Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 29 additions & 9 deletions include/nlohmann/detail/output/serializer.hpp
Original file line number Diff line number Diff line change
Expand Up @@ -465,18 +465,12 @@ class serializer
{
if (codepoint <= 0xFFFF)
{
// NOLINTNEXTLINE(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
static_cast<void>((std::snprintf)(string_buffer.data() + bytes, 7, "\\u%04x",
static_cast<std::uint16_t>(codepoint)));
bytes += 6;
write_u_escape(bytes, static_cast<std::uint16_t>(codepoint));
}
else
{
// NOLINTNEXTLINE(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
static_cast<void>((std::snprintf)(string_buffer.data() + bytes, 13, "\\u%04x\\u%04x",
static_cast<std::uint16_t>(0xD7C0u + (codepoint >> 10u)),
static_cast<std::uint16_t>(0xDC00u + (codepoint & 0x3FFu))));
bytes += 12;
write_u_escape(bytes, static_cast<std::uint16_t>(0xD7C0u + (codepoint >> 10u)));
write_u_escape(bytes, static_cast<std::uint16_t>(0xDC00u + (codepoint & 0x3FFu)));
}
}
else
Expand Down Expand Up @@ -683,6 +677,32 @@ class serializer
return result;
}

/*!
* @brief write a lowercase "\uXXXX" escape sequence into @a string_buffer
*
* Branch-free replacement for `snprintf(buf, 7, "\\u%04x", codeunit)` in the
* string escaping hot path. It writes exactly six characters ('\\', 'u' and
* four hex digits) at position @a pos of @a string_buffer via a nibble
* lookup table, avoiding the format-string parsing and locale machinery of
* `snprintf`. Advances @a pos by the number of bytes written (6).
*
* @param[in] pos position in @a string_buffer to write at; there must
* be at least 6 bytes of headroom
* @param[in] codeunit 16-bit value to encode
*/
void write_u_escape(std::size_t& pos, std::uint16_t codeunit) noexcept
{
JSON_ASSERT(string_buffer.size() - pos >= 6);
constexpr const char* nibble_to_hex = "0123456789abcdef";
string_buffer[pos + 0] = '\\';
string_buffer[pos + 1] = 'u';
string_buffer[pos + 2] = nibble_to_hex[(codeunit >> 12u) & 0x0Fu];
string_buffer[pos + 3] = nibble_to_hex[(codeunit >> 8u) & 0x0Fu];
string_buffer[pos + 4] = nibble_to_hex[(codeunit >> 4u) & 0x0Fu];
string_buffer[pos + 5] = nibble_to_hex[codeunit & 0x0Fu];
pos += 6;
}

// templates to avoid warnings about useless casts
template <typename NumberType, enable_if_t<std::is_signed<NumberType>::value, int> = 0>
bool is_negative_number(NumberType x)
Expand Down
38 changes: 29 additions & 9 deletions single_include/nlohmann/json.hpp
Original file line number Diff line number Diff line change
Expand Up @@ -19752,18 +19752,12 @@ class serializer
{
if (codepoint <= 0xFFFF)
{
// NOLINTNEXTLINE(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
static_cast<void>((std::snprintf)(string_buffer.data() + bytes, 7, "\\u%04x",
static_cast<std::uint16_t>(codepoint)));
bytes += 6;
write_u_escape(bytes, static_cast<std::uint16_t>(codepoint));
}
else
{
// NOLINTNEXTLINE(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
static_cast<void>((std::snprintf)(string_buffer.data() + bytes, 13, "\\u%04x\\u%04x",
static_cast<std::uint16_t>(0xD7C0u + (codepoint >> 10u)),
static_cast<std::uint16_t>(0xDC00u + (codepoint & 0x3FFu))));
bytes += 12;
write_u_escape(bytes, static_cast<std::uint16_t>(0xD7C0u + (codepoint >> 10u)));
write_u_escape(bytes, static_cast<std::uint16_t>(0xDC00u + (codepoint & 0x3FFu)));
}
}
else
Expand Down Expand Up @@ -19970,6 +19964,32 @@ class serializer
return result;
}

/*!
* @brief write a lowercase "\uXXXX" escape sequence into @a string_buffer
*
* Branch-free replacement for `snprintf(buf, 7, "\\u%04x", codeunit)` in the
* string escaping hot path. It writes exactly six characters ('\\', 'u' and
* four hex digits) at position @a pos of @a string_buffer via a nibble
* lookup table, avoiding the format-string parsing and locale machinery of
* `snprintf`. Advances @a pos by the number of bytes written (6).
*
* @param[in] pos position in @a string_buffer to write at; there must
* be at least 6 bytes of headroom
* @param[in] codeunit 16-bit value to encode
*/
void write_u_escape(std::size_t& pos, std::uint16_t codeunit) noexcept
{
JSON_ASSERT(string_buffer.size() - pos >= 6);
constexpr const char* nibble_to_hex = "0123456789abcdef";
string_buffer[pos + 0] = '\\';
string_buffer[pos + 1] = 'u';
string_buffer[pos + 2] = nibble_to_hex[(codeunit >> 12u) & 0x0Fu];
string_buffer[pos + 3] = nibble_to_hex[(codeunit >> 8u) & 0x0Fu];
string_buffer[pos + 4] = nibble_to_hex[(codeunit >> 4u) & 0x0Fu];
string_buffer[pos + 5] = nibble_to_hex[codeunit & 0x0Fu];
pos += 6;
}

// templates to avoid warnings about useless casts
template <typename NumberType, enable_if_t<std::is_signed<NumberType>::value, int> = 0>
bool is_negative_number(NumberType x)
Expand Down
26 changes: 26 additions & 0 deletions tests/src/unit-convenience.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -168,6 +168,32 @@ TEST_CASE("convenience functions")
CHECK_THROWS_WITH_AS(check_escaped("\xC2"), "[json.exception.type_error.316] incomplete UTF-8 string; last byte: 0xC2", json::type_error&);
}

SECTION("string escape with ensure_ascii")
{
// control characters are escaped regardless of ensure_ascii
check_escaped("\x01", "\\u0001", true);
check_escaped("\x1f", "\\u001f", true);

// non-ASCII code points in the Basic Multilingual Plane are emitted as
// a single lowercase \uXXXX escape (exercises every nibble position)
check_escaped("\xC2\x80", "\\u0080", true); // U+0080
check_escaped("\xC3\xBF", "\\u00ff", true); // U+00FF (ÿ)
check_escaped("\xDF\xBF", "\\u07ff", true); // U+07FF
check_escaped("\xE4\xBD\xA0", "\\u4f60", true); // U+4F60 (你)
check_escaped("\xEA\xAF\x8D", "\\uabcd", true); // U+ABCD
check_escaped("\xEF\xBF\xBD", "\\ufffd", true); // U+FFFD (replacement char, all-f nibbles)

// code points outside the BMP are emitted as a UTF-16 surrogate pair
// of two lowercase \uXXXX escapes
check_escaped("\xF0\x90\x80\x80", "\\ud800\\udc00", true); // U+10000 (lowest astral)
check_escaped("\xF0\x9F\x98\x80", "\\ud83d\\ude00", true); // U+1F600 (😀)
check_escaped("\xF4\x8F\xBF\xBF", "\\udbff\\udfff", true); // U+10FFFF (highest code point)

// with ensure_ascii disabled, non-ASCII input is passed through verbatim
check_escaped("\xE4\xBD\xA0", "\xE4\xBD\xA0", false);
check_escaped("\xF0\x9F\x98\x80", "\xF0\x9F\x98\x80", false);
}

SECTION("string concat")
{
using nlohmann::detail::concat;
Expand Down
Loading