Merge develop into remove-dead-checks/binary-formats

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann committed 2026-11-02 18:27:09 +01:00
commit bae6216491
75 files changed
+3200 -766

No files matched your search

@@ -833,7 +833,7 @@ class binary_writer
while (n != 0);
std::reverse(result.begin(), result.end());
return result;
}
} // LCOV_EXCL_LINE (exception cleanup only)
/*!
@brief the decimal digits of the integer @a n, with a leading '-' if it
@@ -860,7 +860,7 @@ class binary_writer
}
std::reverse(result.begin(), result.end());
return result;
}
} // LCOV_EXCL_LINE (exception cleanup only)
/*!
@brief throws because the integer @a j is too large for @a format
@@ -1792,7 +1792,7 @@ class binary_writer
std::memcpy(out, &n, sizeof(NumberType));
if (!is_little_endian)
{
std::reverse(out, out + sizeof(NumberType));
std::reverse(out, out + sizeof(NumberType)); // LCOV_EXCL_LINE (big-endian hosts only)
}
}
@@ -1921,7 +1921,7 @@ class binary_writer
const string_t& value = *j.m_data.m_value.string;
if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::int32_t>(value.size() + 1ul)))
{
return false;
return false; // LCOV_EXCL_LINE (a string of 2 GiB or more)
}
out[0] = to_char_type(0x02);
store_little_endian<std::int32_t>(p, static_cast<std::int32_t>(value.size() + 1ul));
@@ -2378,7 +2378,7 @@ class binary_writer
const std::size_t size = oa.written() - pos;
if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::int32_t>(size)))
{
return false;
return false; // LCOV_EXCL_LINE (a document of 2 GiB or more)
}
const auto le_size = static_cast<std::uint32_t>(size);
oa.overwrite(pos, is_little_endian ? le_size : byteswap(le_size));
@@ -2422,7 +2422,6 @@ class binary_writer
nothing large has been written then, and the caller writes the
document in two passes, which reports that error
*/
template<typename SinkType = OutputSinkType, typename std::enable_if<is_detected<sink_written_t, SinkType>::value, int>::type = 0>
bool write_bson_document_single_pass(const BasicJsonType& document)
{
const std::size_t start = oa.written();
@@ -2507,7 +2506,7 @@ class binary_writer
{
if (JSON_HEDLEY_UNLIKELY(!close_bson_container(nested_size_pos)))
{
return false;
return false; // LCOV_EXCL_LINE (a document of 2 GiB or more)
}
continue;
}
@@ -2522,7 +2521,7 @@ class binary_writer
if (JSON_HEDLEY_UNLIKELY(!close_bson_container(current.size_slot)))
{
return false;
return false; // LCOV_EXCL_LINE (a document of 2 GiB or more)
}
if (parents.empty())
{
@@ -2779,10 +2778,10 @@ class binary_writer
Selected through masks rather than branches, as the type and the sign of
the values in an array of mixed signs alternate unpredictably (non-negative
integers are number_unsigned after parsing). Up to 64 bits, the sign is bit
63 of the result (a narrower integer is sign-extended); computing it with
masks keeps GCC from branching on the type. A wider integer has to be
compared.
integers are number_unsigned after parsing). The sign is bit 63 of the
result (a narrower integer is sign-extended); computing it with masks keeps
GCC from branching on the type. Only called if @ref integers_fit_64_bits();
a wider number type is written with range checks on the whole value.
*/
static std::uint64_t integer_bits(const BasicJsonType& j, std::uint64_t& sign_mask) noexcept
{
@@ -2790,9 +2789,7 @@ class binary_writer
const std::uint64_t raw = is_signed
? static_cast<std::uint64_t>(j.m_data.m_value.number_integer)
: static_cast<std::uint64_t>(j.m_data.m_value.number_unsigned);
sign_mask = sizeof(typename BasicJsonType::number_integer_t) <= sizeof(std::uint64_t)
? (std::uint64_t{0} - static_cast<std::uint64_t>(is_signed)) & (std::uint64_t{0} - (raw >> 63u))
: std::uint64_t{0} - static_cast<std::uint64_t>(is_signed && j.m_data.m_value.number_integer < 0);
sign_mask = (std::uint64_t{0} - static_cast<std::uint64_t>(is_signed)) & (std::uint64_t{0} - (raw >> 63u));
return raw;
}
@@ -4156,57 +4153,34 @@ class binary_writer
}
/*!
@brief validate (dry_run) or write one BJData ND-array element of integer dtype @a T
@return whether @a el's value is in range of @a T; always true when @a dry_run is false
*/
template<typename T>
bool write_bjdata_ndarray_element(const BasicJsonType& el, const bool dry_run)
{
if (dry_run)
{
return bjdata_ndarray_value_in_range<T>(el);
}
using storage_type = typename std::conditional<std::is_unsigned<T>::value, std::uint64_t, std::int64_t>::type;
write_number(static_cast<T>(el.template get<storage_type>()), true);
return true;
}
/*!
@brief validate (dry_run) or write one BJData ND-array element of dtype 'd' (single precision)
@brief whether the BJData ND-array element @a el can be written with dtype 'd' (single precision)
@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
(so the ND-array round-trips exactly), or is infinite or NaN
*/
bool write_bjdata_ndarray_float_element(const BasicJsonType& el, const bool dry_run)
static bool bjdata_ndarray_float_in_range(const BasicJsonType& el) noexcept
{
const auto dval = static_cast<double>(el.m_data.m_value.number_float);
if (dry_run)
{
#ifdef __GNUC__
JSON_HEDLEY_DIAGNOSTIC_PUSH
JSON_HEDLEY_PRAGMA(GCC diagnostic ignored "-Wfloat-equal")
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);
// 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
return 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
JSON_HEDLEY_DIAGNOSTIC_POP
#endif
return in_range;
}
write_number(static_cast<float>(dval), true);
return true;
}
/*!
@brief write the elements of an ND-array as the number kind @a dtype names
(see @ref write_bjdata_ndarray), after they have been found to be
in range by a dry run of @ref write_bjdata_ndarray_elements
in range by @ref bjdata_ndarray_elements_in_range
The elements are encoded in blocks into space reserved from the sink.
*/
@@ -4288,20 +4262,13 @@ class binary_writer
}
/*!
@brief validate or write every element of a BJData ND-array's `_ArrayData_`
@brief whether every element of a BJData ND-array's `_ArrayData_` is in range for its dtype
@param[in] array_data the `_ArrayData_` array
@param[in] dtype the ND-array dtype marker, as returned by bjdata_ndarray_type_marker()
@param[in] dry_run true to only range-check each element, false to write it
@return whether every element is in range for @a dtype (always true when @a dry_run is false)
@return whether every element is in range for @a dtype
*/
bool write_bjdata_ndarray_elements(const BasicJsonType& array_data, const CharType dtype, const bool dry_run)
static bool bjdata_ndarray_elements_in_range(const BasicJsonType& array_data, const CharType dtype)
{
if (!dry_run)
{
write_bjdata_ndarray_values(array_data, dtype);
return true;
}
for (const auto& el : array_data)
{
bool ok = true;
@@ -4309,43 +4276,39 @@ class binary_writer
{
case 'U':
case 'B':
ok = write_bjdata_ndarray_element<std::uint8_t>(el, dry_run);
ok = bjdata_ndarray_value_in_range<std::uint8_t>(el);
break;
case 'C':
// BJData limits a char to 0..127 (the intersection of the int8 and uint8 ranges)
ok = bjdata_ndarray_value_in_range<std::int8_t>(el) && bjdata_ndarray_value_in_range<std::uint8_t>(el);
break;
case 'i':
ok = write_bjdata_ndarray_element<std::int8_t>(el, dry_run);
ok = bjdata_ndarray_value_in_range<std::int8_t>(el);
break;
case 'u':
ok = write_bjdata_ndarray_element<std::uint16_t>(el, dry_run);
ok = bjdata_ndarray_value_in_range<std::uint16_t>(el);
break;
case 'I':
ok = write_bjdata_ndarray_element<std::int16_t>(el, dry_run);
ok = bjdata_ndarray_value_in_range<std::int16_t>(el);
break;
case 'm':
ok = write_bjdata_ndarray_element<std::uint32_t>(el, dry_run);
ok = bjdata_ndarray_value_in_range<std::uint32_t>(el);
break;
case 'l':
ok = write_bjdata_ndarray_element<std::int32_t>(el, dry_run);
ok = bjdata_ndarray_value_in_range<std::int32_t>(el);
break;
case 'M':
ok = write_bjdata_ndarray_element<std::uint64_t>(el, dry_run);
ok = bjdata_ndarray_value_in_range<std::uint64_t>(el);
break;
case 'L':
ok = write_bjdata_ndarray_element<std::int64_t>(el, dry_run);
ok = bjdata_ndarray_value_in_range<std::int64_t>(el);
break;
case 'd':
ok = write_bjdata_ndarray_float_element(el, dry_run);
ok = bjdata_ndarray_float_in_range(el);
break;
case 'D':
default:
// 'D' (double) already spans the full range of number_float_t
if (!dry_run)
{
write_number(el.template get<double>(), true);
}
break;
}
if (!ok)
@@ -4432,7 +4395,7 @@ class binary_writer
const auto dim = el.template get<std::uint64_t>();
if (!value_in_range_of<std::size_t>(dim))
{
return true;
return true; // LCOV_EXCL_LINE (size_t is narrower than 64 bits)
}
const auto dim_size = static_cast<std::size_t>(dim);
@@ -4482,7 +4445,7 @@ class binary_writer
// wrap (integers) or overflow to infinity (the "single" precision
// float) instead of being reported, so such an object falls back to
// a plain object encoding as well
if (!write_bjdata_ndarray_elements(array_data, dtype, true))
if (!bjdata_ndarray_elements_in_range(array_data, dtype))
{
return true;
}
@@ -4494,7 +4457,7 @@ class binary_writer
write_ubjson(array_size, use_count, use_type, true, true, bjdata_version);
write_bjdata_ndarray_elements(array_data, dtype, false);
write_bjdata_ndarray_values(array_data, dtype);
return false;
}
@@ -4820,8 +4783,8 @@ class binary_writer
run are encoded into space reserved from the sink, as in
@ref write_array_elements; an integer that BON8 cannot write (an unsigned
one above the int64 range, or one of a number type wider than 64 bits) throws
from write_bon8_value, like any other value that is not a number. Kept out
of line, like @ref write_cbor_array.
out_of_range.407, as write_bon8_value does. Kept out of line, like
@ref write_cbor_array.
*/
template<typename ArrayType>
JSON_HEDLEY_NEVER_INLINE
@@ -4871,10 +4834,10 @@ class binary_writer
string_open = false;
}
if (unencodable)
if (JSON_HEDLEY_UNLIKELY(unencodable))
{
write_bon8_value(*it, string_open, depth + 1);
++it;
// an integer beyond the int64 range, as write_bon8_value would report it
throw_integer_out_of_range(*it, input_format_t::bon8, "int64");
}
}
}
@@ -4909,14 +4872,13 @@ class binary_writer
break;
case value_t::number_integer:
if (JSON_HEDLEY_LIKELY(integer_fits<std::int64_t>(value.m_data.m_value.number_integer)))
if (JSON_HEDLEY_UNLIKELY(!integer_fits<std::int64_t>(value.m_data.m_value.number_integer)))
{
write_bon8_integer(static_cast<std::int64_t>(value.m_data.m_value.number_integer));
string_open = false;
break;
// beyond 64 bits (number types wider than that)
throw_integer_out_of_range(value, input_format_t::bon8, "int64");
}
// beyond 64 bits (number types wider than that): throws
write_bon8_value(value, string_open, depth + 1);
write_bon8_integer(static_cast<std::int64_t>(value.m_data.m_value.number_integer));
string_open = false;
break;
case value_t::number_float:
@@ -4925,14 +4887,13 @@ class binary_writer
break;
case value_t::number_unsigned:
if (JSON_HEDLEY_LIKELY(integer_fits_max<std::int64_t>(value.m_data.m_value.number_unsigned)))
if (JSON_HEDLEY_UNLIKELY(!integer_fits_max<std::int64_t>(value.m_data.m_value.number_unsigned)))
{
write_bon8_integer(static_cast<std::int64_t>(value.m_data.m_value.number_unsigned));
string_open = false;
break;
// too large for BON8
throw_integer_out_of_range(value, input_format_t::bon8, "int64");
}
// too large for BON8: throws
write_bon8_value(value, string_open, depth + 1);
write_bon8_integer(static_cast<std::int64_t>(value.m_data.m_value.number_unsigned));
string_open = false;
break;
case value_t::object: