Fix some typos in comments, improve some comments, merge some redundant tests

Author: JoshData

email_validator/rfc_constants.py

@@ -13,7 +13,7 @@
 
 # RFC 6531 section 3.3 extends the allowed characters in internationalized
 # addresses to also include three specific ranges of UTF8 defined in
-# RFC3629 section 4, which appear to be the Unicode code points from
+# RFC 3629 section 4, which appear to be the Unicode code points from
 # U+0080 to U+10FFFF.
 ATEXT_INTL = ATEXT + u"\u0080-\U0010FFFF"
 ATEXT_INTL_RE = re.compile('[.' + ATEXT_INTL + ']')  # ATEXT_INTL plus dots

email_validator/syntax.py

@@ -45,7 +45,7 @@ def validate_email_local_part(local: str, allow_smtputf8: bool = True, allow_emp
                 "smtputf8": False,
             }
 
-    # Check the length of the local part by couting characters.
+    # Check the length of the local part by counting characters.
     # (RFC 5321 4.5.3.1.1)
     # We're checking the number of characters here. If the local part
     # is ASCII-only, then that's the same as bytes (octets). If it's
@@ -97,7 +97,7 @@ def validate_email_local_part(local: str, allow_smtputf8: bool = True, allow_emp
         # so we'll return the normalized local part in the return value.
         local = unicodedata.normalize("NFC", local)
 
-        # Check for unsafe characters.
+        # Check that the local part is a valid, safe, and sensible Unicode string.
         # Some of this may be redundant with the range U+0080 to U+10FFFF that is checked
         # by DOT_ATOM_TEXT_INTL. Other characters may be permitted by the email specs, but
         # they may not be valid, safe, or sensible Unicode strings.

tests/test_syntax.py

@@ -256,9 +256,16 @@ def test_email_valid_intl_local_part(email_input, output):
          "The part after the @-sign contains invalid characters (Codepoint U+2488 not allowed "
          "at position 1 in '⒈wouldbeinvalid.com')."),
         ('@example.com', 'There must be something before the @-sign.'),
+        ('white space@test', 'The email address contains invalid characters before the @-sign: SPACE.'),
+        ('test@white space', 'The part after the @-sign contains invalid characters: SPACE.'),
         ('\nmy@example.com', 'The email address contains invalid characters before the @-sign: U+000A.'),
         ('m\ny@example.com', 'The email address contains invalid characters before the @-sign: U+000A.'),
         ('my\n@example.com', 'The email address contains invalid characters before the @-sign: U+000A.'),
+<<<<<<< HEAD
+=======
+        ('test@\n', 'The part after the @-sign contains invalid characters: U+000A.'),
+        ('bad"quotes"@example.com', 'The email address contains invalid characters before the @-sign: \'"\'.'),
+>>>>>>> 6146614 (fixup)
         ('11111111112222222222333333333344444444445555555555666666666677777@example.com', 'The email address is too long before the @-sign (1 character too many).'),
         ('111111111122222222223333333333444444444455555555556666666666777777@example.com', 'The email address is too long before the @-sign (2 characters too many).'),
         ('me@1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.111111111122222222223333333333444444444455555555556.com', 'The email address is too long (4 characters too many).'),
@@ -318,7 +325,8 @@ def test_email_invalid_reserved_domain(email_input):
     ],
 )
 def test_email_unsafe_character(s, expected_error):
-    # Check for various unsafe characters:
+    # Check for various unsafe characters that are permitted by the email
+    # specs but should be disallowed for being unsafe or not sensible Unicode.
 
     with pytest.raises(EmailSyntaxError) as exc_info:
         validate_email(s + "@test", test_environment=True)
@@ -329,30 +337,14 @@ def test_email_unsafe_character(s, expected_error):
     assert "The email address contains unsafe characters" in str(exc_info.value)
 
 
-@pytest.mark.parametrize(
-    ('email_input', 'expected_error'),
-    [
-        ('white space@test', 'The email address contains invalid characters before the @-sign: SPACE.'),
-        ('test@white space', 'The part after the @-sign contains invalid characters: SPACE.'),
-        ('\n@test', 'The email address contains invalid characters before the @-sign: U+000A.'),
-        ('test@\n', 'The part after the @-sign contains invalid characters: U+000A.'),
-    ],
-)
-def test_email_invalid_character(email_input, expected_error):
-    # Check for various unsafe test_email_invalid_character_smtputf8:
-    with pytest.raises(EmailSyntaxError) as exc_info:
-        validate_email(email_input, test_environment=True)
-    assert str(exc_info.value) == expected_error
-
-
 @pytest.mark.parametrize(
     ('email_input', 'expected_error'),
     [
         ('λambdaツ@test', 'Internationalized characters before the @-sign are not supported: \'λ\', \'ツ\'.'),
     ],
 )
 def test_email_invalid_character_smtputf8(email_input, expected_error):
-    # Check for various unsafe characters:
+    # Check that internationalized characters are rejected if allow_smtputf8=False.
     with pytest.raises(EmailSyntaxError) as exc_info:
         validate_email(email_input, allow_smtputf8=False, test_environment=True)
     assert str(exc_info.value) == expected_error
@@ -545,7 +537,7 @@ def test_pyisemail_tests(email_input, status):
     elif "_ERR_" in status or "_TOOLONG" in status \
          or "_CFWS_FWS" in status or "_CFWS_COMMENT" in status \
          or "_IPV6" in status or status == "ISEMAIL_RFC5322_DOMAIN":
-        # Invalid syntax, extranous whitespace, and "(comments)" should be rejected.
+        # Invalid syntax, extraneous whitespace, and "(comments)" should be rejected.
         # The _IPV6_ diagnoses appear to represent syntactically invalid domain literals.
         # The ISEMAIL_RFC5322_DOMAIN diagnosis appears to be a syntactically invalid domain.
         with pytest.raises(EmailSyntaxError):