def _build_wsgi_request_data(request):
request_data = {
'url': wsgiref.util.request_uri(request),
'user_ip': _wsgi_extract_user_ip(request),
'method': request.get('REQUEST_METHOD'),
}
if 'QUERY_STRING' in request:
request_data['GET'] = parse_qs(request['QUERY_STRING'], keep_blank_values=True)
# Collapse single item arrays
request_data['GET'] = dict((k, v[0] if len(v) == 1 else v) for k, v in request_data['GET'].items())
request_data['headers'] = _extract_wsgi_headers(request.items())
try:
length = int(request.get('CONTENT_LENGTH', 0))
except ValueError:
length = 0
input = request.get('wsgi.input')
if length and input and hasattr(input, 'seek') and hasattr(input, 'tell'):
pos = input.tell()
input.seek(0, 0)
request_data['body'] = input.read(length)
input.seek(pos, 0)
return request_data
def _build_wsgi_request_data(request):
request_data = {
'url': wsgiref.util.request_uri(request),
'user_ip': _wsgi_extract_user_ip(request),
'method': request.get('REQUEST_METHOD'),
}
if 'QUERY_STRING' in request:
request_data['GET'] = parse_qs(request['QUERY_STRING'], keep_blank_values=True)
# Collapse single item arrays
request_data['GET'] = dict((k, v[0] if len(v) == 1 else v) for k, v in request_data['GET'].items())
request_data['headers'] = _extract_wsgi_headers(request.items())
try:
length = int(request.get('CONTENT_LENGTH', 0))
except ValueError:
length = 0
input = request.get('wsgi.input')
if length and input and hasattr(input, 'seek') and hasattr(input, 'tell'):
pos = input.tell()
input.seek(0, 0)
request_data['body'] = input.read(length)
input.seek(pos, 0)
return request_data
def redact(self, url_string):
_redact = super(ScrubUrlTransform, self).redact
missing_colon_double_slash = False
if _starts_with_auth_re.match(url_string):
missing_colon_double_slash = True
url_string = '//%s' % url_string
try:
url_parts = urlsplit(url_string)
qs_params = parse_qs(url_parts.query, keep_blank_values=True)
except:
# This isn't a URL, return url_string which is a no-op
# for this transform
return url_string
netloc = url_parts.netloc
# If there's no netloc, give up
if not netloc:
return url_string
for qs_param, vals in iteritems(qs_params):
if qs_param.lower() in self.params_to_scrub:
vals2 = map(_redact, vals)
qs_params[qs_param] = vals2
scrubbed_qs = urlencode(qs_params, doseq=True)
if self.scrub_username and url_parts.username:
redacted_username = _redact(url_parts.username)
netloc = netloc.replace(url_parts.username, redacted_username)
if self.scrub_password and url_parts.password:
redacted_pw = _redact(url_parts.password)
netloc = netloc.replace(url_parts.password, redacted_pw)
scrubbed_url = (url_parts.scheme,
netloc,
url_parts.path,
scrubbed_qs,
url_parts.fragment)
scrubbed_url_string = urlunsplit(scrubbed_url)
if missing_colon_double_slash:
scrubbed_url_string = scrubbed_url_string.lstrip('://')
return scrubbed_url_string
def redact(self, url_string):
_redact = super(ScrubUrlTransform, self).redact
missing_colon_double_slash = False
if _starts_with_auth_re.match(url_string):
missing_colon_double_slash = True
url_string = '//%s' % url_string
try:
url_parts = urlsplit(url_string)
qs_params = parse_qs(url_parts.query)
except:
# This isn't a URL, return url_string which is a no-op
# for this transform
return url_string
netloc = url_parts.netloc
# If there's no netloc, give up
if not netloc:
return url_string
for qs_param, vals in iteritems(qs_params):
if qs_param.lower() in self.params_to_scrub:
vals2 = map(_redact, vals)
qs_params[qs_param] = vals2
scrubbed_qs = urlencode(qs_params, doseq=True)
if self.scrub_username and url_parts.username:
redacted_username = _redact(url_parts.username)
netloc = netloc.replace(url_parts.username, redacted_username)
if self.scrub_password and url_parts.password:
redacted_pw = _redact(url_parts.password)
netloc = netloc.replace(url_parts.password, redacted_pw)
scrubbed_url = (url_parts.scheme,
netloc,
url_parts.path,
scrubbed_qs,
url_parts.fragment)
scrubbed_url_string = urlunsplit(scrubbed_url)
if missing_colon_double_slash:
scrubbed_url_string = scrubbed_url_string.lstrip('://')
return scrubbed_url_string
def _compare_urls(self, url1, url2):
if _starts_with_auth_re.match(url1):
url1 = '//%s' % url1
if _starts_with_auth_re.match(url2):
url2 = '//%s' % url2
parsed_urls = map(urlparse, (url1, url2))
qs_params = map(lambda x: parse_qs(x.query), parsed_urls)
num_params = map(len, qs_params)
param_names = map(lambda x: set(x.keys()), qs_params)
self.assertEqual(*num_params)
self.assertDictEqual(*qs_params)
self.assertSetEqual(*param_names)
for facet in ('scheme', 'netloc', 'path', 'params', 'username', 'password', 'hostname', 'port'):
comp = map(lambda x: getattr(x, facet), parsed_urls)
self.assertEqual(*comp)
def _compare_urls(self, url1, url2):
if _starts_with_auth_re.match(url1):
url1 = '//%s' % url1
if _starts_with_auth_re.match(url2):
url2 = '//%s' % url2
parsed_urls = map(urlparse, (url1, url2))
qs_params = map(lambda x: parse_qs(x.query), parsed_urls)
num_params = map(len, qs_params)
param_names = map(lambda x: set(x.keys()), qs_params)
self.assertEqual(*num_params)
self.assertDictEqual(*qs_params)
self.assertSetEqual(*param_names)
for facet in ('scheme', 'netloc', 'path', 'params', 'username',
'password', 'hostname', 'port'):
comp = map(lambda x: getattr(x, facet), parsed_urls)
self.assertEqual(*comp)