones"""
if isinstance(data, bytes):
return data
return data.encode("latin1") # XXX: utf8 fallback?
def bytes_to_wsgi(data):
assert isinstance(data, bytes), "data must be bytes"
if isinstance(data, str):
return data
else:
return data.decode("latin1")
def quote_header_value(value, extra_chars="", allow_token=True):
"""Quote a header value if necessary.
.. versionadded:: 0.5
:param value: the value to quote.
:param extra_chars: a list of extra characters to skip quoting.
:param allow_token: if this is enabled token values are returned
unchanged.
"""
if isinstance(value, bytes):
value = bytes_to_wsgi(value)
value = str(value)
if allow_token:
token_chars = _token_chars | set(extra_chars)
if set(value).issubset(token_chars):
return value
return '"%s"' % value.replace("\\", "\\\\").replace('"', '\\"')
def unquote_header_value(value, is_filename=False):
r"""Unquotes a header value. (Reversal of :func:`quote_header_value`).
This does not use the real unquoting but what browsers are actually
using for quoting.
.. versionadded:: 0.5
:param value: the header value to unquote.
"""
if value and value[0] == value[-1] == '"':
# this is not the real unquoting, but fixing this so that the
# RFC is met will result in bugs with internet explorer and
# probably some other browsers as well. IE for example is
# uploading files with "C:\foo\bar.txt" as filename
value = value[1:-1]
# if this is a filename and the starting characters look like
# a UNC path, then just return the value without quotes. Using the
# replace sequence below on a UNC path has the effect of turning
# the leading double slash into a single slash and then
# _fix_ie_filename() doesn't work correctly. See #458.
if not is_filename or value[:2] != "\\\\":
return value.replace("\\\\", "\\").replace('\\"', '"')
return value
def dump_options_header(header, options):
"""The reverse function to :func:`parse_options_header`.
:param header: the header to dump
:param options: a dict of options to append.
"""
segments = []
if header is not None:
segments.append(header)
for key, value in iteritems(options):
if value is None:
segments.append(key)
else:
segments.append("%s=%s" % (key, quote_header_value(value)))
return "; ".join(segments)
def dump_header(iterable, allow_token=True):
"""Dump an HTTP header again. This is the reversal of
:func:`parse_list_header`, :func:`parse_set_header` and
:func:`parse_dict_header`. This also quotes strings that include an
equals sign unless you pass it as dict of key, value pairs.
>>> dump_header({'foo': 'bar baz'})
'foo="bar baz"'
>>> dump_header(('foo', 'bar baz'))
'foo, "bar baz"'
:param iterable: the iterable or dict of values to quote.
:param allow_token: if set to `False` tokens as values are disallowed.
See :func:`quote_header_value` for more details.
"""
if isinstance(iterable, dict):
items = []
for key, value in iteritems(iterable):
if value is None:
items.append(key)
else:
items.append(
"%s=%s" % (key, quote_header_value(value, allow_token=allow_token))
)
else:
items = [quote_header_value(x, allow_token=allow_token) for x in iterable]
return ", ".join(items)
def parse_list_header(value):
"""Parse lists as described by RFC 2068 Section 2.
In particular, parse comma-separated lists where the elements of
the list may include quoted-strings. A quoted-string could
contain a comma. A non-quoted string could have quotes in the
middle. Quotes are removed automatically after parsing.
It basically works like :func:`parse_set_header` just that items
may appear multiple times and case sensitivity is preserved.
The return value is a standard :class:`list`:
>>> parse_list_header('token, "quoted value"')
['token', 'quoted value']
To create a header from the :class:`list` again, use the
:func:`dump_header` function.
:param value: a string with a list header.
:return: :class:`list`
"""
result = []
for item in _parse_list_header(value):
if item[:1] == item[-1:] == '"':
item = unquote_header_value(item[1:-1])
result.append(item)
return result
def parse_dict_header(value, cls=dict):
"""Parse lists of key, value pairs as described by RFC 2068 Section 2 and
convert them into a python dict (or any other mapping object created from
the type with a dict like interface provided by the `cls` argument):
>>> d = parse_dict_header('foo="is a fish", bar="as well"')
>>> type(d) is dict
True
>>> sorted(d.items())
[('bar', 'as well'), ('foo', 'is a fish')]
If there is no value for a key it will be `None`:
>>> parse_dict_header('key_without_value')
{'key_without_value': None}
To create a header from the :class:`dict` again, use the
:func:`dump_header` function.
.. versionchanged:: 0.9
Added support for `cls` argument.
:param value: a string with a dict header.
:param cls: callable to use for storage of parsed results.
:return: an instance of `cls`
"""
result = cls()
if not isinstance(value, text_type):
# XXX: validate
value = bytes_to_wsgi(value)
for item in _parse_list_header(value):
if "=" not in item:
result[item] = None
continue
name, value = item.split("=", 1)
if value[:1] == value[-1:] == '"':
value = unquote_header_value(value[1:-1])
result[name] = value
return result
def parse_options_header(value, multiple=False):
"""Parse a ``Content-Type`` like header into a tuple with the content
type and the options:
>>> parse_options_header('text/html; charset=utf8')
('text/html', {'charset': 'utf8'})
This should not be used to parse ``Cache-Control`` like headers that use
a slightly different format. For these headers use the
:func:`parse_dict_header` function.
.. versionchanged:: 0.15
:rfc:`2231` parameter continuations are handled.
.. versionadded:: 0.5
:param value: the header to parse.
:param multiple: Whether try to parse and return multiple MIME types
:return: (mimetype, options) or (mimetype, options, mimetype, options, …)
if multiple=True
"""
if not value:
return "", {}
result = []
value = "," + value.replace("\n", ",")
while value:
match = _option_header_start_mime_type.match(value)
if not match:
break
result.append(match.group(1)) # mimetype
options = {}
# Parse options
rest = match.group(2)
continued_encoding = None
while rest:
optmatch = _option_header_piece_re.match(rest)
if not optmatch:
break
option, count, encoding, language, option_value = optmatch.groups()
# Continuations don't have to supply the encoding after the
# first line. If we're in a continuation, track the current
# encoding to use for subsequent lines. Reset it when the
# continuation ends.
if not count:
continued_encoding = None
else:
if not encoding:
encoding = continued_encoding
continued_encoding = encoding
option = unquote_header_value(option)
if option_value is not None:
option_value = unquote_header_value(option_value, option == "filename")
if encoding is not None:
option_value = _unquote(option_value).decode(encoding)
if count:
# Continuations append to the existing value. For
# simplicity, this ignores the possibility of
# out-of-order indices, which shouldn't happen anyway.
options[option] = options.get(option, "") + option_value
else:
options[option] = option_value
rest = rest[optmatch.end() :]
result.append(options)
if multiple is False:
return tuple(result)
value = rest
return tuple(result) if result else ("", {})
def parse_accept_header(value, cls=None):
"""Parses an HTTP Accept-* header. This does not implement a complete
valid algorithm but one that supports at least value and quality
extraction.
Returns a new :class:`Accept` object (basically a list of ``(value, quality)``
tuples sorted by the quality with some additional accessor methods).
The second parameter can be a subclass of :class:`Accept` that is created
with the parsed values and returned.
:param value: the accept header string to be parsed.
:param cls: the wrapper class for the return value (can be
:class:`Accept` or a subclass thereof)
:return: an instance of `cls`.
"""
if cls is None:
cls = Accept
if not value:
return cls(None)
result = []
for match in _accept_re.finditer(value):
quality = match.group(2)
if not quality:
quality = 1
else:
quality = max(min(float(quality), 1), 0)
result.append((match.group(1), quality))
return cls(result)
def parse_cache_control_header(value, on_update=None, cls=None):
"""Parse a cache control header. The RFC differs between response and
request cache control, this method does not. It's your responsibility
to not use the wrong control statements.
.. versionadded:: 0.5
The `cls` was added. If not specified an immutable
:class:`~werkzeug.datastructures.RequestCacheControl` is returned.
:param value: a cache control header to be parsed.
:param on_update: an optional callable that is called every time a value
on the :class:`~werkzeug.datastructures.CacheControl`
object is changed.
:param cls: the class for the returned object. By default
:class:`~werkzeug.datastructures.RequestCacheControl` is used.
:return: a `cls` object.
"""
if cls is None:
cls = RequestCacheControl
if not value:
return cls(None, on_update)
return cls(parse_dict_header(value), on_update)
def parse_set_header(value, on_update=None):
"""Parse a set-like header and return a
:class:`~werkzeug.datastructures.HeaderSet` object:
>>> hs = parse_set_header('token, "quoted value"')
The return value is an object that treats the items case-insensitively
and keeps the order of the items:
>>> 'TOKEN' in hs
True
>>> hs.index('quoted value')
1
>>> hs
HeaderSet(['token', 'quoted value'])
To create a header from the :class:`HeaderSet` again, use the
:func:`dump_header` function.
:param value: a set header to be parsed.
:param on_update: an optional callable that is called every time a
value on the :class:`~werkzeug.datastructures.HeaderSet`
object is changed.
:return: a :class:`~werkzeug.datastructures.HeaderSet`
"""
if not value:
return HeaderSet(None, on_update)
return HeaderSet(parse_list_header(value), on_update)
def parse_authorization_header(value):
"""Parse an HTTP basic/digest authorization header transmitted by the web
browser. The return value is either `None` if the header was invalid or
not given, otherwise an :class:`~werkzeug.datastructures.Authorization`
object.
:param value: the authorization header to parse.
:return: a :class:`~werkzeug.datastructures.Authorization` object or `None`.
"""
if not value:
return
value = wsgi_to_bytes(value)
try:
auth_type, auth_info = value.split(None, 1)
auth_type = auth_type.lower()
except ValueError:
return
if auth_type == b"basic":
try:
username, password = base64.b64decode(auth_info).split(b":", 1)
except Exception:
return
return Authorization(
"basic",
{
"username": to_unicode(username, _basic_auth_charset),
"password": to_unicode(password, _basic_auth_charset),
},
)
elif auth_type == b"digest":
auth_map = parse_dict_header(auth_info)
for key in "username", "realm", "nonce", "uri", "response":
if key not in auth_map:
return
if "qop" in auth_map:
if not auth_map.get("nc") or not auth_map.get("cnonce"):
return
return Authorization("digest", auth_map)
def parse_www_authenticate_header(value, on_update=None):
"""Parse an HTTP WWW-Authenticate header into a
:class:`~werkzeug.datastructures.WWWAuthenticate` object.
:param value: a WWW-Authenticate header to parse.
:param on_update: an optional callable that is called every time a value
on the :class:`~werkzeug.datastructures.WWWAuthenticate`
object is changed.
:return: a :class:`~werkzeug.datastructures.WWWAuthenticate` object.
"""
if not value:
return WWWAuthenticate(on_update=on_update)
try:
auth_type, auth_info = value.split(None, 1)
auth_type = auth_type.lower()
except (ValueError, AttributeError):
return WWWAuthenticate(value.strip().lower(), on_update=on_update)
return WWWAuthenticate(auth_type, parse_dict_header(auth_info), on_update)
def parse_if_range_header(value):
"""Parses an if-range header which can be an etag or a date. Returns
a :class:`~werkzeug.datastructures.IfRange` object.
.. versionadded:: 0.7
"""
if not value:
return IfRange()
date = parse_date(value)
if date is not None:
return IfRange(date=date)
# drop weakness information
return IfRange(unquote_etag(value)[0])
def parse_range_header(value, make_inclusive=True):
"""Parses a range header into a :class:`~werkzeug.datastructures.Range`
object. If the header is missing or malformed `None` is returned.
`ranges` is a list of ``(start, stop)`` tuples where the ranges are
non-inclusive.
.. versionadded:: 0.7
"""
if not value or "=" not in value:
return None
ranges = []
last_end = 0
units, rng = value.split("=", 1)
units = units.strip().lower()
for item in rng.split(","):
item = item.strip()
if "-" not in item:
return None
if item.startswith("-"):
if last_end < 0:
return None
try:
begin = int(item)
except ValueError:
return None
end = None
last_end = -1
elif "-" in item:
begin, end = item.split("-", 1)
begin = begin.strip()
end = end.strip()
if not begin.isdigit():
return None
begin = int(begin)
if begin < last_end or last_end < 0:
return None
if end:
if not end.isdigit():
return None
end = int(end) + 1
if begin >= end:
return None
else:
end = None
last_end = end
ranges.append((begin, end))
return Range(units, ranges)
def parse_content_range_header(value, on_update=None):
"""Parses a range header into a
:class:`~werkzeug.datastructures.ContentRange` object or `None` if
parsing is not possible.
.. versionadded:: 0.7
:param value: a content range header to be parsed.
:param on_update: an optional callable that is called every time a value
on the :class:`~werkzeug.datastructures.ContentRange`
object is changed.
"""
if value is None:
return None
try:
units, rangedef = (value or "").strip().split(None, 1)
except ValueError:
return None
if "/" not in rangedef:
return None
rng, length = rangedef.split("/", 1)
if length == "*":
length = None
elif length.isdigit():
length = int(length)
else:
return None
if rng == "*":
return ContentRange(units, None, None, length, on_update=on_update)
elif "-" not in rng:
return None
start, stop = rng.split("-", 1)
try:
start = int(start)
stop = int(stop) + 1
except ValueError:
return None
if is_byte_range_valid(start, stop, length):
return ContentRange(units, start, stop, length, on_update=on_update)
def quote_etag(etag, weak=False):
"""Quote an etag.
:param etag: the etag to quote.
:param weak: set to `True` to tag it "weak".
"""
if '"' in etag:
raise ValueError("invalid etag")
etag = '"%s"' % etag
if weak:
etag = "W/" + etag
return etag
def unquote_etag(etag):
"""Unquote a single etag:
>>> unquote_etag('W/"bar"')
('bar', True)
>>> unquote_etag('"bar"')
('bar', False)
:param etag: the etag identifier to unquote.
:return: a ``(etag, weak)`` tuple.
"""
if not etag:
return None, None
etag = etag.strip()
weak = False
if etag.startswith(("W/", "w/")):
weak = True
etag = etag[2:]
if etag[:1] == etag[-1:] == '"':
etag = etag[1:-1]
return etag, weak
def parse_etags(value):
"""Parse an etag header.
:param value: the tag header to parse
:return: an :class:`~werkzeug.datastructures.ETags` object.
"""
if not value:
return ETags()
strong = []
weak = []
end = len(value)
pos = 0
while pos < end:
match = _etag_re.match(value, pos)
if match is None:
break
is_weak, quoted, raw = match.groups()
if raw == "*":
return ETags(star_tag=True)
elif quoted:
raw = quoted
if is_weak:
weak.append(raw)
else:
strong.append(raw)
pos = match.end()
return ETags(strong, weak)
def generate_etag(data):
"""Generate an etag for some data."""
return md5(data).hexdigest()
def parse_date(value):
"""Parse one of the following date formats into a datetime object:
.. sourcecode:: text
Sun, 06 Nov 1994 08:49:37 GMT ; RFC 822, updated by RFC 1123
Sunday, 06-Nov-94 08:49:37 GMT ; RFC 850, obsoleted by RFC 1036
Sun Nov 6 08:49:37 1994 ; ANSI C's asctime() format
If parsing fails the return value is `None`.
:param value: a string with a supported date format.
:return: a :class:`datetime.datetime` object.
"""
if value:
t = parsedate_tz(value.strip())
if t is not None:
try:
year = t[0]
# unfortunately that function does not tell us if two digit
# years were part of the string, or if they were prefixed
# with two zeroes. So what we do is to assume that 69-99
# refer to 1900, and everything below to 2000
if year >= 0 and year <= 68:
year += 2000
elif year >= 69 and year <= 99:
year += 1900
return datetime(*((year,) + t[1:7])) - timedelta(seconds=t[-1] or 0)
except (ValueError, OverflowError):
return None
def _dump_date(d, delim):
"""Used for `http_date` and `cookie_date`."""
if d is None:
d = gmtime()
elif isinstance(d, datetime):
d = d.utctimetuple()
elif isinstance(d, (integer_types, float)):
d = gmtime(d)
return "%s, %02d%s%s%s%s %02d:%02d:%02d GMT" % (
("Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun")[d.tm_wday],
d.tm_mday,
delim,
(
"Jan",
"Feb",
"Mar",
"Apr",
"May",
"Jun",
"Jul",
"Aug",
"Sep",
"Oct",
"Nov",
"Dec",
)[d.tm_mon - 1],
delim,
str(d.tm_year),
d.tm_hour,
d.tm_min,
d.tm_sec,
)
def cookie_date(expires=None):
"""Formats the time to ensure compatibility with Netscape's cookie
standard.
Accepts a floating point number expressed in seconds since the epoch in, a
datetime object or a timetuple. All times in UTC. The :func:`parse_date`
function can be used to parse such a date.
Outputs a string in the format ``Wdy, DD-Mon-YYYY HH:MM:SS GMT``.
:param expires: If provided that date is used, otherwise the current.
"""
return _dump_date(expires, "-")
def http_date(timestamp=None):
"""Formats the time to match the RFC1123 date format.
Accepts a floating point number expressed in seconds since the epoch in, a
datetime object or a timetuple. All times in UTC. The :func:`parse_date`
function can be used to parse such a date.
Outputs a string in the format ``Wdy, DD Mon YYYY HH:MM:SS GMT``.
:param timestamp: If provided that date is used, otherwise the current.
"""
return _dump_date(timestamp, " ")
def parse_age(value=None):
"""Parses a base-10 integer count of seconds into a timedelta.
If parsing fails, the return value is `None`.
:param value: a string consisting of an integer represented in base-10
:return: a :class:`datetime.timedelta` object or `None`.
"""
if not value:
return None
try:
seconds = int(value)
except ValueError:
return None
if seconds < 0:
return None
try:
return timedelta(seconds=seconds)
except OverflowError:
return None
def dump_age(age=None):
"""Formats the duration as a base-10 integer.
:param age: should be an integer number of seconds,
a :class:`datetime.timedelta` object, or,
if the age is unknown, `None` (default).
"""
if age is None:
return
if isinstance(age, timedelta):
# do the equivalent of Python 2.7's timedelta.total_seconds(),
# but disregarding fractional seconds
age = age.seconds + (age.days * 24 * 3600)
age = int(age)
if age < 0:
raise ValueError("age cannot be negative")
return str(age)
def is_resource_modified(
environ, etag=None, data=None, last_modified=None, ignore_if_range=True
):
"""Convenience method for conditional requests.
:param environ: the WSGI environment of the request to be checked.
:param etag: the etag for the response for comparison.
:param data: or alternatively the data of the response to automatically
generate an etag using :func:`generate_etag`.
:param last_modified: an optional date of the last modification.
:param ignore_if_range: If `False`, `If-Range` header will be taken into
account.
:return: `True` if the resource was modified, otherwise `False`.
"""
if etag is None and data is not None:
etag = generate_etag(data)
elif data is not None:
raise TypeError("both data and etag given")
if environ["REQUEST_METHOD"] not in ("GET", "HEAD"):
return False
unmodified = False
if isinstance(last_modified, string_types):
last_modified = parse_date(last_modified)
# ensure that microsecond is zero because the HTTP spec does not transmit
# that either and we might have some false positives. See issue #39
if last_modified is not None:
last_modified = last_modified.replace(microsecond=0)
if_range = None
if not ignore_if_range and "HTTP_RANGE" in environ:
# https://tools.ietf.org/html/rfc7233#section-3.2
# A server MUST ignore an If-Range header field received in a request
# that does not contain a Range header field.
if_range = parse_if_range_header(environ.get("HTTP_IF_RANGE"))
if if_range is not None and if_range.date is not None:
modified_since = if_range.date
else:
modified_since = parse_date(environ.get("HTTP_IF_MODIFIED_SINCE"))
if modified_since and last_modified and last_modified <= modified_since:
unmodified = True
if etag:
etag, _ = unquote_etag(etag)
if if_range is not None and if_range.etag is not None:
unmodified = parse_etags(if_range.etag).contains(etag)
else:
if_none_match = parse_etags(environ.get("HTTP_IF_NONE_MATCH"))
if if_none_match:
# https://tools.ietf.org/html/rfc7232#section-3.2
# "A recipient MUST use the weak comparison function when comparing
# entity-tags for If-None-Match"
unmodified = if_none_match.contains_weak(etag)
# https://tools.ietf.org/html/rfc7232#section-3.1
# "Origin server MUST use the strong comparison function when
# comparing entity-tags for If-Match"
if_match = parse_etags(environ.get("HTTP_IF_MATCH"))
if if_match:
unmodified = not if_match.is_strong(etag)
return not unmodified
def remove_entity_headers(headers, allowed=("expires", "content-location")):
"""Remove all entity headers from a list or :class:`Headers` object. This
operation works in-place. `Expires` and `Content-Location` headers are
by default not removed. The reason for this is :rfc:`2616` section
10.3.5 which specifies some entity headers that should be sent.
.. versionchanged:: 0.5
added `allowed` parameter.
:param headers: a list or :class:`Headers` object.
:param allowed: a list of headers that should still be allowed even though
they are entity headers.
"""
allowed = set(x.lower() for x in allowed)
headers[:] = [
(key, value)
for key, value in headers
if not is_entity_header(key) or key.lower() in allowed
]
def remove_hop_by_hop_headers(headers):
"""Remove all HTTP/1.1 "Hop-by-Hop" headers from a list or
:class:`Headers` object. This operation works in-place.
.. versionadded:: 0.5
:param headers: a list or :class:`Headers` object.
"""
headers[:] = [
(key, value) for key, value in headers if not is_hop_by_hop_header(key)
]
def is_entity_header(header):
"""Check if a header is an entity header.
.. versionadded:: 0.5
:param header: the header to test.
:return: `True` if it's an entity header, `False` otherwise.
"""
return header.lower() in _entity_headers
def is_hop_by_hop_header(header):
"""Check if a header is an HTTP/1.1 "Hop-by-Hop" header.
.. versionadded:: 0.5
:param header: the header to test.
:return: `True` if it's an HTTP/1.1 "Hop-by-Hop" header, `False` otherwise.
"""
return header.lower() in _hop_by_hop_headers
def parse_cookie(header, charset="utf-8", errors="replace", cls=None):
"""Parse a cookie. Either from a string or WSGI environ.
Per default encoding errors are ignored. If you want a different behavior
you can set `errors` to ``'replace'`` or ``'strict'``. In strict mode a
:exc:`HTTPUnicodeError` is raised.
.. versionchanged:: 0.5
This function now returns a :class:`TypeConversionDict` instead of a
regular dict. The `cls` parameter was added.
:param header: the header to be used to parse the cookie. Alternatively
this can be a WSGI environment.
:param charset: the charset for the cookie values.
:param errors: the error behavior for the charset decoding.
:param cls: an optional dict class to use. If this is not specified
or `None` the default :class:`TypeConversionDict` is
used.
"""
if isinstance(header, dict):
header = header.get("HTTP_COOKIE", "")
elif header is None:
header = ""
# If the value is an unicode string it's mangled through latin1. This
# is done because on PEP 3333 on Python 3 all headers are assumed latin1
# which however is incorrect for cookies, which are sent in page encoding.
# As a result we
if isinstance(header, text_type):
header = header.encode("latin1", "replace")
if cls is None:
cls = TypeConversionDict
def _parse_pairs():
for key, val in _cookie_parse_impl(header):
key = to_unicode(key, charset, errors, allow_none_charset=True)
if not key:
continue
val = to_unicode(val, charset, errors, allow_none_charset=True)
yield try_coerce_native(key), val
return cls(_parse_pairs())
def dump_cookie(
key,
value="",
max_age=None,
expires=None,
path="/",
domain=None,
secure=False,
httponly=False,
charset="utf-8",
sync_expires=True,
max_size=4093,
samesite=None,
):
"""Creates a new Set-Cookie header without the ``Set-Cookie`` prefix
The parameters are the same as in the cookie Morsel object in the
Python standard library but it accepts unicode data, too.
On Python 3 the return value of this function will be a unicode
string, on Python 2 it will be a native string. In both cases the
return value is usually restricted to ascii as the vast majority of
values are properly escaped, but that is no guarantee. If a unicode
string is returned it's tunneled through latin1 as required by
PEP 3333.
The return value is not ASCII safe if the key contains unicode
characters. This is technically against the specification but
happens in the wild. It's strongly recommended to not use
non-ASCII values for the keys.
:param max_age: should be a number of seconds, or `None` (default) if
the cookie should last only as long as the client's
browser session. Additionally `timedelta` objects
are accepted, too.
:param expires: should be a `datetime` object or unix timestamp.
:param path: limits the cookie to a given path, per default it will
span the whole domain.
:param domain: Use this if you want to set a cross-domain cookie. For
example, ``domain=".example.com"`` will set a cookie
that is readable by the domain ``www.example.com``,
``foo.example.com`` etc. Otherwise, a cookie will only
be readable by the domain that set it.
:param secure: The cookie will only be available via HTTPS
:param httponly: disallow JavaScript to access the cookie. This is an
extension to the cookie standard and probably not
supported by all browsers.
:param charset: the encoding for unicode values.
:param sync_expires: automatically set expires if max_age is defined
but expires not.
:param max_size: Warn if the final header value exceeds this size. The
default, 4093, should be safely `supported by most browsers
<cookie_>`_. Set to 0 to disable this check.
:param samesite: Limits the scope of the cookie such that it will only
be attached to requests if those requests are "same-site".
.. _`cookie`: http://browsercookielimits.squawky.net/
"""
key = to_bytes(key, charset)
value = to_bytes(value, charset)
if path is not None:
from .urls import iri_to_uri
path = iri_to_uri(path, charset)
domain = _make_cookie_domain(domain)
if isinstance(max_age, timedelta):
max_age = (max_age.days * 60 * 60 * 24) + max_age.seconds
if expires is not None:
if not isinstance(expires, string_types):
expires = cookie_date(expires)
elif max_age is not None and sync_expires:
expires = to_bytes(cookie_date(time() + max_age))
samesite = samesite.title() if samesite else None
if samesite not in ("Strict", "Lax", None):
raise ValueError("invalid SameSite value; must be 'Strict', 'Lax' or None")
buf = [key + b"=" + _cookie_quote(value)]
# XXX: In theory all of these parameters that are not marked with `None`
# should be quoted. Because stdlib did not quote it before I did not
# want to introduce quoting there now.
for k, v, q in (
(b"Domain", domain, True),
(b"Expires", expires, False),
(b"Max-Age", max_age, False),
(b"Secure", secure, None),
(b"HttpOnly", httponly, None),
(b"Path", path, False),
(b"SameSite", samesite, False),
):
if q is None:
if v:
buf.append(k)
continue
if v is None:
continue
tmp = bytearray(k)
if not isinstance(v, (bytes, bytearray)):
v = to_bytes(text_type(v), charset)
if q:
v = _cookie_quote(v)
tmp += b"=" + v
buf.append(bytes(tmp))
# The return value will be an incorrectly encoded latin1 header on
# Python 3 for consistency with the headers object and a bytestring
# on Python 2 because that's how the API makes more sense.
rv = b"; ".join(buf)
if not PY2:
rv = rv.decode("latin1")
# Warn if the final value of the cookie is less than the limit. If the
# cookie is too large, then it may be silently ignored, which can be quite
# hard to debug.
cookie_size = len(rv)
if max_size and cookie_size > max_size:
value_size = len(value)
warnings.warn(
'The "{key}" cookie is too large: the value was {value_size} bytes'
" but the header required {extra_size} extra bytes. The final size"
" was {cookie_size} bytes but the limit is {max_size} bytes."
" Browsers may silently ignore cookies larger than this.".format(
key=key,
value_size=value_size,
extra_size=cookie_size - value_size,
cookie_size=cookie_size,
max_size=max_size,
),
stacklevel=2,
)
return rv
def is_byte_range_valid(start, stop, length):
"""Checks if a given byte content range is valid for the given length.
.. versionadded:: 0.7
"""
if (start is None) != (stop is None):
return False
elif start is None:
return length is None or length >= 0
elif length is None:
return 0 <= start < stop
elif start >= stop:
return False
return 0 <= start < length
# circular dependencies
from .datastructures import Accept
from .datastructures import Authorization
from .datastructures import ContentRange
from .datastructures import ETags
from .datastructures import HeaderSet
from .datastructures import IfRange
from .datastructures import Range
from .datastructures import RequestCacheControl
from .datastructures import TypeConversionDict
from .datastructures import WWWAuthenticate
from werkzeug import _DeprecatedImportModule
_DeprecatedImportModule(
__name__,
{".datastructures": ["CharsetAccept", "Headers", "LanguageAccept", "MIMEAccept"]},
"Werkzeug 1.0",
)
del _DeprecatedImportModule
|