def test_url_escape_quote_plus(self):
unescaped = '+ #%'
plus_escaped = '%2B+%23%25'
escaped = '%2B%20%23%25'
self.assertEqual(url_escape(unescaped), plus_escaped)
self.assertEqual(url_escape(unescaped, plus=False), escaped)
self.assertEqual(url_unescape(plus_escaped), unescaped)
self.assertEqual(url_unescape(escaped, plus=False), unescaped)
self.assertEqual(url_unescape(plus_escaped, encoding=None),
utf8(unescaped))
self.assertEqual(url_unescape(escaped, encoding=None, plus=False),
utf8(unescaped))
def test_url_unescape_unicode(self):
tests = [
('%C3%A9', u'\u00e9', 'utf8'),
('%C3%A9', u'\u00c3\u00a9', 'latin1'),
('%C3%A9', utf8(u'\u00e9'), None),
]
for escaped, unescaped, encoding in tests:
# input strings to url_unescape should only contain ascii
# characters, but make sure the function accepts both byte
# and unicode strings.
self.assertEqual(url_unescape(to_unicode(escaped), encoding),
unescaped)
self.assertEqual(url_unescape(utf8(escaped), encoding), unescaped)
def _unquote_or_none(s):
"""None-safe wrapper around url_unescape to handle unmatched optional
groups correctly.
Note that args are passed as bytes so the handler can decide what
encoding to use.
"""
if s is None:
return s
return url_unescape(s, encoding=None, plus=False)
def environ(request):
"""Converts a `tornado.httputil.HTTPServerRequest` to a WSGI environment.
"""
hostport = request.host.split(":")
if len(hostport) == 2:
host = hostport[0]
port = int(hostport[1])
else:
host = request.host
port = 443 if request.protocol == "https" else 80
environ = {
"REQUEST_METHOD":
request.method,
"SCRIPT_NAME":
"",
"PATH_INFO":
to_wsgi_str(
escape.url_unescape(request.path, encoding=None, plus=False)),
"QUERY_STRING":
request.query,
"REMOTE_ADDR":
request.remote_ip,
"SERVER_NAME":
host,
"SERVER_PORT":
str(port),
"SERVER_PROTOCOL":
request.version,
"wsgi.version": (1, 0),
"wsgi.url_scheme":
request.protocol,
"wsgi.input":
BytesIO(escape.utf8(request.body)),
"wsgi.errors":
sys.stderr,
"wsgi.multithread":
False,
"wsgi.multiprocess":
True,
"wsgi.run_once":
False,
}
if "Content-Type" in request.headers:
environ["CONTENT_TYPE"] = request.headers.pop("Content-Type")
if "Content-Length" in request.headers:
environ["CONTENT_LENGTH"] = request.headers.pop("Content-Length")
for key, value in request.headers.items():
environ["HTTP_" + key.replace("-", "_").upper()] = value
return environ