File: __init__.py

package info (click to toggle)
python-httplib2 0.11.3-2
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 924 kB
  • sloc: python: 5,701; makefile: 4
file content (1779 lines) | stat: -rw-r--r-- 73,431 bytes parent folder | download
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
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
from __future__ import print_function
"""
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",
                    "Alex Yu"]
__license__ = "MIT"
__version__ = '0.11.3'

import re
import sys
import email
import email.Utils
import email.Message
import email.FeedParser
import StringIO
import gzip
import zlib
import httplib
import urlparse
import urllib
import base64
import os
import copy
import calendar
import time
import random
import errno
try:
    from hashlib import sha1 as _sha, md5 as _md5
except ImportError:
    # prior to Python 2.5, these were separate modules
    import sha
    import md5
    _sha = sha.new
    _md5 = md5.new
import hmac
from gettext import gettext as _
import socket

try:
    from httplib2 import socks
except ImportError:
    try:
        import socks
    except (ImportError, AttributeError):
        socks = None

# Build the appropriate socket wrapper for ssl
ssl = None
ssl_SSLError = None
ssl_CertificateError = None
try:
    import ssl  # python 2.6
except ImportError:
    pass
if ssl is not None:
    ssl_SSLError = getattr(ssl, 'SSLError', None)
    ssl_CertificateError = getattr(ssl, 'CertificateError', None)


def _ssl_wrap_socket(sock, key_file, cert_file, disable_validation,
                     ca_certs, ssl_version, hostname):
    if disable_validation:
        cert_reqs = ssl.CERT_NONE
    else:
        cert_reqs = ssl.CERT_REQUIRED
    if ssl_version is None:
        ssl_version = ssl.PROTOCOL_SSLv23

    if hasattr(ssl, 'SSLContext'):  # Python 2.7.9
        context = ssl.SSLContext(ssl_version)
        context.verify_mode = cert_reqs
        context.check_hostname = (cert_reqs != ssl.CERT_NONE)
        if cert_file:
            context.load_cert_chain(cert_file, key_file)
        if ca_certs:
            context.load_verify_locations(ca_certs)
        return context.wrap_socket(sock, server_hostname=hostname)
    else:
        return ssl.wrap_socket(sock, keyfile=key_file, certfile=cert_file,
                               cert_reqs=cert_reqs, ca_certs=ca_certs,
                               ssl_version=ssl_version)


def _ssl_wrap_socket_unsupported(sock, key_file, cert_file, disable_validation,
                                 ca_certs, ssl_version, hostname):
    if not disable_validation:
        raise CertificateValidationUnsupported(
                "SSL certificate validation is not supported without "
                "the ssl module installed. To avoid this error, install "
                "the ssl module, or explicity disable validation.")
    ssl_sock = socket.ssl(sock, key_file, cert_file)
    return httplib.FakeSocket(sock, ssl_sock)

if ssl is None:
    _ssl_wrap_socket = _ssl_wrap_socket_unsupported


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

def has_timeout(timeout): # python 2.6
    if hasattr(socket, '_GLOBAL_DEFAULT_TIMEOUT'):
        return (timeout is not None and timeout is not socket._GLOBAL_DEFAULT_TIMEOUT)
    return (timeout is not None)

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


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

# A request will be tried 'RETRIES' times if it fails at the socket/connection level.
RETRIES = 2

# 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 MalformedHeader(HttpLib2Error): pass
class RelativeURIError(HttpLib2Error): pass
class ServerNotFoundError(HttpLib2Error): pass
class ProxiesUnavailableError(HttpLib2Error): pass
class CertificateValidationUnsupported(HttpLib2Error): pass
class SSLHandshakeError(HttpLib2Error): pass
class NotSupportedOnThisPlatform(HttpLib2Error): pass
class CertificateHostnameMismatch(SSLHandshakeError):
    def __init__(self, desc, host, cert):
        HttpLib2Error.__init__(self, desc)
        self.host = host
        self.cert = cert

class NotRunningAppEngineEnvironment(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

try:
    # Users can optionally provide a module that tells us where the CA_CERTS
    # are located.
    import ca_certs_locater
    CA_CERTS = ca_certs_locater.get()
except ImportError:
    # Use system CA certificates
    CA_CERTS = "/etc/ssl/certs/ca-certificates.crt"

# 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(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 'cache-control' in headers:
        parts =  headers['cache-control'].split(',')
        parts_with_args = [tuple([x.strip().lower() for x in part.split("=", 1)]) for part in parts if -1 != part.find("=")]
        parts_wo_args = [(name.strip().lower(), 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 headername in headers:
        try:

            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()

        except ValueError:
            raise MalformedHeader("WWW-Authenticate")
    return retval


# TODO: add current time as _entry_disposition argument to avoid sleep in tests
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 'pragma' in request_headers 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 'no-cache' in cc:
        retval = "TRANSPARENT"
    elif 'no-cache' in cc_response:
        retval = "STALE"
    elif 'only-if-cached' in cc:
        retval = "FRESH"
    elif 'date' in response_headers:
        date = calendar.timegm(email.Utils.parsedate_tz(response_headers['date']))
        now = time.time()
        current_age = max(0, now - date)
        if 'max-age' in cc_response:
            try:
                freshness_lifetime = int(cc_response['max-age'])
            except ValueError:
                freshness_lifetime = 0
        elif 'expires' in response_headers:
            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 'max-age' in cc:
            try:
                freshness_lifetime = int(cc['max-age'])
            except ValueError:
                freshness_lifetime = 0
        if 'min-fresh' in cc:
            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, -zlib.MAX_WBITS)
            response['content-length'] = str(len(content))
            # Record the historical presence of the encoding in a way the won't interfere.
            response['-content-encoding'] = response['content-encoding']
            del response['content-encoding']
    except (IOError, zlib.error):
        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 'no-store' in cc or 'no-store' in cc_response:
            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

            # Add annotations to the cache to indicate what headers
            # are variant for this request.
            vary = response_headers.get('vary', None)
            if vary:
                vary_headers = vary.lower().replace(' ', '').split(',')
                for header in vary_headers:
                    key = '-varied-%s' % header
                    try:
                        info[key] = request_headers[header]
                    except KeyError:
                        pass

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

            status_header = 'status: %d\r\n' % 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("%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.b64encode(_sha("%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-ride 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.b64encode("%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', 'auth')
        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').upper()
        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(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'])
        if self.challenge.get('opaque'):
            headers['authorization'] += ', opaque="%s"' % self.challenge['opaque']
        self.challenge['nc'] += 1

    def response(self, response, content):
        if 'authentication-info' not in response:
            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 'nextnonce' in updated_challenge:
                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"]


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, "rb")
            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, "wb")
        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 AllHosts(object):
    pass


class ProxyInfo(object):
    """Collect information required to use a proxy."""
    bypass_hosts = ()

    def __init__(self, proxy_type, proxy_host, proxy_port,
                 proxy_rdns=True, proxy_user=None, proxy_pass=None, proxy_headers=None):
        """
        Args:
          proxy_type: The type of proxy server.  This 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)

          proxy_host: The hostname or IP address of the proxy server.

          proxy_port: The port that the proxy server is running on.

          proxy_rdns: If True (default), DNS queries will not be performed
          locally, and instead, handed to the proxy to resolve.  This is useful
          if the network does not allow resolution of non-local names.  In
          httplib2 0.9 and earlier, this defaulted to False.

          proxy_user: The username used to authenticate with the proxy server.

          proxy_pass: The password used to authenticate with the proxy server.

          proxy_headers: Additional or modified headers for the proxy connect request.
        """
        self.proxy_type = proxy_type
        self.proxy_host = proxy_host
        self.proxy_port = proxy_port
        self.proxy_rdns = proxy_rdns
        self.proxy_user = proxy_user
        self.proxy_pass = proxy_pass
        self.proxy_headers = proxy_headers

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

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

    def applies_to(self, hostname):
        return not self.bypass_host(hostname)

    def bypass_host(self, hostname):
        """Has this host been excluded from the proxy config"""
        if self.bypass_hosts is AllHosts:
            return True

        hostname = '.' + hostname.lstrip('.')
        for skip_name in self.bypass_hosts:
            # *.suffix
            if skip_name.startswith('.') and hostname.endswith(skip_name):
                return True
            # exact match
            if hostname == '.' + skip_name:
                return True
        return False

    def __repr__(self):
        return (
            '<ProxyInfo type={p.proxy_type} host:port={p.proxy_host}:{p.proxy_port} rdns={p.proxy_rdns}' +
            ' user={p.proxy_user} headers={p.proxy_headers}>').format(p=self)


def proxy_info_from_environment(method='http'):
    """
    Read proxy info from the environment variables.
    """
    if method not in ['http', 'https']:
        return

    env_var = method + '_proxy'
    url = os.environ.get(env_var, os.environ.get(env_var.upper()))
    if not url:
        return
    return proxy_info_from_url(url, method, None)


def proxy_info_from_url(url, method='http', noproxy=None):
    """
    Construct a ProxyInfo from a URL (such as http_proxy env var)
    """
    url = urlparse.urlparse(url)
    username = None
    password = None
    port = None
    if '@' in url[1]:
        ident, host_port = url[1].split('@', 1)
        if ':' in ident:
            username, password = ident.split(':', 1)
        else:
            password = ident
    else:
        host_port = url[1]
    if ':' in host_port:
        host, port = host_port.split(':', 1)
    else:
        host = host_port

    if port:
        port = int(port)
    else:
        port = dict(https=443, http=80)[method]

    proxy_type = 3  # socks.PROXY_TYPE_HTTP
    pi = ProxyInfo(
        proxy_type = proxy_type,
        proxy_host = host,
        proxy_port = port,
        proxy_user = username or None,
        proxy_pass = password or None,
        proxy_headers = None,
    )

    bypass_hosts = []
    # If not given an explicit noproxy value, respect values in env vars.
    if noproxy is None:
        noproxy = os.environ.get('no_proxy', os.environ.get('NO_PROXY', ''))
    # Special case: A single '*' character means all hosts should be bypassed.
    if noproxy == '*':
        bypass_hosts = AllHosts
    elif noproxy.strip():
        bypass_hosts = noproxy.split(',')
        bypass_hosts = filter(bool, bypass_hosts)  # To exclude empty string.

    pi.bypass_hosts = bypass_hosts
    return pi


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

    All timeouts are in seconds. If None is passed for timeout then
    Python's default timeout for sockets will be used. See for example
    the docs of socket.setdefaulttimeout():
    http://docs.python.org/library/socket.html#socket.setdefaulttimeout
    """

    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.
        if self.proxy_info and socks is None:
            raise ProxiesUnavailableError(
                'Proxy support missing but proxy use was requested!')
        msg = "getaddrinfo returns an empty list"
        if self.proxy_info and self.proxy_info.isgood():
            use_proxy = True
            proxy_type, proxy_host, proxy_port, proxy_rdns, proxy_user, proxy_pass, proxy_headers = self.proxy_info.astuple()

            host = proxy_host
            port = proxy_port
        else:
            use_proxy = False

            host = self.host
            port = self.port

        for res in socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM):
            af, socktype, proto, canonname, sa = res
            try:
                if use_proxy:
                    self.sock = socks.socksocket(af, socktype, proto)
                    self.sock.setproxy(proxy_type, proxy_host, proxy_port, proxy_rdns, proxy_user, proxy_pass, proxy_headers)
                else:
                    self.sock = socket.socket(af, socktype, proto)
                    self.sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1)
                # Different from httplib: support timeouts.
                if has_timeout(self.timeout):
                    self.sock.settimeout(self.timeout)
                    # End of difference from httplib.
                if self.debuglevel > 0:
                    print("connect: (%s, %s) ************" % (self.host, self.port))
                    if use_proxy:
                        print("proxy: %s ************" % str((proxy_host, proxy_port, proxy_rdns, proxy_user, proxy_pass, proxy_headers)))
                if use_proxy:
                    self.sock.connect((self.host, self.port) + sa[2:])
                else:
                    self.sock.connect(sa)
            except socket.error as msg:
                if self.debuglevel > 0:
                    print("connect fail: (%s, %s)" % (self.host, self.port))
                    if use_proxy:
                        print("proxy: %s" % str((proxy_host, proxy_port, proxy_rdns, proxy_user, proxy_pass, proxy_headers)))
                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.

    All timeouts are in seconds. If None is passed for timeout then
    Python's default timeout for sockets will be used. See for example
    the docs of socket.setdefaulttimeout():
    http://docs.python.org/library/socket.html#socket.setdefaulttimeout
    """
    def __init__(self, host, port=None, key_file=None, cert_file=None,
                 strict=None, timeout=None, proxy_info=None,
                 ca_certs=None, disable_ssl_certificate_validation=False,
                 ssl_version=None):
        httplib.HTTPSConnection.__init__(self, host, port=port,
                                         key_file=key_file,
                                         cert_file=cert_file, strict=strict)
        self.timeout = timeout
        self.proxy_info = proxy_info
        if ca_certs is None:
            ca_certs = CA_CERTS
        self.ca_certs = ca_certs
        self.disable_ssl_certificate_validation = \
                disable_ssl_certificate_validation
        self.ssl_version = ssl_version

    # The following two methods were adapted from https_wrapper.py, released
    # with the Google Appengine SDK at
    # http://googleappengine.googlecode.com/svn-history/r136/trunk/python/google/appengine/tools/https_wrapper.py
    # under the following license:
    #
    # Copyright 2007 Google Inc.
    #
    # Licensed under the Apache License, Version 2.0 (the "License");
    # you may not use this file except in compliance with the License.
    # You may obtain a copy of the License at
    #
    #     http://www.apache.org/licenses/LICENSE-2.0
    #
    # Unless required by applicable law or agreed to in writing, software
    # distributed under the License is distributed on an "AS IS" BASIS,
    # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
    # See the License for the specific language governing permissions and
    # limitations under the License.
    #

    def _GetValidHostsForCert(self, cert):
        """Returns a list of valid host globs for an SSL certificate.

        Args:
          cert: A dictionary representing an SSL certificate.
        Returns:
          list: A list of valid host globs.
        """
        if 'subjectAltName' in cert:
            return [x[1] for x in cert['subjectAltName']
                    if x[0].lower() == 'dns']
        else:
            return [x[0][1] for x in cert['subject']
                    if x[0][0].lower() == 'commonname']

    def _ValidateCertificateHostname(self, cert, hostname):
        """Validates that a given hostname is valid for an SSL certificate.

        Args:
          cert: A dictionary representing an SSL certificate.
          hostname: The hostname to test.
        Returns:
          bool: Whether or not the hostname is valid for this certificate.
        """
        hosts = self._GetValidHostsForCert(cert)
        for host in hosts:
            host_re = host.replace('.', '\.').replace('*', '[^.]*')
            if re.search('^%s$' % (host_re,), hostname, re.I):
                return True
        return False

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

        msg = "getaddrinfo returns an empty list"
        if self.proxy_info and self.proxy_info.isgood():
            use_proxy = True
            proxy_type, proxy_host, proxy_port, proxy_rdns, proxy_user, proxy_pass, proxy_headers = self.proxy_info.astuple()

            host = proxy_host
            port = proxy_port
        else:
            use_proxy = False

            host = self.host
            port = self.port

        address_info = socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM)
        for family, socktype, proto, canonname, sockaddr in address_info:
            try:
                if use_proxy:
                    sock = socks.socksocket(family, socktype, proto)

                    sock.setproxy(proxy_type, proxy_host, proxy_port, proxy_rdns, proxy_user, proxy_pass, proxy_headers)
                else:
                    sock = socket.socket(family, socktype, proto)
                    sock.setsockopt(socket.IPPROTO_TCP, socket.TCP_NODELAY, 1)

                if has_timeout(self.timeout):
                    sock.settimeout(self.timeout)

                if use_proxy:
                    sock.connect((self.host, self.port) + sockaddr[:2])
                else:
                    sock.connect(sockaddr)
                self.sock =_ssl_wrap_socket(
                    sock, self.key_file, self.cert_file,
                    self.disable_ssl_certificate_validation, self.ca_certs,
                    self.ssl_version, self.host)
                if self.debuglevel > 0:
                    print("connect: (%s, %s)" % (self.host, self.port))
                    if use_proxy:
                        print("proxy: %s" % str((proxy_host, proxy_port, proxy_rdns, proxy_user, proxy_pass, proxy_headers)))
                if not self.disable_ssl_certificate_validation:
                    cert = self.sock.getpeercert()
                    hostname = self.host.split(':', 0)[0]
                    if not self._ValidateCertificateHostname(cert, hostname):
                        raise CertificateHostnameMismatch(
                            'Server presented certificate that does not match '
                            'host %s: %s' % (hostname, cert), hostname, cert)
            except (ssl_SSLError, ssl_CertificateError, CertificateHostnameMismatch) as e:
                if sock:
                    sock.close()
                if self.sock:
                    self.sock.close()
                self.sock = None
                # Unfortunately the ssl module doesn't seem to provide any way
                # to get at more detailed error information, in particular
                # whether the error is due to certificate validation or
                # something else (such as SSL protocol mismatch).
                if getattr(e, 'errno', None) == ssl.SSL_ERROR_SSL:
                    raise SSLHandshakeError(e)
                else:
                    raise
            except (socket.timeout, socket.gaierror):
                raise
            except socket.error as msg:
                if self.debuglevel > 0:
                    print("connect fail: (%s, %s)" % (self.host, self.port))
                    if use_proxy:
                        print("proxy: %s" % str((proxy_host, proxy_port, proxy_rdns, proxy_user, proxy_pass, proxy_headers)))
                if self.sock:
                    self.sock.close()
                self.sock = None
                continue
            break
        if not self.sock:
            raise socket.error, msg

SCHEME_TO_CONNECTION = {
    'http': HTTPConnectionWithTimeout,
    'https': HTTPSConnectionWithTimeout
}


def _new_fixed_fetch(validate_certificate):
    def fixed_fetch(url, payload=None, method="GET", headers={},
                    allow_truncated=False, follow_redirects=True,
                    deadline=None):
        if deadline is None:
            deadline = socket.getdefaulttimeout()
        return fetch(url, payload=payload, method=method, headers=headers,
                     allow_truncated=allow_truncated,
                     follow_redirects=follow_redirects, deadline=deadline,
                     validate_certificate=validate_certificate)
    return fixed_fetch


class AppEngineHttpConnection(httplib.HTTPConnection):
    """Use httplib on App Engine, but compensate for its weirdness.

    The parameters key_file, cert_file, proxy_info, ca_certs,
    disable_ssl_certificate_validation, and ssl_version are all dropped on
    the ground.
    """
    def __init__(self, host, port=None, key_file=None, cert_file=None,
                 strict=None, timeout=None, proxy_info=None, ca_certs=None,
                 disable_ssl_certificate_validation=False,
                 ssl_version=None):
        httplib.HTTPConnection.__init__(self, host, port=port,
                                        strict=strict, timeout=timeout)


class AppEngineHttpsConnection(httplib.HTTPSConnection):
    """Same as AppEngineHttpConnection, but for HTTPS URIs.

    The parameters proxy_info, ca_certs, disable_ssl_certificate_validation,
    and ssl_version are all dropped on the ground.
    """
    def __init__(self, host, port=None, key_file=None, cert_file=None,
                 strict=None, timeout=None, proxy_info=None, ca_certs=None,
                 disable_ssl_certificate_validation=False,
                 ssl_version=None):
        httplib.HTTPSConnection.__init__(self, host, port=port,
                                         key_file=key_file,
                                         cert_file=cert_file, strict=strict,
                                         timeout=timeout)
        self._fetch = _new_fixed_fetch(
                not disable_ssl_certificate_validation)

# Use a different connection object for Google App Engine
try:
    server_software = os.environ.get('SERVER_SOFTWARE')
    if not server_software:
        raise NotRunningAppEngineEnvironment()
    elif not (server_software.startswith('Google App Engine/') or
              server_software.startswith('Development/')):
        raise NotRunningAppEngineEnvironment()

    from google.appengine.api import apiproxy_stub_map
    if apiproxy_stub_map.apiproxy.GetStub('urlfetch') is None:
        raise ImportError  # Bail out; we're not actually running on App Engine.
    from google.appengine.api.urlfetch import fetch
    from google.appengine.api.urlfetch import InvalidURLError

    # Update the connection classes to use the Googel App Engine specific ones.
    SCHEME_TO_CONNECTION = {
        'http': AppEngineHttpConnection,
        'https': AppEngineHttpsConnection
    }
except (ImportError, AttributeError, NotRunningAppEngineEnvironment):
    pass


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=proxy_info_from_environment,
                 ca_certs=None, disable_ssl_certificate_validation=False,
                 ssl_version=None):
        """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.

        All timeouts are in seconds. If None is passed for timeout
        then Python's default timeout for sockets will be used. See
        for example the docs of socket.setdefaulttimeout():
        http://docs.python.org/library/socket.html#socket.setdefaulttimeout

        `proxy_info` may be:
          - a callable that takes the http scheme ('http' or 'https') and
            returns a ProxyInfo instance per request. By default, uses
            proxy_nfo_from_environment.
          - a ProxyInfo instance (static proxy config).
          - None (proxy disabled).

        ca_certs is the path of a file containing root CA certificates for SSL
        server certificate validation.  By default, a CA cert file bundled with
        httplib2 is used.

        If disable_ssl_certificate_validation is true, SSL cert validation will
        not be performed.

        By default, ssl.PROTOCOL_SSLv23 will be used for the ssl version.
        """
        self.proxy_info = proxy_info
        self.ca_certs = ca_certs
        self.disable_ssl_certificate_validation = \
                disable_ssl_certificate_validation
        self.ssl_version = ssl_version

        # 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, basestring):
            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

        # Which HTTP methods do we apply optimistic concurrency to, i.e.
        # which methods get an "if-match:" etag header added to them.
        self.optimistic_concurrency_methods = ["PUT", "PATCH"]

        # 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

        # Keep Authorization: headers on a redirect.
        self.forward_authorization_headers = False

    def __getstate__(self):
        state_dict = copy.copy(self.__dict__)
        # In case request is augmented by some foreign object such as
        # credentials which handle auth
        if 'request' in state_dict:
            del state_dict['request']
        if 'connections' in state_dict:
            del state_dict['connections']
        return state_dict

    def __setstate__(self, state):
        self.__dict__.update(state)
        self.connections = {}

    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 scheme in challenges:
                    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):
        i = 0
        seen_bad_status_line = False
        while i < RETRIES:
            i += 1
            try:
                if hasattr(conn, 'sock') and conn.sock is None:
                    conn.connect()
                conn.request(method, request_uri, body, headers)
            except socket.timeout:
                raise
            except socket.gaierror:
                conn.close()
                raise ServerNotFoundError("Unable to find the server at %s" % conn.host)
            except ssl_SSLError:
                conn.close()
                raise
            except socket.error as e:
                err = 0
                if hasattr(e, 'args'):
                    err = getattr(e, 'args')[0]
                else:
                    err = e.errno
                if err == errno.ECONNREFUSED:  # Connection refused
                    raise
                if err in (errno.ENETUNREACH, errno.EADDRNOTAVAIL) and i < RETRIES:
                    continue  # retry on potentially transient socket errors
            except httplib.HTTPException:
                # Just because the server closed the connection doesn't apparently mean
                # that the server didn't send a response.
                if hasattr(conn, 'sock') and conn.sock is None:
                    if i < RETRIES-1:
                        conn.close()
                        conn.connect()
                        continue
                    else:
                        conn.close()
                        raise
                if i < RETRIES-1:
                    conn.close()
                    conn.connect()
                    continue
            try:
                response = conn.getresponse()
            except httplib.BadStatusLine:
                # If we get a BadStatusLine on the first try then that means
                # the connection just went stale, so retry regardless of the
                # number of RETRIES set.
                if not seen_bad_status_line and i == 1:
                    i = 0
                    seen_bad_status_line = True
                    conn.close()
                    conn.connect()
                    continue
                else:
                    conn.close()
                    raise
            except (socket.error, httplib.HTTPException):
                if i < RETRIES-1:
                    conn.close()
                    conn.connect()
                    continue
                else:
                    conn.close()
                    raise
            else:
                content = ""
                if method == "HEAD":
                    conn.close()
                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 'location' not in response 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 'location' in response:
                        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 'content-location' not in response:
                            response['content-location'] = absolute_uri
                        _updateCache(headers, response, content, self.cache, cachekey)
                    if 'if-none-match' in headers:
                        del headers['if-none-match']
                    if 'if-modified-since' in headers:
                        del headers['if-modified-since']
                    if 'authorization' in headers and not self.forward_authorization_headers:
                        del headers['authorization']
                    if 'location' in response:
                        location = response['location']
                        old_response = copy.deepcopy(response)
                        if 'content-location' not in old_response:
                            old_response['content-location'] = absolute_uri
                        redirect_method = method
                        if response.status in [302, 303]:
                            redirect_method = "GET"
                            body = None
                        (response, content) = self.request(
                            location, method=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 in ["GET", "HEAD"]:
                # Don't cache 206's since we aren't going to handle byte range requests
                if 'content-location' not in response:
                    response['content-location'] = absolute_uri
                _updateCache(headers, response, content, self.cache, cachekey)

        return (response, content)

    def _normalize_headers(self, headers):
        return _normalize_headers(headers)

# 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 = self._normalize_headers(headers)

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

            uri = iri2uri(uri)

            (scheme, authority, request_uri, defrag_uri) = urlnorm(uri)
            domain_port = authority.split(":")[0:2]
            if len(domain_port) == 2 and domain_port[1] == '443' and scheme == 'http':
                scheme = 'https'
                authority = domain_port[0]

            proxy_info = self._get_proxy_info(scheme, authority)

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

            if 'range' not in headers and 'accept-encoding' not in headers:
                headers['accept-encoding'] = 'gzip, deflate'

            info = email.Message.Message()
            cached_value = None
            if self.cache:
                cachekey = defrag_uri.encode('utf-8')
                cached_value = self.cache.get(cachekey)
                if cached_value:
                    # info = email.message_from_string(cached_value)
                    #
                    # Need to replace the line above with the kludge below
                    # to fix the non-existent bug not fixed in this
                    # bug report: http://mail.python.org/pipermail/python-bugs-list/2005-September/030289.html
                    try:
                        info, content = cached_value.split('\r\n\r\n', 1)
                        feedparser = email.FeedParser.FeedParser()
                        feedparser.feed(info)
                        info = feedparser.close()
                        feedparser._parse = None
                    except (IndexError, ValueError):
                        self.cache.delete(cachekey)
                        cachekey = None
                        cached_value = None
            else:
                cachekey = None

            if method in self.optimistic_concurrency_methods and self.cache and 'etag' in info 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)

            # Check the vary header in the cache to see if this request
            # matches what varies in the cache.
            if method in ['GET', 'HEAD'] and 'vary' in info:
                vary = info['vary']
                vary_headers = vary.lower().replace(' ', '').split(',')
                for header in vary_headers:
                    key = '-varied-%s' % header
                    value = info[key]
                    if headers.get(header, None) != value:
                        cached_value = None
                        break

            if cached_value and method in ["GET", "HEAD"] and self.cache and 'range' not in headers:
                if '-x-permanent-redirect-url' in info:
                    # Should cached permanent redirects be counted in our redirection count? For now, yes.
                    if redirections <= 0:
                        raise RedirectLimit("Redirected more times than rediection_limit allows.", {}, "")
                    (response, new_content) = self.request(
                        info['-x-permanent-redirect-url'], method='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 'etag' in info and not self.ignore_etag and not 'if-none-match' in headers:
                            headers['if-none-match'] = info['etag']
                        if 'last-modified' in info 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:
                cc = _parse_cache_control(headers)
                if 'only-if-cached' in cc:
                    info['status'] = '504'
                    response = Response(info)
                    content = ""
                else:
                    (response, content) = self._request(conn, authority, uri, request_uri, method, body, headers, redirections, cachekey)
        except Exception as 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)

    def _get_proxy_info(self, scheme, authority):
        """Return a ProxyInfo instance (or None) based on the scheme
        and authority.
        """
        hostname, port = urllib.splitport(authority)
        proxy_info = self.proxy_info
        if callable(proxy_info):
            proxy_info = proxy_info(scheme)

        if (hasattr(proxy_info, 'applies_to')
            and not proxy_info.applies_to(hostname)):
            proxy_info = None
        return proxy_info


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.lower()] = 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.lower()] = value
            self.status = int(self['status'])
        else:
            for key, value in info.iteritems():
                self[key.lower()] = value
            self.status = int(self.get('status', self.status))
            self.reason = self.get('reason', self.reason)

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