Disallow _ in domain names

rendercv/data_model.py

@@ -1057,8 +1057,24 @@ class Connection(BaseModel):
     value: str
 
     @staticmethod
-    def MastodonUname2Url(id: str) -> Optional[HttpUrl]:
-        """From a Mastodon id "user@domain.example" returns profile url."""
+    def MastodonUname2Url(address: str) -> Optional[HttpUrl]:
+        """returns profile url from a mastodon user address.
+
+        Args:
+            address (str): A Mastodon user address. E.g., "user@social.example"
+
+        Returns:
+            A pydantic HttpUrl object with the https URL for the user profile
+
+        Example:
+            ```
+            url = MastodonUname2Url("user@social.example")
+            assert(url == HttpUrl(http://social.example/@user))
+            ```
+
+        Exceptions:
+            ValueError if the address is malformed.
+        """
 
         # The closest thing to a formal spec of Mastodon usernames
         # where these regular expressions from a (reference?)
@@ -1068,19 +1084,23 @@ class Connection(BaseModel):
         #
         # USERNAME_RE   = /[a-z0-9_]+([a-z0-9_.-]+[a-z0-9_]+)?/i
         # SERNAME_RE   = /[a-z0-9_]+([a-z0-9_.-]+[a-z0-9_]+)?/i
-        # MENTION_RE    = %r{(?<![=/[:word:]])@((#{USERNAME_RE})(?:@[[:word:].-]+[[:word:]]+)?)}i
-        # URL_PREFIX_RE = %r{\Ahttp(s?)://[^/]+}
+        #
+        # Note that the SERNAME expersion would allow underscores in DNS
+        # hostname labels. That would lead to invalid hostnames.
+        #
+        # I consider that a bug and will not be carrying that over here.
+        # (It is possible that pydantic would catch the error)
 
         pattern = re.compile(r"""
             ^\s*                    # ignore leading spaces
             @?                      # Optional @ prefix
             (?P<uname>[a-z0-9_]+([a-z0-9_.-]+[a-z0-9_]+)?)  # username part
             @                       # separator
-            (?P<domain>[a-z0-9_]+([a-z0-9_.-]+[a-z0-9_]+)?) # domain part
+            (?P<domain>[a-z0-9]+([a-z0-9.-]+[a-z0-9]+)?) # domain part
             \s*$                    # ignore trailing whitespace
         """, re.VERBOSE | re.IGNORECASE)
 
-        m = pattern.match(id)
+        m = pattern.match(address)
         if m is None:
             raise ValueError("Invalid mastodon address")
         uname = m.group("uname")

tests/test_data_model.py

@@ -862,14 +862,14 @@ class TestDataModel(unittest.TestCase):
                 data_model.read_input_file("nonexistent.json")
 
     def test_mastodon_parsing(self):
-        mastodon_name = 'jpgoldberg@ioc.exchange'
-        expected = HttpUrl("https://ioc.exchange/@jpgoldberg")
+        mastodon_name = 'a_tooter@example.exchange'
+        expected = HttpUrl("https://example.exchange/@a_tooter")
         result = data_model.Connection.MastodonUname2Url(mastodon_name)
         with self.subTest("Without '@' prefix"):
             self.assertEqual(result, expected)
 
-        mastodon_name = '@jpgoldberg@ioc.exchange'
-        expected = HttpUrl("https://ioc.exchange/@jpgoldberg")
+        mastodon_name = '@a_tooter@example.exchange'
+        expected = HttpUrl("https://example.exchange/@a_tooter")
         result = data_model.Connection.MastodonUname2Url(mastodon_name)
         with self.subTest("With '@' prefix"):
             self.assertEqual(result, expected)
@@ -879,5 +879,17 @@ class TestDataModel(unittest.TestCase):
             with self.assertRaises(ValueError):
                 data_model.Connection.MastodonUname2Url(mastodon_name)
 
+        mastodon_name = '@not_enough_at_symbols'
+        with self.subTest("Missing '@' separator"):
+            with self.assertRaises(ValueError):
+                data_model.Connection.MastodonUname2Url(mastodon_name)
+
+        mastodon_name = 'user@bad_domain.example'
+        with self.subTest("Underscore in domain portion"):
+            with self.assertRaises(ValueError):
+                data_model.Connection.MastodonUname2Url(mastodon_name)
+
+
+
 if __name__ == '__main__':
     unittest.main()