Review

Author: StanFromIreland

Lib/email/_header_value_parser.py

@@ -796,14 +796,13 @@ def params(self):
                         value = urllib.parse.unquote(value, encoding='latin-1')
                     else:
                         try:
-                            charset = utils._sanitize_charset_name(charset, 'ascii')
                             value = value.decode(charset, 'surrogateescape')
                         except (LookupError, UnicodeEncodeError):
                             # XXX: there should really be a custom defect for
                             # unknown character set to make it easy to find,
                             # because otherwise unknown charset is a silent
                             # failure.
-                            value = value.decode('ascii', 'surrogateescape')
+                            value = value.decode('us-ascii', 'surrogateescape')
                         if utils._has_surrogates(value):
                             param.defects.append(errors.UndecodableBytesDefect())
                 value_parts.append(value)

Lib/email/utils.py

@@ -446,16 +446,8 @@ def decode_params(params):
                 new_params.append((name, '"%s"' % value))
     return new_params
 
-_SANITIZE_TABLE = str.maketrans({i: None for i in range(128, 65536)})
-
-def _sanitize_charset_name(charset, fallback_charset):
-    if not charset:
-        return charset
-    sanitized = charset.translate(_SANITIZE_TABLE)
-    return sanitized if sanitized else fallback_charset
-
 def collapse_rfc2231_value(value, errors='replace',
-                           fallback_charset='ascii'):
+                           fallback_charset='us-ascii'):
     if not isinstance(value, tuple) or len(value) != 3:
         return unquote(value)
     # While value comes to us as a unicode string, we need it to be a bytes
@@ -466,7 +458,6 @@ def collapse_rfc2231_value(value, errors='replace',
         # Issue 17369: if charset/lang is None, decode_rfc2231 couldn't parse
         # the value, so use the fallback_charset.
         charset = fallback_charset
-    charset = _sanitize_charset_name(charset, fallback_charset)
     rawbytes = bytes(text, 'raw-unicode-escape')
     try:
         return str(rawbytes, charset, errors)

Lib/test/test_email/test_email.py

@@ -5717,7 +5717,10 @@ def test_rfc2231_bad_character_in_encoding(self):
 
 """
         msg = email.message_from_string(m)
-        self.assertEqual(msg.get_filename(), 'myfile.txt')
+        import warnings
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", DeprecationWarning)
+            self.assertEqual(msg.get_filename(), 'myfile.txt')
 
     def test_rfc2231_single_tick_in_filename_extended(self):
         eq = self.assertEqual