mirror of
https://github.com/nlohmann/json.git
synced 2026-10-06 22:47:13 +00:00
Add basic_json_view::dump() and the comparison operators, and read floats from the parser's digit layout instead of rescanning the token. dump(indent, indent_char, ensure_ascii, number_format) writes a value the way ordered_json::parse(text).dump() writes it for the same arguments: members in document order, all of them should a key occur more than once; strings escaped by the same rules, using the library's scanning kernels; floats written with the library's to_chars conversion, so the output equals basic_json's byte for byte; integers copied from the source, where they are already canonical, except -0, which parse() reads as 0. There is no error_handler argument, because the view only holds valid UTF-8. number_format::source copies numbers exactly as they appear in the source (e.g. "1.50", "1E2", "-0"), which basic_json cannot provide. operator<< takes the indentation from the stream width, as for basic_json. The writer walks iteratively, so nesting depth is limited by memory only. operator== and operator!= compare two views, or a view and a basic_json value in either order, by the rules basic_json's operator== uses: numbers compare by value across their types, objects compare by their members with duplicate keys resolved as parse() resolves them, member order matters only where the object type keeps one, and discarded views compare as discarded basic_json values do, including under JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON. Nothing is materialized except single scalars. While parsing, the view now records where the integer digits, the fraction digits, and the exponent of a float token are, so floats and doubles with at most 19 digits are read from that layout with the library's decimal_to_float() instead of rescanning the token. Both round correctly, so the values are those of parse(). get<double>(), materialize(), dump(), and the comparisons all use it. Signed-off-by: Niels Lohmann <mail@nlohmann.me>
162 lines
5.6 KiB
C++
162 lines
5.6 KiB
C++
// __ _____ _____ _____
|
|
// __| | __| | | | JSON for Modern C++
|
|
// | | |__ | | | | | | version 3.12.0
|
|
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
|
|
//
|
|
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
|
|
// SPDX-License-Identifier: MIT
|
|
|
|
#pragma once
|
|
|
|
#include <cstddef> // size_t
|
|
#include <cstdint> // int64_t, uint64_t
|
|
#include <string> // string
|
|
#include <type_traits> // integral_constant
|
|
|
|
#include <nlohmann/json.hpp>
|
|
#include <nlohmann/detail/view/document_data.hpp>
|
|
#include <nlohmann/detail/view/macro_scope.hpp>
|
|
#include <nlohmann/detail/view/node.hpp>
|
|
#include <nlohmann/detail/view/scan.hpp>
|
|
|
|
NLOHMANN_JSON_NAMESPACE_BEGIN
|
|
namespace detail
|
|
{
|
|
namespace view
|
|
{
|
|
|
|
/*!
|
|
@brief the value of the float token of a node, as parse() converts it
|
|
|
|
Uses the lexer's conversion (detail::convert_float), so that the values are
|
|
bit-identical to parse(): float and double are converted without allocation
|
|
and independent of the locale. The digit layout recorded while parsing locates
|
|
the decimal point and the exponent without scanning the token.
|
|
*/
|
|
template<typename FloatType>
|
|
NLOHMANN_VIEW_NOINLINE FloatType float_value(const char* first, const node& n)
|
|
{
|
|
const char* const last = first + n.len;
|
|
const std::size_t neg = first[0] == '-' ? 1 : 0;
|
|
const std::size_t int_digits = n.extra & 0xFFu;
|
|
const std::size_t frac_digits = n.extra >> 8u;
|
|
std::size_t dot = std::string::npos;
|
|
std::size_t mantissa_end = n.len;
|
|
if (int_digits != 255 && frac_digits != 255)
|
|
{
|
|
dot = frac_digits != 0 ? neg + int_digits : std::string::npos;
|
|
mantissa_end = neg + int_digits + (frac_digits != 0 ? 1 + frac_digits : 0);
|
|
}
|
|
else
|
|
{
|
|
// more digits than the layout records: locate them
|
|
for (std::size_t i = 0; i < n.len; ++i)
|
|
{
|
|
if (first[i] == '.')
|
|
{
|
|
dot = i;
|
|
}
|
|
else if (first[i] == 'e' || first[i] == 'E')
|
|
{
|
|
mantissa_end = i;
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
return convert_float<FloatType>(first, last, dot, mantissa_end);
|
|
}
|
|
|
|
/*!
|
|
@brief the digits of a float token with at most 19 digits, from its layout
|
|
|
|
The digit layout recorded while parsing says where the integer digits, the
|
|
fraction digits, and the exponent are, so the digits are read eight at a
|
|
time without scanning.
|
|
|
|
@param[in] p first character of the token
|
|
@param[in] e end of the token
|
|
@param[in] limit end of the readable memory (the source text)
|
|
*/
|
|
NLOHMANN_VIEW_ALWAYS_INLINE float_significand layout_decimal(const unsigned char* p, const unsigned char* e, unsigned int_digits, unsigned frac_digits, const unsigned char* limit) noexcept
|
|
{
|
|
const bool negative = *p == '-';
|
|
p += negative ? 1 : 0;
|
|
std::uint64_t w = parse_upto19(p, int_digits, limit);
|
|
p += int_digits;
|
|
std::int64_t q = 0;
|
|
if (frac_digits != 0)
|
|
{
|
|
w = (w * int_pow10(frac_digits)) + parse_upto19(p + 1, frac_digits, limit);
|
|
p += 1 + frac_digits;
|
|
q = -static_cast<std::int64_t>(frac_digits);
|
|
}
|
|
if (p != e)
|
|
{
|
|
// [eE][+-]digits; huge exponents saturate (the parser rejected overflow)
|
|
++p;
|
|
const bool exp_negative = *p == '-';
|
|
p += (*p == '-' || *p == '+') ? 1 : 0;
|
|
std::int64_t exp_value = 0;
|
|
for (; p != e; ++p)
|
|
{
|
|
if (exp_value < 0x10000000)
|
|
{
|
|
exp_value = (exp_value * 10) + (*p - '0');
|
|
}
|
|
}
|
|
q += exp_negative ? -exp_value : exp_value;
|
|
}
|
|
|
|
float_significand d;
|
|
d.w = w;
|
|
d.exponent = q;
|
|
d.negative = negative;
|
|
return d;
|
|
}
|
|
|
|
/*!
|
|
@brief the value of a float token with at most 19 digits, from its layout
|
|
|
|
The result is correctly rounded by the lexer's conversion
|
|
(detail::decimal_to_float(): Clinger's fast path where both operands are
|
|
exact, else the Eisel-Lemire algorithm, which needs no fallback for up to 19
|
|
digits), so it is the value parse() produces.
|
|
*/
|
|
template<typename FloatType>
|
|
NLOHMANN_VIEW_ALWAYS_INLINE FloatType layout_float(const unsigned char* p, const unsigned char* e, unsigned int_digits, unsigned frac_digits, const unsigned char* limit) noexcept
|
|
{
|
|
return decimal_to_float<FloatType>(layout_decimal(p, e, int_digits, frac_digits, limit));
|
|
}
|
|
|
|
/// the value of the float token of a node, as parse() converts it; floats and
|
|
/// doubles with at most 19 digits are converted from the digit layout
|
|
template<typename FloatType>
|
|
FloatType float_value(const document_data& d, const node& n)
|
|
{
|
|
return float_value<FloatType>(d, n, std::integral_constant<bool, has_native_float_format<FloatType>::value> {});
|
|
}
|
|
|
|
template<typename FloatType>
|
|
FloatType float_value(const document_data& d, const node& n, std::true_type /*binary32 or binary64*/)
|
|
{
|
|
const unsigned int_digits = n.extra & 0xFFu;
|
|
const unsigned frac_digits = n.extra >> 8u;
|
|
if (NLOHMANN_VIEW_LIKELY(int_digits + frac_digits <= 19)) // (255 marks "many")
|
|
{
|
|
// (a float token not written by an edit is in the text)
|
|
const auto* const first = reinterpret_cast<const unsigned char*>(d.src + n.off); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
|
|
return layout_float<FloatType>(first, first + n.len, int_digits, frac_digits, reinterpret_cast<const unsigned char*>(d.src + d.size)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
|
|
}
|
|
return float_value<FloatType>(d.str(n), n);
|
|
}
|
|
|
|
template<typename FloatType>
|
|
FloatType float_value(const document_data& d, const node& n, std::false_type /*other*/)
|
|
{
|
|
return float_value<FloatType>(d.str(n), n);
|
|
}
|
|
|
|
} // namespace view
|
|
} // namespace detail
|
|
NLOHMANN_JSON_NAMESPACE_END
|