reject out-of-range code points in UTF-32 wide-string input (#5348)

* reject out-of-range code points in UTF-32 wide-string input Signed-off-by: Angadi Yashaswini <angadi@digiscrypt.com> * remove useless cast to char_traits<char>::int_type Signed-off-by: Angadi Yashaswini <angadi@digiscrypt.com> --------- Signed-off-by: Angadi Yashaswini <angadi@digiscrypt.com>
2026-08-06 09:13:18 +00:00 · 2026-08-05 13:43:36 +02:00
parent acd87e2336
commit dca9d49a33
3 changed files with 22 additions and 4 deletions
@@ -7348,8 +7348,12 @@ struct wide_string_input_helper<BaseInputAdapter, 4>
            }
            else
            {
-                // unknown character
-                utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(wc);
+                // A code point above U+10FFFF has no UTF-8 encoding. Passing the
+                // unit through would narrow it to int, where 0xFFFFFFFF becomes
+                // char_traits<char>::eof() and would end the input silently, so
+                // emit a byte that is never valid UTF-8 and let the decoder
+                // reject it.
+                utf8_bytes[0] = 0xFF;
                utf8_bytes_filled = 1;
            }
        }