json/include/nlohmann/detail/view/node.hpp

//     __ _____ _____ _____
//  __|  |   __|     |   | |  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);
}

/// whether n bytes are equal; the short texts of JSON (keys, numbers, most
/// strings) are compared by two overlapping loads instead of a library call
NLOHMANN_VIEW_ALWAYS_INLINE bool bytes_equal(const char* x, const char* y, std::size_t n) noexcept
{
    const auto load8 = [](const char* p)
    {
        std::uint64_t v = 0;
        std::memcpy(&v, p, sizeof(v));
        return v;
    };
    const auto load4 = [](const char* p)
    {
        std::uint32_t v = 0;
        std::memcpy(&v, p, sizeof(v));
        return v;
    };
    if (n >= 8)
    {
        std::size_t i = 0;
        for (; i + 8 < n; i += 8)
        {
            if (load8(x + i) != load8(y + i))
            {
                return false;
            }
        }
        return load8(x + n - 8) == load8(y + n - 8);
    }
    if (n >= 4)
    {
        return load4(x) == load4(y) && load4(x + n - 4) == load4(y + n - 4);
    }
    for (std::size_t i = 0; i < n; ++i)
    {
        if (x[i] != y[i])
        {
            return false;
        }
    }
    return true;
}

/// whether the n1 bytes at x are before the n2 bytes at y (memcmp() order, then the shorter first);
/// the first difference is found eight bytes at a time
NLOHMANN_VIEW_ALWAYS_INLINE bool bytes_less(const char* x, std::size_t n1, const char* y, std::size_t n2) noexcept
{
    const std::size_t n = n1 < n2 ? n1 : n2;
    std::size_t i = 0;
    for (; i + 8 <= n; i += 8)
    {
        const std::uint64_t u = read_eight_bytes(x + i);
        const std::uint64_t v = read_eight_bytes(y + i);
        if (u != v)
        {
            const auto shift = static_cast<unsigned>(count_trailing_zeros(u ^ v)) & ~7u; // (the first byte that differs)
            return ((u >> shift) & 0xFFu) < ((v >> shift) & 0xFFu);
        }
    }
    for (; i < n; ++i)
    {
        if (x[i] != y[i])
        {
            return static_cast<unsigned char>(x[i]) < static_cast<unsigned char>(y[i]);
        }
    }
    return n1 < n2;
}

/// 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