Repository navigation
Expand file tree
/
Copy pathhandlers.py
More file actions
573 lines (454 loc) · 21.2 KB
/
Copy pathhandlers.py
File metadata and controls
573 lines (454 loc) · 21.2 KB
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
"""Base classes for server/gateway implementations"""
from .util import FileWrapper, guess_scheme, is_hop_by_hop
from .headers import Headers
import sys, os, time
__all__ = [
'BaseHandler', 'SimpleHandler', 'BaseCGIHandler', 'CGIHandler',
'IISCGIHandler', 'read_environ'
]
# Weekday and month names for HTTP date/time formatting; always English!
_weekdayname = ["Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun"]
_monthname = [None, # Dummy so we can use 1-based month numbers
"Jan", "Feb", "Mar", "Apr", "May", "Jun",
"Jul", "Aug", "Sep", "Oct", "Nov", "Dec"]
def format_date_time(timestamp):
year, month, day, hh, mm, ss, wd, y, z = time.gmtime(timestamp)
return "%s, %02d %3s %4d %02d:%02d:%02d GMT" % (
_weekdayname[wd], day, _monthname[month], year, hh, mm, ss
)
_is_request = {
'SCRIPT_NAME', 'PATH_INFO', 'QUERY_STRING', 'REQUEST_METHOD', 'AUTH_TYPE',
'CONTENT_TYPE', 'CONTENT_LENGTH', 'HTTPS', 'REMOTE_USER', 'REMOTE_IDENT',
}.__contains__
def _needs_transcode(k):
return _is_request(k) or k.startswith('HTTP_') or k.startswith('SSL_') \
or (k.startswith('REDIRECT_') and _needs_transcode(k[9:]))
def read_environ():
"""Read environment, fixing HTTP variables"""
enc = sys.getfilesystemencoding()
esc = 'surrogateescape'
try:
''.encode('utf-8', esc)
except LookupError:
esc = 'replace'
environ = {}
# Take the basic environment from native-unicode os.environ. Attempt to
# fix up the variables that come from the HTTP request to compensate for
# the bytes->unicode decoding step that will already have taken place.
for k, v in os.environ.items():
if _needs_transcode(k):
# On win32, the os.environ is natively Unicode. Different servers
# decode the request bytes using different encodings.
if sys.platform == 'win32':
software = os.environ.get('SERVER_SOFTWARE', '').lower()
# On IIS, the HTTP request will be decoded as UTF-8 as long
# as the input is a valid UTF-8 sequence. Otherwise it is
# decoded using the system code page (mbcs), with no way to
# detect this has happened. Because UTF-8 is the more likely
# encoding, and mbcs is inherently unreliable (an mbcs string
# that happens to be valid UTF-8 will not be decoded as mbcs)
# always recreate the original bytes as UTF-8.
if software.startswith('microsoft-iis/'):
v = v.encode('utf-8').decode('iso-8859-1')
# Apache mod_cgi writes bytes-as-unicode (as if ISO-8859-1) direct
# to the Unicode environ. No modification needed.
elif software.startswith('apache/'):
pass
# Python 3's http.server.CGIHTTPRequestHandler decodes
# using the urllib.unquote default of UTF-8, amongst other
# issues.
elif (
software.startswith('simplehttp/')
and 'python/3' in software
):
v = v.encode('utf-8').decode('iso-8859-1')
# For other servers, guess that they have written bytes to
# the environ using stdio byte-oriented interfaces, ending up
# with the system code page.
else:
v = v.encode(enc, 'replace').decode('iso-8859-1')
# Recover bytes from unicode environ, using surrogate escapes
# where available (Python 3.1+).
else:
v = v.encode(enc, esc).decode('iso-8859-1')
environ[k] = v
return environ
class BaseHandler:
"""Manage the invocation of a WSGI application"""
# Configuration parameters; can override per-subclass or per-instance
wsgi_version = (1,0)
wsgi_multithread = True
wsgi_multiprocess = True
wsgi_run_once = False
origin_server = True # We are transmitting direct to client
http_version = "1.0" # Version that should be used for response
server_software = None # String name of server software, if any
# os_environ is used to supply configuration from the OS environment:
# by default it's a copy of 'os.environ' as of import time, but you can
# override this in e.g. your __init__ method.
os_environ= read_environ()
# Collaborator classes
wsgi_file_wrapper = FileWrapper # set to None to disable
headers_class = Headers # must be a Headers-like class
# Error handling (also per-subclass or per-instance)
traceback_limit = None # Print entire traceback to self.get_stderr()
error_status = "500 Internal Server Error"
error_headers = [('Content-Type','text/plain')]
error_body = b"A server error occurred. Please contact the administrator."
# State variables (don't mess with these)
status = result = None
headers_sent = False
headers = None
bytes_sent = 0
def run(self, application):
"""Invoke the application"""
# Note to self: don't move the close()! Asynchronous servers shouldn't
# call close() from finish_response(), so if you close() anywhere but
# the double-error branch here, you'll break asynchronous servers by
# prematurely closing. Async servers must return from 'run()' without
# closing if there might still be output to iterate over.
try:
self.setup_environ()
self.result = application(self.environ, self.start_response)
self.finish_response()
except (ConnectionAbortedError, BrokenPipeError, ConnectionResetError):
# We expect the client to close the connection abruptly from time
# to time.
return
except:
try:
self.handle_error()
except:
# If we get an error handling an error, just give up already!
self.close()
raise # ...and let the actual server figure it out.
def setup_environ(self):
"""Set up the environment for one request"""
env = self
8000
.environ = self.os_environ.copy()
self.add_cgi_vars()
env['wsgi.input'] = self.get_stdin()
env['wsgi.errors'] = self.get_stderr()
env['wsgi.version'] = self.wsgi_version
env['wsgi.run_once'] = self.wsgi_run_once
env['wsgi.url_scheme'] = self.get_scheme()
env['wsgi.multithread'] = self.wsgi_multithread
env['wsgi.multiprocess'] = self.wsgi_multiprocess
if self.wsgi_file_wrapper is not None:
env['wsgi.file_wrapper'] = self.wsgi_file_wrapper
if self.origin_server and self.server_software:
env.setdefault('SERVER_SOFTWARE',self.server_software)
def finish_response(self):
"""Send any iterable data, then close self and the iterable
Subclasses intended for use in asynchronous servers will
want to redefine this method, such that it sets up callbacks
in the event loop to iterate over the data, and to call
'self.close()' once the response is finished.
"""
try:
if not self.result_is_file() or not self.sendfile():
for data in self.result:
self.write(data)
self.finish_content()
except:
# Call close() on the iterable returned by the WSGI application
# in case of an exception.
if hasattr(self.result, 'close'):
self.result.close()
raise
else:
# We only call close() when no exception is raised, because it
# will set status, result, headers, and environ fields to None.
# See bpo-29183 for more details.
self.close()
def get_scheme(self):
"""Return the URL scheme being used"""
return guess_scheme(self.environ)
def set_content_length(self):
"""Compute Content-Length or switch to chunked encoding if possible"""
try:
blocks = len(self.result)
except (TypeError,AttributeError,NotImplementedError):
pass
else:
if blocks==1:
self.headers['Content-Length'] = str(self.bytes_sent)
return
# XXX Try for chunked encoding if origin server and client is 1.1
def cleanup_headers(self):
"""Make any necessary header changes or defaults
Subclasses can extend this to add other defaults.
"""
if 'Content-Length' not in self.headers:
self.set_content_length()
def start_response(self, status, headers,exc_info=None):
"""'start_response()' callable as specified by PEP 3333"""
if exc_info:
try:
if self.headers_sent:
raise
finally:
exc_info = None # avoid dangling circular ref
elif self.headers is not None:
raise AssertionError("Headers already set!")
self.status = status
self.headers = self.headers_class(headers)
status = self._convert_string_type(status, "Status")
self._validate_status(status)
if __debug__:
for name, val in headers:
name = self._convert_string_type(name, "Header name")
val = self._convert_string_type(val, "Header value")
assert not is_hop_by_hop(name),\
f"Hop-by-hop header, '{name}: {val}', not allowed"
return self.write
def _validate_status(self, status):
if len(status) < 4:
raise AssertionError("Status must be at least 4 characters")
if not status[:3].isdigit():
raise AssertionError("Status message must begin w/3-digit code")
if status[3] != " ":
raise AssertionError("Status message must have a space after code")
def _convert_string_type(self, value, title):
"""Convert/check value type."""
if type(value) is str:
return value
raise AssertionError(
"{0} must be of type str (got {1})".format(title, repr(value))
)
def send_preamble(self):
"""Transmit version/status/date/server, via self._write()"""
if self.origin_server:
if self.client_is_modern():
self._write(('HTTP/%s %s\r\n' % (self.http_version,self.status)).encode('iso-8859-1'))
if 'Date' not in self.headers:
self._write(
('Date: %s\r\n' % format_date_time(time.time())).encode('iso-8859-1')
)
if self.server_software and 'Server' not in self.headers:
self._write(('Server: %s\r\n' % self.server_software).encode('iso-8859-1'))
else:
self._write(('Status: %s\r\n' % self.status).encode('iso-8859-1'))
def write(self, data):
"""'write()' callable as specified by PEP 3333"""
assert type(data) is bytes, \
"write() argument must be a bytes instance"
if not self.status:
raise AssertionError("write() before start_response()")
elif not self.headers_sent:
# Before the first output, send the stored headers
self.bytes_sent = len(data) # make sure we know content-length
self.send_headers()
else:
self.bytes_sent += len(data)
# XXX check Content-Length and truncate if too many bytes written?
self._write(data)
self._flush()
def sendfile(self):
"""Platform-specific file transmission
Override this method in subclasses to support platform-specific
file transmission. It is only called if the application's
return iterable ('self.result') is an instance of
'self.wsgi_file_wrapper'.
This method should return a true value if it was able to actually
transmit the wrapped file-like object using a platform-specific
approach. It should return a false value if normal iteration
should be used instead. An exception can be raised to indicate
that transmission was attempted, but failed.
NOTE: this method should call 'self.send_headers()' if
'self.headers_sent' is false and it is going to attempt direct
transmission of the file.
"""
return False # No platform-specific transmission by default
def finish_content(self):
"""Ensure headers and content have both been sent"""
if not self.headers_sent:
# Only zero Content-Length if not set by the application (so
# that HEAD requests can be satisfied properly, see #3839)
self.headers.setdefault('Content-Length', "0")
self.send_headers()
else:
pass # XXX check if content-length was too short?
def close(self):
"""Close the iterable (if needed) and reset all instance vars
Subclasses may want to also drop the client connection.
"""
try:
if hasattr(self.result,'close'):
self.result.close()
finally:
self.result = self.headers = self.status = self.environ = None
self.bytes_sent = 0; self.headers_sent = False
def send_headers(self):
"""Transmit headers to the client, via self._write()"""
self.cleanup_headers()
self.headers_sent = True
if not self.origin_server or self.client_is_modern():
self.send_preamble()
self._write(bytes(self.headers))
def result_is_file(self):
"""True if 'self.result' is an instance of 'self.wsgi_file_wrapper'"""
wrapper = self.wsgi_file_wrapper
return wrapper is not None and isinstance(self.result,wrapper)
def client_is_modern(self):
"""True if client can accept status and headers"""
return self.environ['SERVER_PROTOCOL'].upper() != 'HTTP/0.9'
def log_exception(self,exc_info):
"""Log the 'exc_info' tuple in the server log
Subclasses may override to retarget the output or change its format.
"""
try:
from traceback import print_exception
stderr = self.get_stderr()
print_exception(
exc_info[0], exc_info[1], exc_info[2],
self.traceback_limit, stderr
)
stderr.flush()
finally:
exc_info = None
def handle_error(self):
"""Log current error, and send error output to client if possible"""
self.log_exception(sys.exc_info())
if not self.headers_sent:
self.result = self.error_output(self.environ, self.start_response)
self.finish_response()
# XXX else: attempt advanced recovery techniques for HTML or text?
def error_output(self, environ, start_response):
"""WSGI mini-app to create error output
By default, this just uses the 'error_status', 'error_headers',
and 'error_body' attributes to generate an output page. It can
be overridden in a subclass to dynamically generate diagnostics,
choose an appropriate message for the user's preferred language, etc.
Note, however, that it's not recommended from a security perspective to
spit out diagnostics to any old user; ideally, you should have to do
something special to enable diagnostic output, which is why we don't
include any here!
"""
start_response(self.error_status,self.error_headers[:],sys.exc_info())
return [self.error_body]
# Pure abstract methods; *must* be overridden in subclasses
def _write(self,data):
"""Override in subclass to buffer data for send to client
It's okay if this method actually transmits the data; BaseHandler
just separates write and flush operations for greater efficiency
when the underlying system actually has such a distinction.
"""
raise NotImplementedError
def _flush(self):
"""Override in subclass to force sending of recent '_write()' calls
It's okay if this method is a no-op (i.e., if '_write()' actually
sends the data.
"""
raise NotImplementedError
def get_stdin(self):
"""Override in subclass to return suitable 'wsgi.input'"""
raise NotImplementedError
def get_stderr(self):
"""Override in subclass to return suitable 'wsgi.errors'"""
raise NotImplementedError
def add_cgi_vars(self):
"""Override in subclass to insert CGI variables in 'self.environ'"""
raise NotImplementedError
class SimpleHandler(BaseHandler):
"""Handler that's just initialized with streams, environment, etc.
This handler subclass is intended for synchronous HTTP/1.0 origin servers,
and handles sending the entire response output, given the correct inputs.
Usage::
handler = SimpleHandler(
inp,out,err,env, multithread=False, multiprocess=True
)
handler.run(app)"""
def __init__(self,stdin,stdout,stderr,environ,
multithread=True, multiprocess=False
):
self.stdin = stdin
self.stdout = stdout
self.stderr = stderr
self.base_env = environ
self.wsgi_multithread = multithread
self.wsgi_multiprocess = multiprocess
def get_stdin(self):
return self.stdin
def get_stderr(self):
return self.stderr
def add_cgi_vars(self):
self.environ.update(self.base_env)
def _write(self,data):
result = self.stdout.write(data)
if result is None or result == len(data):
return
from warnings import warn
warn("SimpleHandler.stdout.write() should not do partial writes",
DeprecationWarning)
while data := data[result:]:
result = self.stdout.write(data)
def _flush(self):
self.stdout.flush()
self._flush = self.stdout.flush
class BaseCGIHandler(SimpleHandler):
"""CGI-like systems using input/output/error streams and environ mapping
Usage::
handler = BaseCGIHandler(inp,out,err,env)
handler.run(app)
This handler class is useful for gateway protocols like ReadyExec and
FastCGI, that have usable input/output/error streams and an environment
mapping. It's also the base class for CGIHandler, which just uses
sys.stdin, os.environ, and so on.
The constructor also takes keyword arguments 'multithread' and
'multiprocess' (defaulting to 'True' and 'False' respectively) to control
the configuration sent to the application. It sets 'origin_server' to
False (to enable CGI-like output), and assumes that 'wsgi.run_once' is
False.
"""
origin_server = False
class CGIHandler(BaseCGIHandler):
"""CGI-based invocation via sys.stdin/stdout/stderr and os.environ
Usage::
CGIHandler().run(app)
The difference between this class and BaseCGIHandler is that it always
uses 'wsgi.run_once' of 'True', 'wsgi.multithread' of 'False', and
'wsgi.multiprocess' of 'True'. It does not take any initialization
parameters, but always uses 'sys.stdin', 'os.environ', and friends.
If you need to override any of these parameters, use BaseCGIHandler
instead.
"""
wsgi_run_once = True
# Do not allow os.environ to leak between requests in Google App Engine
# and other multi-run CGI use cases. This is not easily testable.
# See http://bugs.python.org/issue7250
os_environ = {}
def __init__(self):
BaseCGIHandler.__init__(
self, sys.stdin.buffer, sys.stdout.buffer, sys.stderr,
read_environ(), multithread=False, multiprocess=True
)
class IISCGIHandler(BaseCGIHandler):
"""CGI-based invocation with workaround for IIS path bug
This handler should be used in preference to CGIHandler when deploying on
Microsoft IIS without having set the config allowPathInfo option (IIS>=7)
or metabase allowPathInfoForScriptMappings (IIS<7).
"""
wsgi_run_once = True
os_environ = {}
# By default, IIS gives a PATH_INFO that duplicates the SCRIPT_NAME at
# the front, causing problems for WSGI applications that wish to implement
# routing. This handler strips any such duplicated path.
# IIS can be configured to pass the correct PATH_INFO, but this causes
# another bug where PATH_TRANSLATED is wrong. Luckily this variable is
# rarely used and is not guaranteed by WSGI. On IIS<7, though, the
# setting can only be made on a vhost level, affecting all other script
# mappings, many of which break when exposed to the PATH_TRANSLATED bug.
# For this reason IIS<7 is almost never deployed with the fix. (Even IIS7
# rarely uses it because there is still no UI for it.)
# There is no way for CGI code to tell whether the option was set, so a
# separate handler class is provided.
def __init__(self):
environ= read_environ()
path = environ.get('PATH_INFO', '')
script = environ.get('SCRIPT_NAME', '')
if (path+'/').startswith(script+'/'):
environ['PATH_INFO'] = path[len(script):]
BaseCGIHandler.__init__(
self, sys.stdin.buffer, sys.stdout.buffer, sys.stderr,
environ, multithread=False, multiprocess=True
)