summaryrefslogtreecommitdiffstats
path: root/Lib/httplib.py
blob: d367ea7ac29f091ff51f1f82e824e8f70eca614e (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
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
"""HTTP/1.1 client library

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

HTTPConnection go through a number of "states", which defines 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 errno
import mimetools
import socket
from urlparse import urlsplit

try:
    from cStringIO import StringIO
except ImportError:
    from StringIO import StringIO

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

HTTP_PORT = 80
HTTPS_PORT = 443

_UNKNOWN = 'UNKNOWN'

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

class HTTPMessage(mimetools.Message):

    def addheader(self, key, value):
        """Add header for field key handling repeats."""
        prev = self.dict.get(key)
        if prev is None:
            self.dict[key] = value
        else:
            combined = ", ".join((prev, value))
            self.dict[key] = combined

    def addcontinue(self, key, more):
        """Add more field data from a continuation line."""
        prev = self.dict[key]
        self.dict[key] = prev + "\n " + more

    def readheaders(self):
        """Read header lines.

        Read header lines up to the entirely blank line that terminates them.
        The (normally blank) line that ends the headers is skipped, but not
        included in the returned list.  If a non-header line ends the headers,
        (which is an error), an attempt is made to backspace over it; it is
        never included in the returned list.

        The variable self.status is set to the empty string if all went well,
        otherwise it is an error message.  The variable self.headers is a
        completely uninterpreted list of lines contained in the header (so
        printing them will reproduce the header exactly as it appears in the
        file).

        If multiple header fields with the same name occur, they are combined
        according to the rules in RFC 2616 sec 4.2:

        Appending each subsequent field-value to the first, each separated
        by a comma. The order in which header fields with the same field-name
        are received is significant to the interpretation of the combined
        field value.
        """
        # XXX The implementation overrides the readheaders() method of
        # rfc822.Message.  The base class design isn't amenable to
        # customized behavior here so the method here is a copy of the
        # base class code with a few small changes.

        self.dict = {}
        self.unixfrom = ''
        self.headers = list = []
        self.status = ''
        headerseen = ""
        firstline = 1
        startofline = unread = tell = None
        if hasattr(self.fp, 'unread'):
            unread = self.fp.unread
        elif self.seekable:
            tell = self.fp.tell
        while 1:
            if tell:
                try:
                    startofline = tell()
                except IOError:
                    startofline = tell = None
                    self.seekable = 0
            line = self.fp.readline()
            if not line:
                self.status = 'EOF in headers'
                break
            # Skip unix From name time lines
            if firstline and line.startswith('From '):
                self.unixfrom = self.unixfrom + line
                continue
            firstline = 0
            if headerseen and line[0] in ' \t':
                # XXX Not sure if continuation lines are handled properly
                # for http and/or for repeating headers
                # It's a continuation line.
                list.append(line)
                self.addcontinue(headerseen, line.strip())
                continue
            elif self.iscomment(line):
                # It's a comment.  Ignore it.
                continue
            elif self.islast(line):
                # Note! No pushback here!  The delimiter line gets eaten.
                break
            headerseen = self.isheader(line)
            if headerseen:
                # It's a legal header line, save it.
                list.append(line)
                self.addheader(headerseen, line[len(headerseen)+1:].strip())
                continue
            else:
                # It's not a header line; throw it back and stop here.
                if not self.dict:
                    self.status = 'No headers'
                else:
                    self.status = 'Non-header line where header expected'
                # Try to undo the read.
                if unread:
                    unread(line)
                elif tell:
                    self.fp.seek(startofline)
                else:
                    self.status = self.status + '; bad seek'
                break

class HTTPResponse:

    # 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.

    def __init__(self, sock, debuglevel=0, strict=0):
        self.fp = sock.makefile('rb', 0)
        self.debuglevel = debuglevel
        self.strict = strict

        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 = self.fp.readline()
        if self.debuglevel > 0:
            print "reply:", repr(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
                self.fp = LineAndFileWrapper(line, 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.msg is not None:
            # we've already started reading the response
            return

        # read until we get a non-100 response
        while 1:
            version, status, reason = self._read_status()
            if status != 100:
                break
            # skip the header from the 100 response
            while 1:
                skip = self.fp.readline().strip()
                if not skip:
                    break
                if self.debuglevel > 0:
                    print "header:", skip

        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.chunked = 0
            self.will_close = 1
            self.msg = HTTPMessage(StringIO())
            return

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

        # don't let the msg keep an fp
        self.msg.fp = None

        # are we using the chunked-style of transfer encoding?
        tr_enc = self.msg.getheader('transfer-encoding')
        if tr_enc and tr_enc.lower() == "chunked":
            self.chunked = 1
            self.chunk_left = None
        else:
            self.chunked = 0

        # 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"
        length = self.msg.getheader('content-length')
        if length and not self.chunked:
            try:
                self.length = int(length)
            except ValueError:
                self.length = None
        else:
            self.length = None

        # does the body have a fixed length? (of zero)
        if (status == 204 or            # No Content
            status == 304 or            # Not Modified
            100 <= status < 200):       # 1xx codes
            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 = 1

    def _check_close(self):
        if self.version == 11:
            # An HTTP/1.1 proxy is assumed to stay open unless
            # explicitly closed.
            conn = self.msg.getheader('connection')
            if conn and conn.lower().find("close") >= 0:
                return True
            return False

        # An HTTP/1.0 response with a Connection header is probably
        # the result of a confused proxy.  Ignore it.

        # For older HTTP, Keep-Alive indiciates persistent connection.
        if self.msg.getheader('keep-alive'):
            return False
        
        # Proxy-Connection is a netscape hack.
        pconn = self.msg.getheader('proxy-connection')
        if pconn and pconn.lower().find("keep-alive") >= 0:
            return False

        # otherwise, assume it will close
        return True

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

    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 ''

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

        if amt is None:
            # unbounded read
            if self.will_close:
                s = self.fp.read()
            else:
                s = self._safe_read(self.length)
            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
            self.length -= amt

        # 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)

        return s

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

        # XXX This accumulates chunks by repeated string concatenation,
        # which is not efficient as the number or size of chunks gets big.
        while 1:
            if chunk_left is None:
                line = self.fp.readline()
                i = line.find(';')
                if i >= 0:
                    line = line[:i] # strip chunk-extensions
                chunk_left = int(line, 16)
                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 1:
            line = self.fp.readline()
            if line == '\r\n':
                break

        # we read everything; close the "file"
        # XXX Shouldn't the client 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(amt)
            if not chunk:
                raise IncompleteRead(s)
            s = s + chunk
            amt = amt - len(chunk)
        return s

    def getheader(self, name, default=None):
        if self.msg is None:
            raise ResponseNotReady()
        return self.msg.getheader(name, default)


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):
        self.sock = None
        self._buffer = []
        self.__response = None
        self.__state = _CS_IDLE

        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.find(':')
            if i >= 0:
                try:
                    port = int(host[i+1:])
                except ValueError:
                    raise InvalidURL("nonnumeric port: '%s'" % host[i+1:])
                host = host[:i]
            else:
                port = self.default_port
        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__."""
        msg = "getaddrinfo returns an empty list"
        for res in socket.getaddrinfo(self.host, self.port, 0,
                                      socket.SOCK_STREAM):
            af, socktype, proto, canonname, sa = res
            try:
                self.sock = socket.socket(af, socktype, proto)
                if self.debuglevel > 0:
                    print "connect: (%s, %s)" % (self.host, self.port)
                self.sock.connect(sa)
            except socket.error, msg:
                if self.debuglevel > 0:
                    print 'connect fail:', (self.host, self.port)
                if self.sock:
                    self.sock.close()
                self.sock = None
                continue
            break
        if not self.sock:
            raise socket.error, msg

    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)
        try:
            self.sock.sendall(str)
        except socket.error, v:
            if v[0] == 32:      # Broken pipe
                self.close()
            raise

    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):
        """Send the currently buffered request and clear the buffer.

        Appends an extra \\r\\n to the buffer.
        """
        self._buffer.extend(("", ""))
        msg = "\r\n".join(self._buffer)
        del self._buffer[:]
        self.send(msg)

    def putrequest(self, method, url, skip_host=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'.
        """

        # check if a prior response has been completed
        # XXX What if it hasn't?
        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()

        if not url:
            url = '/'
        str = '%s %s %s' % (method, url, self._http_vsn_str)

        self._output(str)

        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:
                    self.putheader('Host', netloc)
                elif self.port == HTTP_PORT:
                    self.putheader('Host', self.host)
                else:
                    self.putheader('Host', "%s:%s" % (self.host, 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.
            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, value):
        """Send a request header line to the server.

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

        str = '%s: %s' % (header, value)
        self._output(str)

    def endheaders(self):
        """Indicate that the last header line has been sent to the server."""

        if self.__state == _CS_REQ_STARTED:
            self.__state = _CS_REQ_SENT
        else:
            raise CannotSendHeader()

        self._send_output()

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

        try:
            self._send_request(method, url, body, headers)
        except socket.error, v:
            # trap 'Broken pipe' if we're allowed to automatically reconnect
            if v[0] != 32 or not self.auto_open:
                raise
            # try one more time
            self._send_request(method, url, body, headers)

    def _send_request(self, method, url, body, headers):
        # If headers already contains a host header, then define the
        # optional skip_host argument to putrequest().  The check is
        # harder because field names are case insensitive.
        if 'Host' in (headers
            or [k for k in headers.iterkeys() if k.lower() == "host"]):
            self.putrequest(method, url, skip_host=1)
        else:
            self.putrequest(method, url)

        if body:
            self.putheader('Content-Length', str(len(body)))
        for hdr, value in headers.items():
            self.putheader(hdr, value)
        self.endheaders()

        if body:
            self.send(body)

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

        # check if a prior response has been completed
        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()

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

        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

# The next several classes are used to define FakeSocket,a socket-like
# interface to an SSL connection.

# The primary complexity comes from faking a makefile() method.  The
# standard socket makefile() implementation calls dup() on the socket
# file descriptor.  As a consequence, clients can call close() on the
# parent socket and its makefile children in any order.  The underlying
# socket isn't closed until they are all closed.

# The implementation uses reference counting to keep the socket open
# until the last client calls close().  SharedSocket keeps track of
# the reference counting and SharedSocketClient provides an constructor
# and close() method that call incref() and decref() correctly.

class SharedSocket:

    def __init__(self, sock):
        self.sock = sock
        self._refcnt = 0

    def incref(self):
        self._refcnt += 1

    def decref(self):
        self._refcnt -= 1
        assert self._refcnt >= 0
        if self._refcnt == 0:
            self.sock.close()

    def __del__(self):
        self.sock.close()

class SharedSocketClient:

    def __init__(self, shared):
        self._closed = 0
        self._shared = shared
        self._shared.incref()
        self._sock = shared.sock

    def close(self):
        if not self._closed:
            self._shared.decref()
            self._closed = 1
            self._shared = None

class SSLFile(SharedSocketClient):
    """File-like object wrapping an SSL socket."""

    BUFSIZE = 8192

    def __init__(self, sock, ssl, bufsize=None):
        SharedSocketClient.__init__(self, sock)
        self._ssl = ssl
        self._buf = ''
        self._bufsize = bufsize or self.__class__.BUFSIZE

    def _read(self):
        buf = ''
        # put in a loop so that we retry on transient errors
        while 1:
            try:
                buf = self._ssl.read(self._bufsize)
            except socket.sslerror, err:
                if (err[0] == socket.SSL_ERROR_WANT_READ
                    or err[0] == socket.SSL_ERROR_WANT_WRITE):
                    continue
                if (err[0] == socket.SSL_ERROR_ZERO_RETURN
                    or err[0] == socket.SSL_ERROR_EOF):
                    break
                raise
            except socket.error, err:
                if err[0] == errno.EINTR:
                    continue
                if err[0] == errno.EBADF:
                    # XXX socket was closed?
                    break
                raise
            else:
                break
        return buf

    def read(self, size=None):
        L = [self._buf]
        avail = len(self._buf)
        while size is None or avail < size:
            s = self._read()
            if s == '':
                break
            L.append(s)
            avail += len(s)
        all = "".join(L)
        if size is None:
            self._buf = ''
            return all
        else:
            self._buf = all[size:]
            return all[:size]

    def readline(self):
        L = [self._buf]
        self._buf = ''
        while 1:
            i = L[-1].find("\n")
            if i >= 0:
                break
            s = self._read()
            if s == '':
                break
            L.append(s)
        if i == -1:
            # loop exited because there is no more data
            return "".join(L)
        else:
            all = "".join(L)
            # XXX could do enough bookkeeping not to do a 2nd search
            i = all.find("\n") + 1
            line = all[:i]
            self._buf = all[i:]
            return line

class FakeSocket(SharedSocketClient):

    class _closedsocket:
        def __getattr__(self, name):
            raise error(9, 'Bad file descriptor')

    def __init__(self, sock, ssl):
        sock = SharedSocket(sock)
        SharedSocketClient.__init__(self, sock)
        self._ssl = ssl

    def close(self):
        SharedSocketClient.close(self)
        self._sock = self.__class__._closedsocket()

    def makefile(self, mode, bufsize=None):
        if mode != 'r' and mode != 'rb':
            raise UnimplementedFileMode()
        return SSLFile(self._shared, self._ssl, bufsize)

    def send(self, stuff, flags = 0):
        return self._ssl.write(stuff)

    sendall = send

    def recv(self, len = 1024, flags = 0):
        return self._ssl.read(len)

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


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):
        HTTPConnection.__init__(self, host, port, strict)
        self.key_file = key_file
        self.cert_file = cert_file

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

        sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
        sock.connect((self.host, self.port))
        realsock = sock
        if hasattr(sock, "_sock"):
            realsock = sock._sock
        ssl = socket.ssl(realsock, self.key_file, self.cert_file)
        self.sock = FakeSocket(sock, ssl)


class HTTP:
    "Compatibility class with httplib.py from 1.5."

    _http_vsn = 10
    _http_vsn_str = 'HTTP/1.0'

    debuglevel = 0

    _connection_class = HTTPConnection

    def __init__(self, host='', port=None, strict=None):
        "Provide a default host, since the superclass requires one."

        # some joker passed 0 explicitly, meaning default port
        if port == 0:
            port = None

        # Note that we may pass an empty string as the host; this will throw
        # an error when we attempt to connect. Presumably, the client code
        # will call connect before then, with a proper host.
        self._setup(self._connection_class(host, port, strict))

    def _setup(self, conn):
        self._conn = conn

        # set up delegation to flesh out interface
        self.send = conn.send
        self.putrequest = conn.putrequest
        self.endheaders = conn.endheaders
        self.set_debuglevel = conn.set_debuglevel

        conn._http_vsn = self._http_vsn
        conn._http_vsn_str = self._http_vsn_str

        self.file = None

    def connect(self, host=None, port=None):
        "Accept arguments to set the host/port, since the superclass doesn't."

        if host is not None:
            self._conn._set_hostport(host, port)
        self._conn.connect()

    def getfile(self):
        "Provide a getfile, since the superclass' does not use this concept."
        return self.file

    def putheader(self, header, *values):
        "The superclass allows only one value argument."
        self._conn.putheader(header, '\r\n\t'.join(values))

    def getreply(self):
        """Compat definition since superclass does not define it.

        Returns a tuple consisting of:
        - server status code (e.g. '200' if all goes well)
        - server "reason" corresponding to status code
        - any RFC822 headers in the response from the server
        """
        try:
            response = self._conn.getresponse()
        except BadStatusLine, e:
            ### hmm. if getresponse() ever closes the socket on a bad request,
            ### then we are going to have problems with self.sock

            ### should we keep this behavior? do people use it?
            # keep the socket open (as a file), and return it
            self.file = self._conn.sock.makefile('rb', 0)

            # close our socket -- we want to restart after any protocol error
            self.close()

            self.headers = None
            return -1, e.line, None

        self.headers = response.msg
        self.file = response.fp
        return response.status, response.reason, response.msg

    def close(self):
        self._conn.close()

        # note that self.file == response.fp, which gets closed by the
        # superclass. just clear the object ref here.
        ### hmm. messy. if status==-1, then self.file is owned by us.
        ### well... we aren't explicitly closing, but losing this ref will
        ### do it
        self.file = None

if hasattr(socket, 'ssl'):
    class HTTPS(HTTP):
        """Compatibility with 1.5 httplib interface

        Python 1.5.2 did not have an HTTPS class, but it defined an
        interface for sending http requests that is also useful for
        https.
        """

        _connection_class = HTTPSConnection

        def __init__(self, host='', port=None, key_file=None, cert_file=None,
                     strict=None):
            # provide a default host, pass the X509 cert info

            # urf. compensate for bad input.
            if port == 0:
                port = None
            self._setup(self._connection_class(host, port, key_file,
                                               cert_file, strict))

            # we never actually use these for anything, but we keep them
            # here for compatibility with post-1.5.2 CVS.
            self.key_file = key_file
            self.cert_file = cert_file


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):
        self.args = partial,
        self.partial = partial

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
        # obhect.
        self._line_consumed = 1
        self.read = self._file.read
        self.readline = self._file.readline
        self.readlines = self._file.readlines

    def read(self, amt=None):
        assert not self._line_consumed and 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):
        s = self._line[self._line_offset:]
        self._done()
        return s

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

def test():
    """Test this module.

    A hodge podge of tests collected here, because they have too many
    external dependencies for the regular test suite.
    """

    import sys
    import getopt
    opts, args = getopt.getopt(sys.argv[1:], 'd')
    dl = 0
    for o, a in opts:
        if o == '-d': dl = dl + 1
    host = 'www.python.org'
    selector = '/'
    if args[0:]: host = args[0]
    if args[1:]: selector = args[1]
    h = HTTP()
    h.set_debuglevel(dl)
    h.connect(host)
    h.putrequest('GET', selector)
    h.endheaders()
    status, reason, headers = h.getreply()
    print 'status =', status
    print 'reason =', reason
    print "read", len(h.getfile().read())
    print
    if headers:
        for header in headers.headers: print header.strip()
    print

    # minimal test that code to extract host from url works
    class HTTP11(HTTP):
        _http_vsn = 11
        _http_vsn_str = 'HTTP/1.1'

    h = HTTP11('www.python.org')
    h.putrequest('GET', 'http://www.python.org/~jeremy/')
    h.endheaders()
    h.getreply()
    h.close()

    if hasattr(socket, 'ssl'):

        for host, selector in (('sourceforge.net', '/projects/python'),
                               ):
            print "https://%s%s" % (host, selector)
            hs = HTTPS()
            hs.set_debuglevel(dl)
            hs.connect(host)
            hs.putrequest('GET', selector)
            hs.endheaders()
            status, reason, headers = hs.getreply()
            print 'status =', status
            print 'reason =', reason
            print "read", len(hs.getfile().read())
            print
            if headers:
                for header in headers.headers: print header.strip()
            print

if __name__ == '__main__':
    test()