bpo-38216, bpo-36274: Allow subclasses to separately override validation and encoding behavior (GH-16448)
* bpo-38216: Allow bypassing input validation
* bpo-36274: Also allow the URL encoding to be overridden.
* bpo-38216, bpo-36274: Add tests demonstrating a hook for overriding validation, test demonstrating override encoding, and a test to capture expectation of the interface for the URL.
* Call with skip_host to avoid tripping on the host checking in the URL.
* Remove obsolete comment.
* Make _prepare_path_encoding its own attr.
This makes overriding just that simpler.
Also, don't use the := operator to make backporting easier.
* Add a news entry.
* _prepare_path_encoding -> _encode_prepared_path()
* Once again separate the path validation and request encoding, drastically simplifying the behavior. Drop the guarantee that all processing happens in _prepare_path.
diff --git a/Lib/http/client.py b/Lib/http/client.py
index f61267e..33a4347 100644
--- a/Lib/http/client.py
+++ b/Lib/http/client.py
@@ -1085,18 +1085,15 @@
else:
raise CannotSendRequest(self.__state)
- # Save the method we use, we need it later in the response phase
+ # Save the method for use later in the response phase
self._method = method
- if not url:
- url = '/'
- # Prevent CVE-2019-9740.
- if match := _contains_disallowed_url_pchar_re.search(url):
- raise InvalidURL(f"URL can't contain control characters. {url!r} "
- f"(found at least {match.group()!r})")
+
+ url = url or '/'
+ self._validate_path(url)
+
request = '%s %s %s' % (method, url, self._http_vsn_str)
- # Non-ASCII characters should have been eliminated earlier
- self._output(request.encode('ascii'))
+ self._output(self._encode_request(request))
if self._http_vsn == 11:
# Issue some standard headers for better HTTP/1.1 compliance
@@ -1174,6 +1171,18 @@
# For HTTP/1.0, the server will assume "not chunked"
pass
+ def _encode_request(self, request):
+ # ASCII also helps prevent CVE-2019-9740.
+ return request.encode('ascii')
+
+ def _validate_path(self, url):
+ """Validate a url for putrequest."""
+ # Prevent CVE-2019-9740.
+ match = _contains_disallowed_url_pchar_re.search(url)
+ if match:
+ raise InvalidURL(f"URL can't contain control characters. {url!r} "
+ f"(found at least {match.group()!r})")
+
def putheader(self, header, *values):
"""Send a request header line to the server.