gh-105704: Disallow IPv6 URLs with invalid prefix/suffix

Author: bcail

Lib/test/test_urlparse.py

@@ -1402,16 +1402,29 @@ def test_issue14072(self):
         self.assertEqual(p2.path, '+31641044153')
 
     def test_invalid_bracketed_hosts(self):
-        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[192.0.2.146]/Path?Query')
-        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[important.com:8000]/Path?Query')
-        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v123r.IP]/Path?Query')
-        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v12ae]/Path?Query')
-        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v.IP]/Path?Query')
-        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v123.]/Path?Query')
-        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[v]/Path?Query')
-        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[0439:23af::2309::fae7:1234]/Path?Query')
-        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@[0439:23af:2309::fae7:1234:2342:438e:192.0.2.146]/Path?Query')
-        self.assertRaises(ValueError, urllib.parse.urlsplit, 'Scheme://user@]v6a.ip[/Path')
+        cases = [
+            'Scheme://user@[192.0.2.146]/Path?Query',
+            'Scheme://user@[important.com:8000]/Path?Query',
+            'Scheme://user@[v123r.IP]/Path?Query',
+            'Scheme://user@[v12ae]/Path?Query',
+            'Scheme://user@[v.IP]/Path?Query',
+            'Scheme://user@[v123.]/Path?Query',
+            'Scheme://user@[v]/Path?Query',
+            'Scheme://user@[0439:23af::2309::fae7:1234]/Path?Query',
+            'Scheme://user@[0439:23af:2309::fae7:1234:2342:438e:192.0.2.146]/Path?Query',
+            'Scheme://user@]v6a.ip[/Path',
+            'Scheme://user@[v6a.ip/path?query',
+            'Scheme://user@v6a.ip]/path?query',
+            'Scheme://user@prefix.[v6a.ip]/path?query',
+            'Scheme://user@[v6a.ip].suffix/path?query',
+        ]
+
+        for case in cases:
+            with self.subTest(case=case):
+                with self.assertRaises(ValueError):
+                    urllib.parse.urlsplit(case).hostname
+                with self.assertRaises(ValueError):
+                    urllib.parse.urlparse(case).hostname
 
     def test_splitting_bracketed_hosts(self):
         p1 = urllib.parse.urlsplit('scheme://user@[v6a.ip]/path?query')

Lib/urllib/parse.py

@@ -206,10 +206,15 @@ def _userinfo(self):
     def _hostinfo(self):
         netloc = self.netloc
         _, _, hostinfo = netloc.rpartition('@')
-        _, have_open_br, bracketed = hostinfo.partition('[')
+        bracket_prefix, have_open_br, bracketed = hostinfo.partition('[')
         if have_open_br:
+            if bracket_prefix:
+                raise ValueError('Invalid IPv6 URL')
             hostname, _, port = bracketed.partition(']')
-            _, _, port = port.partition(':')
+            _check_bracketed_host(hostname)
+            bracket_suffix, _, port = port.partition(':')
+            if bracket_suffix:
+                raise ValueError('Invalid IPv6 URL')
         else:
             hostname, _, port = hostinfo.partition(':')
         if not port:
@@ -504,9 +509,6 @@ def _urlsplit(url, scheme=None, allow_fragments=True):
         if (('[' in netloc and ']' not in netloc) or
                 (']' in netloc and '[' not in netloc)):
             raise ValueError("Invalid IPv6 URL")
-        if '[' in netloc and ']' in netloc:
-            bracketed_host = netloc.partition('[')[2].partition(']')[0]
-            _check_bracketed_host(bracketed_host)
     if allow_fragments and '#' in url:
         url, fragment = url.split('#', 1)
     if '?' in url: