From c1dbaa6656acc62c586dad1018f06113cde2d8a4 Mon Sep 17 00:00:00 2001 From: Ben Boeckel Date: Tue, 6 Jun 2023 16:50:22 -0400 Subject: libcpp: reject codepoints above 0x10FFFF Unicode does not support such values because they are unrepresentable in UTF-16. libcpp/ * charset.cc: Reject encodings of codepoints above 0x10FFFF. UTF-16 does not support such codepoints and therefore all Unicode rejects such values. Signed-off-by: Ben Boeckel --- libcpp/charset.cc | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/libcpp/charset.cc b/libcpp/charset.cc index d7f323b..d4f573e 100644 --- a/libcpp/charset.cc +++ b/libcpp/charset.cc @@ -1886,6 +1886,13 @@ cpp_valid_utf8_p (const char *buffer, size_t num_bytes) int err = one_utf8_to_cppchar (&iter, &bytesleft, &cp); if (err) return false; + + /* Additionally, Unicode declares that all codepoints above 0010FFFF are + invalid because they cannot be represented in UTF-16. + + Reject such values.*/ + if (cp >= UCS_LIMIT) + return false; } /* No problems encountered. */ return true; -- cgit v1.1