Function validate_email_domain_name

email_validator/syntax.py:498–694

Validates the syntax of the domain part of an email address.

(domain: str, test_environment: bool = False, globally_deliverable: bool = True)

def validate_email_domain_name(domain: str, test_environment: bool = False, globally_deliverable: bool = True) -> DomainNameValidationResult:
    """Validates the syntax of the domain part of an email address."""

    # Check for invalid characters.
    # (RFC 952 plus RFC 6531 section 3.3 for internationalized addresses)
    bad_chars = {
        safe_character_display(c)
        for c in domain
        if not ATEXT_HOSTNAME_INTL.match(c)
    }
    if bad_chars:
        raise EmailSyntaxError("The part after the @-sign contains invalid characters: " + ", ".join(sorted(bad_chars)) + ".")

    # Check for unsafe characters.
    # 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.
    check_unsafe_chars(domain)

    # Reject characters that would be rejected by UTS-46 normalization next but
    # with an error message under our control.
    bad_chars = {
        safe_character_display(c) for c in domain
        if not uts46_valid_char(c)
    }
    if bad_chars:
        raise EmailSyntaxError("The part after the @-sign contains invalid characters: " + ", ".join(sorted(bad_chars)) + ".")

    # Perform UTS-46 normalization, which includes casefolding, NFC normalization,
    # and converting all label separators (the period/full stop, fullwidth full stop,
    # ideographic full stop, and halfwidth ideographic full stop) to regular dots.
    # It will also raise an exception if there is an invalid character in the input,
    # such as "⒈" which is invalid because it would expand to include a dot and
    # U+1FEF which normalizes to a backtick, which is not an allowed hostname character.
    # Since several characters *are* normalized to a dot, this has to come before
    # checks related to dots, like check_dot_atom which comes next.
    original_domain = domain
    try:
        domain = idna.uts46_remap(domain, std3_rules=False, transitional=False)
    except idna.IDNAError as e:
        raise EmailSyntaxError(f"The part after the @-sign contains invalid characters ({e}).") from e

    # Check for invalid characters after Unicode normalization which are not caught
    # by uts46_remap (see tests for examples).
    bad_chars = {
        safe_character_display(c)
        for c in domain
        if not ATEXT_HOSTNAME_INTL.match(c)
    }
    if bad_chars:
        raise EmailSyntaxError("The part after the @-sign contains invalid characters after Unicode normalization: " + ", ".join(sorted(bad_chars)) + ".")

    # The domain part is made up dot-separated "labels." Each label must
    # have at least one character and cannot start or end with dashes, which
    # means there are some surprising restrictions on periods and dashes.
    # Check that before we do IDNA encoding because the IDNA library gives
    # unfriendly errors for these cases, but after UTS-46 normalization because
    # it can insert periods and hyphens (from fullwidth characters).