-
Notifications
You must be signed in to change notification settings - Fork 509
/
server_modular_send_head.py
1336 lines (1114 loc) · 47.6 KB
/
server_modular_send_head.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
"""HTTP server classes.
Note: BaseHTTPRequestHandler doesn't implement any HTTP request; see
SimpleHTTPRequestHandler for simple implementations of GET, HEAD and POST,
and CGIHTTPRequestHandler for CGI scripts.
It does, however, optionally implement HTTP/1.1 persistent connections,
as of version 0.3.
Notes on CGIHTTPRequestHandler
------------------------------
This class implements GET and POST requests to cgi-bin scripts.
If the os.fork() function is not present (e.g. on Windows),
subprocess.Popen() is used as a fallback, with slightly altered semantics.
In all cases, the implementation is intentionally naive -- all
requests are executed synchronously.
SECURITY WARNING: DON'T USE THIS CODE UNLESS YOU ARE INSIDE A FIREWALL
-- it may execute arbitrary Python code or external programs.
Note that status code 200 is sent prior to execution of a CGI script, so
scripts cannot send other status codes such as 302 (redirect).
XXX To do:
- log requests even later (to capture byte count)
- log user-agent header and other interesting goodies
- send error log to separate file
"""
# See also:
#
# HTTP Working Group T. Berners-Lee
# INTERNET-DRAFT R. T. Fielding
# <draft-ietf-http-v10-spec-00.txt> H. Frystyk Nielsen
# Expires September 8, 1995 March 8, 1995
#
# URL: http://www.ics.uci.edu/pub/ietf/http/draft-ietf-http-v10-spec-00.txt
#
# and
#
# Network Working Group R. Fielding
# Request for Comments: 2616 et al
# Obsoletes: 2068 June 1999
# Category: Standards Track
#
# URL: http://www.faqs.org/rfcs/rfc2616.html
# Log files
# ---------
#
# Here's a quote from the NCSA httpd docs about log file format.
#
# | The logfile format is as follows. Each line consists of:
# |
# | host rfc931 authuser [DD/Mon/YYYY:hh:mm:ss] "request" ddd bbbb
# |
# | host: Either the DNS name or the IP number of the remote client
# | rfc931: Any information returned by identd for this person,
# | - otherwise.
# | authuser: If user sent a userid for authentication, the user name,
# | - otherwise.
# | DD: Day
# | Mon: Month (calendar name)
# | YYYY: Year
# | hh: hour (24-hour format, the machine's timezone)
# | mm: minutes
# | ss: seconds
# | request: The first line of the HTTP request as sent by the client.
# | ddd: the status code returned by the server, - if not available.
# | bbbb: the total number of bytes sent,
# | *not including the HTTP/1.0 header*, - if not available
# |
# | You can determine the name of the file accessed through request.
#
# (Actually, the latter is only true if you know the server configuration
# at the time the request was made!)
__version__ = "0.6"
__all__ = [
"HTTPServer", "ThreadingHTTPServer", "BaseHTTPRequestHandler",
"SimpleHTTPRequestHandler", "CGIHTTPRequestHandler",
]
import copy
import datetime
import email.utils
import html
import http.client
import io
import mimetypes
import os
import posixpath
import select
import shutil
import socket # For gethostbyaddr()
import socketserver
import sys
import time
import urllib.parse
from functools import partial
from http import HTTPStatus
# Default error message template
DEFAULT_ERROR_MESSAGE = """\
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html;charset=utf-8">
<title>Error response</title>
</head>
<body>
<h1>Error response</h1>
<p>Error code: %(code)d</p>
<p>Message: %(message)s.</p>
<p>Error code explanation: %(code)s - %(explain)s.</p>
</body>
</html>
"""
DEFAULT_ERROR_CONTENT_TYPE = "text/html;charset=utf-8"
class HTTPServer(socketserver.TCPServer):
allow_reuse_address = 1 # Seems to make sense in testing environment
def server_bind(self):
"""Override server_bind to store the server name."""
socketserver.TCPServer.server_bind(self)
host, port = self.server_address[:2]
self.server_name = socket.getfqdn(host)
self.server_port = port
class ThreadingHTTPServer(socketserver.ThreadingMixIn, HTTPServer):
daemon_threads = True
class BaseHTTPRequestHandler(socketserver.StreamRequestHandler):
"""HTTP request handler base class.
The following explanation of HTTP serves to guide you through the
code as well as to expose any misunderstandings I may have about
HTTP (so you don't need to read the code to figure out I'm wrong
:-).
HTTP (HyperText Transfer Protocol) is an extensible protocol on
top of a reliable stream transport (e.g. TCP/IP). The protocol
recognizes three parts to a request:
1. One line identifying the request type and path
2. An optional set of RFC-822-style headers
3. An optional data part
The headers and data are separated by a blank line.
The first line of the request has the form
<command> <path> <version>
where <command> is a (case-sensitive) keyword such as GET or POST,
<path> is a string containing path information for the request,
and <version> should be the string "HTTP/1.0" or "HTTP/1.1".
<path> is encoded using the URL encoding scheme (using %xx to signify
the ASCII character with hex code xx).
The specification specifies that lines are separated by CRLF but
for compatibility with the widest range of clients recommends
servers also handle LF. Similarly, whitespace in the request line
is treated sensibly (allowing multiple spaces between components
and allowing trailing whitespace).
Similarly, for output, lines ought to be separated by CRLF pairs
but most clients grok LF characters just fine.
If the first line of the request has the form
<command> <path>
(i.e. <version> is left out) then this is assumed to be an HTTP
0.9 request; this form has no optional headers and data part and
the reply consists of just the data.
The reply form of the HTTP 1.x protocol again has three parts:
1. One line giving the response code
2. An optional set of RFC-822-style headers
3. The data
Again, the headers and data are separated by a blank line.
The response code line has the form
<version> <responsecode> <responsestring>
where <version> is the protocol version ("HTTP/1.0" or "HTTP/1.1"),
<responsecode> is a 3-digit response code indicating success or
failure of the request, and <responsestring> is an optional
human-readable string explaining what the response code means.
This server parses the request and the headers, and then calls a
function specific to the request type (<command>). Specifically,
a request SPAM will be handled by a method do_SPAM(). If no
such method exists the server sends an error response to the
client. If it exists, it is called with no arguments:
do_SPAM()
Note that the request name is case sensitive (i.e. SPAM and spam
are different requests).
The various request details are stored in instance variables:
- client_address is the client IP address in the form (host,
port);
- command, path and version are the broken-down request line;
- headers is an instance of email.message.Message (or a derived
class) containing the header information;
- rfile is a file object open for reading positioned at the
start of the optional input data part;
- wfile is a file object open for writing.
IT IS IMPORTANT TO ADHERE TO THE PROTOCOL FOR WRITING!
The first thing to be written must be the response line. Then
follow 0 or more header lines, then a blank line, and then the
actual data (if any). The meaning of the header lines depends on
the command executed by the server; in most cases, when data is
returned, there should be at least one header line of the form
Content-type: <type>/<subtype>
where <type> and <subtype> should be registered MIME types,
e.g. "text/html" or "text/plain".
"""
# The Python system version, truncated to its first component.
sys_version = "Python/" + sys.version.split()[0]
# The server software version. You may want to override this.
# The format is multiple whitespace-separated strings,
# where each string is of the form name[/version].
server_version = "BaseHTTP/" + __version__
error_message_format = DEFAULT_ERROR_MESSAGE
error_content_type = DEFAULT_ERROR_CONTENT_TYPE
# The default request version. This only affects responses up until
# the point where the request line is parsed, so it mainly decides what
# the client gets back when sending a malformed request line.
# Most web servers default to HTTP 0.9, i.e. don't send a status line.
default_request_version = "HTTP/0.9"
def parse_request(self):
"""Parse a request (internal).
The request should be stored in self.raw_requestline; the results
are in self.command, self.path, self.request_version and
self.headers.
Return True for success, False for failure; on failure, any relevant
error response has already been sent back.
"""
self.command = None # set in case of error on the first line
self.request_version = version = self.default_request_version
self.close_connection = True
requestline = str(self.raw_requestline, 'iso-8859-1')
requestline = requestline.rstrip('\r\n')
self.requestline = requestline
words = requestline.split()
if len(words) == 0:
return False
if len(words) >= 3: # Enough to determine protocol version
version = words[-1]
try:
if not version.startswith('HTTP/'):
raise ValueError
base_version_number = version.split('/', 1)[1]
version_number = base_version_number.split(".")
# RFC 2145 section 3.1 says there can be only one "." and
# - major and minor numbers MUST be treated as
# separate integers;
# - HTTP/2.4 is a lower version than HTTP/2.13, which in
# turn is lower than HTTP/12.3;
# - Leading zeros MUST be ignored by recipients.
if len(version_number) != 2:
raise ValueError
version_number = int(version_number[0]), int(version_number[1])
except (ValueError, IndexError):
self.send_error(
HTTPStatus.BAD_REQUEST,
"Bad request version (%r)" % version)
return False
if version_number >= (1, 1) and self.protocol_version >= "HTTP/1.1":
self.close_connection = False
if version_number >= (2, 0):
self.send_error(
HTTPStatus.HTTP_VERSION_NOT_SUPPORTED,
"Invalid HTTP version (%s)" % base_version_number)
return False
self.request_version = version
if not 2 <= len(words) <= 3:
self.send_error(
HTTPStatus.BAD_REQUEST,
"Bad request syntax (%r)" % requestline)
return False
command, path = words[:2]
if len(words) == 2:
self.close_connection = True
if command != 'GET':
self.send_error(
HTTPStatus.BAD_REQUEST,
"Bad HTTP/0.9 request type (%r)" % command)
return False
self.command, self.path = command, path
# Examine the headers and look for a Connection directive.
try:
self.headers = http.client.parse_headers(self.rfile,
_class=self.MessageClass)
except http.client.LineTooLong as err:
self.send_error(
HTTPStatus.REQUEST_HEADER_FIELDS_TOO_LARGE,
"Line too long",
str(err))
return False
except http.client.HTTPException as err:
self.send_error(
HTTPStatus.REQUEST_HEADER_FIELDS_TOO_LARGE,
"Too many headers",
str(err)
)
return False
conntype = self.headers.get('Connection', "")
if conntype.lower() == 'close':
self.close_connection = True
elif (conntype.lower() == 'keep-alive' and
self.protocol_version >= "HTTP/1.1"):
self.close_connection = False
# Examine the headers and look for an Expect directive
expect = self.headers.get('Expect', "")
if (expect.lower() == "100-continue" and
self.protocol_version >= "HTTP/1.1" and
self.request_version >= "HTTP/1.1"):
if not self.handle_expect_100():
return False
return True
def handle_expect_100(self):
"""Decide what to do with an "Expect: 100-continue" header.
If the client is expecting a 100 Continue response, we must
respond with either a 100 Continue or a final response before
waiting for the request body. The default is to always respond
with a 100 Continue. You can behave differently (for example,
reject unauthorized requests) by overriding this method.
This method should either return True (possibly after sending
a 100 Continue response) or send an error response and return
False.
"""
self.send_response_only(HTTPStatus.CONTINUE)
self.end_headers()
return True
def handle_one_request(self):
"""Handle a single HTTP request.
You normally don't need to override this method; see the class
__doc__ string for information on how to handle specific HTTP
commands such as GET and POST.
"""
try:
self.raw_requestline = self.rfile.readline(65537)
if len(self.raw_requestline) > 65536:
self.requestline = ''
self.request_version = ''
self.command = ''
self.send_error(HTTPStatus.REQUEST_URI_TOO_LONG)
return
if not self.raw_requestline:
self.close_connection = True
return
if not self.parse_request():
# An error code has been sent, just exit
return
mname = 'do_' + self.command
if not hasattr(self, mname):
self.send_error(
HTTPStatus.NOT_IMPLEMENTED,
"Unsupported method (%r)" % self.command)
return
method = getattr(self, mname)
method()
self.wfile.flush() #actually send the response if not already done.
except socket.timeout as e:
#a read or a write timed out. Discard this connection
self.log_error("Request timed out: %r", e)
self.close_connection = True
return
def handle(self):
"""Handle multiple requests if necessary."""
self.close_connection = True
self.handle_one_request()
while not self.close_connection:
self.handle_one_request()
def send_error(self, code, message=None, explain=None):
"""Send and log an error reply.
Arguments are
* code: an HTTP error code
3 digits
* message: a simple optional 1 line reason phrase.
*( HTAB / SP / VCHAR / %x80-FF )
defaults to short entry matching the response code
* explain: a detailed message defaults to the long entry
matching the response code.
This sends an error response (so it must be called before any
output has been generated), logs the error, and finally sends
a piece of HTML explaining the error to the user.
"""
try:
shortmsg, longmsg = self.responses[code]
except KeyError:
shortmsg, longmsg = '???', '???'
if message is None:
message = shortmsg
if explain is None:
explain = longmsg
self.log_error("code %d, message %s", code, message)
self.send_response(code, message)
self.send_header('Connection', 'close')
# Message body is omitted for cases described in:
# - RFC7230: 3.3. 1xx, 204(No Content), 304(Not Modified)
# - RFC7231: 6.3.6. 205(Reset Content)
body = None
if (code >= 200 and
code not in (HTTPStatus.NO_CONTENT,
HTTPStatus.RESET_CONTENT,
HTTPStatus.NOT_MODIFIED)):
# HTML encode to prevent Cross Site Scripting attacks
# (see bug #1100201)
content = (self.error_message_format % {
'code': code,
'message': html.escape(message, quote=False),
'explain': html.escape(explain, quote=False)
})
body = content.encode('UTF-8', 'replace')
self.send_header("Content-Type", self.error_content_type)
self.send_header('Content-Length', str(len(body)))
self.end_headers()
if self.command != 'HEAD' and body:
self.wfile.write(body)
def send_response(self, code, message=None):
"""Add the response header to the headers buffer and log the
response code.
Also send two standard headers with the server software
version and the current date.
"""
self.log_request(code)
self.send_response_only(code, message)
self.send_header('Server', self.version_string())
self.send_header('Date', self.date_time_string())
def send_response_only(self, code, message=None):
"""Send the response header only."""
if self.request_version != 'HTTP/0.9':
if message is None:
if code in self.responses:
message = self.responses[code][0]
else:
message = ''
if not hasattr(self, '_headers_buffer'):
self._headers_buffer = []
self._headers_buffer.append(("%s %d %s\r\n" %
(self.protocol_version, code, message)).encode(
'latin-1', 'strict'))
def send_header(self, keyword, value):
"""Send a MIME header to the headers buffer."""
if self.request_version != 'HTTP/0.9':
if not hasattr(self, '_headers_buffer'):
self._headers_buffer = []
self._headers_buffer.append(
("%s: %s\r\n" % (keyword, value)).encode('latin-1', 'strict'))
if keyword.lower() == 'connection':
if value.lower() == 'close':
self.close_connection = True
elif value.lower() == 'keep-alive':
self.close_connection = False
def end_headers(self):
"""Send the blank line ending the MIME headers."""
if self.request_version != 'HTTP/0.9':
self._headers_buffer.append(b"\r\n")
self.flush_headers()
def flush_headers(self):
if hasattr(self, '_headers_buffer'):
self.wfile.write(b"".join(self._headers_buffer))
self._headers_buffer = []
def log_request(self, code='-', size='-'):
"""Log an accepted request.
This is called by send_response().
"""
if isinstance(code, HTTPStatus):
code = code.value
self.log_message('"%s" %s %s',
self.requestline, str(code), str(size))
def log_error(self, format, *args):
"""Log an error.
This is called when a request cannot be fulfilled. By
default it passes the message on to log_message().
Arguments are the same as for log_message().
XXX This should go to the separate error log.
"""
self.log_message(format, *args)
def log_message(self, format, *args):
"""Log an arbitrary message.
This is used by all other logging functions. Override
it if you have specific logging wishes.
The first argument, FORMAT, is a format string for the
message to be logged. If the format string contains
any % escapes requiring parameters, they should be
specified as subsequent arguments (it's just like
printf!).
The client ip and current date/time are prefixed to
every message.
"""
sys.stderr.write("%s - - [%s] %s\n" %
(self.address_string(),
self.log_date_time_string(),
format%args))
def version_string(self):
"""Return the server software version string."""
return self.server_version + ' ' + self.sys_version
def date_time_string(self, timestamp=None):
"""Return the current date and time formatted for a message header."""
if timestamp is None:
timestamp = time.time()
return email.utils.formatdate(timestamp, usegmt=True)
def log_date_time_string(self):
"""Return the current time formatted for logging."""
now = time.time()
year, month, day, hh, mm, ss, x, y, z = time.localtime(now)
s = "%02d/%3s/%04d %02d:%02d:%02d" % (
day, self.monthname[month], year, hh, mm, ss)
return s
weekdayname = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']
monthname = [None,
'Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun',
'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
def address_string(self):
"""Return the client address."""
return self.client_address[0]
# Essentially static class variables
# The version of the HTTP protocol we support.
# Set this to HTTP/1.1 to enable automatic keepalive
protocol_version = "HTTP/1.0"
# MessageClass used to parse headers
MessageClass = http.client.HTTPMessage
# hack to maintain backwards compatibility
responses = {
v: (v.phrase, v.description)
for v in HTTPStatus.__members__.values()
}
class SimpleHTTPRequestHandler(BaseHTTPRequestHandler):
"""Simple HTTP request handler with GET and HEAD commands.
This serves files from the current directory and any of its
subdirectories. The MIME type for files is determined by
calling the .guess_type() method.
The GET and HEAD requests are identical except that the HEAD
request omits the actual contents of the file.
"""
server_version = "SimpleHTTP/" + __version__
def __init__(self, *args, directory=None, **kwargs):
if directory is None:
directory = os.getcwd()
self.directory = directory
super().__init__(*args, **kwargs)
def do_GET(self):
"""Serve a GET request."""
f = self.send_head()
if f:
try:
if hasattr(f, "read"):
self.copyfile(f, self.wfile)
else:
# The object returned by send_head() can be a generator,
# eg if method handle_compression() returns a generator
# for compressed data
if self.protocol_version >= "HTTP/1.1":
# Chunked Transfer
for data in f:
if data:
chunk = (f"{len(data):X}".encode("ascii") +
b"\r\n" + data + b"\r\n")
self.wfile.write(chunk)
self.wfile.write(b'0\r\n\r\n')
else:
for data in f:
self.wfile.write(data)
finally:
f.close()
def do_HEAD(self):
"""Serve a HEAD request."""
f = self.send_head()
if f:
f.close()
def handle_browser_cache(self):
"""Use browser cache. If conditions are ok (file not modified since
the data in If-Modified-Since header), return True.
"""
if ("If-Modified-Since" in self.headers
and "If-None-Match" not in self.headers):
# compare If-Modified-Since and time of last file modification
try:
ims = email.utils.parsedate_to_datetime(
self.headers["If-Modified-Since"])
except (TypeError, IndexError, OverflowError, ValueError):
# ignore ill-formed values
pass
else:
if ims.tzinfo is None:
# obsolete format with no timezone, cf.
# https://tools.ietf.org/html/rfc7231#section-7.1.1.1
ims = ims.replace(tzinfo=datetime.timezone.utc)
if ims.tzinfo is datetime.timezone.utc:
# compare to UTC datetime of last modification
last_modif = datetime.datetime.fromtimestamp(self.mtime,
datetime.timezone.utc)
# remove microseconds, like in If-Modified-Since
last_modif = last_modif.replace(microsecond=0)
if last_modif <= ims:
return True
def handle_compression(self, f):
"""Entry point for HTTP compression.
If the content is not compressed (eg it's in an already compressed
format such as jpg or mp3), return the file object f.
Otherwise, return either:
- a file-like object (one that has a method read() that returns
bytes); the attribute self.content_length must be set to the length
of this file object
- or a generator of data chunks, in this case self.content_length must
be set to None
"""
# By default, don't compress
return f
def send_head(self):
"""Common code for GET and HEAD commands.
This sends the response code and MIME headers.
Return value is either a file object (which has to be copied
to the outputfile by the caller unless the command was HEAD,
and must be closed by the caller under all circumstances), or
a generator of data chunks, or None, in which case the caller
has nothing further to do.
"""
path = self.translate_path(self.path)
f = None
if os.path.isdir(path):
parts = urllib.parse.urlsplit(self.path)
if not parts.path.endswith('/'):
# redirect browser - doing basically what apache does
self.send_response(HTTPStatus.MOVED_PERMANENTLY)
new_parts = (parts[0], parts[1], parts[2] + '/',
parts[3], parts[4])
new_url = urllib.parse.urlunsplit(new_parts)
self.send_header("Location", new_url)
self.end_headers()
return None
for index in "index.html", "index.htm":
index = os.path.join(path, index)
if os.path.exists(index):
path = index
break
else:
return self.list_directory(path)
# check for trailing "/" which should return 404. See Issue17324
# The test for this was added in test_httpserver.py
# However, some OS platforms accept a trailingSlash as a filename
# See discussion on python-dev and Issue34711 regarding
# parseing and rejection of filenames with a trailing slash
if path.endswith("/"):
self.send_error(HTTPStatus.NOT_FOUND, "File not found")
return None
try:
f = open(path, 'rb')
except OSError:
self.send_error(HTTPStatus.NOT_FOUND, "File not found")
return None
self.ctype = self.guess_type(path)
try:
fs = os.fstat(f.fileno())
self.mtime = fs.st_mtime
self.content_length = fs[6]
# Use browser cache if possible
if self.handle_browser_cache():
self.send_response(HTTPStatus.NOT_MODIFIED)
self.end_headers()
f.close()
return
self.send_response(HTTPStatus.OK)
self.send_header("Content-type", self.ctype)
self.send_header("Last-Modified",
self.date_time_string(fs.st_mtime))
# Use HTTP compression if available
f = self.handle_compression(f)
if self.content_length: # Not set for Chunked Transfer Encoding
self.send_header("Content-Length", str(self.content_length))
self.end_headers()
return f
except:
f.close()
raise
def list_directory(self, path):
"""Helper to produce a directory listing (absent index.html).
Return value is either a file object, or None (indicating an
error). In either case, the headers are sent, making the
interface the same as for send_head().
"""
try:
list = os.listdir(path)
except OSError:
self.send_error(
HTTPStatus.NOT_FOUND,
"No permission to list directory")
return None
list.sort(key=lambda a: a.lower())
r = []
try:
displaypath = urllib.parse.unquote(self.path,
errors='surrogatepass')
except UnicodeDecodeError:
displaypath = urllib.parse.unquote(path)
displaypath = html.escape(displaypath, quote=False)
enc = sys.getfilesystemencoding()
title = 'Directory listing for %s' % displaypath
r.append('<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" '
'"http://www.w3.org/TR/html4/strict.dtd">')
r.append('<html>\n<head>')
r.append('<meta http-equiv="Content-Type" '
'content="text/html; charset=%s">' % enc)
r.append('<title>%s</title>\n</head>' % title)
r.append('<body>\n<h1>%s</h1>' % title)
r.append('<hr>\n<ul>')
for name in list:
fullname = os.path.join(path, name)
displayname = linkname = name
# Append / for directories or @ for symbolic links
if os.path.isdir(fullname):
displayname = name + "/"
linkname = name + "/"
if os.path.islink(fullname):
displayname = name + "@"
# Note: a link to a directory displays with @ and links with /
r.append('<li><a href="%s">%s</a></li>'
% (urllib.parse.quote(linkname,
errors='surrogatepass'),
html.escape(displayname, quote=False)))
r.append('</ul>\n<hr>\n</body>\n</html>\n')
encoded = '\n'.join(r).encode(enc, 'surrogateescape')
f = io.BytesIO()
f.write(encoded)
f.seek(0)
self.send_response(HTTPStatus.OK)
self.send_header("Content-type", "text/html; charset=%s" % enc)
self.send_header("Content-Length", str(len(encoded)))
self.end_headers()
return f
def translate_path(self, path):
"""Translate a /-separated PATH to the local filename syntax.
Components that mean special things to the local file system
(e.g. drive or directory names) are ignored. (XXX They should
probably be diagnosed.)
"""
# abandon query parameters
path = path.split('?',1)[0]
path = path.split('#',1)[0]
# Don't forget explicit trailing slash when normalizing. Issue17324
trailing_slash = path.rstrip().endswith('/')
try:
path = urllib.parse.unquote(path, errors='surrogatepass')
except UnicodeDecodeError:
path = urllib.parse.unquote(path)
path = posixpath.normpath(path)
words = path.split('/')
words = filter(None, words)
path = self.directory
for word in words:
if os.path.dirname(word) or word in (os.curdir, os.pardir):
# Ignore components that are not a simple file/directory name
continue
path = os.path.join(path, word)
if trailing_slash:
path += '/'
return path
def copyfile(self, source, outputfile):
"""Copy all data between two file objects.
The SOURCE argument is a file object open for reading
(or anything with a read() method) and the DESTINATION
argument is a file object open for writing (or
anything with a write() method).
The only reason for overriding this would be to change
the block size or perhaps to replace newlines by CRLF
-- note however that this the default server uses this
to copy binary data as well.
"""
shutil.copyfileobj(source, outputfile)
def guess_type(self, path):
"""Guess the type of a file.
Argument is a PATH (a filename).
Return value is a string of the form type/subtype,
usable for a MIME Content-type header.
The default implementation looks the file's extension
up in the table self.extensions_map, using application/octet-stream
as a default; however it would be permissible (if
slow) to look inside the data to make a better guess.
"""
base, ext = posixpath.splitext(path)
if ext in self.extensions_map:
return self.extensions_map[ext]
ext = ext.lower()
if ext in self.extensions_map:
return self.extensions_map[ext]
else:
return self.extensions_map['']
if not mimetypes.inited:
mimetypes.init() # try to read system mime.types
extensions_map = mimetypes.types_map.copy()
extensions_map.update({
'': 'application/octet-stream', # Default
'.py': 'text/plain',
'.c': 'text/plain',
'.h': 'text/plain',
})
# Utilities for CGIHTTPRequestHandler
def _url_collapse_path(path):
"""
Given a URL path, remove extra '/'s and '.' path elements and collapse
any '..' references and returns a collapsed path.
Implements something akin to RFC-2396 5.2 step 6 to parse relative paths.
The utility of this function is limited to is_cgi method and helps
preventing some security attacks.
Returns: The reconstituted URL, which will always start with a '/'.
Raises: IndexError if too many '..' occur within the path.
"""
# Query component should not be involved.
path, _, query = path.partition('?')
path = urllib.parse.unquote(path)
# Similar to os.path.split(os.path.normpath(path)) but specific to URL
# path semantics rather than local operating system semantics.
path_parts = path.split('/')
head_parts = []
for part in path_parts[:-1]:
if part == '..':
head_parts.pop() # IndexError if more '..' than prior parts
elif part and part != '.':
head_parts.append( part )
if path_parts:
tail_part = path_parts.pop()
if tail_part:
if tail_part == '..':
head_parts.pop()
tail_part = ''
elif tail_part == '.':
tail_part = ''
else:
tail_part = ''
if query:
tail_part = '?'.join((tail_part, query))
splitpath = ('/' + '/'.join(head_parts), tail_part)
collapsed_path = "/".join(splitpath)
return collapsed_path
nobody = None
def nobody_uid():
"""Internal routine to get nobody's uid"""
global nobody
if nobody:
return nobody
try:
import pwd
except ImportError:
return -1
try:
nobody = pwd.getpwnam('nobody')[2]