Apply the IDNA Bidi Rule to every label of a Bidi domain (#188)

The idna package checks the RFC 5893 Bidi Rule only on labels that
contain right-to-left characters. RFC 5893 and UTS #46 CheckBidi
require every label to satisfy it once any label does, so domains like
1.אב.com and אב.1.com were both accepted although they render
identically.

Author: Keerthana-64

CHANGELOG.md

@@ -5,6 +5,7 @@ In Development
 * The `original` field of the returned validated email object incorrectly un-escaped the local part of the email address. Now it returns the original address, without any display name, as passed to validate_email.
 * add support python3.15
 * The IPv6 tag of a domain literal is now case-insensitive, as in the RFCs, so `me@[ipv6:::1]` is accepted (and normalized to `me@[IPv6:::1]`) when `allow_domain_literal=True`.
+* Internationalized domains with a right-to-left label are now rejected if any other label breaks the IDNA Bidi Rule (RFC 5893), such as a label starting with a digit. Such domains, like `1.xn--4dbc.com` and `xn--4dbc.1.com` (`1.אב.com` and `אב.1.com` in Unicode), could be displayed identically.
 
 2.3.0 (August 26, 2025)
 -----------------------

email_validator/syntax.py

@@ -675,6 +675,20 @@ def validate_email_domain_name(domain: str, test_environment: bool = False, glob
         raise EmailSyntaxError("The part after the @-sign contains invalid characters: " + ", ".join(sorted(bad_chars)) + ".")
     check_unsafe_chars(domain_i18n)
 
+    # If any label has right-to-left characters, the Bidi Rule applies to
+    # every label in the domain, including left-to-right ones (RFC 5893
+    # Section 1.4 and 2, UTS #46 CheckBidi). The idna package only checks
+    # each label on its own, so a label like "1" next to a right-to-left
+    # label was accepted, and such domains can be displayed identically to
+    # a different domain (e.g. 1.xn--4dbc.com and xn--4dbc.1.com, which
+    # are 1.אב.com and אב.1.com in Unicode, with Hebrew alef bet).
+    if any(unicodedata.bidirectional(c) in ("R", "AL", "AN") for c in domain_i18n):
+        for label in domain_i18n.split("."):
+            try:
+                idna.check_bidi(label, check_ltr=True)
+            except idna.IDNAError as e:
+                raise EmailSyntaxError(f"The part after the @-sign is not valid IDNA ({e}).") from e
+
     # Check that it can be encoded back to IDNA ASCII. We have no test
     # case for this.
     try:

tests/test_syntax.py

@@ -478,7 +478,7 @@ def test_domain_literal() -> None:
         ('meme@1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.1111111111222222222233333333334444444444555555555.com', 'The email address is too long (4 characters too many).'),
         ('my.long.address@1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.11111111112222222222333333333344444.info', 'The email address is too long (2 characters too many).'),
         ('my.long.address@λ111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.1111111111222222222233333333334444.info', 'The email address is too long (1-2 characters too many).'),
-        ('my.long.address@\uFB2C111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.1111111111222222222233333333334444.info', 'The email address is too long (1-3 characters too many).'),
+        ('my.long.address@\uFB2C111111111222222222233333333334444444444555555555.a666666666777777777788888888889999999999000000000.a111111111222222222233333333334444444444555555555.a666666666777777777788888888889999999999000000000.a111111111222222222233333333334444.info', 'The email address is too long (1-3 characters too many).'),
         ('my.λong.address@1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.111111111122222222223333333333444.info', 'The email address is too long (1 character too many).'),
         ('my.λong.address@1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.1111111111222222222233333333334444.info', 'The email address is too long (1-2 characters too many).'),
         ('my.\u0073\u0323\u0307.address@1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.1111111111222222222233333333334444444444555555555.6666666666777777777788888888889999999999000000000.1111111111222222222233333333334444.info', 'The email address is too long (1-2 characters too many).'),
@@ -489,6 +489,11 @@ def test_domain_literal() -> None:
         ('me@bad-tld-1', 'The part after the @-sign is not valid. It should have a period.'),
         ('me@bad.tld-2', 'The part after the @-sign is not valid. It is not within a valid top-level domain.'),
         ('me@xn--0.tld', 'The part after the @-sign is not valid IDNA (Invalid A-label).'),
+        # 1.xn--4dbc.com is 1.אב.com and xn--4dbc.1.com is אב.1.com
+        # (alef bet in Hebrew). Both display as the same string, so both are rejected.
+        ('me@1.xn--4dbc.com', 'The part after the @-sign is not valid IDNA (First codepoint in label \'1\' must be directionality L, R or AL).'),
+        ('me@xn--4dbc.1.com', 'The part after the @-sign is not valid IDNA (First codepoint in label \'1\' must be directionality L, R or AL).'),
+        ('me@1.xn--4dbrk0ce', 'The part after the @-sign is not valid IDNA (First codepoint in label \'1\' must be directionality L, R or AL).'),
         ('me@yy--0.tld', 'An email address cannot have two letters followed by two dashes immediately after the @-sign or after a period, except Punycode.'),
         ('me@yy－－0.tld', 'An email address cannot have two letters followed by two dashes immediately after the @-sign or after a period, except Punycode.'),
         ('me@[127.0.0.1]', 'A bracketed IP address after the @-sign is not allowed here.'),