summaryrefslogtreecommitdiffstats
path: root/Lib/http/client.py
blob: 4885f5a6ffa0b9c71b12534c5841099dd5fca0fa (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
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
"""HTTP/1.1 client library

<intro stuff goes here>
<other stuff, too>

HTTPConnection goes through a number of "states", which define when a client
may legally make another request or fetch the response for a particular
request. This diagram details these state transitions:

    (null)
      |
      | HTTPConnection()
      v
    Idle
      |
      | putrequest()
      v
    Request-started
      |
      | ( putheader() )*  endheaders()
      v
    Request-sent
      |
      | response = getresponse()
      v
    Unread-response   [Response-headers-read]
      |\____________________
      |                     |
      | response.read()     | putrequest()
      v                     v
    Idle                  Req-started-unread-response
                     ______/|
                   /        |
   response.read() |        | ( putheader() )*  endheaders()
                   v        v
       Request-started    Req-sent-unread-response
                            |
                            | response.read()
                            v
                          Request-sent

This diagram presents the following rules:
  -- a second request may not be started until {response-headers-read}
  -- a response [object] cannot be retrieved until {request-sent}
  -- there is no differentiation between an unread response body and a
     partially read response body

Note: this enforcement is applied by the HTTPConnection class. The
      HTTPResponse class does not enforce this state machine, which
      implies sophisticated clients may accelerate the request/response
      pipeline. Caution should be taken, though: accelerating the states
      beyond the above pattern may imply knowledge of the server's
      connection-close behavior for certain requests. For example, it
      is impossible to tell whether the server will close the connection
      UNTIL the response headers have been read; this means that further
      requests cannot be placed into the pipeline until it is known that
      the server will NOT be closing the connection.

Logical State                  __state            __response
-------------                  -------            ----------
Idle                           _CS_IDLE           None
Request-started                _CS_REQ_STARTED    None
Request-sent                   _CS_REQ_SENT       None
Unread-response                _CS_IDLE           <response_class>
Req-started-unread-response    _CS_REQ_STARTED    <response_class>
Req-sent-unread-response       _CS_REQ_SENT       <response_class>
"""

import email.parser
import email.message
import io
import os
import socket
from urllib.parse import urlsplit
import warnings

__all__ = ["HTTPResponse", "HTTPConnection",
           "HTTPException", "NotConnected", "UnknownProtocol",
           "UnknownTransferEncoding", "UnimplementedFileMode",
           "IncompleteRead", "InvalidURL", "ImproperConnectionState",
           "CannotSendRequest", "CannotSendHeader", "ResponseNotReady",
           "BadStatusLine", "error", "responses"]

HTTP_PORT = 80
HTTPS_PORT = 443

_UNKNOWN = 'UNKNOWN'

# connection states
_CS_IDLE = 'Idle'
_CS_REQ_STARTED = 'Request-started'
_CS_REQ_SENT = 'Request-sent'

# status codes
# informational
CONTINUE = 100
SWITCHING_PROTOCOLS = 101
PROCESSING = 102

# successful
OK = 200
CREATED = 201
ACCEPTED = 202
NON_AUTHORITATIVE_INFORMATION = 203
NO_CONTENT = 204
RESET_CONTENT = 205
PARTIAL_CONTENT = 206
MULTI_STATUS = 207
IM_USED = 226

# redirection
MULTIPLE_CHOICES = 300
MOVED_PERMANENTLY = 301
FOUND = 302
SEE_OTHER = 303
NOT_MODIFIED = 304
USE_PROXY = 305
TEMPORARY_REDIRECT = 307

# client error
BAD_REQUEST = 400
UNAUTHORIZED = 401
PAYMENT_REQUIRED = 402
FORBIDDEN = 403
NOT_FOUND = 404
METHOD_NOT_ALLOWED = 405
NOT_ACCEPTABLE = 406
PROXY_AUTHENTICATION_REQUIRED = 407
REQUEST_TIMEOUT = 408
CONFLICT = 409
GONE = 410
LENGTH_REQUIRED = 411
PRECONDITION_FAILED = 412
REQUEST_ENTITY_TOO_LARGE = 413
REQUEST_URI_TOO_LONG = 414
UNSUPPORTED_MEDIA_TYPE = 415
REQUESTED_RANGE_NOT_SATISFIABLE = 416
EXPECTATION_FAILED = 417
UNPROCESSABLE_ENTITY = 422
LOCKED = 423
FAILED_DEPENDENCY = 424
UPGRADE_REQUIRED = 426

# server error
INTERNAL_SERVER_ERROR = 500
NOT_IMPLEMENTED = 501
BAD_GATEWAY = 502
SERVICE_UNAVAILABLE = 503
GATEWAY_TIMEOUT = 504
HTTP_VERSION_NOT_SUPPORTED = 505
INSUFFICIENT_STORAGE = 507
NOT_EXTENDED = 510

# Mapping status codes to official W3C names
responses = {
    100: 'Continue',
    101: 'Switching Protocols',

    200: 'OK',
    201: 'Created',
    202: 'Accepted',
    203: 'Non-Authoritative Information',
    204: 'No Content',
    205: 'Reset Content',
    206: 'Partial Content',

    300: 'Multiple Choices',
    301: 'Moved Permanently',
    302: 'Found',
    303: 'See Other',
    304: 'Not Modified',
    305: 'Use Proxy',
    306: '(Unused)',
    307: 'Temporary Redirect',

    400: 'Bad Request',
    401: 'Unauthorized',
    402: 'Payment Required',
    403: 'Forbidden',
    404: 'Not Found',
    405: 'Method Not Allowed',
    406: 'Not Acceptable',
    407: 'Proxy Authentication Required',
    408: 'Request Timeout',
    409: 'Conflict',
    410: 'Gone',
    411: 'Length Required',
    412: 'Precondition Failed',
    413: 'Request Entity Too Large',
    414: 'Request-URI Too Long',
    415: 'Unsupported Media Type',
    416: 'Requested Range Not Satisfiable',
    417: 'Expectation Failed',

    500: 'Internal Server Error',
    501: 'Not Implemented',
    502: 'Bad Gateway',
    503: 'Service Unavailable',
    504: 'Gateway Timeout',
    505: 'HTTP Version Not Supported',
}

# maximal amount of data to read at one time in _safe_read
MAXAMOUNT = 1048576

class HTTPMessage(email.message.Message):
    # XXX The only usage of this method is in
    # http.server.CGIHTTPRequestHandler.  Maybe move the code there so
    # that it doesn't need to be part of the public API.  The API has
    # never been defined so this could cause backwards compatibility
    # issues.

    def getallmatchingheaders(self, name):
        """Find all header lines matching a given header name.

        Look through the list of headers and find all lines matching a given
        header name (and their continuation lines).  A list of the lines is
        returned, without interpretation.  If the header does not occur, an
        empty list is returned.  If the header occurs multiple times, all
        occurrences are returned.  Case is not important in the header name.

        """
        name = name.lower() + ':'
        n = len(name)
        lst = []
        hit = 0
        for line in self.keys():
            if line[:n].lower() == name:
                hit = 1
            elif not line[:1].isspace():
                hit = 0
            if hit:
                lst.append(line)
        return lst

def parse_headers(fp, _class=HTTPMessage):
    """Parses only RFC2822 headers from a file pointer.

    email Parser wants to see strings rather than bytes.
    But a TextIOWrapper around self.rfile would buffer too many bytes
    from the stream, bytes which we later need to read as bytes.
    So we read the correct bytes here, as bytes, for email Parser
    to parse.

    """
    headers = []
    while True:
        line = fp.readline()
        headers.append(line)
        if line in (b'\r\n', b'\n', b''):
            break
    hstring = b''.join(headers).decode('iso-8859-1')
    return email.parser.Parser(_class=_class).parsestr(hstring)

class HTTPResponse(io.RawIOBase):

    # strict: If true, raise BadStatusLine if the status line can't be
    # parsed as a valid HTTP/1.0 or 1.1 status line.  By default it is
    # false because it prevents clients from talking to HTTP/0.9
    # servers.  Note that a response with a sufficiently corrupted
    # status line will look like an HTTP/0.9 response.

    # See RFC 2616 sec 19.6 and RFC 1945 sec 6 for details.

    # The bytes from the socket object are iso-8859-1 strings.
    # See RFC 2616 sec 2.2 which notes an exception for MIME-encoded
    # text following RFC 2047.  The basic status line parsing only
    # accepts iso-8859-1.

    def __init__(self, sock, debuglevel=0, strict=0, method=None, url=None):
        # If the response includes a content-length header, we need to
        # make sure that the client doesn't read more than the
        # specified number of bytes.  If it does, it will block until
        # the server times out and closes the connection.  This will
        # happen if a self.fp.read() is done (without a size) whether
        # self.fp is buffered or not.  So, no self.fp.read() by
        # clients unless they know what they are doing.
        self.fp = sock.makefile("rb")
        self.debuglevel = debuglevel
        self.strict = strict
        self._method = method

        # The HTTPResponse object is returned via urllib.  The clients
        # of http and urllib expect different attributes for the
        # headers.  headers is used here and supports urllib.  msg is
        # provided as a backwards compatibility layer for http
        # clients.

        self.headers = self.msg = None

        # from the Status-Line of the response
        self.version = _UNKNOWN # HTTP-Version
        self.status = _UNKNOWN  # Status-Code
        self.reason = _UNKNOWN  # Reason-Phrase

        self.chunked = _UNKNOWN         # is "chunked" being used?
        self.chunk_left = _UNKNOWN      # bytes left to read in current chunk
        self.length = _UNKNOWN          # number of bytes left in response
        self.will_close = _UNKNOWN      # conn will close at end of response

    def _read_status(self):
        # Initialize with Simple-Response defaults.
        line = str(self.fp.readline(), "iso-8859-1")
        if self.debuglevel > 0:
            print("reply:", repr(line))
        if not line:
            # Presumably, the server closed the connection before
            # sending a valid response.
            raise BadStatusLine(line)
        try:
            [version, status, reason] = line.split(None, 2)
        except ValueError:
            try:
                [version, status] = line.split(None, 1)
                reason = ""
            except ValueError:
                # empty version will cause next test to fail and status
                # will be treated as 0.9 response.
                version = ""
        if not version.startswith("HTTP/"):
            if self.strict:
                self.close()
                raise BadStatusLine(line)
            else:
                # Assume it's a Simple-Response from an 0.9 server.
                # We have to convert the first line back to raw bytes
                # because self.fp.readline() needs to return bytes.
                self.fp = LineAndFileWrapper(bytes(line, "ascii"), self.fp)
                return "HTTP/0.9", 200, ""

        # The status code is a three-digit number
        try:
            status = int(status)
            if status < 100 or status > 999:
                raise BadStatusLine(line)
        except ValueError:
            raise BadStatusLine(line)
        return version, status, reason

    def begin(self):
        if self.headers is not None:
            # we've already started reading the response
            return

        # read until we get a non-100 response
        while True:
            version, status, reason = self._read_status()
            if status != CONTINUE:
                break
            # skip the header from the 100 response
            while True:
                skip = self.fp.readline().strip()
                if not skip:
                    break
                if self.debuglevel > 0:
                    print("header:", skip)

        self.code = self.status = status
        self.reason = reason.strip()
        if version == "HTTP/1.0":
            self.version = 10
        elif version.startswith("HTTP/1."):
            self.version = 11   # use HTTP/1.1 code for HTTP/1.x where x>=1
        elif version == "HTTP/0.9":
            self.version = 9
        else:
            raise UnknownProtocol(version)

        if self.version == 9:
            self.length = None
            self.chunked = False
            self.will_close = True
            self.headers = self.msg = email.message_from_string('')
            return

        self.headers = self.msg = parse_headers(self.fp)

        if self.debuglevel > 0:
            for hdr in self.headers:
                print("header:", hdr, end=" ")

        # are we using the chunked-style of transfer encoding?
        tr_enc = self.headers.get("transfer-encoding")
        if tr_enc and tr_enc.lower() == "chunked":
            self.chunked = True
            self.chunk_left = None
        else:
            self.chunked = False

        # will the connection close at the end of the response?
        self.will_close = self._check_close()

        # do we have a Content-Length?
        # NOTE: RFC 2616, S4.4, #3 says we ignore this if tr_enc is "chunked"
        self.length = None
        length = self.headers.get("content-length")

         # are we using the chunked-style of transfer encoding?
        tr_enc = self.headers.get("transfer-encoding")
        if length and not self.chunked:
            try:
                self.length = int(length)
            except ValueError:
                self.length = None
            else:
                if self.length < 0:  # ignore nonsensical negative lengths
                    self.length = None
        else:
            self.length = None

        # does the body have a fixed length? (of zero)
        if (status == NO_CONTENT or status == NOT_MODIFIED or
            100 <= status < 200 or      # 1xx codes
            self._method == "HEAD"):
            self.length = 0

        # if the connection remains open, and we aren't using chunked, and
        # a content-length was not provided, then assume that the connection
        # WILL close.
        if (not self.will_close and
            not self.chunked and
            self.length is None):
            self.will_close = True

    def _check_close(self):
        conn = self.headers.get("connection")
        if self.version == 11:
            # An HTTP/1.1 proxy is assumed to stay open unless
            # explicitly closed.
            conn = self.headers.get("connection")
            if conn and "close" in conn.lower():
                return True
            return False

        # Some HTTP/1.0 implementations have support for persistent
        # connections, using rules different than HTTP/1.1.

        # For older HTTP, Keep-Alive indicates persistent connection.
        if self.headers.get("keep-alive"):
            return False

        # At least Akamai returns a "Connection: Keep-Alive" header,
        # which was supposed to be sent by the client.
        if conn and "keep-alive" in conn.lower():
            return False

        # Proxy-Connection is a netscape hack.
        pconn = self.headers.get("proxy-connection")
        if pconn and "keep-alive" in pconn.lower():
            return False

        # otherwise, assume it will close
        return True

    def close(self):
        if self.fp:
            self.fp.close()
            self.fp = None

    # These implementations are for the benefit of io.BufferedReader.

    # XXX This class should probably be revised to act more like
    # the "raw stream" that BufferedReader expects.

    @property
    def closed(self):
        return self.isclosed()

    def flush(self):
        self.fp.flush()

    # End of "raw stream" methods

    def isclosed(self):
        # NOTE: it is possible that we will not ever call self.close(). This
        #       case occurs when will_close is TRUE, length is None, and we
        #       read up to the last byte, but NOT past it.
        #
        # IMPLIES: if will_close is FALSE, then self.close() will ALWAYS be
        #          called, meaning self.isclosed() is meaningful.
        return self.fp is None

    def read(self, amt=None):
        if self.fp is None:
            return b""

        if self.chunked:
            return self._read_chunked(amt)

        if amt is None:
            # unbounded read
            if self.length is None:
                s = self.fp.read()
            else:
                s = self._safe_read(self.length)
                self.length = 0
            self.close()        # we read everything
            return s

        if self.length is not None:
            if amt > self.length:
                # clip the read to the "end of response"
                amt = self.length

        # we do not use _safe_read() here because this may be a .will_close
        # connection, and the user is reading more bytes than will be provided
        # (for example, reading in 1k chunks)
        s = self.fp.read(amt)
        if self.length is not None:
            self.length -= len(s)
            if not self.length:
                self.close()
        return s

    def _read_chunked(self, amt):
        assert self.chunked != _UNKNOWN
        chunk_left = self.chunk_left
        value = b""

        # XXX This accumulates chunks by repeated string concatenation,
        # which is not efficient as the number or size of chunks gets big.
        while True:
            if chunk_left is None:
                line = self.fp.readline()
                i = line.find(b";")
                if i >= 0:
                    line = line[:i] # strip chunk-extensions
                try:
                    chunk_left = int(line, 16)
                except ValueError:
                    # close the connection as protocol synchronisation is
                    # probably lost
                    self.close()
                    raise IncompleteRead(value)
                if chunk_left == 0:
                    break
            if amt is None:
                value += self._safe_read(chunk_left)
            elif amt < chunk_left:
                value += self._safe_read(amt)
                self.chunk_left = chunk_left - amt
                return value
            elif amt == chunk_left:
                value += self._safe_read(amt)
                self._safe_read(2)  # toss the CRLF at the end of the chunk
                self.chunk_left = None
                return value
            else:
                value += self._safe_read(chunk_left)
                amt -= chunk_left

            # we read the whole chunk, get another
            self._safe_read(2)      # toss the CRLF at the end of the chunk
            chunk_left = None

        # read and discard trailer up to the CRLF terminator
        ### note: we shouldn't have any trailers!
        while True:
            line = self.fp.readline()
            if not line:
                # a vanishingly small number of sites EOF without
                # sending the trailer
                break
            if line == b"\r\n":
                break

        # we read everything; close the "file"
        self.close()

        return value

    def _safe_read(self, amt):
        """Read the number of bytes requested, compensating for partial reads.

        Normally, we have a blocking socket, but a read() can be interrupted
        by a signal (resulting in a partial read).

        Note that we cannot distinguish between EOF and an interrupt when zero
        bytes have been read. IncompleteRead() will be raised in this
        situation.

        This function should be used when <amt> bytes "should" be present for
        reading. If the bytes are truly not available (due to EOF), then the
        IncompleteRead exception can be used to detect the problem.
        """
        s = []
        while amt > 0:
            chunk = self.fp.read(min(amt, MAXAMOUNT))
            if not chunk:
                raise IncompleteRead(b''.join(s), amt)
            s.append(chunk)
            amt -= len(chunk)
        return b"".join(s)

    def fileno(self):
        return self.fp.fileno()

    def getheader(self, name, default=None):
        if self.headers is None:
            raise ResponseNotReady()
        return ', '.join(self.headers.get_all(name, default))

    def getheaders(self):
        """Return list of (header, value) tuples."""
        if self.headers is None:
            raise ResponseNotReady()
        return list(self.headers.items())

    # We override IOBase.__iter__ so that it doesn't check for closed-ness

    def __iter__(self):
        return self

    # For compatibility with old-style urllib responses.

    def info(self):
        return self.headers

    def geturl(self):
        return self.url

    def getcode(self):
        return self.status

class HTTPConnection:

    _http_vsn = 11
    _http_vsn_str = 'HTTP/1.1'

    response_class = HTTPResponse
    default_port = HTTP_PORT
    auto_open = 1
    debuglevel = 0
    strict = 0

    def __init__(self, host, port=None, strict=None,
                 timeout=socket._GLOBAL_DEFAULT_TIMEOUT):
        self.timeout = timeout
        self.sock = None
        self._buffer = []
        self.__response = None
        self.__state = _CS_IDLE
        self._method = None

        self._set_hostport(host, port)
        if strict is not None:
            self.strict = strict

    def _set_hostport(self, host, port):
        if port is None:
            i = host.rfind(':')
            j = host.rfind(']')         # ipv6 addresses have [...]
            if i > j:
                try:
                    port = int(host[i+1:])
                except ValueError:
                    raise InvalidURL("nonnumeric port: '%s'" % host[i+1:])
                host = host[:i]
            else:
                port = self.default_port
            if host and host[0] == '[' and host[-1] == ']':
                host = host[1:-1]
        self.host = host
        self.port = port

    def set_debuglevel(self, level):
        self.debuglevel = level

    def connect(self):
        """Connect to the host and port specified in __init__."""
        self.sock = socket.create_connection((self.host,self.port),
                                             self.timeout)

    def close(self):
        """Close the connection to the HTTP server."""
        if self.sock:
            self.sock.close()   # close it manually... there may be other refs
            self.sock = None
        if self.__response:
            self.__response.close()
            self.__response = None
        self.__state = _CS_IDLE

    def send(self, str):
        """Send `str' to the server."""
        if self.sock is None:
            if self.auto_open:
                self.connect()
            else:
                raise NotConnected()

        # send the data to the server. if we get a broken pipe, then close
        # the socket. we want to reconnect when somebody tries to send again.
        #
        # NOTE: we DO propagate the error, though, because we cannot simply
        #       ignore the error... the caller will know if they can retry.
        if self.debuglevel > 0:
            print("send:", repr(str))
        blocksize = 8192
        if hasattr(str, "read") :
            if self.debuglevel > 0:
                print("sendIng a read()able")
            encode = False
            if "b" not in str.mode:
                encode = True
                if self.debuglevel > 0:
                    print("encoding file using iso-8859-1")
            while 1:
                data = str.read(blocksize)
                if not data:
                    break
                if encode:
                    data = data.encode("iso-8859-1")
                self.sock.sendall(data)
        else:
            self.sock.sendall(str)

    def _output(self, s):
        """Add a line of output to the current request buffer.

        Assumes that the line does *not* end with \\r\\n.
        """
        self._buffer.append(s)

    def _send_output(self, message_body=None):
        """Send the currently buffered request and clear the buffer.

        Appends an extra \\r\\n to the buffer.
        A message_body may be specified, to be appended to the request.
        """
        self._buffer.extend((b"", b""))
        msg = b"\r\n".join(self._buffer)
        del self._buffer[:]
        # If msg and message_body are sent in a single send() call,
        # it will avoid performance problems caused by the interaction
        # between delayed ack and the Nagle algorithim.
        if isinstance(message_body, bytes):
            msg += message_body
            message_body = None
        self.send(msg)
        if message_body is not None:
            # message_body was not a string (i.e. it is a file), and
            # we must run the risk of Nagle.
            self.send(message_body)

    def putrequest(self, method, url, skip_host=0, skip_accept_encoding=0):
        """Send a request to the server.

        `method' specifies an HTTP request method, e.g. 'GET'.
        `url' specifies the object being requested, e.g. '/index.html'.
        `skip_host' if True does not add automatically a 'Host:' header
        `skip_accept_encoding' if True does not add automatically an
           'Accept-Encoding:' header
        """

        # if a prior response has been completed, then forget about it.
        if self.__response and self.__response.isclosed():
            self.__response = None


        # in certain cases, we cannot issue another request on this connection.
        # this occurs when:
        #   1) we are in the process of sending a request.   (_CS_REQ_STARTED)
        #   2) a response to a previous request has signalled that it is going
        #      to close the connection upon completion.
        #   3) the headers for the previous response have not been read, thus
        #      we cannot determine whether point (2) is true.   (_CS_REQ_SENT)
        #
        # if there is no prior response, then we can request at will.
        #
        # if point (2) is true, then we will have passed the socket to the
        # response (effectively meaning, "there is no prior response"), and
        # will open a new one when a new request is made.
        #
        # Note: if a prior response exists, then we *can* start a new request.
        #       We are not allowed to begin fetching the response to this new
        #       request, however, until that prior response is complete.
        #
        if self.__state == _CS_IDLE:
            self.__state = _CS_REQ_STARTED
        else:
            raise CannotSendRequest(self.__state)

        # Save the method we use, we need it later in the response phase
        self._method = method
        if not url:
            url = '/'
        request = '%s %s %s' % (method, url, self._http_vsn_str)

        # Non-ASCII characters should have been eliminated earlier
        self._output(request.encode('ascii'))

        if self._http_vsn == 11:
            # Issue some standard headers for better HTTP/1.1 compliance

            if not skip_host:
                # this header is issued *only* for HTTP/1.1
                # connections. more specifically, this means it is
                # only issued when the client uses the new
                # HTTPConnection() class. backwards-compat clients
                # will be using HTTP/1.0 and those clients may be
                # issuing this header themselves. we should NOT issue
                # it twice; some web servers (such as Apache) barf
                # when they see two Host: headers

                # If we need a non-standard port,include it in the
                # header.  If the request is going through a proxy,
                # but the host of the actual URL, not the host of the
                # proxy.

                netloc = ''
                if url.startswith('http'):
                    nil, netloc, nil, nil, nil = urlsplit(url)

                if netloc:
                    try:
                        netloc_enc = netloc.encode("ascii")
                    except UnicodeEncodeError:
                        netloc_enc = netloc.encode("idna")
                    self.putheader('Host', netloc_enc)
                else:
                    try:
                        host_enc = self.host.encode("ascii")
                    except UnicodeEncodeError:
                        host_enc = self.host.encode("idna")
                    if self.port == self.default_port:
                        self.putheader('Host', host_enc)
                    else:
                        host_enc = host_enc.decode("ascii")
                        self.putheader('Host', "%s:%s" % (host_enc, self.port))

            # note: we are assuming that clients will not attempt to set these
            #       headers since *this* library must deal with the
            #       consequences. this also means that when the supporting
            #       libraries are updated to recognize other forms, then this
            #       code should be changed (removed or updated).

            # we only want a Content-Encoding of "identity" since we don't
            # support encodings such as x-gzip or x-deflate.
            if not skip_accept_encoding:
                self.putheader('Accept-Encoding', 'identity')

            # we can accept "chunked" Transfer-Encodings, but no others
            # NOTE: no TE header implies *only* "chunked"
            #self.putheader('TE', 'chunked')

            # if TE is supplied in the header, then it must appear in a
            # Connection header.
            #self.putheader('Connection', 'TE')

        else:
            # For HTTP/1.0, the server will assume "not chunked"
            pass

    def putheader(self, header, *values):
        """Send a request header line to the server.

        For example: h.putheader('Accept', 'text/html')
        """
        if self.__state != _CS_REQ_STARTED:
            raise CannotSendHeader()

        if hasattr(header, 'encode'):
            header = header.encode('ascii')
        values = list(values)
        for i, one_value in enumerate(values):
            if hasattr(one_value, 'encode'):
                values[i] = one_value.encode('ascii')
        value = b'\r\n\t'.join(values)
        header = header + b': ' + value
        self._output(header)

    def endheaders(self, message_body=None):
        """Indicate that the last header line has been sent to the server.

        This method sends the request to the server.  The optional
        message_body argument can be used to pass message body
        associated with the request.  The message body will be sent in
        the same packet as the message headers if possible.  The
        message_body should be a string.
        """
        if self.__state == _CS_REQ_STARTED:
            self.__state = _CS_REQ_SENT
        else:
            raise CannotSendHeader()
        self._send_output(message_body)

    def request(self, method, url, body=None, headers={}):
        """Send a complete request to the server."""
        self._send_request(method, url, body, headers)

    def _set_content_length(self, body):
        # Set the content-length based on the body.
        thelen = None
        try:
            thelen = str(len(body))
        except TypeError as te:
            # If this is a file-like object, try to
            # fstat its file descriptor
            try:
                thelen = str(os.fstat(body.fileno()).st_size)
            except (AttributeError, OSError):
                # Don't send a length if this failed
                if self.debuglevel > 0: print("Cannot stat!!")

        if thelen is not None:
            self.putheader('Content-Length', thelen)

    def _send_request(self, method, url, body, headers):
        # Honor explicitly requested Host: and Accept-Encoding: headers.
        header_names = dict.fromkeys([k.lower() for k in headers])
        skips = {}
        if 'host' in header_names:
            skips['skip_host'] = 1
        if 'accept-encoding' in header_names:
            skips['skip_accept_encoding'] = 1

        self.putrequest(method, url, **skips)

        if body and ('content-length' not in header_names):
            self._set_content_length(body)
        for hdr, value in headers.items():
            self.putheader(hdr, value)
        if isinstance(body, str):
            # RFC 2616 Section 3.7.1 says that text default has a
            # default charset of iso-8859-1.
            body = body.encode('iso-8859-1')
        self.endheaders(body)

    def getresponse(self):
        """Get the response from the server.

        If the HTTPConnection is in the correct state, returns an
        instance of HTTPResponse or of whatever object is returned by
        class the response_class variable.

        If a request has not been sent or if a previous response has
        not be handled, ResponseNotReady is raised.  If the HTTP
        response indicates that the connection should be closed, then
        it will be closed before the response is returned.  When the
        connection is closed, the underlying socket is closed.
        """

        # if a prior response has been completed, then forget about it.
        if self.__response and self.__response.isclosed():
            self.__response = None

        # if a prior response exists, then it must be completed (otherwise, we
        # cannot read this response's header to determine the connection-close
        # behavior)
        #
        # note: if a prior response existed, but was connection-close, then the
        # socket and response were made independent of this HTTPConnection
        # object since a new request requires that we open a whole new
        # connection
        #
        # this means the prior response had one of two states:
        #   1) will_close: this connection was reset and the prior socket and
        #                  response operate independently
        #   2) persistent: the response was retained and we await its
        #                  isclosed() status to become true.
        #
        if self.__state != _CS_REQ_SENT or self.__response:
            raise ResponseNotReady(self.__state)

        if self.debuglevel > 0:
            response = self.response_class(self.sock, self.debuglevel,
                                           strict=self.strict,
                                           method=self._method)
        else:
            response = self.response_class(self.sock, strict=self.strict,
                                           method=self._method)

        response.begin()
        assert response.will_close != _UNKNOWN
        self.__state = _CS_IDLE

        if response.will_close:
            # this effectively passes the connection to the response
            self.close()
        else:
            # remember this, so we can tell when it is complete
            self.__response = response

        return response

try:
    import ssl
except ImportError:
    pass
else:
    class HTTPSConnection(HTTPConnection):
        "This class allows communication via SSL."

        default_port = HTTPS_PORT

        def __init__(self, host, port=None, key_file=None, cert_file=None,
                     strict=None, timeout=socket._GLOBAL_DEFAULT_TIMEOUT):
            HTTPConnection.__init__(self, host, port, strict, timeout)
            self.key_file = key_file
            self.cert_file = cert_file

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

            sock = socket.create_connection((self.host, self.port),
                                            self.timeout)
            self.sock = ssl.wrap_socket(sock, self.key_file, self.cert_file)


    def FakeSocket (sock, sslobj):
        warnings.warn("FakeSocket is deprecated, and won't be in 3.x.  " +
                      "Use the result of ssl.wrap_socket() directly instead.",
                      DeprecationWarning, stacklevel=2)
        return sslobj

    __all__.append("HTTPSConnection")

class HTTPException(Exception):
    # Subclasses that define an __init__ must call Exception.__init__
    # or define self.args.  Otherwise, str() will fail.
    pass

class NotConnected(HTTPException):
    pass

class InvalidURL(HTTPException):
    pass

class UnknownProtocol(HTTPException):
    def __init__(self, version):
        self.args = version,
        self.version = version

class UnknownTransferEncoding(HTTPException):
    pass

class UnimplementedFileMode(HTTPException):
    pass

class IncompleteRead(HTTPException):
    def __init__(self, partial, expected=None):
        self.args = partial,
        self.partial = partial
        self.expected = expected
    def __repr__(self):
        if self.expected is not None:
            e = ', %i more expected' % self.expected
        else:
            e = ''
        return 'IncompleteRead(%i bytes read%s)' % (len(self.partial), e)
    def __str__(self):
        return repr(self)

class ImproperConnectionState(HTTPException):
    pass

class CannotSendRequest(ImproperConnectionState):
    pass

class CannotSendHeader(ImproperConnectionState):
    pass

class ResponseNotReady(ImproperConnectionState):
    pass

class BadStatusLine(HTTPException):
    def __init__(self, line):
        self.args = line,
        self.line = line

# for backwards compatibility
error = HTTPException

class LineAndFileWrapper:
    """A limited file-like object for HTTP/0.9 responses."""

    # The status-line parsing code calls readline(), which normally
    # get the HTTP status line.  For a 0.9 response, however, this is
    # actually the first line of the body!  Clients need to get a
    # readable file object that contains that line.

    def __init__(self, line, file):
        self._line = line
        self._file = file
        self._line_consumed = 0
        self._line_offset = 0
        self._line_left = len(line)

    def __getattr__(self, attr):
        return getattr(self._file, attr)

    def _done(self):
        # called when the last byte is read from the line.  After the
        # call, all read methods are delegated to the underlying file
        # object.
        self._line_consumed = 1
        self.read = self._file.read
        self.readline = self._file.readline
        self.readlines = self._file.readlines

    def read(self, amt=None):
        if self._line_consumed:
            return self._file.read(amt)
        assert self._line_left
        if amt is None or amt > self._line_left:
            s = self._line[self._line_offset:]
            self._done()
            if amt is None:
                return s + self._file.read()
            else:
                return s + self._file.read(amt - len(s))
        else:
            assert amt <= self._line_left
            i = self._line_offset
            j = i + amt
            s = self._line[i:j]
            self._line_offset = j
            self._line_left -= amt
            if self._line_left == 0:
                self._done()
            return s

    def readline(self):
        if self._line_consumed:
            return self._file.readline()
        assert self._line_left
        s = self._line[self._line_offset:]
        self._done()
        return s

    def readlines(self, size=None):
        if self._line_consumed:
            return self._file.readlines(size)
        assert self._line_left
        L = [self._line[self._line_offset:]]
        self._done()
        if size is None:
            return L + self._file.readlines()
        else:
            return L + self._file.readlines(size)