Web   ·   Wiki   ·   Activities   ·   Blog   ·   Lists   ·   Chat   ·   Meeting   ·   Bugs   ·   Git   ·   Translate   ·   Archive   ·   People   ·   Donate
summaryrefslogtreecommitdiffstats
path: root/tutorius/apilib/httplib2/__init__.py
blob: 982bf8a02af7a87cb260b63a99792492853ef316 (plain)
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
from __future__ import generators
"""
httplib2

A caching http interface that supports ETags and gzip
to conserve bandwidth. 

Requires Python 2.3 or later

Changelog:
2007-08-18, Rick: Modified so it's able to use a socks proxy if needed.

"""

__author__ = "Joe Gregorio (joe@bitworking.org)"
__copyright__ = "Copyright 2006, Joe Gregorio"
__contributors__ = ["Thomas Broyer (t.broyer@ltgt.net)",
    "James Antill",
    "Xavier Verges Farrero",
    "Jonathan Feinberg",
    "Blair Zajac",
    "Sam Ruby",
    "Louis Nyffenegger"]
__license__ = "MIT"
__version__ = "$Rev: 259 $"

import re 
import sys 
import md5
import email
import email.Utils
import email.Message
import StringIO
import gzip
import zlib
import httplib
import urlparse
import base64
import os
import copy
import calendar
import time
import random
import sha
import hmac
from gettext import gettext as _
import socket

try:
    import socks
except ImportError:
    socks = None

if sys.version_info >= (2,3):
    from iri2uri import iri2uri
else:
    def iri2uri(uri):
        return uri

__all__ = ['Http', 'Response', 'ProxyInfo', 'HttpLib2Error',
  'RedirectMissingLocation', 'RedirectLimit', 'FailedToDecompressContent', 
  'UnimplementedDigestAuthOptionError', 'UnimplementedHmacDigestAuthOptionError',
  'debuglevel']


# The httplib debug level, set to a non-zero value to get debug output
debuglevel = 0

# Python 2.3 support
if sys.version_info < (2,4):
    def sorted(seq):
        seq.sort()
        return seq

# Python 2.3 support
def HTTPResponse__getheaders(self):
    """Return list of (header, value) tuples."""
    if self.msg is None:
        raise httplib.ResponseNotReady()
    return self.msg.items()

if not hasattr(httplib.HTTPResponse, 'getheaders'):
    httplib.HTTPResponse.getheaders = HTTPResponse__getheaders

# All exceptions raised here derive from HttpLib2Error
class HttpLib2Error(Exception): pass

# Some exceptions can be caught and optionally 
# be turned back into responses. 
class HttpLib2ErrorWithResponse(HttpLib2Error):
    def __init__(self, desc, response, content):
        self.response = response
        self.content = content
        HttpLib2Error.__init__(self, desc)

class RedirectMissingLocation(HttpLib2ErrorWithResponse): pass
class RedirectLimit(HttpLib2ErrorWithResponse): pass
class FailedToDecompressContent(HttpLib2ErrorWithResponse): pass
class UnimplementedDigestAuthOptionError(HttpLib2ErrorWithResponse): pass
class UnimplementedHmacDigestAuthOptionError(HttpLib2ErrorWithResponse): pass

class RelativeURIError(HttpLib2Error): pass
class ServerNotFoundError(HttpLib2Error): pass

# Open Items:
# -----------
# Proxy support

# Are we removing the cached content too soon on PUT (only delete on 200 Maybe?)

# Pluggable cache storage (supports storing the cache in
#   flat files by default. We need a plug-in architecture
#   that can support Berkeley DB and Squid)

# == Known Issues ==
# Does not handle a resource that uses conneg and Last-Modified but no ETag as a cache validator.
# Does not handle Cache-Control: max-stale
# Does not use Age: headers when calculating cache freshness.


# The number of redirections to follow before giving up.
# Note that only GET redirects are automatically followed.
# Will also honor 301 requests by saving that info and never
# requesting that URI again.
DEFAULT_MAX_REDIRECTS = 5

# Which headers are hop-by-hop headers by default
HOP_BY_HOP = ['connection', 'keep-alive', 'proxy-authenticate', 'proxy-authorization', 'te', 'trailers', 'transfer-encoding', 'upgrade']

def _get_end2end_headers(response):
    hopbyhop = list(HOP_BY_HOP)
    hopbyhop.extend([x.strip() for x in response.get('connection', '').split(',')])
    return [header for header in response.keys() if header not in hopbyhop]

URI = re.compile(r"^(([^:/?#]+):)?(//([^/?#]*))?([^?#]*)(\?([^#]*))?(#(.*))?")

def parse_uri(uri):
    """Parses a URI using the regex given in Appendix B of RFC 3986.

        (scheme, authority, path, query, fragment) = parse_uri(uri)
    """
    groups = URI.match(uri).groups()
    return (groups[1], groups[3], groups[4], groups[6], groups[8])

def urlnorm(uri):
    (scheme, authority, path, query, fragment) = parse_uri(uri)
    if not scheme or not authority:
        raise RelativeURIError("Only absolute URIs are allowed. uri = %s" % uri)
    authority = authority.lower()
    scheme = scheme.lower()
    if not path: 
        path = "/"
    # Could do syntax based normalization of the URI before
    # computing the digest. See Section 6.2.2 of Std 66.
    request_uri = query and "?".join([path, query]) or path
    scheme = scheme.lower()
    defrag_uri = scheme + "://" + authority + request_uri
    return scheme, authority, request_uri, defrag_uri


# Cache filename construction (original borrowed from Venus http://intertwingly.net/code/venus/)
re_url_scheme    = re.compile(r'^\w+://')
re_slash         = re.compile(r'[?/:|]+')

def safename(filename):
    """Return a filename suitable for the cache.

    Strips dangerous and common characters to create a filename we
    can use to store the cache in.
    """

    try:
        if re_url_scheme.match(filename):
            if isinstance(filename,str):
                filename = filename.decode('utf-8')
                filename = filename.encode('idna')
            else:
                filename = filename.encode('idna')
    except UnicodeError:
        pass
    if isinstance(filename,unicode):
        filename=filename.encode('utf-8')
    filemd5 = md5.new(filename).hexdigest()
    filename = re_url_scheme.sub("", filename)
    filename = re_slash.sub(",", filename)

    # limit length of filename
    if len(filename)>200:
        filename=filename[:200]
    return ",".join((filename, filemd5))

NORMALIZE_SPACE = re.compile(r'(?:\r\n)?[ \t]+')
def _normalize_headers(headers):
    return dict([ (key.lower(), NORMALIZE_SPACE.sub(value, ' ').strip())  for (key, value) in headers.iteritems()])

def _parse_cache_control(headers):
    retval = {}
    if headers.has_key('cache-control'):
        parts =  headers['cache-control'].split(',')
        parts_with_args = [tuple([x.strip() for x in part.split("=")]) for part in parts if -1 != part.find("=")]
        parts_wo_args = [(name.strip(), 1) for name in parts if -1 == name.find("=")]
        retval = dict(parts_with_args + parts_wo_args)
    return retval 

# Whether to use a strict mode to parse WWW-Authenticate headers
# Might lead to bad results in case of ill-formed header value,
# so disabled by default, falling back to relaxed parsing.
# Set to true to turn on, usefull for testing servers.
USE_WWW_AUTH_STRICT_PARSING = 0

# In regex below:
#    [^\0-\x1f\x7f-\xff()<>@,;:\\\"/[\]?={} \t]+             matches a "token" as defined by HTTP
#    "(?:[^\0-\x08\x0A-\x1f\x7f-\xff\\\"]|\\[\0-\x7f])*?"    matches a "quoted-string" as defined by HTTP, when LWS have already been replaced by a single space
# Actually, as an auth-param value can be either a token or a quoted-string, they are combined in a single pattern which matches both:
#    \"?((?<=\")(?:[^\0-\x1f\x7f-\xff\\\"]|\\[\0-\x7f])*?(?=\")|(?<!\")[^\0-\x08\x0A-\x1f\x7f-\xff()<>@,;:\\\"/[\]?={} \t]+(?!\"))\"?
WWW_AUTH_STRICT = re.compile(r"^(?:\s*(?:,\s*)?([^\0-\x1f\x7f-\xff()<>@,;:\\\"/[\]?={} \t]+)\s*=\s*\"?((?<=\")(?:[^\0-\x08\x0A-\x1f\x7f-\xff\\\"]|\\[\0-\x7f])*?(?=\")|(?<!\")[^\0-\x1f\x7f-\xff()<>@,;:\\\"/[\]?={} \t]+(?!\"))\"?)(.*)$")
WWW_AUTH_RELAXED = re.compile(r"^(?:\s*(?:,\s*)?([^ \t\r\n=]+)\s*=\s*\"?((?<=\")(?:[^\\\"]|\\.)*?(?=\")|(?<!\")[^ \t\r\n,]+(?!\"))\"?)(.*)$")
UNQUOTE_PAIRS = re.compile(r'\\(.)')
def _parse_www_authenticate(headers, headername='www-authenticate'):
    """Returns a dictionary of dictionaries, one dict
    per auth_scheme."""
    retval = {}
    if headers.has_key(headername):
        authenticate = headers[headername].strip()
        www_auth = USE_WWW_AUTH_STRICT_PARSING and WWW_AUTH_STRICT or WWW_AUTH_RELAXED
        while authenticate:
            # Break off the scheme at the beginning of the line
            if headername == 'authentication-info':
                (auth_scheme, the_rest) = ('digest', authenticate)                
            else:
                (auth_scheme, the_rest) = authenticate.split(" ", 1)
            # Now loop over all the key value pairs that come after the scheme, 
            # being careful not to roll into the next scheme
            match = www_auth.search(the_rest)
            auth_params = {}
            while match:
                if match and len(match.groups()) == 3:
                    (key, value, the_rest) = match.groups()
                    auth_params[key.lower()] = UNQUOTE_PAIRS.sub(r'\1', value) # '\\'.join([x.replace('\\', '') for x in value.split('\\\\')])
                match = www_auth.search(the_rest)
            retval[auth_scheme.lower()] = auth_params
            authenticate = the_rest.strip()
    return retval


def _entry_disposition(response_headers, request_headers):
    """Determine freshness from the Date, Expires and Cache-Control headers.

    We don't handle the following:

    1. Cache-Control: max-stale
    2. Age: headers are not used in the calculations.

    Not that this algorithm is simpler than you might think 
    because we are operating as a private (non-shared) cache.
    This lets us ignore 's-maxage'. We can also ignore
    'proxy-invalidate' since we aren't a proxy.
    We will never return a stale document as 
    fresh as a design decision, and thus the non-implementation 
    of 'max-stale'. This also lets us safely ignore 'must-revalidate' 
    since we operate as if every server has sent 'must-revalidate'.
    Since we are private we get to ignore both 'public' and
    'private' parameters. We also ignore 'no-transform' since
    we don't do any transformations.    
    The 'no-store' parameter is handled at a higher level.
    So the only Cache-Control parameters we look at are:

    no-cache
    only-if-cached
    max-age
    min-fresh
    """
    
    retval = "STALE"
    cc = _parse_cache_control(request_headers)
    cc_response = _parse_cache_control(response_headers)

    if request_headers.has_key('pragma') and request_headers['pragma'].lower().find('no-cache') != -1:
        retval = "TRANSPARENT"
        if 'cache-control' not in request_headers:
            request_headers['cache-control'] = 'no-cache'
    elif cc.has_key('no-cache'):
        retval = "TRANSPARENT"
    elif cc_response.has_key('no-cache'):
        retval = "STALE"
    elif cc.has_key('only-if-cached'):
        retval = "FRESH"
    elif response_headers.has_key('date'):
        date = calendar.timegm(email.Utils.parsedate_tz(response_headers['date']))
        now = time.time()
        current_age = max(0, now - date)
        if cc_response.has_key('max-age'):
            try:
                freshness_lifetime = int(cc_response['max-age'])
            except ValueError:
                freshness_lifetime = 0
        elif response_headers.has_key('expires'):
            expires = email.Utils.parsedate_tz(response_headers['expires'])
            if None == expires:
                freshness_lifetime = 0
            else:
                freshness_lifetime = max(0, calendar.timegm(expires) - date)
        else:
            freshness_lifetime = 0
        if cc.has_key('max-age'):
            try:
                freshness_lifetime = int(cc['max-age'])
            except ValueError:
                freshness_lifetime = 0
        if cc.has_key('min-fresh'):
            try:
                min_fresh = int(cc['min-fresh'])
            except ValueError:
                min_fresh = 0
            current_age += min_fresh 
        if freshness_lifetime > current_age:
            retval = "FRESH"
    return retval 

def _decompressContent(response, new_content):
    content = new_content
    try:
        encoding = response.get('content-encoding', None)
        if encoding in ['gzip', 'deflate']:
            if encoding == 'gzip':
                content = gzip.GzipFile(fileobj=StringIO.StringIO(new_content)).read()
            if encoding == 'deflate':
                content = zlib.decompress(content)
            response['content-length'] = str(len(content))
            del response['content-encoding']
    except IOError:
        content = ""
        raise FailedToDecompressContent(_("Content purported to be compressed with %s but failed to decompress.") % response.get('content-encoding'), response, content)
    return content

def _updateCache(request_headers, response_headers, content, cache, cachekey):
    if cachekey:
        cc = _parse_cache_control(request_headers)
        cc_response = _parse_cache_control(response_headers)
        if cc.has_key('no-store') or cc_response.has_key('no-store'):
            cache.delete(cachekey)
        else:
            info = email.Message.Message()
            for key, value in response_headers.iteritems():
                if key not in ['status','content-encoding','transfer-encoding']:
                    info[key] = value

            status = response_headers.status
            if status == 304:
                status = 200

            status_header = 'status: %d\r\n' % response_headers.status

            header_str = info.as_string()

            header_str = re.sub("\r(?!\n)|(?<!\r)\n", "\r\n", header_str)
            text = "".join([status_header, header_str, content])

            cache.set(cachekey, text)

def _cnonce():
    dig = md5.new("%s:%s" % (time.ctime(), ["0123456789"[random.randrange(0, 9)] for i in range(20)])).hexdigest()
    return dig[:16]

def _wsse_username_token(cnonce, iso_now, password):
    return base64.encodestring(sha.new("%s%s%s" % (cnonce, iso_now, password)).digest()).strip()


# For credentials we need two things, first 
# a pool of credential to try (not necesarily tied to BAsic, Digest, etc.)
# Then we also need a list of URIs that have already demanded authentication
# That list is tricky since sub-URIs can take the same auth, or the 
# auth scheme may change as you descend the tree.
# So we also need each Auth instance to be able to tell us
# how close to the 'top' it is.

class Authentication(object):
    def __init__(self, credentials, host, request_uri, headers, response, content, http):
        (scheme, authority, path, query, fragment) = parse_uri(request_uri)
        self.path = path
        self.host = host
        self.credentials = credentials
        self.http = http

    def depth(self, request_uri):
        (scheme, authority, path, query, fragment) = parse_uri(request_uri)
        return request_uri[len(self.path):].count("/")

    def inscope(self, host, request_uri):
        # XXX Should we normalize the request_uri?
        (scheme, authority, path, query, fragment) = parse_uri(request_uri)
        return (host == self.host) and path.startswith(self.path)

    def request(self, method, request_uri, headers, content):
        """Modify the request headers to add the appropriate
        Authorization header. Over-rise this in sub-classes."""
        pass

    def response(self, response, content):
        """Gives us a chance to update with new nonces
        or such returned from the last authorized response.
        Over-rise this in sub-classes if necessary.

        Return TRUE is the request is to be retried, for 
        example Digest may return stale=true.
        """
        return False



class BasicAuthentication(Authentication):
    def __init__(self, credentials, host, request_uri, headers, response, content, http):
        Authentication.__init__(self, credentials, host, request_uri, headers, response, content, http)

    def request(self, method, request_uri, headers, content):
        """Modify the request headers to add the appropriate
        Authorization header."""
        headers['authorization'] = 'Basic ' + base64.encodestring("%s:%s" % self.credentials).strip()  


class DigestAuthentication(Authentication):
    """Only do qop='auth' and MD5, since that 
    is all Apache currently implements"""
    def __init__(self, credentials, host, request_uri, headers, response, content, http):
        Authentication.__init__(self, credentials, host, request_uri, headers, response, content, http)
        challenge = _parse_www_authenticate(response, 'www-authenticate')
        self.challenge = challenge['digest']
        qop = self.challenge.get('qop')
        self.challenge['qop'] = ('auth' in [x.strip() for x in qop.split()]) and 'auth' or None
        if self.challenge['qop'] is None:
            raise UnimplementedDigestAuthOptionError( _("Unsupported value for qop: %s." % qop))
        self.challenge['algorithm'] = self.challenge.get('algorithm', 'MD5')
        if self.challenge['algorithm'] != 'MD5':
            raise UnimplementedDigestAuthOptionError( _("Unsupported value for algorithm: %s." % self.challenge['algorithm']))
        self.A1 = "".join([self.credentials[0], ":", self.challenge['realm'], ":", self.credentials[1]])   
        self.challenge['nc'] = 1

    def request(self, method, request_uri, headers, content, cnonce = None):
        """Modify the request headers"""
        H = lambda x: md5.new(x).hexdigest()
        KD = lambda s, d: H("%s:%s" % (s, d))
        A2 = "".join([method, ":", request_uri])
        self.challenge['cnonce'] = cnonce or _cnonce() 
        request_digest  = '"%s"' % KD(H(self.A1), "%s:%s:%s:%s:%s" % (self.challenge['nonce'], 
                    '%08x' % self.challenge['nc'], 
                    self.challenge['cnonce'], 
                    self.challenge['qop'], H(A2)
                    )) 
        headers['Authorization'] = 'Digest username="%s", realm="%s", nonce="%s", uri="%s", algorithm=%s, response=%s, qop=%s, nc=%08x, cnonce="%s"' % (
                self.credentials[0], 
                self.challenge['realm'],
                self.challenge['nonce'],
                request_uri, 
                self.challenge['algorithm'],
                request_digest,
                self.challenge['qop'],
                self.challenge['nc'],
                self.challenge['cnonce'],
                )
        self.challenge['nc'] += 1

    def response(self, response, content):
        if not response.has_key('authentication-info'):
            challenge = _parse_www_authenticate(response, 'www-authenticate').get('digest', {})
            if 'true' == challenge.get('stale'):
                self.challenge['nonce'] = challenge['nonce']
                self.challenge['nc'] = 1 
                return True
        else:
            updated_challenge = _parse_www_authenticate(response, 'authentication-info').get('digest', {})

            if updated_challenge.has_key('nextnonce'):
                self.challenge['nonce'] = updated_challenge['nextnonce']
                self.challenge['nc'] = 1 
        return False


class HmacDigestAuthentication(Authentication):
    """Adapted from Robert Sayre's code and DigestAuthentication above."""
    __author__ = "Thomas Broyer (t.broyer@ltgt.net)"

    def __init__(self, credentials, host, request_uri, headers, response, content, http):
        Authentication.__init__(self, credentials, host, request_uri, headers, response, content, http)
        challenge = _parse_www_authenticate(response, 'www-authenticate')
        self.challenge = challenge['hmacdigest']
        # TODO: self.challenge['domain']
        self.challenge['reason'] = self.challenge.get('reason', 'unauthorized')
        if self.challenge['reason'] not in ['unauthorized', 'integrity']:
            self.challenge['reason'] = 'unauthorized'
        self.challenge['salt'] = self.challenge.get('salt', '')
        if not self.challenge.get('snonce'):
            raise UnimplementedHmacDigestAuthOptionError( _("The challenge doesn't contain a server nonce, or this one is empty."))
        self.challenge['algorithm'] = self.challenge.get('algorithm', 'HMAC-SHA-1')
        if self.challenge['algorithm'] not in ['HMAC-SHA-1', 'HMAC-MD5']:
            raise UnimplementedHmacDigestAuthOptionError( _("Unsupported value for algorithm: %s." % self.challenge['algorithm']))
        self.challenge['pw-algorithm'] = self.challenge.get('pw-algorithm', 'SHA-1')
        if self.challenge['pw-algorithm'] not in ['SHA-1', 'MD5']:
            raise UnimplementedHmacDigestAuthOptionError( _("Unsupported value for pw-algorithm: %s." % self.challenge['pw-algorithm']))
        if self.challenge['algorithm'] == 'HMAC-MD5':
            self.hashmod = md5
        else:
            self.hashmod = sha
        if self.challenge['pw-algorithm'] == 'MD5':
            self.pwhashmod = md5
        else:
            self.pwhashmod = sha
        self.key = "".join([self.credentials[0], ":",
                    self.pwhashmod.new("".join([self.credentials[1], self.challenge['salt']])).hexdigest().lower(),
                    ":", self.challenge['realm']
                    ])
        self.key = self.pwhashmod.new(self.key).hexdigest().lower()

    def request(self, method, request_uri, headers, content):
        """Modify the request headers"""
        keys = _get_end2end_headers(headers)
        keylist = "".join(["%s " % k for k in keys])
        headers_val = "".join([headers[k] for k in keys])
        created = time.strftime('%Y-%m-%dT%H:%M:%SZ',time.gmtime())
        cnonce = _cnonce()
        request_digest = "%s:%s:%s:%s:%s" % (method, request_uri, cnonce, self.challenge['snonce'], headers_val)
        request_digest  = hmac.new(self.key, request_digest, self.hashmod).hexdigest().lower()
        headers['Authorization'] = 'HMACDigest username="%s", realm="%s", snonce="%s", cnonce="%s", uri="%s", created="%s", response="%s", headers="%s"' % (
                self.credentials[0], 
                self.challenge['realm'],
                self.challenge['snonce'],
                cnonce,
                request_uri, 
                created,
                request_digest,
                keylist,
                )

    def response(self, response, content):
        challenge = _parse_www_authenticate(response, 'www-authenticate').get('hmacdigest', {})
        if challenge.get('reason') in ['integrity', 'stale']:
            return True
        return False


class WsseAuthentication(Authentication):
    """This is thinly tested and should not be relied upon.
    At this time there isn't any third party server to test against.
    Blogger and TypePad implemented this algorithm at one point
    but Blogger has since switched to Basic over HTTPS and 
    TypePad has implemented it wrong, by never issuing a 401
    challenge but instead requiring your client to telepathically know that
    their endpoint is expecting WSSE profile="UsernameToken"."""
    def __init__(self, credentials, host, request_uri, headers, response, content, http):
        Authentication.__init__(self, credentials, host, request_uri, headers, response, content, http)

    def request(self, method, request_uri, headers, content):
        """Modify the request headers to add the appropriate
        Authorization header."""
        headers['Authorization'] = 'WSSE profile="UsernameToken"'
        iso_now = time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime())
        cnonce = _cnonce()
        password_digest = _wsse_username_token(cnonce, iso_now, self.credentials[1])
        headers['X-WSSE'] = 'UsernameToken Username="%s", PasswordDigest="%s", Nonce="%s", Created="%s"' % (
                self.credentials[0],
                password_digest,
                cnonce,
                iso_now)

class GoogleLoginAuthentication(Authentication):
    def __init__(self, credentials, host, request_uri, headers, response, content, http):
        from urllib import urlencode
        Authentication.__init__(self, credentials, host, request_uri, headers, response, content, http)
        challenge = _parse_www_authenticate(response, 'www-authenticate')
        service = challenge['googlelogin'].get('service', 'xapi')
        # Bloggger actually returns the service in the challenge
        # For the rest we guess based on the URI
        if service == 'xapi' and  request_uri.find("calendar") > 0:
            service = "cl"
        # No point in guessing Base or Spreadsheet
        #elif request_uri.find("spreadsheets") > 0:
        #    service = "wise"

        auth = dict(Email=credentials[0], Passwd=credentials[1], service=service, source=headers['user-agent'])
        resp, content = self.http.request("https://www.google.com/accounts/ClientLogin", method="POST", body=urlencode(auth), headers={'Content-Type': 'application/x-www-form-urlencoded'})
        lines = content.split('\n')
        d = dict([tuple(line.split("=", 1)) for line in lines if line])
        if resp.status == 403:
            self.Auth = ""
        else:
            self.Auth = d['Auth']

    def request(self, method, request_uri, headers, content):
        """Modify the request headers to add the appropriate
        Authorization header."""
        headers['authorization'] = 'GoogleLogin Auth=' + self.Auth 


AUTH_SCHEME_CLASSES = {
    "basic": BasicAuthentication,
    "wsse": WsseAuthentication,
    "digest": DigestAuthentication,
    "hmacdigest": HmacDigestAuthentication,
    "googlelogin": GoogleLoginAuthentication
}

AUTH_SCHEME_ORDER = ["hmacdigest", "googlelogin", "digest", "wsse", "basic"]

def _md5(s):
    return 

class FileCache(object):
    """Uses a local directory as a store for cached files.
    Not really safe to use if multiple threads or processes are going to 
    be running on the same cache.
    """
    def __init__(self, cache, safe=safename): # use safe=lambda x: md5.new(x).hexdigest() for the old behavior
        self.cache = cache
        self.safe = safe
        if not os.path.exists(cache): 
            os.makedirs(self.cache)

    def get(self, key):
        retval = None
        cacheFullPath = os.path.join(self.cache, self.safe(key))
        try:
            f = file(cacheFullPath, "r")
            retval = f.read()
            f.close()
        except IOError:
            pass
        return retval

    def set(self, key, value):
        cacheFullPath = os.path.join(self.cache, self.safe(key))
        f = file(cacheFullPath, "w")
        f.write(value)
        f.close()

    def delete(self, key):
        cacheFullPath = os.path.join(self.cache, self.safe(key))
        if os.path.exists(cacheFullPath):
            os.remove(cacheFullPath)

class Credentials(object):
    def __init__(self):
        self.credentials = []

    def add(self, name, password, domain=""):
        self.credentials.append((domain.lower(), name, password))

    def clear(self):
        self.credentials = []

    def iter(self, domain):
        for (cdomain, name, password) in self.credentials:
            if cdomain == "" or domain == cdomain:
                yield (name, password) 

class KeyCerts(Credentials):
    """Identical to Credentials except that
    name/password are mapped to key/cert."""
    pass


class ProxyInfo(object):
  """Collect information required to use a proxy."""
  def __init__(self, proxy_type, proxy_host, proxy_port, proxy_rdns=None, proxy_user=None, proxy_pass=None):
      """The parameter proxy_type must be set to one of socks.PROXY_TYPE_XXX
      constants. For example:

p = ProxyInfo(proxy_type=socks.PROXY_TYPE_HTTP, proxy_host='localhost', proxy_port=8000)
      """
      self.proxy_type, self.proxy_host, self.proxy_port, self.proxy_rdns, self.proxy_user, self.proxy_pass = proxy_type, proxy_host, proxy_port, proxy_rdns, proxy_user, proxy_pass

  def astuple(self):
    return (self.proxy_type, self.proxy_host, self.proxy_port, self.proxy_rdns,
        self.proxy_user, self.proxy_pass)

  def isgood(self):
    return socks and (self.proxy_host != None) and (self.proxy_port != None)


class HTTPConnectionWithTimeout(httplib.HTTPConnection):
    """HTTPConnection subclass that supports timeouts"""

    def __init__(self, host, port=None, strict=None, timeout=None, proxy_info=None):
        httplib.HTTPConnection.__init__(self, host, port, strict)
        self.timeout = timeout
        self.proxy_info = proxy_info

    def connect(self):
        """Connect to the host and port specified in __init__."""
        # Mostly verbatim from httplib.py.
        msg = "getaddrinfo returns an empty list"
        for res in socket.getaddrinfo(self.host, self.port, 0,
                socket.SOCK_STREAM):
            af, socktype, proto, canonname, sa = res
            try:
                if self.proxy_info and self.proxy_info.isgood():
                    self.sock = socks.socksocket(af, socktype, proto)
                    self.sock.setproxy(*self.proxy_info.astuple())
                else:
                    self.sock = socket.socket(af, socktype, proto)
                # Different from httplib: support timeouts.
                if self.timeout is not None:
                    self.sock.settimeout(self.timeout)
                    # End of difference from httplib.
                if self.debuglevel > 0:
                    print "connect: (%s, %s)" % (self.host, self.port)
                self.sock.connect(sa)
            except socket.error, msg:
                if self.debuglevel > 0:
                    print 'connect fail:', (self.host, self.port)
                if self.sock:
                    self.sock.close()
                self.sock = None
                continue
            break
        if not self.sock:
            raise socket.error, msg

class HTTPSConnectionWithTimeout(httplib.HTTPSConnection):
    "This class allows communication via SSL."

    def __init__(self, host, port=None, key_file=None, cert_file=None,
                 strict=None, timeout=None, proxy_info=None):
        self.timeout = timeout
        self.proxy_info = proxy_info
        httplib.HTTPSConnection.__init__(self, host, port=port, key_file=key_file,
                cert_file=cert_file, strict=strict)

    def connect(self):
        "Connect to a host on a given (SSL) port."

        if self.proxy_info and self.proxy_info.isgood():
            self.sock.setproxy(*self.proxy_info.astuple())
            sock.setproxy(*self.proxy_info.astuple())
        else:
            sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        if self.timeout is not None:
            sock.settimeout(self.timeout)
        sock.connect((self.host, self.port))
        ssl = socket.ssl(sock, self.key_file, self.cert_file)
        self.sock = httplib.FakeSocket(sock, ssl)



class Http(object):
    """An HTTP client that handles:
- all methods
- caching
- ETags
- compression,
- HTTPS
- Basic
- Digest
- WSSE

and more.
    """
    def __init__(self, cache=None, timeout=None, proxy_info=None):
        """The value of proxy_info is a ProxyInfo instance.

If 'cache' is a string then it is used as a directory name
for a disk cache. Otherwise it must be an object that supports
the same interface as FileCache."""
        self.proxy_info = proxy_info
        # Map domain name to an httplib connection
        self.connections = {}
        # The location of the cache, for now a directory
        # where cached responses are held.
        if cache and isinstance(cache, str):
            self.cache = FileCache(cache)
        else:
            self.cache = cache

        # Name/password
        self.credentials = Credentials()

        # Key/cert
        self.certificates = KeyCerts()

        # authorization objects
        self.authorizations = []

        # If set to False then no redirects are followed, even safe ones.
        self.follow_redirects = True

        # If 'follow_redirects' is True, and this is set to True then
        # all redirecs are followed, including unsafe ones.
        self.follow_all_redirects = False

        self.ignore_etag = False

        self.force_exception_to_status_code = False 

        self.timeout = timeout

    def _auth_from_challenge(self, host, request_uri, headers, response, content):
        """A generator that creates Authorization objects
           that can be applied to requests.
        """
        challenges = _parse_www_authenticate(response, 'www-authenticate')
        for cred in self.credentials.iter(host):
            for scheme in AUTH_SCHEME_ORDER:
                if challenges.has_key(scheme):
                    yield AUTH_SCHEME_CLASSES[scheme](cred, host, request_uri, headers, response, content, self)

    def add_credentials(self, name, password, domain=""):
        """Add a name and password that will be used
        any time a request requires authentication."""
        self.credentials.add(name, password, domain)

    def add_certificate(self, key, cert, domain):
        """Add a key and cert that will be used
        any time a request requires authentication."""
        self.certificates.add(key, cert, domain)

    def clear_credentials(self):
        """Remove all the names and passwords
        that are used for authentication"""
        self.credentials.clear()
        self.authorizations = []

    def _conn_request(self, conn, request_uri, method, body, headers):
        for i in range(2):
            try:
                conn.request(method, request_uri, body, headers)
                response = conn.getresponse()
            except socket.gaierror:
                conn.close()
                raise ServerNotFoundError("Unable to find the server at %s" % conn.host)
            except httplib.HTTPException, e:
                if i == 0:
                    conn.close()
                    conn.connect()
                    continue
                else:
                    raise
            else:
                content = response.read()
                response = Response(response)
                if method != "HEAD":
                    content = _decompressContent(response, content)

            break;
        return (response, content)


    def _request(self, conn, host, absolute_uri, request_uri, method, body, headers, redirections, cachekey):
        """Do the actual request using the connection object
        and also follow one level of redirects if necessary"""

        auths = [(auth.depth(request_uri), auth) for auth in self.authorizations if auth.inscope(host, request_uri)]
        auth = auths and sorted(auths)[0][1] or None
        if auth: 
            auth.request(method, request_uri, headers, body)

        (response, content) = self._conn_request(conn, request_uri, method, body, headers)

        if auth: 
            if auth.response(response, body):
                auth.request(method, request_uri, headers, body)
                (response, content) = self._conn_request(conn, request_uri, method, body, headers )
                response._stale_digest = 1

        if response.status == 401:
            for authorization in self._auth_from_challenge(host, request_uri, headers, response, content):
                authorization.request(method, request_uri, headers, body) 
                (response, content) = self._conn_request(conn, request_uri, method, body, headers, )
                if response.status != 401:
                    self.authorizations.append(authorization)
                    authorization.response(response, body)
                    break

        if (self.follow_all_redirects or (method in ["GET", "HEAD"]) or response.status == 303):
            if self.follow_redirects and response.status in [300, 301, 302, 303, 307]:
                # Pick out the location header and basically start from the beginning
                # remembering first to strip the ETag header and decrement our 'depth'
                if redirections:
                    if not response.has_key('location') and response.status != 300:
                        raise RedirectMissingLocation( _("Redirected but the response is missing a Location: header."), response, content)
                    # Fix-up relative redirects (which violate an RFC 2616 MUST)
                    if response.has_key('location'):
                        location = response['location']
                        (scheme, authority, path, query, fragment) = parse_uri(location)
                        if authority == None:
                            response['location'] = urlparse.urljoin(absolute_uri, location)
                    if response.status == 301 and method in ["GET", "HEAD"]:
                        response['-x-permanent-redirect-url'] = response['location']
                        if not response.has_key('content-location'):
                            response['content-location'] = absolute_uri 
                        _updateCache(headers, response, content, self.cache, cachekey)
                    if headers.has_key('if-none-match'):
                        del headers['if-none-match']
                    if headers.has_key('if-modified-since'):
                        del headers['if-modified-since']
                    if response.has_key('location'):
                        location = response['location']
                        old_response = copy.deepcopy(response)
                        if not old_response.has_key('content-location'):
                            old_response['content-location'] = absolute_uri 
                        redirect_method = ((response.status == 303) and (method not in ["GET", "HEAD"])) and "GET" or method
                        (response, content) = self.request(location, redirect_method, body=body, headers = headers, redirections = redirections - 1)
                        response.previous = old_response
                else:
                    raise RedirectLimit( _("Redirected more times than rediection_limit allows."), response, content)
            elif response.status in [200, 203] and method == "GET":
                # Don't cache 206's since we aren't going to handle byte range requests
                if not response.has_key('content-location'):
                    response['content-location'] = absolute_uri 
                _updateCache(headers, response, content, self.cache, cachekey)

        return (response, content)


# Need to catch and rebrand some exceptions
# Then need to optionally turn all exceptions into status codes
# including all socket.* and httplib.* exceptions.


    def request(self, uri, method="GET", body=None, headers=None, redirections=DEFAULT_MAX_REDIRECTS, connection_type=None):
        """ Performs a single HTTP request.
The 'uri' is the URI of the HTTP resource and can begin 
with either 'http' or 'https'. The value of 'uri' must be an absolute URI.

The 'method' is the HTTP method to perform, such as GET, POST, DELETE, etc. 
There is no restriction on the methods allowed.

The 'body' is the entity body to be sent with the request. It is a string
object.

Any extra headers that are to be sent with the request should be provided in the
'headers' dictionary.

The maximum number of redirect to follow before raising an 
exception is 'redirections. The default is 5.

The return value is a tuple of (response, content), the first 
being and instance of the 'Response' class, the second being 
a string that contains the response entity body.
        """
        try:
            if headers is None:
                headers = {}
            else:
                headers = _normalize_headers(headers)

            if not headers.has_key('user-agent'):
                headers['user-agent'] = "Python-httplib2/%s" % __version__

            uri = iri2uri(uri)

            (scheme, authority, request_uri, defrag_uri) = urlnorm(uri)

            conn_key = scheme+":"+authority
            if conn_key in self.connections:
                conn = self.connections[conn_key]
            else:
                if not connection_type:
                    connection_type = (scheme == 'https') and HTTPSConnectionWithTimeout or HTTPConnectionWithTimeout
                certs = list(self.certificates.iter(authority))
                if scheme == 'https' and certs:
                    conn = self.connections[conn_key] = connection_type(authority, key_file=certs[0][0],
                        cert_file=certs[0][1], timeout=self.timeout, proxy_info=self.proxy_info)
                else:
                    conn = self.connections[conn_key] = connection_type(authority, timeout=self.timeout, proxy_info=self.proxy_info)
                conn.set_debuglevel(debuglevel)

            if method in ["GET", "HEAD"] and 'range' not in headers:
                headers['accept-encoding'] = 'compress, gzip'

            info = email.Message.Message()
            cached_value = None
            if self.cache:
                cachekey = defrag_uri
                cached_value = self.cache.get(cachekey)
                if cached_value:
                    info = email.message_from_string(cached_value)
                    try:
                        content = cached_value.split('\r\n\r\n', 1)[1]
                    except IndexError:
                        self.cache.delete(cachekey)
                        cachekey = None
                        cached_value = None
            else:
                cachekey = None

            if method in ["PUT"] and self.cache and info.has_key('etag') and not self.ignore_etag and 'if-match' not in headers:
                # http://www.w3.org/1999/04/Editing/
                headers['if-match'] = info['etag']

            if method not in ["GET", "HEAD"] and self.cache and cachekey:
                # RFC 2616 Section 13.10
                self.cache.delete(cachekey)

            if cached_value and method in ["GET", "HEAD"] and self.cache and 'range' not in headers:
                if info.has_key('-x-permanent-redirect-url'):
                    # Should cached permanent redirects be counted in our redirection count? For now, yes.
                    (response, new_content) = self.request(info['-x-permanent-redirect-url'], "GET", headers = headers, redirections = redirections - 1)
                    response.previous = Response(info)
                    response.previous.fromcache = True
                else:
                    # Determine our course of action:
                    #   Is the cached entry fresh or stale?
                    #   Has the client requested a non-cached response?
                    #   
                    # There seems to be three possible answers: 
                    # 1. [FRESH] Return the cache entry w/o doing a GET
                    # 2. [STALE] Do the GET (but add in cache validators if available)
                    # 3. [TRANSPARENT] Do a GET w/o any cache validators (Cache-Control: no-cache) on the request
                    entry_disposition = _entry_disposition(info, headers) 
                    
                    if entry_disposition == "FRESH":
                        if not cached_value:
                            info['status'] = '504'
                            content = ""
                        response = Response(info)
                        if cached_value:
                            response.fromcache = True
                        return (response, content)

                    if entry_disposition == "STALE":
                        if info.has_key('etag') and not self.ignore_etag and not 'if-none-match' in headers:
                            headers['if-none-match'] = info['etag']
                        if info.has_key('last-modified') and not 'last-modified' in headers:
                            headers['if-modified-since'] = info['last-modified']
                    elif entry_disposition == "TRANSPARENT":
                        pass

                    (response, new_content) = self._request(conn, authority, uri, request_uri, method, body, headers, redirections, cachekey)

                if response.status == 304 and method == "GET":
                    # Rewrite the cache entry with the new end-to-end headers
                    # Take all headers that are in response 
                    # and overwrite their values in info.
                    # unless they are hop-by-hop, or are listed in the connection header.

                    for key in _get_end2end_headers(response):
                        info[key] = response[key]
                    merged_response = Response(info)
                    if hasattr(response, "_stale_digest"):
                        merged_response._stale_digest = response._stale_digest
                    _updateCache(headers, merged_response, content, self.cache, cachekey)
                    response = merged_response
                    response.status = 200
                    response.fromcache = True 

                elif response.status == 200:
                    content = new_content
                else:
                    self.cache.delete(cachekey)
                    content = new_content 
            else: 
                (response, content) = self._request(conn, authority, uri, request_uri, method, body, headers, redirections, cachekey)
        except Exception, e:
            if self.force_exception_to_status_code:
                if isinstance(e, HttpLib2ErrorWithResponse):
                    response = e.response
                    content = e.content
                    response.status = 500
                    response.reason = str(e) 
                elif isinstance(e, socket.timeout):
                    content = "Request Timeout"
                    response = Response( {
                            "content-type": "text/plain",
                            "status": "408",
                            "content-length": len(content)
                            })
                    response.reason = "Request Timeout"
                else:
                    content = str(e) 
                    response = Response( {
                            "content-type": "text/plain",
                            "status": "400",
                            "content-length": len(content)
                            })
                    response.reason = "Bad Request" 
            else:
                raise

 
        return (response, content)

 

class Response(dict):
    """An object more like email.Message than httplib.HTTPResponse."""
   
    """Is this response from our local cache"""
    fromcache = False

    """HTTP protocol version used by server. 10 for HTTP/1.0, 11 for HTTP/1.1. """
    version = 11

    "Status code returned by server. "
    status = 200

    """Reason phrase returned by server."""
    reason = "Ok"

    previous = None

    def __init__(self, info):
        # info is either an email.Message or 
        # an httplib.HTTPResponse object.
        if isinstance(info, httplib.HTTPResponse):
            for key, value in info.getheaders(): 
                self[key] = value 
            self.status = info.status
            self['status'] = str(self.status)
            self.reason = info.reason
            self.version = info.version
        elif isinstance(info, email.Message.Message):
            for key, value in info.items(): 
                self[key] = value 
            self.status = int(self['status'])
        else:
            for key, value in info.iteritems(): 
                self[key] = value 
            self.status = int(self.get('status', self.status))


    def __getattr__(self, name):
        if name == 'dict':
            return self 
        else:  
            raise AttributeError, name