diff options
author | Marc Abramowitz <marc@marc-abramowitz.com> | 2015-04-30 17:39:24 -0700 |
---|---|---|
committer | Marc Abramowitz <marc@marc-abramowitz.com> | 2015-04-30 17:39:24 -0700 |
commit | fa100c92c06d3a8a61a0dda1a2e06018437b09c6 (patch) | |
tree | a1cc50f93fbf257685c3849e03496c5e33949281 /paste/debug/testserver.py | |
download | paste-git-test_wsgirequest_charset_use_UTF-8_instead_of_iso-8859-1.tar.gz |
test_wsgirequest_charset: Use UTF-8 instead of iso-8859-1test_wsgirequest_charset_use_UTF-8_instead_of_iso-8859-1
because it seems that the defacto standard for encoding URIs is to use UTF-8.
I've been reading about url encoding and it seems like perhaps using an
encoding other than UTF-8 is very non-standard and not well-supported (this
test is trying to use `iso-8859-1`).
From http://en.wikipedia.org/wiki/Percent-encoding
> For a non-ASCII character, it is typically converted to its byte sequence in
> UTF-8, and then each byte value is represented as above.
> The generic URI syntax mandates that new URI schemes that provide for the
> representation of character data in a URI must, in effect, represent
> characters from the unreserved set without translation, and should convert
> all other characters to bytes according to UTF-8, and then percent-encode
> those values. This requirement was introduced in January 2005 with the
> publication of RFC 3986
From http://tools.ietf.org/html/rfc3986:
> Non-ASCII characters must first be encoded according to UTF-8 [STD63], and
> then each octet of the corresponding UTF-8 sequence must be percent-encoded
> to be represented as URI characters. URI producing applications must not use
> percent-encoding in host unless it is used to represent a UTF-8 character
> sequence.
From http://tools.ietf.org/html/rfc3987:
> Conversions from URIs to IRIs MUST NOT use any character encoding other than
> UTF-8 in steps 3 and 4, even if it might be possible to guess from the
> context that another character encoding than UTF-8 was used in the URI. For
> example, the URI "http://www.example.org/r%E9sum%E9.html" might with some
> guessing be interpreted to contain two e-acute characters encoded as
> iso-8859-1. It must not be converted to an IRI containing these e-acute
> characters. Otherwise, in the future the IRI will be mapped to
> "http://www.example.org/r%C3%A9sum%C3%A9.html", which is a different URI from
> "http://www.example.org/r%E9sum%E9.html".
See issue #7, which I think this at least partially fixes.
Diffstat (limited to 'paste/debug/testserver.py')
-rwxr-xr-x | paste/debug/testserver.py | 93 |
1 files changed, 93 insertions, 0 deletions
diff --git a/paste/debug/testserver.py b/paste/debug/testserver.py new file mode 100755 index 0000000..8044c7c --- /dev/null +++ b/paste/debug/testserver.py @@ -0,0 +1,93 @@ +# (c) 2005 Clark C. Evans +# This module is part of the Python Paste Project and is released under +# the MIT License: http://www.opensource.org/licenses/mit-license.php +# This code was written with funding by http://prometheusresearch.com +""" +WSGI Test Server + +This builds upon paste.util.baseserver to customize it for regressions +where using raw_interactive won't do. + + +""" +import time +from paste.httpserver import * + +class WSGIRegressionServer(WSGIServer): + """ + A threaded WSGIServer for use in regression testing. To use this + module, call serve(application, regression=True), and then call + server.accept() to let it handle one request. When finished, use + server.stop() to shutdown the server. Note that all pending requests + are processed before the server shuts down. + """ + defaulttimeout = 10 + def __init__ (self, *args, **kwargs): + WSGIServer.__init__(self, *args, **kwargs) + self.stopping = [] + self.pending = [] + self.timeout = self.defaulttimeout + # this is a local connection, be quick + self.socket.settimeout(2) + def serve_forever(self): + from threading import Thread + thread = Thread(target=self.serve_pending) + thread.start() + def reset_expires(self): + if self.timeout: + self.expires = time.time() + self.timeout + def close_request(self, *args, **kwargs): + WSGIServer.close_request(self, *args, **kwargs) + self.pending.pop() + self.reset_expires() + def serve_pending(self): + self.reset_expires() + while not self.stopping or self.pending: + now = time.time() + if now > self.expires and self.timeout: + # note regression test doesn't handle exceptions in + # threads very well; so we just print and exit + print("\nWARNING: WSGIRegressionServer timeout exceeded\n") + break + if self.pending: + self.handle_request() + time.sleep(.1) + def stop(self): + """ stop the server (called from tester's thread) """ + self.stopping.append(True) + def accept(self, count = 1): + """ accept another request (called from tester's thread) """ + assert not self.stopping + [self.pending.append(True) for x in range(count)] + +def serve(application, host=None, port=None, handler=None): + server = WSGIRegressionServer(application, host, port, handler) + print("serving on %s:%s" % server.server_address) + server.serve_forever() + return server + +if __name__ == '__main__': + from six.moves.urllib.request import urlopen + from paste.wsgilib import dump_environ + server = serve(dump_environ) + baseuri = ("http://%s:%s" % server.server_address) + + def fetch(path): + # tell the server to humor exactly one more request + server.accept(1) + # not needed; but this is what you do if the server + # may not respond in a resonable time period + import socket + socket.setdefaulttimeout(5) + # build a uri, fetch and return + return urlopen(baseuri + path).read() + + assert "PATH_INFO: /foo" in fetch("/foo") + assert "PATH_INFO: /womble" in fetch("/womble") + + # ok, let's make one more final request... + server.accept(1) + # and then schedule a stop() + server.stop() + # and then... fetch it... + urlopen(baseuri) |