Files
json/include/nlohmann/detail/view/lookup.hpp
T
Niels Lohmann c8b380769c Index arrays without subtrees directly
operator[](idx), at(idx) and back() skipped the elements of an array one
after the other, whatever they were. In an array none of whose elements is
an array or object (numbers, strings, booleans, null) the elements are
adjacent nodes, which the array node's own sizes tell: its subtree has
exactly one node more than it has elements. Such an element is now the
node idx after the array node; any other array is walked as before.

Reading r[i] for every i of an array of 3000 integers:
  Apple M1: 28.8 M instructions, 3.1 ms -> 0.1 M instructions, 4 us
  Linux x86-64 Ir (whole run), GCC 13 / Clang 18: 84.1 M -> 3.1 M / 75.0 M -> 3.0 M
Arrays that contain arrays are unchanged.

Belongs to the PR "json_view: read-side speedups".

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-10-22 09:30:12 +02:00

202 lines
6.9 KiB
C++

// __ _____ _____ _____
// __| | __| | | | JSON for Modern C++
// | | |__ | | | | | | version 3.12.0
// |_____|_____|_____|_|___| https://github.com/nlohmann/json
//
// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
// SPDX-License-Identifier: MIT
#pragma once
#include <cstddef> // size_t
#include <cstdint> // 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
}
if (array->next == array->len + 1u && (!nav::editable() || (array->flags & node_flags::moved) == 0))
{
return e + idx; // no element has a subtree: the elements are the nodes after the array
}
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);
if (value_offset == 0 && container->next == container->len + 1u && (!navigation<Editable>::editable() || (container->flags & node_flags::moved) == 0))
{
return last + (container->len - 1u); // an array without subtrees: the elements are the nodes after it
}
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