Merge pull request #261 from Pylons/bugfix/uri_parsing

Bugfix: uri parsing

CHANGES.txt

@@ -1,3 +1,17 @@
+1.3.1 (2019-08-27)
+------------------
+
+Bugfixes
+~~~~~~~~
+
+- Waitress won't accidentally throw away part of the path if it starts with a
+  double slash (``GET //testing/whatever HTTP/1.0``). WSGI applications will
+  now receive a ``PATH_INFO`` in the environment that contains
+  ``//testing/whatever`` as required. See
+  https://github.com/Pylons/waitress/issues/260 and
+  https://github.com/Pylons/waitress/pull/261
+
+
 1.3.0 (2019-04-22)
 ------------------
 

waitress/parser.py

@@ -253,10 +253,30 @@ def close(self):
 def split_uri(uri):
     # urlsplit handles byte input by returning bytes on py3, so
     # scheme, netloc, path, query, and fragment are bytes
-    try:
-        scheme, netloc, path, query, fragment = urlparse.urlsplit(uri)
-    except UnicodeError:
-        raise ParsingError('Bad URI')
+
+    scheme = netloc = path = query = fragment = b''
+
+    # urlsplit below will treat this as a scheme-less netloc, thereby losing
+    # the original intent of the request. Here we shamelessly stole 4 lines of
+    # code from the CPython stdlib to parse out the fragment and query but
+    # leave the path alone. See
+    # https://github.com/python/cpython/blob/8c9e9b0cd5b24dfbf1424d1f253d02de80e8f5ef/Lib/urllib/parse.py#L465-L468
+    # and https://github.com/Pylons/waitress/issues/260
+
+    if uri[:2] == b'//':
+        path = uri
+
+        if b'#' in path:
+            path, fragment = path.split(b'#', 1)
+
+        if b'?' in path:
+            path, query = path.split(b'?', 1)
+    else:
+        try:
+            scheme, netloc, path, query, fragment = urlparse.urlsplit(uri)
+        except UnicodeError:
+            raise ParsingError('Bad URI')
+
     return (
         tostr(scheme),
         tostr(netloc),

waitress/tests/test_parser.py

@@ -259,6 +259,30 @@ def test_split_uri_unicode_error_raises_parsing_error(self):
         except ParsingError:
             pass
 
+    def test_split_uri_path(self):
+        self._callFUT(b'//testing/whatever')
+        self.assertEqual(self.path, '//testing/whatever')
+        self.assertEqual(self.proxy_scheme, '')
+        self.assertEqual(self.proxy_netloc, '')
+        self.assertEqual(self.query, '')
+        self.assertEqual(self.fragment, '')
+
+    def test_split_uri_path_query(self):
+        self._callFUT(b'//testing/whatever?a=1&b=2')
+        self.assertEqual(self.path, '//testing/whatever')
+        self.assertEqual(self.proxy_scheme, '')
+        self.assertEqual(self.proxy_netloc, '')
+        self.assertEqual(self.query, 'a=1&b=2')
+        self.assertEqual(self.fragment, '')
+
+    def test_split_uri_path_query_fragment(self):
+        self._callFUT(b'//testing/whatever?a=1&b=2#fragment')
+        self.assertEqual(self.path, '//testing/whatever')
+        self.assertEqual(self.proxy_scheme, '')
+        self.assertEqual(self.proxy_netloc, '')
+        self.assertEqual(self.query, 'a=1&b=2')
+        self.assertEqual(self.fragment, 'fragment')
+
 class Test_get_header_lines(unittest.TestCase):
 
     def _callFUT(self, data):