wt/json
1
0 Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-10-21 11:29:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'develop' into claude/test-compilation-speed-993125

Browse Source 
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
This commit is contained in:
Niels Lohmann committed 2026-10-21 10:45:45 +02:00
2 parents 589c29d69b bd5227c2ec
commit d01e6382fe
496 files changed
+623369 -6434
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

include/nlohmann/detail/abi_config.hpp
+33
View File
@@ -0,0 +1,33 @@
// __ _____ _____ _____
// __| | __| | | | 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 <nlohmann/detail/abi_macros.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
/*!
@brief the configuration macros that json_view.hpp reads
json.hpp undefines these macros at its end (see macro_unscope.hpp), so code
that builds on the library after it (json_view.hpp) reads them here. A macro
is added when the view starts to depend on it. Like the
macros, they are part of the ABI namespace, so they always match the
basic_json they are used with.
*/
struct abi_config
{
/// JSON_STRICT_NUL_HANDLING: a null byte is an error, not the end of input
static constexpr bool strict_nul_handling = JSON_STRICT_NUL_HANDLING != 0;
};
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/abi_macros.hpp
+40 -4
View File
@@ -54,6 +54,14 @@
#define JSON_USE_OBJECTS_FOR_ENUM_KEYED_MAPS 0
#endif
#ifndef JSON_DISABLE_STREAM_BULK_SCAN
#define JSON_DISABLE_STREAM_BULK_SCAN 0
#endif
#ifndef JSON_DISABLE_UNLOCKED_FILE_IO
#define JSON_DISABLE_UNLOCKED_FILE_IO 0
#endif
#if JSON_DIAGNOSTICS
#define NLOHMANN_JSON_ABI_TAG_DIAGNOSTICS _diag
#else
@@ -102,14 +110,38 @@
#define NLOHMANN_JSON_ABI_TAG_OBJECTS_FOR_ENUM_KEYED_MAPS
#endif
#if JSON_DISABLE_STREAM_BULK_SCAN
#define NLOHMANN_JSON_ABI_TAG_DISABLE_STREAM_BULK_SCAN _dsbs
#else
#define NLOHMANN_JSON_ABI_TAG_DISABLE_STREAM_BULK_SCAN
#endif
#if JSON_DISABLE_UNLOCKED_FILE_IO
#define NLOHMANN_JSON_ABI_TAG_DISABLE_UNLOCKED_FILE_IO _dufio
#else
#define NLOHMANN_JSON_ABI_TAG_DISABLE_UNLOCKED_FILE_IO
#endif
#ifdef JSON_VIEW_NO_SIMD
#define NLOHMANN_JSON_ABI_TAG_VIEW_NO_SIMD _vns
#else
#define NLOHMANN_JSON_ABI_TAG_VIEW_NO_SIMD
#endif
#ifdef JSON_VIEW_USE_SSSE3
#define NLOHMANN_JSON_ABI_TAG_VIEW_USE_SSSE3 _vssse3
#else
#define NLOHMANN_JSON_ABI_TAG_VIEW_USE_SSSE3
#endif
#ifndef NLOHMANN_JSON_NAMESPACE_NO_VERSION
#define NLOHMANN_JSON_NAMESPACE_NO_VERSION 0
#endif
// Construct the namespace ABI tags component
#define NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c, d, e, f, g, h) json_abi ## a ## b ## c ## d ## e ## f ## g ## h
#define NLOHMANN_JSON_ABI_TAGS_CONCAT(a, b, c, d, e, f, g, h) \
NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c, d, e, f, g, h)
#define NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c, d, e, f, g, h, i, j, k, l) json_abi ## a ## b ## c ## d ## e ## f ## g ## h ## i ## j ## k ## l
#define NLOHMANN_JSON_ABI_TAGS_CONCAT(a, b, c, d, e, f, g, h, i, j, k, l) \
NLOHMANN_JSON_ABI_TAGS_CONCAT_EX(a, b, c, d, e, f, g, h, i, j, k, l)
#define NLOHMANN_JSON_ABI_TAGS \
NLOHMANN_JSON_ABI_TAGS_CONCAT( \
@@ -120,7 +152,11 @@
NLOHMANN_JSON_ABI_TAG_PRECISE_STREAM_POSITION, \
NLOHMANN_JSON_ABI_TAG_STRICT_NUL_HANDLING, \
NLOHMANN_JSON_ABI_TAG_STRICT_BINARY_UTF8, \
NLOHMANN_JSON_ABI_TAG_OBJECTS_FOR_ENUM_KEYED_MAPS)
NLOHMANN_JSON_ABI_TAG_OBJECTS_FOR_ENUM_KEYED_MAPS, \
NLOHMANN_JSON_ABI_TAG_DISABLE_STREAM_BULK_SCAN, \
NLOHMANN_JSON_ABI_TAG_DISABLE_UNLOCKED_FILE_IO, \
NLOHMANN_JSON_ABI_TAG_VIEW_NO_SIMD, \
NLOHMANN_JSON_ABI_TAG_VIEW_USE_SSSE3)
// Construct the namespace version component
#define NLOHMANN_JSON_NAMESPACE_VERSION_CONCAT_EX(major, minor, patch) \
include/nlohmann/detail/bit_ops.hpp
+47 -7
View File
@@ -9,11 +9,12 @@
#pragma once
#include <cstdint> // uint64_t
#if !defined(__SIZEOF_INT128__) && defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
#include <intrin0.h> // __umulh, _umul128
#include <cstring> // memcpy
#if defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64)) && (!defined(__SIZEOF_INT128__) || (!defined(__GNUC__) && !defined(__clang__)))
#include <intrin0.h> // __umulh, _umul128, _BitScanForward64, _BitScanReverse64
#endif
#include <nlohmann/detail/abi_macros.hpp>
#include <nlohmann/detail/macro_scope.hpp> // JSON_HEDLEY_ALWAYS_INLINE, NLOHMANN_JSON_NAMESPACE_BEGIN
// Portable bit-level helpers for the number and string scanners. They use
// compiler builtins or platform-specific intrinsics where available and plain
@@ -28,6 +29,10 @@ inline int count_leading_zeros(std::uint64_t x) noexcept
{
#if defined(__GNUC__) || defined(__clang__)
return __builtin_clzll(x);
#elif defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan*64 takes
_BitScanReverse64(&index, x);
return 63 - static_cast<int>(index);
#else
int n = 0;
for (int shift = 32; shift != 0; shift >>= 1)
@@ -42,6 +47,29 @@ inline int count_leading_zeros(std::uint64_t x) noexcept
#endif
}
/// number of trailing zero bits of x (x != 0)
inline int count_trailing_zeros(std::uint64_t x) noexcept
{
#if defined(__GNUC__) || defined(__clang__)
return __builtin_ctzll(x);
#elif defined(_MSC_VER) && (defined(_M_X64) || defined(_M_ARM64))
unsigned long index = 0; // NOLINT(runtime/int): the type _BitScan*64 takes
_BitScanForward64(&index, x);
return static_cast<int>(index);
#else
int n = 0;
for (int shift = 32; shift != 0; shift >>= 1)
{
if ((x << (64 - shift)) == 0)
{
n += shift;
x >>= shift;
}
}
return n;
#endif
}
/// the 128-bit product of two 64-bit numbers
struct uint128_parts
{
@@ -75,15 +103,27 @@ inline uint128_parts full_multiplication(std::uint64_t a, std::uint64_t b) noexc
#endif
}
/// eight bytes as a little-endian word (compilers fold this into one load on
/// little-endian targets)
inline std::uint64_t read_eight_bytes(const char* p) noexcept
/// eight bytes as a little-endian word (a single load on little-endian
/// targets; always inlined, as GCC otherwise calls it in the number loops)
JSON_HEDLEY_ALWAYS_INLINE std::uint64_t read_eight_bytes(const unsigned char* b) noexcept
{
const auto* b = reinterpret_cast<const unsigned char*>(p); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
#if defined(_MSC_VER) || defined(__x86_64__) || defined(__i386__) || (defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__)
// the byte order already matches (all MSVC targets are little-endian)
std::uint64_t result = 0;
std::memcpy(&result, b, sizeof(result));
return result;
#else
return static_cast<std::uint64_t>(b[0]) | (static_cast<std::uint64_t>(b[1]) << 8u)
| (static_cast<std::uint64_t>(b[2]) << 16u) | (static_cast<std::uint64_t>(b[3]) << 24u)
| (static_cast<std::uint64_t>(b[4]) << 32u) | (static_cast<std::uint64_t>(b[5]) << 40u)
| (static_cast<std::uint64_t>(b[6]) << 48u) | (static_cast<std::uint64_t>(b[7]) << 56u);
#endif
}
/// eight bytes as a little-endian word
JSON_HEDLEY_ALWAYS_INLINE std::uint64_t read_eight_bytes(const char* p) noexcept
{
return read_eight_bytes(reinterpret_cast<const unsigned char*>(p)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
}
} // namespace detail
include/nlohmann/detail/conversions/from_json.hpp
+67 -28
View File
@@ -48,7 +48,7 @@ inline void from_json(const BasicJsonType& j, typename std::nullptr_t& n)
{
if (JSON_HEDLEY_UNLIKELY(!j.is_null()))
{
JSON_THROW(type_error::create(302, concat("type must be null, but is ", j.type_name()), &j));
throw_type_must_be("null", j);
}
n = nullptr;
}
@@ -80,7 +80,11 @@ void get_arithmetic_value(const BasicJsonType& j, ArithmeticType& val)
{
case value_t::number_unsigned:
{
val = static_cast<ArithmeticType>(*j.template get_ptr<const typename BasicJsonType::number_unsigned_t*>());
// never null: a basic_json whose number_unsigned_t is number_integer_t
// stores no number_unsigned values (#2573)
const auto* ptr = j.template get_ptr<const typename BasicJsonType::number_unsigned_t*>();
JSON_ASSERT(ptr != nullptr);
val = static_cast<ArithmeticType>(*ptr);
break;
}
case value_t::number_integer:
@@ -102,7 +106,7 @@ void get_arithmetic_value(const BasicJsonType& j, ArithmeticType& val)
case value_t::binary:
case value_t::discarded:
default:
JSON_THROW(type_error::create(302, concat("type must be number, but is ", j.type_name()), &j));
throw_type_must_be("number", j);
}
}
@@ -111,7 +115,7 @@ inline void from_json(const BasicJsonType& j, typename BasicJsonType::boolean_t&
{
if (JSON_HEDLEY_UNLIKELY(!j.is_boolean()))
{
JSON_THROW(type_error::create(302, concat("type must be boolean, but is ", j.type_name()), &j));
throw_type_must_be("boolean", j);
}
b = *j.template get_ptr<const typename BasicJsonType::boolean_t*>();
}
@@ -121,7 +125,7 @@ inline void from_json(const BasicJsonType& j, typename BasicJsonType::string_t&
{
if (JSON_HEDLEY_UNLIKELY(!j.is_string()))
{
JSON_THROW(type_error::create(302, concat("type must be string, but is ", j.type_name()), &j));
throw_type_must_be("string", j);
}
s = *j.template get_ptr<const typename BasicJsonType::string_t*>();
}
@@ -137,7 +141,7 @@ inline void from_json(const BasicJsonType& j, StringType& s)
{
if (JSON_HEDLEY_UNLIKELY(!j.is_string()))
{
JSON_THROW(type_error::create(302, concat("type must be string, but is ", j.type_name()), &j));
throw_type_must_be("string", j);
}
s = *j.template get_ptr<const typename BasicJsonType::string_t*>();
@@ -150,7 +154,7 @@ inline void from_json(const BasicJsonType& j, typename BasicJsonType::number_flo
}
template<typename BasicJsonType>
inline void from_json(const BasicJsonType& j, typename BasicJsonType::number_unsigned_t& val)
inline void from_json(const BasicJsonType& j, number_unsigned_overload_t<BasicJsonType>& val)
{
get_arithmetic_value(j, val);
}
@@ -183,7 +187,7 @@ inline void from_json(const BasicJsonType& j, std::forward_list<T, Allocator>& l
{
if (JSON_HEDLEY_UNLIKELY(!j.is_array()))
{
JSON_THROW(type_error::create(302, concat("type must be array, but is ", j.type_name()), &j));
throw_type_must_be("array", j);
}
l.clear();
std::transform(j.rbegin(), j.rend(),
@@ -200,7 +204,7 @@ inline void from_json(const BasicJsonType& j, std::valarray<T>& l)
{
if (JSON_HEDLEY_UNLIKELY(!j.is_array()))
{
JSON_THROW(type_error::create(302, concat("type must be array, but is ", j.type_name()), &j));
throw_type_must_be("array", j);
}
l.resize(j.size());
std::transform(j.begin(), j.end(), std::begin(l),
@@ -266,6 +270,22 @@ template<typename ConstructibleArrayType>
void from_json_array_reserve(ConstructibleArrayType& /*arr*/, std::size_t /*size*/, priority_tag<0> /*unused*/)
{}
// append through push_back() where available; containers without it (such as
// std::set) fall back to insert(end(), ...), which is what std::inserter did
template<typename ConstructibleArrayType, typename ValueType>
auto from_json_array_append(ConstructibleArrayType& arr, ValueType&& value, priority_tag<1> /*unused*/)
-> decltype(arr.push_back(std::forward<ValueType>(value)), void())
{
arr.push_back(std::forward<ValueType>(value));
}
template<typename ConstructibleArrayType, typename ValueType>
void from_json_array_append(ConstructibleArrayType& arr, ValueType&& value, priority_tag<0> /*unused*/)
{
using std::end;
arr.insert(end(arr), std::forward<ValueType>(value));
}
template<typename BasicJsonType, typename ConstructibleArrayType,
enable_if_t<
std::is_assignable<ConstructibleArrayType&, ConstructibleArrayType>::value,
@@ -275,17 +295,15 @@ auto from_json_array_impl(const BasicJsonType& j, ConstructibleArrayType& arr, p
j.template get<typename ConstructibleArrayType::value_type>(),
void())
{
using std::end;
ConstructibleArrayType ret;
from_json_array_reserve(ret, j.size(), priority_tag<1> {});
std::transform(j.begin(), j.end(),
std::inserter(ret, end(ret)), [](const BasicJsonType & i)
const auto* inner_array = j.template get_ptr<const typename BasicJsonType::array_t*>();
from_json_array_reserve(ret, inner_array->size(), priority_tag<1> {});
for (const auto& elem : *inner_array)
{
// get<BasicJsonType>() returns *this, this won't call a from_json
// method when value_type is BasicJsonType
return i.template get<typename ConstructibleArrayType::value_type>();
});
from_json_array_append(ret, elem.template get<typename ConstructibleArrayType::value_type>(), priority_tag<1> {});
}
arr = std::move(ret);
}
@@ -305,7 +323,7 @@ void())
{
if (JSON_HEDLEY_UNLIKELY(!j.is_array()))
{
JSON_THROW(type_error::create(302, concat("type must be array, but is ", j.type_name()), &j));
throw_type_must_be("array", j);
}
from_json_array_impl(j, arr, priority_tag<3> {});
@@ -324,7 +342,7 @@ auto from_json(const BasicJsonType& j, identity_tag<std::array<T, N>> tag)
{
if (JSON_HEDLEY_UNLIKELY(!j.is_array()))
{
JSON_THROW(type_error::create(302, concat("type must be array, but is ", j.type_name()), &j));
throw_type_must_be("array", j);
}
return from_json_inplace_array_impl(j, tag, make_index_sequence<N> {});
@@ -335,7 +353,7 @@ inline void from_json(const BasicJsonType& j, typename BasicJsonType::binary_t&
{
if (JSON_HEDLEY_UNLIKELY(!j.is_binary()))
{
JSON_THROW(type_error::create(302, concat("type must be binary, but is ", j.type_name()), &j));
throw_type_must_be("binary", j);
}
bin = *j.template get_ptr<const typename BasicJsonType::binary_t*>();
@@ -356,7 +374,7 @@ inline void from_json(const BasicJsonType& j, CompatibleArrayType& bin)
}
else
{
JSON_THROW(type_error::create(302, concat("type must be binary or array, but is ", j.type_name()), &j));
throw_type_must_be("binary or array", j);
}
}
@@ -371,13 +389,30 @@ template<typename ConstructibleObjectType>
inline void from_json_object_reserve(ConstructibleObjectType& /*obj*/, std::size_t /*size*/, priority_tag<0> /*unused*/)
{}
// the keys of the source are sorted for the usual object types, so hinting the
// end makes every insertion constant-time (for containers that order their keys
// the same way); containers without emplace_hint() (such as ordered_map) fall
// back to emplace()
template<typename ConstructibleObjectType, typename Key, typename Value>
auto from_json_object_emplace(ConstructibleObjectType& obj, Key&& key, Value&& value, priority_tag<1> /*unused*/)
-> decltype(obj.emplace_hint(obj.end(), std::forward<Key>(key), std::forward<Value>(value)), void())
{
obj.emplace_hint(obj.end(), std::forward<Key>(key), std::forward<Value>(value));
}
template<typename ConstructibleObjectType, typename Key, typename Value>
void from_json_object_emplace(ConstructibleObjectType& obj, Key&& key, Value&& value, priority_tag<0> /*unused*/)
{
obj.emplace(std::forward<Key>(key), std::forward<Value>(value));
}
template<typename BasicJsonType, typename ConstructibleObjectType,
enable_if_t<is_constructible_object_type<BasicJsonType, ConstructibleObjectType>::value, int> = 0>
inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj)
{
if (JSON_HEDLEY_UNLIKELY(!j.is_object()))
{
JSON_THROW(type_error::create(302, concat("type must be object, but is ", j.type_name()), &j));
throw_type_must_be("object", j);
}
ConstructibleObjectType ret;
@@ -385,7 +420,7 @@ inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj)
from_json_object_reserve(ret, inner_object->size(), priority_tag<1> {});
for (const auto& p : *inner_object)
{
ret.emplace(p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>());
from_json_object_emplace(ret, p.first, p.second.template get<typename ConstructibleObjectType::mapped_type>(), priority_tag<1> {});
}
obj = std::move(ret);
}
@@ -406,7 +441,11 @@ inline void from_json(const BasicJsonType& j, ArithmeticType& val)
{
case value_t::number_unsigned:
{
val = static_cast<ArithmeticType>(*j.template get_ptr<const typename BasicJsonType::number_unsigned_t*>());
// never null: a basic_json whose number_unsigned_t is number_integer_t
// stores no number_unsigned values (#2573)
const auto* ptr = j.template get_ptr<const typename BasicJsonType::number_unsigned_t*>();
JSON_ASSERT(ptr != nullptr);
val = static_cast<ArithmeticType>(*ptr);
break;
}
case value_t::number_integer:
@@ -432,7 +471,7 @@ inline void from_json(const BasicJsonType& j, ArithmeticType& val)
case value_t::binary:
case value_t::discarded:
default:
JSON_THROW(type_error::create(302, concat("type must be number, but is ", j.type_name()), &j));
throw_type_must_be("number", j);
}
}
@@ -504,7 +543,7 @@ auto from_json(const BasicJsonType& j, TupleRelated&& t)
{
if (JSON_HEDLEY_UNLIKELY(!j.is_array()))
{
JSON_THROW(type_error::create(302, concat("type must be array, but is ", j.type_name()), &j));
throw_type_must_be("array", j);
}
return from_json_tuple_impl(j, std::forward<TupleRelated>(t), priority_tag<3> {});
@@ -517,14 +556,14 @@ void from_json_pair_array_to_map(const BasicJsonType& j, MapType& m)
{
if (JSON_HEDLEY_UNLIKELY(!j.is_array()))
{
JSON_THROW(type_error::create(302, concat("type must be array, but is ", j.type_name()), &j));
throw_type_must_be("array", j);
}
m.clear();
for (const auto& p : j)
{
if (JSON_HEDLEY_UNLIKELY(!p.is_array()))
{
JSON_THROW(type_error::create(302, concat("type must be array, but is ", p.type_name()), &p));
throw_type_must_be("array", p);
}
m.emplace(p.at(0).template get<typename MapType::key_type>(), p.at(1).template get<typename MapType::mapped_type>());
}
@@ -591,7 +630,7 @@ inline void from_json(const BasicJsonType& j, std_fs::path& p)
{
if (JSON_HEDLEY_UNLIKELY(!j.is_string()))
{
JSON_THROW(type_error::create(302, concat("type must be string, but is ", j.type_name()), &j));
throw_type_must_be("string", j);
}
const auto& s = *j.template get_ptr<const typename BasicJsonType::string_t*>();
// Checking for C++20 standard or later can be insufficient in case the
include/nlohmann/detail/conversions/to_chars.hpp
+458 -23
View File
@@ -4,6 +4,7 @@
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2009 Florian Loitsch <https://florian.loitsch.com/>
// SPDX-FileCopyrightText: 2025 Victor Zverovich <https://github.com/vitaut/zmij>
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
@@ -11,11 +12,32 @@
#include <array> // array
#include <cmath> // signbit, isfinite
#include <cstddef> // size_t
#include <cstdint> // intN_t, uintN_t
#include <cstring> // memcpy, memmove
#include <limits> // numeric_limits
#include <type_traits> // conditional
#ifdef _MSC_VER
#include <cstdlib> // _byteswap_uint64
#endif
// SSE2 (every x86-64 CPU) and NEON (every 64-bit Arm CPU) convert the 16
// digits of a double at once
#if defined(__x86_64__) || (defined(_M_X64) && !defined(_M_ARM64EC))
#include <emmintrin.h>
#define JSON_DTOA_SSE2 1
#define JSON_DTOA_NEON 0
#elif (defined(__aarch64__) || defined(_M_ARM64)) && !defined(_M_ARM64EC) && !defined(__ARM_BIG_ENDIAN)
#include <arm_neon.h>
#define JSON_DTOA_SSE2 0
#define JSON_DTOA_NEON 1
#else
#define JSON_DTOA_SSE2 0
#define JSON_DTOA_NEON 0
#endif
#include <nlohmann/detail/conversions/zmij.hpp>
#include <nlohmann/detail/macro_scope.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -1047,6 +1069,441 @@ inline char* format_buffer(char* buf, int len, int decimal_exponent,
return append_exponent(buf, n - 1);
}
/// eight decimal digits (a value below 10^8) as bytes 0..9, the first digit
/// in the most significant byte: three steps that divide all lanes at once
/// by a multiplication (the conversion of Xiang JunBo, as in Zmij)
inline std::uint64_t eight_digit_bytes(std::uint64_t abcdefgh) noexcept
{
const std::uint64_t abcd_efgh = abcdefgh + (((std::uint64_t{1} << 32u) - 10000u) * ((abcdefgh * (((std::uint64_t{1} << 40u) / 10000u) + 1u)) >> 40u));
const std::uint64_t ab_cd_ef_gh = abcd_efgh + (((std::uint64_t{1} << 16u) - 100u) * (((abcd_efgh * (((std::uint64_t{1} << 19u) / 100u) + 1u)) >> 19u) & 0x7F0000007Fu));
return ab_cd_ef_gh + (((std::uint64_t{1} << 8u) - 10u) * (((ab_cd_ef_gh * (((std::uint64_t{1} << 10u) / 10u) + 1u)) >> 10u) & 0x000F000F000F000Fu));
}
/// store the bytes of v, the most significant one first (one byte swap and
/// one store where the byte order is known: compilers do not reliably merge
/// the byte stores once this is inlined)
inline void store_msb_first(char* p, std::uint64_t v) noexcept
{
#if defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
v = __builtin_bswap64(v);
std::memcpy(p, &v, sizeof(v));
#elif defined(__BYTE_ORDER__) && defined(__ORDER_BIG_ENDIAN__) && __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
std::memcpy(p, &v, sizeof(v));
#elif defined(_MSC_VER) // (little-endian on all its targets)
v = _byteswap_uint64(v);
std::memcpy(p, &v, sizeof(v));
#else
for (unsigned i = 0; i < 8; ++i)
{
p[i] = static_cast<char>(v >> (56u - (8u * i)));
}
#endif
}
/*!
@brief digits * 10^exp for a double, in the layout of format_buffer()
The layout is that of format_buffer() with min_exp -4 and max_exp 15 (the
digits10 of double). The digits are converted eight at a time and placed
with fixed-size moves instead of per-digit loops and moves of the buffer.
@param[in] digits the digits (not 0, at most 17 digits; trailing zeros allowed)
@param[in] exp the decimal exponent of the last digit
@return a pointer past the text; up to 41 bytes at @a first are written
(some beyond the returned end)
*/
JSON_HEDLEY_NON_NULL(1)
JSON_HEDLEY_RETURNS_NON_NULL
inline char* write_decimal(char* first, std::uint64_t digits, int exp) noexcept
{
JSON_ASSERT(digits != 0 && digits < 100000000000000000u);
const std::uint64_t upper = digits / 100000000u;
const std::uint64_t b0 = upper / 100000000u; // (one digit: it is its own byte)
const std::uint64_t b1 = eight_digit_bytes(upper % 100000000u);
const std::uint64_t b2 = eight_digit_bytes(digits % 100000000u);
// leading and trailing zero digits: zero bytes, counted without division
int leading = 16;
int zeros = 16;
if (b0 != 0)
{
leading = count_leading_zeros(b0) / 8;
}
else if (b1 != 0)
{
leading = 8 + (count_leading_zeros(b1) / 8);
}
else
{
leading += count_leading_zeros(b2) / 8;
}
if (b2 != 0)
{
zeros = count_trailing_zeros(b2) / 8;
}
else if (b1 != 0)
{
zeros = 8 + (count_trailing_zeros(b1) / 8);
}
// (else: 16, b0 is the one digit that is not 0)
// the digits as text at text + leading, then '0's, so that fixed-size
// moves need not check how many digits there are
std::array<char, 64> text; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
store_msb_first(text.data(), b0 + 0x3030303030303030u);
store_msb_first(text.data() + 8, b1 + 0x3030303030303030u);
store_msb_first(text.data() + 16, b2 + 0x3030303030303030u);
std::memset(text.data() + 24, '0', 40);
const int k = 24 - leading - zeros; // significant digits
const int n = k + exp + zeros; // position of the decimal point after the first digit
const char* const s0 = text.data() + leading;
if (-4 < n && n <= 15)
{
// "0.[000]digits" (n <= 0) is the digits after 1 - n leading '0's
// with the point after the first; "digits[000].0" (n >= k) and
// "dig.its" put the point after n characters
const int pad = n <= 0 ? 1 - n : 0;
const char* const s = s0 - pad;
const int len = k + pad;
const int point = n + pad;
std::memcpy(first, s, 16);
std::memcpy(first + point + 1, s + point, 24);
first[point] = '.';
return first + (point >= len ? point + 2 : len + 1);
}
// d.igitse+XX, with at least two exponent digits (as append_exponent())
std::memcpy(first, s0, 16);
std::memcpy(first + 2, s0 + 1, 16);
first[1] = '.';
char* const end = first + (k == 1 ? 1 : k + 1);
const int e = n - 1;
const auto ea = e < 0 ? 0u - static_cast<unsigned>(e) : static_cast<unsigned>(e); // (unsigned: no signed overflow to assume)
const bool three = ea >= 100;
end[0] = 'e';
end[1] = e < 0 ? '-' : '+';
end[2] = static_cast<char>('0' + (three ? ea / 100 : (ea / 10) % 10));
end[3] = static_cast<char>('0' + (three ? (ea / 10) % 10 : ea % 10));
end[4] = static_cast<char>('0' + (ea % 10));
return end + (three ? 5 : 4);
}
/*!
@brief the shortest decimal of a positive double (Zmij), as write_decimal()
writes it
For a normal double, the shorter candidate has 15 or 16 digits: they are
converted at once (two halves of eight digits) and followed by the digit
after them, if there is one, without the multiplication and division by 10
that counting the digits of one number would take. The fixed layouts move
the digits after the point by one byte.
@return a pointer past the text; up to 41 bytes at @a first are written
(some beyond the returned end)
*/
JSON_HEDLEY_NON_NULL(1)
JSON_HEDLEY_RETURNS_NON_NULL
inline char* write_shortest(char* first, const zmij::shortest_decimal d) noexcept
{
const std::uint64_t sig = d.integral;
if (JSON_HEDLEY_UNLIKELY(sig < 100000000000000u || sig >= 10000000000000000u))
{
// (subnormals)
return d.has_digit ? write_decimal(first, (sig * 10) + d.digit, d.exponent) : write_decimal(first, sig, d.exponent + 1);
}
const bool sixteen = sig >= 1000000000000000u; // (else 15 digits)
const int last = d.has_digit ? d.digit : 0;
const std::uint64_t upper = sig / 100000000u;
#if JSON_DTOA_SSE2
// NOLINTBEGIN(portability-simd-intrinsics)
// the two halves in the 64-bit lanes, each as abcd * 2^32 + efgh, then as
// bytes (as eight_digit_bytes(), one lane each)
const __m128i x = _mm_set_epi64x(static_cast<long long>(sig - (upper * 100000000u)), static_cast<long long>(upper)); // NOLINT(runtime/int)
const __m128i abcd = _mm_srli_epi64(_mm_mul_epu32(x, _mm_set1_epi64x(109951163)), 40); // 2^40 / 10000 + 1
const __m128i abcd_efgh = _mm_add_epi64(x, _mm_mul_epu32(abcd, _mm_set1_epi64x(4294957296))); // 2^32 - 10000
// 32-bit lanes in the order of the text: abcd, efgh of both halves
const __m128i fours = _mm_shuffle_epi32(abcd_efgh, _MM_SHUFFLE(2, 3, 0, 1));
const __m128i ab = _mm_srli_epi16(_mm_mulhi_epu16(fours, _mm_set1_epi32(5243)), 3);
const __m128i ab_cd = _mm_or_si128(_mm_slli_epi32(_mm_sub_epi16(fours, _mm_mullo_epi16(ab, _mm_set1_epi32(100))), 16), ab);
// 16-bit lanes ab (< 100) -> bytes a, b: 256 * ab - 2559 * (ab / 10)
const __m128i bytes = _mm_sub_epi16(_mm_slli_epi16(ab_cd, 8), _mm_mullo_epi16(_mm_set1_epi16(2559), _mm_mulhi_epu16(ab_cd, _mm_set1_epi16(6554))));
// the last digit that is not 0 (sig is not 0)
const auto nonzero = static_cast<std::uint64_t>(_mm_movemask_epi8(_mm_cmpgt_epi8(bytes, _mm_setzero_si128())));
const int digits = 63 - count_leading_zeros(nonzero) + (sixteen ? 1 : 0); // without trailing zeros
const __m128i chars = _mm_add_epi8(bytes, _mm_set1_epi8('0'));
// the 16 characters from the first digit
const __m128i s = sixteen ? chars : _mm_or_si128(_mm_srli_si128(chars, 1), _mm_slli_si128(_mm_cvtsi32_si128('0' + last), 15));
const char s16 = static_cast<char>(sixteen ? '0' + last : '0'); // the 17th
const auto store_16 = [&s](char* p) noexcept
{
std::memcpy(p, &s, 16);
};
const char first_digit = static_cast<char>(_mm_cvtsi128_si32(s));
// NOLINTEND(portability-simd-intrinsics)
#elif JSON_DTOA_NEON
// as with SSE2: the halves in 32-bit lanes, then abcd, efgh of both
const uint32x2_t halves = vcreate_u32(upper | ((sig - (upper * 100000000u)) << 32u));
const uint32x2_t abcd = vmovn_u64(vshrq_n_u64(vmull_n_u32(halves, static_cast<std::uint32_t>(((std::uint64_t{1} << 40u) / 10000u) + 1u)), 40));
const uint32x2_t efgh = vmls_n_u32(halves, abcd, 10000u);
const uint32x4_t fours = vcombine_u32(vzip1_u32(abcd, efgh), vzip2_u32(abcd, efgh));
const uint32x4_t ab = vshrq_n_u32(vmulq_n_u32(fours, 5243u), 19);
const uint16x8_t ab_cd = vreinterpretq_u16_u32(vorrq_u32(ab, vshlq_n_u32(vmlsq_n_u32(fours, ab, 100u), 16)));
const uint16x8_t tens = vshrq_n_u16(vmulq_n_u16(ab_cd, 103u), 10);
const uint8x16_t bytes = vreinterpretq_u8_u16(vorrq_u16(tens, vshlq_n_u16(vmlsq_n_u16(ab_cd, tens, 10u), 8)));
// the last digit that is not 0 (sig is not 0): a nibble per byte
const std::uint64_t nonzero = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(vtstq_u8(bytes, bytes)), 4)), 0);
const int digits = ((63 - count_leading_zeros(nonzero)) / 4) + (sixteen ? 1 : 0); // without trailing zeros
const uint8x16_t chars = vaddq_u8(bytes, vdupq_n_u8('0'));
// the 16 characters from the first digit
const uint8x16_t s = sixteen ? chars : vextq_u8(chars, vdupq_n_u8(static_cast<std::uint8_t>('0' + last)), 1);
const char s16 = static_cast<char>(sixteen ? '0' + last : '0'); // the 17th
const auto store_16 = [&s](char* p) noexcept
{
vst1q_u8(reinterpret_cast<std::uint8_t*>(p), s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
};
const auto first_digit = static_cast<char>(vgetq_lane_u8(s, 0));
#else
const std::uint64_t hi = eight_digit_bytes(upper);
const std::uint64_t lo = eight_digit_bytes(sig - (upper * 100000000u));
// trailing zero digits: zero bytes (sig is not 0)
const int zeros = lo != 0 ? count_trailing_zeros(lo) / 8 : 8 + (count_trailing_zeros(hi) / 8);
const int digits = 15 - zeros + (sixteen ? 1 : 0); // without trailing zeros
// the 16 characters from the first digit
const std::uint64_t s_hi = (sixteen ? hi : (hi << 8u) | (lo >> 56u)) + 0x3030303030303030u;
const std::uint64_t s_lo = (sixteen ? lo : (lo << 8u) | static_cast<std::uint64_t>(last)) + 0x3030303030303030u;
const char s16 = static_cast<char>(sixteen ? '0' + last : '0'); // the 17th
const auto store_16 = [s_hi, s_lo](char* p) noexcept
{
store_msb_first(p, s_hi);
store_msb_first(p + 8, s_lo);
};
const auto first_digit = static_cast<char>(s_hi >> 56u);
#endif
const int len = d.has_digit ? 16 + (sixteen ? 1 : 0) : digits; // significant digits
const int n = 16 + (sixteen ? 1 : 0) + d.exponent; // digits before the point
if (JSON_HEDLEY_LIKELY(n >= 1 && n <= 15))
{
// "dig.its" and "digits[000].0": the digits after the point move by
// one byte ('0's follow the digits)
#if JSON_DTOA_SSE2
// NOLINTBEGIN(portability-simd-intrinsics)
// (in the register: reading the digits back from memory right after
// storing them waits until the stores are done)
const __m128i at = _mm_set1_epi8(static_cast<char>(n));
const __m128i index = _mm_setr_epi8(0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15);
const __m128i before = _mm_cmpgt_epi8(at, index);
const __m128i after = _mm_cmpgt_epi8(index, at);
const __m128i text = _mm_or_si128(_mm_or_si128(_mm_and_si128(s, before), _mm_and_si128(_mm_slli_si128(s, 1), after)),
_mm_andnot_si128(_mm_or_si128(before, after), _mm_set1_epi8('.')));
std::memcpy(first, &text, 16);
first[16] = static_cast<char>(_mm_extract_epi16(s, 7) >> 8);
first[17] = s16;
// NOLINTEND(portability-simd-intrinsics)
#elif JSON_DTOA_NEON
const uint8x16_t index = vcombine_u8(vcreate_u8(0x0706050403020100u), vcreate_u8(0x0F0E0D0C0B0A0908u));
const uint8x16_t at = vdupq_n_u8(static_cast<std::uint8_t>(n));
const uint8x16_t after_point = vbslq_u8(vcgtq_u8(index, at), vextq_u8(vdupq_n_u8(0), s, 15), vdupq_n_u8('.'));
vst1q_u8(reinterpret_cast<std::uint8_t*>(first), vbslq_u8(vcltq_u8(index, at), s, after_point)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
first[16] = static_cast<char>(vgetq_lane_u8(s, 15));
first[17] = s16;
#else
store_16(first);
first[16] = s16;
std::uint64_t after_point[2]; // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays,cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
std::memcpy(after_point, first + n, 16);
std::memcpy(first + n + 1, after_point, 16);
first[n] = '.';
#endif
return first + (n >= len ? n + 2 : len + 1);
}
if (n <= 0 && n > -4)
{
// "0.[000]digits"
std::memset(first, '0', 8);
first[1] = '.';
store_16(first + 2 - n);
first[18 - n] = s16;
return first + 2 - n + len;
}
// d.igitse+XX, with at least two exponent digits (as append_exponent())
store_16(first + 1);
first[17] = s16;
first[0] = first_digit;
first[1] = '.';
char* const end = first + (len == 1 ? 1 : len + 1);
const int e = n - 1;
const auto ea = e < 0 ? 0u - static_cast<unsigned>(e) : static_cast<unsigned>(e); // (unsigned: no signed overflow to assume)
const bool three = ea >= 100;
end[0] = 'e';
end[1] = e < 0 ? '-' : '+';
end[2] = static_cast<char>('0' + (three ? ea / 100 : (ea / 10) % 10));
end[3] = static_cast<char>('0' + (three ? (ea / 10) % 10 : ea % 10));
end[4] = static_cast<char>('0' + (ea % 10));
return end + (three ? 5 : 4);
}
/// the powers of ten up to 10^19 (all that fit in std::uint64_t)
inline const std::array<std::uint64_t, 20>& powers_of_ten() noexcept
{
static const std::array<std::uint64_t, 20> powers =
{
{
1u,
10u,
100u,
1000u,
10000u,
100000u,
1000000u,
10000000u,
100000000u,
1000000000u,
10000000000u,
100000000000u,
1000000000000u,
10000000000000u,
100000000000000u,
1000000000000000u,
10000000000000000u,
100000000000000000u,
1000000000000000000u,
10000000000000000000u
}
};
return powers;
}
/*!
@brief digits * 10^exp, as write_decimal() writes it, for the digits of a
double that need no conversion (count digits, at most 15, the first not 0;
trailing zeros allowed): extended to 16 digits and written by write_shortest()
@return a pointer past the text; up to 41 bytes at @a first are written
(some beyond the returned end)
*/
JSON_HEDLEY_NON_NULL(1)
JSON_HEDLEY_RETURNS_NON_NULL
inline char* write_short_decimal(char* first, std::uint64_t digits, int count, int exp) noexcept
{
JSON_ASSERT(digits >= powers_of_ten()[static_cast<std::size_t>(count - 1)] && count <= 15);
const int scale = 16 - count;
return write_shortest(first, zmij::shortest_decimal{digits * powers_of_ten()[static_cast<std::size_t>(scale)], exp - scale - 1, 0, false});
}
/// as write_short_decimal(), counting the digits (not 0, less than 10^15)
JSON_HEDLEY_NON_NULL(1)
JSON_HEDLEY_RETURNS_NON_NULL
inline char* write_short_decimal(char* first, std::uint64_t digits, int exp) noexcept
{
JSON_ASSERT(digits != 0 && digits < 1000000000000000u);
// floor(log10(2^bits)) + 1 digits, or one less
const int log2_bound = ((64 - count_leading_zeros(digits)) * 1233) >> 12;
const int count = log2_bound + (digits >= powers_of_ten()[static_cast<std::size_t>(log2_bound)] ? 1 : 0);
return write_short_decimal(first, digits, count, exp);
}
/*!
@brief whether FloatType is an IEEE 754 binary64 type (a double, or a long double
that has the same format, as with MSVC and on Apple's Arm CPUs)
These are the types the conversion of Zmij (see zmij.hpp) is used for; all
others (binary32, or a format the library does not know) use Grisu2.
*/
template<typename FloatType>
constexpr bool has_binary64_format() noexcept
{
return std::numeric_limits<FloatType>::is_iec559
&& std::numeric_limits<FloatType>::digits == 53
&& std::numeric_limits<FloatType>::max_exponent == 1024
&& sizeof(FloatType) == sizeof(std::uint64_t);
}
template<typename FloatType>
struct is_binary64 : std::integral_constant<bool, has_binary64_format<FloatType>()> {};
/// a positive finite float (other than binary64): Grisu2 and format_buffer()
template<typename FloatType>
JSON_HEDLEY_NON_NULL(1, 2)
JSON_HEDLEY_RETURNS_NON_NULL
char* write_positive_grisu2(char* first, const char* last, FloatType value)
{
JSON_ASSERT(last - first >= std::numeric_limits<FloatType>::max_digits10);
static_cast<void>(last); // (only used in the assertion)
// Compute v = buffer * 10^decimal_exponent.
// The decimal digits are stored in the buffer, which needs to be interpreted
// as an unsigned decimal integer.
// len is the length of the buffer, i.e., the number of decimal digits.
int len = 0;
int decimal_exponent = 0;
grisu2(first, len, decimal_exponent, value);
JSON_ASSERT(len <= std::numeric_limits<FloatType>::max_digits10);
// Format the buffer like printf("%.*g", prec, value)
constexpr int kMinExp = -4;
// Use digits10 here to increase compatibility with version 2.
constexpr int kMaxExp = std::numeric_limits<FloatType>::digits10;
JSON_ASSERT(last - first >= kMaxExp + 2);
JSON_ASSERT(last - first >= 2 + (-kMinExp - 1) + std::numeric_limits<FloatType>::max_digits10);
JSON_ASSERT(last - first >= std::numeric_limits<FloatType>::max_digits10 + 6);
return format_buffer(first, len, decimal_exponent, kMinExp, kMaxExp);
}
/// a positive finite binary64 number: the shortest digits (Zmij), laid out by
/// write_shortest() (through a local buffer if [first, last) is shorter than
/// the 41 bytes it may write)
template<typename FloatType>
JSON_HEDLEY_NON_NULL(1, 2)
JSON_HEDLEY_RETURNS_NON_NULL
char* write_positive_zmij(char* first, const char* last, FloatType value)
{
static_assert(is_binary64<FloatType>::value,
"internal error: the conversion of Zmij needs IEEE 754 binary64 numbers");
std::uint64_t bits = 0;
std::memcpy(&bits, &value, sizeof(bits));
const zmij::shortest_decimal d = zmij::to_shortest(bits);
if (JSON_HEDLEY_LIKELY(last - first >= 41))
{
return write_shortest(first, d);
}
std::array<char, 64> buf; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
const auto len = static_cast<std::size_t>(write_shortest(buf.data(), d) - buf.data());
JSON_ASSERT(last - first >= static_cast<std::ptrdiff_t>(len));
std::memcpy(first, buf.data(), len);
return first + len;
}
/// a positive finite binary64 number: Zmij (as a long double has the format of
/// a double here, its bits are those of the double of the same value)
template<typename FloatType>
JSON_HEDLEY_NON_NULL(1, 2)
JSON_HEDLEY_RETURNS_NON_NULL
char* write_positive(char* first, const char* last, FloatType value, std::true_type /*is_binary64*/)
{
return write_positive_zmij(first, last, value);
}
/// a positive finite float of any other format: Grisu2
template<typename FloatType>
JSON_HEDLEY_NON_NULL(1, 2)
JSON_HEDLEY_RETURNS_NON_NULL
char* write_positive(char* first, const char* last, FloatType value, std::false_type /*is_binary64*/)
{
return write_positive_grisu2(first, last, value);
}
/// a positive finite float: Zmij for binary64 numbers, Grisu2 otherwise
template<typename FloatType>
JSON_HEDLEY_NON_NULL(1, 2)
JSON_HEDLEY_RETURNS_NON_NULL
char* write_positive(char* first, const char* last, FloatType value)
{
return write_positive(first, last, value, is_binary64<FloatType> {});
}
} // namespace dtoa_impl
/*!
@@ -1064,7 +1521,6 @@ JSON_HEDLEY_NON_NULL(1, 2)
JSON_HEDLEY_RETURNS_NON_NULL
char* to_chars(char* first, const char* last, FloatType value)
{
static_cast<void>(last); // maybe unused - fix warning
JSON_ASSERT(std::isfinite(value));
// Use signbit(value) instead of (value < 0) since signbit works for -0.
@@ -1090,28 +1546,7 @@ char* to_chars(char* first, const char* last, FloatType value)
JSON_HEDLEY_DIAGNOSTIC_POP
#endif
JSON_ASSERT(last - first >= std::numeric_limits<FloatType>::max_digits10);
// Compute v = buffer * 10^decimal_exponent.
// The decimal digits are stored in the buffer, which needs to be interpreted
// as an unsigned decimal integer.
// len is the length of the buffer, i.e., the number of decimal digits.
int len = 0;
int decimal_exponent = 0;
dtoa_impl::grisu2(first, len, decimal_exponent, value);
JSON_ASSERT(len <= std::numeric_limits<FloatType>::max_digits10);
// Format the buffer like printf("%.*g", prec, value)
constexpr int kMinExp = -4;
// Use digits10 here to increase compatibility with version 2.
constexpr int kMaxExp = std::numeric_limits<FloatType>::digits10;
JSON_ASSERT(last - first >= kMaxExp + 2);
JSON_ASSERT(last - first >= 2 + (-kMinExp - 1) + std::numeric_limits<FloatType>::max_digits10);
JSON_ASSERT(last - first >= std::numeric_limits<FloatType>::max_digits10 + 6);
return dtoa_impl::format_buffer(first, len, decimal_exponent, kMinExp, kMaxExp);
return dtoa_impl::write_positive(first, last, value);
}
} // namespace detail
include/nlohmann/detail/conversions/to_json.hpp
+129 -5
View File
@@ -13,7 +13,7 @@
#include <optional> // optional
#endif
#include <iterator> // begin, end
#include <iterator> // begin, end, make_move_iterator, move_iterator
#include <memory> // allocator_traits
#include <string> // basic_string, char_traits
#include <tuple> // tuple, get
@@ -48,6 +48,32 @@ namespace detail
* leave j with the type of the new value, but the pointer to the destroyed old one.
*/
// a move iterator over the elements of an rvalue container, unless they are
// const (e.g., std::set): libstdc++ before GCC 5 defines the reference of a
// std::move_iterator as value_type&&, which cannot bind to a const element
template<typename Iterator>
std::move_iterator<Iterator> make_move_iterator_if_mutable_impl(const Iterator& it, std::true_type /*mutable*/)
{
return std::make_move_iterator(it);
}
template<typename Iterator>
Iterator make_move_iterator_if_mutable_impl(const Iterator& it, std::false_type /*mutable*/)
{
return it;
}
template<typename Iterator>
using is_mutable_iterator = std::integral_constant < bool,
!std::is_const<typename std::remove_reference<decltype(*std::declval<Iterator&>())>::type>::value >;
template<typename Iterator>
auto make_move_iterator_if_mutable(const Iterator& it)
-> decltype(make_move_iterator_if_mutable_impl(it, is_mutable_iterator<Iterator> {}))
{
return make_move_iterator_if_mutable_impl(it, is_mutable_iterator<Iterator> {});
}
template<value_t> struct external_constructor;
template<>
@@ -167,6 +193,17 @@ struct external_constructor<value_t::array>
j.replace_value(value_t::array, value);
}
/// an rvalue container: move its elements
template<typename BasicJsonType, typename CompatibleArrayType>
static void construct_moving(BasicJsonType& j, CompatibleArrayType& arr)
{
using std::begin;
using std::end;
const typename BasicJsonType::json_value value(j.template create<typename BasicJsonType::array_t>(make_move_iterator_if_mutable(begin(arr)), make_move_iterator_if_mutable(end(arr))));
j.replace_value(value_t::array, value);
}
template<typename BasicJsonType>
static void construct(BasicJsonType& j, const std::vector<bool>& arr)
{
@@ -217,6 +254,17 @@ struct external_constructor<value_t::object>
j.replace_value(value_t::object, value);
}
/// an rvalue container: move its values
template<typename BasicJsonType, typename CompatibleObjectType>
static void construct_moving(BasicJsonType& j, CompatibleObjectType& obj)
{
using std::begin;
using std::end;
const typename BasicJsonType::json_value value(j.template create<typename BasicJsonType::object_t>(make_move_iterator_if_mutable(begin(obj)), make_move_iterator_if_mutable(end(obj))));
j.replace_value(value_t::object, value);
}
template < typename BasicJsonType, typename CompatibleObjectType,
enable_if_t < !std::is_same<CompatibleObjectType, typename BasicJsonType::object_t>::value, int > = 0 >
static void construct(BasicJsonType& j, const CompatibleObjectType& obj)
@@ -303,14 +351,14 @@ inline void to_json(BasicJsonType& j, FloatType val) noexcept
}
template<typename BasicJsonType, typename CompatibleNumberUnsignedType,
enable_if_t<is_compatible_integer_type<typename BasicJsonType::number_unsigned_t, CompatibleNumberUnsignedType>::value, int> = 0>
enable_if_t<is_compatible_integer_type<number_unsigned_overload_t<BasicJsonType>, CompatibleNumberUnsignedType>::value, int> = 0>
inline void to_json(BasicJsonType& j, CompatibleNumberUnsignedType val) noexcept
{
external_constructor<value_t::number_unsigned>::construct(j, static_cast<typename BasicJsonType::number_unsigned_t>(val));
}
template<typename BasicJsonType, typename CompatibleNumberIntegerType,
enable_if_t<is_compatible_integer_type<typename BasicJsonType::number_integer_t, CompatibleNumberIntegerType>::value, int> = 0>
enable_if_t<is_compatible_number_integer_type<BasicJsonType, CompatibleNumberIntegerType>::value, int> = 0>
inline void to_json(BasicJsonType& j, CompatibleNumberIntegerType val) noexcept
{
external_constructor<value_t::number_integer>::construct(j, static_cast<typename BasicJsonType::number_integer_t>(val));
@@ -354,6 +402,68 @@ inline void to_json(BasicJsonType& j, const CompatibleArrayType& arr)
external_constructor<value_t::array>::construct(j, arr);
}
// types that have a dedicated to_json overload and must not be treated as generic containers
template<typename T>
struct has_dedicated_to_json : std::false_type {};
#if JSON_HAS_FILESYSTEM || JSON_HAS_EXPERIMENTAL_FILESYSTEM
template<>
struct has_dedicated_to_json<std_fs::path> : std::true_type {};
#endif
#if defined(__cpp_lib_char8_t)
template<typename Tr, typename Allocator>
struct has_dedicated_to_json<std::basic_string<char8_t, Tr, Allocator>> : std::true_type {};
#endif
#if JSON_HAS_RANGE_VIEW_CONVERSION
template<typename T>
struct is_range_view_type : is_compatible_range_view<T> {};
#else
template<typename T>
struct is_range_view_type : std::false_type {};
#endif
#if JSON_USE_OBJECTS_FOR_ENUM_KEYED_MAPS
template<typename T>
struct is_enum_keyed_map_type : is_enum_keyed_map<T> {};
#else
template<typename T>
struct is_enum_keyed_map_type : std::false_type {};
#endif
// rvalue (non-const) container: the generic to_json takes its elements by move
template<typename T>
using is_movable_container_rvalue = negation<disjunction<
std::is_lvalue_reference<T>,
std::is_const<T>,
has_dedicated_to_json<T>,
is_basic_json<T>,
is_enum_keyed_map_type<T>,
std::is_same<T, std::vector<bool>>>>;
// rvalue array-like containers; object types are ruled out before views are
// checked, as std::ranges::view<T> for the object_t of an ordered_json would
// need that ordered_json to be complete (GCC 11, see #3312)
template<typename BasicJsonType, typename T>
using is_rvalue_array_to_json = conjunction<is_movable_container_rvalue<T>,
negation<is_compatible_object_type<BasicJsonType, T>>,
negation<is_range_view_type<T>>,
is_compatible_array_type<BasicJsonType, T>,
negation<disjunction<
std::is_same<T, typename BasicJsonType::array_t>,
std::is_same<T, typename BasicJsonType::binary_t>,
is_compatible_string_type<BasicJsonType, T>,
is_compatible_binary_type<BasicJsonType, T>>>>;
// rvalue containers: their elements are moved instead of copied
template<typename BasicJsonType, typename CompatibleArrayType,
enable_if_t<is_rvalue_array_to_json<BasicJsonType, CompatibleArrayType>::value, int> = 0>
inline void to_json(BasicJsonType& j, CompatibleArrayType && arr) // NOLINT(cppcoreguidelines-missing-std-forward)
{
external_constructor<value_t::array>::construct_moving(j, arr);
}
#if JSON_HAS_RANGE_VIEW_CONVERSION
template < typename BasicJsonType, typename T,
enable_if_t < is_compatible_range_view<std::remove_cvref_t<T>>::value
@@ -414,19 +524,33 @@ inline void to_json(BasicJsonType& j, const EnumKeyedMap& map)
BasicJsonType key = p.first;
if (JSON_HEDLEY_UNLIKELY(!key.is_string()))
{
JSON_THROW(type_error::create(302, concat("type must be string, but is ", key.type_name()), &key));
throw_type_must_be("string", key);
}
auto& key_string = *key.template get_ptr<typename BasicJsonType::string_t*>();
if (JSON_HEDLEY_UNLIKELY(!obj.emplace(key_string, BasicJsonType(p.second)).second))
{
JSON_THROW(type_error::create(318, concat("duplicate object key '", key_string, "'"), &key));
JSON_THROW(type_error::create(exception_id::enum_key_duplicate, concat("duplicate object key '", key_string, "'"), &key));
}
}
external_constructor<value_t::object>::construct(j, std::move(obj));
}
#endif
// rvalue object-like containers (views have no key_type and mapped_type, so
// they are no compatible object type)
template<typename BasicJsonType, typename T>
using is_rvalue_object_to_json = conjunction<is_movable_container_rvalue<T>,
negation<std::is_same<T, typename BasicJsonType::object_t>>,
is_compatible_object_type<BasicJsonType, T>>;
template<typename BasicJsonType, typename CompatibleObjectType,
enable_if_t<is_rvalue_object_to_json<BasicJsonType, CompatibleObjectType>::value, int> = 0>
inline void to_json(BasicJsonType& j, CompatibleObjectType && obj) // NOLINT(cppcoreguidelines-missing-std-forward)
{
external_constructor<value_t::object>::construct_moving(j, obj);
}
template<typename BasicJsonType>
inline void to_json(BasicJsonType& j, typename BasicJsonType::object_t&& obj)
{
include/nlohmann/detail/conversions/zmij.hpp
+222
View File
@@ -0,0 +1,222 @@
// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2025 Victor Zverovich <https://github.com/vitaut/zmij>
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
#pragma once
#include <array> // array
#include <cstddef> // size_t
#include <cstdint> // uint32_t, uint64_t
#include <nlohmann/detail/abi_macros.hpp>
#include <nlohmann/detail/bit_ops.hpp>
#include <nlohmann/detail/input/pow5_table.hpp>
#include <nlohmann/detail/macro_scope.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
/*!
@brief the shortest decimal representation of a double
A C++11 port of the conversion of Zmij by Victor Zverovich
(https://github.com/vitaut/zmij, MIT license): the shortest decimal in the
rounding interval of a double, the closest one if there are several. Zmij
credits Xiang JunBo (producing the shorter candidate without a division) and
Dougall Johnson (the compressed powers of ten). The powers of ten are taken
from the table for number parsing (pow5_table.hpp) where it holds them, and
computed from the compressed tables of Zmij beyond it.
*/
namespace zmij
{
/// the compressed powers of ten of Zmij
inline const std::array<std::uint64_t, 28>& pow10_minor() noexcept
{
static const std::array<std::uint64_t, 28> table =
{
{
0x8000000000000000u, 0xa000000000000000u, 0xc800000000000000u, 0xfa00000000000000u, 0x9c40000000000000u,
0xc350000000000000u, 0xf424000000000000u, 0x9896800000000000u, 0xbebc200000000000u, 0xee6b280000000000u,
0x9502f90000000000u, 0xba43b74000000000u, 0xe8d4a51000000000u, 0x9184e72a00000000u, 0xb5e620f480000000u,
0xe35fa931a0000000u, 0x8e1bc9bf04000000u, 0xb1a2bc2ec5000000u, 0xde0b6b3a76400000u, 0x8ac7230489e80000u,
0xad78ebc5ac620000u, 0xd8d726b7177a8000u, 0x878678326eac9000u, 0xa968163f0a57b400u, 0xd3c21bcecceda100u,
0x84595161401484a0u, 0xa56fa5b99019a5c8u, 0xcecb8f27f4200f3au
}
};
return table;
}
/// (high, low) pairs
inline const std::array<std::uint64_t, 50>& pow10_major() noexcept
{
static const std::array<std::uint64_t, 50> table =
{
{
0xaddcb9e83c6b1793u, 0xdf4abe242a1bbf3eu, 0xaf8e5410288e1b6fu, 0x07ecf0ae5ee44ddau, 0xb1442798f49ffb4au, 0x99cd11cfdf41779du,
0xb2fe3f0b8599ef07u, 0x861fa7e6dcb4aa15u, 0xb4bca50b065abe63u, 0x0fed077a756b53aau, 0xb67f6455292cbf08u, 0x1a3bc84c17b1d543u,
0xb84687c269ef3bfbu, 0x3d5d514f40eea742u, 0xba121a4650e4ddebu, 0x92f34d62616ce413u, 0xbbe226efb628afeau, 0x890489f70a55368cu,
0xbdb6b8e905cb600fu, 0x5400e987bbc1c921u, 0xbf8fdb78849a5f96u, 0xde98520472bdd034u, 0xc16d9a0095928a27u, 0x75b7053c0f178294u,
0xc350000000000000u, 0x0000000000000000u, 0xc5371912364ce305u, 0x6c28000000000000u, 0xc722f0ef9d80aad6u, 0x424d3ad2b7b97ef6u,
0xc913936dd571c84cu, 0x03bc3a19cd1e38eau, 0xcb090c8001ab551cu, 0x5cadf5bfd3072cc6u, 0xcd036837130890a1u, 0x36dba887c37a8c10u,
0xcf02b2c21207ef2eu, 0x94f967e45e03f4bcu, 0xd106f86e69d785c7u, 0xe13336d701beba52u, 0xd31045a8341ca07cu, 0x1ede48111209a051u,
0xd51ea6fa85785631u, 0x552a74227f3ea566u, 0xd732290fbacaf133u, 0xa97c177947ad4096u, 0xd94ad8b1c7380874u, 0x18375281ae7822bdu,
0xdb68c2ca82ed2a05u, 0xa67398db9f6820e1u
}
};
return table;
}
/// one bit per power: whether the computed value is one unit too large
inline const std::array<std::uint32_t, 21>& pow10_fixups() noexcept
{
static const std::array<std::uint32_t, 21> table =
{
{
0x8d8fc810u, 0x06100293u, 0x19000000u, 0x00100000u, 0x00000908u, 0x00000000u, 0x04e00300u, 0x3807e0b2u, 0x3d83d793u, 0x0006f5ccu,
0x00000000u, 0xffff0000u, 0x8076337du, 0x4ff45ba0u, 0x09405033u, 0x034376d9u, 0x09000000u, 0x4e100501u, 0x076d14dcu, 0xf964f45eu,
0x0000003du
}
};
return table;
}
/// the 128-bit significand of 10^k, rounded down, for k in [-307, 341]
/// (compute_pow10 of Zmij)
inline uint128_parts compute_pow10(int k) noexcept
{
const auto i = static_cast<unsigned>(k + 307);
const std::uint64_t m = pow10_minor()[(i + 24) % 28];
const std::size_t j = 2 * static_cast<std::size_t>((i + 24) / 28);
const std::uint64_t h_hi = pow10_major()[j];
const std::uint64_t h_lo = pow10_major()[j + 1];
const std::uint64_t h1 = full_multiplication(h_lo, m).high;
const std::uint64_t c0 = h_lo * m;
const std::uint64_t c1 = h1 + (h_hi * m);
const std::uint64_t c2 = (c1 < h1 ? 1u : 0u) + full_multiplication(h_hi, m).high;
uint128_parts r{};
if ((c2 >> 63u) != 0)
{
r.high = c2;
r.low = c1;
}
else
{
r.high = (c2 << 1u) | (c1 >> 63u);
r.low = (c1 << 1u) | (c0 >> 63u);
}
r.low -= (pow10_fixups()[i >> 5u] >> (i & 31u)) & 1u;
return r;
}
/// The 128-bit significand of 10^k, rounded down, for k in [-342, 341].
/// Up to 10^308, the table for number parsing holds the same significands
/// (those of 5^k), except for k in [-27, -1], where it holds them one unit
/// larger (as the Eisel-Lemire algorithm needs them).
inline uint128_parts pow10(int k) noexcept
{
if (k > pow5_128_largest_power)
{
return compute_pow10(k); // (only for the smallest doubles)
}
const auto i = 2 * static_cast<std::size_t>(k - pow5_128_smallest_power);
uint128_parts r{pow5_128()[i + 1], pow5_128()[i]};
const std::uint64_t adjust = static_cast<unsigned>(k + 27) < 27u ? 1u : 0u;
r.high -= r.low < adjust ? 1u : 0u;
r.low -= adjust;
return r;
}
/// (x_hi * 2^64 + x_lo) * y >> 64, as 128 bits
inline uint128_parts umul192_hi128(std::uint64_t x_hi, std::uint64_t x_lo, std::uint64_t y) noexcept
{
const uint128_parts p = full_multiplication(x_hi, y);
uint128_parts r{};
r.low = p.low + full_multiplication(x_lo, y).high;
r.high = p.high + (r.low < p.low ? 1u : 0u);
return r;
}
/// (x * y + c) >> 64
inline std::uint64_t umul128_add_hi64(std::uint64_t x, std::uint64_t y, std::uint64_t c) noexcept
{
const uint128_parts p = full_multiplication(x, y);
return p.high + (p.low + c < p.low ? 1u : 0u);
}
/// the result of Zmij: the shorter candidate and, if that is outside the
/// rounding interval, the digit after it (16 bytes: returned in registers)
struct shortest_decimal
{
std::uint64_t integral; ///< the shorter candidate (15 or 16 digits for normal doubles)
int exponent; ///< the decimal exponent of the digit after it
unsigned char digit; ///< the digit after it (if has_digit)
bool has_digit; ///< whether the shortest decimal is integral * 10 + digit
};
/// The shortest decimal in the rounding interval of a positive finite double
/// given by its bits, the closest one if there are several (to_decimal of
/// Zmij, which keeps the last digit apart: the 15 or 16 digits before it can be
/// converted without a multiplication by 10 first). Always inlined: GCC
/// otherwise calls it, and its result goes through memory.
JSON_HEDLEY_ALWAYS_INLINE shortest_decimal to_shortest(std::uint64_t bits) noexcept
{
constexpr int extra_shift = 9;
const auto raw_exp = static_cast<int>((bits >> 52u) & 0x7FFu);
std::uint64_t bin_sig = bits & ((std::uint64_t{1} << 52u) - 1);
// a power of two has a narrower interval below (except the smallest normal)
const bool regular = bin_sig != 0 || raw_exp <= 1;
const int bin_exp = (raw_exp == 0 ? 1 : raw_exp) - 1075;
if (raw_exp != 0)
{
bin_sig |= std::uint64_t{1} << 52u;
}
// floor(log10(2^bin_exp)), or floor(log10(3/4 * 2^bin_exp)) for the irregular case
const int dec_exp = ((bin_exp * 315653) - (regular ? 0 : 131072)) >> 20;
// scaled by 10^(-dec_exp - 1): the integral part is the shorter candidate
const int shift = bin_exp + ((-(dec_exp + 1) * 217707) >> 16) + 1 + extra_shift;
const uint128_parts p10 = pow10(-dec_exp - 1);
const uint128_parts p = umul192_hi128(p10.high, p10.low, bin_sig << static_cast<unsigned>(shift));
std::uint64_t integral = p.high >> static_cast<unsigned>(extra_shift);
// (no casts in the shifts: MSVC 2015 warns C4554 on them despite the parentheses)
constexpr auto fractional_low_shift = static_cast<unsigned>(extra_shift);
constexpr unsigned fractional_high_shift = 64u - fractional_low_shift;
const std::uint64_t fractional = (p.high << fractional_high_shift) | (p.low >> fractional_low_shift);
std::uint64_t digit = 0;
bool round_up = false;
bool round_down = false;
if (JSON_HEDLEY_LIKELY(regular))
{
const std::uint64_t half_ulp = (p10.high >> static_cast<unsigned>(extra_shift + 1 - shift)) + (1 - (bin_sig & 1u));
round_up = fractional + half_ulp < fractional;
round_down = half_ulp > fractional;
// the last digit of the longer candidate, rounded to nearest
digit = umul128_add_hi64(fractional, 10, (std::uint64_t{1} << 63u) + 6);
if (fractional == (std::uint64_t{1} << 62u))
{
digit = 2; // 2.5 rounds to 2
}
}
else
{
const std::uint64_t half_ulp = p10.high >> static_cast<unsigned>(extra_shift + 1 - shift);
round_up = half_ulp > ~std::uint64_t{0} - fractional;
round_down = (half_ulp >> 1u) > fractional;
digit = umul128_add_hi64(fractional, 10, (std::uint64_t{1} << 63u) - 1);
const std::uint64_t lowest = umul128_add_hi64(fractional - (half_ulp >> 1u), 10, ~std::uint64_t{0});
digit = digit < lowest ? lowest : digit;
}
integral += round_up ? 1u : 0u;
// if the shorter candidate is outside the rounding interval: one digit more
return shortest_decimal{integral, dec_exp, static_cast<unsigned char>(digit), !round_up && !round_down};
}
} // namespace zmij
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/exceptions.hpp
+214
View File
@@ -45,6 +45,84 @@ namespace detail
// exceptions //
////////////////
/*!
@brief the ids of the exceptions thrown by the library
@note The values are part of the public API: they are the `id` member of the
exceptions and appear in their `what()` messages.
@sa https://json.nlohmann.me/home/exceptions/
*/
enum class exception_id : int
{
// parse_error
syntax_error = 101, ///< unexpected token or invalid literal while parsing JSON
patch_not_an_array = 104, ///< a JSON Patch document is not an array of objects
patch_invalid_operation = 105, ///< a JSON Patch operation is malformed
pointer_index_leading_zero = 106, ///< a JSON Pointer array index has a leading zero
pointer_missing_slash = 107, ///< a JSON Pointer does not start with '/'
pointer_invalid_escape = 108, ///< a JSON Pointer contains an escape other than ~0 and ~1
pointer_index_not_a_number = 109, ///< a JSON Pointer array index is not a number
unexpected_end_of_input = 110, ///< a binary input ends early, or has bytes left at its end
unexpected_byte = 112, ///< a binary input contains an unexpected byte or invalid length
invalid_string_or_size = 113, ///< a binary input contains an invalid string or size specification
bson_unsupported_type = 114, ///< a BSON record type is not supported
invalid_high_precision_number = 115, ///< a UBJSON/BJData high-precision number cannot be parsed
// invalid_iterator
iterators_incompatible = 201, ///< the iterators of a range belong to different values
iterator_from_other_value = 202, ///< an iterator does not belong to the value it is used with
iterator_range_from_other_value = 203, ///< an iterator range does not belong to the value it is used with
iterator_range_out_of_range = 204, ///< an iterator range of a primitive value is not [begin, end)
iterator_out_of_range = 205, ///< an iterator of a primitive value is not begin()
iterator_range_of_null = 206, ///< an iterator range belongs to a null value
iterator_key_not_object = 207, ///< key() is called on an iterator of a non-object
iterator_subscript_on_object = 208, ///< operator[] is called on an iterator of an object
iterator_arithmetic_on_object = 209, ///< an offset operator is used on an iterator of an object
insert_range_incompatible = 210, ///< the iterators of an inserted range belong to different values
insert_range_into_itself = 211, ///< an inserted range belongs to the value it is inserted into
iterators_compare_different_values = 212, ///< iterators of different values are compared
iterator_order_on_object = 213, ///< iterators of an object are compared by order
iterator_value_unavailable = 214, ///< an iterator does not refer to a value
// type_error
object_from_non_pairs = 301, ///< an object is created from an initializer list that is not a list of pairs
type_mismatch = 302, ///< a value has the wrong type for a conversion
incompatible_reference_type = 303, ///< get_ref() is called with a reference type that does not match the value
at_wrong_type = 304, ///< at() is called on a value of the wrong type
subscript_wrong_type = 305, ///< operator[] is called on a value of the wrong type
value_wrong_type = 306, ///< value() is called on a value of the wrong type
erase_wrong_type = 307, ///< erase() is called on a value of the wrong type
push_back_wrong_type = 308, ///< push_back() or operator+= is called on a value of the wrong type
insert_wrong_type = 309, ///< insert() is called on a value of the wrong type
swap_wrong_type = 310, ///< swap() is called on a value of the wrong type
emplace_wrong_type = 311, ///< emplace() or emplace_back() is called on a value of the wrong type
update_wrong_type = 312, ///< update() is called on a value of the wrong type
unflatten_invalid_value = 313, ///< unflatten() finds conflicting paths
unflatten_not_object = 314, ///< unflatten() is called on a non-object
unflatten_value_not_primitive = 315, ///< unflatten() is called on an object with non-primitive values
invalid_utf8 = 316, ///< dump() finds a string that is not valid UTF-8
type_not_serializable = 317, ///< a value cannot be serialized to the requested binary format
enum_key_duplicate = 318, ///< an enum-keyed map has two keys that serialize to the same string
discarded_value_used = 321, ///< a discarded value is used
// out_of_range
array_index_out_of_range = 401, ///< an array index is out of range
pointer_past_the_end_index = 402, ///< a JSON Pointer uses the array index '-'
key_not_found = 403, ///< an object key is not found
pointer_unresolved = 404, ///< a JSON Pointer reference token cannot be resolved
patch_on_root = 405, ///< the root of a value has no parent, e.g. for a JSON Patch 'remove' or 'add' at the root
number_overflow = 406, ///< a number cannot be stored without overflowing to NaN or INF
integer_too_large = 407, ///< an integer cannot be represented in the binary format
container_too_large = 408, ///< the size of a container in a binary input exceeds the maximal capacity
bson_key_with_null = 409, ///< a BSON key contains U+0000
value_out_of_range = 410, ///< an enum value is undefined, or a JSON Pointer array index exceeds size_type
patch_add_parent_not_container = 411, ///< the parent of a JSON Patch 'add' target is not a container
length_too_large = 412, ///< a length does not fit into the length field of a binary format
patch_remove_parent_not_container = 413, ///< the parent of a JSON Patch 'remove' target is not a container
patch_move_into_child = 414, ///< a JSON Patch 'move' moves a value into one of its children
subtype_out_of_range = 415, ///< a binary subtype does not fit into one byte
// other_error
internal_error = 500, ///< unreachable code was reached
patch_test_failed = 501, ///< a JSON Patch 'test' operation failed
size_marker_required = 502 ///< UBJSON/BJData output with type markers requires size markers
};
/// @brief general exception of the @ref basic_json class
/// @sa https://json.nlohmann.me/api/basic_json/exception/
class exception : public std::exception
@@ -195,6 +273,18 @@ class parse_error : public exception
return {id_, byte_, w.c_str()};
}
template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
static parse_error create(exception_id id_, const position_t& pos, const std::string& what_arg, BasicJsonContext context)
{
return create(static_cast<int>(id_), pos, what_arg, context);
}
template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
static parse_error create(exception_id id_, std::size_t byte_, const std::string& what_arg, BasicJsonContext context)
{
return create(static_cast<int>(id_), byte_, what_arg, context);
}
/*!
@brief byte index of the parse error
@@ -229,6 +319,12 @@ class invalid_iterator : public exception
return {id_, w.c_str()};
}
template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
static invalid_iterator create(exception_id id_, const std::string& what_arg, BasicJsonContext context)
{
return create(static_cast<int>(id_), what_arg, context);
}
private:
JSON_HEDLEY_NON_NULL(3)
invalid_iterator(int id_, const char* what_arg)
@@ -247,6 +343,12 @@ class type_error : public exception
return {id_, w.c_str()};
}
template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
static type_error create(exception_id id_, const std::string& what_arg, BasicJsonContext context)
{
return create(static_cast<int>(id_), what_arg, context);
}
private:
JSON_HEDLEY_NON_NULL(3)
type_error(int id_, const char* what_arg) : exception(id_, what_arg) {}
@@ -264,6 +366,12 @@ class out_of_range : public exception
return {id_, w.c_str()};
}
template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
static out_of_range create(exception_id id_, const std::string& what_arg, BasicJsonContext context)
{
return create(static_cast<int>(id_), what_arg, context);
}
private:
JSON_HEDLEY_NON_NULL(3)
out_of_range(int id_, const char* what_arg) : exception(id_, what_arg) {}
@@ -281,6 +389,12 @@ class other_error : public exception
return {id_, w.c_str()};
}
template<typename BasicJsonContext, enable_if_t<is_basic_json_context<BasicJsonContext>::value, int> = 0>
static other_error create(exception_id id_, const std::string& what_arg, BasicJsonContext context)
{
return create(static_cast<int>(id_), what_arg, context);
}
private:
JSON_HEDLEY_NON_NULL(3)
other_error(int id_, const char* what_arg) : exception(id_, what_arg) {}
@@ -307,6 +421,106 @@ void templated_json_throw(ExceptionType exception)
(void)exception;
}
/*!
@brief throws because @a j does not have the type a conversion expects
@param[in] expected the expected type(s), e.g. "array" or "binary or array"
@param[in] j the value with the wrong type
@throw type_error.302 always
*/
template<typename BasicJsonType>
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE void throw_type_must_be(const char* expected, const BasicJsonType& j)
{
static_cast<void>(expected); // unused when JSON_NOEXCEPTION is defined
static_cast<void>(j);
JSON_THROW(type_error::create(exception_id::type_mismatch, concat("type must be ", expected, ", but is ", j.type_name()), &j));
}
/*!
@brief throws because an operation is not supported for the type of @a j
@param[in] id_ the id of the type_error exception (at_wrong_type..update_wrong_type)
@param[in] operation the operation, e.g. "erase()"
@param[in] j the value the operation was called on
@throw type_error always
*/
template<typename BasicJsonType>
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE void throw_cannot_use_with(const exception_id id_, const char* operation, const BasicJsonType& j)
{
static_cast<void>(id_); // unused when JSON_NOEXCEPTION is defined
static_cast<void>(operation);
static_cast<void>(j);
JSON_THROW(type_error::create(id_, concat("cannot use ", operation, " with ", j.type_name()), &j));
}
/*!
@brief throws ExceptionType with a fixed message; kept out of line so that callers do not carry the exception construction
*/
template<typename ExceptionType, typename BasicJsonContext>
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE void throw_literal(const exception_id id_, const char* what_arg, BasicJsonContext context)
{
static_cast<void>(id_); // unused when JSON_NOEXCEPTION is defined
static_cast<void>(what_arg);
static_cast<void>(context);
JSON_THROW(ExceptionType::create(id_, what_arg, context));
}
// JSON Patch errors; constructed out of line so that patch_inplace() does not carry them
template<typename BasicJsonType>
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE void throw_patch_add_parent(const BasicJsonType& parent)
{
static_cast<void>(parent);
JSON_THROW(out_of_range::create(exception_id::patch_add_parent_not_container, concat("cannot add value: the JSON Patch 'add' target's parent is of type ", parent.type_name(), ", but must be an object or array"), &parent));
}
template<typename BasicJsonType>
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE void throw_patch_remove_parent(const BasicJsonType& parent)
{
static_cast<void>(parent);
JSON_THROW(out_of_range::create(exception_id::patch_remove_parent_not_container, concat("cannot remove value: the JSON Patch 'remove' target's parent is of type ", parent.type_name(), ", but must be an object or array"), &parent));
}
template<typename BasicJsonType>
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE void throw_patch_not_an_array(const BasicJsonType& j)
{
static_cast<void>(j);
JSON_THROW(parse_error::create(exception_id::patch_not_an_array, 0, "JSON patch must be an array of objects", &j));
}
template<typename StringType, typename BasicJsonType>
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE void throw_patch_missing_member(const StringType& op, const StringType& member, const bool string_type, const BasicJsonType& val)
{
static_cast<void>(op);
static_cast<void>(member);
static_cast<void>(string_type);
static_cast<void>(val);
// context-sensitive error message
JSON_THROW(parse_error::create(exception_id::patch_invalid_operation, 0, concat((op == "op") ? std::string("operation") : concat("operation '", op, '\''), string_type ? " must have string member '" : " must have member '", member, "'"), &val));
}
template<typename StringType, typename BasicJsonType>
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE void throw_patch_move_into_child(const StringType& from_path, const StringType& path, const BasicJsonType& result)
{
static_cast<void>(from_path);
static_cast<void>(path);
static_cast<void>(result);
JSON_THROW(out_of_range::create(exception_id::patch_move_into_child, concat("cannot move value: 'from' path '", from_path, "' is a proper prefix of 'path' '", path, "'"), &result));
}
template<typename BasicJsonType>
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE void throw_patch_test_failed(const BasicJsonType& val)
{
static_cast<void>(val);
JSON_THROW(other_error::create(exception_id::patch_test_failed, concat("unsuccessful: ", val.dump()), &val));
}
template<typename StringType, typename BasicJsonType>
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE void throw_patch_invalid_operation(const StringType& op, const BasicJsonType& val)
{
static_cast<void>(op);
static_cast<void>(val);
JSON_THROW(parse_error::create(exception_id::patch_invalid_operation, 0, concat("operation value '", op, "' is invalid"), &val));
}
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/input/binary_reader.hpp
+147 -142
View File
@@ -12,7 +12,6 @@
#include <cmath> // ldexp
#include <cstddef> // size_t
#include <cstdint> // uint8_t, uint16_t, uint32_t, uint64_t, uintmax_t
#include <cstdio> // snprintf
#include <cstring> // memcpy
#include <iterator> // back_inserter
#include <limits> // numeric_limits
@@ -196,8 +195,7 @@ class binary_reader
if (JSON_HEDLEY_UNLIKELY(current != char_traits<char_type>::eof()))
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(110, chars_read,
exception_message(concat("expected end of input; last byte: 0x", get_token_string()), "value"), nullptr));
return last_byte_error(exception_id::unexpected_end_of_input, "expected end of input", "value", "");
}
}
@@ -319,8 +317,7 @@ class binary_reader
{
if (JSON_HEDLEY_UNLIKELY(document_size < 0 || static_cast<std::size_t>(document_size) != chars_read - document_start))
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
exception_message(concat("document size ", std::to_string(document_size), " does not match the number of bytes read (", std::to_string(chars_read - document_start), ")"), "document"), nullptr));
return bson_document_size_error(document_size, chars_read - document_start);
}
return true;
}
@@ -512,9 +509,7 @@ class binary_reader
{
if (JSON_HEDLEY_UNLIKELY(len < 1))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("string length must be at least 1, is ", std::to_string(len)), "string"), nullptr));
return bson_length_error("string length must be at least 1, is ", len, "string");
}
if (JSON_HEDLEY_UNLIKELY(!get_string(len - static_cast<NumberType>(1), result)))
@@ -524,10 +519,7 @@ class binary_reader
if (JSON_HEDLEY_UNLIKELY(get() != 0x00))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message("BSON string is not null-terminated",
"string"), nullptr));
return last_byte_error(exception_id::unexpected_byte, "BSON string is not null-terminated", "string");
}
return check_string_utf8(result, "string");
@@ -547,9 +539,7 @@ class binary_reader
{
if (JSON_HEDLEY_UNLIKELY(len < 0))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("byte array length cannot be negative, is ", std::to_string(len)), "binary"), nullptr));
return bson_length_error("byte array length cannot be negative, is ", len, "binary");
}
// All BSON binary values have a subtype
@@ -639,11 +629,7 @@ class binary_reader
default: // anything else is not supported (yet)
{
std::array<char, 3> cr{{}};
static_cast<void>((std::snprintf)(cr.data(), cr.size(), "%.2hhX", static_cast<unsigned char>(element_type))); // NOLINT(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
const std::string cr_str{cr.data()};
return sax->parse_error(element_type_parse_position, cr_str,
parse_error::create(114, element_type_parse_position, concat("Unsupported BSON record type 0x", cr_str), nullptr));
return bson_unsupported_type_error(element_type_parse_position, element_type);
}
}
}
@@ -967,9 +953,7 @@ class binary_reader
{
if (tag_handler == cbor_tag_handler_t::error)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("invalid byte: 0x", last_token), "value"), nullptr));
return unexpected_byte("invalid byte", "value");
}
// ignore and store: the tag value is already in the head, so
@@ -989,9 +973,7 @@ class binary_reader
{
case cbor_tag_handler_t::error:
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("invalid byte: 0x", last_token), "value"), nullptr));
return unexpected_byte("invalid byte", "value");
}
case cbor_tag_handler_t::ignore:
@@ -1065,9 +1047,7 @@ class binary_reader
default: // anything else (0xFF is handled inside the other types)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("invalid byte: 0x", last_token), "value"), nullptr));
return unexpected_byte("invalid byte", "value");
}
}
}
@@ -1078,12 +1058,10 @@ class binary_reader
@param[in] context parsing context for the error message
@return whether the SAX consumer accepts the parse error
*/
JSON_HEDLEY_NEVER_INLINE
bool cbor_indefinite_string_error(const char* type_name, const char* context)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("indefinite-length ", type_name,
" is not allowed inside indefinite-length ", type_name, "; last byte: 0x", last_token), context), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, concat("indefinite-length ", type_name, " is not allowed inside indefinite-length ", type_name, "; last byte: 0x", get_token_string()), context);
}
/*!
@@ -1160,9 +1138,7 @@ class binary_reader
default:
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("expected length specification (0x60-0x7B)", inside_indefinite ? "" : " or indefinite string type (0x7F)", "; last byte: 0x", last_token), "string"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "expected length specification (0x60-0x7B)", "string", inside_indefinite ? "" : " or indefinite string type (0x7F)");
}
}
}
@@ -1292,9 +1268,7 @@ class binary_reader
break;
}
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("only string keys are supported, but found ", found, "; last byte: 0x", last_token), "object key"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "only string keys are supported, but found ", "object key", found);
}
/*!
@@ -1375,9 +1349,7 @@ class binary_reader
default:
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("expected length specification (0x40-0x5B)", inside_indefinite ? "" : " or indefinite binary array type (0x5F)", "; last byte: 0x", last_token), "binary"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "expected length specification (0x40-0x5B)", "binary", inside_indefinite ? "" : " or indefinite binary array type (0x5F)");
}
}
}
@@ -1523,8 +1495,7 @@ class binary_reader
{
if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::size_t>(len) || len == detail::unknown_size()))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
exception_message(concat("excessive ", context, " size"), "size"), nullptr));
return container_size_error(context);
}
result = conditional_static_cast<std::size_t>(len);
return true;
@@ -2011,9 +1982,7 @@ class binary_reader
default: // anything else
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("invalid byte: 0x", last_token), "value"), nullptr));
return unexpected_byte("invalid byte", "value");
}
}
}
@@ -2094,9 +2063,7 @@ class binary_reader
default:
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("expected length specification (0xA0-0xBF, 0xD9-0xDB); last byte: 0x", last_token), "string"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "expected length specification (0xA0-0xBF, 0xD9-0xDB)", "string", "");
}
}
}
@@ -2188,9 +2155,7 @@ class binary_reader
break;
}
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("only string keys are supported, but found ", found, "; last byte: 0x", last_token), "object key"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "only string keys are supported, but found ", "object key", found);
}
/*!
@@ -2499,8 +2464,7 @@ class binary_reader
{
if (JSON_HEDLEY_UNLIKELY(len < 0))
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
exception_message("string length must not be negative", "string"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "string length must not be negative", "string");
}
return true;
}
@@ -2600,18 +2564,7 @@ class binary_reader
default:
break;
}
auto last_token = get_token_string();
std::string message;
if (input_format != input_format_t::bjdata)
{
message = "expected length type specification (U, i, I, l, L); last byte: 0x" + last_token;
}
else
{
message = "expected length type specification (U, i, u, I, m, l, M, L); last byte: 0x" + last_token;
}
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(message, "string"), nullptr));
return length_type_error("", "string");
}
/*!
@@ -2696,13 +2649,11 @@ class binary_reader
}
if (JSON_HEDLEY_UNLIKELY(number < 0))
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read,
exception_message("count in an optimized container must be positive", "size"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "count in an optimized container must be positive", "size");
}
if (JSON_HEDLEY_UNLIKELY(!value_in_range_of<std::size_t>(number)))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
exception_message("integer value overflow", "size"), nullptr));
return out_of_range_error(exception_id::container_too_large, "integer value overflow", "size");
}
result = static_cast<std::size_t>(number); // NOLINT(bugprone-signed-char-misuse,cert-str34-c): number is not a char
return true;
@@ -2799,8 +2750,7 @@ class binary_reader
}
if (!value_in_range_of<std::size_t>(number))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
exception_message("integer value overflow", "size"), nullptr));
return out_of_range_error(exception_id::container_too_large, "integer value overflow", "size");
}
result = detail::conditional_static_cast<std::size_t>(number);
return true;
@@ -2814,7 +2764,7 @@ class binary_reader
}
if (is_ndarray) // ndarray dimensional vector can only contain integers and cannot embed another array
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(113, chars_read, exception_message("ndarray dimensional vector is not allowed", "size"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "ndarray dimensional vector is not allowed", "size");
}
std::vector<size_t> dim;
if (JSON_HEDLEY_UNLIKELY(!get_ubjson_ndarray_size(dim)))
@@ -2850,9 +2800,7 @@ class binary_reader
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));
return unexpected_byte("invalid byte", "type");
}
string_t type_key = "_ArrayType_";
@@ -2880,7 +2828,7 @@ class binary_reader
// or SIZE_MAX.
if (JSON_HEDLEY_UNLIKELY(result > (std::numeric_limits<std::size_t>::max)() / i))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408, exception_message("excessive ndarray size caused overflow", "size"), nullptr));
return out_of_range_error(exception_id::container_too_large, "excessive ndarray size caused overflow", "size");
}
result *= i;
// the pre-check above already rules out result becoming 0
@@ -2889,7 +2837,7 @@ class binary_reader
// unknown-size container (see get_ubjson_size_type())
if (result == npos)
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408, exception_message("excessive ndarray size caused overflow", "size"), nullptr));
return out_of_range_error(exception_id::container_too_large, "excessive ndarray size caused overflow", "size");
}
if (JSON_HEDLEY_UNLIKELY(!emit_unsigned(i)))
{
@@ -2906,18 +2854,7 @@ class binary_reader
default:
break;
}
auto last_token = get_token_string();
std::string message;
if (input_format != input_format_t::bjdata)
{
message = "expected length type specification (U, i, I, l, L) after '#'; last byte: 0x" + last_token;
}
else
{
message = "expected length type specification (U, i, u, I, m, l, M, L) after '#'; last byte: 0x" + last_token;
}
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read, exception_message(message, "size"), nullptr));
return length_type_error(" after '#'", "size");
}
/*!
@@ -2950,9 +2887,7 @@ class binary_reader
if (input_format == input_format_t::bjdata
&& JSON_HEDLEY_UNLIKELY(is_bjd_excluded_optimized_type(result.second)))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("marker 0x", last_token, " is not a permitted optimized array type"), "type"), nullptr));
return optimized_type_error();
}
if (JSON_HEDLEY_UNLIKELY(!unexpect_eof("type")))
@@ -2967,9 +2902,7 @@ class binary_reader
{
return false;
}
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat("expected '#' after type information; last byte: 0x", last_token), "size"), nullptr));
return last_byte_error(exception_id::unexpected_byte, "expected '#' after type information", "size", "");
}
const bool is_error = get_ubjson_size_value(result.first, is_ndarray, 0, result.second);
@@ -2988,8 +2921,7 @@ class binary_reader
const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
if (input_format == input_format_t::bjdata && is_ndarray && !inside_ndarray)
{
return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
exception_message("ndarray requires both type and size", "size"), nullptr));
return last_byte_error(exception_id::unexpected_byte, "ndarray requires both type and size", "size");
}
return is_error;
}
@@ -3121,9 +3053,7 @@ class binary_reader
}
if (JSON_HEDLEY_UNLIKELY(current > 127))
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message(concat("byte after 'C' must be in range 0x00..0x7F; last byte: 0x", last_token), "char"), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "byte after 'C' must be in range 0x00..0x7F", "char", "");
}
string_t s(1, static_cast<typename string_t::value_type>(current));
return sax->string(s);
@@ -3144,8 +3074,7 @@ class binary_reader
default: // anything else
break;
}
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, "value"), nullptr));
return unexpected_byte("invalid byte", "value");
}
/*!
@@ -3208,8 +3137,7 @@ class binary_reader
if (JSON_HEDLEY_UNLIKELY((size_and_type.second == 'Z' || size_and_type.second == 'T' || size_and_type.second == 'F')
&& size_and_type.first > max_valueless_container_size))
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(408,
exception_message("excessive array size", "size"), nullptr));
return out_of_range_error(exception_id::container_too_large, "excessive array size", "size");
}
if (JSON_HEDLEY_UNLIKELY(!enter_array(size_and_type.first, size_and_type.second)))
@@ -3244,9 +3172,7 @@ class binary_reader
// do not accept ND-array size in objects in BJData
if (input_format == input_format_t::bjdata && size_and_type.first != npos && (size_and_type.second & (1 << 8)) != 0)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message("BJData object does not support ND-array size in optimized format", "object"), nullptr));
return last_byte_error(exception_id::unexpected_byte, "BJData object does not support ND-array size in optimized format", "object");
}
if (size_and_type.first != npos)
@@ -3283,7 +3209,7 @@ class binary_reader
// the lexer would stop at a NUL and accept the digits before it
if (JSON_HEDLEY_UNLIKELY(current == '\0'))
{
return sax->parse_error(chars_read, "00", parse_error::create(115, chars_read,
return sax->parse_error(chars_read, "00", parse_error::create(exception_id::invalid_high_precision_number, chars_read,
exception_message("invalid number text; last byte: 0x00", "high-precision number"), nullptr));
}
number_vector.push_back(static_cast<char>(current));
@@ -3300,7 +3226,7 @@ class binary_reader
if (JSON_HEDLEY_UNLIKELY(result_remainder != token_type::end_of_input))
{
return sax->parse_error(chars_read, number_string, parse_error::create(115, chars_read,
return sax->parse_error(chars_read, number_string, parse_error::create(exception_id::invalid_high_precision_number, chars_read,
exception_message(concat("invalid number text: ", number_lexer.get_token_string()), "high-precision number"), nullptr));
}
@@ -3318,7 +3244,7 @@ class binary_reader
return sax->parse_error(
chars_read,
number_string,
out_of_range::create(406, concat("number overflow parsing '", number_string, '\''), nullptr));
out_of_range::create(exception_id::number_overflow, concat("number overflow parsing '", number_string, '\''), nullptr));
}
// number_string is a std::string, while the SAX interface takes a
// string_t; convert explicitly, as the two are only implicitly
@@ -3340,7 +3266,7 @@ class binary_reader
case token_type::end_of_input:
case token_type::literal_or_value:
default:
return sax->parse_error(chars_read, number_string, parse_error::create(115, chars_read,
return sax->parse_error(chars_read, number_string, parse_error::create(exception_id::invalid_high_precision_number, chars_read,
exception_message(concat("invalid number text: ", number_lexer.get_token_string()), "high-precision number"), nullptr));
}
}
@@ -3399,20 +3325,6 @@ class binary_reader
return 0x80 <= c && c <= 0xBF;
}
/*!
@brief report a parse error at the last read byte
@param[in] detail a detailed error message
@param[in] context further context information
@return false
*/
bool bon8_error(const std::string& detail, const char* context)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(112, chars_read,
exception_message(concat(detail, ": 0x", last_token), context), nullptr));
}
/*!
@brief read a BON8 value and everything nested inside it
@@ -3628,7 +3540,7 @@ class binary_reader
}
// 0xFE: end of container where a value is expected
return bon8_error("invalid byte", "value");
return unexpected_byte("invalid byte", "value");
}
/*!
@@ -3755,7 +3667,7 @@ class binary_reader
current = byte;
}
return bon8_error("expected a string; last byte", "key");
return unexpected_byte("expected a string; last byte", "key");
}
/*!
@@ -3878,7 +3790,7 @@ class binary_reader
if (JSON_HEDLEY_UNLIKELY(!valid_second))
{
return bon8_error("invalid UTF-8 byte", "string");
return unexpected_byte("invalid UTF-8 byte", "string");
}
result.push_back(static_cast<typename string_t::value_type>(byte));
@@ -3892,7 +3804,7 @@ class binary_reader
}
if (JSON_HEDLEY_UNLIKELY(!is_bon8_continuation(current)))
{
return bon8_error("invalid UTF-8 byte", "string");
return unexpected_byte("invalid UTF-8 byte", "string");
}
result.push_back(static_cast<typename string_t::value_type>(current));
}
@@ -3937,7 +3849,7 @@ class binary_reader
{
// in case of failure, advance position by 1 to report the failing location
++chars_read;
sax->parse_error(chars_read, "<end of file>", parse_error::create(110, chars_read, exception_message("unexpected end of input", context), nullptr));
static_cast<void>(report_eof(context));
return false;
}
return true;
@@ -4090,8 +4002,7 @@ class binary_reader
const auto result = static_cast<number_float_t>(number);
if (JSON_HEDLEY_UNLIKELY(std::isfinite(number) && !std::isfinite(result)))
{
return sax->parse_error(chars_read, get_token_string(),
out_of_range::create(406, exception_message("number overflow", "value"), nullptr));
return out_of_range_error(exception_id::number_overflow, "number overflow", "value");
}
return sax->number_float(result, "");
}
@@ -4211,9 +4122,7 @@ class binary_reader
if (error_handler == error_handler_t::strict)
{
auto last_token = get_token_string();
return sax->parse_error(chars_read, last_token, parse_error::create(113, chars_read,
exception_message("invalid string: ill-formed UTF-8 byte", context), nullptr));
return last_byte_error(exception_id::invalid_string_or_size, "invalid string: ill-formed UTF-8 byte", context);
}
result = sanitize_utf8(result, error_handler);
@@ -4308,20 +4217,116 @@ class binary_reader
{
if (JSON_HEDLEY_UNLIKELY(current == char_traits<char_type>::eof()))
{
return sax->parse_error(chars_read, "<end of file>",
parse_error::create(110, chars_read, exception_message("unexpected end of input", context), nullptr));
return report_eof(context);
}
return true;
}
/*!
@brief reports an unexpected end of input (out of line to keep the exception
construction out of the hot reading functions)
@param[in] context further context information (for diagnostics)
@return the result of the SAX parser's parse_error()
*/
JSON_HEDLEY_NON_NULL(2)
JSON_HEDLEY_NEVER_INLINE
bool report_eof(const char* context) const
{
return sax->parse_error(chars_read, "<end of file>",
parse_error::create(exception_id::unexpected_end_of_input, chars_read, exception_message("unexpected end of input", context), nullptr));
}
/*!
@brief reports an out_of_range error at the last read byte (out of line)
*/
JSON_HEDLEY_NEVER_INLINE
bool out_of_range_error(const exception_id id_, const char* detail, const char* context) const
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(id_, exception_message(detail, context), nullptr));
}
JSON_HEDLEY_NEVER_INLINE
bool container_size_error(const char* what) const
{
return sax->parse_error(chars_read, get_token_string(), out_of_range::create(exception_id::container_too_large,
exception_message(concat("excessive ", what, " size"), "size"), nullptr));
}
JSON_HEDLEY_NEVER_INLINE
bool optimized_type_error() const
{
return last_byte_error(exception_id::unexpected_byte, concat("marker 0x", get_token_string(), " is not a permitted optimized array type"), "type");
}
template<typename NumberType>
JSON_HEDLEY_NEVER_INLINE
bool bson_length_error(const char* prefix, const NumberType len, const char* context) const
{
return last_byte_error(exception_id::unexpected_byte, concat(prefix, std::to_string(len)), context);
}
JSON_HEDLEY_NEVER_INLINE
bool bson_document_size_error(const std::int32_t document_size, const std::size_t bytes_read) const
{
return last_byte_error(exception_id::unexpected_byte, concat("document size ", std::to_string(document_size), " does not match the number of bytes read (", std::to_string(bytes_read), ")"), "document");
}
JSON_HEDLEY_NEVER_INLINE
bool bson_unsupported_type_error(const std::size_t position, const char_int_type element_type) const
{
const std::string cr_str = hex_byte(static_cast<std::uint8_t>(element_type));
return sax->parse_error(position, cr_str,
parse_error::create(exception_id::bson_unsupported_type, position, concat("Unsupported BSON record type 0x", cr_str), nullptr));
}
/*!
@brief reports a parse error at the last read byte
@param[in] id_ the id of the parse_error exception
@param[in] detail a detailed error message
@param[in] context further context information
@param[in] tail optional text appended to the detail, followed by "; last byte: 0x<token>"
@return the result of the SAX parser's parse_error()
*/
JSON_HEDLEY_NEVER_INLINE
bool last_byte_error(const exception_id id_, const std::string& detail, const char* context, const char* tail = nullptr) const
{
// with a tail, the message reads "<detail><tail>; last byte: 0x<token>"
return sax->parse_error(chars_read, get_token_string(), parse_error::create(id_, chars_read,
exception_message(tail == nullptr ? detail : concat(detail, tail, "; last byte: 0x", get_token_string()), context), nullptr));
}
/*!
@brief reports the last read byte as unexpected (parse_error.112)
@param[in] detail what is wrong with the byte, e.g. "invalid byte"
@param[in] context further context information
@return the result of the SAX parser's parse_error()
*/
JSON_HEDLEY_NEVER_INLINE
bool unexpected_byte(const char* detail, const char* context) const
{
return last_byte_error(exception_id::unexpected_byte, concat(detail, ": 0x", get_token_string()), context);
}
/*!
@brief reports that the last read byte is not a UBJSON/BJData length type (parse_error.113)
@param[in] position where the length type was expected, e.g. " after '#'"
@param[in] context further context information
@return the result of the SAX parser's parse_error()
*/
JSON_HEDLEY_NEVER_INLINE
bool length_type_error(const char* position, const char* context) const
{
const char* types = input_format == input_format_t::bjdata ? "U, i, u, I, m, l, M, L" : "U, i, I, l, L";
return last_byte_error(exception_id::invalid_string_or_size,
concat("expected length type specification (", types, ")", position, "; last byte: 0x", get_token_string()), context);
}
/*!
@return a string representation of the last read byte
*/
std::string get_token_string() const
{
std::array<char, 3> cr{{}};
static_cast<void>((std::snprintf)(cr.data(), cr.size(), "%.2hhX", static_cast<unsigned char>(current))); // NOLINT(cppcoreguidelines-pro-type-vararg,hicpp-vararg)
return std::string{cr.data()};
return hex_byte(static_cast<std::uint8_t>(current));
}
/*!
include/nlohmann/detail/input/input_adapters.hpp
+333 -17
View File
@@ -8,16 +8,18 @@
#pragma once
#include <algorithm> // min
#include <algorithm> // count, find, min
#include <array> // array
#include <cstddef> // size_t
#include <cstdint> // uint32_t
#include <cstring> // strlen
#include <iterator> // begin, end, iterator_traits, random_access_iterator_tag, distance, next
#include <iterator> // begin, end, iterator_traits, random_access_iterator_tag, distance, next, reverse_iterator
#include <limits> // numeric_limits
#include <streambuf> // streambuf
#include <string> // string, char_traits
#include <type_traits> // enable_if, is_base_of, is_pointer, is_integral, remove_pointer
#include <utility> // pair, declval
#include <vector> // vector
#ifndef JSON_NO_IO
#include <cstdio> // FILE *
@@ -30,6 +32,33 @@
#include <nlohmann/detail/meta/type_traits.hpp>
#include <nlohmann/detail/string_utils.hpp>
#ifndef JSON_NO_IO
// Which unlocked stdio functions file_input_adapter uses (see
// JSON_DISABLE_UNLOCKED_FILE_IO): 1 = POSIX flockfile/getc_unlocked,
// 2 = Microsoft CRT _lock_file/_fgetc_nolock, 0 = none (std::fgetc, which
// locks the file for every character). Only C libraries known to declare
// the functions are listed; the macros are tested after <cstdio>, which
// defines __GLIBC__. MemorySanitizer builds always use std::fgetc: glibc's
// inline getc_unlocked reads the stdio buffer directly, which glibc (not
// instrumented) filled, so MemorySanitizer would report a false positive.
#if defined(__has_feature)
#if __has_feature(memory_sanitizer)
#define JSON_UNLOCKED_FILE_IO_MSAN 1
#endif
#endif
#if JSON_DISABLE_UNLOCKED_FILE_IO || defined(JSON_UNLOCKED_FILE_IO_MSAN)
#define JSON_UNLOCKED_FILE_IO 0
#elif defined(_MSC_VER)
#define JSON_UNLOCKED_FILE_IO 2
#elif defined(__GLIBC__) || defined(__APPLE__) || defined(__ANDROID__) || defined(__FreeBSD__) || defined(__NetBSD__) || defined(__OpenBSD__) || defined(__DragonFly__)
#define JSON_UNLOCKED_FILE_IO 1
#else
#define JSON_UNLOCKED_FILE_IO 0
#endif
#undef JSON_UNLOCKED_FILE_IO_MSAN
#endif // JSON_NO_IO
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
@@ -56,18 +85,35 @@ class file_input_adapter
: m_file(f)
{
JSON_ASSERT(m_file != nullptr);
lock();
}
// make class move-only
file_input_adapter(const file_input_adapter&) = delete;
file_input_adapter(file_input_adapter&&) noexcept = default;
file_input_adapter(file_input_adapter&& rhs) noexcept
: m_file(rhs.m_file)
{
// the lock is owned by the thread, not the adapter: hand it over
rhs.m_file = nullptr;
}
file_input_adapter& operator=(const file_input_adapter&) = delete;
file_input_adapter& operator=(file_input_adapter&&) = delete;
~file_input_adapter() = default;
~file_input_adapter()
{
unlock();
}
std::char_traits<char>::int_type get_character() noexcept
{
// the file is locked for the lifetime of the adapter, so the
// per-character lock of std::fgetc can be skipped
#if JSON_UNLOCKED_FILE_IO == 1
return getc_unlocked(m_file);
#elif JSON_UNLOCKED_FILE_IO == 2
return _fgetc_nolock(m_file);
#else
return std::fgetc(m_file);
#endif
}
// returns the number of characters successfully read
@@ -78,6 +124,32 @@ class file_input_adapter
}
private:
// Lock the file once for the whole parse instead of once per character.
// The lock is recursive, so fread() and the user's own stdio calls on the
// same thread keep working.
void lock() noexcept
{
#if JSON_UNLOCKED_FILE_IO == 1
flockfile(m_file);
#elif JSON_UNLOCKED_FILE_IO == 2
_lock_file(m_file);
#endif
}
void unlock() noexcept
{
// a moved-from adapter has no file and holds no lock
if (m_file == nullptr)
{
return;
}
#if JSON_UNLOCKED_FILE_IO == 1
funlockfile(m_file);
#elif JSON_UNLOCKED_FILE_IO == 2
_unlock_file(m_file);
#endif
}
/// the file pointer to read from
std::FILE* m_file;
};
@@ -127,15 +199,26 @@ class input_stream_adapter
input_stream_adapter& operator=(input_stream_adapter&) = delete;
input_stream_adapter& operator=(input_stream_adapter&&) = delete;
#if JSON_PRECISE_STREAM_POSITION
input_stream_adapter(input_stream_adapter&& rhs) noexcept
: is(rhs.is), sb(rhs.sb), lookahead(rhs.lookahead)
: is(rhs.is), sb(rhs.sb)
#if JSON_PRECISE_STREAM_POSITION
, lookahead(rhs.lookahead)
#endif
#if !JSON_DISABLE_STREAM_BULK_SCAN
, token_carry(std::move(rhs.token_carry))
, token_segment(rhs.token_segment)
, current_in_get_area(rhs.current_in_get_area)
, tracking_token(rhs.tracking_token)
#endif
{
rhs.is = nullptr;
rhs.sb = nullptr;
#if JSON_PRECISE_STREAM_POSITION
rhs.lookahead = false;
#endif
}
#if JSON_PRECISE_STREAM_POSITION
// Whether the character last returned by get_character() can be given back
// to the input with release_lookahead().
static constexpr bool supports_lookahead = true;
@@ -155,17 +238,41 @@ class input_stream_adapter
sb->sbumpc();
}
#if !JSON_DISABLE_STREAM_BULK_SCAN
// sgetc() refills the get area if it is exhausted
const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
if (JSON_HEDLEY_UNLIKELY(refill))
{
save_token_segment();
}
#endif
auto res = sb->sgetc();
// set eof manually, as we don't use the istream interface.
if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof()))
{
// there is nothing to step over next time
lookahead = false;
#if !JSON_DISABLE_STREAM_BULK_SCAN
current_in_get_area = false;
#endif
is->clear(is->rdstate() | std::ios::eofbit);
}
else
{
lookahead = true;
#if !JSON_DISABLE_STREAM_BULK_SCAN
if (JSON_HEDLEY_UNLIKELY(refill))
{
// the peeked character is at gptr(), unless the streambuf has
// no get area
after_refill(res, streambuf_access::get_ptr(sb) != streambuf_access::get_end(sb));
}
else
{
current_in_get_area = true;
}
#endif
}
return res;
}
@@ -179,13 +286,6 @@ class input_stream_adapter
lookahead = false;
}
#else
input_stream_adapter(input_stream_adapter&& rhs) noexcept
: is(rhs.is), sb(rhs.sb)
{
rhs.is = nullptr;
rhs.sb = nullptr;
}
// std::istream/std::streambuf use std::char_traits<char>::to_int_type, to
// ensure that std::char_traits<char>::eof() and the character 0xFF do not
// end up as the same value, e.g., 0xFFFFFFFF.
@@ -194,12 +294,37 @@ class input_stream_adapter
// stays consumed after parsing; see JSON_PRECISE_STREAM_POSITION.
std::char_traits<char>::int_type get_character()
{
#if !JSON_DISABLE_STREAM_BULK_SCAN
// sbumpc() refills the get area if it is exhausted
const bool refill = streambuf_access::get_ptr(sb) == streambuf_access::get_end(sb);
if (JSON_HEDLEY_UNLIKELY(refill))
{
save_token_segment();
}
#endif
auto res = sb->sbumpc();
// set eof manually, as we don't use the istream interface.
if (JSON_HEDLEY_UNLIKELY(res == std::char_traits<char>::eof()))
{
#if !JSON_DISABLE_STREAM_BULK_SCAN
current_in_get_area = false;
#endif
is->clear(is->rdstate() | std::ios::eofbit);
}
#if !JSON_DISABLE_STREAM_BULK_SCAN
else if (JSON_HEDLEY_UNLIKELY(refill))
{
// the consumed character is at gptr() - 1, unless the streambuf
// has no get area and returned it from uflow()
const char* const next = streambuf_access::get_ptr(sb);
after_refill(res, next != nullptr && next != streambuf_access::get_begin(sb));
}
else
{
current_in_get_area = true;
}
#endif
return res;
}
#endif
@@ -218,7 +343,165 @@ class input_stream_adapter
return res;
}
#if !JSON_DISABLE_STREAM_BULK_SCAN
// The lexer may scan the characters in the get area of the streambuf
// directly (SWAR fast paths). The get area is only a window into the
// input: it ends wherever the streambuf's buffer ends, and is refilled by
// the next get_character(). The lexer therefore keeps counting the
// position itself and treats the end of the window as "unknown", not as
// the end of the input.
static constexpr bool supports_bulk_scan = true;
static constexpr bool bulk_window = true;
// Pointer to the next unread character; only valid when
// bulk_remaining() > 0. The character before it is the one last returned
// by get_character().
const char* bulk_data() const
{
return current_end();
}
// Number of unread characters in the get area.
std::size_t bulk_remaining() const
{
if (!current_in_get_area)
{
return 0;
}
return static_cast<std::size_t>(streambuf_access::get_end(sb) - current_end());
}
// Consume @a n characters previously inspected via bulk_data(); the last
// of them becomes the character last returned by get_character().
void bulk_skip(std::size_t n)
{
JSON_ASSERT(n <= bulk_remaining());
// gbump() takes an int, but a get area (e.g., of a std::stringbuf) can
// be larger
constexpr auto max_bump = static_cast<std::size_t>((std::numeric_limits<int>::max)());
for (; n > max_bump; n -= max_bump)
{
streambuf_access::bump(sb, static_cast<int>(max_bump));
}
streambuf_access::bump(sb, static_cast<int>(n));
}
// The adapter keeps the current token for the lexer's error messages: the
// part in the get area is only remembered as a pointer, and copied out
// when the get area is about to be refilled.
static constexpr bool supports_token_tracking = true;
// Start a token with the characters read from now on. Until this is
// called, nothing is tracked (the binary readers never call it).
void begin_token() noexcept
{
tracking_token = true;
token_carry.clear();
token_segment = current_end();
}
// Start a new token with the character @a c last returned by
// get_character().
void mark_token_start(std::char_traits<char>::int_type c)
{
tracking_token = true;
token_carry.clear();
if (current_in_get_area)
{
token_segment = current_end() - 1;
}
else
{
token_segment = nullptr;
token_carry.push_back(std::char_traits<char>::to_char_type(c));
}
}
// Copy the characters read since mark_token_start() to @a out, without the
// last one if @a drop_last.
void copy_token(std::vector<char>& out, bool drop_last) const
{
out = token_carry;
if (token_segment != nullptr)
{
out.insert(out.end(), token_segment, current_end());
}
if (drop_last && !out.empty())
{
out.pop_back();
}
}
#endif
private:
#if !JSON_DISABLE_STREAM_BULK_SCAN
// Reads the protected get-area pointers of any std::streambuf. Naming the
// members through a derived class makes forming the member pointers
// accessible; calling them on another streambuf object is then ordinary
// member access through a pointer to member.
struct streambuf_access : std::streambuf
{
static const char* get_ptr(std::streambuf* s)
{
return (s->*(&streambuf_access::gptr))();
}
static const char* get_end(std::streambuf* s)
{
return (s->*(&streambuf_access::egptr))();
}
static const char* get_begin(std::streambuf* s)
{
return (s->*(&streambuf_access::eback))();
}
static void bump(std::streambuf* s, int n)
{
(s->*(&streambuf_access::gbump))(n);
}
};
// one past the character last returned by get_character(), if that is in
// the get area
const char* current_end() const
{
#if JSON_PRECISE_STREAM_POSITION
// the character is peeked at gptr() and not stepped over yet, unless
// it was given back with release_lookahead()
return streambuf_access::get_ptr(sb) + (lookahead ? 1 : 0);
#else
return streambuf_access::get_ptr(sb);
#endif
}
// the get area is about to be replaced: copy the token's part in it
void save_token_segment()
{
if (token_segment != nullptr)
{
token_carry.insert(token_carry.end(), token_segment, streambuf_access::get_end(sb));
token_segment = nullptr;
}
}
// character @a c was just read into a new get area (@a in_get_area) or
// returned without one
void after_refill(std::char_traits<char>::int_type c, bool in_get_area)
{
current_in_get_area = in_get_area;
if (!tracking_token)
{
return;
}
if (in_get_area)
{
token_segment = current_end() - 1;
}
else
{
token_carry.push_back(std::char_traits<char>::to_char_type(c));
}
}
#endif
#if JSON_PRECISE_STREAM_POSITION
// Step over the character last returned by get_character(). The character
// has already been peeked successfully, so for every streambuf with a get
@@ -240,6 +523,16 @@ class input_stream_adapter
/// whether get_character() peeked a character that is not consumed yet
bool lookahead = false;
#endif
#if !JSON_DISABLE_STREAM_BULK_SCAN
/// the part of the current token that was in earlier get areas
std::vector<char> token_carry{}; // NOLINT(readability-redundant-member-init)
/// start of the current token's part in the get area, or nullptr
const char* token_segment = nullptr;
/// whether the character last returned by get_character() is in the get area
bool current_in_get_area = false;
/// whether a token is tracked at all; the binary readers never start one
bool tracking_token = false;
#endif
};
#endif // JSON_NO_IO
@@ -297,6 +590,7 @@ class iterator_input_adapter
return result;
}
++eof_reads;
return char_traits<char_type>::eof();
}
@@ -306,6 +600,26 @@ class iterator_input_adapter
return static_cast<std::size_t>(std::distance(begin, current));
}
// number of get_character() calls so far, including those that returned
// EOF; the lexer derives its position from it (see lexer::lazy_position)
std::size_t get_read_count() const
{
return get_consumed_count() + eof_reads;
}
// number of newlines in the consumed range [0, last_index); @a line_start
// is set to the index after the last of them (0 if there is none); only
// valid when supports_seek
std::size_t count_consumed_lines(std::size_t last_index, std::size_t& line_start) const
{
const auto to = std::next(begin, static_cast<typename std::iterator_traits<IteratorType>::difference_type>(last_index));
const auto newline = char_traits<char_type>::to_char_type('\n');
using reverse_it = std::reverse_iterator<IteratorType>;
const auto last_newline = std::find(reverse_it(to), reverse_it(begin), newline);
line_start = static_cast<std::size_t>(std::distance(begin, last_newline.base()));
return static_cast<std::size_t>(std::count(begin, last_newline.base(), newline));
}
// append the already-consumed characters in the half-open range
// [first_index, last_index) to @a out; only valid when supports_seek
template<typename ContainerType>
@@ -422,6 +736,8 @@ class iterator_input_adapter
IteratorType begin;
IteratorType current;
SentinelType end;
/// number of get_character() calls that returned EOF
std::size_t eof_reads = 0;
template<typename BaseInputAdapter, size_t T>
friend struct wide_string_input_helper;
@@ -581,7 +897,7 @@ class wide_string_input_adapter
template<class T>
JSON_HEDLEY_NO_RETURN std::size_t get_elements(T* /*dest*/, std::size_t /*count*/ = 1)
{
JSON_THROW(parse_error::create(112, 1, "wide string type cannot be interpreted as binary data", nullptr));
JSON_THROW(parse_error::create(exception_id::unexpected_byte, 1, "wide string type cannot be interpreted as binary data", nullptr));
}
private:
@@ -793,7 +1109,7 @@ inline file_input_adapter input_adapter(std::FILE* file)
{
if (file == nullptr)
{
JSON_THROW(parse_error::create(101, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
JSON_THROW(parse_error::create(exception_id::syntax_error, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
}
return file_input_adapter(file);
}
@@ -802,7 +1118,7 @@ inline input_stream_adapter input_adapter(std::istream& stream)
{
if (stream.rdbuf() == nullptr)
{
JSON_THROW(parse_error::create(101, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
JSON_THROW(parse_error::create(exception_id::syntax_error, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
}
return input_stream_adapter(stream);
}
@@ -827,7 +1143,7 @@ contiguous_bytes_input_adapter input_adapter(CharT b)
{
if (b == nullptr)
{
JSON_THROW(parse_error::create(101, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
JSON_THROW(parse_error::create(exception_id::syntax_error, 0, "attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
}
auto length = std::strlen(reinterpret_cast<const char*>(b));
const auto* ptr = reinterpret_cast<const char*>(b);
include/nlohmann/detail/input/json_sax.hpp
+97 -80
View File
@@ -176,6 +176,34 @@ template<typename ArrayType>
inline void reserve_array(ArrayType& /*arr*/, std::size_t /*len*/, priority_tag<0> /*unused*/)
{}
/*!
@brief reports an object or array whose announced size exceeds max_size()
Shared by json_sax_dom_parser and json_sax_dom_callback_parser.
@param[in] sax the SAX parser to report the error to
@param[in] len the number of elements announced by the input, or unknown_size()
@param[in] kind "object" or "array"
@param[in] ref the object or array that was just created
@return whether parsing should continue (false after reporting out_of_range.408)
*/
template<typename SAX, typename BasicJsonType>
JSON_HEDLEY_NEVER_INLINE
bool container_too_large_error(SAX& sax, std::size_t len, const char* kind, BasicJsonType* ref)
{
return sax.parse_error(0, "", out_of_range::create(exception_id::container_too_large, concat("excessive ", kind, " size: ", std::to_string(len)), ref));
}
template<typename SAX, typename BasicJsonType>
bool check_container_size(SAX& sax, std::size_t len, const char* kind, BasicJsonType* ref)
{
if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref->max_size()))
{
return container_too_large_error(sax, len, kind, ref);
}
return true;
}
#if JSON_DIAGNOSTIC_POSITIONS
/*!
@brief set the diagnostic positions of a value the DOM SAX parsers just stored
@@ -185,6 +213,35 @@ befriends this struct, as the position members are private.
*/
struct diagnostic_positions
{
/*!
@param[in,out] v the object or array whose opening brace or bracket was just read
@param[in] lexer the lexer that read it, or nullptr to leave @a v alone
*/
template<typename BasicJsonType, typename LexerType>
static void set_container_start(BasicJsonType& v, LexerType* lexer)
{
if (lexer)
{
// Lexer has read the first character of the container, so
// subtract 1 from the position to get the correct start position.
v.start_position = lexer->get_chars_read_total() - 1;
}
}
/*!
@param[in,out] v the object or array whose closing brace or bracket was just read
@param[in] lexer the lexer that read it, or nullptr to leave @a v alone
*/
template<typename BasicJsonType, typename LexerType>
static void set_container_end(BasicJsonType& v, LexerType* lexer)
{
if (lexer)
{
// Lexer's position is past the closing brace or bracket, so set that as the end position.
v.end_position = lexer->get_chars_read_total();
}
}
/*!
@param[in,out] v the value that was just parsed
@param[in] lexer the lexer that read it, or nullptr to leave @a v alone
@@ -197,7 +254,7 @@ struct diagnostic_positions
// Lexer has read past the current field value, so set the end position to the current position.
// The start position will be set below based on the length of the string representation
// of the value.
v.end_position = lexer->get_position();
v.end_position = lexer->get_chars_read_total();
switch (v.type())
{
@@ -349,22 +406,11 @@ class json_sax_dom_parser
ref_stack.push_back(handle_value(BasicJsonType::value_t::object));
#if JSON_DIAGNOSTIC_POSITIONS
// Manually set the start position of the object here.
// Ensure this is after the call to handle_value to ensure correct start position.
if (m_lexer_ref)
{
// Lexer has read the first character of the object, so
// subtract 1 from the position to get the correct start position.
ref_stack.back()->start_position = m_lexer_ref->get_position() - 1;
}
diagnostic_positions::set_container_start(*ref_stack.back(), m_lexer_ref);
#endif
if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
{
return parse_error(0, "", out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
}
return true;
return check_container_size(*this, len, "object", ref_stack.back());
}
bool key(string_t& val)
@@ -383,11 +429,7 @@ class json_sax_dom_parser
JSON_ASSERT(ref_stack.back()->is_object());
#if JSON_DIAGNOSTIC_POSITIONS
if (m_lexer_ref)
{
// Lexer's position is past the closing brace, so set that as the end position.
ref_stack.back()->end_position = m_lexer_ref->get_position();
}
diagnostic_positions::set_container_end(*ref_stack.back(), m_lexer_ref);
#endif
ref_stack.back()->set_parents();
@@ -400,17 +442,13 @@ class json_sax_dom_parser
ref_stack.push_back(handle_value(BasicJsonType::value_t::array));
#if JSON_DIAGNOSTIC_POSITIONS
// Manually set the start position of the array here.
// Ensure this is after the call to handle_value to ensure correct start position.
if (m_lexer_ref)
{
ref_stack.back()->start_position = m_lexer_ref->get_position() - 1;
}
diagnostic_positions::set_container_start(*ref_stack.back(), m_lexer_ref);
#endif
if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
if (JSON_HEDLEY_UNLIKELY(!check_container_size(*this, len, "array", ref_stack.back())))
{
return parse_error(0, "", out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
return false;
}
if (len != detail::unknown_size())
@@ -427,11 +465,7 @@ class json_sax_dom_parser
JSON_ASSERT(ref_stack.back()->is_array());
#if JSON_DIAGNOSTIC_POSITIONS
if (m_lexer_ref)
{
// Lexer's position is past the closing bracket, so set that as the end position.
ref_stack.back()->end_position = m_lexer_ref->get_position();
}
diagnostic_positions::set_container_end(*ref_stack.back(), m_lexer_ref);
#endif
ref_stack.back()->set_parents();
@@ -611,21 +645,11 @@ class json_sax_dom_callback_parser
{
#if JSON_DIAGNOSTIC_POSITIONS
// Manually set the start position of the object here.
// Ensure this is after the call to handle_value to ensure correct start position.
if (m_lexer_ref)
{
// Lexer has read the first character of the object, so
// subtract 1 from the position to get the correct start position.
ref_stack.back()->start_position = m_lexer_ref->get_position() - 1;
}
diagnostic_positions::set_container_start(*ref_stack.back(), m_lexer_ref);
#endif
// check object limit
if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
{
return parse_error(0, "", out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
}
return check_container_size(*this, len, "object", ref_stack.back());
}
return true;
}
@@ -657,16 +681,19 @@ class json_sax_dom_callback_parser
if (keep && ref_stack.back())
{
auto& obj = *ref_stack.back()->m_data.m_value.object;
const auto it = obj.find(val);
if (it != obj.end())
// a single lookup: insert the placeholder, or find the existing member
const auto inserted = obj.emplace(val, discarded);
const auto it = inserted.first;
if (!inserted.second)
{
// this is a duplicate key (legal in JSON); remember its
// current value so it can be restored later if the new
// value is rejected by the callback, instead of being
// erased together with the discarded placeholder
duplicate_key_stash.emplace_back(&(it->second), it->second);
it->second = discarded;
}
object_element = &(obj[val] = discarded);
object_element = &(it->second);
}
return true;
@@ -695,11 +722,7 @@ class json_sax_dom_callback_parser
{
#if JSON_DIAGNOSTIC_POSITIONS
if (m_lexer_ref)
{
// Lexer's position is past the closing brace, so set that as the end position.
ref_stack.back()->end_position = m_lexer_ref->get_position();
}
diagnostic_positions::set_container_end(*ref_stack.back(), m_lexer_ref);
#endif
ref_stack.back()->set_parents();
@@ -710,13 +733,7 @@ class json_sax_dom_callback_parser
}
}
JSON_ASSERT(!ref_stack.empty());
JSON_ASSERT(!keep_stack.empty());
JSON_ASSERT(!container_key_stack.empty());
ref_stack.pop_back();
keep_stack.pop_back();
const string_t object_key = std::move(container_key_stack.back());
container_key_stack.pop_back();
const string_t object_key = pop_container();
if (!ref_stack.empty() && ref_stack.back() && ref_stack.back()->is_structured())
{
@@ -742,20 +759,13 @@ class json_sax_dom_callback_parser
{
#if JSON_DIAGNOSTIC_POSITIONS
// Manually set the start position of the array here.
// Ensure this is after the call to handle_value to ensure correct start position.
if (m_lexer_ref)
{
// Lexer has read the first character of the array, so
// subtract 1 from the position to get the correct start position.
ref_stack.back()->start_position = m_lexer_ref->get_position() - 1;
}
diagnostic_positions::set_container_start(*ref_stack.back(), m_lexer_ref);
#endif
// check array limit
if (JSON_HEDLEY_UNLIKELY(len != detail::unknown_size() && len > ref_stack.back()->max_size()))
if (JSON_HEDLEY_UNLIKELY(!check_container_size(*this, len, "array", ref_stack.back())))
{
return parse_error(0, "", out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
return false;
}
if (len != detail::unknown_size())
@@ -779,11 +789,7 @@ class json_sax_dom_callback_parser
{
#if JSON_DIAGNOSTIC_POSITIONS
if (m_lexer_ref)
{
// Lexer's position is past the closing bracket, so set that as the end position.
ref_stack.back()->end_position = m_lexer_ref->get_position();
}
diagnostic_positions::set_container_end(*ref_stack.back(), m_lexer_ref);
#endif
ref_stack.back()->set_parents();
@@ -809,13 +815,7 @@ class json_sax_dom_callback_parser
}
}
JSON_ASSERT(!ref_stack.empty());
JSON_ASSERT(!keep_stack.empty());
JSON_ASSERT(!container_key_stack.empty());
ref_stack.pop_back();
keep_stack.pop_back();
const string_t object_key = std::move(container_key_stack.back());
container_key_stack.pop_back();
const string_t object_key = pop_container();
// remove discarded value
if (!ref_stack.empty() && ref_stack.back())
@@ -902,6 +902,23 @@ class json_sax_dom_callback_parser
return string_t{};
}
/*!
@brief leave the object or array that end_object()/end_array() just closed
@return the key the container is stored under in its parent (see
container_key_stack)
*/
string_t pop_container()
{
JSON_ASSERT(!ref_stack.empty());
JSON_ASSERT(!keep_stack.empty());
JSON_ASSERT(!container_key_stack.empty());
ref_stack.pop_back();
keep_stack.pop_back();
string_t object_key = std::move(container_key_stack.back());
container_key_stack.pop_back();
return object_key;
}
/*!
@brief remove the discarded value the callback rejected from its parent,
unless it is a duplicate key's slot with a stashed previous value, in
include/nlohmann/detail/input/lexer.hpp
+351 -40
View File
@@ -17,6 +17,7 @@
#include <utility> // move
#include <vector> // vector
#include <nlohmann/detail/bit_ops.hpp>
#include <nlohmann/detail/input/input_adapters.hpp>
#include <nlohmann/detail/input/number_parse.hpp>
#include <nlohmann/detail/input/position_t.hpp>
@@ -165,6 +166,43 @@ constexpr bool input_adapter_supports_bulk_scan(std::false_type /*detected*/)
return false;
}
// Detect whether an input adapter keeps the current token itself and can
// hand it out on demand (see input_stream_adapter::supports_token_tracking),
// so the lexer need not copy every scanned character into token_string.
template<typename InputAdapterType>
using detect_supports_token_tracking = decltype(InputAdapterType::supports_token_tracking);
template<typename InputAdapterType>
constexpr bool input_adapter_supports_token_tracking(std::true_type /*detected*/)
{
return InputAdapterType::supports_token_tracking;
}
template<typename InputAdapterType>
constexpr bool input_adapter_supports_token_tracking(std::false_type /*detected*/)
{
return false;
}
// Detect whether the contiguous block of a bulk-scan adapter is only a window
// into the input (see input_stream_adapter::bulk_window): its end is not the
// end of the input, so a token that touches it must be finished character by
// character.
template<typename InputAdapterType>
using detect_bulk_window = decltype(InputAdapterType::bulk_window);
template<typename InputAdapterType>
constexpr bool input_adapter_bulk_window(std::true_type /*detected*/)
{
return InputAdapterType::bulk_window;
}
template<typename InputAdapterType>
constexpr bool input_adapter_bulk_window(std::false_type /*detected*/)
{
return false;
}
/*!
@brief lexical analysis
@@ -183,9 +221,29 @@ class lexer : public lexer_base<BasicJsonType>
/// whether the last read token can be reconstructed from the input adapter
/// on demand (in error paths) instead of being copied on every scanned
/// character; see input_adapter_supports_seek
static constexpr bool lazy_token_string =
static constexpr bool seekable =
input_adapter_supports_seek<InputAdapterType>(is_detected<detect_supports_seek, InputAdapterType> {});
/// whether the adapter keeps the token itself (mark_token_start() /
/// copy_token()); see input_adapter_supports_token_tracking
static constexpr bool adapter_token =
!seekable && input_adapter_supports_token_tracking<InputAdapterType>(is_detected<detect_supports_token_tracking, InputAdapterType> {});
/// whether the last read token is obtained from the input adapter on
/// demand (in error paths) instead of being copied on every scanned
/// character: seekable adapters reconstruct it from the consumed input,
/// token-tracking adapters keep it themselves
static constexpr bool lazy_token_string = seekable || adapter_token;
/// whether the read position is derived from the input adapter on demand
/// instead of being counted on every scanned character. Seekable adapters
/// know how much input they consumed and can revisit it, so
/// chars_read_total is the adapter's read count (minus a pending unget),
/// and line and column are recomputed from the consumed input only when
/// get_position() is called (errors). Counting per character kept two
/// increments and a newline check in the hot path of every get().
static constexpr bool lazy_position = seekable;
/// whether a simulated unget can be passed on to the input adapter, which
/// then leaves the character in the input; see
/// input_adapter_supports_lookahead
@@ -193,12 +251,17 @@ class lexer : public lexer_base<BasicJsonType>
input_adapter_supports_lookahead<InputAdapterType>(is_detected<detect_supports_lookahead, InputAdapterType> {});
/// whether string scanning may bulk-consume runs of ordinary characters
/// directly from a contiguous input buffer (SWAR fast path). This requires
/// the token to be reconstructible lazily (lazy_token_string), so bypassing
/// the per-character capture in get() cannot lose error diagnostics.
/// directly from a contiguous input buffer (SWAR fast path). Without
/// lazy_token_string / lazy_position, the bulk paths copy the consumed
/// characters into token_string and advance the position counters
/// themselves (see bulk_consume).
static constexpr bool bulk_scan =
lazy_token_string
&& input_adapter_supports_bulk_scan<InputAdapterType>(is_detected<detect_supports_bulk_scan, InputAdapterType> {});
input_adapter_supports_bulk_scan<InputAdapterType>(is_detected<detect_supports_bulk_scan, InputAdapterType> {});
/// whether the contiguous block is only a window into the input, so that
/// its end does not end a token; see input_adapter_bulk_window
static constexpr bool bulk_window =
input_adapter_bulk_window<InputAdapterType>(is_detected<detect_bulk_window, InputAdapterType> {});
public:
using token_type = typename lexer_base<BasicJsonType>::token_type;
@@ -207,7 +270,11 @@ class lexer : public lexer_base<BasicJsonType>
: ia(std::move(adapter))
, ignore_comments(ignore_comments_)
, discard_number_values(discard_number_values_)
{}
{
// the token string of an error before the first token is everything
// read so far
begin_token(std::integral_constant<bool, adapter_token> {});
}
// deleted because of pointer members
lexer(const lexer&) = delete;
@@ -221,6 +288,41 @@ class lexer : public lexer_base<BasicJsonType>
// scan functions
/////////////////////
/// contiguous input: try to decode the 4 hex digits following `\\u`
/// directly from the input buffer via hex_codepoint(), instead of 4 calls
/// to get(). On success, advances the adapter exactly as those 4 get()
/// calls would (including the position and token bookkeeping of a
/// streaming adapter, see bulk_consume) and leaves @a current holding the last of
/// the 4 digits, just as the last such get() would; the codepoint is
/// written to @a out. Makes no state change and returns false for a
/// pending unget, fewer than 4 remaining bytes, or any of the 4 bytes not
/// being a hex digit, so the caller falls back unchanged to the
/// per-character loop, which then reports the same diagnostic (stopping
/// at the first invalid digit) as before this optimization.
bool get_codepoint_bulk(std::true_type /*bulk*/, int& out)
{
if (next_unget || ia.bulk_remaining() < 4)
{
return false;
}
const char_type* const raw = ia.bulk_data();
const int codepoint = hex_codepoint(reinterpret_cast<const unsigned char*>(raw));
if (codepoint < 0)
{
return false;
}
bulk_consume(reinterpret_cast<const char*>(raw), 4);
current = char_traits<char_type>::to_int_type(raw[3]);
out = codepoint;
return true;
}
/// streaming input: no bulk fast path
bool get_codepoint_bulk(std::false_type /*bulk*/, int& /*out*/) const noexcept
{
return false;
}
/*!
@brief get codepoint from 4 hex characters following `\\u`
@@ -240,6 +342,14 @@ class lexer : public lexer_base<BasicJsonType>
{
// this function only makes sense after reading `\u`
JSON_ASSERT(current == 'u');
// contiguous input: decode all 4 hex digits directly from the buffer
int fast_codepoint = 0;
if (get_codepoint_bulk(std::integral_constant<bool, bulk_scan> {}, fast_codepoint))
{
return fast_codepoint;
}
int codepoint = 0;
const auto factors = { 12u, 8u, 4u, 0u };
@@ -330,11 +440,36 @@ class lexer : public lexer_base<BasicJsonType>
return;
}
token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), pos);
ia.bulk_skip(pos);
// the run contains no newline (all bytes < 0x20 are treated as special),
// so only the flat character counters advance
position.chars_read_total += pos;
position.chars_read_current_line += pos;
bulk_consume(reinterpret_cast<const char*>(data), pos);
}
/// consume @a n characters at @a data (the adapter's bulk_data()) and do
/// the bookkeeping get() would have done for them; the characters are
/// never newlines
void bulk_consume(const char* data, std::size_t n)
{
bulk_track_position(n, std::integral_constant<bool, lazy_position> {});
bulk_track_token(data, n, std::integral_constant<bool, lazy_token_string> {});
ia.bulk_skip(n);
}
/// seekable adapter: the position is derived from the adapter
void bulk_track_position(std::size_t /*n*/, std::true_type /*lazy*/) const noexcept {}
/// streaming adapter: count the characters
void bulk_track_position(std::size_t n, std::false_type /*lazy*/) noexcept
{
position.chars_read_total += n;
position.chars_read_current_line += n;
}
/// the token is obtained from the adapter
void bulk_track_token(const char* /*data*/, std::size_t /*n*/, std::true_type /*lazy*/) const noexcept {}
/// streaming adapter: capture the characters
void bulk_track_token(const char* data, std::size_t n, std::false_type /*lazy*/)
{
token_string.insert(token_string.end(), data, data + n);
}
/// streaming input: no bulk fast path
@@ -1044,9 +1179,11 @@ class lexer : public lexer_base<BasicJsonType>
token_type::parse_error otherwise
@note The scanner is independent of the current locale: token_buffer
always holds `.`. Only the std::strtod fallback of convert_number()
depends on the locale, and it looks up the decimal point right
before converting (see detail::convert_float_locale_aware()).
always holds `.`. The conversion of float and double does not use
the locale either. Only the std::strtold fallback of
convert_number() for long double formats other than binary64
depends on it, and it looks up the decimal point right before
converting (see detail::convert_float_locale_aware()).
*/
token_type scan_number() // lgtm [cpp/use-of-goto] `goto` is used in this function to implement the number-parsing state machine described above. By design, any finite input will eventually reach the "done" state or return token_type::parse_error. In each intermediate state, 1 byte of the input is appended to the token_buffer vector, and only the already initialized variables token_buffer, number_type, and error_message are manipulated.
{
@@ -1059,7 +1196,7 @@ class lexer : public lexer_base<BasicJsonType>
// offset just past the last mantissa byte in token_buffer (i.e. the
// index of 'e'/'E', or the whole token when there is no exponent).
// convert_number() uses it to count significant digits; npos means
// convert_number() uses it to split the token; npos means
// "not seen an exponent yet" and is resolved at scan_number_done
std::size_t mantissa_end = std::string::npos;
@@ -1389,8 +1526,8 @@ scan_number_done:
@param[in] mantissa_end offset just past the last mantissa byte in
token_buffer (the index of 'e'/'E', or
token_buffer.size() when there is no exponent);
used to skip Clinger's fast path when it cannot
possibly succeed - see detail::mantissa_fits_clinger()
with decimal_point_position, it locates the parts
of a float token without scanning it again
*/
token_type convert_number(token_type number_type, std::size_t mantissa_end)
{
@@ -1444,10 +1581,11 @@ scan_number_done:
}
// this code is reached if we parse a floating-point number or if an
// integer conversion above overflowed. Prefer std::from_chars
// (Eisel-Lemire, locale-independent, correctly rounded) when available;
// otherwise the exact Clinger fast path (double only); otherwise the
// locale-aware strtof/strtod/strtold.
// integer conversion above overflowed. float and double (and long
// double where it is binary64) are converted by the library itself,
// correctly rounded and independent of the locale; other long double
// formats use std::from_chars when available, otherwise the
// locale-aware strtold.
if (convert_float_fast(num_begin, num_end, decimal_point_position, mantissa_end, value_float))
{
return token_type::value_float;
@@ -1549,6 +1687,10 @@ scan_number_done:
}
}
const std::size_t len = i;
if (number_may_continue(len == avail, std::integral_constant<bool, bulk_window> {}))
{
return token_type::uninitialized;
}
// reset() records where this token starts (for diagnostics), so it has
// to run before the input position advances below
@@ -1566,9 +1708,8 @@ scan_number_done:
const token_type integer_result = convert_integer(number_type, data, data + len);
if (JSON_HEDLEY_LIKELY(integer_result != token_type::uninitialized))
{
ia.bulk_skip(len - 1);
position.chars_read_total += (len - 1);
position.chars_read_current_line += (len - 1);
bulk_consume(data + 1, len - 1);
read_number_terminator(std::integral_constant<bool, bulk_window> {});
return integer_result;
}
// The value does not fit an integer, so this token converts as a
@@ -1584,13 +1725,37 @@ scan_number_done:
token_buffer.append(reinterpret_cast<const typename string_t::value_type*>(data), len);
decimal_point_position = dot_index;
ia.bulk_skip(len - 1);
position.chars_read_total += (len - 1);
position.chars_read_current_line += (len - 1);
bulk_consume(data + 1, len - 1);
read_number_terminator(std::integral_constant<bool, bulk_window> {});
return convert_number(number_type, mantissa_end);
}
/// window adapter: a number that reaches the end of the window may continue
/// after it, so scan_number() has to read it character by character
static constexpr bool number_may_continue(bool at_end, std::true_type /*window*/) noexcept
{
return at_end;
}
/// the end of the block is the end of the input, which ends the number
static constexpr bool number_may_continue(bool /*at_end*/, std::false_type /*window*/) noexcept
{
return false;
}
/// window adapter: read the character after a bulk-scanned number and unget
/// it, as scan_number() does. The adapter is a stream that is handed back to
/// the user, who must find the same input consumed either way.
void read_number_terminator(std::true_type /*window*/)
{
get();
unget();
}
/// the input is not handed back, so the terminator can stay unread
void read_number_terminator(std::false_type /*window*/) const noexcept {}
/// contiguous input: try the number fast path, else the byte-path scanner
token_type scan_number_dispatch(std::true_type /*bulk*/)
{
@@ -1637,7 +1802,7 @@ scan_number_done:
#if JSON_DIAGNOSTIC_POSITIONS
// the first character of the token has already been read, hence the -1
token_start_position = position.chars_read_total - 1;
token_start_position = get_chars_read_total() - 1;
#endif
note_token_start(std::integral_constant<bool, lazy_token_string> {});
@@ -1646,11 +1811,30 @@ scan_number_done:
/// seekable adapter: remember where the current token starts so it can be
/// reconstructed from the input on error; current has already been
/// consumed, hence the -1
void note_token_start(std::true_type /*lazy*/) noexcept
void note_token_start(std::true_type /*lazy*/)
{
note_token_start_lazy(std::integral_constant<bool, adapter_token> {});
}
void note_token_start_lazy(std::false_type /*adapter_token*/) noexcept
{
token_string_start = ia.get_consumed_count() - 1;
}
/// token-tracking adapter: start tracking the token at the first character
void begin_token(std::true_type /*adapter_token*/) noexcept
{
ia.begin_token();
}
void begin_token(std::false_type /*adapter_token*/) const noexcept {}
/// token-tracking adapter: the token starts with the current character
void note_token_start_lazy(std::true_type /*adapter_token*/)
{
ia.mark_token_start(current);
}
/// streaming adapter: start copying the token eagerly, beginning with the
/// already-read first character
void note_token_start(std::false_type /*lazy*/) noexcept
@@ -1690,6 +1874,15 @@ scan_number_done:
/// per-character position counters (line-count-on-'\n' bookkeeping is
/// handled afterwards, in track_after_read(), once `current` is known)
void advance_position() noexcept
{
advance_position_impl(std::integral_constant<bool, lazy_position> {});
}
/// seekable adapter: the position is derived from the adapter on demand
void advance_position_impl(std::true_type /*lazy*/) const noexcept {}
/// streaming adapter: count the character
void advance_position_impl(std::false_type /*lazy*/) noexcept
{
++position.chars_read_total;
++position.chars_read_current_line;
@@ -1703,7 +1896,16 @@ scan_number_done:
// seekable adapters reconstruct the token lazily on error (see
// get_token_string), so the eager per-character copy is skipped
capture_char(std::integral_constant<bool, lazy_token_string> {});
track_newline(std::integral_constant<bool, lazy_position> {});
return current;
}
/// seekable adapter: lines are counted on demand in get_position()
void track_newline(std::true_type /*lazy*/) const noexcept {}
/// streaming adapter: start a new line after reading a newline
void track_newline(std::false_type /*lazy*/) noexcept
{
if (current == '\n')
{
++position.lines_read;
@@ -1712,8 +1914,6 @@ scan_number_done:
chars_read_before_newline = position.chars_read_current_line;
position.chars_read_current_line = 0;
}
return current;
}
/*!
@@ -1757,12 +1957,22 @@ scan_number_done:
We implement unget by setting variable next_unget to true. The input is not
changed - we just simulate ungetting by modifying chars_read_total,
chars_read_current_line, and token_string. The next call to get() will
behave as if the unget character is read again.
behave as if the unget character is read again. With lazy_position, the
pending next_unget is all get_chars_read_total() needs.
*/
void unget()
{
next_unget = true;
unget_position(std::integral_constant<bool, lazy_position> {});
uncapture_char(std::integral_constant<bool, lazy_token_string> {});
}
/// seekable adapter: get_chars_read_total() accounts for next_unget
void unget_position(std::true_type /*lazy*/) const noexcept {}
/// streaming adapter: step the counters back over the ungotten character
void unget_position(std::false_type /*lazy*/) noexcept
{
--position.chars_read_total;
// in case we "unget" a newline, we have to also decrement the lines_read
@@ -1785,8 +1995,6 @@ scan_number_done:
{
--position.chars_read_current_line;
}
uncapture_char(std::integral_constant<bool, lazy_token_string> {});
}
/// adapter without lookahead: nothing to do (see release_lookahead)
@@ -1857,10 +2065,21 @@ scan_number_done:
// diagnostics
/////////////////////
/// return position of last read token
constexpr position_t get_position() const noexcept
/*!
@brief return the number of characters read so far
Unlike get_position(), this is O(1) for all adapters, so it may be called
for every value (JSON_DIAGNOSTIC_POSITIONS).
*/
std::size_t get_chars_read_total() const noexcept
{
return position;
return get_chars_read_total_impl(std::integral_constant<bool, lazy_position> {});
}
/// return position of last read token
position_t get_position() const
{
return get_position_impl(std::integral_constant<bool, lazy_position> {});
}
/*!
@@ -1897,8 +2116,59 @@ scan_number_done:
}
#endif
private:
/// seekable adapter: every get() either read from the adapter (including
/// reads at EOF, which get() counts as characters as well) or replayed an
/// ungotten character, so the count is the adapter's read count minus a
/// still pending unget
std::size_t get_chars_read_total_impl(std::true_type /*lazy*/) const noexcept
{
return ia.get_read_count() - (next_unget ? 1u : 0u);
}
/// streaming adapter: the counter is maintained by get() and unget()
std::size_t get_chars_read_total_impl(std::false_type /*lazy*/) const noexcept
{
return position.chars_read_total;
}
/// seekable adapter: count the lines in the consumed input; O(input read
/// so far), but only called on errors
position_t get_position_impl(std::true_type /*lazy*/) const
{
position_t result;
result.chars_read_total = get_chars_read_total();
// reads at EOF count as characters but are not part of the input
const std::size_t consumed = (std::min)(result.chars_read_total, ia.get_consumed_count());
std::size_t line_start = 0;
result.lines_read = ia.count_consumed_lines(consumed, line_start);
result.chars_read_current_line = result.chars_read_total - line_start;
return result;
}
/// streaming adapter: the position is maintained by get() and unget()
position_t get_position_impl(std::false_type /*lazy*/) const noexcept
{
return position;
}
public:
/// seekable adapter: rebuild the last read token from the input on demand
const std::vector<char_type>& collect_token_chars(std::vector<char_type>& out, std::true_type /*lazy*/) const
{
return collect_token_chars_lazy(out, std::integral_constant<bool, adapter_token> {});
}
/// token-tracking adapter: the adapter hands out everything read since
/// mark_token_start(), except a pending unget (see below)
const std::vector<char_type>& collect_token_chars_lazy(std::vector<char_type>& out, std::true_type /*adapter_token*/) const
{
const bool pending_real_unget = next_unget && current != char_traits<char_type>::eof();
ia.copy_token(out, pending_real_unget);
return out;
}
const std::vector<char_type>& collect_token_chars_lazy(std::vector<char_type>& out, std::false_type /*adapter_token*/) const
{
// a pending unget of a real (non-EOF) character means that character
// was consumed from the input but is not part of the token; EOF is
@@ -2004,15 +2274,56 @@ scan_number_done:
// into one that reloads the pointer from memory every character
do
{
if (current == '\n')
{
skip_indentation(std::integral_constant<bool, bulk_scan> {});
}
get_ignoring_pending_unget();
}
while (current_is_whitespace());
}
/*!
@brief contiguous input: skip the space indentation that follows a newline
8 bytes at a time
Pretty-printed JSON indents every line with a run of spaces, which the loop
in skip_whitespace() would otherwise read one character at a time. The
spaces are skipped 8 bytes at a time; the last 7 bytes of the input and any
other whitespace are left to that loop. Skipping bypasses get();
bulk_consume() does its bookkeeping.
*/
void skip_indentation(std::true_type /*bulk*/)
{
JSON_ASSERT(!next_unget);
const std::size_t remaining = ia.bulk_remaining();
if (remaining < 8)
{
return;
}
const char* const data = reinterpret_cast<const char*>(ia.bulk_data());
std::size_t pos = 0;
for (; pos + 8 <= remaining; pos += 8)
{
// little-endian, so the first byte is the lowest
const std::uint64_t non_space = read_eight_bytes(data + pos) ^ 0x2020202020202020ull;
if (non_space != 0)
{
// skip the spaces before the first other byte of this word
pos += static_cast<std::size_t>(count_trailing_zeros(non_space)) / 8;
break;
}
}
bulk_consume(data, pos);
}
/// streaming input: no bulk fast path
void skip_indentation(std::false_type /*bulk*/) const noexcept {}
token_type scan()
{
// initially, skip the BOM
if (position.chars_read_total == 0 && !skip_bom())
if (get_chars_read_total() == 0 && !skip_bom())
{
error_message = "invalid BOM; must be 0xEF 0xBB 0xBF if given";
return token_type::parse_error;
@@ -2039,7 +2350,7 @@ scan_number_done:
token_type scan_expecting(token_type expected_type)
{
JSON_ASSERT(expected_type == token_type::name_separator || expected_type == token_type::value_separator);
JSON_ASSERT(position.chars_read_total > 0);
JSON_ASSERT(get_chars_read_total() > 0);
const char_int_type expected_char = static_cast<unsigned char>((expected_type == token_type::name_separator) ? ':' : ',');
skip_whitespace();
if (JSON_HEDLEY_LIKELY(current == expected_char))
include/nlohmann/detail/input/number_parse.hpp
+725 -386
View File
File diff suppressed because it is too large. Load diff
include/nlohmann/detail/input/parser.hpp
+31 -40
View File
@@ -156,9 +156,7 @@ class parser
// strict mode: next byte must be EOF
if (get_token() != token_type::end_of_input)
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_of_input, "value"), nullptr));
return syntax_error(*sax, exception_message(token_type::end_of_input, "value"));
}
}
else
@@ -197,10 +195,7 @@ class parser
// in strict mode, input must be completely read
if (get_token() != token_type::end_of_input)
{
sdp.parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(),
exception_message(token_type::end_of_input, "value"), nullptr));
syntax_error(sdp, exception_message(token_type::end_of_input, "value"));
}
}
else
@@ -250,9 +245,7 @@ class parser
// parse key
if (JSON_HEDLEY_UNLIKELY(last_token != token_type::value_string))
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::value_string, "object key"), nullptr));
return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
}
if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
{
@@ -262,9 +255,7 @@ class parser
// parse separator (:)
if (JSON_HEDLEY_UNLIKELY(!get_token_expecting(token_type::name_separator)))
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::name_separator, "object separator"), nullptr));
return syntax_error(*sax, exception_message(token_type::name_separator, "object separator"));
}
// remember we are now inside an object
@@ -307,7 +298,7 @@ class parser
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
out_of_range::create(406, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr));
out_of_range::create(exception_id::number_overflow, concat("number overflow parsing '", m_lexer.get_token_string(), '\''), nullptr));
}
if (JSON_HEDLEY_UNLIKELY(!sax->number_float(res, m_lexer.get_string())))
@@ -375,23 +366,16 @@ class parser
case token_type::parse_error:
{
// using "uninitialized" to avoid an "expected" message
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::uninitialized, "value"), nullptr));
return syntax_error(*sax, exception_message(token_type::uninitialized, "value"));
}
case token_type::end_of_input:
{
if (JSON_HEDLEY_UNLIKELY(m_lexer.get_position().chars_read_total == 1))
if (JSON_HEDLEY_UNLIKELY(m_lexer.get_chars_read_total() == 1))
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(),
"attempting to parse an empty input; check that your input string or stream contains the expected JSON", nullptr));
return syntax_error(*sax, "attempting to parse an empty input; check that your input string or stream contains the expected JSON");
}
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr));
return syntax_error(*sax, exception_message(token_type::literal_or_value, "value"));
}
case token_type::uninitialized:
case token_type::end_array:
@@ -401,9 +385,7 @@ class parser
case token_type::literal_or_value:
default: // the last token was unexpected
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::literal_or_value, "value"), nullptr));
return syntax_error(*sax, exception_message(token_type::literal_or_value, "value"));
}
}
}
@@ -454,9 +436,7 @@ class parser
continue;
}
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_array, "array"), nullptr));
return syntax_error(*sax, exception_message(token_type::end_array, "array"));
}
// states.back() is false -> object
@@ -473,9 +453,7 @@ class parser
// parse key
if (JSON_HEDLEY_UNLIKELY(last_token != token_type::value_string))
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::value_string, "object key"), nullptr));
return syntax_error(*sax, exception_message(token_type::value_string, "object key"));
}
if (JSON_HEDLEY_UNLIKELY(!sax->key(m_lexer.get_string())))
@@ -486,9 +464,7 @@ class parser
// parse separator (:)
if (JSON_HEDLEY_UNLIKELY(!get_token_expecting(token_type::name_separator)))
{
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::name_separator, "object separator"), nullptr));
return syntax_error(*sax, exception_message(token_type::name_separator, "object separator"));
}
// parse values
@@ -516,9 +492,7 @@ class parser
continue;
}
return sax->parse_error(m_lexer.get_position(),
m_lexer.get_token_string(),
parse_error::create(101, m_lexer.get_position(), exception_message(token_type::end_object, "object"), nullptr));
return syntax_error(*sax, exception_message(token_type::end_object, "object"));
}
}
@@ -535,6 +509,23 @@ class parser
return (last_token = m_lexer.scan_expecting(expected_type)) == expected_type;
}
/*!
@brief reports a syntax error at the current token (parse_error.101)
@param[in] sax the SAX parser to report the error to
@param[in] message the error message
@return the result of the SAX parser's parse_error()
*/
template<typename SAX>
bool syntax_error(SAX& sax, const std::string& message)
{
// MSVC 2015 reports C4100 (unreferenced parameter) when SAX::parse_error is static
static_cast<void>(sax);
// computing the position is O(input read so far) for seekable input
const position_t position = m_lexer.get_position();
return sax.parse_error(position, m_lexer.get_token_string(),
parse_error::create(exception_id::syntax_error, position, message, nullptr));
}
std::string exception_message(const token_type expected, const std::string& context)
{
std::string error_msg = "syntax error ";
include/nlohmann/detail/input/pow5_table.hpp
+4
View File
@@ -22,6 +22,10 @@ namespace detail
constexpr std::int64_t pow5_128_smallest_power = -342;
constexpr std::int64_t pow5_128_largest_power = 308;
// every entry of pow5_128() holds two 64-bit halves of 5^q, one per covered power of 5
static_assert((pow5_128_largest_power - pow5_128_smallest_power + 1) * 2 == 1302,
"pow5_128_smallest_power/pow5_128_largest_power must match the size of the pow5_128() table");
/*!
@brief 128-bit approximations of 5^q for q in [-342, 308]
include/nlohmann/detail/input/string_scan.hpp
+70 -29
View File
@@ -8,10 +8,12 @@
#pragma once
#include <array> // array
#include <cstddef> // size_t
#include <cstdint> // uint64_t
#include <cstdint> // uint64_t, uint8_t
#include <cstring> // memcpy
#include <nlohmann/detail/bit_ops.hpp>
#include <nlohmann/detail/macro_scope.hpp>
// Optional SIMD backend for bulk UTF-8 validation. This is an opt-in external
@@ -69,18 +71,12 @@ inline std::size_t find_string_special(const unsigned char* data, std::size_t n)
std::size_t i = 0;
for (; i + 8 <= n; i += 8)
{
std::uint64_t word = 0;
std::memcpy(&word, data + i, sizeof(word));
if (swar_string_special(word) != 0)
const std::uint64_t special = swar_string_special(read_eight_bytes(data + i));
if (special != 0)
{
// a special byte is in this word; locate it (endian-agnostic)
for (std::size_t j = 0; j < 8; ++j)
{
if (is_string_special(data[i + j]))
{
return i + j;
}
}
// the lowest flagged byte is the first special one: the borrows of
// the subtractions can only flag bytes above a true hit
return i + (static_cast<std::size_t>(count_trailing_zeros(special)) / 8);
}
}
for (; i < n; ++i)
@@ -114,8 +110,7 @@ inline std::size_t find_ascii_copyable_run(const unsigned char* data, std::size_
std::size_t i = 0;
for (; i + 8 <= n; i += 8)
{
std::uint64_t v = 0;
std::memcpy(&v, data + i, sizeof(v));
const std::uint64_t v = read_eight_bytes(data + i);
const std::uint64_t q = v ^ 0x2222222222222222ull; // '"' (0x22)
const std::uint64_t b = v ^ 0x5C5C5C5C5C5C5C5Cull; // '\\' (0x5C)
const std::uint64_t d = v ^ 0x7F7F7F7F7F7F7F7Full; // DEL (0x7F)
@@ -126,7 +121,9 @@ inline std::size_t find_ascii_copyable_run(const unsigned char* data, std::size_
| (v & high); // >= 0x80
if (stop != 0)
{
break;
// the lowest flagged byte is the first one to stop at (see
// find_string_special())
return i + (static_cast<std::size_t>(count_trailing_zeros(stop)) / 8);
}
}
for (; i < n; ++i)
@@ -253,12 +250,18 @@ inline std::size_t scalar_string_bulk_run(const unsigned char* data, std::size_t
{
break; // end of buffer, or a quote/escape/control byte
}
const std::size_t seq = validate_one_utf8(data + pos, n - pos);
if (seq == 0)
// a run of multi-byte sequences (e.g. CJK text) is validated sequence
// by sequence without searching for the next special byte in between
do
{
break; // ill-formed or truncated: let the byte path diagnose it
const std::size_t seq = validate_one_utf8(data + pos, n - pos);
if (seq == 0)
{
return pos; // ill-formed or truncated: let the byte path diagnose it
}
pos += seq;
}
pos += seq;
while (pos < n && data[pos] >= 0x80u);
}
return pos;
}
@@ -273,8 +276,7 @@ inline std::size_t find_string_delimiter(const unsigned char* data, std::size_t
std::size_t i = 0;
for (; i + 8 <= n; i += 8)
{
std::uint64_t v = 0;
std::memcpy(&v, data + i, sizeof(v));
const std::uint64_t v = read_eight_bytes(data + i);
const std::uint64_t q = v ^ 0x2222222222222222ull;
const std::uint64_t b = v ^ 0x5C5C5C5C5C5C5C5Cull;
const std::uint64_t hit = ((q - ones) & ~q & high)
@@ -282,14 +284,8 @@ inline std::size_t find_string_delimiter(const unsigned char* data, std::size_t
| ((v - 0x2020202020202020ull) & ~v & high);
if (hit != 0)
{
for (std::size_t j = 0; j < 8; ++j)
{
const unsigned char c = data[i + j];
if (c == '\"' || c == '\\' || c < 0x20u)
{
return i + j;
}
}
// the lowest flagged byte is the first delimiter (see find_string_special())
return i + (static_cast<std::size_t>(count_trailing_zeros(hit)) / 8);
}
}
for (; i < n; ++i)
@@ -320,5 +316,50 @@ inline std::size_t string_bulk_run(const unsigned char* data, std::size_t n) noe
return scalar_string_bulk_run(data, n);
}
// Decode the 4 hex digits at [data, data+4) - the digits following a `\u`
// escape - into a codepoint 0x0000..0xFFFF via one table lookup per byte
// (after yyjson's read_hex_u16), or return -1 if any of the 4 bytes is not a
// hex digit ('0'..'9', 'A'..'F', 'a'..'f'). The caller must already have
// checked that 4 bytes are available; used by lexer::get_codepoint()'s
// contiguous fast path. On -1 it falls back to the byte-at-a-time loop, which
// stops at the first invalid digit, so the reported error and position are
// unaffected by this fast path.
inline int hex_codepoint(const unsigned char* data) noexcept
{
static const std::array<std::uint8_t, 256> hex_digit_table = // NOLINT(cppcoreguidelines-avoid-non-const-global-variables)
{
{
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 00..0F
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 10..1F
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 20..2F
0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 30..3F ('0'..'9')
0xFF, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 40..4F ('A'..'F')
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 50..5F
0xFF, 0x0A, 0x0B, 0x0C, 0x0D, 0x0E, 0x0F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 60..6F ('a'..'f')
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 70..7F
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 80..8F
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // 90..9F
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // A0..AF
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // B0..BF
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // C0..CF
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // D0..DF
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, // E0..EF
0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF // F0..FF
}
};
const std::uint8_t d0 = hex_digit_table[data[0]];
const std::uint8_t d1 = hex_digit_table[data[1]];
const std::uint8_t d2 = hex_digit_table[data[2]];
const std::uint8_t d3 = hex_digit_table[data[3]];
// every valid digit is <= 0xF; the combined OR only exceeds it if at
// least one of the four bytes was not a hex digit (looked up as 0xFF)
if ((d0 | d1 | d2 | d3) > 0x0F)
{
return -1;
}
return (d0 << 12) | (d1 << 8) | (d2 << 4) | d3;
}
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/iterators/iter_impl.hpp
+83 -142
View File
@@ -279,6 +279,12 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
}
}
/// @throw invalid_iterator.214 always
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE void throw_cannot_get_value() const
{
JSON_THROW(invalid_iterator::create(exception_id::iterator_value_unavailable, "cannot get value", m_object));
}
public:
/*!
@brief return a reference to the value pointed to by the iterator
@@ -288,40 +294,25 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
{
JSON_ASSERT(m_object != nullptr);
switch (m_object->m_data.m_type)
if (JSON_HEDLEY_LIKELY(m_object->m_data.m_type == value_t::array))
{
case value_t::object:
{
JSON_ASSERT(m_it.object_iterator != m_object->m_data.m_value.object->end());
return m_it.object_iterator->second;
}
case value_t::array:
{
JSON_ASSERT(m_it.array_iterator != m_object->m_data.m_value.array->end());
return *m_it.array_iterator;
}
case value_t::null:
JSON_THROW(invalid_iterator::create(214, "cannot get value", m_object));
case value_t::string:
case value_t::boolean:
case value_t::number_integer:
case value_t::number_unsigned:
case value_t::number_float:
case value_t::binary:
case value_t::discarded:
default:
{
if (JSON_HEDLEY_LIKELY(m_it.primitive_iterator.is_begin()))
{
return *m_object;
}
JSON_THROW(invalid_iterator::create(214, "cannot get value", m_object));
}
JSON_ASSERT(m_it.array_iterator != m_object->m_data.m_value.array->end());
return *m_it.array_iterator;
}
if (JSON_HEDLEY_LIKELY(m_object->m_data.m_type == value_t::object))
{
JSON_ASSERT(m_it.object_iterator != m_object->m_data.m_value.object->end());
return m_it.object_iterator->second;
}
// neither array nor object: a primitive value (null has no value to point to)
if (JSON_HEDLEY_LIKELY(m_object->m_data.m_type != value_t::null && m_it.primitive_iterator.is_begin()))
{
return *m_object;
}
throw_cannot_get_value();
}
/*!
@@ -332,38 +323,25 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
{
JSON_ASSERT(m_object != nullptr);
switch (m_object->m_data.m_type)
if (JSON_HEDLEY_LIKELY(m_object->m_data.m_type == value_t::array))
{
case value_t::object:
{
JSON_ASSERT(m_it.object_iterator != m_object->m_data.m_value.object->end());
return &(m_it.object_iterator->second);
}
case value_t::array:
{
JSON_ASSERT(m_it.array_iterator != m_object->m_data.m_value.array->end());
return &*m_it.array_iterator;
}
case value_t::null:
case value_t::string:
case value_t::boolean:
case value_t::number_integer:
case value_t::number_unsigned:
case value_t::number_float:
case value_t::binary:
case value_t::discarded:
default:
{
if (JSON_HEDLEY_LIKELY(m_it.primitive_iterator.is_begin()))
{
return m_object;
}
JSON_THROW(invalid_iterator::create(214, "cannot get value", m_object));
}
JSON_ASSERT(m_it.array_iterator != m_object->m_data.m_value.array->end());
return &*m_it.array_iterator;
}
if (JSON_HEDLEY_LIKELY(m_object->m_data.m_type == value_t::object))
{
JSON_ASSERT(m_it.object_iterator != m_object->m_data.m_value.object->end());
return &(m_it.object_iterator->second);
}
// neither array nor object: a primitive value
if (JSON_HEDLEY_LIKELY(m_it.primitive_iterator.is_begin()))
{
return m_object;
}
throw_cannot_get_value();
}
/*!
@@ -385,35 +363,20 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
{
JSON_ASSERT(m_object != nullptr);
switch (m_object->m_data.m_type)
if (JSON_HEDLEY_LIKELY(m_object->m_data.m_type == value_t::array))
{
case value_t::object:
{
std::advance(m_it.object_iterator, 1);
break;
}
case value_t::array:
{
std::advance(m_it.array_iterator, 1);
break;
}
case value_t::null:
case value_t::string:
case value_t::boolean:
case value_t::number_integer:
case value_t::number_unsigned:
case value_t::number_float:
case value_t::binary:
case value_t::discarded:
default:
{
++m_it.primitive_iterator;
break;
}
++m_it.array_iterator;
return *this;
}
if (JSON_HEDLEY_LIKELY(m_object->m_data.m_type == value_t::object))
{
std::advance(m_it.object_iterator, 1);
return *this;
}
// neither array nor object: a primitive value
++m_it.primitive_iterator;
return *this;
}
@@ -436,35 +399,20 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
{
JSON_ASSERT(m_object != nullptr);
switch (m_object->m_data.m_type)
if (JSON_HEDLEY_LIKELY(m_object->m_data.m_type == value_t::array))
{
case value_t::object:
{
std::advance(m_it.object_iterator, -1);
break;
}
case value_t::array:
{
std::advance(m_it.array_iterator, -1);
break;
}
case value_t::null:
case value_t::string:
case value_t::boolean:
case value_t::number_integer:
case value_t::number_unsigned:
case value_t::number_float:
case value_t::binary:
case value_t::discarded:
default:
{
--m_it.primitive_iterator;
break;
}
--m_it.array_iterator;
return *this;
}
if (JSON_HEDLEY_LIKELY(m_object->m_data.m_type == value_t::object))
{
std::advance(m_it.object_iterator, -1);
return *this;
}
// neither array nor object: a primitive value
--m_it.primitive_iterator;
return *this;
}
@@ -478,7 +426,7 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
// if objects are not the same, the comparison is undefined
if (JSON_HEDLEY_UNLIKELY(m_object != other.m_object))
{
JSON_THROW(invalid_iterator::create(212, "cannot compare iterators of different containers", m_object));
throw_literal<invalid_iterator>(exception_id::iterators_compare_different_values, "cannot compare iterators of different containers", m_object);
}
// value-initialized forward iterators can be compared, and must compare equal to other value-initialized iterators of the same type #4493
@@ -487,25 +435,18 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
return true;
}
switch (m_object->m_data.m_type)
if (JSON_HEDLEY_LIKELY(m_object->m_data.m_type == value_t::array))
{
case value_t::object:
return (m_it.object_iterator == other.m_it.object_iterator);
case value_t::array:
return (m_it.array_iterator == other.m_it.array_iterator);
case value_t::null:
case value_t::string:
case value_t::boolean:
case value_t::number_integer:
case value_t::number_unsigned:
case value_t::number_float:
case value_t::binary:
case value_t::discarded:
default:
return (m_it.primitive_iterator == other.m_it.primitive_iterator);
return (m_it.array_iterator == other.m_it.array_iterator);
}
if (JSON_HEDLEY_LIKELY(m_object->m_data.m_type == value_t::object))
{
return (m_it.object_iterator == other.m_it.object_iterator);
}
// neither array nor object: a primitive value
return (m_it.primitive_iterator == other.m_it.primitive_iterator);
}
/*!
@@ -527,7 +468,7 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
// if objects are not the same, the comparison is undefined
if (JSON_HEDLEY_UNLIKELY(m_object != other.m_object))
{
JSON_THROW(invalid_iterator::create(212, "cannot compare iterators of different containers", m_object));
throw_literal<invalid_iterator>(exception_id::iterators_compare_different_values, "cannot compare iterators of different containers", m_object);
}
// value-initialized forward iterators can be compared, and must compare equal to other value-initialized iterators of the same type #4493
@@ -540,7 +481,7 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
switch (m_object->m_data.m_type)
{
case value_t::object:
JSON_THROW(invalid_iterator::create(213, "cannot compare order of object iterators", m_object));
throw_literal<invalid_iterator>(exception_id::iterator_order_on_object, "cannot compare order of object iterators", m_object);
case value_t::array:
return (m_it.array_iterator < other.m_it.array_iterator);
@@ -596,7 +537,7 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
switch (m_object->m_data.m_type)
{
case value_t::object:
JSON_THROW(invalid_iterator::create(209, "cannot use offsets with object iterators", m_object));
throw_literal<invalid_iterator>(exception_id::iterator_arithmetic_on_object, "cannot use offsets with object iterators", m_object);
case value_t::array:
{
@@ -675,7 +616,7 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
switch (m_object->m_data.m_type)
{
case value_t::object:
JSON_THROW(invalid_iterator::create(209, "cannot use offsets with object iterators", m_object));
throw_literal<invalid_iterator>(exception_id::iterator_arithmetic_on_object, "cannot use offsets with object iterators", m_object);
case value_t::array:
return m_it.array_iterator - other.m_it.array_iterator;
@@ -704,13 +645,13 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
switch (m_object->m_data.m_type)
{
case value_t::object:
JSON_THROW(invalid_iterator::create(208, "cannot use operator[] for object iterators", m_object));
throw_literal<invalid_iterator>(exception_id::iterator_subscript_on_object, "cannot use operator[] for object iterators", m_object);
case value_t::array:
return *std::next(m_it.array_iterator, n);
case value_t::null:
JSON_THROW(invalid_iterator::create(214, "cannot get value", m_object));
throw_cannot_get_value();
case value_t::string:
case value_t::boolean:
@@ -726,7 +667,7 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
return *m_object;
}
JSON_THROW(invalid_iterator::create(214, "cannot get value", m_object));
throw_cannot_get_value();
}
}
}
@@ -739,12 +680,12 @@ class iter_impl // NOLINT(cppcoreguidelines-special-member-functions,hicpp-speci
{
JSON_ASSERT(m_object != nullptr);
if (JSON_HEDLEY_LIKELY(m_object->is_object()))
if (JSON_HEDLEY_UNLIKELY(!m_object->is_object()))
{
return m_it.object_iterator->first;
throw_literal<invalid_iterator>(exception_id::iterator_key_not_object, "cannot use key() for non-object iterators", m_object);
}
JSON_THROW(invalid_iterator::create(207, "cannot use key() for non-object iterators", m_object));
return m_it.object_iterator->first;
}
/*!
include/nlohmann/detail/json_pointer.hpp
+408 -112
View File
@@ -11,19 +11,19 @@
#include <algorithm> // all_of
#include <cctype> // isdigit
#include <cerrno> // errno, ERANGE
#include <cstddef> // size_t
#include <cstdlib> // strtoull
#ifndef JSON_NO_IO
#include <iosfwd> // ostream
#endif // JSON_NO_IO
#include <limits> // max
#include <map> // map
#include <numeric> // accumulate
#include <string> // string
#include <utility> // move
#include <vector> // vector
#include <nlohmann/detail/exceptions.hpp>
#include <nlohmann/detail/macro_scope.hpp>
#include <nlohmann/detail/meta/cpp_future.hpp>
#include <nlohmann/detail/string_concat.hpp>
#include <nlohmann/detail/string_escape.hpp>
#include <nlohmann/detail/string_utils.hpp>
@@ -31,6 +31,11 @@
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
struct json_pointer_access;
} // namespace detail
/// @brief JSON Pointer defines a string syntax for identifying a specific value within a JSON document
/// @sa https://json.nlohmann.me/api/json_pointer/
template<typename RefStringType>
@@ -43,6 +48,8 @@ class json_pointer
template<typename>
friend class json_pointer;
friend struct detail::json_pointer_access;
template<typename T>
struct string_t_helper
{
@@ -69,12 +76,21 @@ class json_pointer
/// @sa https://json.nlohmann.me/api/json_pointer/to_string/
string_t to_string() const
{
return std::accumulate(reference_tokens.begin(), reference_tokens.end(),
string_t{},
[](const string_t& a, const string_t& b)
// one buffer: every token adds its escaped form (at least its length) and a slash
std::size_t length = 0;
for (const auto& reference_token : reference_tokens)
{
return detail::concat<string_t>(a, '/', detail::escape(b));
});
length += reference_token.size() + 1;
}
string_t result;
result.reserve(length);
for (const auto& reference_token : reference_tokens)
{
result.append("/", 1);
detail::escape_into(result, reference_token);
}
return result;
}
/// @brief return a string representation of the JSON pointer
@@ -129,21 +145,29 @@ class json_pointer
friend json_pointer operator/(const json_pointer& lhs,
const json_pointer& rhs)
{
return json_pointer(lhs) /= rhs;
json_pointer result;
result.reference_tokens.reserve(lhs.reference_tokens.size() + rhs.reference_tokens.size());
result.reference_tokens.insert(result.reference_tokens.end(), lhs.reference_tokens.begin(), lhs.reference_tokens.end());
result.reference_tokens.insert(result.reference_tokens.end(), rhs.reference_tokens.begin(), rhs.reference_tokens.end());
return result;
}
/// @brief create a new JSON pointer by appending the unescaped token at the end of the JSON pointer
/// @sa https://json.nlohmann.me/api/json_pointer/operator_slash/
friend json_pointer operator/(const json_pointer& lhs, string_t token) // NOLINT(performance-unnecessary-value-param)
{
return json_pointer(lhs) /= std::move(token);
json_pointer result;
result.reference_tokens.reserve(lhs.reference_tokens.size() + 1);
result.reference_tokens.insert(result.reference_tokens.end(), lhs.reference_tokens.begin(), lhs.reference_tokens.end());
result.reference_tokens.push_back(std::move(token));
return result;
}
/// @brief create a new JSON pointer by appending the array-index-token at the end of the JSON pointer
/// @sa https://json.nlohmann.me/api/json_pointer/operator_slash/
friend json_pointer operator/(const json_pointer& lhs, std::size_t array_idx)
{
return json_pointer(lhs) /= array_idx;
return lhs / detail::to_string<string_t>(array_idx);
}
/// @brief returns the parent of this JSON pointer
@@ -155,8 +179,8 @@ class json_pointer
return *this;
}
json_pointer res = *this;
res.pop_back();
json_pointer res;
res.reference_tokens = std::vector<string_t>(reference_tokens.begin(), reference_tokens.end() - 1);
return res;
}
@@ -166,7 +190,7 @@ class json_pointer
{
if (JSON_HEDLEY_UNLIKELY(empty()))
{
JSON_THROW(detail::out_of_range::create(405, "JSON pointer has no parent", nullptr));
throw_no_parent();
}
reference_tokens.erase(reference_tokens.begin());
@@ -178,7 +202,7 @@ class json_pointer
{
if (JSON_HEDLEY_UNLIKELY(empty()))
{
JSON_THROW(detail::out_of_range::create(405, "JSON pointer has no parent", nullptr));
throw_no_parent();
}
return reference_tokens.front();
@@ -204,7 +228,7 @@ class json_pointer
{
if (JSON_HEDLEY_UNLIKELY(empty()))
{
JSON_THROW(detail::out_of_range::create(405, "JSON pointer has no parent", nullptr));
throw_no_parent();
}
reference_tokens.pop_back();
@@ -216,7 +240,7 @@ class json_pointer
{
if (JSON_HEDLEY_UNLIKELY(empty()))
{
JSON_THROW(detail::out_of_range::create(405, "JSON pointer has no parent", nullptr));
throw_no_parent();
}
return reference_tokens.back();
@@ -244,6 +268,21 @@ class json_pointer
}
private:
/// @throw out_of_range.405 always
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE static void throw_no_parent()
{
JSON_THROW(detail::out_of_range::create(detail::exception_id::patch_on_root, "JSON pointer has no parent", nullptr));
}
/// @throw out_of_range.404 always
template<typename BasicJsonContext>
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE static void throw_unresolved(const string_t& reference_token, BasicJsonContext context)
{
static_cast<void>(reference_token); // unused when JSON_NOEXCEPTION is defined
static_cast<void>(context);
JSON_THROW(detail::out_of_range::create(detail::exception_id::pointer_unresolved, detail::concat("unresolved reference token '", reference_token, "'"), context));
}
/*!
@brief result of @ref parse_array_index
@@ -255,7 +294,7 @@ class json_pointer
{
ok, ///< @a s is a valid, representable array index
leading_zero, ///< @a s begins with '0' but has more than one character
not_a_number, ///< @a s does not begin with a digit
not_a_number, ///< @a s is neither empty nor "-" and does not begin with a digit
unresolved, ///< @a s could not be converted to an integer
exceeds_size_type ///< @a s converts to an integer that exceeds size_type
};
@@ -282,12 +321,36 @@ class json_pointer
return array_index_status::leading_zero;
}
// error condition (cf. RFC 6901, Sect. 4)
if (JSON_HEDLEY_UNLIKELY(s.size() > 1 && !(s[0] >= '1' && s[0] <= '9')))
// error condition (cf. RFC 6901, Sect. 4); this also covers single-
// character tokens, so "/x" and "/xy" fail alike; "-" and the empty
// token are left to the conversion below and are reported as unresolved
if (JSON_HEDLEY_UNLIKELY(!s.empty() && s != "-" && !(s[0] >= '0' && s[0] <= '9')))
{
return array_index_status::not_a_number;
}
// fast path: up to 18 decimal digits cannot overflow unsigned long long or
// size_type (9 digits for a 32-bit size_type), so strtoull and errno are not needed
constexpr std::size_t max_fast_digits = sizeof(size_type) >= 8 ? 18 : 9;
if (!s.empty() && s.size() <= max_fast_digits)
{
size_type acc = 0;
for (std::size_t i = 0; i < s.size(); ++i)
{
const char c = s[i];
if (JSON_HEDLEY_UNLIKELY(c < '0' || c > '9'))
{
break; // not a plain number: let strtoull decide
}
acc = static_cast<size_type>((acc * 10) + static_cast<size_type>(c - '0'));
if (JSON_HEDLEY_UNLIKELY(i == s.size() - 1))
{
idx = acc;
return array_index_status::ok;
}
}
}
const char* p = s.data();
char* p_end = nullptr; // NOLINT(misc-const-correctness)
errno = 0; // strtoull doesn't reset errno
@@ -329,13 +392,13 @@ class json_pointer
// the branches differ in their messages, not after JSON_THROW's expansion
// NOLINTNEXTLINE(bugprone-branch-clone)
case array_index_status::leading_zero:
JSON_THROW(detail::parse_error::create(106, 0, detail::concat("array index '", s, "' must not begin with '0'"), nullptr));
JSON_THROW(detail::parse_error::create(detail::exception_id::pointer_index_leading_zero, 0, detail::concat("array index '", s, "' must not begin with '0'"), nullptr));
case array_index_status::not_a_number:
JSON_THROW(detail::parse_error::create(109, 0, detail::concat("array index '", s, "' is not a number"), nullptr));
JSON_THROW(detail::parse_error::create(detail::exception_id::pointer_index_not_a_number, 0, detail::concat("array index '", s, "' is not a number"), nullptr));
case array_index_status::unresolved:
JSON_THROW(detail::out_of_range::create(404, detail::concat("unresolved reference token '", s, "'"), nullptr));
throw_unresolved(s, nullptr);
case array_index_status::exceeds_size_type:
JSON_THROW(detail::out_of_range::create(410, detail::concat("array index ", s, " exceeds size_type"), nullptr));
JSON_THROW(detail::out_of_range::create(detail::exception_id::value_out_of_range, detail::concat("array index ", s, " exceeds size_type"), nullptr));
case array_index_status::ok:
default:
break;
@@ -344,12 +407,89 @@ class json_pointer
return idx;
}
/*!
@brief compare with a JSON pointer string without splitting it into tokens
@throw parse_error.107 if the string is not empty or begins with '/'
@throw parse_error.108 if character '~' is not followed by '0' or '1'
*/
bool equals_string(const string_t& reference_string) const
{
if (reference_string.empty())
{
return reference_tokens.empty();
}
if (JSON_HEDLEY_UNLIKELY(reference_string[0] != '/'))
{
JSON_THROW(detail::parse_error::create(detail::exception_id::pointer_missing_slash, 1, detail::concat("JSON pointer must be empty or begin with '/' - was: '", reference_string, "'"), nullptr));
}
// the whole string is validated, whether or not it matches
const std::size_t size = reference_string.size();
for (std::size_t pos = reference_string.find_first_of('~');
pos != string_t::npos;
pos = reference_string.find_first_of('~', pos + 1))
{
if (JSON_HEDLEY_UNLIKELY(pos == size - 1 || (reference_string[pos + 1] != '0' && reference_string[pos + 1] != '1')))
{
JSON_THROW(detail::parse_error::create(detail::exception_id::pointer_invalid_escape, 0, "escape character '~' must be followed with '0' or '1'", nullptr));
}
}
// compare token by token, unescaping the string on the fly
std::size_t pos = 0; // the slash in front of the next token
for (const auto& reference_token : reference_tokens)
{
if (pos >= size)
{
return false;
}
std::size_t i = pos + 1;
std::size_t j = 0;
const std::size_t token_size = reference_token.size();
while (i < size && reference_string[i] != '/')
{
char c = reference_string[i++];
if (c == '~')
{
c = (reference_string[i++] == '0') ? '~' : '/';
}
if (j == token_size || reference_token[j] != c)
{
return false;
}
++j;
}
if (j != token_size)
{
return false;
}
pos = i;
}
return pos == size;
}
/// @brief object member access with a key that is only copied if it is inserted
template<typename BasicJsonType>
static BasicJsonType& object_member(BasicJsonType& object, const string_t& key)
{
auto& members = *object.m_data.m_value.object;
const auto it = members.find(key);
if (it != members.end())
{
return it->second;
}
return object.operator[](key);
}
JSON_PRIVATE_UNLESS_TESTED:
json_pointer top() const
{
if (JSON_HEDLEY_UNLIKELY(empty()))
{
JSON_THROW(detail::out_of_range::create(405, "JSON pointer has no parent", nullptr));
throw_no_parent();
}
json_pointer result = *this;
@@ -367,84 +507,141 @@ class json_pointer
the result independent of the order in which the flattened object is
iterated, which is unspecified for some object types.
The prefixes form a tree and are numbered, so each of them is stored only
once (as a node) rather than as a copy of all of its reference tokens.
The prefixes form a tree and are numbered (number 0 is the empty prefix),
so each of them is stored only once (as a node) rather than as a copy of
all of its reference tokens. The tree does not own the reference tokens:
it refers to the tokens of the parsed keys, which must outlive it.
*/
struct prefix_tree
{
// children[id] maps a reference token to the number of the prefix
// extended by that token; number 0 is the empty prefix
std::vector<std::map<string_t, std::size_t>> children;
// open-addressing hash table from (parent, last reference token) to
// the number of the node; empty slots have token == nullptr
struct slot
{
std::size_t hash;
std::size_t parent;
const string_t* token;
std::size_t id;
slot() noexcept
: hash(0), parent(0), token(nullptr), id(0)
{}
slot(std::size_t h, std::size_t p, const string_t* t, std::size_t i) noexcept
: hash(h), parent(p), token(t), id(i)
{}
};
std::vector<slot> table;
std::size_t used = 0;
static std::size_t hash_of(std::size_t parent, const string_t& token) noexcept
{
std::size_t h = parent * static_cast<std::size_t>(0x9E3779B97F4A7C15ULL & (std::numeric_limits<std::size_t>::max)());
for (std::size_t i = 0; i < token.size(); ++i)
{
h = (h ^ static_cast<unsigned char>(token[i])) * static_cast<std::size_t>(0x100000001B3ULL & (std::numeric_limits<std::size_t>::max)());
}
return h ^ (h >> 29u);
}
void grow()
{
std::vector<slot> old(table.size() * 2);
old.swap(table);
const std::size_t mask = table.size() - 1;
for (const auto& s : old)
{
if (s.token != nullptr)
{
std::size_t i = s.hash & mask;
while (table[i].token != nullptr)
{
i = (i + 1) & mask;
}
table[i] = s;
}
}
}
// parent[id] is the number of the prefix without its last token
std::vector<std::size_t> parent;
// is_array[id] is true iff some flattened key has the reference token
// 0 directly below the prefix with number id
std::vector<bool> is_array;
// start with the empty prefix only
prefix_tree()
: children(1)
: table(16)
, parent(1, 0)
, is_array(1, false)
{}
// return the number of the prefix with number id extended by
// reference_token, adding it if it is new
std::size_t add_child(std::size_t id, string_t&& reference_token)
std::size_t add_child(std::size_t id, const string_t& reference_token)
{
const std::size_t hash = hash_of(id, reference_token);
const std::size_t mask = table.size() - 1;
std::size_t i = hash & mask;
while (table[i].token != nullptr)
{
if (table[i].hash == hash && table[i].parent == id && *table[i].token == reference_token)
{
return table[i].id;
}
i = (i + 1) & mask;
}
// new prefix
const std::size_t child = parent.size();
table[i] = slot(hash, id, &reference_token, child);
if (reference_token == "0")
{
is_array[id] = true;
}
parent.push_back(id);
is_array.push_back(false);
// read the number before the emplace_back below, which may
// reallocate children and invalidate the iterator
const std::size_t next = children.size();
const auto inserted = children[id].emplace(std::move(reference_token), next);
const std::size_t child = inserted.first->second;
if (inserted.second)
// keep the load factor below 1/2
if (++used * 2 > table.size())
{
children.emplace_back();
is_array.push_back(false);
grow();
}
return child;
}
// return the number of the prefix with number id extended by
// reference_token, which must have been added before
std::size_t find_child(std::size_t id, const string_t& reference_token) const
{
const auto it = children[id].find(reference_token);
JSON_ASSERT(it != children[id].end());
return it->second;
}
};
/*!
@brief create and return a reference to the pointed to value
Complexity: Linear in the number of reference tokens (times the logarithm
of the number of siblings for the prefix lookup).
@param[in] j the value to create the pointed to value in
@param[in] tokens the reference tokens of the pointer
@param[in] prefixes prefixes[i] is the number in @a tree of the prefix
consisting of the first i reference tokens
Complexity: Linear in the number of reference tokens.
@throw parse_error.106 if an array index begins with '0'
@throw parse_error.109 if array index is not a number
@throw type_error.313 if value cannot be unflattened
*/
template<typename BasicJsonType>
BasicJsonType& get_and_create(BasicJsonType& j, const prefix_tree& tree) const
static BasicJsonType& get_and_create(BasicJsonType& j, const std::vector<string_t>& tokens,
const std::vector<std::size_t>& prefixes, const prefix_tree& tree)
{
auto* result = &j;
// the number of the prefix consumed so far; used to look up whether
// the value to be created below is an array or an object
std::size_t id = 0;
// in case no reference tokens exist, return a reference to the JSON value
// j which will be overwritten by a primitive value
for (const auto& reference_token : reference_tokens)
for (std::size_t i = 0; i < tokens.size(); ++i)
{
const auto& reference_token = tokens[i];
switch (result->type())
{
case detail::value_t::null:
{
if (tree.is_array[id])
if (tree.is_array[prefixes[i]])
{
// some reference token below this position is 0, so the
// value is an array
@@ -461,7 +658,7 @@ class json_pointer
case detail::value_t::object:
{
// create an entry in the object
result = &result->operator[](reference_token);
result = &object_member(*result, reference_token);
break;
}
@@ -486,10 +683,8 @@ class json_pointer
case detail::value_t::binary:
case detail::value_t::discarded:
default:
JSON_THROW(detail::type_error::create(313, "invalid value to unflatten", &j));
JSON_THROW(detail::type_error::create(detail::exception_id::unflatten_invalid_value, "invalid value to unflatten", &j));
}
id = tree.find_child(id, reference_token);
}
return *result;
@@ -541,7 +736,7 @@ class json_pointer
case detail::value_t::object:
{
// use unchecked object access
ptr = &ptr->operator[](reference_token);
ptr = &object_member(*ptr, reference_token);
break;
}
@@ -569,7 +764,7 @@ class json_pointer
case detail::value_t::binary:
case detail::value_t::discarded:
default:
JSON_THROW(detail::out_of_range::create(404, detail::concat("unresolved reference token '", reference_token, "'"), ptr));
throw_unresolved(reference_token, ptr);
}
}
@@ -591,8 +786,13 @@ class json_pointer
{
case detail::value_t::object:
{
// note: at performs range check
ptr = &ptr->at(reference_token);
const auto it = ptr->m_data.m_value.object->find(reference_token);
if (JSON_HEDLEY_UNLIKELY(it == ptr->m_data.m_value.object->end()))
{
// at() throws out_of_range.403 with the usual message
ptr->at(reference_token);
}
ptr = &it->second;
break;
}
@@ -601,7 +801,7 @@ class json_pointer
if (JSON_HEDLEY_UNLIKELY(reference_token == "-"))
{
// "-" always fails the range check
JSON_THROW(detail::out_of_range::create(402, detail::concat(
JSON_THROW(detail::out_of_range::create(detail::exception_id::pointer_past_the_end_index, detail::concat(
"array index '-' (", std::to_string(ptr->m_data.m_value.array->size()),
") is out of range"), ptr));
}
@@ -610,10 +810,10 @@ class json_pointer
// Bounds check before access to avoid exception with JSON_NOEXCEPTION
if (JSON_HEDLEY_UNLIKELY(idx >= ptr->m_data.m_value.array->size()))
{
JSON_THROW(detail::out_of_range::create(401, detail::concat(
JSON_THROW(detail::out_of_range::create(detail::exception_id::array_index_out_of_range, detail::concat(
"array index ", std::to_string(idx), " is out of range"), ptr));
}
ptr = &ptr->operator[](idx);
ptr = &(*ptr->m_data.m_value.array)[idx];
break;
}
@@ -626,7 +826,7 @@ class json_pointer
case detail::value_t::binary:
case detail::value_t::discarded:
default:
JSON_THROW(detail::out_of_range::create(404, detail::concat("unresolved reference token '", reference_token, "'"), ptr));
throw_unresolved(reference_token, ptr);
}
}
@@ -661,7 +861,9 @@ class json_pointer
{
// use unchecked object access; the const operator[]
// asserts that the key exists
ptr = &ptr->operator[](reference_token);
const auto it = ptr->m_data.m_value.object->find(reference_token);
JSON_ASSERT(it != ptr->m_data.m_value.object->end());
ptr = &it->second;
break;
}
@@ -670,12 +872,14 @@ class json_pointer
if (JSON_HEDLEY_UNLIKELY(reference_token == "-"))
{
// "-" cannot be used for const access
JSON_THROW(detail::out_of_range::create(402, detail::concat("array index '-' (", std::to_string(ptr->m_data.m_value.array->size()), ") is out of range"), ptr));
JSON_THROW(detail::out_of_range::create(detail::exception_id::pointer_past_the_end_index, detail::concat("array index '-' (", std::to_string(ptr->m_data.m_value.array->size()), ") is out of range"), ptr));
}
// use unchecked array access; the const operator[]
// asserts that the index exists
ptr = &ptr->operator[](array_index<BasicJsonType>(reference_token));
const auto idx = array_index<BasicJsonType>(reference_token);
JSON_ASSERT(idx < ptr->m_data.m_value.array->size());
ptr = &(*ptr->m_data.m_value.array)[idx];
break;
}
@@ -688,7 +892,7 @@ class json_pointer
case detail::value_t::binary:
case detail::value_t::discarded:
default:
JSON_THROW(detail::out_of_range::create(404, detail::concat("unresolved reference token '", reference_token, "'"), ptr));
throw_unresolved(reference_token, ptr);
}
}
@@ -716,12 +920,12 @@ class json_pointer
{
case detail::value_t::object:
{
const auto it = ptr->find(reference_token);
if (JSON_HEDLEY_UNLIKELY(it == ptr->end()))
const auto it = ptr->m_data.m_value.object->find(reference_token);
if (JSON_HEDLEY_UNLIKELY(it == ptr->m_data.m_value.object->end()))
{
return nullptr;
}
ptr = &*it;
ptr = &it->second;
break;
}
@@ -743,9 +947,9 @@ class json_pointer
// the branches differ in their messages, not after JSON_THROW's expansion
// NOLINTNEXTLINE(bugprone-branch-clone)
case array_index_status::leading_zero:
JSON_THROW(detail::parse_error::create(106, 0, detail::concat("array index '", reference_token, "' must not begin with '0'"), nullptr));
JSON_THROW(detail::parse_error::create(detail::exception_id::pointer_index_leading_zero, 0, detail::concat("array index '", reference_token, "' must not begin with '0'"), nullptr));
case array_index_status::not_a_number:
JSON_THROW(detail::parse_error::create(109, 0, detail::concat("array index '", reference_token, "' is not a number"), nullptr));
JSON_THROW(detail::parse_error::create(detail::exception_id::pointer_index_not_a_number, 0, detail::concat("array index '", reference_token, "' is not a number"), nullptr));
case array_index_status::unresolved:
case array_index_status::exceeds_size_type:
return nullptr;
@@ -758,7 +962,7 @@ class json_pointer
{
return nullptr;
}
ptr = &ptr->operator[](idx);
ptr = &(*ptr->m_data.m_value.array)[idx];
break;
}
@@ -791,13 +995,14 @@ class json_pointer
{
case detail::value_t::object:
{
if (!ptr->contains(reference_token))
const auto it = ptr->m_data.m_value.object->find(reference_token);
if (it == ptr->m_data.m_value.object->end())
{
// we did not find the key in the object
return false;
}
ptr = &ptr->operator[](reference_token);
ptr = &it->second;
break;
}
@@ -819,13 +1024,13 @@ class json_pointer
return false;
}
if (idx >= ptr->size())
if (idx >= ptr->m_data.m_value.array->size())
{
// index out of range
return false;
}
ptr = &ptr->operator[](idx);
ptr = &(*ptr->m_data.m_value.array)[idx];
break;
}
@@ -872,9 +1077,18 @@ class json_pointer
// check if a nonempty reference string begins with slash
if (JSON_HEDLEY_UNLIKELY(reference_string[0] != '/'))
{
JSON_THROW(detail::parse_error::create(107, 1, detail::concat("JSON pointer must be empty or begin with '/' - was: '", reference_string, "'"), nullptr));
JSON_THROW(detail::parse_error::create(detail::exception_id::pointer_missing_slash, 1, detail::concat("JSON pointer must be empty or begin with '/' - was: '", reference_string, "'"), nullptr));
}
// every slash starts a reference token
const std::size_t size = reference_string.size();
std::size_t token_count = 0;
for (std::size_t i = 0; i < size; ++i)
{
token_count += static_cast<std::size_t>(reference_string[i] == '/');
}
result.reserve(token_count);
// extract the reference tokens:
// - slash: position of the last read slash (or end of string)
// - start: position after the previous slash
@@ -896,31 +1110,52 @@ class json_pointer
const auto count = (slash == string_t::npos ? reference_string.size() : slash) - start;
auto reference_token = string_t(reference_string.data() + start, count);
// check reference tokens are properly escaped
for (std::size_t pos = reference_token.find_first_of('~');
pos != string_t::npos;
pos = reference_token.find_first_of('~', pos + 1))
// check reference tokens are properly escaped; a token without
// a '~' (the common case) needs neither check nor unescaping
std::size_t pos = reference_token.find_first_of('~');
if (pos != string_t::npos)
{
JSON_ASSERT(reference_token[pos] == '~');
// ~ must be followed by 0 or 1
if (JSON_HEDLEY_UNLIKELY(pos == reference_token.size() - 1 ||
(reference_token[pos + 1] != '0' &&
reference_token[pos + 1] != '1')))
for (; pos != string_t::npos; pos = reference_token.find_first_of('~', pos + 1))
{
JSON_THROW(detail::parse_error::create(108, 0, "escape character '~' must be followed with '0' or '1'", nullptr));
JSON_ASSERT(reference_token[pos] == '~');
// ~ must be followed by 0 or 1
if (JSON_HEDLEY_UNLIKELY(pos == reference_token.size() - 1 ||
(reference_token[pos + 1] != '0' &&
reference_token[pos + 1] != '1')))
{
JSON_THROW(detail::parse_error::create(detail::exception_id::pointer_invalid_escape, 0, "escape character '~' must be followed with '0' or '1'", nullptr));
}
}
detail::unescape(reference_token);
}
// finally, store the reference token
detail::unescape(reference_token);
result.push_back(reference_token);
result.push_back(std::move(reference_token));
}
return result;
}
private:
// Add the entry (key, v) to the object `obj`. Flattened paths are pairwise
// distinct, so objects that can append a key known to be absent
// (ordered_map) skip the lookup, which is linear and would make flatten
// quadratic; all other object types use operator[].
template<typename ObjectType, typename ValueType>
static auto add_flattened(ObjectType& obj, const string_t& key, ValueType&& v, detail::priority_tag<1> /*unused*/)
-> decltype(obj.emplace_new_key(key, std::forward<ValueType>(v)), void())
{
obj.emplace_new_key(key, std::forward<ValueType>(v));
}
template<typename ObjectType, typename ValueType>
static void add_flattened(ObjectType& obj, const string_t& key, ValueType&& v, detail::priority_tag<0> /*unused*/)
{
obj[key] = std::forward<ValueType>(v);
}
/*!
@param[in] reference_string the reference string to the current value
@param[in] value the value to consider
@@ -965,7 +1200,8 @@ class json_pointer
// flatten `v`, whose path is `path`: primitives and empty containers
// are added to the result right away; other containers get a frame
const auto enter = [&stack, &path, &result](const BasicJsonType & v)
auto& object = *result.m_data.m_value.object;
const auto enter = [&stack, &path, &object](const BasicJsonType & v)
{
switch (v.type())
{
@@ -974,7 +1210,7 @@ class json_pointer
if (v.m_data.m_value.array->empty())
{
// flatten empty array as null
result[path] = nullptr;
add_flattened(object, path, nullptr, detail::priority_tag<1> {});
}
else
{
@@ -988,7 +1224,7 @@ class json_pointer
if (v.m_data.m_value.object->empty())
{
// flatten empty object as null
result[path] = nullptr;
add_flattened(object, path, nullptr, detail::priority_tag<1> {});
}
else
{
@@ -1008,7 +1244,7 @@ class json_pointer
default:
{
// add a primitive value with its reference string
result[path] = v;
add_flattened(object, path, v, detail::priority_tag<1> {});
return;
}
}
@@ -1054,6 +1290,10 @@ class json_pointer
enter(it->second);
}
}
// the entries were added without going through basic_json, so the
// parent pointers (JSON_DIAGNOSTICS) have to be set now
result.set_parents();
}
/*!
@@ -1072,38 +1312,80 @@ class json_pointer
{
if (JSON_HEDLEY_UNLIKELY(!value.is_object()))
{
JSON_THROW(detail::type_error::create(314, "only objects can be unflattened", &value));
JSON_THROW(detail::type_error::create(detail::exception_id::unflatten_not_object, "only objects can be unflattened", &value));
}
BasicJsonType result;
// parse every key once; the reference tokens are kept for the second
// pass (the vectors are never resized, so the tree may refer to them)
std::vector<std::vector<string_t>> keys;
keys.reserve(value.m_data.m_value.object->size());
for (const auto& element : *value.m_data.m_value.object)
{
json_pointer ptr(element.first);
keys.push_back(std::move(ptr.reference_tokens));
}
// collect the pointer prefixes that have a reference token 0 among
// their children; the values below them are arrays, all others are
// objects (see prefix_tree)
prefix_tree tree;
for (const auto& element : *value.m_data.m_value.object)
// the number of the prefix with i + 1 tokens of the previous key; keys
// are often sorted, so most of the prefix is the same as for the
// previous key and need not be looked up again
std::vector<std::size_t> path;
const std::vector<string_t>* previous = nullptr;
// the number of the complete prefix (i.e., the key) of each key
std::vector<std::size_t> leaves;
leaves.reserve(keys.size());
for (const auto& tokens : keys)
{
json_pointer ptr(element.first);
std::size_t id = 0;
for (auto& reference_token : ptr.reference_tokens)
std::size_t common = 0;
if (previous != nullptr)
{
id = tree.add_child(id, std::move(reference_token));
const std::size_t limit = (std::min)(tokens.size(), previous->size());
while (common < limit && tokens[common] == (*previous)[common])
{
++common;
}
}
path.resize(common);
std::size_t id = common == 0 ? 0 : path[common - 1];
for (std::size_t i = common; i < tokens.size(); ++i)
{
id = tree.add_child(id, tokens[i]);
path.push_back(id);
}
leaves.push_back(id);
previous = &tokens;
}
// iterate the JSON object values
std::vector<std::size_t> prefixes;
std::size_t key_index = 0;
for (const auto& element : *value.m_data.m_value.object)
{
if (JSON_HEDLEY_UNLIKELY(!element.second.is_primitive()))
{
JSON_THROW(detail::type_error::create(315, "values in object must be primitive", &element.second));
JSON_THROW(detail::type_error::create(detail::exception_id::unflatten_value_not_primitive, "values in object must be primitive", &element.second));
}
const auto& tokens = keys[key_index];
// number the prefixes of this key from its last one to the first
prefixes.resize(tokens.size());
for (std::size_t i = tokens.size(), id = leaves[key_index]; i > 0; --i)
{
id = tree.parent[id];
prefixes[i - 1] = id;
}
++key_index;
// Assign the value to the reference pointed to by JSON pointer. Note
// that if the JSON pointer is "" (i.e., points to the whole value),
// function get_and_create returns a reference to the result itself.
// An assignment will then create a primitive value.
json_pointer(element.first).get_and_create(result, tree) = element.second;
get_and_create(result, tokens, prefixes, tree) = element.second;
}
return result;
@@ -1142,7 +1424,7 @@ class json_pointer
= delete;
#else
{
return *this == json_pointer(rhs);
return equals_string(rhs);
}
#endif
@@ -1226,7 +1508,7 @@ inline bool operator==(const json_pointer<RefStringTypeLhs>& lhs,
= delete;
#else
{
return lhs == json_pointer<RefStringTypeLhs>(rhs);
return lhs.equals_string(rhs);
}
#endif
@@ -1239,7 +1521,7 @@ inline bool operator==(const StringType& lhs,
= delete;
#else
{
return json_pointer<RefStringTypeRhs>(lhs) == rhs;
return rhs.equals_string(lhs);
}
#endif
@@ -1284,4 +1566,18 @@ inline bool operator<(const json_pointer<RefStringTypeLhs>& lhs,
}
#endif
namespace detail
{
/// the reference tokens of a json_pointer, for code that resolves pointers
/// without a basic_json value (such as the zero-copy view)
struct json_pointer_access
{
template<typename RefStringType>
static const std::vector<typename json_pointer<RefStringType>::string_t>& reference_tokens(const json_pointer<RefStringType>& ptr) noexcept
{
return ptr.reference_tokens;
}
};
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/macro_scope.hpp
+2 -2
View File
@@ -312,7 +312,7 @@
return ej_pair.first == e; \
}); \
if (it != std::end(m)) j = it->second; \
else ::nlohmann::detail::templated_json_throw<nlohmann::detail::out_of_range>(nlohmann::detail::out_of_range::create(410,"enum value out of range for " #ENUM_TYPE, nullptr)); \
else ::nlohmann::detail::templated_json_throw<nlohmann::detail::out_of_range>(nlohmann::detail::out_of_range::create(nlohmann::detail::exception_id::value_out_of_range,"enum value out of range for " #ENUM_TYPE, nullptr)); \
} \
template<typename BasicJsonType> \
inline void from_json(const BasicJsonType& j, ENUM_TYPE& e) \
@@ -327,7 +327,7 @@
return ej_pair.second == j; \
}); \
if (it != std::end(m)) e = it->first; \
else ::nlohmann::detail::templated_json_throw<nlohmann::detail::out_of_range>(nlohmann::detail::out_of_range::create(410, nlohmann::detail::concat("enum value out of range for " #ENUM_TYPE ": ", j.dump(-1, ' ', false, nlohmann::detail::error_handler_t::replace)), &j)); \
else ::nlohmann::detail::templated_json_throw<nlohmann::detail::out_of_range>(nlohmann::detail::out_of_range::create(nlohmann::detail::exception_id::value_out_of_range, nlohmann::detail::concat("enum value out of range for " #ENUM_TYPE ": ", j.dump(-1, ' ', false, nlohmann::detail::error_handler_t::replace)), &j)); \
}
// Ugly macros to avoid uglier copy-paste when specializing basic_json. They
include/nlohmann/detail/macro_unscope.hpp
+5
View File
@@ -19,6 +19,9 @@
#undef NLOHMANN_CAN_CALL_STD_FUNC_IMPL
#undef JSON_INLINE_VARIABLE
#undef JSON_NO_UNIQUE_ADDRESS
#undef JSON_UNLOCKED_FILE_IO
#undef JSON_DTOA_SSE2
#undef JSON_DTOA_NEON
#ifndef JSON_TEST_KEEP_MACROS
#undef JSON_CATCH
@@ -45,6 +48,8 @@
#undef JSON_USE_OBJECTS_FOR_ENUM_KEYED_MAPS
#undef JSON_DISABLE_ENUM_SERIALIZATION
#undef JSON_DISABLE_TUPLE_REFERENCE_CONVERSION
#undef JSON_DISABLE_STREAM_BULK_SCAN
#undef JSON_DISABLE_UNLOCKED_FILE_IO
#endif
#include <nlohmann/thirdparty/hedley/hedley_undef.hpp>
include/nlohmann/detail/meta/type_traits.hpp
+66
View File
@@ -9,9 +9,11 @@
#pragma once
#include <limits> // numeric_limits
#include <map> // map, multimap
#include <string> // char_traits
#include <tuple> // tuple
#include <type_traits> // false_type, is_constructible, is_integral, is_same, true_type
#include <unordered_map> // unordered_map, unordered_multimap
#include <utility> // declval
#include <vector> // vector
#if defined(__cpp_lib_byte) && __cpp_lib_byte >= 201603L
@@ -172,6 +174,10 @@ struct has_to_json < BasicJsonType, T, enable_if_t < !is_basic_json<T>::value >>
template<typename T>
using detect_key_compare = typename T::key_compare;
// detects whether two values of type T can be compared with operator==
template<typename T>
using detect_equal_comparable = decltype(static_cast<bool>(std::declval<const T&>() == std::declval<const T&>()));
// obtains the actual object key comparator: object_t::key_compare if the
// object type defines it, and default_object_comparator_t otherwise
//
@@ -679,6 +685,22 @@ struct is_compatible_integer_type
: is_compatible_integer_type_impl<RealIntegerType,
CompatibleNumberIntegerType> {};
// whether to_json() stores an integer of type CompatibleNumberIntegerType as
// number_integer
template<typename BasicJsonType, typename CompatibleNumberIntegerType, typename = void>
struct is_compatible_number_integer_type
: is_compatible_integer_type<typename BasicJsonType::number_integer_t, CompatibleNumberIntegerType> {};
// if number_unsigned_t is the same type as number_integer_t, unsigned integers
// are stored as number_integer as well (#2573)
template<typename BasicJsonType, typename CompatibleNumberIntegerType>
struct is_compatible_number_integer_type<BasicJsonType, CompatibleNumberIntegerType,
enable_if_t<conjunction<std::is_same<typename BasicJsonType::number_integer_t, typename BasicJsonType::number_unsigned_t>,
std::is_integral<CompatibleNumberIntegerType>,
std::is_unsigned<CompatibleNumberIntegerType>,
negation<std::is_same<bool, CompatibleNumberIntegerType>>>::value>>
: std::is_constructible<typename BasicJsonType::number_integer_t, CompatibleNumberIntegerType> {};
template<typename BasicJsonType, typename CompatibleType, typename = void>
struct is_compatible_type_impl: std::false_type {};
@@ -893,6 +915,31 @@ struct has_capacity : std::integral_constant<bool, is_detected<detect_capacity,
template <typename T>
struct is_ordered_map : has_capacity<T> {};
// whether T is a specialization of nlohmann::ordered_map, which only ever
// appends members, so they can only move when its capacity changes
template<typename T>
struct is_nlohmann_ordered_map : std::false_type {};
template<class Key, class T, class IgnoredLess, class Allocator>
struct is_nlohmann_ordered_map<ordered_map<Key, T, IgnoredLess, Allocator>> : std::true_type {};
// whether adding or erasing elements never moves the other elements of the
// container T; only node-based standard containers are known to guarantee this
template<typename T>
struct has_stable_elements : std::false_type {};
template<class Key, class T, class Compare, class Allocator>
struct has_stable_elements<std::map<Key, T, Compare, Allocator>> : std::true_type {};
template<class Key, class T, class Compare, class Allocator>
struct has_stable_elements<std::multimap<Key, T, Compare, Allocator>> : std::true_type {};
template<class Key, class T, class Hash, class KeyEqual, class Allocator>
struct has_stable_elements<std::unordered_map<Key, T, Hash, KeyEqual, Allocator>> : std::true_type {};
template<class Key, class T, class Hash, class KeyEqual, class Allocator>
struct has_stable_elements<std::unordered_multimap<Key, T, Hash, KeyEqual, Allocator>> : std::true_type {};
// to avoid useless casts (see https://github.com/nlohmann/json/issues/2893#issuecomment-889152324)
template < typename T, typename U, enable_if_t < !std::is_same<T, U>::value, int > = 0 >
T conditional_static_cast(U value)
@@ -1016,6 +1063,25 @@ constexpr bool value_in_range_of(T val)
template<bool Value>
using bool_constant = std::integral_constant<bool, Value>;
// Stands in for number_unsigned_t in overload sets if it is the same type as
// number_integer_t, so that the unsigned overloads do not collide with the
// integer ones. Never constructed. Such a basic_json stores every integer as
// number_integer (#2573).
struct same_as_number_integer_type {};
// NumberUnsignedType, or same_as_number_integer_type if it is the same type as
// NumberIntegerType; basic_json uses this one, as it cannot name its own member
// types through an incomplete basic_json (MSVC reports a recursive alias, and
// old GCC versions crash)
template<typename NumberIntegerType, typename NumberUnsignedType>
using number_unsigned_overload_type = typename std::conditional<std::is_same<NumberIntegerType, NumberUnsignedType>::value,
same_as_number_integer_type, NumberUnsignedType>::type;
// number_unsigned_t of BasicJsonType, or same_as_number_integer_type if it is
// the same type as number_integer_t
template<typename BasicJsonType>
using number_unsigned_overload_t = number_unsigned_overload_type<typename BasicJsonType::number_integer_t, typename BasicJsonType::number_unsigned_t>;
///////////////////////////////////////////////////////////////////////////////
// is_c_string
///////////////////////////////////////////////////////////////////////////////
include/nlohmann/detail/output/binary_writer.hpp
+722 -129
View File
File diff suppressed because it is too large. Load diff
include/nlohmann/detail/output/output_adapters.hpp
+164 -34
View File
@@ -8,7 +8,10 @@
#pragma once
#include <algorithm> // max
#include <array> // array
#include <cstddef> // size_t
#include <cstring> // memcpy
#include <memory> // shared_ptr, make_shared
#include <string> // basic_string
#include <type_traits> // conditional, integral_constant, is_same
@@ -48,32 +51,170 @@ template<typename CharType> struct output_adapter_protocol
template<typename CharType>
using output_adapter_t = std::shared_ptr<output_adapter_protocol<CharType>>;
/// the largest number of characters a writer may reserve() from a sink at once;
/// output_vector_sink also appends writes of at least this size with insert()
constexpr std::size_t max_reserve_size = 256;
/// @brief non-virtual output sink writing into a std::vector
///
/// This sink is not part of the virtual output_adapter_protocol hierarchy: it is
/// passed to binary_writer by value as a template parameter, so
/// write_character()/write_characters() are ordinary (inlinable) calls with no
/// vtable lookup and no shared_ptr. It is used for the common
/// `to_cbor`/`to_msgpack`/... into a std::vector. output_vector_adapter below
/// wraps this same sink to provide the virtual interface.
/// `to_cbor`/`to_msgpack`/... into a std::vector.
///
/// Most writes are a few bytes - a type marker, or a number of 1, 2, 4, or 8
/// bytes - and appending those with push_back() or insert() cost more than
/// encoding them: insert() is an out-of-line call into a routine that can insert
/// anywhere, and resize() is one as well with libstdc++. The sink therefore keeps
/// its own write position: it grows the vector geometrically ahead of the
/// position and copies each write to it, so a write is a capacity check and a
/// short copy. The destructor shrinks the vector to the bytes actually written,
/// also when a write throws; shrinking a vector never allocates. The sink owns
/// that trim, so it can be moved but not copied, and the vector must not be used
/// while the sink is alive.
template<typename CharType, typename AllocatorType = std::allocator<CharType>>
class output_vector_sink
{
public:
explicit output_vector_sink(std::vector<CharType, AllocatorType>& vec) noexcept
: v(&vec), position(vec.size())
{}
output_vector_sink(const output_vector_sink&) = delete;
output_vector_sink& operator=(const output_vector_sink&) = delete;
output_vector_sink& operator=(output_vector_sink&&) = delete;
output_vector_sink(output_vector_sink&& other) noexcept
: v(other.v), position(other.position)
{
other.v = nullptr;
}
~output_vector_sink()
{
if (v != nullptr)
{
v->resize(position);
}
}
// always inlined: GCC otherwise keeps these out of line in a large
// translation unit, and a call per byte or number costs more than the write
JSON_HEDLEY_ALWAYS_INLINE
void write_character(CharType c)
{
if (JSON_HEDLEY_UNLIKELY(position == v->size()))
{
grow(1);
}
(*v)[position++] = c;
}
// no JSON_HEDLEY_NON_NULL here: binary_writer legitimately passes a null
// pointer with length 0 for empty strings/binary values; memcpy must not
// see it.
JSON_HEDLEY_ALWAYS_INLINE
void write_characters(const CharType* s, std::size_t length)
{
if (JSON_HEDLEY_UNLIKELY(v->size() - position < length))
{
if (length >= max_reserve_size)
{
append(s, length);
return;
}
grow(length);
}
if (length != 0)
{
std::memcpy(v->data() + position, s, length * sizeof(CharType));
position += length;
}
}
/// @brief space for writing up to @a length characters directly
///
/// Returns a pointer to at least @a length (at most @ref max_reserve_size)
/// writable characters at the write position; @ref commit then keeps the
/// first ones of them. A writer can store whole words there and keep only
/// the bytes it needs, and keep its write pointer in a register across many
/// values instead of updating the sink after each.
JSON_HEDLEY_ALWAYS_INLINE
CharType* reserve(const std::size_t length)
{
JSON_ASSERT(length <= max_reserve_size);
if (JSON_HEDLEY_UNLIKELY(v->size() - position < length))
{
grow(length);
}
return v->data() + position;
}
/// keep the first @a length characters written to the space from reserve()
JSON_HEDLEY_ALWAYS_INLINE
void commit(const std::size_t length) noexcept
{
position += length;
}
private:
/// make room for at least @a length more characters after the position;
/// kept out of line so that the write functions stay small enough for
/// GCC to inline them into the writer
JSON_HEDLEY_NEVER_INLINE
void grow(const std::size_t length)
{
// use the capacity the vector already has, else at least double it;
// never less than 64 characters, so that a small value does not
// reallocate for every few bytes
const std::size_t needed = position + length;
v->resize((std::max)(std::size_t{64}, needed <= v->capacity()
? v->capacity()
: (std::max)(needed, v->capacity() * 2)));
}
/// append @a length (at least max_reserve_size) characters that do not fit
/// the space ahead of the position: insert() copies them once into the
/// grown vector, where grow() would first zero the new space and then copy
/// over it - noticeable for a large string or binary value
JSON_HEDLEY_NEVER_INLINE
void append(const CharType* s, const std::size_t length)
{
v->resize(position);
if (v->capacity() - position < length)
{
// grow geometrically, with room for the writes that follow, so
// that the next grow() need not reallocate right away
v->reserve((std::max)(v->capacity() * 2, position + length + max_reserve_size));
}
v->insert(v->end(), s, s + length);
position = v->size();
}
std::vector<CharType, AllocatorType>* v;
/// number of characters of *v written so far
std::size_t position;
};
/// output adapter for byte vectors
template<typename CharType, typename AllocatorType = std::allocator<CharType>>
class output_vector_adapter : public output_adapter_protocol<CharType>
{
public:
explicit output_vector_adapter(std::vector<CharType, AllocatorType>& vec) noexcept
: v(vec)
{}
void write_character(CharType c)
void write_character(CharType c) override
{
v.push_back(c);
}
// no JSON_HEDLEY_NON_NULL here: binary_writer legitimately passes a null
// pointer with length 0 for empty strings/binary values. Appending an empty
// range is a no-op; the type-erased path tolerates this via the (unattributed)
// virtual base, and the concrete sink must do the same.
void write_characters(const CharType* s, std::size_t length)
// pointer with length 0 for empty strings/binary values; appending an empty
// range is a no-op
void write_characters(const CharType* s, std::size_t length) override
{
v.insert(v.end(), s, s + length);
}
@@ -82,33 +223,6 @@ class output_vector_sink
std::vector<CharType, AllocatorType>& v;
};
/// output adapter for byte vectors
///
/// The appending itself lives in output_vector_sink; this class only adds the
/// virtual output_adapter_protocol interface on top of it, so both the
/// type-erased and the templated path share one implementation.
template<typename CharType, typename AllocatorType = std::allocator<CharType>>
class output_vector_adapter : public output_adapter_protocol<CharType>
{
public:
explicit output_vector_adapter(std::vector<CharType, AllocatorType>& vec) noexcept
: sink(vec)
{}
void write_character(CharType c) override
{
sink.write_character(c);
}
void write_characters(const CharType* s, std::size_t length) override
{
sink.write_characters(s, length);
}
private:
output_vector_sink<CharType, AllocatorType> sink;
};
#ifndef JSON_NO_IO
/// output adapter for output streams
template<typename CharType>
@@ -188,8 +302,24 @@ class output_adapter_sink
oa->write_characters(s, length);
}
/// space for writing up to @a length characters (see
/// output_vector_sink::reserve)
CharType* reserve(const std::size_t length) noexcept
{
JSON_ASSERT(length <= max_reserve_size);
static_cast<void>(length);
return reserved.data();
}
/// write the first @a length characters written to the space from reserve()
void commit(const std::size_t length)
{
oa->write_characters(reserved.data(), length);
}
private:
output_adapter_t<CharType> oa;
std::array<CharType, max_reserve_size> reserved{};
};
/// @brief whether std::basic_string<CharType> has a non-deprecated std::char_traits
include/nlohmann/detail/output/serializer.hpp
+225 -112
View File
@@ -49,6 +49,12 @@ class serializer
using number_float_t = typename BasicJsonType::number_float_t;
using number_integer_t = typename BasicJsonType::number_integer_t;
using number_unsigned_t = typename BasicJsonType::number_unsigned_t;
/// type of the absolute value of an integer: number_unsigned_t, or its
/// unsigned counterpart if it is signed (it may be number_integer_t, #2573)
using number_magnitude_t = typename std::conditional <
std::is_integral<number_unsigned_t>::value && std::is_signed<number_unsigned_t>::value,
std::make_unsigned<number_unsigned_t>,
std::enable_if<true, number_unsigned_t >>::type::type;
using binary_char_t = typename BasicJsonType::binary_t::value_type;
public:
@@ -772,6 +778,33 @@ class serializer
break;
}
}
// A byte below 0x60 is a complete code point and needs no
// UTF-8 decoding. The scanner stops only at a control
// character, a quote, or a backslash in that range, so look up
// its escape sequence and write all 8 bytes of the table entry
// straight into the write buffer; only the length stored in the
// last byte of the entry is kept.
if (data[i] < 0x60)
{
// emit any bytes still pending in string_buffer first to
// preserve output order
if (bytes != 0)
{
put_buffer(string_buffer, bytes);
bytes = 0;
}
const auto& escape = ascii_escapes()[data[i]];
if (JSON_HEDLEY_UNLIKELY(write_buffer.size() - write_buffer_pos < escape.size()))
{
flush();
}
std::memcpy(write_buffer.data() + write_buffer_pos, escape.data(), escape.size());
write_buffer_pos += static_cast<std::size_t>(escape[7]);
bytes_after_last_accept = 0;
undumped_chars = 0;
continue;
}
}
const auto byte = static_cast<std::uint8_t>(s[i]);
@@ -780,92 +813,39 @@ class serializer
{
case UTF8_ACCEPT: // decode found a new code point
{
switch (codepoint)
// the code point is at least 0x60 (smaller ones are handled
// above) and is not printable ASCII (which the scanner
// copies): it is DEL (0x7F) under EnsureAscii or a non-ASCII
// character
if (EnsureAscii)
{
case 0x08: // backspace
JSON_ASSERT(codepoint >= 0x7F);
if (error_handler == error_handler_t::keep)
{
string_buffer[bytes++] = '\\';
string_buffer[bytes++] = 'b';
break;
// this character was buffered as raw bytes below
// in case it turned out to be part of an
// ill-formed sequence (which is kept as is); now
// that it decoded to a well-formed code point,
// undo that and \u-escape it like any other
// character instead
bytes = bytes_after_last_accept;
}
case 0x09: // horizontal tab
if (codepoint <= 0xFFFF)
{
string_buffer[bytes++] = '\\';
string_buffer[bytes++] = 't';
break;
write_u_escape(bytes, static_cast<std::uint16_t>(codepoint));
}
case 0x0A: // newline
else
{
string_buffer[bytes++] = '\\';
string_buffer[bytes++] = 'n';
break;
}
case 0x0C: // formfeed
{
string_buffer[bytes++] = '\\';
string_buffer[bytes++] = 'f';
break;
}
case 0x0D: // carriage return
{
string_buffer[bytes++] = '\\';
string_buffer[bytes++] = 'r';
break;
}
case 0x22: // quotation mark
{
string_buffer[bytes++] = '\\';
string_buffer[bytes++] = '"';
break;
}
case 0x5C: // reverse solidus
{
string_buffer[bytes++] = '\\';
string_buffer[bytes++] = '\\';
break;
}
default:
{
// escape control characters (0x00..0x1F) or, if
// EnsureAscii parameter is used, non-ASCII characters
if ((codepoint <= 0x1F) || (EnsureAscii && (codepoint >= 0x7F)))
{
if (EnsureAscii && error_handler == error_handler_t::keep)
{
// this character was buffered as raw bytes
// below in case it turned out to be part of
// an ill-formed sequence (which is kept as
// is); now that it decoded to a well-formed
// code point, undo that and \u-escape it
// like any other character instead
bytes = bytes_after_last_accept;
}
if (codepoint <= 0xFFFF)
{
write_u_escape(bytes, static_cast<std::uint16_t>(codepoint));
}
else
{
write_u_escape(bytes, static_cast<std::uint16_t>(0xD7C0u + (codepoint >> 10u)));
write_u_escape(bytes, static_cast<std::uint16_t>(0xDC00u + (codepoint & 0x3FFu)));
}
}
else
{
// copy byte to buffer (all previous bytes
// been copied have in default case above)
string_buffer[bytes++] = s[i];
}
break;
write_u_escape(bytes, static_cast<std::uint16_t>(0xD7C0u + (codepoint >> 10u)));
write_u_escape(bytes, static_cast<std::uint16_t>(0xDC00u + (codepoint & 0x3FFu)));
}
}
else
{
// copy byte to buffer (all previous bytes of the
// sequence have been copied in the default case below)
string_buffer[bytes++] = s[i];
}
// write buffer and reset index; there must be 13 bytes
// left, as this is the maximal number of bytes to be
@@ -888,7 +868,7 @@ class serializer
{
case error_handler_t::strict:
{
JSON_THROW(type_error::create(316, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", detail::hex_byte(byte)), nullptr));
JSON_THROW(type_error::create(exception_id::invalid_utf8, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", detail::hex_byte(byte)), nullptr));
}
case error_handler_t::ignore:
@@ -1021,7 +1001,7 @@ class serializer
{
case error_handler_t::strict:
{
JSON_THROW(type_error::create(316, concat("incomplete UTF-8 string; last byte: 0x", detail::hex_byte(static_cast<std::uint8_t>(s[s.size() - 1]))), nullptr));
JSON_THROW(type_error::create(exception_id::invalid_utf8, concat("incomplete UTF-8 string; last byte: 0x", detail::hex_byte(static_cast<std::uint8_t>(s[s.size() - 1]))), nullptr));
}
case error_handler_t::ignore:
@@ -1227,7 +1207,7 @@ class serializer
@param[in] x unsigned integer number to count its digits
@return number of decimal digits
*/
unsigned int count_digits(number_unsigned_t x) noexcept
unsigned int count_digits(number_magnitude_t x) noexcept
{
unsigned int n_digits = 1;
for (;;)
@@ -1253,6 +1233,121 @@ class serializer
}
}
/*!
@brief the JSON form of each character below 0x60
Entry c holds the escape sequence of character c - the short form for
\\b, \\t, \\n, \\f, \\r, \\" and \\\\, \\u00xx for the other control characters -
or c itself if it needs no escaping, padded with zeros to 7 bytes. The last
byte is the length of the sequence. The 8 bytes of an entry are copied at
once, so writing an escape needs neither a branch nor a byte-wise loop.
*/
static const std::array<std::array<char, 8>, 0x60>& ascii_escapes() noexcept
{
static const std::array<std::array<char, 8>, 0x60> escapes =
{
{
{{'\\', 'u', '0', '0', '0', '0', 0, 6}}, // 0x00
{{'\\', 'u', '0', '0', '0', '1', 0, 6}}, // 0x01
{{'\\', 'u', '0', '0', '0', '2', 0, 6}}, // 0x02
{{'\\', 'u', '0', '0', '0', '3', 0, 6}}, // 0x03
{{'\\', 'u', '0', '0', '0', '4', 0, 6}}, // 0x04
{{'\\', 'u', '0', '0', '0', '5', 0, 6}}, // 0x05
{{'\\', 'u', '0', '0', '0', '6', 0, 6}}, // 0x06
{{'\\', 'u', '0', '0', '0', '7', 0, 6}}, // 0x07
{{'\\', 'b', 0, 0, 0, 0, 0, 2}}, // 0x08
{{'\\', 't', 0, 0, 0, 0, 0, 2}}, // 0x09
{{'\\', 'n', 0, 0, 0, 0, 0, 2}}, // 0x0A
{{'\\', 'u', '0', '0', '0', 'b', 0, 6}}, // 0x0B
{{'\\', 'f', 0, 0, 0, 0, 0, 2}}, // 0x0C
{{'\\', 'r', 0, 0, 0, 0, 0, 2}}, // 0x0D
{{'\\', 'u', '0', '0', '0', 'e', 0, 6}}, // 0x0E
{{'\\', 'u', '0', '0', '0', 'f', 0, 6}}, // 0x0F
{{'\\', 'u', '0', '0', '1', '0', 0, 6}}, // 0x10
{{'\\', 'u', '0', '0', '1', '1', 0, 6}}, // 0x11
{{'\\', 'u', '0', '0', '1', '2', 0, 6}}, // 0x12
{{'\\', 'u', '0', '0', '1', '3', 0, 6}}, // 0x13
{{'\\', 'u', '0', '0', '1', '4', 0, 6}}, // 0x14
{{'\\', 'u', '0', '0', '1', '5', 0, 6}}, // 0x15
{{'\\', 'u', '0', '0', '1', '6', 0, 6}}, // 0x16
{{'\\', 'u', '0', '0', '1', '7', 0, 6}}, // 0x17
{{'\\', 'u', '0', '0', '1', '8', 0, 6}}, // 0x18
{{'\\', 'u', '0', '0', '1', '9', 0, 6}}, // 0x19
{{'\\', 'u', '0', '0', '1', 'a', 0, 6}}, // 0x1A
{{'\\', 'u', '0', '0', '1', 'b', 0, 6}}, // 0x1B
{{'\\', 'u', '0', '0', '1', 'c', 0, 6}}, // 0x1C
{{'\\', 'u', '0', '0', '1', 'd', 0, 6}}, // 0x1D
{{'\\', 'u', '0', '0', '1', 'e', 0, 6}}, // 0x1E
{{'\\', 'u', '0', '0', '1', 'f', 0, 6}}, // 0x1F
{{' ', 0, 0, 0, 0, 0, 0, 1}}, // 0x20
{{'!', 0, 0, 0, 0, 0, 0, 1}}, // 0x21
{{'\\', '"', 0, 0, 0, 0, 0, 2}}, // 0x22
{{'#', 0, 0, 0, 0, 0, 0, 1}}, // 0x23
{{'$', 0, 0, 0, 0, 0, 0, 1}}, // 0x24
{{'%', 0, 0, 0, 0, 0, 0, 1}}, // 0x25
{{'&', 0, 0, 0, 0, 0, 0, 1}}, // 0x26
{{'\'', 0, 0, 0, 0, 0, 0, 1}}, // 0x27
{{'(', 0, 0, 0, 0, 0, 0, 1}}, // 0x28
{{')', 0, 0, 0, 0, 0, 0, 1}}, // 0x29
{{'*', 0, 0, 0, 0, 0, 0, 1}}, // 0x2A
{{'+', 0, 0, 0, 0, 0, 0, 1}}, // 0x2B
{{',', 0, 0, 0, 0, 0, 0, 1}}, // 0x2C
{{'-', 0, 0, 0, 0, 0, 0, 1}}, // 0x2D
{{'.', 0, 0, 0, 0, 0, 0, 1}}, // 0x2E
{{'/', 0, 0, 0, 0, 0, 0, 1}}, // 0x2F
{{'0', 0, 0, 0, 0, 0, 0, 1}}, // 0x30
{{'1', 0, 0, 0, 0, 0, 0, 1}}, // 0x31
{{'2', 0, 0, 0, 0, 0, 0, 1}}, // 0x32
{{'3', 0, 0, 0, 0, 0, 0, 1}}, // 0x33
{{'4', 0, 0, 0, 0, 0, 0, 1}}, // 0x34
{{'5', 0, 0, 0, 0, 0, 0, 1}}, // 0x35
{{'6', 0, 0, 0, 0, 0, 0, 1}}, // 0x36
{{'7', 0, 0, 0, 0, 0, 0, 1}}, // 0x37
{{'8', 0, 0, 0, 0, 0, 0, 1}}, // 0x38
{{'9', 0, 0, 0, 0, 0, 0, 1}}, // 0x39
{{':', 0, 0, 0, 0, 0, 0, 1}}, // 0x3A
{{';', 0, 0, 0, 0, 0, 0, 1}}, // 0x3B
{{'<', 0, 0, 0, 0, 0, 0, 1}}, // 0x3C
{{'=', 0, 0, 0, 0, 0, 0, 1}}, // 0x3D
{{'>', 0, 0, 0, 0, 0, 0, 1}}, // 0x3E
{{'?', 0, 0, 0, 0, 0, 0, 1}}, // 0x3F
{{'@', 0, 0, 0, 0, 0, 0, 1}}, // 0x40
{{'A', 0, 0, 0, 0, 0, 0, 1}}, // 0x41
{{'B', 0, 0, 0, 0, 0, 0, 1}}, // 0x42
{{'C', 0, 0, 0, 0, 0, 0, 1}}, // 0x43
{{'D', 0, 0, 0, 0, 0, 0, 1}}, // 0x44
{{'E', 0, 0, 0, 0, 0, 0, 1}}, // 0x45
{{'F', 0, 0, 0, 0, 0, 0, 1}}, // 0x46
{{'G', 0, 0, 0, 0, 0, 0, 1}}, // 0x47
{{'H', 0, 0, 0, 0, 0, 0, 1}}, // 0x48
{{'I', 0, 0, 0, 0, 0, 0, 1}}, // 0x49
{{'J', 0, 0, 0, 0, 0, 0, 1}}, // 0x4A
{{'K', 0, 0, 0, 0, 0, 0, 1}}, // 0x4B
{{'L', 0, 0, 0, 0, 0, 0, 1}}, // 0x4C
{{'M', 0, 0, 0, 0, 0, 0, 1}}, // 0x4D
{{'N', 0, 0, 0, 0, 0, 0, 1}}, // 0x4E
{{'O', 0, 0, 0, 0, 0, 0, 1}}, // 0x4F
{{'P', 0, 0, 0, 0, 0, 0, 1}}, // 0x50
{{'Q', 0, 0, 0, 0, 0, 0, 1}}, // 0x51
{{'R', 0, 0, 0, 0, 0, 0, 1}}, // 0x52
{{'S', 0, 0, 0, 0, 0, 0, 1}}, // 0x53
{{'T', 0, 0, 0, 0, 0, 0, 1}}, // 0x54
{{'U', 0, 0, 0, 0, 0, 0, 1}}, // 0x55
{{'V', 0, 0, 0, 0, 0, 0, 1}}, // 0x56
{{'W', 0, 0, 0, 0, 0, 0, 1}}, // 0x57
{{'X', 0, 0, 0, 0, 0, 0, 1}}, // 0x58
{{'Y', 0, 0, 0, 0, 0, 0, 1}}, // 0x59
{{'Z', 0, 0, 0, 0, 0, 0, 1}}, // 0x5A
{{'[', 0, 0, 0, 0, 0, 0, 1}}, // 0x5B
{{'\\', '\\', 0, 0, 0, 0, 0, 2}}, // 0x5C
{{']', 0, 0, 0, 0, 0, 0, 1}}, // 0x5D
{{'^', 0, 0, 0, 0, 0, 0, 1}}, // 0x5E
{{'_', 0, 0, 0, 0, 0, 0, 1}}, // 0x5F
}
};
return escapes;
}
/*!
* @brief write a lowercase "\\uXXXX" escape sequence into @a string_buffer
*
@@ -1366,8 +1461,9 @@ class serializer
/*!
@brief dump an integer
Dump a given integer, appending it to @ref write_buffer. Works internally with
@a number_buffer.
Dump a given integer, appending it to @ref write_buffer (directly: copying
the digits from another buffer right after writing them waits until the
stores are done).
@param[in] x integer number (signed or unsigned) to dump
@tparam NumberType either @a number_integer_t or @a number_unsigned_t
@@ -1402,33 +1498,57 @@ class serializer
return;
}
// use a pointer to fill the buffer
auto buffer_ptr = number_buffer.begin(); // NOLINT(llvm-qualified-auto,readability-qualified-auto)
// use a pointer to fill the buffer (room for as much as number_buffer holds)
if (JSON_HEDLEY_UNLIKELY(write_buffer_pos + number_buffer.size() > write_buffer.size()))
{
flush();
}
auto* buffer_ptr = write_buffer.data() + write_buffer_pos;
number_unsigned_t abs_value;
number_magnitude_t abs_value;
unsigned int n_chars{};
// one byte for the minus sign
unsigned int n_chars = 0;
if (is_negative_number(x))
{
*buffer_ptr = '-';
abs_value = remove_sign(static_cast<number_integer_t>(x));
// account one more byte for the minus sign
n_chars = 1 + count_digits(abs_value);
n_chars = 1;
}
else
{
abs_value = static_cast<number_unsigned_t>(x);
n_chars = count_digits(abs_value);
abs_value = static_cast<number_magnitude_t>(x);
}
// up to 16 digits: eight at a time (as the digits of floats), written
// without leading zeros
if (abs_value < 10000000000000000u)
{
const auto value = static_cast<std::uint64_t>(abs_value); // fits: abs_value < 10^16
const std::uint64_t upper = value / 100000000u;
const std::uint64_t first = dtoa_impl::eight_digit_bytes(upper != 0 ? upper : value);
const auto leading = static_cast<unsigned>(count_leading_zeros(first) / 8); // (first is not 0)
char* const p = buffer_ptr + n_chars;
dtoa_impl::store_msb_first(p, (first << (8 * leading)) + 0x3030303030303030u);
n_chars += 8 - leading;
if (upper != 0)
{
dtoa_impl::store_msb_first(p + 8 - leading, dtoa_impl::eight_digit_bytes(value - (upper * 100000000u)) + 0x3030303030303030u);
n_chars += 8;
}
write_buffer_pos += n_chars;
return;
}
n_chars += count_digits(abs_value);
// spare 1 byte for '\0'
JSON_ASSERT(n_chars < number_buffer.size() - 1);
// jump to the end to generate the string from backward,
// so we later avoid reversing the result
buffer_ptr += static_cast<typename decltype(number_buffer)::difference_type>(n_chars);
buffer_ptr += n_chars;
// Fast int2ascii implementation inspired by "Fastware" talk by Andrei Alexandrescu
// See: https://www.youtube.com/watch?v=o4-CwDo2zpg
@@ -1451,14 +1571,13 @@ class serializer
*(--buffer_ptr) = static_cast<char>('0' + abs_value);
}
put_buffer(number_buffer, n_chars);
write_buffer_pos += n_chars;
}
/*!
@brief dump a floating-point number
Dump a given floating-point number, appending it to @ref write_buffer. Works internally
with @a number_buffer.
Dump a given floating-point number, appending it to @ref write_buffer.
@param[in] x floating-point number to dump
*/
@@ -1485,10 +1604,15 @@ class serializer
void dump_float(number_float_t x, std::true_type /*is_ieee_single_or_double*/)
{
auto* begin = number_buffer.data();
// directly into the write buffer: copying the text from number_buffer
// right after to_chars() wrote it waits until its stores are done
if (JSON_HEDLEY_UNLIKELY(write_buffer_pos + number_buffer.size() > write_buffer.size()))
{
flush();
}
auto* begin = write_buffer.data() + write_buffer_pos;
auto* end = ::nlohmann::detail::to_chars(begin, begin + number_buffer.size(), x);
put_buffer(number_buffer, static_cast<std::size_t>(end - begin));
write_buffer_pos += static_cast<std::size_t>(end - begin);
}
JSON_HEDLEY_NON_NULL(1)
@@ -1562,17 +1686,6 @@ class serializer
}
}
/*
* Overload to make the compiler happy while it is instantiating
* dump_integer for number_unsigned_t.
* Must never be called.
*/
number_unsigned_t remove_sign(number_unsigned_t x)
{
JSON_ASSERT(false); // NOLINT(cert-dcl03-c,hicpp-static-assert,misc-static-assert) LCOV_EXCL_LINE
return x; // LCOV_EXCL_LINE
}
/*
* Helper function for dump_integer
*
@@ -1582,10 +1695,10 @@ class serializer
* absolute values of INT_MIN and INT_MAX are usually not the same. See
* #1708 for details.
*/
number_unsigned_t remove_sign(number_integer_t x) noexcept
number_magnitude_t remove_sign(number_integer_t x) noexcept
{
JSON_ASSERT(x < 0);
return static_cast<number_unsigned_t>(-(x + 1)) + 1;
return static_cast<number_magnitude_t>(-(x + 1)) + 1;
}
private:
include/nlohmann/detail/string_escape.hpp
+33 -24
View File
@@ -9,6 +9,7 @@
#pragma once
#include <cstddef> // size_t
#include <utility> // move
#include <nlohmann/detail/abi_macros.hpp>
@@ -16,6 +17,25 @@ NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
/// append @a s to @a out, escaped like @ref escape does
template<typename StringType>
inline void escape_into(StringType& out, const StringType& s)
{
const std::size_t size = s.size();
std::size_t run = 0;
for (std::size_t i = 0; i < size; ++i)
{
const char c = s[i];
if (c == '~' || c == '/')
{
out.append(s.data() + run, i - run);
out.append(c == '~' ? "~0" : "~1", 2);
run = i + 1;
}
}
out.append(s.data() + run, size - run);
}
/*!
* @brief string escaping as described in RFC 6901 (Sect. 4)
* @param[in] s string to escape
@@ -24,39 +44,28 @@ namespace detail
* Note the order of escaping "~" to "~0" and "/" to "~1" is important.
*
* The string is rebuilt in a single pass, appending whole runs between the
* characters that need escaping. Scanning with find_first_of() keeps the
* common case -- nothing to escape -- as fast as a single search, while
* repeated replace() calls would move the tail of the string once per
* escaped character.
* characters that need escaping, while repeated replace() calls would move
* the tail of the string once per escaped character. @ref escape_into appends
* the escaped string to an existing one.
*/
template<typename StringType>
inline StringType escape(const StringType& s)
{
auto next_special = [&s](std::size_t from)
// a single scan for both special characters; nothing to escape is the common case
const std::size_t size = s.size();
std::size_t i = 0;
while (i < size && s[i] != '~' && s[i] != '/')
{
const auto tilde = s.find_first_of('~', from);
const auto slash = s.find_first_of('/', from);
return tilde < slash ? tilde : slash; // npos is the largest value
};
auto pos = next_special(0);
if (pos == StringType::npos)
++i;
}
if (i == size)
{
return s;
}
StringType result;
result.reserve(s.size() + 2);
std::size_t run = 0;
while (pos != StringType::npos)
{
result.append(s.data() + run, pos - run);
result.append(s[pos] == '~' ? "~0" : "~1", 2);
run = pos + 1;
pos = next_special(run);
}
result.append(s.data() + run, s.size() - run);
result.reserve(size + 2);
escape_into(result, s);
return result;
}
@@ -101,7 +110,7 @@ inline void unescape(StringType& s)
pos = s.find_first_of('~', run);
}
result.append(s.data() + run, s.size() - run);
s = result;
s = std::move(result);
}
} // namespace detail
include/nlohmann/detail/value_t.hpp
+67 -4
View File
@@ -14,7 +14,6 @@
#include <cstdint> // uint8_t
#include <limits> // numeric_limits
#include <string> // string
#include <type_traits> // is_signed
#include <nlohmann/detail/macro_scope.hpp>
#if JSON_HAS_THREE_WAY_COMPARISON
@@ -67,6 +66,39 @@ enum class value_t : std::uint8_t
discarded ///< discarded by the parser callback function
};
/*!
@brief the name of a JSON type, as returned by basic_json::type_name()
Used in exception messages; also by code that reports types without a
basic_json value at hand (such as the zero-copy view).
*/
inline const char* value_type_name(const value_t t) noexcept
{
switch (t)
{
case value_t::null:
return "null";
case value_t::object:
return "object";
case value_t::array:
return "array";
case value_t::string:
return "string";
case value_t::boolean:
return "boolean";
case value_t::binary:
return "binary";
case value_t::discarded:
return "discarded";
case value_t::number_integer:
case value_t::number_unsigned:
case value_t::number_float:
return "number";
default:
return "invalid";
}
}
/*!
@brief comparison operator for JSON types
@@ -117,6 +149,34 @@ inline bool operator<(const value_t lhs, const value_t rhs) noexcept
}
#endif
/*!
@brief whether a value of the given type owns heap memory
Strings, binaries, objects, and arrays are stored as pointers to allocated
values; all other types are stored directly in the union. Every enumerator is
listed so that -Wswitch-enum flags this function when a new type is added.
*/
inline bool owns_memory(const value_t t) noexcept
{
switch (t)
{
case value_t::object:
case value_t::array:
case value_t::string:
case value_t::binary:
return true;
case value_t::null:
case value_t::boolean:
case value_t::number_integer:
case value_t::number_unsigned:
case value_t::number_float:
case value_t::discarded:
default:
return false;
}
}
/*!
@brief compare an integer with a floating point number without precision loss
@@ -147,13 +207,16 @@ FloatType compare_integer_with_float(const IntegerType i, const FloatType f) noe
// values of IntegerType lie in [-bound, bound) when signed and in
// [0, bound) when unsigned; digits excludes the sign bit, so bound is a
// power of two that the float represents exactly
const FloatType bound = std::ldexp(static_cast<FloatType>(1), std::numeric_limits<IntegerType>::digits);
// power of two that the float represents exactly; the signedness comes
// from numeric_limits as well, because std::is_signed is false for class
// types such as 128-bit or multiprecision integers
using limits = std::numeric_limits<IntegerType>;
const FloatType bound = std::ldexp(static_cast<FloatType>(1), limits::digits);
if (f >= bound)
{
return ordered(-1);
}
if (std::is_signed<IntegerType>::value ? (f < -bound) : (f < static_cast<FloatType>(0)))
if (limits::is_signed ? (f < -bound) : (f < static_cast<FloatType>(0)))
{
return ordered(1);
}
include/nlohmann/detail/view/builder.hpp
+1111
View File
File diff suppressed because it is too large. Load diff
include/nlohmann/detail/view/compare.hpp
+320
View File
@@ -0,0 +1,320 @@
// __ _____ _____ _____
// __| | __| | | | 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 <algorithm> // sort, stable_sort
#include <cstddef> // size_t
#include <string> // string
#include <utility> // move, pair
#include <vector> // vector
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
// Equality of views, and of views with basic_json values, with the semantics
// of basic_json's operator== applied to the values parse() would produce:
// numbers compare by value across their types, an object is compared by its
// members with duplicate keys resolved as parse() resolves them (the last
// value, at the position of the first occurrence), and in document order if
// the object type keeps an order (ordered_json), by key otherwise.
/// one side of a comparison: a view
template<typename BasicJsonType, typename View>
class view_side
{
public:
using string_view_t = typename View::string_view_t;
explicit view_side(const View& v) noexcept
: m_view(v)
{}
value_t type() const noexcept
{
return m_view.type();
}
std::size_t size() const noexcept
{
return m_view.size();
}
string_view_t string() const
{
return m_view.get_string();
}
/// a number, boolean, or null as a basic_json value (no allocation)
BasicJsonType scalar() const
{
switch (m_view.type())
{
case value_t::number_integer:
return BasicJsonType(m_view.template get<typename BasicJsonType::number_integer_t>());
case value_t::number_unsigned:
return BasicJsonType(m_view.template get<typename BasicJsonType::number_unsigned_t>());
case value_t::number_float:
return BasicJsonType(m_view.template get<typename BasicJsonType::number_float_t>());
case value_t::boolean:
return BasicJsonType(m_view.template get<bool>());
case value_t::null:
case value_t::object:
case value_t::array:
case value_t::string:
case value_t::binary:
case value_t::discarded:
default:
return BasicJsonType(nullptr);
}
}
void elements(std::vector<view_side>& out) const
{
out.reserve(m_view.size());
for (const View e : m_view)
{
out.emplace_back(e);
}
}
/// the members as parse() keeps them: one per key, the last value at the
/// position of the first occurrence; in that order, or sorted by key
void members(std::vector<std::pair<string_view_t, view_side>>& out, bool ordered) const
{
struct member
{
string_view_t key;
View value;
std::size_t position;
};
std::vector<member> all;
all.reserve(m_view.size());
std::size_t position = 0;
for (auto it = m_view.begin(); it != m_view.end(); ++it)
{
all.push_back(member{it.key(), it.value(), position++});
}
std::stable_sort(all.begin(), all.end(), [](const member & a, const member & b)
{
return a.key < b.key;
});
std::vector<member> unique;
unique.reserve(all.size());
for (std::size_t i = 0; i < all.size();)
{
std::size_t last = i;
while (last + 1 < all.size() && all[last + 1].key == all[i].key)
{
++last;
}
unique.push_back(member{all[i].key, all[last].value, all[i].position});
i = last + 1;
}
if (ordered)
{
std::sort(unique.begin(), unique.end(), [](const member & a, const member & b)
{
return a.position < b.position;
});
}
out.reserve(unique.size());
for (const member& m : unique)
{
out.emplace_back(m.key, view_side(m.value));
}
}
private:
View m_view;
};
/// the other side of a comparison: a basic_json value
template<typename BasicJsonType, typename StringView>
class json_side
{
public:
using string_view_t = StringView;
explicit json_side(const BasicJsonType& j) noexcept
: m_json(&j)
{}
value_t type() const noexcept
{
return m_json->type();
}
std::size_t size() const noexcept
{
return m_json->size();
}
string_view_t string() const
{
const auto& s = m_json->template get_ref<const typename BasicJsonType::string_t&>();
return string_view_t(s.data(), s.size());
}
BasicJsonType scalar() const
{
return *m_json;
}
void elements(std::vector<json_side>& out) const
{
out.reserve(m_json->size());
for (const auto& e : *m_json)
{
out.emplace_back(e);
}
}
void members(std::vector<std::pair<string_view_t, json_side>>& out, bool ordered) const
{
out.reserve(m_json->size());
for (auto it = m_json->cbegin(); it != m_json->cend(); ++it)
{
out.emplace_back(string_view_t(it.key().data(), it.key().size()), json_side(it.value()));
}
if (!ordered)
{
std::sort(out.begin(), out.end(), [](const std::pair<string_view_t, json_side>& a, const std::pair<string_view_t, json_side>& b)
{
return a.first < b.first;
});
}
}
private:
const BasicJsonType* m_json;
};
inline bool is_number(value_t t) noexcept
{
return t == value_t::number_integer || t == value_t::number_unsigned || t == value_t::number_float;
}
/// whether two sides are equal; iterative, so that the nesting depth is
/// limited by memory only
template<typename BasicJsonType, typename A, typename B>
bool equal(const A& a0, const B& b0)
{
using string_view_t = typename A::string_view_t;
const bool ordered = is_ordered_map<typename BasicJsonType::object_t>::value;
struct frame
{
std::vector<A> elements_a{};
std::vector<B> elements_b{};
std::vector<std::pair<string_view_t, A>> members_a{};
std::vector<std::pair<string_view_t, B>> members_b{};
bool object = false;
std::size_t next = 0;
};
std::vector<frame> stack;
A a = a0;
B b = b0;
for (;;)
{
const value_t ta = a.type();
const value_t tb = b.type();
if (ta == value_t::discarded || tb == value_t::discarded)
{
// basic_json decides (JSON_USE_LEGACY_DISCARDED_VALUE_COMPARISON)
if (ta != tb || !(BasicJsonType(value_t::discarded) == BasicJsonType(value_t::discarded)))
{
return false;
}
}
else
{
if (ta != tb && !(is_number(ta) && is_number(tb))) // numbers of different types can be equal
{
return false;
}
if (ta == value_t::string)
{
if (a.string() != b.string())
{
return false;
}
}
else if (ta == value_t::array || ta == value_t::object)
{
if (a.size() != b.size() && ta == value_t::array)
{
return false;
}
frame f;
f.object = ta == value_t::object;
if (f.object)
{
a.members(f.members_a, ordered);
b.members(f.members_b, ordered);
if (f.members_a.size() != f.members_b.size())
{
return false;
}
}
else
{
a.elements(f.elements_a);
b.elements(f.elements_b);
}
stack.push_back(std::move(f));
}
else if (a.scalar() != b.scalar()) // numbers (also of different types), null, boolean
{
return false;
}
}
// the next pair of values
for (;;)
{
if (stack.empty())
{
return true;
}
frame& f = stack.back();
const std::size_t count = f.object ? f.members_a.size() : f.elements_a.size();
if (f.next == count)
{
stack.pop_back(); // (f dangles now, and is bound again after continue)
continue;
}
if (f.object)
{
if (!(f.members_a[f.next].first == f.members_b[f.next].first))
{
return false;
}
a = f.members_a[f.next].second;
b = f.members_b[f.next].second;
}
else
{
a = f.elements_a[f.next];
b = f.elements_b[f.next];
}
++f.next;
break;
}
}
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/document_data.hpp
+299
View File
@@ -0,0 +1,299 @@
// __ _____ _____ _____
// __| | __| | | | 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 <array> // array
#include <cstddef> // size_t
#include <cstdint> // uint8_t, uint32_t
#include <cstring> // memcmp, memcpy
#include <limits> // numeric_limits
#include <map> // map
#include <memory> // unique_ptr
#include <new> // bad_alloc, operator new, placement new
#include <string> // string
#include <vector> // vector
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
#include <nlohmann/detail/view/node.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/// storage of a parsed document; heap-allocated (header and an initial node
/// array in one block) so that views survive moves of the owning document
struct document_data
{
const char* src = nullptr;
std::size_t size = 0;
node* nodes = nullptr; ///< the node index (see node.hpp)
std::size_t node_count = 0;
std::size_t node_capacity = 0;
node* inline_nodes = nullptr; ///< node array allocated together with this header
std::size_t inline_capacity = 0;
std::size_t max_depth = 0; ///< deepest nesting of arrays and objects (the root container is depth 1)
std::vector<char> arena; ///< decoded strings that contained escapes (no terminator: they are handed out with their length)
std::size_t arena_size = 0; ///< bytes of decoded strings at base[1] (the arena, or those of a loaded image)
std::string owned; ///< owned copy of the input, if any (a std::string, so that its NUL serves as the parser's sentinel)
std::vector<std::uint8_t> owned_image; ///< a loaded image the document owns (the text and the decoded strings point into it)
// hash indexes of the keys of large objects (see object_index.hpp)
static constexpr std::uint32_t index_min_members = 128;
struct object_index
{
std::size_t start; ///< first slot in index_slots
std::uint32_t mask; ///< slot count - 1 (a power of two minus one)
};
std::vector<object_index> indexes;
std::vector<std::uint32_t> index_slots;
std::vector<std::uint32_t> large_objects; ///< positions of the objects to index (noted while parsing)
std::array<const char*, 4> base = {{nullptr, nullptr, nullptr, nullptr}}; ///< string bases: source, arena, edit arena, unused (indexed by flags & node_flags::storage)
bool discarded = true;
/// The storage of edits (editable documents only; see edit_storage.hpp).
/// No edit moves or resizes the parsed index, and the nodes of values
/// written by edits never move either, so a view stays valid whenever it
/// was taken, before the first edit or between later ones: an array/object
/// whose elements change gets node_flags::moved, and its elements then live
/// in a separate sequence (a header node, then the entries), whose entries
/// link to the values.
struct edit_state
{
std::vector<node*> moved{}; ///< element sequences of moved arrays/objects (header node first) // NOLINT(readability-redundant-member-init)
std::vector<std::size_t> moved_cap{}; ///< capacity in nodes of a growable block; 0: a fixed sequence (a new value) // NOLINT(readability-redundant-member-init)
std::vector<std::unique_ptr<node[]>> chunks{}; ///< storage of new values and blocks; never moved // NOLINT(readability-redundant-member-init,cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
std::map<const node*, node*> regions{}; ///< new arrays/objects: root -> container that uses it as its element sequence (nullptr: linked from a block) // NOLINT(readability-redundant-member-init)
node* chunk_cur = nullptr;
node* chunk_end = nullptr;
std::size_t chunk_next = 64;
std::vector<std::unique_ptr<char[]>> texts{}; ///< edit arena, the current buffer last; earlier ones stay alive for string views // NOLINT(readability-redundant-member-init,cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
std::size_t text_used = 0;
std::size_t text_cap = 0;
std::size_t bytes = 0; ///< memory held by edits
};
std::unique_ptr<edit_state> edits; ///< created by the first edit
/// One allocation for the header and room for `count` nodes, so that a
/// small document needs one allocation instead of two. Large documents get
/// a separate node array instead (so it can be trimmed). When a document
/// outgrows the inline array, that array stays unused: at most 256 nodes
/// (4 KiB), and only for documents whose estimate was too small.
static document_data* create(std::size_t count)
{
count = count <= 256 ? count : 0;
void* mem = ::operator new (sizeof(document_data) + (count * sizeof(node)));
auto* d = new (mem) document_data(); // NOLINT(cppcoreguidelines-owning-memory): owned by the returned pointer, freed by deleter
// (aligned: sizeof is a multiple of the alignment; through void*, as GCC's -Wcast-align wants)
// (null without inline nodes, not a pointer past the end of the allocation)
d->inline_nodes = count == 0 ? nullptr : static_cast<node*>(static_cast<void*>(static_cast<char*>(mem) + sizeof(document_data))); // NOLINT(bugprone-casting-through-void)
d->inline_capacity = count;
d->nodes = d->inline_nodes;
d->node_capacity = count;
return d;
}
struct deleter
{
void operator()(document_data* d) const noexcept
{
d->~document_data();
::operator delete (d);
}
};
/// user-provided so that the class-type members can be initialized in the
/// member initialization list (-Weffc++ asks for it, and old GCC rejects a
/// defaulted constructor whose exception specification differs from the
/// implicit one); they cannot take default member initializers, which old
/// Clang (3.4-3.6) rejects. The other members have default member
/// initializers. noexcept: create() constructs into raw memory and could not
/// release it if this threw (the std::vector and std::string default
/// constructors do not allocate).
document_data() noexcept
: arena() // NOLINT(readability-redundant-member-init)
, owned() // NOLINT(readability-redundant-member-init)
, owned_image() // NOLINT(readability-redundant-member-init)
, indexes() // NOLINT(readability-redundant-member-init)
, index_slots() // NOLINT(readability-redundant-member-init)
, large_objects() // NOLINT(readability-redundant-member-init)
, edits() // NOLINT(readability-redundant-member-init)
{}
document_data(const document_data&) = delete;
document_data(document_data&&) = delete;
document_data& operator=(const document_data&) = delete;
document_data& operator=(document_data&&) = delete;
~document_data()
{
release();
}
void release() noexcept
{
if (nodes != inline_nodes)
{
::operator delete (nodes);
}
nodes = inline_nodes;
node_capacity = inline_capacity;
}
/// the largest node count whose size in bytes fits a std::size_t
static constexpr std::size_t max_nodes() noexcept
{
return (std::numeric_limits<std::size_t>::max)() / sizeof(node);
}
[[noreturn]] NLOHMANN_VIEW_NOINLINE static void throw_bad_alloc()
{
NLOHMANN_VIEW_THROW(std::bad_alloc());
}
/// make room for n nodes; keeps the first node_count nodes (throws
/// std::bad_alloc for a count that does not fit the address space,
/// instead of wrapping around in n * sizeof(node))
void reserve(std::size_t n)
{
if (n <= node_capacity)
{
return;
}
if (NLOHMANN_VIEW_UNLIKELY(n > max_nodes()))
{
throw_bad_alloc();
}
node* fresh = static_cast<node*>(::operator new (n * sizeof(node)));
if (node_count != 0)
{
std::memcpy(fresh, nodes, node_count * sizeof(node));
}
release();
nodes = fresh;
node_capacity = n;
}
const char* str(const node& n) const noexcept
{
return base[n.flags & node_flags::storage] + n.off;
}
/// whether the string of node k (a key) is the n bytes at key
bool key_equals(const node& k, const char* key, std::size_t n) const noexcept
{
return k.len == n && (n == 0 || std::memcmp(str(k), key, n) == 0);
}
/// the node after n's subtree (containers span `next` nodes, scalars one)
static NLOHMANN_VIEW_ALWAYS_INLINE const node* after(const node* n) noexcept
{
return n + (is_container(*n) ? n->next : 1u);
}
/// first element (array) or first key (object) of a container
static NLOHMANN_VIEW_ALWAYS_INLINE const node* first_child(const node* n) noexcept
{
return n + 1;
}
/// end of the elements of a container
static NLOHMANN_VIEW_ALWAYS_INLINE const node* child_end(const node* n) noexcept
{
return n + n->next;
}
/// (editable documents) first element or key, also of a moved container
NLOHMANN_VIEW_ALWAYS_INLINE const node* first_child_edited(const node* n) const noexcept
{
return NLOHMANN_VIEW_LIKELY((n->flags & node_flags::moved) == 0) ? n + 1 : edits->moved[n->off] + 1;
}
/// (editable documents) end of the elements, also of a moved container
NLOHMANN_VIEW_ALWAYS_INLINE const node* child_end_edited(const node* n) const noexcept
{
if (NLOHMANN_VIEW_LIKELY((n->flags & node_flags::moved) == 0))
{
return n + n->next;
}
const node* const h = edits->moved[n->off];
return h + h->next;
}
/// (editable documents) the value at an element position: entries of
/// moved sequences are links. The link case is out of line, so that this
/// compiles to a predicted branch rather than a select that delays the
/// following loads.
static NLOHMANN_VIEW_ALWAYS_INLINE const node* deref(const node* n) noexcept
{
return NLOHMANN_VIEW_LIKELY(n->kind != kind_link) ? n : follow_link(n);
}
static NLOHMANN_VIEW_NOINLINE const node* follow_link(const node* n) noexcept
{
return link_target(*n);
}
};
/// How the index is walked: views of read-only documents follow the node
/// array alone and compile without any of the edit handling; views of
/// editable documents also follow moved element sequences and links.
template<bool Editable>
struct navigation
{
/// whether the walk follows edits (the template argument as a runtime
/// condition: `Editable && ...` is a constant condition for MSVC, C4127)
static NLOHMANN_VIEW_ALWAYS_INLINE bool editable() noexcept
{
return false;
}
static NLOHMANN_VIEW_ALWAYS_INLINE const node* first(const document_data& /*d*/, const node* n) noexcept
{
return n + 1;
}
static NLOHMANN_VIEW_ALWAYS_INLINE const node* end(const document_data& /*d*/, const node* n) noexcept
{
return n + n->next;
}
static NLOHMANN_VIEW_ALWAYS_INLINE const node* value(const node* n) noexcept
{
return n;
}
};
template<>
struct navigation<true>
{
static NLOHMANN_VIEW_ALWAYS_INLINE bool editable() noexcept
{
return true;
}
static NLOHMANN_VIEW_ALWAYS_INLINE const node* first(const document_data& d, const node* n) noexcept
{
return d.first_child_edited(n);
}
static NLOHMANN_VIEW_ALWAYS_INLINE const node* end(const document_data& d, const node* n) noexcept
{
return d.child_end_edited(n);
}
static NLOHMANN_VIEW_ALWAYS_INLINE const node* value(const node* n) noexcept
{
return document_data::deref(n);
}
};
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/edit.hpp
+883
View File
@@ -0,0 +1,883 @@
// __ _____ _____ _____
// __| | __| | | | 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 <array> // array
#include <cmath> // isinf, isnan
#include <cstddef> // size_t
#include <cstdint> // int64_t, uint8_t, uint32_t, uint64_t
#include <cstring> // memmove
#include <limits> // numeric_limits
#include <string> // string, to_string
#include <type_traits> // decay, enable_if, integral_constant, is_arithmetic, is_convertible, is_floating_point, is_same, is_signed
#include <utility> // forward
#include <vector> // vector
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/document_data.hpp>
#include <nlohmann/detail/view/edit_storage.hpp>
#include <nlohmann/detail/view/errors.hpp>
#include <nlohmann/detail/view/lookup.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
#include <nlohmann/detail/view/node.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
template<typename BasicJsonType, bool Editable>
class basic_json_view;
namespace detail
{
namespace view
{
/// the index of the first true condition (the number of conditions if none is)
template<bool... Conditions>
struct first_true : std::integral_constant<int, 0> {};
template<bool... Conditions>
struct first_true<false, Conditions...> : std::integral_constant < int, 1 + first_true<Conditions...>::value > {};
/// Checks a string the way basic_json's serializer does when it writes it
/// (type_error.316 with the same message), so that an editable document
/// only holds valid UTF-8: the error is at the first byte that no
/// well-formed sequence can continue with (Unicode, Table 3-7).
inline void check_utf8(const char* s, std::size_t n)
{
const auto* const p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
const auto hex = [](unsigned char c)
{
constexpr const char* digits = "0123456789ABCDEF";
return std::string{digits[c >> 4u], digits[c & 0xFu]};
};
for (std::size_t i = 0; i < n;)
{
const unsigned char c = p[i];
if (c < 0x80)
{
++i;
continue;
}
std::size_t len = 0;
unsigned char lo = 0x80;
unsigned char hi = 0xBF;
if (c >= 0xC2 && c <= 0xDF)
{
len = 2;
}
else if (c >= 0xE0 && c <= 0xEF)
{
len = 3;
lo = c == 0xE0 ? 0xA0 : 0x80;
hi = c == 0xED ? 0x9F : 0xBF;
}
else if (c >= 0xF0 && c <= 0xF4)
{
len = 4;
lo = c == 0xF0 ? 0x90 : 0x80;
hi = c == 0xF4 ? 0x8F : 0xBF;
}
else
{
throw_type_error(316, concat("invalid UTF-8 byte at index ", std::to_string(i), ": 0x", hex(c)));
}
for (std::size_t k = 1; k < len; ++k)
{
if (i + k == n)
{
throw_type_error(316, concat("incomplete UTF-8 string; last byte: 0x", hex(p[n - 1])));
}
const unsigned char b = p[i + k];
if (b < (k == 1 ? lo : 0x80) || b > (k == 1 ? hi : 0xBF))
{
throw_type_error(316, concat("invalid UTF-8 byte at index ", std::to_string(i + k), ": 0x", hex(b)));
}
}
i += len;
}
}
/*!
@brief the edits of an editable basic_json_document
Values are accepted as views (of any document), BasicJsonType values, and
everything BasicJsonType can be constructed from. The source text is never
written: new values go to storage owned by the document (see
edit_storage.hpp).
*/
template<typename BasicJsonType, typename View>
class editor
{
using number_integer_t = typename BasicJsonType::number_integer_t;
using number_unsigned_t = typename BasicJsonType::number_unsigned_t;
using number_float_t = typename BasicJsonType::number_float_t;
using string_t = typename BasicJsonType::string_t;
using string_view_t = typename View::string_view_t;
using nav = navigation<true>;
public:
explicit editor(document_data& d) noexcept
: m_doc(d)
{}
/// replace a value; returns its view
template<typename V>
View set(const View& target, V&& value)
{
node* const slot = own(target);
const encoded e = encode(std::forward<V>(value));
assign(slot, e, nullptr, false);
return View(&m_doc, slot);
}
/// set a member (appended if missing; a null value becomes an object);
/// returns a view of the member value
template<typename V>
View set(const View& object, string_view_t key, V&& value)
{
node* const o = own(object);
if (o->kind != static_cast<std::uint8_t>(value_t::object) && o->kind != static_cast<std::uint8_t>(value_t::null))
{
throw_type_error(305, "cannot use operator[] with a string argument with ", object.type_name());
}
check_utf8(key.data(), key.size());
const encoded e = encode(std::forward<V>(value));
if (o->kind == static_cast<std::uint8_t>(value_t::null))
{
become_empty(o, value_t::object);
}
// an existing member: assign it (and drop later duplicates, so that
// lookups, iteration, and materialize() agree)
node* slot = nullptr;
bool duplicates = false;
for (const node* k = nav::first(m_doc, o), *end = nav::end(m_doc, o); k != end; k = document_data::after(k + 1))
{
if (key_equals(*k, key))
{
if (slot != nullptr)
{
duplicates = true;
break;
}
slot = const_cast<node*>(nav::value(k + 1)); // NOLINT(cppcoreguidelines-pro-type-const-cast): the nodes belong to this document
}
}
if (slot != nullptr)
{
if (duplicates)
{
erase_members(o, key, true);
}
assign(slot, e, o, true);
return View(&m_doc, slot);
}
const node k = string_node(key.data(), key.size());
slot = new_slot(e);
node* const h = block_of(m_doc, o, 2);
h[h->next] = k;
make_link(h[h->next + 1], slot);
h->next += 2;
++h->len;
++o->len;
return View(&m_doc, slot);
}
/// assign an existing array element; returns a view of it
template<typename V>
View set(const View& array, std::size_t idx, V&& value)
{
node* const a = own(array);
if (a->kind != static_cast<std::uint8_t>(value_t::array))
{
throw_type_error(305, "cannot use operator[] with a numeric argument with ", array.type_name());
}
check_index(idx, a->len);
const encoded e = encode(std::forward<V>(value));
node* const slot = const_cast<node*>(nav::value(element_at<true>(m_doc, a, idx))); // NOLINT(cppcoreguidelines-pro-type-const-cast)
assign(slot, e, a, true);
return View(&m_doc, slot);
}
/// append to an array (a null value becomes an array); returns a view of
/// the new element
template<typename V>
View push_back(const View& array, V&& value)
{
node* const a = own(array);
if (a->kind != static_cast<std::uint8_t>(value_t::array) && a->kind != static_cast<std::uint8_t>(value_t::null))
{
throw_type_error(308, "cannot use push_back() with ", array.type_name());
}
const encoded e = encode(std::forward<V>(value));
if (a->kind == static_cast<std::uint8_t>(value_t::null))
{
become_empty(a, value_t::array);
}
node* const slot = new_slot(e);
node* const h = block_of(m_doc, a, 1);
make_link(h[h->next], slot);
++h->next;
++h->len;
++a->len;
return View(&m_doc, slot);
}
/// insert into an array before position idx (idx <= size()); returns a
/// view of the new element
template<typename V>
View insert(const View& array, std::size_t idx, V&& value)
{
node* const a = own(array);
if (a->kind != static_cast<std::uint8_t>(value_t::array))
{
throw_type_error(309, "cannot use insert() with ", array.type_name());
}
check_index(idx, a->len + 1);
const encoded e = encode(std::forward<V>(value));
node* const slot = new_slot(e);
node* const h = block_of(m_doc, a, 1);
std::memmove(h + 2 + idx, h + 1 + idx, (h->next - 1 - idx) * sizeof(node));
make_link(h[1 + idx], slot);
++h->next;
++h->len;
++a->len;
return View(&m_doc, slot);
}
/// remove all members with this key; returns their number
std::size_t erase(const View& object, string_view_t key)
{
node* const o = own(object);
if (o->kind != static_cast<std::uint8_t>(value_t::object))
{
throw_type_error(307, "cannot use erase() with ", object.type_name());
}
for (const node* k = nav::first(m_doc, o), *end = nav::end(m_doc, o); k != end; k = document_data::after(k + 1))
{
if (key_equals(*k, key))
{
return erase_members(o, key, false);
}
}
return 0;
}
/// remove an array element
void erase(const View& array, std::size_t idx)
{
node* const a = own(array);
if (a->kind != static_cast<std::uint8_t>(value_t::array))
{
throw_type_error(307, "cannot use erase() with ", array.type_name());
}
check_index(idx, a->len);
node* const h = block_of(m_doc, a, 0);
std::memmove(h + 1 + idx, h + 2 + idx, (h->next - 2 - idx) * sizeof(node));
--h->next;
--h->len;
--a->len;
}
private:
/// an encoded value: a scalar node, or the root of a new array/object
struct encoded
{
node scalar{};
node* region = nullptr;
};
/// the node of a view of this document
node* own(const View& v)
{
if (NLOHMANN_VIEW_UNLIKELY(v.m_doc != &m_doc || v.m_node == nullptr))
{
throw_invalid_iterator(202, "view does not belong to this document");
}
edit_state_of(m_doc);
return const_cast<node*>(v.m_node); // NOLINT(cppcoreguidelines-pro-type-const-cast): the nodes belong to this document
}
static void check_index(std::size_t idx, std::size_t limit)
{
if (idx >= limit)
{
throw_out_of_range(401, concat("array index ", std::to_string(idx), " is out of range"));
}
}
bool key_equals(const node& k, string_view_t key) const noexcept
{
return m_doc.key_equals(k, key.data(), key.size());
}
/// remove the members with this key (all, or all but the first) from an object
std::size_t erase_members(node* o, string_view_t key, bool keep_first)
{
node* const h = block_of(m_doc, o, 0);
node* w = h + 1;
std::size_t erased = 0;
bool kept = false;
for (const node* r = h + 1, *end = h + h->next; r != end; r += 2)
{
const bool match = key_equals(*r, key);
if (match && (kept || !keep_first))
{
++erased;
continue;
}
kept = kept || match;
if (w != r)
{
w[0] = r[0];
w[1] = r[1];
}
w += 2;
}
h->next = static_cast<std::uint32_t>(w - h);
h->len -= static_cast<std::uint32_t>(erased);
o->len -= static_cast<std::uint32_t>(erased);
return erased;
}
/// turn a null into an empty array/object in place
static void become_empty(node* n, value_t k) noexcept
{
const std::uint8_t linked = n->flags & node_flags::linked;
*n = node{};
n->kind = static_cast<std::uint8_t>(k);
n->flags = static_cast<std::uint8_t>(node_flags::is_new | linked);
n->next = 1;
}
/// Replace the value at slot; `parent` is the container whose elements
/// include slot (if known).
void assign(node* slot, const encoded& e, node* parent, bool parent_known)
{
// an entry of a moved sequence links to the slot: it can take any extent
const std::uint8_t linked = slot->flags & node_flags::linked;
if (e.region == nullptr)
{
if (is_container(*slot) && slot->next > 1 && slot != m_doc.nodes && linked == 0)
{
// The slot spans its old elements in the enclosing sequence, but
// a scalar is one node: the enclosing container first switches to
// links (then the extent of the slot no longer matters). Looking
// for the container is linear in the size of the document, so
// links (which are marked in the slot) avoid it.
node* const p = parent_known ? parent : find_parent(m_doc, slot);
if (p != nullptr && ((p->flags & node_flags::moved) == 0 || moved_capacity(m_doc, p) == 0))
{
block_of(m_doc, p, 0);
}
}
*slot = e.scalar;
slot->flags = static_cast<std::uint8_t>(slot->flags | linked);
return;
}
// an array/object: the slot keeps its extent (so that the enclosing
// sequence still steps over it), and the elements come from the new
// sequence
const node* const r = e.region;
const std::uint32_t extent = is_container(*slot) ? slot->next : 1;
const bool was_moved = (slot->flags & node_flags::moved) != 0;
// Everything that can throw happens before the slot changes: a slot
// that is a container without the moved flag would show its old
// elements. reserve_moved() makes the set_moved() below, which sets
// the flag, safe; the entry of `regions` exists already (encode()
// added it), so that the assignment at the end does not allocate.
if (!was_moved)
{
reserve_moved(m_doc);
}
slot->kind = r->kind;
slot->extra = 0;
slot->len = r->len;
slot->next = extent;
// (set_moved() adds the moved flag to a slot that does not have it yet)
slot->flags = static_cast<std::uint8_t>((was_moved ? node_flags::moved | node_flags::is_new : 0) | linked);
set_moved(m_doc, slot, e.region, 0);
edit_state_of(m_doc).regions[e.region] = slot;
}
/// a node for a new element (links point to it; it never moves)
node* new_slot(const encoded& e)
{
if (e.region != nullptr)
{
return e.region;
}
node* const s = alloc_nodes(m_doc, 1);
*s = e.scalar;
return s;
}
//////////////
// encoding //
//////////////
template<int N>
using encode_tag = std::integral_constant<int, N>;
template<typename T>
struct is_view : std::false_type {};
template<typename J, bool E>
struct is_view<basic_json_view<J, E>> : std::true_type {};
template<typename V>
encoded encode(V&& v)
{
using D = typename std::decay<V>::type;
return encode_impl(std::forward<V>(v), encode_tag<first_true<is_view<D>::value,
std::is_same<D, BasicJsonType>::value,
std::is_same<D, std::nullptr_t>::value,
std::is_same<D, bool>::value,
std::is_arithmetic<D>::value,
std::is_convertible<const D&, string_view_t>::value>::value> {});
}
/// a view of any document (copied; nothing is shared with it)
template<typename J, bool E>
encoded encode_impl(const basic_json_view<J, E>& v, encode_tag<0> /*view*/)
{
if (NLOHMANN_VIEW_UNLIKELY(v.m_node == nullptr))
{
throw_type_error(302, "type must be a value, but is ", "discarded");
}
encoded r;
if (!is_container(*v.m_node))
{
r.scalar = copy_scalar(*v.m_doc, *v.m_node);
return r;
}
r.region = alloc_nodes(m_doc, count_nodes<E>(*v.m_doc, v.m_node));
fill_nodes<E>(*v.m_doc, v.m_node, r.region);
edit_state_of(m_doc).regions.emplace(r.region, nullptr);
return r;
}
encoded encode_impl(const BasicJsonType& j, encode_tag<1> /*json*/)
{
encoded r;
if (!j.is_structured())
{
r.scalar = json_scalar(j);
return r;
}
r.region = alloc_nodes(m_doc, count_nodes(j));
fill_nodes(j, r.region);
edit_state_of(m_doc).regions.emplace(r.region, nullptr);
return r;
}
encoded encode_impl(std::nullptr_t /*unused*/, encode_tag<2> /*null*/)
{
encoded r;
r.scalar = plain_node(value_t::null);
return r;
}
encoded encode_impl(bool b, encode_tag<3> /*boolean*/)
{
encoded r;
r.scalar = plain_node(value_t::boolean);
r.scalar.flags = static_cast<std::uint8_t>(r.scalar.flags | (b ? node_flags::is_true : 0));
return r;
}
template<typename T>
encoded encode_impl(T x, encode_tag<4> /*number*/)
{
encoded r;
r.scalar = number_node(x, std::integral_constant<int, first_true<std::is_floating_point<T>::value, std::is_signed<T>::value>::value> {});
return r;
}
template<typename T>
encoded encode_impl(const T& s, encode_tag<5> /*string*/)
{
const string_view_t sv(s);
check_utf8(sv.data(), sv.size());
encoded r;
r.scalar = string_node(sv.data(), sv.size());
return r;
}
template<typename T>
encoded encode_impl(T&& x, encode_tag<6> /*other*/)
{
return encode_impl(BasicJsonType(std::forward<T>(x)), encode_tag<1> {});
}
static node plain_node(value_t k) noexcept
{
node n{};
n.kind = static_cast<std::uint8_t>(k);
n.flags = node_flags::is_new;
return n;
}
template<typename T>
node number_node(T x, std::integral_constant<int, 0> /*floating-point*/)
{
return float_node(static_cast<number_float_t>(x));
}
template<typename T>
node number_node(T x, std::integral_constant<int, 1> /*signed*/)
{
return integer_node(static_cast<std::uint64_t>(static_cast<std::int64_t>(x)), value_t::number_integer);
}
template<typename T>
node number_node(T x, std::integral_constant<int, 2> /*unsigned*/)
{
return integer_node(static_cast<std::uint64_t>(x), value_t::number_unsigned);
}
/// an integer with its canonical token in the edit arena
node integer_node(std::uint64_t bits, value_t k)
{
const bool negative = k == value_t::number_integer && static_cast<std::int64_t>(bits) < 0;
std::uint64_t magnitude = negative ? 0 - bits : bits;
std::array<char, 24> buf{};
char* p = buf.data() + buf.size(); // NOLINT(misc-const-correctness): digits are written through p
do
{
*--p = static_cast<char>('0' + (magnitude % 10));
magnitude /= 10;
}
while (magnitude != 0);
if (negative)
{
*--p = '-';
}
const auto len = static_cast<std::size_t>(buf.data() + buf.size() - p);
node n = plain_node(k);
n.flags = static_cast<std::uint8_t>(n.flags | node_flags::edited);
n.off = append_text(m_doc, p, len);
// number_length() adds one for the sign of number_integer nodes
n.extra = static_cast<std::uint16_t>(k == value_t::number_integer ? len - 1 : len);
set_integer_bits(n, bits);
return n;
}
/// a float with its shortest round-trip token (as basic_json::dump()
/// writes it), or nan, inf, -inf, in the edit arena
node float_node(number_float_t x)
{
string_t text;
if (std::isnan(x))
{
text = "nan";
}
else if (std::isinf(x))
{
text = x > 0 ? "inf" : "-inf";
}
else
{
text = BasicJsonType(x).dump();
}
node n = plain_node(value_t::number_float);
n.flags = static_cast<std::uint8_t>(n.flags | node_flags::edited);
n.extra = 0xFFFFu; // (the digit layout is not recorded)
n.off = append_text(m_doc, text.data(), text.size());
n.len = static_cast<std::uint32_t>(text.size());
return n;
}
/// a string (or key) in the edit arena
node string_node(const char* s, std::size_t len)
{
if (NLOHMANN_VIEW_UNLIKELY(len >= 0xFFFFFFFFu))
{
throw_out_of_range(416, "strings of 4 GiB or more are not supported by json_document"); // LCOV_EXCL_LINE
}
node n = plain_node(value_t::string);
n.flags = static_cast<std::uint8_t>(n.flags | node_flags::edited);
n.off = append_text(m_doc, s, len);
n.len = static_cast<std::uint32_t>(len);
return n;
}
/// a scalar of a view (of any document) as a node of this document
node copy_scalar(const document_data& from, const node& n)
{
if (&from == &m_doc)
{
return n; // the same storage
}
switch (static_cast<value_t>(n.kind))
{
case value_t::string:
// (an editable document only holds valid UTF-8, whatever the check of the other document was)
check_utf8(from.str(n), n.len);
return string_node(from.str(n), n.len);
case value_t::number_integer:
case value_t::number_unsigned:
return integer_node(integer_bits(n), static_cast<value_t>(n.kind));
case value_t::number_float:
{
node r = plain_node(value_t::number_float);
r.flags = static_cast<std::uint8_t>(r.flags | node_flags::edited);
r.off = append_text(m_doc, from.str(n), n.len);
r.len = n.len;
r.extra = n.extra;
return r;
}
case value_t::boolean:
{
node r = plain_node(value_t::boolean);
r.flags = static_cast<std::uint8_t>(r.flags | (n.flags & node_flags::is_true));
return r;
}
case value_t::null:
case value_t::object:
case value_t::array:
case value_t::binary:
case value_t::discarded:
default:
return plain_node(value_t::null);
}
}
node json_scalar(const BasicJsonType& j)
{
switch (j.type())
{
case value_t::null:
return plain_node(value_t::null);
case value_t::boolean:
{
node r = plain_node(value_t::boolean);
r.flags = static_cast<std::uint8_t>(r.flags | (j.template get<bool>() ? node_flags::is_true : 0));
return r;
}
case value_t::number_integer:
return integer_node(static_cast<std::uint64_t>(static_cast<std::int64_t>(j.template get<number_integer_t>())), value_t::number_integer);
case value_t::number_unsigned:
return integer_node(static_cast<std::uint64_t>(j.template get<number_unsigned_t>()), value_t::number_unsigned);
case value_t::number_float:
return float_node(j.template get<number_float_t>());
case value_t::string:
{
const auto& s = j.template get_ref<const string_t&>();
check_utf8(s.data(), s.size());
return string_node(s.data(), s.size());
}
case value_t::binary:
throw_type_error(319, "cannot store a binary value in a json_document", "");
case value_t::discarded:
case value_t::object:
case value_t::array:
default:
throw_type_error(302, "type must be a value, but is ", "discarded");
}
}
// The subtrees are walked with an explicit stack (as materialize() does):
// the nesting depth is limited by memory only, not by the call stack.
/// number of nodes of a subtree (containers, keys, scalars)
template<bool E>
static std::size_t count_nodes(const document_data& d, const node* n)
{
using walk = navigation<E>;
struct frame
{
const node* pos; ///< next element, or key of the next member
const node* end;
bool object;
};
std::vector<frame> open;
std::size_t r = 0;
for (;;)
{
++r;
if (is_container(*n))
{
open.push_back(frame{walk::first(d, n), walk::end(d, n), n->kind == static_cast<std::uint8_t>(value_t::object)});
}
// the next value: close finished containers, then step over the key
for (;;)
{
if (open.empty())
{
return r;
}
frame& f = open.back();
if (f.pos == f.end)
{
open.pop_back();
continue;
}
const node* v = f.pos;
if (f.object)
{
++r; // the key
++v;
}
f.pos = document_data::after(v);
n = walk::value(v);
break;
}
}
}
/// copy a subtree (of any document) as a contiguous sequence of
/// count_nodes() nodes
template<bool E>
void fill_nodes(const document_data& d, const node* n, node* out)
{
using walk = navigation<E>;
struct frame
{
const node* pos; ///< next element, or key of the next member
const node* end;
bool object;
node* self; ///< the container in the copy
};
std::vector<frame> open;
for (;;)
{
if (is_container(*n))
{
node* const self = out++;
*self = plain_node(static_cast<value_t>(n->kind));
self->len = n->len;
open.push_back(frame{walk::first(d, n), walk::end(d, n), n->kind == static_cast<std::uint8_t>(value_t::object), self});
}
else
{
*out++ = copy_scalar(d, *n);
}
// the next value: close finished containers, then copy the key
for (;;)
{
if (open.empty())
{
return;
}
frame& f = open.back();
if (f.pos == f.end)
{
f.self->next = static_cast<std::uint32_t>(out - f.self);
open.pop_back();
continue;
}
const node* v = f.pos;
if (f.object)
{
*out++ = copy_scalar(d, *v);
++v;
}
f.pos = document_data::after(v);
n = walk::value(v);
break;
}
}
}
static std::size_t count_nodes(const BasicJsonType& j)
{
using iterator = typename BasicJsonType::const_iterator;
struct frame
{
iterator pos;
iterator end;
bool object;
};
std::vector<frame> open;
const BasicJsonType* n = &j;
std::size_t r = 0;
for (;;)
{
++r;
if (n->is_structured())
{
open.push_back(frame{n->cbegin(), n->cend(), n->is_object()});
}
for (;;)
{
if (open.empty())
{
return r;
}
frame& f = open.back();
if (f.pos == f.end)
{
open.pop_back();
continue;
}
r += f.object ? 1 : 0; // the key
n = &*f.pos;
++f.pos;
break;
}
}
}
void fill_nodes(const BasicJsonType& j, node* out)
{
using iterator = typename BasicJsonType::const_iterator;
struct frame
{
iterator pos;
iterator end;
bool object;
node* self; ///< the container in the copy
};
std::vector<frame> open;
const BasicJsonType* n = &j;
for (;;)
{
if (n->is_structured())
{
node* const self = out++;
*self = plain_node(n->type());
self->len = static_cast<std::uint32_t>(n->size());
open.push_back(frame{n->cbegin(), n->cend(), n->is_object(), self});
}
else
{
*out++ = json_scalar(*n);
}
for (;;)
{
if (open.empty())
{
return;
}
frame& f = open.back();
if (f.pos == f.end)
{
f.self->next = static_cast<std::uint32_t>(out - f.self);
open.pop_back();
continue;
}
if (f.object)
{
const auto& key = f.pos.key();
check_utf8(key.data(), key.size());
*out++ = string_node(key.data(), key.size());
}
n = &*f.pos;
++f.pos;
break;
}
}
}
document_data& m_doc;
};
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/edit_storage.hpp
+281
View File
@@ -0,0 +1,281 @@
// __ _____ _____ _____
// __| | __| | | | 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 <algorithm> // max, min
#include <cstddef> // size_t
#include <cstdint> // uint8_t, uint32_t
#include <cstring> // memcpy
#include <functional> // less
#include <memory> // unique_ptr
#include <utility> // move
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/document_data.hpp>
#include <nlohmann/detail/view/errors.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
#include <nlohmann/detail/view/node.hpp>
// The storage of edits. Edits never move or resize the parsed index: every
// value keeps its node, so views stay valid. New values and element sequences
// live in chunks that never move; strings and number tokens written by edits
// live in the edit arena. An array/object whose elements change gets
// node_flags::moved: its elements then live in a separate sequence (a header
// node, then the entries), whose entries link to the values (kind_link).
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
inline document_data::edit_state& edit_state_of(document_data& d)
{
if (!d.edits)
{
d.edits.reset(new document_data::edit_state()); // NOLINT(cppcoreguidelines-owning-memory,modernize-make-unique): owned by the unique_ptr; std::make_unique is C++14
}
return *d.edits;
}
/// k consecutive nodes that never move (new values and blocks)
inline node* alloc_nodes(document_data& d, std::size_t k)
{
document_data::edit_state& e = edit_state_of(d);
if (NLOHMANN_VIEW_UNLIKELY(static_cast<std::size_t>(e.chunk_end - e.chunk_cur) < k))
{
if (k >= e.chunk_next / 2)
{
// a large request (half of the next chunk or more) gets a chunk of
// its own, so that the rest of the current chunk stays available
// for smaller ones
std::unique_ptr<node[]> own(new node[k]()); // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
e.chunks.push_back(std::move(own));
e.bytes += k * sizeof(node);
return e.chunks.back().get();
}
// a smaller request leaves the rest of the current chunk unused
// (fewer than k nodes, and k is less than half of the new chunk)
const std::size_t count = e.chunk_next;
std::unique_ptr<node[]> fresh(new node[count]()); // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
e.chunks.push_back(std::move(fresh));
e.chunk_cur = e.chunks.back().get();
e.chunk_end = e.chunk_cur + count;
e.chunk_next = (std::min)(e.chunk_next * 2, std::size_t{65536});
e.bytes += count * sizeof(node);
}
node* const r = e.chunk_cur;
e.chunk_cur += k;
return r;
}
/// The capacity of the edit arena after it grows by n bytes (`used` of `cap`
/// are taken): doubled, or what is needed plus some room, but never more than
/// the 4 GiB - 1 bytes that the 32-bit offsets of nodes can address. An error
/// if n more bytes do not fit even then.
inline std::size_t text_capacity(std::size_t cap, std::size_t used, std::size_t n)
{
constexpr std::size_t limit = 0xFFFFFFFFu;
if (NLOHMANN_VIEW_UNLIKELY(used > limit || n > limit - used))
{
throw_out_of_range(416, "edits of 4 GiB or more are not supported by json_document");
}
const std::size_t needed = used + n;
const std::size_t wanted = needed + (std::min)(limit - needed, std::size_t{256});
const std::size_t doubled = cap > limit / 2 ? limit : cap * 2;
return (std::max)(doubled, wanted);
}
/// copy n bytes into the edit arena and return their offset; a new buffer
/// leaves the old one alive, so that string views into it remain valid; n is
/// 0 for an empty string (written by an edit, or the key of a new member)
inline std::uint32_t append_text(document_data& d, const char* s, std::size_t n)
{
document_data::edit_state& e = edit_state_of(d);
if (NLOHMANN_VIEW_UNLIKELY(e.text_cap - e.text_used < n))
{
const std::size_t cap = text_capacity(e.text_cap, e.text_used, n);
std::unique_ptr<char[]> fresh(new char[cap]); // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
if (NLOHMANN_VIEW_LIKELY(e.text_used != 0)) // (0 only for the first buffer, and then texts is empty)
{
std::memcpy(fresh.get(), e.texts.back().get(), e.text_used);
}
e.texts.push_back(std::move(fresh));
e.text_cap = cap;
e.bytes += cap;
d.base[2] = e.texts.back().get();
}
const auto off = static_cast<std::uint32_t>(e.text_used);
if (n != 0)
{
std::memcpy(e.texts.back().get() + e.text_used, s, n);
}
e.text_used += n;
return off;
}
/// the capacity in nodes of the block of a moved container (0: a fixed
/// sequence, the elements of a new value)
inline std::size_t moved_capacity(const document_data& d, const node* n) noexcept
{
return d.edits->moved_cap[n->off];
}
/// Make room for one more moved container. This is the part of set_moved()
/// that can throw: a caller that changes a node before it calls set_moved()
/// calls this first, so that a failure leaves the node as it was.
inline void reserve_moved(document_data& d)
{
document_data::edit_state& e = edit_state_of(d);
if (e.moved.size() >= 0xFFFFFFFFu)
{
throw_out_of_range(416, "more than 4294967295 edited arrays and objects are not supported by json_document"); // LCOV_EXCL_LINE
}
if (e.moved.size() == e.moved.capacity() || e.moved_cap.size() == e.moved_cap.capacity())
{
// both grow before either changes, so that the push_backs cannot throw
// (both conditions are needed: reserve() may allocate more than asked,
// so the two capacities can differ)
e.moved.reserve((e.moved.size() * 2) + 16);
e.moved_cap.reserve((e.moved.size() * 2) + 16);
}
}
/// let container n take its elements from `seq` (header node first); cannot
/// throw if n is moved already or reserve_moved() was called
inline void set_moved(document_data& d, node* n, node* seq, std::size_t cap)
{
document_data::edit_state& e = edit_state_of(d);
if ((n->flags & node_flags::moved) != 0)
{
e.moved[n->off] = seq;
e.moved_cap[n->off] = cap;
return;
}
reserve_moved(d);
e.moved.push_back(seq);
e.moved_cap.push_back(cap);
n->off = static_cast<std::uint32_t>(e.moved.size() - 1);
n->flags = static_cast<std::uint8_t>(n->flags | node_flags::moved | node_flags::is_new);
}
/// Make the elements of container n a growable block with room for `extra`
/// more nodes, and return its header. The entries link to the existing
/// values, which stay where they are. A block that grows is copied (its old
/// space is not reused).
inline node* block_of(document_data& d, node* n, std::size_t extra)
{
if ((n->flags & node_flags::moved) != 0 && moved_capacity(d, n) != 0)
{
node* const h = d.edits->moved[n->off];
if (h->next + extra <= moved_capacity(d, n))
{
return h;
}
const std::size_t cap = (std::max)(2 * moved_capacity(d, n), h->next + extra);
node* const nh = alloc_nodes(d, cap);
std::memcpy(nh, h, h->next * sizeof(node));
set_moved(d, n, nh, cap);
return nh;
}
reserve_moved(d); // (so that set_moved() below cannot throw: the links are marked before)
const bool object = n->kind == static_cast<std::uint8_t>(value_t::object);
const std::size_t used = 1 + (static_cast<std::size_t>(n->len) * (object ? 2 : 1));
const std::size_t cap = used + extra;
node* const h = alloc_nodes(d, cap);
*h = node{};
h->kind = n->kind;
h->len = n->len;
h->next = static_cast<std::uint32_t>(used);
node* o = h + 1;
for (const node* c = d.first_child_edited(n), *e = d.child_end_edited(n); c != e;)
{
if (object)
{
*o++ = *c++; // the key
}
make_link(*o, const_cast<node*>(document_data::deref(c))); // NOLINT(cppcoreguidelines-pro-type-const-cast): the nodes belong to the document
++o;
c = document_data::after(c);
}
set_moved(d, n, h, cap);
return h;
}
/// The container whose elements include `target`; nullptr for the root, for
/// a value that is no longer part of the document, and for a value that is
/// only reached through a link. Values never move between allocations, so
/// the path to `target` stays inside the allocation that holds it (the parsed
/// index, or one new value), where the extent of each container (`next`)
/// still covers its original subtree.
inline node* find_parent(const document_data& d, const node* target)
{
const std::less<const node*> lt{};
const node* lo = d.nodes;
const node* hi = d.nodes + d.node_count;
const node* c = d.nodes;
if (lt(target, lo) || !lt(target, hi))
{
if (!d.edits)
{
return nullptr; // LCOV_EXCL_LINE (nodes outside the index exist only after edits)
}
auto it = d.edits->regions.upper_bound(target);
if (it == d.edits->regions.begin())
{
return nullptr; // LCOV_EXCL_LINE (an array/object with elements is in the index or a new value)
}
--it;
lo = it->first;
hi = lo + lo->next;
if (!lt(target, hi))
{
return nullptr; // LCOV_EXCL_LINE (a single-node value, reached through a link)
}
// the root of a new value is the element sequence of its owner, or a linked value
c = it->second != nullptr ? it->second : lo;
}
if (target == lo)
{
return nullptr;
}
for (;;)
{
if (!is_container(*c))
{
return nullptr; // LCOV_EXCL_LINE (the value is inside c)
}
const bool object = c->kind == static_cast<std::uint8_t>(value_t::object);
const node* down = nullptr;
for (const node* p = d.first_child_edited(c), *e = d.child_end_edited(c); p != e;)
{
const node* const at = object ? p + 1 : p;
const node* const v = document_data::deref(at);
if (v == target)
{
return const_cast<node*>(c); // NOLINT(cppcoreguidelines-pro-type-const-cast): the nodes belong to the document
}
if (is_container(*v) && !lt(v, lo) && lt(v, target) && lt(target, v + v->next))
{
down = v;
break;
}
p = document_data::after(at);
}
if (down == nullptr)
{
return nullptr;
}
c = down;
}
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/errors.hpp
+178
View File
@@ -0,0 +1,178 @@
// __ _____ _____ _____
// __| | __| | | | 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 <algorithm> // min
#include <cstddef> // size_t
#include <string> // string
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/builder.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
// Exceptions are thrown out of line, so that the accessors that may throw stay
// small enough to be inlined.
[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(int id, const char* prefix, const char* type)
{
NLOHMANN_VIEW_THROW(type_error::create(id, concat(prefix, type), nullptr));
}
[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_type_error(int id, const std::string& msg)
{
NLOHMANN_VIEW_THROW(type_error::create(id, msg, nullptr));
}
[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_out_of_range(int id, const std::string& msg)
{
NLOHMANN_VIEW_THROW(out_of_range::create(id, msg, nullptr));
}
[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_iterator(int id, const char* msg)
{
NLOHMANN_VIEW_THROW(invalid_iterator::create(id, msg, nullptr));
}
/// a parse error without a position (as those of json_pointer)
[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_parse_error(int id, const std::string& msg)
{
NLOHMANN_VIEW_THROW(parse_error::create(id, 0, msg, nullptr));
}
/// SAX handler of the error replay: accepts every event without storing it,
/// and throws the exception the parser reports
template<typename BasicJsonType>
struct throwing_sax
{
using number_integer_t = typename BasicJsonType::number_integer_t;
using number_unsigned_t = typename BasicJsonType::number_unsigned_t;
using number_float_t = typename BasicJsonType::number_float_t;
using string_t = typename BasicJsonType::string_t;
using binary_t = typename BasicJsonType::binary_t;
bool null()
{
return true;
}
bool boolean(bool /*unused*/)
{
return true;
}
bool number_integer(number_integer_t /*unused*/)
{
return true;
}
bool number_unsigned(number_unsigned_t /*unused*/)
{
return true;
}
bool number_float(number_float_t /*unused*/, const string_t& /*unused*/)
{
return true;
}
bool string(string_t& /*unused*/)
{
return true;
}
bool binary(binary_t& /*unused*/)
{
return true;
}
bool start_object(std::size_t /*unused*/)
{
return true;
}
bool key(string_t& /*unused*/)
{
return true;
}
bool end_object()
{
return true;
}
bool start_array(std::size_t /*unused*/)
{
return true;
}
bool end_array()
{
return true;
}
/// (a template, as in json_sax_dom_parser: the parser passes the concrete
/// exception type, which is thrown as is)
template<class Exception>
[[noreturn]] bool parse_error(std::size_t /*unused*/, const std::string& /*unused*/, const Exception& ex)
{
NLOHMANN_VIEW_THROW(ex);
}
};
/*!
@brief throw the exception BasicJsonType::parse would throw for this input
The view accepts exactly the inputs parse() accepts, so on a failure the
library parser is run on the same bytes: it throws the exception parse() would
throw, with the same message, position, and "last read" token. The replay
uses a SAX handler that stores nothing, so it only lexes and parses up to the
error, without building values. The error path is cold, so this costs nothing
on valid input. Should parse() accept the input nevertheless (a bug), the
view's own failure is reported.
*/
template<typename BasicJsonType>
[[noreturn]] NLOHMANN_VIEW_NOINLINE void throw_parse_failure(const parse_failure& f, const char* src, std::size_t size,
bool ignore_comments, bool ignore_trailing_commas)
{
if (f.code == error_code::input_too_large)
{
// (the limit is detail::view::max_input_size(): 4 GiB minus 16 bytes)
NLOHMANN_VIEW_THROW(out_of_range::create(416, "input of 4294967280 bytes or more is not supported by json_document", nullptr));
}
throwing_sax<BasicJsonType> sax;
const bool accepted = BasicJsonType::sax_parse(src, src + size, &sax, input_format_t::json, true, ignore_comments, ignore_trailing_commas);
// LCOV_EXCL_START (only if parse() accepts what the view rejects: a bug)
static_cast<void>(accepted);
position_t pos;
const std::size_t off = (std::min)(f.offset, size);
pos.chars_read_total = off + 1;
std::size_t line_start = 0;
for (std::size_t i = 0; i < off; ++i)
{
if (src[i] == '\n')
{
++pos.lines_read;
line_start = i + 1;
}
}
pos.chars_read_current_line = off + 1 - line_start;
NLOHMANN_VIEW_THROW(parse_error::create(101, pos, "syntax error while parsing value", nullptr));
// LCOV_EXCL_STOP
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/image.hpp
+744
View File
@@ -0,0 +1,744 @@
// __ _____ _____ _____
// __| | __| | | | 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 <algorithm> // min, sort
#include <array> // array
#include <cstddef> // offsetof, size_t
#include <cstdint> // int64_t, uint8_t, uint16_t, uint32_t, uint64_t
#include <cstring> // memcmp, memcpy, memset
#include <limits> // numeric_limits
#include <string> // string
#include <vector> // vector
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/document_data.hpp>
#include <nlohmann/detail/view/errors.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
#include <nlohmann/detail/view/node.hpp>
#include <nlohmann/detail/view/number.hpp>
#include <nlohmann/detail/view/object_index.hpp>
#include <nlohmann/detail/view/scan.hpp>
// Images: a document stored so that loading it needs no parsing.
//
// Layout (little-endian): a 64-byte header, the nodes, the text (the source,
// followed by the number tokens written by edits), a NUL, the decoded strings
// (followed by the strings written by edits), a NUL. The idea is that of
// zero-copy formats such as FlatBuffers (https://github.com/google/flatbuffers)
// and YaFF (https://github.com/yandex/yaff); no code is taken from them.
// check_image follows the idea of FlatBuffers' Verifier (bounds and
// structure) and also checks what the parser guarantees about strings and
// numbers, so that reading and serializing a checked image is safe and yields
// valid JSON.
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/// how load() checks an image
enum class image_check
{
/// everything the parser guarantees: structure and bounds, strings (valid
/// UTF-8; source strings without quotes, backslashes, and control
/// characters), and numbers (well-formed, matching the stored values)
full,
/// structure and bounds only: reading and serializing are safe, but a
/// crafted image can yield invalid UTF-8, strings that serialize to
/// invalid JSON, or numbers that differ from their text
bounds,
/// none: for images from a trusted source only (a damaged image is
/// undefined behavior)
none,
};
struct image_header
{
std::array<char, 4> magic; ///< "NJVI"
std::uint32_t version; ///< 1
std::uint64_t node_count;
std::uint64_t text_size;
std::uint64_t arena_size;
std::array<std::uint64_t, 4> reserved; ///< zero (for later versions)
};
static_assert(sizeof(image_header) == 64, "the image header must be 64 bytes");
constexpr std::uint32_t image_version = 1;
/// the largest node count and text or string size of an image (as for parsed
/// documents, offsets and counts must fit 32 bits)
constexpr std::uint64_t image_limit = 0xFFFFFFF0u;
/// Copy the current structure of an edited document into nodes in document
/// order, as the parser would have written them. Text written by edits is
/// appended to text_tail (number tokens) and arena_tail (strings); floats that
/// are not finite become null, as dump() writes them.
inline void compact_nodes(const document_data& d, std::size_t arena_size, std::vector<node>& out, std::string& text_tail, std::string& arena_tail)
{
struct frame
{
const node* cur;
const node* end;
std::size_t index; ///< the container's node in out
std::uint32_t count;
bool object;
};
std::vector<frame> stack;
const auto string_node = [&](const node & s)
{
node r = s;
r.extra = 0;
r.flags = static_cast<std::uint8_t>(s.flags & node_flags::storage);
if (r.flags == node_flags::edited)
{
r.off = static_cast<std::uint32_t>(arena_size + arena_tail.size());
arena_tail.append(d.str(s), s.len);
r.flags = node_flags::escaped;
}
return r;
};
const auto copy_node = [&](const node * v)
{
node r = *v;
switch (static_cast<value_t>(v->kind))
{
case value_t::object:
case value_t::array:
r.flags = 0;
r.extra = 0;
r.off = (v->flags & (node_flags::moved | node_flags::is_new)) != 0 ? 0 : v->off;
r.len = 0; // counted below
r.next = 0; // set when the container is complete
stack.push_back(frame{d.first_child_edited(v), d.child_end_edited(v), out.size(), 0, v->kind == static_cast<std::uint8_t>(value_t::object)});
break;
case value_t::string:
r = string_node(*v);
break;
case value_t::number_integer:
case value_t::number_unsigned:
if ((v->flags & node_flags::storage) == node_flags::edited)
{
r.off = static_cast<std::uint32_t>(d.size + text_tail.size());
text_tail.append(d.str(*v), number_length(*v));
}
r.flags = 0;
break;
case value_t::number_float:
if ((v->flags & node_flags::storage) == node_flags::edited)
{
const char* const t = d.str(*v);
if (t[0] == 'n' || t[0] == 'i' || (v->len > 1 && t[1] == 'i'))
{
r = node{}; // nan and infinity: null, as dump() writes them
r.kind = static_cast<std::uint8_t>(value_t::null);
break;
}
r.off = static_cast<std::uint32_t>(d.size + text_tail.size());
text_tail.append(t, v->len);
r.extra = 0xFFFFu; // the digit layout is not recorded
}
r.flags = 0;
break;
case value_t::boolean:
r.flags = static_cast<std::uint8_t>(v->flags & node_flags::is_true);
break;
case value_t::null:
case value_t::binary:
case value_t::discarded:
default:
r.flags = 0;
break;
}
out.push_back(r);
};
copy_node(d.nodes);
while (!stack.empty())
{
const frame top = stack.back();
if (top.cur == top.end)
{
node& c = out[top.index];
c.len = top.count;
c.next = static_cast<std::uint32_t>(out.size() - top.index);
stack.pop_back();
continue;
}
if (top.object)
{
out.push_back(string_node(*top.cur));
}
const node* const value = top.cur + (top.object ? 1 : 0);
stack.back().cur = document_data::after(value);
++stack.back().count;
copy_node(document_data::deref(value)); // may grow the stack
}
}
/// the document as an image
inline std::vector<std::uint8_t> save_image(const document_data& d)
{
#if !NLOHMANN_VIEW_LITTLE_ENDIAN
throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
#endif
const std::size_t arena_size = d.arena_size;
std::vector<node> compacted;
std::string text_tail;
std::string arena_tail;
if (d.edits)
{
compact_nodes(d, arena_size, compacted, text_tail, arena_tail);
}
const node* const nodes = d.edits ? compacted.data() : d.nodes;
const std::size_t count = d.edits ? compacted.size() : d.node_count;
const std::size_t text_size = d.size + text_tail.size();
const std::size_t total_arena = arena_size + arena_tail.size();
if (NLOHMANN_VIEW_UNLIKELY(text_size >= image_limit || total_arena >= image_limit || count >= image_limit))
{
// LCOV_EXCL_START (4 GiB)
throw_out_of_range(416, "images of 4 GiB or more are not supported by json_document");
// LCOV_EXCL_STOP
}
image_header h{};
h.magic = {{'N', 'J', 'V', 'I'}};
h.version = image_version;
h.node_count = count;
h.text_size = text_size;
h.arena_size = total_arena;
std::vector<std::uint8_t> image(sizeof(h) + (count * sizeof(node)) + text_size + 1 + total_arena + 1);
std::uint8_t* o = image.data();
std::memcpy(o, &h, sizeof(h));
o += sizeof(h);
std::memcpy(o, nodes, count * sizeof(node));
// the hash indexes are rebuilt by load(), whose check rejects any other
// extra of an object, and the same document saves to the same bytes
for (std::size_t i = 0; i < count; ++i)
{
if (nodes[i].kind == static_cast<std::uint8_t>(value_t::object) && nodes[i].extra != 0)
{
std::memset(o + (i * sizeof(node)) + offsetof(node, extra), 0, sizeof(nodes[i].extra));
}
}
o += count * sizeof(node);
const auto append = [&o](const char* s, std::size_t n)
{
if (n != 0)
{
std::memcpy(o, s, n);
o += n;
}
};
append(d.src, d.size);
append(text_tail.data(), text_tail.size());
*o++ = 0;
append(d.base[1], arena_size);
append(arena_tail.data(), arena_tail.size());
*o = 0;
return image;
}
/// the parts of a number token that the checks need
struct number_token
{
const unsigned char* int_start;
std::size_t int_digits;
std::size_t frac_digits;
std::int64_t exponent;
bool negative;
bool is_float; ///< a fraction or an exponent
};
/// whether [s, s + len) is a JSON number (the grammar the parser accepts)
inline bool scan_number_token(const unsigned char* s, std::size_t len, number_token& t)
{
const unsigned char* const e = s + len;
const unsigned char* p = s;
t.negative = p != e && *p == '-';
p += t.negative ? 1 : 0;
if (p == e)
{
return false;
}
t.int_start = p;
if (*p == '0')
{
++p;
}
else if (*p >= '1' && *p <= '9')
{
do
{
++p;
}
while (p != e && is_digit(*p));
}
else
{
return false;
}
t.int_digits = static_cast<std::size_t>(p - t.int_start);
t.frac_digits = 0;
t.is_float = false;
if (p != e && *p == '.')
{
const unsigned char* const f0 = ++p;
while (p != e && is_digit(*p))
{
++p;
}
if (p == f0)
{
return false;
}
t.frac_digits = static_cast<std::size_t>(p - f0);
t.is_float = true;
}
t.exponent = 0;
if (p != e && (*p | 0x20u) == 'e')
{
++p;
const bool exp_negative = p != e && *p == '-';
p += (p != e && (*p == '+' || *p == '-')) ? 1 : 0;
if (p == e || !is_digit(*p))
{
return false;
}
do
{
t.exponent = t.exponent < 100000 ? (t.exponent * 10) + (*p - '0') : t.exponent;
++p;
}
while (p != e && is_digit(*p));
t.exponent = exp_negative ? -t.exponent : t.exponent;
t.is_float = true;
}
return p == e;
}
/// the digit layout the parser records for a float token (compaction
/// writes "many" instead; the caller accepts both)
inline std::uint16_t float_layout(const number_token& t)
{
return static_cast<std::uint16_t>((std::min)(t.int_digits, std::size_t{255}) | ((std::min)(t.frac_digits, std::size_t{255}) << 8u));
}
/// whether a float token (well-formed, per scan_number_token) is finite as
/// double; parse() rejects floats that overflow, and as there, only a number
/// whose magnitude could reach 1e308 needs the conversion
inline bool float_token_finite(const unsigned char* s, std::size_t len, const number_token& t)
{
if (static_cast<std::int64_t>(t.int_digits) + t.exponent > 300)
{
node n{};
n.kind = static_cast<std::uint8_t>(value_t::number_float);
n.len = static_cast<std::uint32_t>(len);
const auto v = float_value<double>(reinterpret_cast<const char*>(s), n); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
return v <= (std::numeric_limits<double>::max)() && v >= -(std::numeric_limits<double>::max)();
}
return true;
}
/// whether an integer node matches its token the way the parser records it
/// (after the bounds check; the token has at most 256 characters)
inline bool check_integer(const node& n, const unsigned char* text)
{
const std::size_t len = number_length(n);
const unsigned char* const s = text + n.off;
number_token t{};
if (!scan_number_token(s, len, t))
{
return false;
}
// the token's value is the stored one; number_integer nodes of edits can
// be non-negative (as basic_json keeps the type of a value)
const bool integer = n.kind == static_cast<std::uint8_t>(value_t::number_integer);
if (t.is_float || t.int_digits > 20 || (t.negative && !integer))
{
return false;
}
// (at most 19 digits cannot overflow; 20 digits are compared with 2^64 - 1)
if (t.int_digits == 20 && std::memcmp(t.int_start, "18446744073709551615", 20) > 0)
{
return false;
}
std::uint64_t m = 0;
for (const unsigned char* d = t.int_start; d != t.int_start + t.int_digits; ++d)
{
m = (m * 10) + static_cast<std::uint64_t>(*d - '0');
}
if (integer && m > (t.negative ? std::uint64_t{1} << 63u : (std::uint64_t{1} << 63u) - 1))
{
return false;
}
return integer_bits(n) == (t.negative ? 0 - m : m);
}
/// a byte range of the text or of the decoded strings
struct byte_range
{
std::uint32_t off;
std::uint32_t len;
};
/// a float token and the digit layout its node records
struct float_range
{
std::uint32_t off;
std::uint32_t len;
std::uint16_t extra;
};
/// Run check once for each distinct range of ranges (which are within bounds
/// and not empty). Ranges that are not identical must not overlap: save()
/// writes every string and token to a place of its own, and nodes that share
/// a value (copies within a document) share the whole range. This bounds the
/// work by the size of the text, however many nodes point to the same bytes.
template<typename Check>
bool check_distinct_ranges(std::vector<byte_range>& ranges, Check check)
{
std::sort(ranges.begin(), ranges.end(), [](const byte_range & a, const byte_range & b)
{
return a.off != b.off ? a.off < b.off : a.len < b.len;
});
std::size_t end = 0;
for (std::size_t i = 0; i < ranges.size(); ++i)
{
const byte_range r = ranges[i];
if (i != 0 && r.off == ranges[i - 1].off && r.len == ranges[i - 1].len)
{
continue;
}
if (r.off < end || !check(r))
{
return false;
}
end = static_cast<std::size_t>(r.off) + r.len;
}
return true;
}
/// Check the float nodes: each token once (nodes of the same token must
/// record layouts that match it), tokens must not overlap.
inline bool check_float_ranges(std::vector<float_range>& ranges, const unsigned char* text)
{
std::sort(ranges.begin(), ranges.end(), [](const float_range & a, const float_range & b)
{
if (a.off != b.off)
{
return a.off < b.off;
}
if (a.len != b.len)
{
return a.len < b.len;
}
return a.extra < b.extra;
});
std::size_t end = 0;
std::size_t i = 0;
while (i < ranges.size())
{
const float_range r = ranges[i];
if (r.off < end)
{
return false;
}
number_token t{};
const unsigned char* const s = text + r.off;
if (!scan_number_token(s, r.len, t) || !float_token_finite(s, r.len, t))
{
return false;
}
// the digit layout the parser records (or "many", as compaction writes it)
const std::uint16_t layout = float_layout(t);
for (; i < ranges.size() && ranges[i].off == r.off && ranges[i].len == r.len; ++i)
{
if (ranges[i].extra != layout && ranges[i].extra != 0xFFFFu)
{
return false;
}
}
end = static_cast<std::size_t>(r.off) + r.len;
}
return true;
}
/// the content checks of check_image: source strings as the parser leaves
/// them (no quotes, backslashes, or control characters), decoded strings
/// (valid UTF-8), and float tokens
inline bool check_contents(const unsigned char* text, const unsigned char* arena,
std::vector<byte_range>& source_strings, std::vector<byte_range>& decoded_strings,
std::vector<float_range>& floats)
{
return check_distinct_ranges(source_strings, [text](const byte_range & r)
{
const unsigned char* const b = text + r.off;
return scan_string_run(b, b + r.len) == b + r.len;
})
&& check_distinct_ranges(decoded_strings, [arena](const byte_range & r)
{
return valid_utf8_prefix(arena + r.off, r.len) == r.len;
})
&& check_float_ranges(floats, text);
}
/// Check the nodes of a loaded image against its text and decoded strings:
/// kinds, flags, and `extra`; extents and element counts of arrays and
/// objects; keys; bounds; string contents (source strings as the parser
/// leaves them: no quotes, backslashes, or control characters; all strings
/// valid UTF-8); and number tokens.
///
/// The structure and the bounds are checked node by node. The contents of
/// strings and of float tokens are checked afterwards, once for each distinct
/// range (see check_distinct_ranges), so that the full check is linear in the
/// size of the image plus the sorting of the ranges, and not in the number of
/// nodes times the size of the text.
inline bool check_image(const node* nodes, std::size_t count, const unsigned char* text, std::size_t text_size,
const unsigned char* arena, std::size_t arena_size, bool full)
{
struct frame
{
std::size_t end;
std::uint32_t len;
std::uint32_t seen;
bool object;
bool expect_key;
};
std::vector<frame> stack;
std::vector<byte_range> source_strings;
std::vector<byte_range> decoded_strings;
std::vector<float_range> floats;
const auto check_string = [&](const node & n) -> bool
{
if ((n.flags & ~node_flags::escaped) != 0 || n.extra != 0)
{
return false;
}
const bool decoded = (n.flags & node_flags::escaped) != 0;
const std::size_t limit = decoded ? arena_size : text_size;
if (n.off > limit || n.len > limit - n.off)
{
return false;
}
if (full && n.len != 0)
{
(decoded ? decoded_strings : source_strings).push_back(byte_range{n.off, n.len});
}
return true;
};
// bounds of a number token; the recorded digit layout must lie within it
const auto number_in_bounds = [&](const node & n) -> bool
{
const std::size_t len = number_length(n);
if (len == 0 || n.off > text_size || len > text_size - n.off)
{
return false;
}
if (n.kind != static_cast<std::uint8_t>(value_t::number_float))
{
return (n.extra >> 8u) == 0;
}
// float_value() reads the sign, the integer digits, and the point and
// fraction digits the layout records (a layout of more than 19 digits
// means the general conversion, which stays within the token)
const std::size_t int_digits = n.extra & 0xFFu;
const std::size_t frac_digits = n.extra >> 8u;
const std::size_t need = (text[n.off] == '-' ? 1u : 0u) + int_digits + (frac_digits != 0 ? frac_digits + 1 : 0);
return int_digits + frac_digits > 19 || need <= len;
};
std::size_t i = 0;
for (;;)
{
// close finished arrays and objects
while (!stack.empty() && i == stack.back().end)
{
const frame f = stack.back();
if (f.seen != f.len || (f.object && !f.expect_key))
{
return false;
}
stack.pop_back();
if (!stack.empty())
{
++stack.back().seen;
stack.back().expect_key = true;
}
}
if (i == count)
{
return stack.empty() && (!full || check_contents(text, arena, source_strings, decoded_strings, floats));
}
if (i != 0 && stack.empty())
{
return false; // nodes after the root
}
const node& n = nodes[i];
if (!stack.empty() && stack.back().object && stack.back().expect_key)
{
if (n.kind != static_cast<std::uint8_t>(value_t::string) || !check_string(n))
{
return false;
}
stack.back().expect_key = false;
++i;
continue;
}
bool complete = true;
switch (static_cast<value_t>(n.kind))
{
case value_t::null:
// (the offset of a literal is read to size the output of dump())
if (n.flags != 0 || n.extra != 0 || n.off > text_size)
{
return false;
}
break;
case value_t::boolean:
if ((n.flags & ~node_flags::is_true) != 0 || n.extra != 0 || n.off > text_size)
{
return false;
}
break;
case value_t::string:
if (!check_string(n))
{
return false;
}
break;
case value_t::number_integer:
case value_t::number_unsigned:
case value_t::number_float:
if (n.flags != 0 || !number_in_bounds(n))
{
return false;
}
if (full)
{
// (the contents of float tokens are checked later; the token of an
// integer has at most 256 characters)
if (n.kind == static_cast<std::uint8_t>(value_t::number_float))
{
floats.push_back(float_range{n.off, n.len, n.extra});
}
else if (!check_integer(n, text))
{
return false;
}
}
break;
case value_t::array:
case value_t::object:
{
const std::size_t limit = stack.empty() ? count : stack.back().end;
if (n.flags != 0 || n.extra != 0 || n.next == 0 || n.next > limit - i || n.off > text_size)
{
return false;
}
stack.push_back(frame{i + n.next, n.len, 0, n.kind == static_cast<std::uint8_t>(value_t::object), true});
complete = false;
break;
}
case value_t::binary:
case value_t::discarded:
default:
return false;
}
++i;
if (complete && !stack.empty())
{
++stack.back().seen;
stack.back().expect_key = true;
}
}
}
[[noreturn]] NLOHMANN_VIEW_NOINLINE inline void throw_invalid_image(const char* what)
{
throw_parse_error(116, concat("invalid json_document image: ", what));
}
/// Read an image into d. The text and the decoded strings stay in the image;
/// the nodes are copied (so that they are aligned, and edits can change them).
inline void load_image(document_data& d, const std::uint8_t* image, std::size_t size, image_check check)
{
#if !NLOHMANN_VIEW_LITTLE_ENDIAN
throw_type_error(320, "json_document images need a little-endian target"); // LCOV_EXCL_LINE
#endif
if (image == nullptr || size < sizeof(image_header))
{
throw_invalid_image("too short");
}
image_header h{};
std::memcpy(&h, image, sizeof(h));
// (the reserved fields are for later versions)
if (std::memcmp(h.magic.data(), "NJVI", 4) != 0 || h.version != image_version
|| (h.reserved[0] | h.reserved[1] | h.reserved[2] | h.reserved[3]) != 0)
{
throw_invalid_image("unknown format");
}
const std::size_t room = size - sizeof(h);
if (h.node_count == 0 || h.node_count > room / sizeof(node) || h.node_count >= image_limit || h.text_size >= image_limit || h.arena_size >= image_limit)
{
throw_invalid_image("sizes out of range");
}
const auto count = static_cast<std::size_t>(h.node_count);
const auto text_size = static_cast<std::size_t>(h.text_size);
const auto arena_size = static_cast<std::size_t>(h.arena_size);
const std::size_t text_at = sizeof(h) + (count * sizeof(node));
// the text, a NUL, the decoded strings, a NUL, and nothing after them
if (size - text_at < 2 || text_size > size - text_at - 2 || arena_size != size - text_at - text_size - 2
|| image[text_at + text_size] != 0 || image[size - 1] != 0)
{
throw_invalid_image("sizes out of range");
}
d.discarded = true;
d.edits.reset();
d.base[2] = nullptr;
d.owned.clear();
if (d.owned_image.empty() || image != d.owned_image.data())
{
d.owned_image.clear();
}
d.arena.clear();
d.indexes.clear();
d.index_slots.clear();
d.large_objects.clear();
d.node_count = 0;
d.reserve(count);
std::memcpy(d.nodes, image + sizeof(h), count * sizeof(node));
d.node_count = count;
const std::uint8_t* const text = image + text_at;
const std::uint8_t* const arena = text + text_size + 1;
d.src = reinterpret_cast<const char*>(text); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
d.size = text_size;
d.base[0] = d.src;
d.base[1] = reinterpret_cast<const char*>(arena); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
d.arena_size = arena_size;
if (check != image_check::none && !check_image(d.nodes, count, text, text_size, arena, arena_size, check == image_check::full))
{
throw_invalid_image("the check failed");
}
// the hash indexes of large objects, as after parsing
for (std::size_t i = 0; i < count; ++i)
{
const node& n = d.nodes[i];
if (n.kind == static_cast<std::uint8_t>(value_t::object) && n.len >= document_data::index_min_members)
{
d.large_objects.push_back(static_cast<std::uint32_t>(i));
}
}
build_object_indexes(d);
std::vector<std::uint32_t>().swap(d.large_objects); // (only needed while building)
d.discarded = false;
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/input.hpp
+159
View File
@@ -0,0 +1,159 @@
// __ _____ _____ _____
// __| | __| | | | 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 <algorithm> // max
#include <cstddef> // size_t
#include <istream> // istream, streambuf
#include <string> // basic_string, char_traits, string
#include <type_traits> // decay, integral_constant, is_array, is_const, is_integral, is_lvalue_reference, is_pointer, is_same, remove_cv, remove_extent, remove_pointer, remove_reference
#include <utility> // forward
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
#if NLOHMANN_VIEW_HAS_CPP_17
#include <string_view> // string_view
#endif
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/// how a document takes its input
enum class input_kind
{
move_string, ///< non-const rvalue std::string: owned without a copy
c_string, ///< pointer to single-byte characters (NUL-terminated): borrowed
char_array, ///< array of single-byte characters (e.g. a string literal): borrowed
borrow_range, ///< lvalue contiguous byte container, or std::string_view: borrowed
copy_range, ///< rvalue contiguous byte container (a const rvalue std::string too): copied
wide_c_string, ///< pointer to wide characters (NUL-terminated): converted to UTF-8 into a buffer
adapter, ///< streams, FILE*, wide strings and arrays, and the rest of what the library's input adapter reads: read into a buffer
};
/// a single-byte character type (char, signed/unsigned char, char8_t, std::uint8_t, ...)
template<typename T>
struct is_byte_char : conjunction<std::is_integral<T>, std::integral_constant<bool, sizeof(T) == 1>> {}; // NOLINT(bugprone-sizeof-expression): T is any pointee or element type
/// a character type the library's input adapter converts to UTF-8
template<typename T>
struct is_wide_char : disjunction<std::is_same<T, wchar_t>, std::is_same<T, char16_t>, std::is_same<T, char32_t>> {};
template<typename InputType>
struct classify_input
{
using R = typename std::remove_reference<InputType>::type;
using D = typename std::decay<InputType>::type;
using element = typename std::remove_cv<typename std::remove_extent<R>::type>::type;
using pointee = typename std::remove_cv<typename std::remove_pointer<D>::type>::type;
static constexpr bool is_rvalue = !std::is_lvalue_reference<InputType>::value;
static constexpr bool is_bytes = is_contiguous_byte_container<D>::value;
#if NLOHMANN_VIEW_HAS_CPP_17
static constexpr bool is_string_view = std::is_same<D, std::string_view>::value;
#else
static constexpr bool is_string_view = false;
#endif
// NOLINTBEGIN(readability-avoid-nested-conditional-operator): a constant expression of C++11
// (arrays and pointers of other types, such as wide-character arrays and
// FILE*, go to the library's input adapter)
static constexpr input_kind value =
(std::is_array<R>::value && is_byte_char<element>::value) ? input_kind::char_array
: std::is_array<R>::value ? input_kind::adapter
: (std::is_pointer<D>::value && is_byte_char<pointee>::value) ? input_kind::c_string
: (std::is_pointer<D>::value && is_wide_char<pointee>::value) ? input_kind::wide_c_string
: std::is_pointer<D>::value ? input_kind::adapter
: (is_rvalue && !std::is_const<R>::value && std::is_same<D, std::string>::value) ? input_kind::move_string
: (is_bytes && (!is_rvalue || is_string_view)) ? input_kind::borrow_range
: is_bytes ? input_kind::copy_range
: input_kind::adapter;
// NOLINTEND(readability-avoid-nested-conditional-operator)
};
/// an integer type other than bool: a length passed where a flag is expected
template<typename T>
struct is_integer_not_bool : std::is_integral<T> {};
template<>
struct is_integer_not_bool<bool> : std::false_type {};
/// std::basic_string guarantees a NUL at data()[size()] (the parser's sentinel)
template<typename T>
struct is_std_string : std::false_type {};
template<typename Traits, typename Alloc>
struct is_std_string<std::basic_string<char, Traits, Alloc>> : std::true_type {};
/// append what a json input adapter yields (UTF-16/32 inputs arrive as UTF-8)
template<typename Adapter>
void append_adapter(std::string& buf, Adapter ia)
{
for (;;)
{
const auto ch = ia.get_character();
if (ch == std::char_traits<char>::eof())
{
break;
}
buf.push_back(static_cast<char>(ch));
}
}
/// an input adapter made by the document for an input that the library's
/// input_adapter() does not take as one argument (an iterator range, a wide C
/// string), to be appended with append_adapter()
template<typename Adapter>
struct adapter_input
{
Adapter ia;
};
template<typename T>
struct is_adapter_input : std::false_type {};
template<typename Adapter>
struct is_adapter_input<adapter_input<Adapter>> : std::true_type {};
template<typename Adapter>
adapter_input<typename std::decay<Adapter>::type> make_adapter_input(Adapter&& ia)
{
return {std::forward<Adapter>(ia)};
}
/// append the rest of a stream: its characters need no conversion, so they are
/// read in blocks from the stream buffer, straight into buf (reusing its
/// capacity). As the library's stream adapter, this reads the stream buffer
/// directly and sets eofbit at the end.
inline void append_stream(std::string& buf, std::istream& is)
{
std::streambuf* const sb = is.rdbuf();
if (sb == nullptr)
{
return;
}
for (;;)
{
const std::size_t used = buf.size();
const std::size_t room = (std::max)(buf.capacity() - used, std::size_t{4096});
buf.resize(used + room);
const std::streamsize got = sb->sgetn(&buf[used], static_cast<std::streamsize>(room));
buf.resize(used + static_cast<std::size_t>((std::max)(got, std::streamsize{0})));
if (got <= 0)
{
break;
}
}
is.clear(is.rdstate() | std::ios::eofbit);
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/iterator.hpp
+263
View File
@@ -0,0 +1,263 @@
// __ _____ _____ _____
// __| | __| | | | 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> // ptrdiff_t, size_t
#include <iterator> // forward_iterator_tag
#include <string> // string, to_string
#include <type_traits> // enable_if
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/document_data.hpp>
#include <nlohmann/detail/view/errors.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
#include <nlohmann/detail/view/node.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/// the result of view_iterator::operator->: keeps the view alive for the
/// duration of the member access
template<typename View>
class arrow_proxy
{
public:
explicit arrow_proxy(const View& v) noexcept
: m_view(v)
{}
const View* operator->() const noexcept
{
return &m_view;
}
private:
View m_view;
};
/*!
@brief forward iterator over the elements of a basic_json_view
Iterates over the elements of an array or the member values of an object, in
document order; key() gives the key of an object member. As for basic_json, a
primitive value iterates as a range of one element (itself), and null as an
empty range.
*/
template<typename View>
class view_iterator
{
public:
using iterator_category = std::forward_iterator_tag;
using value_type = View;
using difference_type = std::ptrdiff_t;
using pointer = arrow_proxy<View>;
using reference = View;
using string_view_t = typename View::string_view_t;
view_iterator() noexcept = default;
/// @param[in] pos the element, or the key of the member
/// @param[in] object whether pos is a key (its value is the next node)
view_iterator(const document_data* d, const node* pos, bool object) noexcept
: m_doc(d), m_pos(pos), m_value_offset(object ? 1 : 0)
{}
NLOHMANN_VIEW_ALWAYS_INLINE View operator*() const noexcept
{
return View(m_doc, View::navigation::value(m_pos + m_value_offset));
}
pointer operator->() const noexcept
{
return pointer(**this);
}
NLOHMANN_VIEW_ALWAYS_INLINE view_iterator& operator++() noexcept
{
m_pos = document_data::after(m_pos + m_value_offset);
return *this;
}
view_iterator operator++(int) noexcept
{
const view_iterator r = *this;
++*this;
return r;
}
friend bool operator==(const view_iterator& a, const view_iterator& b) noexcept
{
return a.m_pos == b.m_pos;
}
friend bool operator!=(const view_iterator& a, const view_iterator& b) noexcept
{
return a.m_pos != b.m_pos;
}
/// the key of the current object member; throws invalid_iterator.207 for
/// other iterators, like basic_json's iterators
string_view_t key() const
{
if (NLOHMANN_VIEW_UNLIKELY(m_value_offset == 0))
{
throw_invalid_iterator(207, "cannot use key() for non-object iterators");
}
return string_view_t(m_doc->str(*m_pos), m_pos->len);
}
View value() const noexcept
{
return **this;
}
/// whether the iterator runs over the members of an object
bool is_object_iterator() const noexcept
{
return m_value_offset != 0;
}
private:
const document_data* m_doc = nullptr;
const node* m_pos = nullptr;
std::size_t m_value_offset = 0; ///< 1 for objects: the value follows its key
};
/*!
@brief a (key, value) item of basic_json_view::items()
The key of an array element is its index, as for basic_json::items().
Supports structured bindings: for (const auto [key, value] : view.items())
*/
template<typename View>
class view_item
{
public:
using string_view_t = typename View::string_view_t;
using iterator = view_iterator<View>;
view_item(const iterator& it, std::size_t index)
: m_it(it)
{
if (!it.is_object_iterator())
{
m_index = std::to_string(index);
}
}
/// the member key, or the element index for arrays
string_view_t key() const
{
if (m_it.is_object_iterator())
{
return m_it.key();
}
return string_view_t(m_index.data(), m_index.size());
}
View value() const noexcept
{
return *m_it;
}
template<std::size_t N, typename std::enable_if<N == 0, int>::type = 0>
string_view_t get() const
{
return key();
}
template<std::size_t N, typename std::enable_if<N == 1, int>::type = 0>
View get() const noexcept
{
return value();
}
private:
iterator m_it;
std::string m_index{}; // NOLINT(readability-redundant-member-init)
};
/// the range returned by basic_json_view::items()
template<typename View>
class view_items
{
public:
using item = view_item<View>;
class iterator
{
public:
using iterator_category = std::forward_iterator_tag;
using value_type = item;
using difference_type = std::ptrdiff_t;
using pointer = void;
using reference = item;
explicit iterator(const view_iterator<View>& it) noexcept
: m_it(it)
{}
item operator*() const
{
return item(m_it, m_index);
}
iterator& operator++() noexcept
{
++m_it;
++m_index;
return *this;
}
iterator operator++(int) noexcept
{
const iterator r = *this;
++*this;
return r;
}
friend bool operator==(const iterator& a, const iterator& b) noexcept
{
return a.m_it == b.m_it;
}
friend bool operator!=(const iterator& a, const iterator& b) noexcept
{
return a.m_it != b.m_it;
}
private:
view_iterator<View> m_it;
std::size_t m_index = 0;
};
explicit view_items(const View& v) noexcept
: m_view(v)
{}
iterator begin() const noexcept
{
return iterator(m_view.begin());
}
iterator end() const noexcept
{
return iterator(m_view.end());
}
private:
View m_view;
};
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/lookup.hpp
+193
View File
@@ -0,0 +1,193 @@
// __ _____ _____ _____
// __| | __| | | | 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> // uint16_t, uint32_t, uint64_t
#include <cstring> // memcmp, memcpy
#include <limits> // numeric_limits
#include <type_traits> // integral_constant, is_integral, is_same
#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/object_index.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/// equality test for strings of one length n <= 16: two overlapping loads per
/// string (the first and the last 8, 4, or 2 bytes) replace a memcmp, and no
/// byte outside [s, s + n) is read
class short_key
{
public:
short_key(const unsigned char* k, std::size_t n) noexcept
: m_n(n)
{
load(k, m_a, m_b);
}
NLOHMANN_VIEW_ALWAYS_INLINE bool matches(const unsigned char* s) const noexcept
{
std::uint64_t a = 0;
std::uint64_t b = 0;
load(s, a, b);
return a == m_a && b == m_b;
}
private:
template<typename T>
static NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t load_word(const unsigned char* s) noexcept
{
T w = 0;
std::memcpy(&w, s, sizeof(T));
return w;
}
NLOHMANN_VIEW_ALWAYS_INLINE void load(const unsigned char* s, std::uint64_t& a, std::uint64_t& b) const noexcept
{
if (m_n >= 8)
{
a = load_word<std::uint64_t>(s);
b = load_word<std::uint64_t>(s + m_n - 8);
}
else if (m_n >= 4)
{
a = load_word<std::uint32_t>(s);
b = load_word<std::uint32_t>(s + m_n - 4);
}
else if (m_n >= 2)
{
a = load_word<std::uint16_t>(s);
b = load_word<std::uint16_t>(s + m_n - 2);
}
else
{
a = m_n == 1 ? s[0] : 0;
b = 0;
}
}
std::size_t m_n;
std::uint64_t m_a = 0;
std::uint64_t m_b = 0;
};
/// the key node of the first member of an object with the given key, or
/// nullptr (the search stops at the first match; materialize() and parse()
/// keep the last value of a duplicate key instead); most keys are rejected by
/// their length, from the index alone
template<bool Editable>
const node* find_member(const document_data& d, const node* object, const char* key, std::size_t n) noexcept
{
using nav = navigation<Editable>;
if (NLOHMANN_VIEW_UNLIKELY(object->extra != 0) && (!nav::editable() || (object->flags & node_flags::moved) == 0))
{
return find_indexed(d, object, key, n); // a large object (whose members have not been edited)
}
const node* const end = nav::end(d, object);
const auto* const k = reinterpret_cast<const unsigned char*>(key); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
if (NLOHMANN_VIEW_LIKELY(n <= 16))
{
const short_key probe(k, n);
for (const node* m = nav::first(d, object); m != end; m = document_data::after(m + 1))
{
if (m->len == n && probe.matches(reinterpret_cast<const unsigned char*>(d.str(*m)))) // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
{
return m;
}
}
return nullptr;
}
for (const node* m = nav::first(d, object); m != end; m = document_data::after(m + 1))
{
if (d.key_equals(*m, key, n))
{
return m;
}
}
return nullptr;
}
/// the number of members of an object with this key (duplicates included)
template<bool Editable>
std::size_t count_members(const document_data& d, const node* object, const char* key, std::size_t n) noexcept
{
using nav = navigation<Editable>;
std::size_t result = 0;
const node* const end = nav::end(d, object);
for (const node* m = nav::first(d, object); m != end; m = document_data::after(m + 1))
{
if (d.key_equals(*m, key, n))
{
++result;
}
}
return result;
}
/// whether an integer type is accepted as an array index by the view's
/// operator[] and at(): every integer type but bool and size_t, which has its
/// own overload
template<typename T>
struct is_index_type : std::integral_constant < bool,
std::is_integral<T>::value && !std::is_same<T, bool>::value && !std::is_same<T, std::size_t>::value >
{};
/// an integer as an index: negative values, and values that do not fit a
/// size_t, map to the largest size_t (out of range for every array)
template<typename SizeType, typename IntegerType>
SizeType to_index(IntegerType idx) noexcept
{
const IntegerType zero = 0;
const auto result = static_cast<SizeType>(idx); // NOLINT(bugprone-signed-char-misuse,cert-str34-c): negative values are mapped below
return (idx < zero || static_cast<IntegerType>(result) != idx) ? (std::numeric_limits<SizeType>::max)() : result;
}
/// the entry of the element of an array at an index below its size (a link
/// in the moved sequences of editable documents)
template<bool Editable>
const node* element_at(const document_data& d, const node* array, std::size_t idx) noexcept
{
using nav = navigation<Editable>;
const node* e = nav::first(d, array);
if (nav::editable() && (array->flags & node_flags::moved) != 0 && d.edits->moved_cap[array->off] != 0)
{
return e + idx; // a growable block: one link per element
}
for (std::size_t i = 0; i < idx; ++i)
{
e = document_data::after(e);
}
return e;
}
/// the entry of the last element of a non-empty array, or the key of the
/// last member of a non-empty object
template<bool Editable>
const node* last_child(const document_data& d, const node* container) noexcept
{
const std::size_t value_offset = container->kind == static_cast<std::uint8_t>(value_t::object) ? 1 : 0;
const node* const end = navigation<Editable>::end(d, container);
const node* last = navigation<Editable>::first(d, container);
for (const node* c = document_data::after(last + value_offset); c != end; c = document_data::after(c + value_offset))
{
last = c;
}
return last;
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/macro_scope.hpp
+80
View File
@@ -0,0 +1,80 @@
// __ _____ _____ _____
// __| | __| | | | 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
// Macros of json_view.hpp and its detail headers. json.hpp undefines its own
// macros at its end (macro_unscope.hpp), so the view defines the few it needs
// under its own prefix; json_view.hpp undefines them all at its end
// (detail/view/macro_unscope.hpp). Configuration that json.hpp undefines is
// read from detail::abi_config instead.
#if (defined(__cplusplus) && __cplusplus >= 201703L) || (defined(_MSVC_LANG) && _MSVC_LANG >= 201703L)
#define NLOHMANN_VIEW_HAS_CPP_17 1
#else
#define NLOHMANN_VIEW_HAS_CPP_17 0
#endif
#if defined(__GNUC__) || defined(__clang__)
#define NLOHMANN_VIEW_LIKELY(x) __builtin_expect(!!(x), 1)
#define NLOHMANN_VIEW_UNLIKELY(x) __builtin_expect(!!(x), 0)
#define NLOHMANN_VIEW_ALWAYS_INLINE inline __attribute__((always_inline))
#define NLOHMANN_VIEW_NOINLINE __attribute__((noinline))
#elif defined(_MSC_VER)
#define NLOHMANN_VIEW_LIKELY(x) (x)
#define NLOHMANN_VIEW_UNLIKELY(x) (x)
// plain inline: __forceinline makes MSVC report C4714 (not inlined) for
// function templates it cannot inline, which is an error under /WX; the
// forced inlining is only a performance hint
#define NLOHMANN_VIEW_ALWAYS_INLINE inline
#define NLOHMANN_VIEW_NOINLINE __declspec(noinline)
#else
#define NLOHMANN_VIEW_LIKELY(x) (x)
#define NLOHMANN_VIEW_UNLIKELY(x) (x)
#define NLOHMANN_VIEW_ALWAYS_INLINE inline
#define NLOHMANN_VIEW_NOINLINE
#endif
#if defined(__GNUC__) || defined(__clang__)
#define NLOHMANN_VIEW_NODISCARD __attribute__((warn_unused_result))
#elif defined(_MSC_VER)
#define NLOHMANN_VIEW_NODISCARD _Check_return_
#else
#define NLOHMANN_VIEW_NODISCARD
#endif
// exceptions as in json.hpp (JSON_NOEXCEPTION, JSON_THROW_USER)
#if (defined(__cpp_exceptions) || defined(__EXCEPTIONS) || defined(_CPPUNWIND)) && !defined(JSON_NOEXCEPTION)
#define NLOHMANN_VIEW_THROW(exception) throw exception
#else
#include <cstdlib>
// (the exception is built first, so that the arguments of the throwing
// helpers count as used; the program ends anyway)
#define NLOHMANN_VIEW_THROW(exception) (static_cast<void>(exception), std::abort())
#endif
#if defined(JSON_THROW_USER)
#undef NLOHMANN_VIEW_THROW
#define NLOHMANN_VIEW_THROW JSON_THROW_USER
#endif
// the parser stores a node's first word at once where the layout of `node` is
// known to be little-endian (MSVC targets are); elsewhere field by field
#if (defined(__BYTE_ORDER__) && defined(__ORDER_LITTLE_ENDIAN__) && __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__) || defined(_MSC_VER)
#define NLOHMANN_VIEW_LITTLE_ENDIAN 1
#else
#define NLOHMANN_VIEW_LITTLE_ENDIAN 0
#endif
/// eight checks at fixed offsets 0..7
#define NLOHMANN_VIEW_REPEAT_FIRST_8(X) X(0) X(1) X(2) X(3) X(4) X(5) X(6) X(7)
/// eight checks at fixed offsets 8..15
#define NLOHMANN_VIEW_REPEAT_SECOND_8(X) X(8) X(9) X(10) X(11) X(12) X(13) X(14) X(15)
/// sixteen checks at fixed offsets 0..15
#define NLOHMANN_VIEW_REPEAT16(X) NLOHMANN_VIEW_REPEAT_FIRST_8(X) NLOHMANN_VIEW_REPEAT_SECOND_8(X)
include/nlohmann/detail/view/macro_unscope.hpp
+30
View File
@@ -0,0 +1,30 @@
// __ _____ _____ _____
// __| | __| | | | 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
// undefine the macros of detail/view/macro_scope.hpp (at the end of json_view.hpp)
#undef NLOHMANN_VIEW_HAS_CPP_17
#undef NLOHMANN_VIEW_LIKELY
#undef NLOHMANN_VIEW_UNLIKELY
#undef NLOHMANN_VIEW_ALWAYS_INLINE
#undef NLOHMANN_VIEW_NOINLINE
#undef NLOHMANN_VIEW_NODISCARD
#undef NLOHMANN_VIEW_THROW
#undef NLOHMANN_VIEW_LITTLE_ENDIAN
#undef NLOHMANN_VIEW_REPEAT16
#undef NLOHMANN_VIEW_REPEAT_SECOND_8
#undef NLOHMANN_VIEW_REPEAT_FIRST_8
#undef NLOHMANN_VIEW_NEON
#undef NLOHMANN_VIEW_SSE2
#undef NLOHMANN_VIEW_SSSE3
#undef NLOHMANN_VIEW_SSSE3_DISPATCH
#undef NLOHMANN_VIEW_SSSE3_TARGET
#undef NLOHMANN_VIEW_VECTOR
#undef NLOHMANN_VIEW_VECTOR_UTF8
include/nlohmann/detail/view/materialize.hpp
+149
View File
@@ -0,0 +1,149 @@
// __ _____ _____ _____
// __| | __| | | | 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 <algorithm> // max
#include <cstddef> // size_t
#include <cstdint> // int64_t, uint8_t
#include <string> // string
#include <vector> // vector
#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/number.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/*!
@brief the basic_json value of the subtree at n
The subtree is replayed into the SAX handler that parse() uses to build its
values, so the result is the value parse() would produce: duplicate keys keep
the last value, and with JSON_DIAGNOSTICS the parent pointers are set. It is
iterative, so the nesting depth is limited by memory only, as for parse().
Without a lexer the handler records no source positions
(JSON_DIAGNOSTIC_POSITIONS).
*/
template<typename BasicJsonType, bool Editable>
BasicJsonType materialize(const document_data& d, const node* n)
{
using string_t = typename BasicJsonType::string_t;
using sax_t = json_sax_dom_parser<BasicJsonType, iterator_input_adapter<const char*>>;
using nav = navigation<Editable>;
// the open containers: their next element (or key of the next member),
// their end, and whether they are objects; sized once from the
// document's deepest nesting (for a subtree an upper bound)
struct frame
{
const node* pos;
const node* end;
bool object;
};
BasicJsonType result;
sax_t sax(result, true);
const string_t no_token{};
std::vector<frame> open((std::max)(d.max_depth, std::size_t{1}));
std::size_t depth = 0;
for (;;)
{
// false positive: n comes from nav::value(), which never returns null for a valid index
// @infer-ignore NULLPTR_DEREFERENCE
switch (static_cast<value_t>(n->kind))
{
case value_t::object:
case value_t::array:
{
const bool object = n->kind == static_cast<std::uint8_t>(value_t::object);
if (object)
{
sax.start_object(n->len);
}
else
{
sax.start_array(n->len);
}
if (NLOHMANN_VIEW_UNLIKELY(depth == open.size()))
{
open.resize(depth * 2); // (deeper than the recorded nesting, e.g. after edits)
}
open[depth++] = frame{nav::first(d, n), nav::end(d, n), object};
break;
}
case value_t::string:
{
string_t s(d.str(*n), n->len);
sax.string(s);
break;
}
case value_t::number_integer:
sax.number_integer(static_cast<typename BasicJsonType::number_integer_t>(static_cast<std::int64_t>(integer_bits(*n))));
break;
case value_t::number_unsigned:
sax.number_unsigned(static_cast<typename BasicJsonType::number_unsigned_t>(integer_bits(*n)));
break;
case value_t::number_float:
sax.number_float(float_value<typename BasicJsonType::number_float_t>(d, *n), no_token);
break;
case value_t::boolean:
sax.boolean((n->flags & node_flags::is_true) != 0);
break;
case value_t::null:
case value_t::binary:
case value_t::discarded:
default:
sax.null();
break;
}
// the next value: close finished containers, then read the key
for (;;)
{
if (depth == 0)
{
return result;
}
frame& f = open[depth - 1];
if (f.pos == f.end)
{
if (f.object)
{
sax.end_object();
}
else
{
sax.end_array();
}
--depth;
continue;
}
const node* entry = f.pos;
if (f.object)
{
string_t key(d.str(*entry), entry->len);
sax.key(key);
++entry;
}
n = nav::value(entry);
f.pos = document_data::after(entry);
break;
}
}
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/node.hpp
+140
View File
@@ -0,0 +1,140 @@
// __ _____ _____ _____
// __| | __| | | | 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> // uint8_t, uint16_t, uint32_t, uint64_t
#include <cstring> // memcpy
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/// The largest input a document accepts, in bytes. Offsets and node counts are
/// 32 bits wide; the limit keeps 16 bytes (the width of the scanner's steps)
/// below 2^32, so that a position one step past the end of the text fits.
constexpr std::size_t max_input_size() noexcept
{
return 0xFFFFFFEFu;
}
/// node flags
struct node_flags
{
static constexpr std::uint8_t escaped = 1; ///< string payload lives in the decode arena, not the source
static constexpr std::uint8_t edited = 2; ///< string or number token lives in the edit arena (editable documents)
static constexpr std::uint8_t storage = escaped | edited; ///< mask: where a string or number token lives (index into document_data::base)
static constexpr std::uint8_t is_true = 4; ///< boolean value
static constexpr std::uint8_t moved = 8; ///< array/object: the elements live in a separate sequence (editable documents)
static constexpr std::uint8_t is_new = 16; ///< written by an edit: no source position
static constexpr std::uint8_t linked = 32; ///< an entry of a moved sequence links to this value (editable documents): its extent in the parsed layout no longer matters
};
/// kind of an entry of an edited sequence that stands for a value stored
/// elsewhere (the address of the value's node is kept in the len/next bytes)
constexpr std::uint8_t kind_link = 10;
/// One entry of the flat index, in document order. An object's members are
/// stored as key node followed by the value's subtree. Integers keep their
/// converted 64-bit value in the len/next bytes (the node after a scalar is
/// always the next one, and the token length follows from `extra`).
struct node
{
std::uint8_t kind; ///< value_t, or kind_link
std::uint8_t flags; ///< node_flags
std::uint16_t extra; ///< numbers: integer digits (low byte) and fraction digits (high byte), 255 = "many"; objects: number of the object's key hash index (1-based, 0 = none); otherwise 0
std::uint32_t off; ///< source offset (string content, number token, literal, bracket); arena offset if escaped/edited; number of the element sequence if moved
std::uint32_t len; ///< string: decoded bytes; float: token bytes; array/object: element count
std::uint32_t next; ///< array/object: number of nodes of the subtree (its extent in the enclosing sequence)
};
static_assert(sizeof(node) == 16, "node must stay 16 bytes");
// the node kinds are value_t values; the test below (object and array are 1
// and 2) and those of the number kinds depend on this numbering
static_assert(static_cast<std::uint8_t>(value_t::null) == 0 && static_cast<std::uint8_t>(value_t::object) == 1
&& static_cast<std::uint8_t>(value_t::array) == 2 && static_cast<std::uint8_t>(value_t::string) == 3
&& static_cast<std::uint8_t>(value_t::boolean) == 4 && static_cast<std::uint8_t>(value_t::number_integer) == 5
&& static_cast<std::uint8_t>(value_t::number_unsigned) == 6 && static_cast<std::uint8_t>(value_t::number_float) == 7,
"the node format depends on the numbering of value_t");
NLOHMANN_VIEW_ALWAYS_INLINE bool is_container(const node& n) noexcept
{
return static_cast<unsigned>(n.kind) - 1u <= 1u;
}
/// the value a link node stands for
NLOHMANN_VIEW_ALWAYS_INLINE const node* link_target(const node& n) noexcept
{
const node* t = nullptr;
std::memcpy(static_cast<void*>(&t), reinterpret_cast<const unsigned char*>(&n) + 8, sizeof(const node*)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
return t;
}
/// let the entry n stand for the value at target (and mark the value)
inline void make_link(node& n, node* target) noexcept
{
target->flags = static_cast<std::uint8_t>(target->flags | node_flags::linked);
n = node{};
n.kind = kind_link;
std::memcpy(reinterpret_cast<unsigned char*>(&n) + 8, static_cast<const void*>(&target), sizeof(const node*)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
}
/// the converted value of an integer node: len is its low half, next its high
/// half (on little-endian targets the two words are the value in memory)
NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t integer_bits(const node& n) noexcept
{
#if NLOHMANN_VIEW_LITTLE_ENDIAN
std::uint64_t v = 0;
std::memcpy(&v, reinterpret_cast<const unsigned char*>(&n) + 8, 8); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
return v;
#else
return static_cast<std::uint64_t>(n.len) | (static_cast<std::uint64_t>(n.next) << 32);
#endif
}
NLOHMANN_VIEW_ALWAYS_INLINE void set_integer_bits(node& n, std::uint64_t v) noexcept
{
#if NLOHMANN_VIEW_LITTLE_ENDIAN
std::memcpy(reinterpret_cast<unsigned char*>(&n) + 8, &v, 8); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
#else
n.len = static_cast<std::uint32_t>(v);
n.next = static_cast<std::uint32_t>(v >> 32);
#endif
}
/// token length of a number node
NLOHMANN_VIEW_ALWAYS_INLINE std::uint32_t number_length(const node& n) noexcept
{
return n.kind == static_cast<std::uint8_t>(value_t::number_float) ? n.len
: (n.extra & 0xFFu) + (n.kind == static_cast<std::uint8_t>(value_t::number_integer) ? 1u : 0u);
}
/// estimated number of nodes for an input of `size` bytes (one node per ~12
/// bytes covers typical documents without regrowth)
inline std::size_t estimate_nodes(std::size_t size) noexcept
{
return (size / 12) + 16;
}
/// estimated number of nodes for the input [src, src + size): pretty-printed
/// input (whitespace after the first byte) needs about a node per 12 bytes,
/// minified input up to one per 4 (yyjson tells the two apart the same way)
inline std::size_t estimate_nodes(const char* src, std::size_t size) noexcept
{
return size >= 2 && (src[1] == ' ' || src[1] == '\n' || src[1] == '\r' || src[1] == '\t') ? estimate_nodes(size) : (size / 4) + 16;
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/number.hpp
+222
View File
@@ -0,0 +1,222 @@
// __ _____ _____ _____
// __| | __| | | | 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 <limits> // numeric_limits
#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 locate the decimal point and the end of the mantissa of a float token
Also checks that the token is a JSON number. Tokens of the parser and of edits
always are; an image loaded with image_check::bounds can hold any bytes, which
must not reach the conversion (it expects a well-formed token).
*/
inline bool float_token_layout(const char* first, const char* last, std::size_t& dot, std::size_t& mantissa_end) noexcept
{
const auto digit = [last](const char* q)
{
return q != last && is_digit(static_cast<unsigned char>(*q));
};
const char* p = first;
p += (p != last && *p == '-') ? 1 : 0;
if (!digit(p) || (*p == '0' && digit(p + 1)))
{
return false;
}
do
{
++p;
}
while (digit(p));
dot = std::string::npos;
if (p != last && *p == '.')
{
dot = static_cast<std::size_t>(p - first);
if (!digit(++p))
{
return false;
}
do
{
++p;
}
while (digit(p));
}
mantissa_end = static_cast<std::size_t>(p - first);
if (p != last && (*p == 'e' || *p == 'E'))
{
++p;
p += (p != last && (*p == '+' || *p == '-')) ? 1 : 0;
if (!digit(p))
{
return false;
}
do
{
++p;
}
while (digit(p));
}
return p == last;
}
/*!
@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. A token that is not a JSON number (only in a
damaged image loaded with image_check::bounds) yields 0.
*/
template<typename FloatType>
NLOHMANN_VIEW_NOINLINE FloatType float_value(const char* first, const node& n)
{
const char* const last = first + n.len;
std::size_t dot = 0;
std::size_t mantissa_end = 0;
if (NLOHMANN_VIEW_UNLIKELY(!float_token_layout(first, last, dot, mantissa_end)))
{
return FloatType{};
}
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). The token is not read beyond e, and the digits are taken
// as unsigned, so that a token that is not well-formed (a damaged
// image loaded with image_check::bounds) yields a wrong value, but no
// overflow.
++p;
const bool exp_negative = p != e && *p == '-';
p += (p != e && (*p == '-' || *p == '+')) ? 1 : 0;
std::int64_t exp_value = 0;
for (; p != e; ++p)
{
if (exp_value < 0x10000000)
{
exp_value = (exp_value * 10) + static_cast<unsigned char>(*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 a float set by an edit: its token (the shortest round-trip
/// text, or "nan", "inf", "-inf") in the edit arena
template<typename FloatType>
NLOHMANN_VIEW_NOINLINE FloatType edited_float(const char* token, const node& n)
{
if (token[0] == 'n')
{
return std::numeric_limits<FloatType>::quiet_NaN();
}
if (token[0] == 'i' || (token[0] == '-' && token[1] == 'i'))
{
return token[0] == 'i' ? std::numeric_limits<FloatType>::infinity() : -std::numeric_limits<FloatType>::infinity();
}
return float_value<FloatType>(token, n);
}
/// 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)
{
if (NLOHMANN_VIEW_UNLIKELY((n.flags & node_flags::storage) == node_flags::edited))
{
return edited_float<FloatType>(d.str(n), 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
include/nlohmann/detail/view/object_index.hpp
+154
View File
@@ -0,0 +1,154 @@
// __ _____ _____ _____
// __| | __| | | | 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> // uint32_t, uint64_t
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/document_data.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
#include <nlohmann/detail/view/node.hpp>
// Hash indexes of the keys of large objects, so that a lookup does not compare thousands
// of keys (as Boost.JSON switches from a linear search to a hash table for
// large objects). An object with document_data::index_min_members members or
// more gets an open-addressing table after parsing; its node stores the
// number of the table (1-based) in `extra`. A slot holds the offset of a key
// node from its object node (0: empty). Of duplicate keys, the first is kept,
// as for the linear search.
//
// The hash is not seeded, so keys chosen to collide could make the build
// quadratic. A key therefore sits at most index_max_displacement slots away
// from its home slot; if a key would sit further away, the table is dropped
// and the object is searched linearly (like a small one). For the same
// reason, a lookup visits at most index_max_displacement + 1 slots.
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/// the farthest a key may sit from its home slot (a table with at most half of
/// its slots in use gives random keys a distance of about 50 for millions of
/// members; and every member costs at most this many steps while building)
constexpr std::size_t index_max_displacement = 64;
// a table has at least 2 * len slots (len >= index_min_members), so the probe
// window of index_max_displacement + 1 slots stays far smaller than the table
// and a probe never wraps around onto its own start
static_assert(document_data::index_min_members >= 2 * index_max_displacement,
"a table must be much larger than the probe window of a lookup");
/// hash of a key: its bytes, eight at a time, in a fixed byte order
inline std::uint64_t key_hash(const char* s, std::size_t n) noexcept
{
std::uint64_t h = 0x9E3779B97F4A7C15u * (n + 1);
const auto* p = reinterpret_cast<const unsigned char*>(s); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
while (n >= 8)
{
h = (h ^ read_eight_bytes(p)) * 0xBF58476D1CE4E5B9u;
h ^= h >> 29u;
p += 8;
n -= 8;
}
std::uint64_t w = 0;
for (std::size_t i = 0; i < n; ++i)
{
w |= static_cast<std::uint64_t>(p[i]) << (8u * i);
}
h = (h ^ w) * 0x94D049BB133111EBu;
return h ^ (h >> 31u);
}
/// build the table of a large object
inline void build_object_index(document_data& d, node* obj)
{
if (d.indexes.size() >= 0xFFFFu)
{
return; // LCOV_EXCL_LINE (the number must fit `extra`; more large objects are searched linearly)
}
std::size_t cap = 16;
while (cap < 2 * static_cast<std::size_t>(obj->len))
{
cap *= 2;
}
const std::size_t start = d.index_slots.size();
d.index_slots.resize(start + cap, 0);
std::uint32_t* const table = d.index_slots.data() + start;
const std::size_t mask = cap - 1;
for (const node* k = document_data::first_child(obj), *end = document_data::child_end(obj); k != end; k = document_data::after(k + 1))
{
const char* const key = d.str(*k);
std::size_t slot = conditional_static_cast<std::size_t>(key_hash(key, k->len)) & mask;
bool duplicate = false;
std::size_t distance = 0;
while (table[slot] != 0)
{
const node* const other = obj + table[slot];
if (d.key_equals(*other, key, k->len))
{
duplicate = true; // keep the first
break;
}
if (distance == index_max_displacement)
{
// too many keys share a home region
d.index_slots.resize(start); // no table: the object is searched linearly
return;
}
++distance;
slot = (slot + 1) & mask;
}
if (!duplicate)
{
table[slot] = static_cast<std::uint32_t>(k - obj);
}
}
d.indexes.push_back(document_data::object_index{start, static_cast<std::uint32_t>(mask)});
obj->extra = static_cast<std::uint16_t>(d.indexes.size());
}
/// build the tables of the large objects the parser noted
inline void build_object_indexes(document_data& d)
{
for (const std::uint32_t i : d.large_objects)
{
build_object_index(d, d.nodes + i);
}
}
/// the key node of the first member with this key of an indexed object, or
/// nullptr
inline const node* find_indexed(const document_data& d, const node* obj, const char* key, std::size_t n) noexcept
{
const document_data::object_index& ix = d.indexes[obj->extra - 1u];
const std::uint32_t* const table = d.index_slots.data() + ix.start;
std::size_t slot = conditional_static_cast<std::size_t>(key_hash(key, n)) & ix.mask;
for (std::size_t distance = 0; distance <= index_max_displacement; ++distance)
{
const std::uint32_t s = table[slot];
if (s == 0)
{
return nullptr;
}
const node* const k = obj + s;
if (d.key_equals(*k, key, n))
{
return k;
}
slot = (slot + 1) & ix.mask;
}
return nullptr; // (no key sits further from its home slot)
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/pointer.hpp
+173
View File
@@ -0,0 +1,173 @@
// __ _____ _____ _____
// __| | __| | | | 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> // uint64_t
#include <limits> // numeric_limits
#include <string> // string, to_string
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/errors.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/// what resolving a JSON pointer does where it cannot continue
enum class pointer_mode
{
unchecked, ///< as const basic_json::operator[]: a discarded view where basic_json's behavior is undefined
checked, ///< as basic_json::at(): out_of_range.401/403
value, ///< as basic_json::value(): no out_of_range exceptions (the default value is used)
contains, ///< as basic_json::contains(): no exceptions at all
};
/// the outcome of reading an array index from a reference token
enum class index_status
{
ok,
leading_zero, ///< parse_error.106
not_number, ///< parse_error.109
unresolved, ///< out_of_range.404
too_large, ///< out_of_range.410
};
/// reads an array index like json_pointer::array_index (RFC 6901, Sect. 4),
/// but reports errors instead of throwing them
template<typename StringType>
index_status array_index(const StringType& s, std::size_t& idx) noexcept
{
// as basic_json: the empty token and "-" (past the last element) are
// unresolved rather than not a number
if (s.empty() || (s.size() == 1 && s[0] == '-'))
{
return index_status::unresolved;
}
if (s[0] < '0' || s[0] > '9')
{
return index_status::not_number;
}
if (s.size() > 1 && s[0] == '0')
{
return index_status::leading_zero;
}
std::uint64_t v = 0;
for (const auto c : s)
{
const auto d = static_cast<unsigned>(static_cast<unsigned char>(c)) - '0';
if (d > 9 || v > ((std::numeric_limits<std::uint64_t>::max)() - d) / 10)
{
return index_status::unresolved; // not a number, or beyond unsigned long long
}
v = (v * 10) + d;
}
if (v >= (std::numeric_limits<std::size_t>::max)()) // (std::size_t converts to std::uint64_t implicitly)
{
return index_status::too_large;
}
idx = static_cast<std::size_t>(v);
return index_status::ok;
}
/// throws the exception json_pointer::array_index throws for this status
template<typename StringType>
[[noreturn]] NLOHMANN_VIEW_NOINLINE void throw_array_index_error(index_status status, const StringType& s)
{
switch (status)
{
case index_status::leading_zero:
throw_parse_error(106, concat("array index '", s, "' must not begin with '0'"));
case index_status::not_number:
throw_parse_error(109, concat("array index '", s, "' is not a number"));
case index_status::too_large:
throw_out_of_range(410, concat("array index ", s, " exceeds size_type")); // LCOV_EXCL_LINE
case index_status::unresolved:
case index_status::ok:
default:
throw_out_of_range(404, concat("unresolved reference token '", s, "'"));
}
}
/*!
@brief resolve the reference tokens of a JSON pointer, starting at a view
The exceptions are those basic_json throws for the same pointer; where
basic_json's behavior is undefined (a missing key or an index out of range
with const operator[]), the result is a discarded view.
*/
template<typename View, typename Tokens>
View resolve_pointer(View cur, const Tokens& tokens, pointer_mode mode)
{
using string_view_t = typename View::string_view_t;
const bool throwing = mode == pointer_mode::unchecked || mode == pointer_mode::checked;
for (const auto& token : tokens)
{
if (cur.is_object())
{
const auto it = cur.find(string_view_t(token.data(), token.size()));
if (it == cur.end())
{
if (mode == pointer_mode::checked)
{
throw_out_of_range(403, concat("key '", token, "' not found"));
}
return View();
}
cur = *it;
}
else if (cur.is_array())
{
if (token.size() == 1 && token[0] == '-')
{
if (throwing)
{
throw_out_of_range(402, concat("array index '-' (", std::to_string(cur.size()), ") is out of range"));
}
return View();
}
std::size_t idx = 0;
const index_status status = array_index(token, idx);
if (status != index_status::ok)
{
const bool parse_error = status == index_status::leading_zero || status == index_status::not_number;
if (throwing || (mode == pointer_mode::value && parse_error))
{
throw_array_index_error(status, token);
}
return View();
}
if (idx >= cur.size())
{
if (mode == pointer_mode::checked)
{
throw_out_of_range(401, concat("array index ", std::to_string(idx), " is out of range"));
}
return View();
}
cur = cur[idx];
}
else
{
if (throwing)
{
throw_out_of_range(404, concat("unresolved reference token '", token, "'"));
}
return View();
}
}
return cur;
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/scan.hpp
+220
View File
@@ -0,0 +1,220 @@
// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-FileCopyrightText: 2020 YaoYuan <https://github.com/ibireme/yyjson>
// SPDX-License-Identifier: MIT
#pragma once
#include <array> // array
#include <cstddef> // size_t
#include <cstdint> // uint8_t, uint16_t, uint64_t
#include <cstring> // memcpy
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
#include <nlohmann/detail/view/simd.hpp>
// Scanning primitives of the view's parser. The unrolled checks at fixed
// offsets follow yyjson (https://github.com/ibireme/yyjson, MIT license): the
// loads do not depend on each other, so the CPU can run ahead. Words are read
// with read_eight_bytes(), so nothing here depends on the byte order.
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/// 1 for bytes that may appear verbatim in a string: 0x20..0x7F except '"' and '\\'
inline const std::uint8_t* string_plain() noexcept
{
static const std::array<std::uint8_t, 256> table =
{
{
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0x00..0x1F
1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x20..0x3F ('"')
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, // 0x40..0x5F ('\\')
1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, // 0x60..0x7F
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0x80..0x9F
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xA0..0xBF
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xC0..0xDF
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, // 0xE0..0xFF
}
};
return table.data();
}
NLOHMANN_VIEW_ALWAYS_INLINE bool is_digit(unsigned char c) noexcept
{
return static_cast<unsigned char>(c - '0') <= 9;
}
/// two bytes as they are in memory (only compared with byte-symmetric patterns)
NLOHMANN_VIEW_ALWAYS_INLINE std::uint16_t load16(const unsigned char* p) noexcept
{
std::uint16_t w = 0;
std::memcpy(&w, p, 2);
return w;
}
/// Advance over plain string bytes and well-formed UTF-8. Stops at a quote,
/// a backslash, a control character, ill-formed UTF-8, or the end. The first
/// bytes are checked one by one, so that the position advances by constants
/// in predicted branches: 16 for keys, whose lengths repeat from record to
/// record, and 8 for string values (Value) where a vector loop follows, as
/// their lengths vary more. Longer runs continue 16 bytes at a time with NEON
/// or SSE2, else eight bytes at a time. With SSE2, the run is checked 16 bytes
/// at a time from its first byte instead: on x86-64, one compare that finds
/// the end of most keys and short values is faster than a branch per byte (on
/// AArch64, where a NEON mask costs more and branches predict well, slower).
template<bool Value = false>
NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* scan_string_run(const unsigned char* p, const unsigned char* e) noexcept
{
const std::uint8_t* plain = string_plain();
for (;;)
{
#if NLOHMANN_VIEW_SSE2
p = vector_plain_run(p, e);
#else
if (e - p >= 16)
{
#define NLOHMANN_VIEW_STEP(i) if (NLOHMANN_VIEW_LIKELY(plain[p[i]] != 0)) {} else { p += (i); goto stop; }
NLOHMANN_VIEW_REPEAT_FIRST_8(NLOHMANN_VIEW_STEP)
#if NLOHMANN_VIEW_VECTOR
if (!Value) // (a plain `!Value || !NLOHMANN_VIEW_VECTOR` is a constant condition for MSVC, C4127)
#endif
{
NLOHMANN_VIEW_REPEAT_SECOND_8(NLOHMANN_VIEW_STEP)
p += 8;
}
#undef NLOHMANN_VIEW_STEP
p += 8;
#if NLOHMANN_VIEW_VECTOR
p = vector_plain_run(p, e);
if (p != e && plain[*p] == 0)
{
goto stop;
}
#else
while (e - p >= 8)
{
const std::uint64_t special = swar_string_special(read_eight_bytes(p));
if (special != 0)
{
p += count_trailing_zeros(special) / 8;
goto stop;
}
p += 8;
}
#endif
continue;
}
#endif
while (p != e && plain[*p] != 0)
{
++p;
}
if (p == e)
{
return p;
}
#if !NLOHMANN_VIEW_SSE2
stop:
#endif
if (*p < 0x80)
{
return p; // quote, backslash, or control character
}
#if NLOHMANN_VIEW_VECTOR_UTF8
#if NLOHMANN_VIEW_SSSE3_DISPATCH
if (NLOHMANN_VIEW_LIKELY(cpu_has_ssse3()))
#endif
{
// non-ASCII: the vector check, out of line
return scan_string_vector(p, e, plain);
}
#endif
#if !NLOHMANN_VIEW_VECTOR_UTF8 || NLOHMANN_VIEW_SSSE3_DISPATCH
// non-ASCII: a run of well-formed sequences (the library's check, so
// that exactly what json::parse accepts is accepted)
do
{
const std::size_t n = validate_one_utf8(p, static_cast<std::size_t>(e - p));
if (n == 0)
{
return p;
}
p += n;
}
while (p != e && *p >= 0x80);
#endif
}
}
/// advance over ASCII digits
NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* skip_digits(const unsigned char* p, const unsigned char* e) noexcept
{
while (e - p >= 16)
{
#define NLOHMANN_VIEW_STEP(i) if (NLOHMANN_VIEW_LIKELY(is_digit(p[i]))) {} else { return p + (i); }
NLOHMANN_VIEW_REPEAT16(NLOHMANN_VIEW_STEP)
#undef NLOHMANN_VIEW_STEP
p += 16;
}
while (p != e && is_digit(*p))
{
++p;
}
return p;
}
/// powers of ten up to 10^19 as integers
inline std::uint64_t int_pow10(unsigned k) noexcept
{
return ::nlohmann::detail::dtoa_impl::powers_of_ten()[k];
}
/// value of 0 < k < 8 digits at p in one step if [p, p + 8) lies below
/// limit, else one digit at a time (whole blocks of eight digits are read by
/// parse_upto19() directly)
NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t parse_upto8(const unsigned char* p, unsigned k, const unsigned char* limit) noexcept
{
if (NLOHMANN_VIEW_LIKELY(limit - p >= 8))
{
// move the k digits to the top and pad the vacated low bytes with '0'
const unsigned shift = 8 * (8 - k);
return parse_eight_digits((read_eight_bytes(p) << shift) | (0x3030303030303030u >> (8 * k)));
}
std::uint64_t v = 0;
for (unsigned i = 0; i < k; ++i)
{
v = (v * 10) + static_cast<std::uint64_t>(p[i] - '0');
}
return v;
}
/// value of k <= 19 digits at p
NLOHMANN_VIEW_ALWAYS_INLINE std::uint64_t parse_upto19(const unsigned char* p, unsigned k, const unsigned char* limit) noexcept
{
std::uint64_t w = 0;
while (k >= 8)
{
// (eight digits of the token: they lie below limit)
w = (w * 100000000u) + parse_eight_digits(read_eight_bytes(p));
p += 8;
k -= 8;
}
if (k != 0)
{
w = (w * int_pow10(k)) + parse_upto8(p, k, limit);
}
return w;
}
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/serializer.hpp
+973
View File
@@ -0,0 +1,973 @@
// __ _____ _____ _____
// __| | __| | | | 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 <algorithm> // max
#include <array> // array
#include <cmath> // isfinite
#include <cstddef> // size_t
#include <cstdint> // uint8_t, uint32_t
#include <cstring> // memcpy, memset
#include <limits> // numeric_limits
#include <type_traits> // integral_constant
#include <vector> // vector
#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/number.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/// append-only output buffer: writes through a raw pointer into a string that
/// is resized ahead, and trimmed by finish(). The estimate is reserved, and the
/// string grows in steps of 64 KiB within it: resize() fills the new bytes
/// with zeros (before C++23, a string cannot grow without), and a small step
/// is filled while the writer is about to use it, in the cache, instead of
/// filling the whole estimate in memory first.
template<typename StringType>
class output_buffer
{
public:
output_buffer(StringType& out, std::size_t estimate)
: m_out(sized(out, estimate))
, m_pos(&m_out[0])
, m_end(m_pos + m_out.size())
{}
void finish()
{
const auto size = static_cast<std::size_t>(m_pos - m_out.data());
m_out.resize(size);
}
NLOHMANN_VIEW_ALWAYS_INLINE void reserve(std::size_t n)
{
if (NLOHMANN_VIEW_UNLIKELY(static_cast<std::size_t>(m_end - m_pos) < n))
{
grow(n);
}
}
NLOHMANN_VIEW_ALWAYS_INLINE void put(char c)
{
reserve(1);
*m_pos++ = c;
}
NLOHMANN_VIEW_ALWAYS_INLINE void put(const char* s, std::size_t n)
{
reserve(n);
std::memcpy(m_pos, s, n);
m_pos += n;
}
/// a string literal, without its terminating NUL
template<std::size_t N>
NLOHMANN_VIEW_ALWAYS_INLINE void put(const char (&s)[N]) // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
{
put(s, N - 1);
}
void put_repeated(char c, std::size_t n)
{
reserve(n);
std::memset(m_pos, c, n);
m_pos += n;
}
/// the write position and the end of the writable space, for a writer
/// that keeps the position in a local variable (set_cursor() hands it back)
char* cursor() const noexcept
{
return m_pos;
}
char* limit() const noexcept
{
return m_end;
}
void set_cursor(char* p) noexcept
{
m_pos = p;
}
private:
/// the size of a growth step (a function: std::min() takes a reference,
/// which a static constexpr member does not have before C++17)
static constexpr std::size_t step() noexcept
{
return 0x10000;
}
static StringType& sized(StringType& out, std::size_t estimate)
{
out.reserve(estimate);
out.resize((std::min)((std::max)(estimate, static_cast<std::size_t>(64)), step()));
return out;
}
NLOHMANN_VIEW_NOINLINE void grow(std::size_t n)
{
const auto used = static_cast<std::size_t>(m_pos - m_out.data());
// (a step does not go beyond the reserved estimate, so that a good
// estimate is never copied to a larger allocation)
const std::size_t size = (std::max)((std::min)(m_out.size() + step(), m_out.capacity()), used + n + 256);
if (size > m_out.capacity())
{
m_out.reserve((std::max)(m_out.capacity() * 2, size));
}
m_out.resize(size);
m_pos = &m_out[0] + used;
m_end = &m_out[0] + m_out.size();
}
StringType& m_out;
char* m_pos;
char* m_end;
};
/// The length of the run at s that dump() writes unchanged without
/// ensure_ascii: all bytes but quotes, backslashes, and control characters.
/// Unlike detail::string_bulk_run(), non-ASCII bytes are not validated: the
/// strings of a document are valid UTF-8 (a damaged image loaded with
/// image_check::bounds can have others, which are then written unchanged).
inline std::size_t plain_output_run(const unsigned char* s, std::size_t n) noexcept
{
constexpr std::uint64_t ones = 0x0101010101010101ull;
constexpr std::uint64_t high = 0x8080808080808080ull;
std::size_t i = 0;
for (; i + 8 <= n; i += 8)
{
const std::uint64_t v = read_eight_bytes(s + i);
const std::uint64_t q = v ^ 0x2222222222222222ull; // '"'
const std::uint64_t b = v ^ 0x5C5C5C5C5C5C5C5Cull; // '\\'
const std::uint64_t stop = (((q - ones) & ~q) | ((b - ones) & ~b) | ((v - 0x2020202020202020ull) & ~v)) & high;
if (stop != 0)
{
// the lowest flagged byte is the first stop: borrows only flag bytes above a true one
return i + (static_cast<std::size_t>(count_trailing_zeros(stop)) / 8);
}
}
for (; i < n; ++i)
{
if (s[i] == '"' || s[i] == '\\' || s[i] < 0x20)
{
return i;
}
}
return n;
}
/// A stack that starts in a buffer of the caller (a local array) and moves to
/// the heap (a vector of the caller) only when that is full, so that dumps of
/// shallow documents need no allocation. The top is a pointer, as in
/// std::vector. grow() is static and out of line: it gets the vector and the
/// used range and returns the new storage, so the address of the stack never
/// reaches a call. Otherwise the compiler would have to keep the three
/// pointers in memory and load and store them on every push_back() and
/// pop_back(), not just when growing.
template<typename T>
class small_stack
{
public:
small_stack(T* buffer, std::size_t capacity, std::vector<T>& heap) noexcept
: m_begin(buffer), m_top(buffer), m_end(buffer + capacity), m_heap(heap)
{}
small_stack(const small_stack&) = delete;
small_stack(small_stack&&) = delete;
small_stack& operator=(const small_stack&) = delete;
small_stack& operator=(small_stack&&) = delete;
~small_stack() = default;
NLOHMANN_VIEW_ALWAYS_INLINE void push_back(const T& x)
{
if (NLOHMANN_VIEW_UNLIKELY(m_top == m_end))
{
const std::size_t used = size();
const std::size_t capacity = 2 * static_cast<std::size_t>(m_end - m_begin);
m_begin = grow(m_heap, m_begin, used, capacity);
m_top = m_begin + used;
m_end = m_begin + capacity;
}
*m_top++ = x;
}
NLOHMANN_VIEW_ALWAYS_INLINE T& back() noexcept
{
return m_top[-1];
}
NLOHMANN_VIEW_ALWAYS_INLINE void pop_back() noexcept
{
--m_top;
}
NLOHMANN_VIEW_ALWAYS_INLINE bool empty() const noexcept
{
return m_top == m_begin;
}
NLOHMANN_VIEW_ALWAYS_INLINE std::size_t size() const noexcept
{
return static_cast<std::size_t>(m_top - m_begin);
}
private:
/// the used entries moved to heap storage of the given capacity
NLOHMANN_VIEW_NOINLINE static T* grow(std::vector<T>& heap, const T* begin, std::size_t used, std::size_t capacity)
{
std::vector<T> bigger(capacity);
std::copy(begin, begin + used, bigger.begin());
heap.swap(bigger);
return heap.data();
}
T* m_begin;
T* m_top;
T* m_end;
std::vector<T>& m_heap;
};
/// a string literal at w, without its terminating NUL (after room())
/// @return a pointer past it
template<std::size_t N>
NLOHMANN_VIEW_ALWAYS_INLINE char* put_literal(char* w, const char (&s)[N]) noexcept // NOLINT(cppcoreguidelines-avoid-c-arrays,hicpp-avoid-c-arrays,modernize-avoid-c-arrays)
{
std::memcpy(w, s, N - 1);
return w + N - 1;
}
/// how the view's dump() writes a value
struct dump_style
{
bool pretty = false; ///< indent >= 0
std::size_t indent = 0; ///< characters per level
char indent_char = ' ';
bool ensure_ascii = false;
bool source_numbers = false; ///< copy number tokens from the source
};
/*!
@brief write a view's subtree as basic_json::dump() writes the value
The output of a subtree equals ordered_json::parse(text).dump() of it for
the same arguments (members in document order): strings are escaped by the
same rules, with the library's scanning kernels; floats are written with
the library's conversion; integers are copied from the source, where they
are canonical (except "-0", which parse() reads as 0). The walk is
iterative, so the nesting depth is limited by memory only.
*/
template<typename BasicJsonType, bool Editable>
class view_serializer
{
using nav = navigation<Editable>;
using string_t = typename BasicJsonType::string_t;
using number_float_t = typename BasicJsonType::number_float_t;
/// doubles that are IEEE 754 binary64 are written from their bits (Zmij)
using fast_double = std::integral_constant < bool, std::is_same<number_float_t, double>::value && ::nlohmann::detail::dtoa_impl::is_binary64<double>::value >;
public:
view_serializer(const document_data& d, string_t& out, std::size_t estimate, const dump_style& style)
: m_doc(d), m_out(out, estimate), m_style(style)
{}
void dump(const node* root)
{
if (!m_style.pretty && !m_style.ensure_ascii)
{
if (m_style.source_numbers)
{
dump_compact<true>(root);
}
else
{
dump_compact<false>(root);
}
return;
}
struct frame
{
const node* pos; ///< next element, or key of the next member
const node* end;
bool object;
bool first; ///< nothing written yet
};
std::array<frame, 32> buffer; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
std::vector<frame> heap;
small_stack<frame> stack(buffer.data(), buffer.size(), heap);
const node* n = root;
for (;;)
{
// write the value at n
if (is_container(*n))
{
const bool object = n->kind == static_cast<std::uint8_t>(value_t::object);
if (n->len == 0)
{
m_out.put(object ? "{}" : "[]", 2);
}
else
{
m_out.put(object ? '{' : '[');
stack.push_back(frame{nav::first(m_doc, n), nav::end(m_doc, n), object, true});
}
}
else
{
write_scalar(*n);
}
// go to the next value: close finished containers, then separate
for (;;)
{
if (stack.empty())
{
m_out.finish();
return;
}
if (stack.back().pos == stack.back().end)
{
const bool object = stack.back().object;
stack.pop_back();
newline(stack.size());
m_out.put(object ? '}' : ']');
continue;
}
frame& f = stack.back();
if (!f.first)
{
m_out.put(',');
}
f.first = false;
newline(stack.size());
if (f.object)
{
write_string(*f.pos);
if (m_style.pretty)
{
m_out.put(": ");
}
else
{
m_out.put(':');
}
n = nav::value(f.pos + 1);
f.pos = document_data::after(f.pos + 1);
}
else
{
n = nav::value(f.pos);
f.pos = document_data::after(f.pos);
}
break;
}
}
}
private:
/// a string that is not a plain string of the source (decoded, or written
/// by an edit), without ensure_ascii: runs without characters to escape
/// are copied
NLOHMANN_VIEW_NOINLINE void write_decoded(const node& n)
{
const auto* const s = reinterpret_cast<const unsigned char*>(m_doc.str(n)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
m_out.put('"');
for (std::size_t i = 0; i < n.len;)
{
const std::size_t run = plain_output_run(s + i, n.len - i);
if (run != 0)
{
m_out.put(reinterpret_cast<const char*>(s + i), run); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
i += run;
continue;
}
write_codepoint<false>(s[i], s + i, 1); // a quote, a backslash, or a control character
++i;
}
m_out.put('"');
}
/// the copies of dump_compact() that are not fixed-size moves (long
/// strings, or near the end of the source); out of line, so that the
/// compiler does not merge the fixed-size moves into this call
NLOHMANN_VIEW_NOINLINE static void copy_long(char* to, const char* from, std::size_t n) noexcept
{
std::memcpy(to, from, n);
}
/// a compile-time option as a runtime condition: testing the template
/// argument directly makes a condition like `Editable && c` constant when
/// the option is off, which MSVC reports as C4127
static NLOHMANN_VIEW_ALWAYS_INLINE bool enabled(bool option) noexcept
{
return option;
}
/*!
@brief the compact output without ensure_ascii (the default dump())
The same walk as dump(), with the write position in a local variable
(stores through char pointers would otherwise force a reload of the
buffer's members after each one), and with strings and number tokens of
the source copied by fixed-size moves of 32 bytes where the source has
that many bytes left, instead of a library call per token. The buffer
keeps 64 bytes of slack for the overshoot.
*/
template<bool SourceNumbers>
void dump_compact(const node* root)
{
struct frame
{
const node* pos; ///< (editable documents) next element, or key of the next member
const node* end;
bool object;
};
std::array<frame, 32> buffer; // NOLINT(cppcoreguidelines-pro-type-member-init,hicpp-member-init): written before read
std::vector<frame> heap;
small_stack<frame> stack(buffer.data(), buffer.size(), heap);
const char* const src = m_doc.src;
const char* const src_end = src + m_doc.size;
char* w = m_out.cursor();
char* lim = m_out.limit();
// room for n bytes and the slack
const auto room = [&](std::size_t n)
{
if (NLOHMANN_VIEW_UNLIKELY(static_cast<std::size_t>(lim - w) < n + 64))
{
m_out.set_cursor(w);
m_out.reserve(n + 64);
w = m_out.cursor();
lim = m_out.limit();
}
};
// copy n bytes of the source (after room(n))
const auto copy = [&](const char* from, std::size_t n)
{
if (n <= 32 && static_cast<std::size_t>(src_end - from) >= 32)
{
std::memcpy(w, from, 32);
}
else if (n <= 256 && static_cast<std::size_t>(src_end - from) >= n + 32)
{
for (std::size_t i = 0; i < n; i += 32)
{
std::memcpy(w + i, from + i, 32);
}
}
else
{
copy_long(w, from, n);
}
w += n;
};
// a string that is not a plain string of the source (out of line, so
// that the cursor stays in a register here)
const auto escaped = [&](const node & n)
{
m_out.set_cursor(w);
write_decoded(n);
w = m_out.cursor();
lim = m_out.limit();
};
// Read-only documents: the elements of a container follow it in the
// node array, so the walk goes through the array in order, and a
// frame only needs the end of its container. Editable documents: the
// elements of a moved container live elsewhere, so a frame keeps the
// position of the next element (see navigation).
// The innermost open container is kept in registers (cur; end ==
// nullptr: none), the stack holds the ones around it.
frame cur{nullptr, nullptr, false};
const node* n = root;
for (;;)
{
// write the value at n (read-only documents: and advance n)
bool opened = false;
// false positive: n comes from nav::value(), which never returns null for a valid index
// @infer-ignore NULLPTR_DEREFERENCE
switch (static_cast<value_t>(n->kind))
{
case value_t::string:
if ((n->flags & node_flags::storage) == 0)
{
room(n->len + 2);
*w++ = '"';
copy(src + n->off, n->len);
*w++ = '"';
}
else
{
escaped(*n);
}
break;
case value_t::number_integer:
case value_t::number_unsigned:
{
const std::uint32_t len = number_length(*n);
room(len);
if (enabled(Editable) && (n->flags & node_flags::storage) != 0)
{
copy_long(w, m_doc.str(*n), len); // a canonical token written by an edit
w += len;
break;
}
const char* const token = src + n->off;
if (!enabled(SourceNumbers) && NLOHMANN_VIEW_UNLIKELY(len == 2 && token[0] == '-' && token[1] == '0'))
{
*w++ = '0'; // parse() reads -0 as the integer 0
}
else
{
copy(token, len);
}
break;
}
case value_t::number_float:
if (enabled(SourceNumbers) && (n->flags & node_flags::storage) != node_flags::edited)
{
room(n->len);
copy(src + n->off, n->len);
}
else if (enabled(fast_double::value))
{
room(64);
w = write_double_at(w, *n);
}
else
{
m_out.set_cursor(w);
write_float_node(*n);
w = m_out.cursor();
lim = m_out.limit();
}
break;
case value_t::boolean:
room(8);
if ((n->flags & node_flags::is_true) != 0)
{
w = put_literal(w, "true");
}
else
{
w = put_literal(w, "false");
}
break;
case value_t::object:
case value_t::array:
{
const bool object = n->kind == static_cast<std::uint8_t>(value_t::object);
room(8);
if (n->len == 0)
{
w = object ? put_literal(w, "{}") : put_literal(w, "[]");
}
else
{
*w++ = object ? '{' : '[';
stack.push_back(cur);
if (Editable)
{
cur = frame{nav::first(m_doc, n), nav::end(m_doc, n), object};
}
else
{
cur = frame{nullptr, n + n->next, object};
}
opened = true;
}
break;
}
case value_t::null:
room(8);
w = put_literal(w, "null");
break;
case value_t::binary: // LCOV_EXCL_LINE (not in a document)
case value_t::discarded: // LCOV_EXCL_LINE
default: // LCOV_EXCL_LINE
break; // LCOV_EXCL_LINE
}
if (!Editable)
{
++n; // the next node: the first element of an opened container, or the node after a scalar
}
// go to the next value: close finished containers, then separate
// (a container just opened has an element)
if (!opened)
{
for (;;)
{
if (cur.end == nullptr)
{
m_out.set_cursor(w);
m_out.finish();
return;
}
if ((Editable ? cur.pos : n) != cur.end)
{
break;
}
room(1);
*w++ = cur.object ? '}' : ']';
cur = stack.back();
stack.pop_back();
}
room(1);
*w++ = ',';
}
const node* const at = Editable ? cur.pos : n;
if (cur.object)
{
const node& key = *at;
if ((key.flags & node_flags::storage) == 0)
{
room(key.len + 3);
*w++ = '"';
copy(src + key.off, key.len);
w[0] = '"';
w[1] = ':';
w += 2;
}
else
{
escaped(key);
room(1);
*w++ = ':';
}
if (Editable)
{
n = nav::value(at + 1);
cur.pos = document_data::after(at + 1);
}
else
{
++n;
}
}
else if (Editable)
{
n = nav::value(at);
cur.pos = document_data::after(at);
}
}
}
void newline(std::size_t level)
{
if (m_style.pretty)
{
m_out.put('\n');
m_out.put_repeated(m_style.indent_char, level * m_style.indent);
}
}
void write_scalar(const node& n)
{
switch (static_cast<value_t>(n.kind))
{
case value_t::null:
m_out.put("null");
break;
case value_t::boolean:
if ((n.flags & node_flags::is_true) != 0)
{
m_out.put("true");
}
else
{
m_out.put("false");
}
break;
case value_t::string:
write_string(n);
break;
case value_t::number_integer:
case value_t::number_unsigned:
{
const char* const token = m_doc.str(n);
const std::uint32_t len = number_length(n);
if (!m_style.source_numbers && len == 2 && token[0] == '-' && token[1] == '0')
{
m_out.put('0'); // parse() reads -0 as the integer 0
}
else
{
m_out.put(token, len);
}
break;
}
case value_t::number_float:
if (m_style.source_numbers && (n.flags & node_flags::storage) != node_flags::edited)
{
m_out.put(m_doc.str(n), n.len); // (a float set by an edit is written as with shortest)
}
else
{
write_float_node(n);
}
break;
case value_t::object: // LCOV_EXCL_LINE (containers are written by dump())
case value_t::array: // LCOV_EXCL_LINE
case value_t::binary: // LCOV_EXCL_LINE (not in a document)
case value_t::discarded: // LCOV_EXCL_LINE
default: // LCOV_EXCL_LINE
break; // LCOV_EXCL_LINE
}
}
/// a float node as dump() writes it
void write_float_node(const node& n)
{
write_float_node(n, fast_double {});
}
void write_float_node(const node& n, std::false_type /*other*/)
{
write_float(float_value<number_float_t>(m_doc, n));
}
void write_float_node(const node& n, std::true_type /*double*/)
{
m_out.reserve(64);
m_out.set_cursor(write_double_at(m_out.cursor(), n));
}
/*!
@brief (doubles) the float at n as dump() writes it, at w (64 bytes of room)
A token of at most 15 significant digits is written from its digits,
without a conversion: two decimals of at most 15 digits are farther
apart than the rounding interval of a (normal) double (the argument
behind DBL_DIG), so the token's digits are the shortest ones of its
double, which the library's conversion writes (Zmij). Other tokens are
converted from the digits already read.
*/
char* write_double_at(char* w, const node& n)
{
const unsigned int_digits = n.extra & 0xFFu;
const unsigned frac_digits = n.extra >> 8u;
if ((n.flags & node_flags::storage) != node_flags::edited && int_digits + frac_digits <= 19)
{
const auto* const first = reinterpret_cast<const unsigned char*>(m_doc.src + n.off); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
const float_significand d = layout_decimal(first, first + n.len, int_digits, frac_digits, reinterpret_cast<const unsigned char*>(m_doc.src + m_doc.size)); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
// (the exponent keeps the value far from subnormals and overflow)
if (d.w != 0 && d.w < 1000000000000000u && d.exponent >= -290 && d.exponent <= 290)
{
*w = '-';
w += d.negative ? 1 : 0;
// (without leading zeros, all digits of the token count; the
// check also keeps an image that was only checked for bounds,
// whose token may not be made of digits, from the counted
// overload)
const auto& powers = ::nlohmann::detail::dtoa_impl::powers_of_ten();
const unsigned count = int_digits + frac_digits;
return count - 1u < 15u && d.w >= powers[count - 1u] && d.w < powers[count]
? ::nlohmann::detail::dtoa_impl::write_short_decimal(w, d.w, static_cast<int>(count), static_cast<int>(d.exponent))
: ::nlohmann::detail::dtoa_impl::write_short_decimal(w, d.w, static_cast<int>(d.exponent));
}
return write_double_value_at(w, decimal_to_float<double>(d)); // (without reading the token again)
}
return write_double_value_at(w, static_cast<double>(float_value<number_float_t>(m_doc, n)));
}
/// n bytes of text at w
static char* write_text_at(char* w, const char* text, std::size_t n) noexcept
{
std::memcpy(w, text, n);
return w + n;
}
/// a double as dump() writes it, at w (64 bytes of room)
static char* write_double_value_at(char* w, double x)
{
// (from the bits: without the checks of to_chars())
std::uint64_t bits = 0;
std::memcpy(&bits, &x, sizeof(bits));
if (NLOHMANN_VIEW_UNLIKELY((bits & 0x7FF0000000000000u) == 0x7FF0000000000000u))
{
return write_text_at(w, "null", 4);
}
*w = '-';
w += bits >> 63u;
bits &= ~(std::uint64_t{1} << 63u);
if (bits == 0)
{
return write_text_at(w, "0.0", 3);
}
return ::nlohmann::detail::dtoa_impl::write_shortest(w, ::nlohmann::detail::zmij::to_shortest(bits));
}
/// as serializer::dump_float()
void write_float(number_float_t x)
{
if (!std::isfinite(x))
{
m_out.put("null");
return;
}
static constexpr bool is_ieee_single_or_double
= std::numeric_limits<number_float_t>::is_iec559
&& ((std::numeric_limits<number_float_t>::digits == 24 && std::numeric_limits<number_float_t>::max_exponent == 128)
|| (std::numeric_limits<number_float_t>::digits == 53 && std::numeric_limits<number_float_t>::max_exponent == 1024));
write_float(x, std::integral_constant<bool, is_ieee_single_or_double>());
}
void write_float(number_float_t x, std::true_type /*is_ieee_single_or_double*/)
{
std::array<char, 64> buf{};
const char* const end = ::nlohmann::detail::to_chars(buf.data(), buf.data() + buf.size(), x);
m_out.put(buf.data(), static_cast<std::size_t>(end - buf.data()));
}
void write_float(number_float_t x, std::false_type /*is_ieee_single_or_double*/)
{
// other types (e.g. long double) are rare: the library writes them
const string_t s = BasicJsonType(x).dump();
m_out.put(s.data(), s.size());
}
void write_string(const node& n)
{
const char* const s = m_doc.str(n);
m_out.put('"');
if ((n.flags & node_flags::storage) == 0 && !m_style.ensure_ascii)
{
// a string of the source without escape sequences has nothing to escape
m_out.put(s, n.len);
}
else if (m_style.ensure_ascii)
{
write_escaped<true>(reinterpret_cast<const unsigned char*>(s), n.len); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
}
else
{
write_escaped<false>(reinterpret_cast<const unsigned char*>(s), n.len); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
}
m_out.put('"');
}
/// as serializer::dump_escaped(); strings of a document are valid UTF-8,
/// except in a damaged image loaded with image_check::bounds, for which
/// this throws what basic_json::dump() throws for the string
template<bool EnsureAscii>
void write_escaped(const unsigned char* s, std::size_t n)
{
std::size_t i = 0;
while (i < n)
{
std::size_t run = 0;
if (!EnsureAscii)
{
run = string_bulk_run(s + i, n - i);
}
else if (is_ascii_copyable(s[i]))
{
run = find_ascii_copyable_run(s + i, n - i);
}
if (run != 0)
{
m_out.put(reinterpret_cast<const char*>(s + i), run); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
i += run;
continue;
}
std::uint32_t codepoint = s[i];
std::size_t len = 1;
if (codepoint >= 0x80)
{
len = validate_one_utf8(s + i, n - i);
if (NLOHMANN_VIEW_UNLIKELY(len == 0))
{
invalid_utf8(s, n);
return;
}
codepoint &= 0xFFu >> (len + 1);
for (std::size_t k = 1; k < len; ++k)
{
codepoint = (codepoint << 6u) | (s[i + k] & 0x3Fu);
}
}
write_codepoint<EnsureAscii>(codepoint, s + i, len);
i += len;
}
}
/// throw what basic_json::dump() throws for a string that is not valid UTF-8
NLOHMANN_VIEW_NOINLINE static void invalid_utf8(const unsigned char* s, std::size_t n)
{
const string_t dumped = BasicJsonType(string_t(reinterpret_cast<const char*>(s), n)).dump(); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast)
static_cast<void>(dumped);
}
template<bool EnsureAscii>
void write_codepoint(std::uint32_t codepoint, const unsigned char* bytes, std::size_t len)
{
switch (codepoint)
{
case 0x08:
m_out.put("\\b");
return;
case 0x09:
m_out.put("\\t");
return;
case 0x0A:
m_out.put("\\n");
return;
case 0x0C:
m_out.put("\\f");
return;
case 0x0D:
m_out.put("\\r");
return;
case 0x22:
m_out.put("\\\"");
return;
case 0x5C:
m_out.put("\\\\");
return;
default:
break;
}
if (codepoint <= 0x1F || (EnsureAscii && codepoint >= 0x7F))
{
if (codepoint <= 0xFFFF)
{
write_u_escape(codepoint);
}
else
{
write_u_escape(0xD7C0u + (codepoint >> 10u));
write_u_escape(0xDC00u + (codepoint & 0x3FFu));
}
return;
}
m_out.put(reinterpret_cast<const char*>(bytes), len); // NOLINT(cppcoreguidelines-pro-type-reinterpret-cast) LCOV_EXCL_LINE (printable characters are copied in runs)
}
void write_u_escape(std::uint32_t u)
{
static constexpr const char* hex = "0123456789abcdef";
const std::array<char, 6> e = {{'\\', 'u', hex[(u >> 12u) & 0xFu], hex[(u >> 8u) & 0xFu], hex[(u >> 4u) & 0xFu], hex[u & 0xFu]}};
m_out.put(e.data(), e.size());
}
const document_data& m_doc;
output_buffer<string_t> m_out;
const dump_style m_style;
};
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/simd.hpp
+339
View File
@@ -0,0 +1,339 @@
// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-FileCopyrightText: 2018-2025 The simdjson authors <https://github.com/simdjson/simdjson>
// SPDX-License-Identifier: MIT
#pragma once
#include <array> // array
#include <atomic> // atomic
#include <cstddef> // size_t
#include <cstdint> // uint8_t, uint64_t
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
// Vector code for long runs of string bytes. NEON (AArch64) and SSE2 (x86-64)
// belong to the baseline instruction sets and are used by default. The vector
// UTF-8 check needs NEON or SSSE3. SSSE3 is not part of x86-64, and the code
// must not depend on the flags of a translation unit (two translation units
// with different flags would have different definitions of the same inline
// functions): the check is compiled for SSSE3 with a function attribute and
// used where the CPU has SSSE3 (all x86-64 CPUs since about 2011), else the
// portable check. JSON_VIEW_USE_SSSE3 skips the CPU check (for code compiled
// for SSSE3 anyway); JSON_VIEW_NO_SIMD selects the portable code.
// NLOHMANN_VIEW_NO_TARGET_ATTRIBUTE (set by the GCC module interface, where GCC
// ignores the target attribute and then rejects the SSSE3 intrinsics) keeps the
// check portable without disabling the SSE2 code.
#if !defined(JSON_VIEW_NO_SIMD) && defined(__aarch64__) && (defined(__GNUC__) || defined(__clang__)) && NLOHMANN_VIEW_LITTLE_ENDIAN
#include <arm_neon.h>
#define NLOHMANN_VIEW_NEON 1
#else
#define NLOHMANN_VIEW_NEON 0
#endif
// (x86 only: other targets can define __SSE2__ as well, e.g., WebAssembly with -msse2, but have no <cpuid.h>)
#if !defined(JSON_VIEW_NO_SIMD) && !NLOHMANN_VIEW_NEON && (defined(__x86_64__) || defined(__i386__) || defined(_M_X64) || defined(_M_IX86)) && (defined(__SSE2__) || defined(_M_X64) || (defined(_M_IX86_FP) && _M_IX86_FP >= 2))
#include <emmintrin.h>
#define NLOHMANN_VIEW_SSE2 1
#else
#define NLOHMANN_VIEW_SSE2 0
#endif
#if NLOHMANN_VIEW_SSE2 && defined(JSON_VIEW_USE_SSSE3)
#include <tmmintrin.h>
#define NLOHMANN_VIEW_SSSE3 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#else
#define NLOHMANN_VIEW_SSSE3 0 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#endif
#if NLOHMANN_VIEW_SSE2 && !NLOHMANN_VIEW_SSSE3 && !defined(NLOHMANN_VIEW_NO_TARGET_ATTRIBUTE) && ((defined(__clang__) && __clang_major__ >= 4) || (defined(__GNUC__) && !defined(__clang__) && (__GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 9))))
// (GCC before 4.9 has no SSSE3 intrinsics without -mssse3)
#include <cpuid.h>
#include <tmmintrin.h>
#define NLOHMANN_VIEW_SSSE3_DISPATCH 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#define NLOHMANN_VIEW_SSSE3_TARGET __attribute__((target("ssse3")))
#elif NLOHMANN_VIEW_SSE2 && !NLOHMANN_VIEW_SSSE3 && defined(_MSC_VER)
// (MSVC compiles intrinsics of any instruction set)
#include <intrin.h>
#include <tmmintrin.h>
#define NLOHMANN_VIEW_SSSE3_DISPATCH 1 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#define NLOHMANN_VIEW_SSSE3_TARGET
#else
#define NLOHMANN_VIEW_SSSE3_DISPATCH 0 // NOLINT(cppcoreguidelines-macro-to-enum,modernize-macro-to-enum)
#define NLOHMANN_VIEW_SSSE3_TARGET
#endif
#define NLOHMANN_VIEW_VECTOR (NLOHMANN_VIEW_NEON || NLOHMANN_VIEW_SSE2)
#define NLOHMANN_VIEW_VECTOR_UTF8 (NLOHMANN_VIEW_NEON || NLOHMANN_VIEW_SSSE3 || NLOHMANN_VIEW_SSSE3_DISPATCH)
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
#if NLOHMANN_VIEW_VECTOR
/*!
@brief the first byte of a string run that is a quote, a backslash, a control
character, or not ASCII, 16 bytes per step
Stops at such a byte, or where fewer than 16 bytes are left (the caller tells
the two apart). A signed compare with 0x20 finds control characters and
non-ASCII bytes at once.
*/
NLOHMANN_VIEW_ALWAYS_INLINE const unsigned char* vector_plain_run(const unsigned char* p, const unsigned char* e) noexcept
{
while (e - p >= 16)
{
#if NLOHMANN_VIEW_NEON
const uint8x16_t in = vld1q_u8(p);
const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))),
vcltq_s8(vreinterpretq_s8_u8(in), vdupq_n_s8(0x20)));
// one nibble per byte (the usual NEON replacement of x86's movemask, see
// D. Kutenin, "Porting x86 vector bitmask optimizations to Arm NEON", 2022)
const std::uint64_t bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
if (bits != 0)
{
return p + (count_trailing_zeros(bits) >> 2u);
}
#else
const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(p))); // NOLINT(bugprone-casting-through-void)
const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
_mm_cmplt_epi8(in, _mm_set1_epi8(0x20)));
const auto bits = static_cast<std::uint64_t>(static_cast<unsigned>(_mm_movemask_epi8(special)));
if (bits != 0)
{
return p + count_trailing_zeros(bits);
}
#endif
p += 16;
}
return p;
}
#endif
#if NLOHMANN_VIEW_SSSE3_DISPATCH
/// whether the CPU has SSSE3 (CPUID leaf 1, ECX bit 9)
inline bool cpu_ssse3() noexcept
{
#if defined(_MSC_VER) && !defined(__clang__)
std::array<int, 4> regs {{}};
__cpuid(regs.data(), 1);
return (static_cast<unsigned>(regs[2]) & (1u << 9u)) != 0;
#else
unsigned eax = 0;
unsigned ebx = 0;
unsigned ecx = 0;
unsigned edx = 0;
return __get_cpuid(1, &eax, &ebx, &ecx, &edx) != 0 && (ecx & (1u << 9u)) != 0;
#endif
}
/// whether the CPU has SSSE3, asked once: the answer is kept in an atomic
/// that is initialized at compile time, so that neither a guard of a local
/// static nor a global constructor is needed (threads that ask at the same
/// time all store the same answer)
NLOHMANN_VIEW_ALWAYS_INLINE bool cpu_has_ssse3() noexcept
{
static std::atomic<int> known{0}; // 0: not asked yet, 1: no, 2: yes
int state = known.load(std::memory_order_relaxed);
if (NLOHMANN_VIEW_UNLIKELY(state == 0))
{
state = cpu_ssse3() ? 2 : 1;
known.store(state, std::memory_order_relaxed);
}
return state == 2;
}
#endif
#if NLOHMANN_VIEW_VECTOR_UTF8
/// Tables of the UTF-8 check of J. Keiser and D. Lemire, "Validating UTF-8 In
/// Less Than One Instruction Per Byte" (2021), as in simdjson ("lookup4"): each
/// maps a nibble (high and low nibble of the previous byte, high nibble of the
/// current byte) to the errors it allows; a byte pair is ill-formed if all
/// three have an error bit in common.
template<typename Dummy = void>
struct utf8_lookup4
{
static constexpr std::uint8_t too_short = 1u << 0u, too_long = 1u << 1u, overlong_3 = 1u << 2u, too_large = 1u << 3u;
static constexpr std::uint8_t surrogate = 1u << 4u, overlong_2 = 1u << 5u, too_large_1000 = 1u << 6u, overlong_4 = 1u << 6u;
static constexpr std::uint8_t two_conts = 1u << 7u, carry = too_short | too_long | two_conts;
static const std::array<std::uint8_t, 16> byte_1_high;
static const std::array<std::uint8_t, 16> byte_1_low;
static const std::array<std::uint8_t, 16> byte_2_high;
};
template<typename Dummy>
const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_1_high =
{
{
too_long, too_long, too_long, too_long, too_long, too_long, too_long, too_long,
two_conts, two_conts, two_conts, two_conts,
too_short | overlong_2, too_short, too_short | overlong_3 | surrogate, too_short | too_large | too_large_1000 | overlong_4
}
};
template<typename Dummy>
const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_1_low =
{
{
carry | overlong_3 | overlong_2 | overlong_4, carry | overlong_2, carry, carry,
carry | too_large, carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000,
carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000, carry | too_large | too_large_1000,
carry | too_large | too_large_1000, carry | too_large | too_large_1000 | surrogate, carry | too_large | too_large_1000, carry | too_large | too_large_1000
}
};
template<typename Dummy>
const std::array<std::uint8_t, 16> utf8_lookup4<Dummy>::byte_2_high =
{
{
too_short, too_short, too_short, too_short, too_short, too_short, too_short, too_short,
static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | overlong_3 | too_large_1000 | overlong_4),
static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | overlong_3 | too_large),
static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | surrogate | too_large),
static_cast<std::uint8_t>(too_long | overlong_2 | two_conts | surrogate | too_large),
too_short, too_short, too_short, too_short
}
};
/// the end of scan_string_vector from block, where the vector loop stopped
/// (ill-formed UTF-8, or fewer than 16 bytes left): one byte or sequence at a
/// time, from the start of a sequence that crosses into the block
inline const unsigned char* scan_string_finish(const unsigned char* p, const unsigned char* block, const unsigned char* e, const std::uint8_t* plain) noexcept
{
for (int i = 1; i <= 3 && block - i >= p; ++i)
{
const unsigned char c = block[-i];
if (c < 0x80)
{
break;
}
if (c >= 0xC0)
{
const int len = 2 + static_cast<int>(c >= 0xE0) + static_cast<int>(c >= 0xF0);
if (len > i)
{
block -= i;
}
break;
}
}
for (p = block; p != e;)
{
if (*p < 0x80)
{
if (plain[*p] == 0)
{
return p;
}
++p;
continue;
}
const std::size_t n = validate_one_utf8(p, static_cast<std::size_t>(e - p));
if (n == 0)
{
return p;
}
p += n;
}
return p;
}
/*!
@brief the rest of a string from p (a character boundary), 16 bytes per step
The first quote, backslash, or control character is found with vector
compares, and the UTF-8 check covers the bytes up to it. Returns where the
string scan stops, like scan_string_run: before ill-formed UTF-8 and for the
last bytes of the input, the bytes are checked one sequence at a time. Out of
line, so that no constants of the check occupy registers in the parse loop.
On x86-64, it is compiled for SSSE3 (see cpu_has_ssse3()).
*/
NLOHMANN_VIEW_SSSE3_TARGET NLOHMANN_VIEW_NOINLINE inline const unsigned char* scan_string_vector(const unsigned char* p, const unsigned char* e, const std::uint8_t* plain) noexcept
{
using lookup = utf8_lookup4<>;
const unsigned char* block = p;
#if NLOHMANN_VIEW_NEON
const uint8x16_t t1h = vld1q_u8(lookup::byte_1_high.data());
const uint8x16_t t1l = vld1q_u8(lookup::byte_1_low.data());
const uint8x16_t t2h = vld1q_u8(lookup::byte_2_high.data());
uint8x16_t prev = vdupq_n_u8(0);
while (e - block >= 16)
{
const uint8x16_t in = vld1q_u8(block);
const uint8x16_t special = vorrq_u8(vorrq_u8(vceqq_u8(in, vdupq_n_u8('"')), vceqq_u8(in, vdupq_n_u8('\\'))), vcltq_u8(in, vdupq_n_u8(0x20)));
const uint8x16_t prev1 = vextq_u8(prev, in, 15);
const uint8x16_t sc = vandq_u8(vandq_u8(vqtbl1q_u8(t1h, vshrq_n_u8(prev1, 4)), vqtbl1q_u8(t1l, vandq_u8(prev1, vdupq_n_u8(0x0F)))), vqtbl1q_u8(t2h, vshrq_n_u8(in, 4)));
const uint8x16_t must23 = vorrq_u8(vqsubq_u8(vextq_u8(prev, in, 14), vdupq_n_u8(0xE0 - 0x80)), vqsubq_u8(vextq_u8(prev, in, 13), vdupq_n_u8(0xF0 - 0x80)));
const uint8x16_t err = veorq_u8(vandq_u8(must23, vdupq_n_u8(0x80)), sc);
const std::uint64_t special_bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(special), 4)), 0);
const std::uint64_t err_bits = vget_lane_u64(vreinterpret_u64_u8(vshrn_n_u16(vreinterpretq_u16_u8(vtstq_u8(err, err)), 4)), 0);
if (special_bits != 0)
{
// errors up to the special byte count (an incomplete sequence
// before a quote shows at the quote); the bytes after it do not
const unsigned k = static_cast<unsigned>(count_trailing_zeros(special_bits)) >> 2u;
const std::uint64_t upto = k == 15 ? ~std::uint64_t{0} :
(std::uint64_t{1} << (4u * (k + 1u))) - 1u;
if ((err_bits & upto) == 0)
{
return block + k;
}
break;
}
if (err_bits != 0)
{
break;
}
prev = in;
block += 16;
}
#else
// the same with SSSE3 (pshufb for the table lookups; nibbles from 16-bit
// shifts, as there are no byte shifts)
const __m128i t1h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_high.data()))); // NOLINT(bugprone-casting-through-void)
const __m128i t1l = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_1_low.data()))); // NOLINT(bugprone-casting-through-void)
const __m128i t2h = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(lookup::byte_2_high.data()))); // NOLINT(bugprone-casting-through-void)
const __m128i nibble = _mm_set1_epi8(0x0F);
const __m128i zero = _mm_setzero_si128();
__m128i prev = zero;
while (e - block >= 16)
{
const __m128i in = _mm_loadu_si128(static_cast<const __m128i*>(static_cast<const void*>(block))); // NOLINT(bugprone-casting-through-void)
const __m128i special = _mm_or_si128(_mm_or_si128(_mm_cmpeq_epi8(in, _mm_set1_epi8('"')), _mm_cmpeq_epi8(in, _mm_set1_epi8('\\'))),
_mm_cmpeq_epi8(_mm_subs_epu8(in, _mm_set1_epi8(0x1F)), zero)); // in < 0x20
const __m128i prev1 = _mm_alignr_epi8(in, prev, 15);
const __m128i sc = _mm_and_si128(_mm_and_si128(_mm_shuffle_epi8(t1h, _mm_and_si128(_mm_srli_epi16(prev1, 4), nibble)),
_mm_shuffle_epi8(t1l, _mm_and_si128(prev1, nibble))),
_mm_shuffle_epi8(t2h, _mm_and_si128(_mm_srli_epi16(in, 4), nibble)));
const __m128i must23 = _mm_or_si128(_mm_subs_epu8(_mm_alignr_epi8(in, prev, 14), _mm_set1_epi8(0xE0 - 0x80)),
_mm_subs_epu8(_mm_alignr_epi8(in, prev, 13), _mm_set1_epi8(0xF0 - 0x80)));
const __m128i err = _mm_xor_si128(_mm_and_si128(must23, _mm_set1_epi8(static_cast<char>(-128))), sc);
const auto special_bits = static_cast<unsigned>(_mm_movemask_epi8(special));
const auto err_bits = ~static_cast<unsigned>(_mm_movemask_epi8(_mm_cmpeq_epi8(err, zero))) & 0xFFFFu;
if (special_bits != 0)
{
const auto k = static_cast<unsigned>(count_trailing_zeros(static_cast<std::uint64_t>(special_bits)));
if ((err_bits & ((2u << k) - 1u)) == 0)
{
return block + k;
}
break;
}
if (err_bits != 0)
{
break;
}
prev = in;
block += 16;
}
#endif
return scan_string_finish(p, block, e, plain);
}
#endif
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/string_ref.hpp
+113
View File
@@ -0,0 +1,113 @@
// __ _____ _____ _____
// __| | __| | | | 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 <algorithm> // min
#include <cstddef> // size_t
#include <cstring> // memcmp, strlen
#include <string> // basic_string
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
#if NLOHMANN_VIEW_HAS_CPP_17
#include <string_view> // string_view
#endif
#ifndef JSON_NO_IO
#include <ostream> // ostream
#endif
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
#if NLOHMANN_VIEW_HAS_CPP_17
using string_ref = std::string_view;
#else
/// minimal C++11 stand-in for std::string_view
class string_ref
{
public:
using size_type = std::size_t;
using const_iterator = const char*;
string_ref() noexcept = default;
// s must be null-terminated, as for std::string_view(const char*)
// flawfinder: ignore
string_ref(const char* s) : m_data(s), m_size(std::strlen(s)) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
string_ref(const char* s, std::size_t n) noexcept : m_data(s), m_size(n) {}
template<typename Traits, typename Alloc>
string_ref(const std::basic_string<char, Traits, Alloc>& s) noexcept : m_data(s.data()), m_size(s.size()) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
const char* data() const noexcept
{
return m_data;
}
std::size_t size() const noexcept
{
return m_size;
}
std::size_t length() const noexcept
{
return m_size;
}
bool empty() const noexcept
{
return m_size == 0;
}
const char* begin() const noexcept
{
return m_data;
}
const char* end() const noexcept
{
return m_data + m_size;
}
char operator[](std::size_t i) const noexcept
{
return m_data[i];
}
template<typename Traits, typename Alloc>
explicit operator std::basic_string<char, Traits, Alloc>() const
{
return std::basic_string<char, Traits, Alloc>(m_data, m_size);
}
friend bool operator==(string_ref a, string_ref b) noexcept
{
return a.m_size == b.m_size && (a.m_size == 0 || std::memcmp(a.m_data, b.m_data, a.m_size) == 0);
}
friend bool operator!=(string_ref a, string_ref b) noexcept
{
return !(a == b);
}
friend bool operator<(string_ref a, string_ref b) noexcept
{
const int c = std::memcmp(a.m_data, b.m_data, (std::min)(a.m_size, b.m_size));
return c != 0 ? c < 0 : a.m_size < b.m_size;
}
#ifndef JSON_NO_IO
friend std::ostream& operator<<(std::ostream& o, string_ref s)
{
return o.write(s.m_data, static_cast<std::streamsize>(s.m_size));
}
#endif
private:
const char* m_data = "";
std::size_t m_size = 0;
};
#endif
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/detail/view/value.hpp
+144
View File
@@ -0,0 +1,144 @@
// __ _____ _____ _____
// __| | __| | | | 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> // nullptr_t, size_t
#include <cstdint> // int64_t
#include <map> // map
#include <string> // basic_string
#include <type_traits> // decay, enable_if, is_arithmetic, is_constructible, is_integral, is_same
#include <unordered_map> // unordered_map
#include <vector> // vector
#include <nlohmann/json.hpp>
#include <nlohmann/detail/view/document_data.hpp>
#include <nlohmann/detail/view/errors.hpp>
#include <nlohmann/detail/view/macro_scope.hpp>
#include <nlohmann/detail/view/node.hpp>
#include <nlohmann/detail/view/number.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
namespace detail
{
namespace view
{
/// selects a conversion by its target type
template<typename T>
struct value_tag {};
/*!
@brief the number or boolean of a node converted to an arithmetic type
As basic_json's get<T>() for arithmetic types: integers and floats are
converted with static_cast, booleans give 0 or 1, and other types throw
type_error.302.
*/
template<typename T, typename BasicJsonType>
NLOHMANN_VIEW_ALWAYS_INLINE T arithmetic_value(const document_data& d, const node& n)
{
switch (static_cast<value_t>(n.kind))
{
case value_t::number_unsigned:
return static_cast<T>(static_cast<typename BasicJsonType::number_unsigned_t>(integer_bits(n)));
case value_t::number_integer:
return static_cast<T>(static_cast<typename BasicJsonType::number_integer_t>(static_cast<std::int64_t>(integer_bits(n))));
case value_t::number_float:
return static_cast<T>(float_value<typename BasicJsonType::number_float_t>(d, n));
case value_t::boolean:
return static_cast<T>((n.flags & node_flags::is_true) != 0);
case value_t::null:
case value_t::object:
case value_t::array:
case value_t::string:
case value_t::binary:
case value_t::discarded:
default:
throw_type_error(302, "type must be number, but is ", value_type_name(static_cast<value_t>(n.kind)));
}
}
/// std::vector from an array, element by element (type_error.302 otherwise)
template<typename View, typename U, typename A>
std::vector<U, A> vector_value(const View& v)
{
if (NLOHMANN_VIEW_UNLIKELY(!v.is_array()))
{
throw_type_error(302, "type must be array, but is ", v.type_name());
}
std::vector<U, A> r;
r.reserve(v.size());
for (const View e : v)
{
r.push_back(e.template get<U>());
}
return r;
}
/// a map with string keys from an object; with duplicate keys, the last
/// value is kept, as parse() does (type_error.302 for other types)
template<typename Map, typename View>
Map map_value(const View& v)
{
if (NLOHMANN_VIEW_UNLIKELY(!v.is_object()))
{
throw_type_error(302, "type must be object, but is ", v.type_name());
}
Map r;
for (auto it = v.begin(); it != v.end(); ++it)
{
const auto key = it.key();
r[typename Map::key_type(key.data(), key.size())] = it.value().template get<typename Map::mapped_type>();
}
return r;
}
/// whether a map type is read member by member (its keys are made from
/// characters and a length); other maps go through basic_json
template<typename Key>
struct is_string_key : std::is_constructible<Key, const char*, std::size_t> {};
/// the arithmetic types arithmetic_value() converts to (bool has its own
/// conversion)
template<typename T>
struct is_non_bool_arithmetic : conjunction<std::is_arithmetic<T>, negation<std::is_same<T, bool>>> {};
/// the default values of value() other than C strings, which have their own
/// overload (returning string_t)
template<typename T>
struct is_non_c_string_default : negation<std::is_same<typename std::decay<T>::type, const char*>> {};
/// the integral types accepted as an array index by the edits of a document
template<typename T>
struct is_non_bool_integral : conjunction<std::is_integral<T>, negation<std::is_same<T, bool>>> {};
/// whether View::get<T>() converts to T without materialize(); get_to()
/// assigns these, and passes the others to from_json
template<typename T, typename BasicJsonType, typename View>
struct is_direct_value : std::integral_constant < bool,
std::is_arithmetic<T>::value || std::is_same<T, std::nullptr_t>::value
|| std::is_same<T, typename View::string_view_t>::value
|| std::is_same<T, BasicJsonType>::value || std::is_same<T, View>::value >
{};
template<typename Traits, typename Alloc, typename BasicJsonType, typename View>
struct is_direct_value<std::basic_string<char, Traits, Alloc>, BasicJsonType, View> : std::true_type {};
template<typename U, typename A, typename BasicJsonType, typename View>
struct is_direct_value<std::vector<U, A>, BasicJsonType, View> : std::true_type {};
template<typename K, typename V, typename C, typename A, typename BasicJsonType, typename View>
struct is_direct_value<std::map<K, V, C, A>, BasicJsonType, View> : is_string_key<K> {};
template<typename K, typename V, typename H, typename E, typename A, typename BasicJsonType, typename View>
struct is_direct_value<std::unordered_map<K, V, H, E, A>, BasicJsonType, View> : is_string_key<K> {};
} // namespace view
} // namespace detail
NLOHMANN_JSON_NAMESPACE_END
include/nlohmann/json.hpp
+995 -424
View File
File diff suppressed because it is too large. Load diff
include/nlohmann/json_view.hpp
+1608
View File
File diff suppressed because it is too large. Load diff
include/nlohmann/ordered_map.hpp
+46 -24
View File
@@ -23,6 +23,7 @@
#include <nlohmann/detail/abi_macros.hpp>
#include <nlohmann/detail/macro_scope.hpp>
#include <nlohmann/detail/meta/type_traits.hpp>
#include <nlohmann/thirdparty/hedley/hedley.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -90,6 +91,28 @@ private:
return self.end();
}
/// @brief throw the exception of a failed at() lookup
/// @note kept out of line so that at_impl() stays small enough to inline
/// @throw std::out_of_range always
JSON_HEDLEY_NO_RETURN JSON_HEDLEY_NEVER_INLINE
static void throw_key_not_found()
{
JSON_THROW(std::out_of_range("key not found"));
}
/// @brief shared implementation of the const and non-const at() overloads
/// @throw std::out_of_range if @a key is not found
template<typename Self, typename KeyType>
static auto at_impl(Self& self, const KeyType& key) -> decltype((self.begin()->second))
{
const auto it = find_impl(self, key);
if (it == self.end())
{
throw_key_not_found();
}
return it->second;
}
/// @brief remove the entry @a it points to, preserving order
/// @note keys are not movable, so the tail is destroyed and re-constructed in place
void erase_at(iterator it)
@@ -130,6 +153,17 @@ public:
return {std::prev(this->end()), true};
}
/// @brief add an element at the end without checking whether the key exists
/// @note The caller must guarantee that @a key is not yet contained, otherwise
/// the container holds duplicate keys. This avoids the linear search of
/// emplace() and operator[] when many keys known to be new are added.
template<class V, detail::enable_if_t<
detail::is_constructible<T, V>::value, int> = 0>
void emplace_new_key(const key_type& key, V && t)
{
append(key, std::forward<V>(t));
}
T& operator[](const key_type& key)
{
return emplace(key, T{}).first->second;
@@ -156,46 +190,26 @@ public:
T& at(const key_type& key)
{
const auto it = find_impl(*this, key);
if (it == this->end())
{
JSON_THROW(std::out_of_range("key not found"));
}
return it->second;
return at_impl(*this, key);
}
template<class KeyType, detail::enable_if_t<
detail::is_usable_as_key_type<key_compare, key_type, KeyType>::value, int> = 0>
T & at(KeyType && key) // NOLINT(cppcoreguidelines-missing-std-forward)
{
const auto it = find_impl(*this, key);
if (it == this->end())
{
JSON_THROW(std::out_of_range("key not found"));
}
return it->second;
return at_impl(*this, key);
}
const T& at(const key_type& key) const
{
const auto it = find_impl(*this, key);
if (it == this->end())
{
JSON_THROW(std::out_of_range("key not found"));
}
return it->second;
return at_impl(*this, key);
}
template<class KeyType, detail::enable_if_t<
detail::is_usable_as_key_type<key_compare, key_type, KeyType>::value, int> = 0>
const T & at(KeyType && key) const // NOLINT(cppcoreguidelines-missing-std-forward)
{
const auto it = find_impl(*this, key);
if (it == this->end())
{
JSON_THROW(std::out_of_range("key not found"));
}
return it->second;
return at_impl(*this, key);
}
size_type erase(const key_type& key)
@@ -247,6 +261,14 @@ public:
// ^ ^
// first last
// Note on conformance: before C++20, [basic.life]/8 did not allow an
// object of a type with a const member (like value_type's const Key)
// to transparently replace the destroyed one, so strictly, accessing
// it through the vector's existing pointers would have required
// std::launder (which does not exist before C++17). C++20 dropped that
// condition (P1971R0, NB comment US 041). Compilers have always treated
// this pattern as intended, so it is kept deliberately.
// Since we cannot move const Keys, we re-construct them in place.
// We start at first and re-construct (viz. copy) the elements from
// the back of the vector. Example for the first iteration: