fix(domain): match IDN TLDs against IANA list in IDNA-encoded form

With consider_tld=True, the TLD was looked up in the IANA list as
written. The list stores internationalized TLDs in their ASCII
(IDNA-encoded) form, so domains like пример.рф were rejected even
though their punycode form xn--e1afmkfd.xn--p1ai was accepted.

Encode the TLD before the lookup (falling back to the raw value
when IDNA encoding fails, so unencodable TLDs are still rejected
exactly like before). hostname() and url() pass consider_tld through
to domain(), so they pick up the fix as well.

Fixes #522

Co-authored-by: rahul05ranjan <11793455+rahul05ranjan@users.noreply.github.com>

Author: rahul05ranjan

src/validators/domain.py

@@ -76,7 +76,16 @@ def domain(
     if not value:
         return False
 
-    if consider_tld and not _IanaTLD.check(value.rstrip(".").rsplit(".", 1)[-1].upper()):
+    tld = value.rstrip(".").rsplit(".", 1)[-1].upper()
+    try:
+        # IANA stores internationalized TLDs in their IDNA-encoded form
+        # (e.g. "XN--P1AI"), so the lookup must use the encoded TLD too
+        tld = tld.encode("idna").decode("utf-8").upper()
+    except UnicodeError:
+        # An unencodable TLD cannot be in the IANA list; keep the raw
+        # value and let the lookup below reject it
+        pass
+    if consider_tld and not _IanaTLD.check(tld):
         return False
 
     try:

tests/test_domain.py

@@ -47,6 +47,10 @@ def test_returns_true_on_valid_domain(value: str, rfc_1034: bool, rfc_2782: bool
         ("example_.com", True, False, True),
         ("somerandomexample.xn--fiqs8s", True, False, False),
         ("somerandomexample.onion", True, False, False),
+        # internationalized TLDs are matched via their IDNA-encoded form
+        # ref: https://github.com/python-validators/validators/issues/522
+        ("пример.рф", True, False, False),
+        ("пример.рф.", True, True, False),
     ],
 )
 def test_returns_true_on_valid_top_level_domain(
@@ -100,6 +104,8 @@ def test_returns_failed_validation_on_invalid_domain(value: str, rfc_1034: bool,
         ("_example.#13", True, False, True),
         ("example_.fo-ul", True, False, True),
         ("somerandomexample.xn-n-fiqs8s", True, False, False),
+        # non-IANA IDN TLDs must still be rejected after encoding
+        ("пример.испытание", True, False, False),
     ],
 )
 def test_returns_failed_validation_invalid_top_level_domain(