/
server.py
2222 lines (1862 loc) · 75.9 KB
/
server.py
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
"""
A high-speed, production ready, thread pooled, generic HTTP server.
For those of you wanting to understand internals of this module, here's the
basic call flow. The server's listening thread runs a very tight loop,
sticking incoming connections onto a Queue::
server = HTTPServer(...)
server.start()
-> while True:
tick()
# This blocks until a request comes in:
child = socket.accept()
conn = HTTPConnection(child, ...)
server.requests.put(conn)
Worker threads are kept in a pool and poll the Queue, popping off and then
handling each connection in turn. Each connection can consist of an arbitrary
number of requests and their responses, so we run a nested loop::
while True:
conn = server.requests.get()
conn.communicate()
-> while True:
req = HTTPRequest(...)
req.parse_request()
-> # Read the Request-Line, e.g. "GET /page HTTP/1.1"
req.rfile.readline()
read_headers(req.rfile, req.inheaders)
req.respond()
-> response = app(...)
try:
for chunk in response:
if chunk:
req.write(chunk)
finally:
if hasattr(response, "close"):
response.close()
if req.close_connection:
return
For running a server you can invoke :func:`start() <HTTPServer.start()>` (it
will run the server forever) or use invoking :func:`prepare()
<HTTPServer.prepare()>` and :func:`serve() <HTTPServer.serve()>` like this::
server = HTTPServer(...)
server.prepare()
try:
threading.Thread(target=server.serve).start()
# waiting/detecting some appropriate stop condition here
...
finally:
server.stop()
And now for a trivial doctest to exercise the test suite
>>> 'HTTPServer' in globals()
True
"""
from __future__ import absolute_import, division, print_function
__metaclass__ = type
import os
import io
import re
import email.utils
import socket
import sys
import time
import traceback as traceback_
import logging
import platform
try:
from functools import lru_cache
except ImportError:
from backports.functools_lru_cache import lru_cache
import six
from six.moves import queue
from six.moves import urllib
from . import errors, __version__
from ._compat import bton, ntou
from ._compat import IS_PPC
from .workers import threadpool
from .makefile import MakeFile, StreamWriter
__all__ = (
'HTTPRequest', 'HTTPConnection', 'HTTPServer',
'SizeCheckWrapper', 'KnownLengthRFile', 'ChunkedRFile',
'Gateway', 'get_ssl_adapter_class',
)
IS_WINDOWS = platform.system() == 'Windows'
"""Flag indicating whether the app is running under Windows."""
IS_GAE = os.getenv('SERVER_SOFTWARE', '').startswith('Google App Engine/')
"""Flag indicating whether the app is running in GAE env.
Ref:
https://cloud.google.com/appengine/docs/standard/python/tools
/using-local-server#detecting_application_runtime_environment
"""
IS_UID_GID_RESOLVABLE = not IS_WINDOWS and not IS_GAE
"""Indicates whether UID/GID resolution's available under current platform."""
if IS_UID_GID_RESOLVABLE:
try:
import grp
import pwd
except ImportError:
"""Unavailable in the current env.
This shouldn't be happening normally.
All of the known cases are excluded via the if clause.
"""
IS_UID_GID_RESOLVABLE = False
grp, pwd = None, None
import struct
if IS_WINDOWS and hasattr(socket, 'AF_INET6'):
if not hasattr(socket, 'IPPROTO_IPV6'):
socket.IPPROTO_IPV6 = 41
if not hasattr(socket, 'IPV6_V6ONLY'):
socket.IPV6_V6ONLY = 27
if not hasattr(socket, 'SO_PEERCRED'):
"""
NOTE: the value for SO_PEERCRED can be architecture specific, in
which case the getsockopt() will hopefully fail. The arch
specific value could be derived from platform.processor()
"""
socket.SO_PEERCRED = 21 if IS_PPC else 17
LF = b'\n'
CRLF = b'\r\n'
TAB = b'\t'
SPACE = b' '
COLON = b':'
SEMICOLON = b';'
EMPTY = b''
ASTERISK = b'*'
FORWARD_SLASH = b'/'
QUOTED_SLASH = b'%2F'
QUOTED_SLASH_REGEX = re.compile(b'(?i)' + QUOTED_SLASH)
comma_separated_headers = [
b'Accept', b'Accept-Charset', b'Accept-Encoding',
b'Accept-Language', b'Accept-Ranges', b'Allow', b'Cache-Control',
b'Connection', b'Content-Encoding', b'Content-Language', b'Expect',
b'If-Match', b'If-None-Match', b'Pragma', b'Proxy-Authenticate', b'TE',
b'Trailer', b'Transfer-Encoding', b'Upgrade', b'Vary', b'Via', b'Warning',
b'WWW-Authenticate',
]
if not hasattr(logging, 'statistics'):
logging.statistics = {}
class HeaderReader:
"""Object for reading headers from an HTTP request.
Interface and default implementation.
"""
def __call__(self, rfile, hdict=None):
"""
Read headers from the given stream into the given header dict.
If hdict is None, a new header dict is created. Returns the populated
header dict.
Headers which are repeated are folded together using a comma if their
specification so dictates.
This function raises ValueError when the read bytes violate the HTTP
spec.
You should probably return "400 Bad Request" if this happens.
"""
if hdict is None:
hdict = {}
while True:
line = rfile.readline()
if not line:
# No more data--illegal end of headers
raise ValueError('Illegal end of headers.')
if line == CRLF:
# Normal end of headers
break
if not line.endswith(CRLF):
raise ValueError('HTTP requires CRLF terminators')
if line[0] in (SPACE, TAB):
# It's a continuation line.
v = line.strip()
else:
try:
k, v = line.split(COLON, 1)
except ValueError:
raise ValueError('Illegal header line.')
v = v.strip()
k = self._transform_key(k)
hname = k
if not self._allow_header(k):
continue
if k in comma_separated_headers:
existing = hdict.get(hname)
if existing:
v = b', '.join((existing, v))
hdict[hname] = v
return hdict
def _allow_header(self, key_name):
return True
def _transform_key(self, key_name):
# TODO: what about TE and WWW-Authenticate?
return key_name.strip().title()
class DropUnderscoreHeaderReader(HeaderReader):
"""Custom HeaderReader to exclude any headers with underscores in them."""
def _allow_header(self, key_name):
orig = super(DropUnderscoreHeaderReader, self)._allow_header(key_name)
return orig and '_' not in key_name
class SizeCheckWrapper:
"""Wraps a file-like object, raising MaxSizeExceeded if too large."""
def __init__(self, rfile, maxlen):
"""Initialize SizeCheckWrapper instance.
Args:
rfile (file): file of a limited size
maxlen (int): maximum length of the file being read
"""
self.rfile = rfile
self.maxlen = maxlen
self.bytes_read = 0
def _check_length(self):
if self.maxlen and self.bytes_read > self.maxlen:
raise errors.MaxSizeExceeded()
def read(self, size=None):
"""Read a chunk from rfile buffer and return it.
Args:
size (int): amount of data to read
Returns:
bytes: Chunk from rfile, limited by size if specified.
"""
data = self.rfile.read(size)
self.bytes_read += len(data)
self._check_length()
return data
def readline(self, size=None):
"""Read a single line from rfile buffer and return it.
Args:
size (int): minimum amount of data to read
Returns:
bytes: One line from rfile.
"""
if size is not None:
data = self.rfile.readline(size)
self.bytes_read += len(data)
self._check_length()
return data
# User didn't specify a size ...
# We read the line in chunks to make sure it's not a 100MB line !
res = []
while True:
data = self.rfile.readline(256)
self.bytes_read += len(data)
self._check_length()
res.append(data)
# See https://github.com/cherrypy/cherrypy/issues/421
if len(data) < 256 or data[-1:] == LF:
return EMPTY.join(res)
def readlines(self, sizehint=0):
"""Read all lines from rfile buffer and return them.
Args:
sizehint (int): hint of minimum amount of data to read
Returns:
list[bytes]: Lines of bytes read from rfile.
"""
# Shamelessly stolen from StringIO
total = 0
lines = []
line = self.readline(sizehint)
while line:
lines.append(line)
total += len(line)
if 0 < sizehint <= total:
break
line = self.readline(sizehint)
return lines
def close(self):
"""Release resources allocated for rfile."""
self.rfile.close()
def __iter__(self):
"""Return file iterator."""
return self
def __next__(self):
"""Generate next file chunk."""
data = next(self.rfile)
self.bytes_read += len(data)
self._check_length()
return data
next = __next__
class KnownLengthRFile:
"""Wraps a file-like object, returning an empty string when exhausted."""
def __init__(self, rfile, content_length):
"""Initialize KnownLengthRFile instance.
Args:
rfile (file): file of a known size
content_length (int): length of the file being read
"""
self.rfile = rfile
self.remaining = content_length
def read(self, size=None):
"""Read a chunk from rfile buffer and return it.
Args:
size (int): amount of data to read
Returns:
bytes: Chunk from rfile, limited by size if specified.
"""
if self.remaining == 0:
return b''
if size is None:
size = self.remaining
else:
size = min(size, self.remaining)
data = self.rfile.read(size)
self.remaining -= len(data)
return data
def readline(self, size=None):
"""Read a single line from rfile buffer and return it.
Args:
size (int): minimum amount of data to read
Returns:
bytes: One line from rfile.
"""
if self.remaining == 0:
return b''
if size is None:
size = self.remaining
else:
size = min(size, self.remaining)
data = self.rfile.readline(size)
self.remaining -= len(data)
return data
def readlines(self, sizehint=0):
"""Read all lines from rfile buffer and return them.
Args:
sizehint (int): hint of minimum amount of data to read
Returns:
list[bytes]: Lines of bytes read from rfile.
"""
# Shamelessly stolen from StringIO
total = 0
lines = []
line = self.readline(sizehint)
while line:
lines.append(line)
total += len(line)
if 0 < sizehint <= total:
break
line = self.readline(sizehint)
return lines
def close(self):
"""Release resources allocated for rfile."""
self.rfile.close()
def __iter__(self):
"""Return file iterator."""
return self
def __next__(self):
"""Generate next file chunk."""
data = next(self.rfile)
self.remaining -= len(data)
return data
next = __next__
class ChunkedRFile:
"""Wraps a file-like object, returning an empty string when exhausted.
This class is intended to provide a conforming wsgi.input value for
request entities that have been encoded with the 'chunked' transfer
encoding.
"""
def __init__(self, rfile, maxlen, bufsize=8192):
"""Initialize ChunkedRFile instance.
Args:
rfile (file): file encoded with the 'chunked' transfer encoding
maxlen (int): maximum length of the file being read
bufsize (int): size of the buffer used to read the file
"""
self.rfile = rfile
self.maxlen = maxlen
self.bytes_read = 0
self.buffer = EMPTY
self.bufsize = bufsize
self.closed = False
def _fetch(self):
if self.closed:
return
line = self.rfile.readline()
self.bytes_read += len(line)
if self.maxlen and self.bytes_read > self.maxlen:
raise errors.MaxSizeExceeded(
'Request Entity Too Large', self.maxlen,
)
line = line.strip().split(SEMICOLON, 1)
try:
chunk_size = line.pop(0)
chunk_size = int(chunk_size, 16)
except ValueError:
raise ValueError('Bad chunked transfer size: ' + repr(chunk_size))
if chunk_size <= 0:
self.closed = True
return
# if line: chunk_extension = line[0]
if self.maxlen and self.bytes_read + chunk_size > self.maxlen:
raise IOError('Request Entity Too Large')
chunk = self.rfile.read(chunk_size)
self.bytes_read += len(chunk)
self.buffer += chunk
crlf = self.rfile.read(2)
if crlf != CRLF:
raise ValueError(
"Bad chunked transfer coding (expected '\\r\\n', "
'got ' + repr(crlf) + ')',
)
def read(self, size=None):
"""Read a chunk from rfile buffer and return it.
Args:
size (int): amount of data to read
Returns:
bytes: Chunk from rfile, limited by size if specified.
"""
data = EMPTY
if size == 0:
return data
while True:
if size and len(data) >= size:
return data
if not self.buffer:
self._fetch()
if not self.buffer:
# EOF
return data
if size:
remaining = size - len(data)
data += self.buffer[:remaining]
self.buffer = self.buffer[remaining:]
else:
data += self.buffer
self.buffer = EMPTY
def readline(self, size=None):
"""Read a single line from rfile buffer and return it.
Args:
size (int): minimum amount of data to read
Returns:
bytes: One line from rfile.
"""
data = EMPTY
if size == 0:
return data
while True:
if size and len(data) >= size:
return data
if not self.buffer:
self._fetch()
if not self.buffer:
# EOF
return data
newline_pos = self.buffer.find(LF)
if size:
if newline_pos == -1:
remaining = size - len(data)
data += self.buffer[:remaining]
self.buffer = self.buffer[remaining:]
else:
remaining = min(size - len(data), newline_pos)
data += self.buffer[:remaining]
self.buffer = self.buffer[remaining:]
else:
if newline_pos == -1:
data += self.buffer
self.buffer = EMPTY
else:
data += self.buffer[:newline_pos]
self.buffer = self.buffer[newline_pos:]
def readlines(self, sizehint=0):
"""Read all lines from rfile buffer and return them.
Args:
sizehint (int): hint of minimum amount of data to read
Returns:
list[bytes]: Lines of bytes read from rfile.
"""
# Shamelessly stolen from StringIO
total = 0
lines = []
line = self.readline(sizehint)
while line:
lines.append(line)
total += len(line)
if 0 < sizehint <= total:
break
line = self.readline(sizehint)
return lines
def read_trailer_lines(self):
"""Read HTTP headers and yield them.
Returns:
Generator: yields CRLF separated lines.
"""
if not self.closed:
raise ValueError(
'Cannot read trailers until the request body has been read.',
)
while True:
line = self.rfile.readline()
if not line:
# No more data--illegal end of headers
raise ValueError('Illegal end of headers.')
self.bytes_read += len(line)
if self.maxlen and self.bytes_read > self.maxlen:
raise IOError('Request Entity Too Large')
if line == CRLF:
# Normal end of headers
break
if not line.endswith(CRLF):
raise ValueError('HTTP requires CRLF terminators')
yield line
def close(self):
"""Release resources allocated for rfile."""
self.rfile.close()
class HTTPRequest:
"""An HTTP Request (and response).
A single HTTP connection may consist of multiple request/response pairs.
"""
server = None
"""The HTTPServer object which is receiving this request."""
conn = None
"""The HTTPConnection object on which this request connected."""
inheaders = {}
"""A dict of request headers."""
outheaders = []
"""A list of header tuples to write in the response."""
ready = False
"""When True, the request has been parsed and is ready to begin generating
the response. When False, signals the calling Connection that the response
should not be generated and the connection should close."""
close_connection = False
"""Signals the calling Connection that the request should close. This does
not imply an error! The client and/or server may each request that the
connection be closed."""
chunked_write = False
"""If True, output will be encoded with the "chunked" transfer-coding.
This value is set automatically inside send_headers."""
header_reader = HeaderReader()
"""
A HeaderReader instance or compatible reader.
"""
def __init__(self, server, conn, proxy_mode=False, strict_mode=True):
"""Initialize HTTP request container instance.
Args:
server (HTTPServer): web server object receiving this request
conn (HTTPConnection): HTTP connection object for this request
proxy_mode (bool): whether this HTTPServer should behave as a PROXY
server for certain requests
strict_mode (bool): whether we should return a 400 Bad Request when
we encounter a request that a HTTP compliant client should not be
making
"""
self.server = server
self.conn = conn
self.ready = False
self.started_request = False
self.scheme = b'http'
if self.server.ssl_adapter is not None:
self.scheme = b'https'
# Use the lowest-common protocol in case read_request_line errors.
self.response_protocol = 'HTTP/1.0'
self.inheaders = {}
self.status = ''
self.outheaders = []
self.sent_headers = False
self.close_connection = self.__class__.close_connection
self.chunked_read = False
self.chunked_write = self.__class__.chunked_write
self.proxy_mode = proxy_mode
self.strict_mode = strict_mode
def parse_request(self):
"""Parse the next HTTP request start-line and message-headers."""
self.rfile = SizeCheckWrapper(
self.conn.rfile,
self.server.max_request_header_size,
)
try:
success = self.read_request_line()
except errors.MaxSizeExceeded:
self.simple_response(
'414 Request-URI Too Long',
'The Request-URI sent with the request exceeds the maximum '
'allowed bytes.',
)
return
else:
if not success:
return
try:
success = self.read_request_headers()
except errors.MaxSizeExceeded:
self.simple_response(
'413 Request Entity Too Large',
'The headers sent with the request exceed the maximum '
'allowed bytes.',
)
return
else:
if not success:
return
self.ready = True
def read_request_line(self):
"""Read and parse first line of the HTTP request.
Returns:
bool: True if the request line is valid or False if it's malformed.
"""
# HTTP/1.1 connections are persistent by default. If a client
# requests a page, then idles (leaves the connection open),
# then rfile.readline() will raise socket.error("timed out").
# Note that it does this based on the value given to settimeout(),
# and doesn't need the client to request or acknowledge the close
# (although your TCP stack might suffer for it: cf Apache's history
# with FIN_WAIT_2).
request_line = self.rfile.readline()
# Set started_request to True so communicate() knows to send 408
# from here on out.
self.started_request = True
if not request_line:
return False
if request_line == CRLF:
# RFC 2616 sec 4.1: "...if the server is reading the protocol
# stream at the beginning of a message and receives a CRLF
# first, it should ignore the CRLF."
# But only ignore one leading line! else we enable a DoS.
request_line = self.rfile.readline()
if not request_line:
return False
if not request_line.endswith(CRLF):
self.simple_response(
'400 Bad Request', 'HTTP requires CRLF terminators',
)
return False
try:
method, uri, req_protocol = request_line.strip().split(SPACE, 2)
if not req_protocol.startswith(b'HTTP/'):
self.simple_response(
'400 Bad Request', 'Malformed Request-Line: bad protocol',
)
return False
rp = req_protocol[5:].split(b'.', 1)
if len(rp) != 2:
self.simple_response(
'400 Bad Request', 'Malformed Request-Line: bad version',
)
return False
rp = tuple(map(int, rp)) # Minor.Major must be threat as integers
if rp > (1, 1):
self.simple_response(
'505 HTTP Version Not Supported', 'Cannot fulfill request',
)
return False
except (ValueError, IndexError):
self.simple_response('400 Bad Request', 'Malformed Request-Line')
return False
self.uri = uri
self.method = method.upper()
if self.strict_mode and method != self.method:
resp = (
'Malformed method name: According to RFC 2616 '
'(section 5.1.1) and its successors '
'RFC 7230 (section 3.1.1) and RFC 7231 (section 4.1) '
'method names are case-sensitive and uppercase.'
)
self.simple_response('400 Bad Request', resp)
return False
try:
if six.PY2: # FIXME: Figure out better way to do this
# Ref: https://stackoverflow.com/a/196392/595220 (like this?)
"""This is a dummy check for unicode in URI."""
ntou(bton(uri, 'ascii'), 'ascii')
scheme, authority, path, qs, fragment = urllib.parse.urlsplit(uri)
except UnicodeError:
self.simple_response('400 Bad Request', 'Malformed Request-URI')
return False
if self.method == b'OPTIONS':
# TODO: cover this branch with tests
path = (
uri
# https://tools.ietf.org/html/rfc7230#section-5.3.4
if self.proxy_mode or uri == ASTERISK
else path
)
elif self.method == b'CONNECT':
# TODO: cover this branch with tests
if not self.proxy_mode:
self.simple_response('405 Method Not Allowed')
return False
# `urlsplit()` above parses "example.com:3128" as path part of URI.
# this is a workaround, which makes it detect netloc correctly
uri_split = urllib.parse.urlsplit(b'//' + uri)
_scheme, _authority, _path, _qs, _fragment = uri_split
_port = EMPTY
try:
_port = uri_split.port
except ValueError:
pass
# FIXME: use third-party validation to make checks against RFC
# the validation doesn't take into account, that urllib parses
# invalid URIs without raising errors
# https://tools.ietf.org/html/rfc7230#section-5.3.3
invalid_path = (
_authority != uri
or not _port
or any((_scheme, _path, _qs, _fragment))
)
if invalid_path:
self.simple_response(
'400 Bad Request',
'Invalid path in Request-URI: request-'
'target must match authority-form.',
)
return False
authority = path = _authority
scheme = qs = fragment = EMPTY
else:
uri_is_absolute_form = (scheme or authority)
disallowed_absolute = (
self.strict_mode
and not self.proxy_mode
and uri_is_absolute_form
)
if disallowed_absolute:
# https://tools.ietf.org/html/rfc7230#section-5.3.2
# (absolute form)
"""Absolute URI is only allowed within proxies."""
self.simple_response(
'400 Bad Request',
'Absolute URI not allowed if server is not a proxy.',
)
return False
invalid_path = (
self.strict_mode
and not uri.startswith(FORWARD_SLASH)
and not uri_is_absolute_form
)
if invalid_path:
# https://tools.ietf.org/html/rfc7230#section-5.3.1
# (origin_form) and
"""Path should start with a forward slash."""
resp = (
'Invalid path in Request-URI: request-target must contain '
'origin-form which starts with absolute-path (URI '
'starting with a slash "/").'
)
self.simple_response('400 Bad Request', resp)
return False
if fragment:
self.simple_response(
'400 Bad Request',
'Illegal #fragment in Request-URI.',
)
return False
if path is None:
# FIXME: It looks like this case cannot happen
self.simple_response(
'400 Bad Request',
'Invalid path in Request-URI.',
)
return False
# Unquote the path+params (e.g. "/this%20path" -> "/this path").
# https://www.w3.org/Protocols/rfc2616/rfc2616-sec5.html#sec5.1.2
#
# But note that "...a URI must be separated into its components
# before the escaped characters within those components can be
# safely decoded." https://www.ietf.org/rfc/rfc2396.txt, sec 2.4.2
# Therefore, "/this%2Fpath" becomes "/this%2Fpath", not
# "/this/path".
try:
# TODO: Figure out whether exception can really happen here.
# It looks like it's caught on urlsplit() call above.
atoms = [
urllib.parse.unquote_to_bytes(x)
for x in QUOTED_SLASH_REGEX.split(path)
]
except ValueError as ex:
self.simple_response('400 Bad Request', ex.args[0])
return False
path = QUOTED_SLASH.join(atoms)
if not path.startswith(FORWARD_SLASH):
path = FORWARD_SLASH + path
if scheme is not EMPTY:
self.scheme = scheme
self.authority = authority
self.path = path
# Note that, like wsgiref and most other HTTP servers,
# we "% HEX HEX"-unquote the path but not the query string.
self.qs = qs
# Compare request and server HTTP protocol versions, in case our
# server does not support the requested protocol. Limit our output
# to min(req, server). We want the following output:
# request server actual written supported response
# protocol protocol response protocol feature set
# a 1.0 1.0 1.0 1.0
# b 1.0 1.1 1.1 1.0
# c 1.1 1.0 1.0 1.0
# d 1.1 1.1 1.1 1.1
# Notice that, in (b), the response will be "HTTP/1.1" even though
# the client only understands 1.0. RFC 2616 10.5.6 says we should
# only return 505 if the _major_ version is different.
sp = int(self.server.protocol[5]), int(self.server.protocol[7])
if sp[0] != rp[0]:
self.simple_response('505 HTTP Version Not Supported')
return False
self.request_protocol = req_protocol
self.response_protocol = 'HTTP/%s.%s' % min(rp, sp)
return True
def read_request_headers(self):
"""Read self.rfile into self.inheaders. Return success."""
# then all the http headers
try:
self.header_reader(self.rfile, self.inheaders)
except ValueError as ex:
self.simple_response('400 Bad Request', ex.args[0])
return False
mrbs = self.server.max_request_body_size
try:
cl = int(self.inheaders.get(b'Content-Length', 0))
except ValueError:
self.simple_response(
'400 Bad Request',
'Malformed Content-Length Header.',
)
return False
if mrbs and cl > mrbs:
self.simple_response(
'413 Request Entity Too Large',