avoid sign extension in char_traits<signed char>::to_int_type (#5336)

* avoid sign extension in char_traits<signed char>::to_int_type

Signed-off-by: Angadi Yashaswini <angadi@digiscrypt.com>

* spell out-of-range signed char constants as negative values (MSVC C4309)

Signed-off-by: Angadi Yashaswini <angadi@digiscrypt.com>

---------

Signed-off-by: Angadi Yashaswini <angadi@digiscrypt.com>
This commit is contained in:
Angadi56
2026-08-03 08:35:53 +02:00
committed by GitHub
parent 585929bff9
commit 5f121d8c50
4 changed files with 60 additions and 2 deletions
+3 -1
View File
@@ -231,7 +231,9 @@ struct char_traits<signed char> : std::char_traits<char>
// Redefine to_int_type function
static int_type to_int_type(char_type c) noexcept
{
return static_cast<int_type>(c);
// cast via unsigned char: sign-extending a negative char_type would make
// byte 0xFF indistinguishable from eof()
return static_cast<int_type>(static_cast<unsigned char>(c));
}
static char_type to_char_type(int_type i) noexcept
+3 -1
View File
@@ -3994,7 +3994,9 @@ struct char_traits<signed char> : std::char_traits<char>
// Redefine to_int_type function
static int_type to_int_type(char_type c) noexcept
{
return static_cast<int_type>(c);
// cast via unsigned char: sign-extending a negative char_type would make
// byte 0xFF indistinguishable from eof()
return static_cast<int_type>(static_cast<unsigned char>(c));
}
static char_type to_char_type(int_type i) noexcept
+24
View File
@@ -427,6 +427,30 @@ TEST_CASE("deserialization")
CHECK(l.events == std::vector<std::string>({"boolean(true)"}));
}
SECTION("from std::vector<signed char>")
{
std::vector<signed char> const v = {'t', 'r', 'u', 'e'};
CHECK(json::parse(v) == json(true));
CHECK(json::accept(v));
SaxEventLogger l;
CHECK(json::sax_parse(v, &l));
CHECK(l.events.size() == 1);
CHECK(l.events == std::vector<std::string>({"boolean(true)"}));
// bytes outside ASCII are negative here and must not be sign-extended;
// 0xC3 and 0xA9 do not fit in signed char (MSVC C4309), so spell them as negative values
std::vector<signed char> const umlaut = {'"', static_cast<signed char>(0xC3 - 0x100), static_cast<signed char>(0xA9 - 0x100), '"'};
CHECK(json::parse(umlaut) == json("\xC3\xA9"));
CHECK(json::accept(umlaut));
// 0xFF (spelled as -1 to stay in range) must not be reported as end of input
std::vector<signed char> const trailing = {'t', 'r', 'u', 'e', static_cast<signed char>(0xFF - 0x100)};
json _;
CHECK_THROWS_WITH_AS(_ = json::parse(trailing), "[json.exception.parse_error.101] parse error at line 1, column 5: syntax error while parsing value - invalid literal; last read: 'true\xFF'; expected end of input", json::parse_error&);
CHECK(!json::accept(trailing));
}
SECTION("from std::array")
{
std::array<uint8_t, 5> const v { {'t', 'r', 'u', 'e'} };
+30
View File
@@ -53,4 +53,34 @@ TEST_CASE("type traits")
// NOLINTEND(hicpp-avoid-c-arrays,modernize-avoid-c-arrays,cppcoreguidelines-avoid-c-arrays)
}
}
SECTION("char_traits")
{
SECTION("to_int_type does not sign-extend")
{
using unsigned_traits = nlohmann::detail::char_traits<unsigned char>;
using signed_traits = nlohmann::detail::char_traits<signed char>;
CHECK(unsigned_traits::to_int_type(static_cast<unsigned char>(0x7F)) == 0x7F);
CHECK(unsigned_traits::to_int_type(static_cast<unsigned char>(0x80)) == 0x80);
CHECK(unsigned_traits::to_int_type(static_cast<unsigned char>(0xFF)) == 0xFF);
CHECK(signed_traits::to_int_type(static_cast<signed char>(0x7F)) == 0x7F);
// 0x80 and 0xFF do not fit in signed char (MSVC C4309), so spell them as negative values
CHECK(signed_traits::to_int_type(static_cast<signed char>(0x80 - 0x100)) == 0x80);
CHECK(signed_traits::to_int_type(static_cast<signed char>(0xFF - 0x100)) == 0xFF);
}
SECTION("no byte value collides with eof")
{
using unsigned_traits = nlohmann::detail::char_traits<unsigned char>;
using signed_traits = nlohmann::detail::char_traits<signed char>;
for (int i = 0; i < 256; ++i)
{
CHECK(unsigned_traits::to_int_type(static_cast<unsigned char>(i)) != unsigned_traits::eof());
CHECK(signed_traits::to_int_type(static_cast<signed char>(i)) != signed_traits::eof());
}
}
}
}