Round-trip BJData ND-array annotations exactly (single precision, key order)

Squashed onto develop from:
- Round-trip BJData ND-array annotations exactly (single precision, key order)

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann
2026-10-06 07:30:26 +02:00
parent 8a142bc436
commit 6b4f4aade6
5 changed files with 166 additions and 50 deletions
+58 -22
View File
@@ -16423,10 +16423,15 @@ class binary_reader
is_ndarray can only return `true` when its initial value
is `false`
@param[in] prefix type marker if already read, otherwise set to 0
@param[in] ndarray_dtype the element type marker of the enclosing bjdata ndarray if
already known (it precedes the dimension vector read here),
otherwise 0; used to emit the "_ArrayType_" annotation key
before "_ArraySize_" if a dimension vector turns out to
describe an ndarray
@return whether size determination completed
*/
bool get_ubjson_size_value(std::size_t& result, bool& is_ndarray, char_int_type prefix = 0)
bool get_ubjson_size_value(std::size_t& result, bool& is_ndarray, char_int_type prefix = 0, char_int_type ndarray_dtype = 0)
{
if (prefix == 0)
{
@@ -16539,8 +16544,34 @@ class binary_reader
}
}
if (JSON_HEDLEY_UNLIKELY(!sax->start_object(3)))
{
return false;
}
// the element type precedes the dimension vector (see get_ubjson_size_type)
// and is passed down as ndarray_dtype; emit it here so the annotation keys
// follow the documented _ArrayType_, _ArraySize_, _ArrayData_ order
if (ndarray_dtype != 0)
{
const char* type_name = bjd_type_name(ndarray_dtype);
if (JSON_HEDLEY_UNLIKELY(type_name == nullptr))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message("invalid byte: 0x" + last_token, "type"), nullptr));
}
string_t type_key = "_ArrayType_";
string_t type = type_name; // sax->string() takes a reference
if (JSON_HEDLEY_UNLIKELY(!sax->key(type_key) || !sax->string(type)))
{
return false;
}
}
string_t key = "_ArraySize_";
if (JSON_HEDLEY_UNLIKELY(!sax->start_object(3) || !sax->key(key) || !sax->start_array(dim.size())))
if (JSON_HEDLEY_UNLIKELY(!sax->key(key) || !sax->start_array(dim.size())))
{
return false;
}
@@ -16648,7 +16679,7 @@ class binary_reader
exception_message(concat("expected '#' after type information; last byte: 0x", last_token), "size"), nullptr));
}
const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
const bool is_error = get_ubjson_size_value(result.first, is_ndarray, 0, result.second);
// an ndarray was read here only if the flag flipped; when it was
// seeded true, get_ubjson_size_value() already rejected the nested
// dimension vector
@@ -16841,27 +16872,17 @@ class binary_reader
if (input_format == input_format_t::bjdata && size_and_type.first != npos && (size_and_type.second & (1 << 8)) != 0)
{
size_and_type.second &= ~(static_cast<char_int_type>(1) << 8); // use bit 8 to indicate ndarray, here we remove the bit to restore the type marker
const char* type_name = bjd_type_name(size_and_type.second);
string_t key = "_ArrayType_";
if (JSON_HEDLEY_UNLIKELY(type_name == nullptr))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message("invalid byte: 0x" + last_token, "type"), nullptr));
}
string_t type = type_name; // sax->string() takes a reference
if (JSON_HEDLEY_UNLIKELY(!sax->key(key) || !sax->string(type)))
{
return false;
}
// the "_ArrayType_" and "_ArraySize_" annotation keys were already emitted by
// get_ubjson_size_value() (the type marker is known before the dimension vector
// that determines size_and_type.first is read, so it is emitted first there to
// match the documented _ArrayType_, _ArraySize_, _ArrayData_ key order)
if (size_and_type.second == 'C' || size_and_type.second == 'B')
{
size_and_type.second = 'U';
}
key = "_ArrayData_";
string_t key = "_ArrayData_";
if (JSON_HEDLEY_UNLIKELY(!sax->key(key) || !sax->start_array(size_and_type.first) ))
{
return false;
@@ -23277,16 +23298,31 @@ class binary_writer
/*!
@brief validate (dry_run) or write one BJData ND-array element of dtype 'd' (single precision)
@return whether @a el's value fits a float without overflow; always true when @a dry_run is false
@return whether @a el's value survives narrowing to float and back without any change
(so the ND-array round-trips exactly), or is infinite or NaN; always true when
@a dry_run is false
*/
bool write_bjdata_ndarray_float_element(const BasicJsonType& el, const bool dry_run)
{
const auto dval = el.template get<double>();
if (dry_run)
{
return !std::isfinite(dval) ||
(dval >= static_cast<double>(std::numeric_limits<float>::lowest()) &&
dval <= static_cast<double>((std::numeric_limits<float>::max)()));
#ifdef __GNUC__
JSON_HEDLEY_DIAGNOSTIC_PUSH
JSON_HEDLEY_PRAGMA(GCC diagnostic ignored "-Wfloat-equal")
#endif
// a value that would be rounded (rather than exactly represented) by the
// narrowing to float is treated like an out-of-range integer element; this
// is the same criterion write_compact_float() uses for CBOR/MessagePack
const bool in_range = std::isnan(dval) ||
(dval >= static_cast<double>(std::numeric_limits<float>::lowest()) &&
dval <= static_cast<double>((std::numeric_limits<float>::max)()) &&
static_cast<double>(static_cast<float>(dval)) == dval) ||
std::isinf(dval);
#ifdef __GNUC__
JSON_HEDLEY_DIAGNOSTIC_POP
#endif
return in_range;
}
write_number(static_cast<float>(dval), true);
return true;