amorfo77/json
1
0 Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-10-09 16:07:14 +00:00
Code Issues Packages Projects Releases Wiki Activity

Avoid allocating temporary basic_json for cbor and msgpack object keys (#5328)

Browse Source 
* avoid allocating temporary basic_json for CBOR and MessagePack object keys

Signed-off-by: alexprabhat99 <alexpbara@gmail.com>

* add size() to the custom object key test type

UBJSON and BJData access object keys through size() and c_str()
directly, so the key type now provides both and the comment says why.

Signed-off-by: alexprabhat99 <alexpbara@gmail.com>

* address review: drop key size()/c_str(), test keys below the depth limit

Nothing in the library calls size() or c_str() on an object key, so the
test key type only keeps data(), which JSON_DIAGNOSTICS needs.

The CBOR and MessagePack custom key tests now also nest objects deeper
than detail::recursion_depth_limit(), so keys written by
write_cbor_iterative and write_msgpack_iterative are covered as well.

Signed-off-by: alexprabhat99 <alexpbara@gmail.com>

---------

Signed-off-by: alexprabhat99 <alexpbara@gmail.com>
This commit is contained in:
Alex Prabhat Bara authored and GitHub committed 2026-10-09 13:22:07 +02:00
1 parent d33068da73
commit 69a0c1b82c
6 files changed
+393 -151
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

include/nlohmann/detail/output/binary_writer.hpp
+105 -75
View File
@@ -244,16 +244,7 @@ class binary_writer
case value_t::string:
{
string_t storage;
const string_t& value = sanitize_utf8_for_write(*j.m_data.m_value.string, j, storage);
// step 1: write control byte and the string length
write_cbor_head(0x60, value.size());
// step 2: write the string
oa.write_characters(
reinterpret_cast<const CharType*>(value.data()),
value.size());
write_cbor_string(*j.m_data.m_value.string, j);
break;
}
@@ -316,23 +307,20 @@ class binary_writer
case value_t::object:
{
static_assert(
std::is_convertible <
typename BasicJsonType::object_t::key_type,
string_t >::value,
"object_t::key_type must be implicitly convertible to string_t");
// step 1: write control byte and the object size
write_cbor_head(0xA0, j.m_data.m_value.object->size());
for (const auto& el : *j.m_data.m_value.object)
{
// el.first is checked here, against the object as
// diagnostics context, because write_cbor(el.first)
// converts it to a temporary basic_json that would be
// used as the context instead; for error_handler_t::keep
// and ::replace/::ignore the recursive write_cbor(el.first)
// call below handles the key like any other string, so no
// separate check is needed here for those
if (error_handler == error_handler_t::strict)
{
check_utf8(el.first, j);
}
write_cbor(el.first);
// el.first is written directly (not via a temporary
// basic_json), with the object as diagnostics context
write_cbor_string(el.first, j);
write_cbor(el.second, depth + 1);
}
break;
@@ -491,39 +479,7 @@ class binary_writer
case value_t::string:
{
string_t storage;
const string_t& value = sanitize_utf8_for_write(*j.m_data.m_value.string, j, storage);
// step 1: write control byte and the string length
const auto N = to_msgpack_length(value.size(), j);
if (N <= 31)
{
// fixstr
write_number(static_cast<std::uint8_t>(0xA0 | N));
}
else if (N <= (std::numeric_limits<std::uint8_t>::max)())
{
// str 8
oa.write_character(to_char_type(0xD9));
write_number(static_cast<std::uint8_t>(N));
}
else if (N <= (std::numeric_limits<std::uint16_t>::max)())
{
// str 16
oa.write_character(to_char_type(0xDA));
write_number(static_cast<std::uint16_t>(N));
}
else
{
// str 32
oa.write_character(to_char_type(0xDB));
write_number(static_cast<std::uint32_t>(N));
}
// step 2: write the string
oa.write_characters(
reinterpret_cast<const CharType*>(value.data()),
value.size());
write_msgpack_string(*j.m_data.m_value.string, j);
break;
}
@@ -629,19 +585,20 @@ class binary_writer
case value_t::object:
{
static_assert(
std::is_convertible <
typename BasicJsonType::object_t::key_type,
string_t >::value,
"object_t::key_type must be implicitly convertible to string_t");
// step 1: write control byte and the object size
write_msgpack_object_prefix(j.m_data.m_value.object->size(), j);
for (const auto& el : *j.m_data.m_value.object)
{
// as in write_cbor, el.first is checked here against the
// object as diagnostics context; the recursive call below
// handles keep/replace/ignore like any other string
if (error_handler == error_handler_t::strict)
{
check_utf8(el.first, j);
}
write_msgpack(el.first);
// as in write_cbor, el.first is written directly with the
// object as diagnostics context
write_msgpack_string(el.first, j);
write_msgpack(el.second, depth + 1);
}
break;
@@ -1025,13 +982,9 @@ class binary_writer
continue;
}
// el.first is checked here, against the object as diagnostics
// context, like the matching check in write_cbor's object case
if (error_handler == error_handler_t::strict)
{
check_utf8(current.object_it->first, *current.value);
}
write_cbor(current.object_it->first);
// the key is written directly (not via a temporary basic_json),
// with the object as diagnostics context, as in write_cbor
write_cbor_string(current.object_it->first, *current.value);
const BasicJsonType* child = &(current.object_it->second);
++stack.back().object_it;
write_cbor_value_or_push(*child, stack);
@@ -1106,11 +1059,9 @@ class binary_writer
continue;
}
if (error_handler == error_handler_t::strict)
{
check_utf8(current.object_it->first, *current.value);
}
write_msgpack(current.object_it->first);
// as in write_cbor_iterative, the key is written directly with
// the object as diagnostics context
write_msgpack_string(current.object_it->first, *current.value);
const BasicJsonType* child = &(current.object_it->second);
++stack.back().object_it;
write_msgpack_value_or_push(*child, stack);
@@ -1988,6 +1939,85 @@ class binary_writer
}
}
/*!
@brief write a CBOR text string
@a value is checked or sanitized according to @ref error_handler, with
@a context (the string value itself, or the object a key belongs to) used
as diagnostics context; this avoids converting object keys to a temporary
basic_json just to write them
@note When object_t::key_type is not string_t, @a value is a temporary
string_t converted from the key, which lives only until the end of
the caller's statement. The reference returned by
@ref sanitize_utf8_for_write may refer to it, so it must not escape
this function.
*/
void write_cbor_string(const string_t& value, const BasicJsonType& context)
{
string_t storage;
const string_t& sanitized = sanitize_utf8_for_write(value, context, storage);
// step 1: write control byte and the string length
write_cbor_head(0x60, sanitized.size());
// step 2: write the string
oa.write_characters(
reinterpret_cast<const CharType*>(sanitized.data()),
sanitized.size());
}
/////////////
// MsgPack //
/////////////
/*!
@brief write a MessagePack str
@a value is checked or sanitized according to @ref error_handler, with
@a context used as diagnostics context, as in @ref write_cbor_string
@note As in @ref write_cbor_string, @a value may be a temporary string_t
converted from a key, so the reference returned by
@ref sanitize_utf8_for_write must not escape this function.
*/
void write_msgpack_string(const string_t& value, const BasicJsonType& context)
{
string_t storage;
const string_t& sanitized = sanitize_utf8_for_write(value, context, storage);
// step 1: write control byte and the string length
const auto N = to_msgpack_length(sanitized.size(), context);
if (N <= 31)
{
// fixstr
write_number(static_cast<std::uint8_t>(0xA0 | N));
}
else if (N <= (std::numeric_limits<std::uint8_t>::max)())
{
// str 8
oa.write_character(to_char_type(0xD9));
write_number(static_cast<std::uint8_t>(N));
}
else if (N <= (std::numeric_limits<std::uint16_t>::max)())
{
// str 16
oa.write_character(to_char_type(0xDA));
write_number(static_cast<std::uint16_t>(N));
}
else
{
// str 32
oa.write_character(to_char_type(0xDB));
write_number(static_cast<std::uint32_t>(N));
}
// step 2: write the string
oa.write_characters(
reinterpret_cast<const CharType*>(sanitized.data()),
sanitized.size());
}
////////////
// UBJSON //
////////////