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/debugapp.py | |
download | paste-git-fa100c92c06d3a8a61a0dda1a2e06018437b09c6.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/debugapp.py')
-rwxr-xr-x | paste/debug/debugapp.py | 79 |
1 files changed, 79 insertions, 0 deletions
diff --git a/paste/debug/debugapp.py b/paste/debug/debugapp.py new file mode 100755 index 0000000..f752c36 --- /dev/null +++ b/paste/debug/debugapp.py @@ -0,0 +1,79 @@ +# (c) 2005 Ian Bicking and contributors; written for Paste (http://pythonpaste.org) +# Licensed under the MIT license: http://www.opensource.org/licenses/mit-license.php +# (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 +""" +Various Applications for Debugging/Testing Purposes +""" + +import time +__all__ = ['SimpleApplication', 'SlowConsumer'] + + +class SimpleApplication(object): + """ + Produces a simple web page + """ + def __call__(self, environ, start_response): + body = b"<html><body>simple</body></html>" + start_response("200 OK", [('Content-Type', 'text/html'), + ('Content-Length', str(len(body)))]) + return [body] + +class SlowConsumer(object): + """ + Consumes an upload slowly... + + NOTE: This should use the iterator form of ``wsgi.input``, + but it isn't implemented in paste.httpserver. + """ + def __init__(self, chunk_size = 4096, delay = 1, progress = True): + self.chunk_size = chunk_size + self.delay = delay + self.progress = True + + def __call__(self, environ, start_response): + size = 0 + total = environ.get('CONTENT_LENGTH') + if total: + remaining = int(total) + while remaining > 0: + if self.progress: + print("%s of %s remaining" % (remaining, total)) + if remaining > 4096: + chunk = environ['wsgi.input'].read(4096) + else: + chunk = environ['wsgi.input'].read(remaining) + if not chunk: + break + size += len(chunk) + remaining -= len(chunk) + if self.delay: + time.sleep(self.delay) + body = "<html><body>%d bytes</body></html>" % size + else: + body = ('<html><body>\n' + '<form method="post" enctype="multipart/form-data">\n' + '<input type="file" name="file">\n' + '<input type="submit" >\n' + '</form></body></html>\n') + print("bingles") + start_response("200 OK", [('Content-Type', 'text/html'), + ('Content-Length', len(body))]) + return [body] + +def make_test_app(global_conf): + return SimpleApplication() + +make_test_app.__doc__ = SimpleApplication.__doc__ + +def make_slow_app(global_conf, chunk_size=4096, delay=1, progress=True): + from paste.deploy.converters import asbool + return SlowConsumer( + chunk_size=int(chunk_size), + delay=int(delay), + progress=asbool(progress)) + +make_slow_app.__doc__ = SlowConsumer.__doc__ |