bpo-46337: Allow caller modification of url classes

This allows the callers of urljoin and urlparse to add guaranteed scheme
classes to the url regardless of the actual scheme, which may not be in
the default uses_* lists of schemes. This call-time behavior is done
through an optional parameter that preserves backwards compatibility.

A test case is added for this, and requires the change present in
test_urlparse.checkJoin.

Author: oldaccountdeadname

Lib/test/test_urlparse.py

@@ -213,12 +213,12 @@ def _encode(t):
                     split = (scheme,) + split
                     self.checkRoundtrips(url, parsed, split)
 
-    def checkJoin(self, base, relurl, expected):
+    def checkJoin(self, base, relurl, expected, classes=[]):
         str_components = (base, relurl, expected)
-        self.assertEqual(urllib.parse.urljoin(base, relurl), expected)
+        self.assertEqual(urllib.parse.urljoin(base, relurl, classes=classes), expected)
         bytes_components = baseb, relurlb, expectedb = [
                             x.encode('ascii') for x in str_components]
-        self.assertEqual(urllib.parse.urljoin(baseb, relurlb), expectedb)
+        self.assertEqual(urllib.parse.urljoin(baseb, relurlb, classes=classes), expectedb)
 
     def test_unparse_parse(self):
         str_cases = ['Python', './Python','x-newscheme://foo.com/stuff','x://y','x:/y','x:/','/',]
@@ -417,6 +417,11 @@ def test_urljoins(self):
         self.checkJoin('svn+ssh://pathtorepo/dir1', 'dir2', 'svn+ssh://pathtorepo/dir2')
         self.checkJoin('ws://a/b','g','ws://a/g')
         self.checkJoin('wss://a/b','g','wss://a/g')
+        self.checkJoin(
+            'nonsensebase://net.loc/url/', '..',
+            'nonsensebase://net.loc/',
+            classes=[urllib.parse.SchemeClass.RELATIVE, urllib.parse.SchemeClass.NETLOC],
+        )
 
         # XXX: The following tests are no longer compatible with RFC3986
         # self.checkJoin(SIMPLE_BASE, '../../../g','http://a/../g')

Lib/urllib/parse.py

@@ -388,7 +388,7 @@ def _fix_result_transcoding():
 _fix_result_transcoding()
 del _fix_result_transcoding
 
-def urlparse(url, scheme='', allow_fragments=True):
+def urlparse(url, scheme='', allow_fragments=True, classes=set()):
     """Parse a URL into 6 components:
     <scheme>://<netloc>/<path>;<params>?<query>#<fragment>
 
@@ -411,7 +411,7 @@ def urlparse(url, scheme='', allow_fragments=True):
     url, scheme, _coerce_result = _coerce_args(url, scheme)
     splitresult = urlsplit(url, scheme, allow_fragments)
     scheme, netloc, url, query, fragment = splitresult
-    scheme_classes = _scheme_classes(scheme)
+    scheme_classes = _scheme_classes(scheme, overrides=classes)
     if SchemeClass.PARAMS in scheme_classes and ';' in url:
         url, params = _splitparams(url)
     else:
@@ -539,21 +539,22 @@ def urlunsplit(components):
         url = url + '#' + fragment
     return _coerce_result(url)
 
-def urljoin(base, url, allow_fragments=True):
+def urljoin(base, url, allow_fragments=True, classes=set()):
     """Join a base URL and a possibly relative URL to form an absolute
-    interpretation of the latter."""
+    interpretation of the latter. Some logic may be enabled by setting
+    the classes variable."""
     if not base:
         return url
     if not url:
         return base
 
     base, url, _coerce_result = _coerce_args(base, url)
     bscheme, bnetloc, bpath, bparams, bquery, bfragment = \
-            urlparse(base, '', allow_fragments)
+            urlparse(base, '', allow_fragments, classes=classes)
     scheme, netloc, path, params, query, fragment = \
-            urlparse(url, bscheme, allow_fragments)
+            urlparse(url, bscheme, allow_fragments, classes=classes)
 
-    scheme_classes = _scheme_classes(scheme)
+    scheme_classes = _scheme_classes(scheme, overrides=classes)
 
     if scheme != bscheme or SchemeClass.RELATIVE not in scheme_classes:
         return _coerce_result(url)