wt/json
1
0 Fork 0
mirror of https://github.com/nlohmann/json.git synced 2026-11-11 16:40:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/develop' into HEAD

Browse Source
This commit is contained in:
Niels Lohmann committed 2026-09-14 21:26:29 +02:00
2 parents a27065bd12 3bfe2b6da7
commit 08d18d5a82
125 files changed
+13540 -4413
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

include/nlohmann/detail/input/json_sax.hpp
+162 -17
View File
@@ -8,6 +8,7 @@
#pragma once
#include <algorithm> // min
#include <cstddef>
#include <string> // string
#include <type_traits> // enable_if_t
@@ -17,6 +18,7 @@
#include <nlohmann/detail/exceptions.hpp>
#include <nlohmann/detail/input/lexer.hpp>
#include <nlohmann/detail/macro_scope.hpp>
#include <nlohmann/detail/meta/cpp_future.hpp>
#include <nlohmann/detail/string_concat.hpp>
NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -174,6 +176,29 @@ constexpr std::size_t unknown_size()
return (std::numeric_limits<std::size_t>::max)();
}
/*!
@brief reserve capacity for @a len elements in array @a arr
Reserving upfront avoids repeated reallocations while the elements are added,
but the reservation is capped so a bogus/hostile length (which is not bounded
by max_size(), unlike e.g. std::vector) cannot trigger an oversized allocation
for a small or truncated input.
The overload below is selected for array types without reserve() (e.g.,
std::deque), which are then left untouched.
*/
template<typename ArrayType>
auto reserve_array(ArrayType& arr, std::size_t len, priority_tag<1> /*unused*/)
-> decltype(arr.reserve(len), void())
{
constexpr std::size_t reserve_cap = 16384;
arr.reserve((std::min)(len, reserve_cap));
}
template<typename ArrayType>
inline void reserve_array(ArrayType& /*arr*/, std::size_t /*len*/, priority_tag<0> /*unused*/)
{}
/*!
@brief SAX implementation to create a JSON value from SAX events
@@ -246,12 +271,16 @@ class json_sax_dom_parser
bool string(string_t& val)
{
handle_value(val);
// json_sax documents that the passed value may be moved from,
// so hand the buffer over instead of copying it
handle_value(std::move(val));
return true;
}
bool binary(binary_t& val)
{
// json_sax documents that the passed value may be moved from,
// so hand the buffer over instead of copying it
handle_value(std::move(val));
return true;
}
@@ -325,6 +354,11 @@ class json_sax_dom_parser
JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
}
if (len != detail::unknown_size())
{
reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
}
return true;
}
@@ -394,8 +428,10 @@ class json_sax_dom_parser
case value_t::string:
{
// include the length of the quotes, which is 2
v.start_position = v.end_position - v.m_data.m_value.string->size() - 2;
// escape sequences make the token longer than the value it
// parses to, so the start position cannot be derived from
// the value; use the offset the lexer recorded instead
v.start_position = m_lexer_ref->get_token_start_position();
break;
}
@@ -554,12 +590,16 @@ class json_sax_dom_callback_parser
bool string(string_t& val)
{
handle_value(val);
// json_sax documents that the passed value may be moved from,
// so hand the buffer over instead of copying it
handle_value(std::move(val));
return true;
}
bool binary(binary_t& val)
{
// json_sax documents that the passed value may be moved from,
// so hand the buffer over instead of copying it
handle_value(std::move(val));
return true;
}
@@ -570,6 +610,11 @@ class json_sax_dom_callback_parser
const bool keep = callback(static_cast<int>(ref_stack.size()), parse_event_t::object_start, discarded);
keep_stack.push_back(keep);
// the key this object will be stored under, read before handle_value()
// may consume it; kept in lockstep with ref_stack so end_object() can
// find the object in its parent again
container_key_stack.push_back(current_key());
auto val = handle_value(BasicJsonType::value_t::object, true);
ref_stack.push_back(val.second);
@@ -603,6 +648,9 @@ class json_sax_dom_callback_parser
// check callback for the key
const bool keep = callback(static_cast<int>(ref_stack.size()), parse_event_t::key, k);
key_keep_stack.push_back(keep);
// remember the key so a rejected value can be erased without searching
// the object for it (kept in lockstep with key_keep_stack)
key_stack.push_back(val);
// add discarded value at the given key and store the reference for later
if (keep && ref_stack.back())
@@ -644,20 +692,16 @@ 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();
if (!ref_stack.empty() && ref_stack.back() && ref_stack.back()->is_structured())
{
// remove discarded value
for (auto it = ref_stack.back()->begin(); it != ref_stack.back()->end(); ++it)
{
if (it->is_discarded())
{
ref_stack.back()->erase(it);
break;
}
}
remove_discarded_value(*ref_stack.back(), object_key);
}
return true;
@@ -668,6 +712,9 @@ class json_sax_dom_callback_parser
const bool keep = callback(static_cast<int>(ref_stack.size()), parse_event_t::array_start, discarded);
keep_stack.push_back(keep);
// see start_object()
container_key_stack.push_back(current_key());
auto val = handle_value(BasicJsonType::value_t::array, true);
ref_stack.push_back(val.second);
@@ -690,6 +737,11 @@ class json_sax_dom_callback_parser
{
JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
}
if (len != detail::unknown_size())
{
reserve_array(*ref_stack.back()->m_data.m_value.array, len, priority_tag<1> {});
}
}
return true;
@@ -698,8 +750,9 @@ class json_sax_dom_callback_parser
bool end_array()
{
bool keep = true;
const bool stored = ref_stack.back() != nullptr;
if (ref_stack.back())
if (stored)
{
keep = callback(static_cast<int>(ref_stack.size()) - 1, parse_event_t::array_end, *ref_stack.back());
if (keep)
@@ -729,13 +782,26 @@ 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();
// remove discarded value
if (!keep && !ref_stack.empty() && ref_stack.back()->is_array())
if (!ref_stack.empty() && ref_stack.back())
{
ref_stack.back()->m_data.m_value.array->pop_back();
if (!keep && ref_stack.back()->is_array())
{
ref_stack.back()->m_data.m_value.array->pop_back();
}
else if ((!keep || !stored) && ref_stack.back()->is_object())
{
// the array is either still stored under its key or was never
// stored, leaving the placeholder key() wrote; both show up as
// a discarded member of the parent object
remove_discarded_value(*ref_stack.back(), object_key);
}
}
return true;
@@ -789,8 +855,10 @@ class json_sax_dom_callback_parser
case value_t::string:
{
// include the length of the quotes, which is 2
v.start_position = v.end_position - v.m_data.m_value.string->size() - 2;
// escape sequences make the token longer than the value it
// parses to, so the start position cannot be derived from
// the value; use the offset the lexer recorded instead
v.start_position = m_lexer_ref->get_token_start_position();
break;
}
@@ -825,6 +893,60 @@ class json_sax_dom_callback_parser
}
#endif
/*!
@brief the key the value now being handled will be stored under
Empty unless the enclosing container is an object, in which case it is the
key of the pending key() event. Read before handle_value() consumes that
key, so it is also correct when the value never reaches its parent.
*/
string_t current_key() const
{
if (!ref_stack.empty() && ref_stack.back() && ref_stack.back()->is_object()
&& !key_stack.empty())
{
return key_stack.back();
}
return string_t{};
}
/*!
@brief remove the discarded value the callback rejected from its parent
A rejected value can only ever be the one most recently added to @a parent:
the last element of an array, or the placeholder key() stored under @a key
in an object. Looking there directly makes this O(1) resp. O(log n), where
searching @a parent for it made a filtering parse quadratic in the number of
members of a single container.
Finding no discarded value there means none was stored in the first place -
the callback rejected the value before it reached its parent - so there is
nothing to remove.
@param[in,out] parent the container to remove the rejected value from
@param[in] key the key the value was stored under; unused for arrays
*/
static void remove_discarded_value(BasicJsonType& parent, const string_t& key)
{
if (parent.is_array())
{
auto& array = *parent.m_data.m_value.array;
if (!array.empty() && array.back().is_discarded())
{
array.pop_back();
}
}
else if (parent.is_object())
{
auto& object = *parent.m_data.m_value.object;
const auto it = object.find(key);
if (it != object.end() && it->second.is_discarded())
{
object.erase(it);
}
}
}
/*!
@param[in] v value to add to the JSON value we build during parsing
@param[in] skip_callback whether we should skip calling the callback
@@ -865,6 +987,21 @@ class json_sax_dom_callback_parser
// do not handle this value if we just learnt it shall be discarded
if (!keep)
{
// if the value was to become an object member, key() already
// stored a placeholder for it that has to be removed again
if (!ref_stack.empty() && ref_stack.back() && ref_stack.back()->is_object())
{
JSON_ASSERT(!key_keep_stack.empty());
JSON_ASSERT(!key_stack.empty());
const bool placeholder_stored = key_keep_stack.back();
key_keep_stack.pop_back();
const string_t key = std::move(key_stack.back());
key_stack.pop_back();
if (placeholder_stored)
{
remove_discarded_value(*ref_stack.back(), key);
}
}
return {false, nullptr};
}
@@ -895,8 +1032,10 @@ class json_sax_dom_callback_parser
JSON_ASSERT(ref_stack.back()->is_object());
// check if we should store an element for the current key
JSON_ASSERT(!key_keep_stack.empty());
JSON_ASSERT(!key_stack.empty());
const bool store_element = key_keep_stack.back();
key_keep_stack.pop_back();
key_stack.pop_back();
if (!store_element)
{
@@ -916,6 +1055,12 @@ class json_sax_dom_callback_parser
std::vector<bool> keep_stack {}; // NOLINT(readability-redundant-member-init)
/// stack to manage which object keys to keep
std::vector<bool> key_keep_stack {}; // NOLINT(readability-redundant-member-init)
/// the keys key() stored a placeholder for, in lockstep with key_keep_stack
std::vector<string_t> key_stack {}; // NOLINT(readability-redundant-member-init)
/// for each open container, the key it is stored under in its parent
/// object, in lockstep with ref_stack; unused where the parent is not an
/// object
std::vector<string_t> container_key_stack {}; // NOLINT(readability-redundant-member-init)
/// helper to hold the reference for the next object element
BasicJsonType* object_element = nullptr;
/// whether a syntax error occurred