potok/json
1
0
Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-07-21 19:23:03 +04:00
Code Packages Releases Wiki Activity

reject unpaired UTF-16 surrogates in wide-string input (#5276)

Browse Source
This commit is contained in:
Angadi56
2026-07-19 22:03:42 +05:30
committed by GitHub
parent a03e65420c
commit 1c5a953de5
3 changed files with 75 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/nlohmann/detail/input/input_adapters.hpp
+21 -8
View File
@@ -395,17 +395,30 @@ struct wide_string_input_helper<BaseInputAdapter, 2>
}
else
{
if (JSON_HEDLEY_UNLIKELY(!input.empty()))
// A supplementary code point is a high surrogate (0xD800..0xDBFF)
// followed by a low surrogate (0xDC00..0xDFFF). A lone low
// surrogate, a high surrogate at the end of the input, or a high
// surrogate followed by any other unit is malformed UTF-16. In
// that case the offending unit is passed through unchanged so the
// UTF-8 decoder rejects it, matching how \uXXXX surrogate escapes
// are handled in the lexer.
bool valid_pair = false;
if (wc <= 0xDBFF && JSON_HEDLEY_UNLIKELY(!input.empty()))
{
const auto wc2 = static_cast<unsigned int>(input.get_character());
const auto charcode = 0x10000u + (((static_cast<unsigned int>(wc) & 0x3FFu) << 10u) | (wc2 & 0x3FFu));
utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xF0u | (charcode >> 18u));
utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 12u) & 0x3Fu));
utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 6u) & 0x3Fu));
utf8_bytes[3] = static_cast<std::char_traits<char>::int_type>(0x80u | (charcode & 0x3Fu));
utf8_bytes_filled = 4;
if (0xDC00 <= wc2 && wc2 <= 0xDFFF)
{
const auto charcode = 0x10000u + (((static_cast<unsigned int>(wc) & 0x3FFu) << 10u) | (wc2 & 0x3FFu));
utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(0xF0u | (charcode >> 18u));
utf8_bytes[1] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 12u) & 0x3Fu));
utf8_bytes[2] = static_cast<std::char_traits<char>::int_type>(0x80u | ((charcode >> 6u) & 0x3Fu));
utf8_bytes[3] = static_cast<std::char_traits<char>::int_type>(0x80u | (charcode & 0x3Fu));
utf8_bytes_filled = 4;
valid_pair = true;
}
}
else
if (!valid_pair)
{
utf8_bytes[0] = static_cast<std::char_traits<char>::int_type>(wc);
utf8_bytes_filled = 1;