amorfo77/json
1
0
Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-10-03 13:10:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add an error_handler parameter to to_msgpack

Browse Source 
The MessagePack spec allows ill-formed UTF-8 in a str, so the default stays
keep (also if JSON_STRICT_BINARY_UTF8 is enabled), but decoders such as
msgpack-python reject it by default. With the parameter, strict catches
such strings and replace/ignore sanitize them, the same way as for the
other binary writers and dump().

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann
2026-10-02 09:02:34 +02:00
parent cf55a6cb3a
commit bbf9b69d38
10 changed files with 115 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/nlohmann/detail/output/binary_writer.hpp
+22 -14
View File
@@ -95,8 +95,8 @@ class binary_writer
output_vector_sink, or output_adapter_sink wrapping a
type-erased output adapter)
@param[in] error_handler_ how to treat a string value or object key that
is not valid UTF-8 (CBOR, UBJSON, BJData, and BSON only; never
consulted by @ref write_msgpack or @ref write_bon8)
is not valid UTF-8 (CBOR, MessagePack, UBJSON, BJData, and BSON;
never consulted by @ref write_bon8)
*/
explicit binary_writer(OutputSinkType sink, const error_handler_t error_handler_ = binary_writer_default_error_handler())
: oa(std::move(sink)), error_handler(error_handler_)
@@ -113,8 +113,8 @@ class binary_writer
@param[in] adapter output adapter to write to
@param[in] error_handler_ how to treat a string value or object key that
is not valid UTF-8 (CBOR, UBJSON, BJData, and BSON only; never
consulted by @ref write_msgpack or @ref write_bon8)
is not valid UTF-8 (CBOR, MessagePack, UBJSON, BJData, and BSON;
never consulted by @ref write_bon8)
*/
template < typename SinkType = OutputSinkType,
typename std::enable_if < std::is_constructible<SinkType, output_adapter_t<CharType>>::value, int >::type = 0 >
@@ -461,8 +461,11 @@ 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(j.m_data.m_value.string->size(), j);
const auto N = to_msgpack_length(value.size(), j);
if (N <= 31)
{
// fixstr
@@ -489,8 +492,8 @@ class binary_writer
// step 2: write the string
oa.write_characters(
reinterpret_cast<const CharType*>(j.m_data.m_value.string->data()),
j.m_data.m_value.string->size());
reinterpret_cast<const CharType*>(value.data()),
value.size());
break;
}
@@ -637,6 +640,13 @@ class binary_writer
// step 2: write each element
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);
write_msgpack(el.second);
}
@@ -2220,12 +2230,10 @@ class binary_writer
/*!
@brief return @a s as it should be written, honoring @ref error_handler
Used by @ref write_cbor, @ref write_ubjson (and so @ref write_bjdata), and
the BSON writing functions for string values and object keys; never by
@ref write_msgpack or @ref write_bon8, which do not take an @ref
error_handler (MessagePack's spec allows a str object to contain
ill-formed UTF-8, and BON8 always validates, since UTF-8 lead bytes are
structural there).
Used by @ref write_cbor, @ref write_msgpack, @ref write_ubjson (and so
@ref write_bjdata), and the BSON writing functions for string values and
object keys; never by @ref write_bon8, which always validates, since UTF-8
lead bytes are structural there.
- @ref error_handler_t::keep: @a s is returned unchanged, without even
checking it (the behavior of release 3.12.0 and earlier).
@@ -2600,7 +2608,7 @@ class binary_writer
OutputSinkType oa;
/// how to treat a string value or object key that is not valid UTF-8
/// (CBOR, UBJSON, BJData, and BSON only)
/// (CBOR, MessagePack, UBJSON, BJData, and BSON; not BON8)
const error_handler_t error_handler = binary_writer_default_error_handler();
};
include/nlohmann/json.hpp
+9 -6
View File
@@ -5473,26 +5473,29 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
/// @brief create a MessagePack serialization of a given JSON value
/// @sa https://json.nlohmann.me/api/basic_json/to_msgpack/
static std::vector<std::uint8_t> to_msgpack(const basic_json& j)
static std::vector<std::uint8_t> to_msgpack(const basic_json& j,
const error_handler_t error_handler = error_handler_t::keep)
{
std::vector<std::uint8_t> result;
result.reserve(detail::binary_reserve_hint(j));
vector_writer(result).write_msgpack(j);
vector_writer(result, error_handler).write_msgpack(j);
return result;
}
/// @brief create a MessagePack serialization of a given JSON value
/// @sa https://json.nlohmann.me/api/basic_json/to_msgpack/
static void to_msgpack(const basic_json& j, detail::output_adapter<std::uint8_t> o)
static void to_msgpack(const basic_json& j, detail::output_adapter<std::uint8_t> o,
const error_handler_t error_handler = error_handler_t::keep)
{
binary_writer<std::uint8_t>(o).write_msgpack(j);
binary_writer<std::uint8_t>(o, error_handler).write_msgpack(j);
}
/// @brief create a MessagePack serialization of a given JSON value
/// @sa https://json.nlohmann.me/api/basic_json/to_msgpack/
static void to_msgpack(const basic_json& j, detail::output_adapter<char> o)
static void to_msgpack(const basic_json& j, detail::output_adapter<char> o,
const error_handler_t error_handler = error_handler_t::keep)
{
binary_writer<char>(o).write_msgpack(j);
binary_writer<char>(o, error_handler).write_msgpack(j);
}
/// @brief create a UBJSON serialization of a given JSON value