Compare commits

..
Author SHA1 Message Date
Niels Lohmann 68c698194b Avoid temporary-string concatenation flagged by clang-tidy in the differential test
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-06 11:11:16 +02:00
Niels Lohmann ef97a360c8 Document why the digit-count fast path is safe regardless of number_unsigned_t/number_integer_t width
Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-05 21:36:16 +02:00
Niels Lohmann 7b648c7dc4 Skip integer conversion in accept()/SAX validation when the value is unused
lexer::scan_number() always converted every numeric token with
strtoull()/strtoll() before returning, even though accept() (and any
consumer using json_sax_acceptor) immediately discards the converted
value. For value_unsigned/value_integer tokens whose digit count
already guarantees the value fits into 64 bits, the conversion cannot
change the accept/reject decision (such tokens are always finite and
unconditionally accepted), so scan_number() can skip strtoull()/
strtoll() entirely in that case when the caller signals it does not
need the value. Numbers with more digits keep using the exact,
unmodified conversion path, so overflow reclassification to
value_float (and the finiteness check on it) is unaffected.

parse() and value_float handling are completely unchanged.

Fixes #5411

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-05 20:59:51 +02:00
9 changed files with 286 additions and 625 deletions
+13 -92
View File
@@ -8,11 +8,10 @@
#pragma once
#include <algorithm> // find_if
#include <cstddef>
#include <string> // string
#include <type_traits> // enable_if_t
#include <utility> // move, pair
#include <utility> // move
#include <vector> // vector
#include <nlohmann/detail/exceptions.hpp>
@@ -586,17 +585,7 @@ class json_sax_dom_callback_parser
// add discarded value at the given key and store the reference for later
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())
{
// 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);
}
object_element = &(obj[val] = discarded);
object_element = &(ref_stack.back()->m_data.m_value.object->operator[](val) = discarded);
}
return true;
@@ -608,18 +597,13 @@ class json_sax_dom_callback_parser
{
if (!callback(static_cast<int>(ref_stack.size()) - 1, parse_event_t::object_end, *ref_stack.back()))
{
// discard object, unless this slot holds a duplicate key's
// previous value pending restoration, in which case that
// value is restored instead of being discarded
if (!resolve_duplicate_key_stash(ref_stack.back(), true))
{
*ref_stack.back() = discarded;
// discard object
*ref_stack.back() = discarded;
#if JSON_DIAGNOSTIC_POSITIONS
// Set start/end positions for discarded object.
handle_diagnostic_positions_for_json_value(*ref_stack.back());
// Set start/end positions for discarded object.
handle_diagnostic_positions_for_json_value(*ref_stack.back());
#endif
}
}
else
{
@@ -633,10 +617,6 @@ class json_sax_dom_callback_parser
#endif
ref_stack.back()->set_parents();
// this object is finally, definitively kept; drop any
// pending duplicate-key stash entry for its slot since it
// can no longer be restored
resolve_duplicate_key_stash(ref_stack.back(), false);
}
}
@@ -706,25 +686,16 @@ class json_sax_dom_callback_parser
#endif
ref_stack.back()->set_parents();
// this array is finally, definitively kept; drop any
// pending duplicate-key stash entry for its slot since it
// can no longer be restored
resolve_duplicate_key_stash(ref_stack.back(), false);
}
else
{
// discard array, unless this slot holds a duplicate key's
// previous value pending restoration, in which case that
// value is restored instead of being discarded
if (!resolve_duplicate_key_stash(ref_stack.back(), true))
{
*ref_stack.back() = discarded;
// discard array
*ref_stack.back() = discarded;
#if JSON_DIAGNOSTIC_POSITIONS
// Set start/end positions for discarded array.
handle_diagnostic_positions_for_json_value(*ref_stack.back());
// Set start/end positions for discarded array.
handle_diagnostic_positions_for_json_value(*ref_stack.back());
#endif
}
}
}
@@ -838,48 +809,14 @@ class json_sax_dom_callback_parser
}
#endif
/// if there is a pending duplicate-key stash entry for this exact slot,
/// remove it from the stash; if restore_value is true, the stashed
/// previous value is moved back into the slot first (use this when the
/// new value at that slot was rejected); otherwise the stash entry is
/// simply dropped (use this when the new value was accepted, so it
/// correctly supersedes the old one and no restore should ever happen
/// for this slot again)
/// @return whether a matching stash entry was found (and processed)
bool resolve_duplicate_key_stash(BasicJsonType* slot, bool restore_value)
{
const auto it = std::find_if(duplicate_key_stash.begin(), duplicate_key_stash.end(),
[slot](const std::pair<BasicJsonType*, BasicJsonType>& entry)
{
return entry.first == slot;
});
if (it == duplicate_key_stash.end())
{
return false;
}
if (restore_value)
{
*slot = std::move(it->second);
}
duplicate_key_stash.erase(it);
return true;
}
/// remove the discarded value the callback rejected from its parent,
/// unless it is a duplicate key's slot with a stashed previous value,
/// in which case that previous value is restored instead
void remove_discarded_value(BasicJsonType& parent)
/// remove the discarded value the callback rejected from its parent
static void remove_discarded_value(BasicJsonType& parent)
{
for (auto it = parent.begin(); it != parent.end(); ++it)
{
if (it->is_discarded())
{
if (!resolve_duplicate_key_stash(&(*it), true))
{
parent.erase(it);
}
parent.erase(it);
break;
}
}
@@ -977,16 +914,6 @@ class json_sax_dom_callback_parser
JSON_ASSERT(object_element);
*object_element = std::move(value);
if (!skip_callback)
{
// this scalar value finally, definitively replaces whatever was
// at this slot; drop any pending duplicate-key stash entry for
// it since it can no longer be restored (a container value at
// this slot is resolved later, in end_object()/end_array(),
// since skip_callback is true for the placeholder handling that
// happens here for those)
resolve_duplicate_key_stash(object_element, false);
}
return {true, object_element};
}
@@ -1000,12 +927,6 @@ class json_sax_dom_callback_parser
std::vector<bool> key_keep_stack {}; // NOLINT(readability-redundant-member-init)
/// helper to hold the reference for the next object element
BasicJsonType* object_element = nullptr;
/// stash of (slot pointer, previous value) for object members that
/// already existed when key() was called again for the same key
/// (duplicate keys); used to restore the previous value if the new
/// value is later rejected by the callback, instead of erasing the
/// member entirely
std::vector<std::pair<BasicJsonType*, BasicJsonType>> duplicate_key_stash {};
/// whether a syntax error occurred
bool errored = false;
/// callback function
+61 -1
View File
@@ -149,10 +149,11 @@ class lexer : public lexer_base<BasicJsonType>
public:
using token_type = typename lexer_base<BasicJsonType>::token_type;
explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false) noexcept
explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
: ia(std::move(adapter))
, ignore_comments(ignore_comments_)
, decimal_point_char(static_cast<char_int_type>(get_decimal_point()))
, discard_number_values(discard_number_values_)
{}
// deleted because of pointer members
@@ -1279,6 +1280,58 @@ scan_number_done:
// we are done scanning a number)
unget();
// If the caller does not need the converted value (only whether the
// input is syntactically valid; see json_sax_acceptor/accept()), an
// unsigned/integer token can be reported without calling
// strtoull()/strtoll() at all, *provided* we can already tell from
// the digit count alone that the conversion cannot overflow 64 bits.
// Such tokens are always finite and are accepted unconditionally by
// the parser regardless of their actual value (parser::sax_parse_internal()
// never checks finiteness for value_unsigned/value_integer), so the
// classification below is all that is needed.
//
// A decimal number with up to 18 digits is always representable in
// both std::uint64_t and std::int64_t (18 nines is ~1e18, well below
// both UINT64_MAX ~1.8e19 and INT64_MAX ~9.2e18), so strtoull()/strtoll()
// could not have set errno to ERANGE for it. Numbers with more digits
// (rare in practice) fall through to the exact code below, unchanged,
// so their handling -- including reclassification to value_float when
// the value overflows 64 bits, and rejection when it is not even
// finite as a double -- is bit-for-bit identical to before this
// optimization.
//
// Note this reasons about std::uint64_t/std::int64_t, not about
// number_unsigned_t/number_integer_t (BasicJsonType's own, possibly
// narrower, template parameters -- e.g. std::uint32_t). That is fine
// *only* because discard_number_values is exclusively set by
// accept() (see json.hpp), and accept() always parses through the
// library's own json_sax_acceptor -- never a user-supplied SAX
// consumer -- whose number_unsigned()/number_integer()/number_float()
// callbacks unconditionally discard their argument and return true.
// So for every caller that can reach this branch, neither the token
// classification below nor the eventual (possibly narrowed, and on
// this fast path left stale/unset) value_unsigned/value_integer is
// ever consulted -- an unsigned/integer token is accepted outright,
// and even a >18-digit token that this fast path deliberately falls
// through for is, once reclassified to value_float, still finite
// (and thus accepted) for any digit count that fits in number_unsigned_t
// or number_integer_t regardless of that type's width. If this
// function is ever taught to run with discard_number_values true for
// a caller that *does* read the converted value, this reasoning (and
// the fast path below) would need to be revisited.
if (discard_number_values)
{
constexpr std::size_t safe_digit_count = 18;
if (number_type == token_type::value_unsigned && token_buffer.size() <= safe_digit_count)
{
return token_type::value_unsigned;
}
if (number_type == token_type::value_integer && token_buffer.size() - 1 <= safe_digit_count)
{
return token_type::value_integer;
}
}
char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
errno = 0;
@@ -1754,6 +1807,13 @@ scan_number_done:
const char_int_type decimal_point_char = '.';
/// the position of the decimal point in the input
std::size_t decimal_point_position = std::string::npos;
/// whether the caller (e.g. accept()/json_sax_acceptor) only needs the
/// token classification and never looks at the converted numeric value;
/// when set, scan_number() may skip strtoull()/strtoll() for
/// value_unsigned/value_integer tokens whose digit count guarantees they
/// fit into 64 bits (see scan_number())
const bool discard_number_values = false;
};
} // namespace detail
+3 -2
View File
@@ -72,9 +72,10 @@ class parser
parser_callback_t<BasicJsonType> cb = nullptr,
const bool allow_exceptions_ = true,
const bool ignore_comments = false,
const bool ignore_trailing_commas_ = false)
const bool ignore_trailing_commas_ = false,
const bool discard_number_values_ = false)
: callback(std::move(cb))
, m_lexer(std::move(adapter), ignore_comments)
, m_lexer(std::move(adapter), ignore_comments, discard_number_values_)
, allow_exceptions(allow_exceptions_)
, ignore_trailing_commas(ignore_trailing_commas_)
{
+20 -126
View File
@@ -164,11 +164,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
detail::parser_callback_t<basic_json>cb = nullptr,
const bool allow_exceptions = true,
const bool ignore_comments = false,
const bool ignore_trailing_commas = false
const bool ignore_trailing_commas = false,
const bool discard_number_values = false
)
{
return ::nlohmann::detail::parser<basic_json, InputAdapterType>(std::move(adapter),
std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas);
std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas, discard_number_values);
}
private:
@@ -3573,7 +3574,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
{
using std::swap;
swap(*(m_data.m_value.array), other);
set_parents();
}
else
{
@@ -3590,7 +3590,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
{
using std::swap;
swap(*(m_data.m_value.object), other);
set_parents();
}
else
{
@@ -4135,7 +4134,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = false,
const bool ignore_trailing_commas = false)
{
return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
}
/// @brief check if the input is valid JSON (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4146,7 +4145,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = false,
const bool ignore_trailing_commas = false)
{
return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
}
JSON_HEDLEY_WARN_UNUSED_RESULT
@@ -4155,7 +4154,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = false,
const bool ignore_trailing_commas = false)
{
return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
}
/// @brief generate SAX events
@@ -5159,139 +5158,34 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
case value_t::object:
{
// first pass: record, for every source key, whether it is
// common to both objects (in source's iteration order) or
// was deleted (i.e., in source but not in target) -- this is
// a by-product of the target.find() call already needed to
// tell the two cases apart, so it adds no extra lookups. The
// "remove" ops themselves are emitted later, interleaved
// with the recursive per-key diffs in the fast path below,
// to match source's original iteration order (as the
// original, pre-reordering-aware implementation did) instead
// of grouping all removes before all recursive diffs.
std::vector<typename object_t::key_type> common_keys_source_order;
// first pass: traverse this object's elements
for (auto it = source.cbegin(); it != source.cend(); ++it)
{
// escape the key name to be used in a JSON patch
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
if (target.find(it.key()) != target.end())
{
common_keys_source_order.push_back(it.key());
}
}
// second pass: find keys that were added (i.e., in target but
// not in source), and record the keys common to both, in
// target's iteration order -- again a by-product of the
// source.find() call already needed to detect added keys. At
// the same time, determine whether every added key comes
// after every common key in target's order (a precondition
// for the fast path below, which only ever appends new keys
// at the very end): for an object_t whose iteration order is
// a pure function of the key set (e.g. the default std::map,
// which always iterates in sorted key order), the order
// check further below is always true and this whole
// mechanism is effectively a no-op; it only matters for a
// reorderable object_t such as the one backing `ordered_json`.
// patch ops for keys that were added (i.e., in target but not
// in source); built here so the fast path below can reuse
// them without a second source.find() per target key. Only
// used by the fast path -- the slow (reordering) path
// rebuilds "add" ops for every key itself.
std::vector<typename object_t::key_type> common_keys_target_order;
basic_json added_ops(value_t::array);
bool new_keys_form_suffix = true;
bool seen_new_key = false;
for (auto it = target.cbegin(); it != target.cend(); ++it)
{
if (source.find(it.key()) == source.end())
{
seen_new_key = true;
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
added_ops.push_back(
{
{"op", "add"}, {"path", path_key},
{"value", it.value()}
});
// recursive call to compare object values at key it
auto temp_diff = diff(it.value(), target[it.key()], path_key);
result.insert(result.end(), temp_diff.begin(), temp_diff.end());
}
else
{
common_keys_target_order.push_back(it.key());
if (seen_new_key)
{
new_keys_form_suffix = false;
}
}
}
if (common_keys_source_order == common_keys_target_order && new_keys_form_suffix)
{
// fast path: order of common keys already matches (or the
// object_t's iteration order does not depend on
// insertion history), so a plain per-key recursive diff
// is correct and minimal, as before. common_keys_source_order
// is, by construction, the subsequence of source's keys
// that are common to both objects, in source's iteration
// order -- so it can be walked in lockstep with `source`
// using a cheap key comparison instead of another lookup.
// Deleted keys (those source keys not in common_keys_source_order)
// are interleaved here too, in source's original order, to
// match the historical (pre-reordering-aware) output order.
auto common_it = common_keys_source_order.cbegin();
for (auto it = source.cbegin(); it != source.cend(); ++it)
{
if (common_it != common_keys_source_order.cend() && it.key() == *common_it)
{
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
auto temp_diff = diff(it.value(), target[it.key()], path_key);
result.insert(result.end(), temp_diff.begin(), temp_diff.end());
++common_it;
}
else
{
// found a key that is not in target -> remove it
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
result.push_back(object(
{
{"op", "remove"}, {"path", path_key}
}));
}
}
// append the "add" ops for brand-new keys collected above
// during the pass over target -- no second source.find()
// per target key needed
result.insert(result.end(), added_ops.begin(), added_ops.end());
}
else
{
// slow path: the common keys are in a different relative
// order in source and target (only possible for a
// reorderable object_t like ordered_map). Building a
// minimal reordering patch is a nontrivial (LCS-like)
// problem; instead, remove every source key -- both
// deleted keys (which must be removed regardless) and
// common keys (removed so they can be re-added in
// target's order) -- and re-add every key that should
// remain, with its final target value, in target's
// order. basic_json::patch()'s "add" operation on an
// object uses operator[], which appends at the end for a
// vector-backed insertion-ordered map when the key does
// not already exist -- so removing a key and then adding
// it moves it to the end, fixing its position.
for (auto it = source.cbegin(); it != source.cend(); ++it)
{
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
// found a key that is not in o -> remove it
result.push_back(object(
{
{"op", "remove"}, {"path", path_key}
}));
}
}
// add every key that is either common (just removed
// above) or brand new, in target's iteration order, so
// that the final order after applying the patch matches
// target exactly
for (auto it = target.cbegin(); it != target.cend(); ++it)
// second pass: traverse other object's elements
for (auto it = target.cbegin(); it != target.cend(); ++it)
{
if (source.find(it.key()) == source.end())
{
// found a key that is not in this -> add it
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
result.push_back(
{
+97 -221
View File
@@ -7768,11 +7768,10 @@ NLOHMANN_JSON_NAMESPACE_END
#include <algorithm> // find_if
#include <cstddef>
#include <string> // string
#include <type_traits> // enable_if_t
#include <utility> // move, pair
#include <utility> // move
#include <vector> // vector
// #include <nlohmann/detail/exceptions.hpp>
@@ -7933,10 +7932,11 @@ class lexer : public lexer_base<BasicJsonType>
public:
using token_type = typename lexer_base<BasicJsonType>::token_type;
explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false) noexcept
explicit lexer(InputAdapterType&& adapter, bool ignore_comments_ = false, bool discard_number_values_ = false) noexcept
: ia(std::move(adapter))
, ignore_comments(ignore_comments_)
, decimal_point_char(static_cast<char_int_type>(get_decimal_point()))
, discard_number_values(discard_number_values_)
{}
// deleted because of pointer members
@@ -9063,6 +9063,58 @@ scan_number_done:
// we are done scanning a number)
unget();
// If the caller does not need the converted value (only whether the
// input is syntactically valid; see json_sax_acceptor/accept()), an
// unsigned/integer token can be reported without calling
// strtoull()/strtoll() at all, *provided* we can already tell from
// the digit count alone that the conversion cannot overflow 64 bits.
// Such tokens are always finite and are accepted unconditionally by
// the parser regardless of their actual value (parser::sax_parse_internal()
// never checks finiteness for value_unsigned/value_integer), so the
// classification below is all that is needed.
//
// A decimal number with up to 18 digits is always representable in
// both std::uint64_t and std::int64_t (18 nines is ~1e18, well below
// both UINT64_MAX ~1.8e19 and INT64_MAX ~9.2e18), so strtoull()/strtoll()
// could not have set errno to ERANGE for it. Numbers with more digits
// (rare in practice) fall through to the exact code below, unchanged,
// so their handling -- including reclassification to value_float when
// the value overflows 64 bits, and rejection when it is not even
// finite as a double -- is bit-for-bit identical to before this
// optimization.
//
// Note this reasons about std::uint64_t/std::int64_t, not about
// number_unsigned_t/number_integer_t (BasicJsonType's own, possibly
// narrower, template parameters -- e.g. std::uint32_t). That is fine
// *only* because discard_number_values is exclusively set by
// accept() (see json.hpp), and accept() always parses through the
// library's own json_sax_acceptor -- never a user-supplied SAX
// consumer -- whose number_unsigned()/number_integer()/number_float()
// callbacks unconditionally discard their argument and return true.
// So for every caller that can reach this branch, neither the token
// classification below nor the eventual (possibly narrowed, and on
// this fast path left stale/unset) value_unsigned/value_integer is
// ever consulted -- an unsigned/integer token is accepted outright,
// and even a >18-digit token that this fast path deliberately falls
// through for is, once reclassified to value_float, still finite
// (and thus accepted) for any digit count that fits in number_unsigned_t
// or number_integer_t regardless of that type's width. If this
// function is ever taught to run with discard_number_values true for
// a caller that *does* read the converted value, this reasoning (and
// the fast path below) would need to be revisited.
if (discard_number_values)
{
constexpr std::size_t safe_digit_count = 18;
if (number_type == token_type::value_unsigned && token_buffer.size() <= safe_digit_count)
{
return token_type::value_unsigned;
}
if (number_type == token_type::value_integer && token_buffer.size() - 1 <= safe_digit_count)
{
return token_type::value_integer;
}
}
char* endptr = nullptr; // NOLINT(misc-const-correctness,cppcoreguidelines-pro-type-vararg,hicpp-vararg)
errno = 0;
@@ -9538,6 +9590,13 @@ scan_number_done:
const char_int_type decimal_point_char = '.';
/// the position of the decimal point in the input
std::size_t decimal_point_position = std::string::npos;
/// whether the caller (e.g. accept()/json_sax_acceptor) only needs the
/// token classification and never looks at the converted numeric value;
/// when set, scan_number() may skip strtoull()/strtoll() for
/// value_unsigned/value_integer tokens whose digit count guarantees they
/// fit into 64 bits (see scan_number())
const bool discard_number_values = false;
};
} // namespace detail
@@ -10114,17 +10173,7 @@ class json_sax_dom_callback_parser
// add discarded value at the given key and store the reference for later
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())
{
// 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);
}
object_element = &(obj[val] = discarded);
object_element = &(ref_stack.back()->m_data.m_value.object->operator[](val) = discarded);
}
return true;
@@ -10136,18 +10185,13 @@ class json_sax_dom_callback_parser
{
if (!callback(static_cast<int>(ref_stack.size()) - 1, parse_event_t::object_end, *ref_stack.back()))
{
// discard object, unless this slot holds a duplicate key's
// previous value pending restoration, in which case that
// value is restored instead of being discarded
if (!resolve_duplicate_key_stash(ref_stack.back(), true))
{
*ref_stack.back() = discarded;
// discard object
*ref_stack.back() = discarded;
#if JSON_DIAGNOSTIC_POSITIONS
// Set start/end positions for discarded object.
handle_diagnostic_positions_for_json_value(*ref_stack.back());
// Set start/end positions for discarded object.
handle_diagnostic_positions_for_json_value(*ref_stack.back());
#endif
}
}
else
{
@@ -10161,10 +10205,6 @@ class json_sax_dom_callback_parser
#endif
ref_stack.back()->set_parents();
// this object is finally, definitively kept; drop any
// pending duplicate-key stash entry for its slot since it
// can no longer be restored
resolve_duplicate_key_stash(ref_stack.back(), false);
}
}
@@ -10234,25 +10274,16 @@ class json_sax_dom_callback_parser
#endif
ref_stack.back()->set_parents();
// this array is finally, definitively kept; drop any
// pending duplicate-key stash entry for its slot since it
// can no longer be restored
resolve_duplicate_key_stash(ref_stack.back(), false);
}
else
{
// discard array, unless this slot holds a duplicate key's
// previous value pending restoration, in which case that
// value is restored instead of being discarded
if (!resolve_duplicate_key_stash(ref_stack.back(), true))
{
*ref_stack.back() = discarded;
// discard array
*ref_stack.back() = discarded;
#if JSON_DIAGNOSTIC_POSITIONS
// Set start/end positions for discarded array.
handle_diagnostic_positions_for_json_value(*ref_stack.back());
// Set start/end positions for discarded array.
handle_diagnostic_positions_for_json_value(*ref_stack.back());
#endif
}
}
}
@@ -10366,48 +10397,14 @@ class json_sax_dom_callback_parser
}
#endif
/// if there is a pending duplicate-key stash entry for this exact slot,
/// remove it from the stash; if restore_value is true, the stashed
/// previous value is moved back into the slot first (use this when the
/// new value at that slot was rejected); otherwise the stash entry is
/// simply dropped (use this when the new value was accepted, so it
/// correctly supersedes the old one and no restore should ever happen
/// for this slot again)
/// @return whether a matching stash entry was found (and processed)
bool resolve_duplicate_key_stash(BasicJsonType* slot, bool restore_value)
{
const auto it = std::find_if(duplicate_key_stash.begin(), duplicate_key_stash.end(),
[slot](const std::pair<BasicJsonType*, BasicJsonType>& entry)
{
return entry.first == slot;
});
if (it == duplicate_key_stash.end())
{
return false;
}
if (restore_value)
{
*slot = std::move(it->second);
}
duplicate_key_stash.erase(it);
return true;
}
/// remove the discarded value the callback rejected from its parent,
/// unless it is a duplicate key's slot with a stashed previous value,
/// in which case that previous value is restored instead
void remove_discarded_value(BasicJsonType& parent)
/// remove the discarded value the callback rejected from its parent
static void remove_discarded_value(BasicJsonType& parent)
{
for (auto it = parent.begin(); it != parent.end(); ++it)
{
if (it->is_discarded())
{
if (!resolve_duplicate_key_stash(&(*it), true))
{
parent.erase(it);
}
parent.erase(it);
break;
}
}
@@ -10505,16 +10502,6 @@ class json_sax_dom_callback_parser
JSON_ASSERT(object_element);
*object_element = std::move(value);
if (!skip_callback)
{
// this scalar value finally, definitively replaces whatever was
// at this slot; drop any pending duplicate-key stash entry for
// it since it can no longer be restored (a container value at
// this slot is resolved later, in end_object()/end_array(),
// since skip_callback is true for the placeholder handling that
// happens here for those)
resolve_duplicate_key_stash(object_element, false);
}
return {true, object_element};
}
@@ -10528,12 +10515,6 @@ class json_sax_dom_callback_parser
std::vector<bool> key_keep_stack {}; // NOLINT(readability-redundant-member-init)
/// helper to hold the reference for the next object element
BasicJsonType* object_element = nullptr;
/// stash of (slot pointer, previous value) for object members that
/// already existed when key() was called again for the same key
/// (duplicate keys); used to restore the previous value if the new
/// value is later rejected by the callback, instead of erasing the
/// member entirely
std::vector<std::pair<BasicJsonType*, BasicJsonType>> duplicate_key_stash {};
/// whether a syntax error occurred
bool errored = false;
/// callback function
@@ -14122,9 +14103,10 @@ class parser
parser_callback_t<BasicJsonType> cb = nullptr,
const bool allow_exceptions_ = true,
const bool ignore_comments = false,
const bool ignore_trailing_commas_ = false)
const bool ignore_trailing_commas_ = false,
const bool discard_number_values_ = false)
: callback(std::move(cb))
, m_lexer(std::move(adapter), ignore_comments)
, m_lexer(std::move(adapter), ignore_comments, discard_number_values_)
, allow_exceptions(allow_exceptions_)
, ignore_trailing_commas(ignore_trailing_commas_)
{
@@ -21671,11 +21653,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
detail::parser_callback_t<basic_json>cb = nullptr,
const bool allow_exceptions = true,
const bool ignore_comments = false,
const bool ignore_trailing_commas = false
const bool ignore_trailing_commas = false,
const bool discard_number_values = false
)
{
return ::nlohmann::detail::parser<basic_json, InputAdapterType>(std::move(adapter),
std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas);
std::move(cb), allow_exceptions, ignore_comments, ignore_trailing_commas, discard_number_values);
}
private:
@@ -25080,7 +25063,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
{
using std::swap;
swap(*(m_data.m_value.array), other);
set_parents();
}
else
{
@@ -25097,7 +25079,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
{
using std::swap;
swap(*(m_data.m_value.object), other);
set_parents();
}
else
{
@@ -25642,7 +25623,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = false,
const bool ignore_trailing_commas = false)
{
return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
return parser(detail::input_adapter(std::forward<InputType>(i)), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
}
/// @brief check if the input is valid JSON (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -25653,7 +25634,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = false,
const bool ignore_trailing_commas = false)
{
return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
return parser(detail::input_adapter(std::move(first), std::move(last)), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
}
JSON_HEDLEY_WARN_UNUSED_RESULT
@@ -25662,7 +25643,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
const bool ignore_comments = false,
const bool ignore_trailing_commas = false)
{
return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas).accept(true);
return parser(i.get(), nullptr, false, ignore_comments, ignore_trailing_commas, true).accept(true);
}
/// @brief generate SAX events
@@ -26666,139 +26647,34 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
case value_t::object:
{
// first pass: record, for every source key, whether it is
// common to both objects (in source's iteration order) or
// was deleted (i.e., in source but not in target) -- this is
// a by-product of the target.find() call already needed to
// tell the two cases apart, so it adds no extra lookups. The
// "remove" ops themselves are emitted later, interleaved
// with the recursive per-key diffs in the fast path below,
// to match source's original iteration order (as the
// original, pre-reordering-aware implementation did) instead
// of grouping all removes before all recursive diffs.
std::vector<typename object_t::key_type> common_keys_source_order;
// first pass: traverse this object's elements
for (auto it = source.cbegin(); it != source.cend(); ++it)
{
// escape the key name to be used in a JSON patch
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
if (target.find(it.key()) != target.end())
{
common_keys_source_order.push_back(it.key());
}
}
// second pass: find keys that were added (i.e., in target but
// not in source), and record the keys common to both, in
// target's iteration order -- again a by-product of the
// source.find() call already needed to detect added keys. At
// the same time, determine whether every added key comes
// after every common key in target's order (a precondition
// for the fast path below, which only ever appends new keys
// at the very end): for an object_t whose iteration order is
// a pure function of the key set (e.g. the default std::map,
// which always iterates in sorted key order), the order
// check further below is always true and this whole
// mechanism is effectively a no-op; it only matters for a
// reorderable object_t such as the one backing `ordered_json`.
// patch ops for keys that were added (i.e., in target but not
// in source); built here so the fast path below can reuse
// them without a second source.find() per target key. Only
// used by the fast path -- the slow (reordering) path
// rebuilds "add" ops for every key itself.
std::vector<typename object_t::key_type> common_keys_target_order;
basic_json added_ops(value_t::array);
bool new_keys_form_suffix = true;
bool seen_new_key = false;
for (auto it = target.cbegin(); it != target.cend(); ++it)
{
if (source.find(it.key()) == source.end())
{
seen_new_key = true;
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
added_ops.push_back(
{
{"op", "add"}, {"path", path_key},
{"value", it.value()}
});
// recursive call to compare object values at key it
auto temp_diff = diff(it.value(), target[it.key()], path_key);
result.insert(result.end(), temp_diff.begin(), temp_diff.end());
}
else
{
common_keys_target_order.push_back(it.key());
if (seen_new_key)
{
new_keys_form_suffix = false;
}
}
}
if (common_keys_source_order == common_keys_target_order && new_keys_form_suffix)
{
// fast path: order of common keys already matches (or the
// object_t's iteration order does not depend on
// insertion history), so a plain per-key recursive diff
// is correct and minimal, as before. common_keys_source_order
// is, by construction, the subsequence of source's keys
// that are common to both objects, in source's iteration
// order -- so it can be walked in lockstep with `source`
// using a cheap key comparison instead of another lookup.
// Deleted keys (those source keys not in common_keys_source_order)
// are interleaved here too, in source's original order, to
// match the historical (pre-reordering-aware) output order.
auto common_it = common_keys_source_order.cbegin();
for (auto it = source.cbegin(); it != source.cend(); ++it)
{
if (common_it != common_keys_source_order.cend() && it.key() == *common_it)
{
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
auto temp_diff = diff(it.value(), target[it.key()], path_key);
result.insert(result.end(), temp_diff.begin(), temp_diff.end());
++common_it;
}
else
{
// found a key that is not in target -> remove it
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
result.push_back(object(
{
{"op", "remove"}, {"path", path_key}
}));
}
}
// append the "add" ops for brand-new keys collected above
// during the pass over target -- no second source.find()
// per target key needed
result.insert(result.end(), added_ops.begin(), added_ops.end());
}
else
{
// slow path: the common keys are in a different relative
// order in source and target (only possible for a
// reorderable object_t like ordered_map). Building a
// minimal reordering patch is a nontrivial (LCS-like)
// problem; instead, remove every source key -- both
// deleted keys (which must be removed regardless) and
// common keys (removed so they can be re-added in
// target's order) -- and re-add every key that should
// remain, with its final target value, in target's
// order. basic_json::patch()'s "add" operation on an
// object uses operator[], which appends at the end for a
// vector-backed insertion-ordered map when the key does
// not already exist -- so removing a key and then adding
// it moves it to the end, fixing its position.
for (auto it = source.cbegin(); it != source.cend(); ++it)
{
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
// found a key that is not in o -> remove it
result.push_back(object(
{
{"op", "remove"}, {"path", path_key}
}));
}
}
// add every key that is either common (just removed
// above) or brand new, in target's iteration order, so
// that the final order after applying the patch matches
// target exactly
for (auto it = target.cbegin(); it != target.cend(); ++it)
// second pass: traverse other object's elements
for (auto it = target.cbegin(); it != target.cend(); ++it)
{
if (source.find(it.key()) == source.end())
{
// found a key that is not in this -> add it
const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
result.push_back(
{
+92
View File
@@ -930,6 +930,98 @@ TEST_CASE("parser class")
CHECK(accept_helper("+1") == false);
CHECK(accept_helper("+0") == false);
}
SECTION("issue #5411 - skip conversion when accept() does not need the numeric value")
{
// lexer::scan_number() may skip strtoull()/strtoll() for
// value_unsigned/value_integer tokens when the caller (e.g.
// json::accept()) does not need the converted value, as long
// as the digit count alone guarantees no 64-bit overflow (see
// the "safe_digit_count" fast path in scan_number()). This
// differential test checks that json::accept() (which enables
// the fast path) and json::parse() (which never does) always
// agree, over a corpus that exercises both the fast path
// (<=18 digits) and the untouched, exact fallback path (>=19
// digits) -- including reclassification of huge digit-only
// integers to a (possibly non-finite) floating-point value.
const std::vector<std::pair<std::string, bool>> cases =
{
// normal small/large integers, both signs
{"0", true}, {"1", true}, {"-1", true}, {"42", true}, {"-42", true},
{"123456789", true}, {"-123456789", true},
// digit-count boundary around the 18-digit safe cutoff (both signs)
{std::string(17, '9'), true},
{std::string(18, '9'), true},
{std::string(19, '9'), true},
{std::string(20, '9'), true},
{"-" + std::string(17, '9'), true},
{"-" + std::string(18, '9'), true},
{"-" + std::string(19, '9'), true},
{"-" + std::string(20, '9'), true},
// 64-bit boundaries
{"9223372036854775807", true}, // INT64_MAX
{"-9223372036854775808", true}, // INT64_MIN
{"18446744073709551615", true}, // UINT64_MAX
{"18446744073709551616", true}, // UINT64_MAX + 1 (overflows uint64_t, finite double)
// the 28-digit example from the issue: overflows uint64_t
// but is finite as a double, so the scanner reclassifies
// it to value_float and it is accepted
{"9999999999999999999999999999", true},
// huge digit-only integers that overflow even a double -> rejected
{std::string(309, '9'), false},
{std::string(400, '9'), false},
{"1" + std::string(400, '0'), false},
// 1e999 / 1e400 style overflow -> rejected
{"1e999", false},
{"1e400", false},
{"-1e999", false},
{"1E999", false},
// values straddling DBL_MAX
{"1.7976931348623157e308", true}, // <= DBL_MAX, finite
{"1.7976931348623159e308", false}, // > DBL_MAX, overflows to inf
// a mix of other valid/invalid numeric syntax
{"3.14159", true},
{"-0.0", true},
{"1.0e10", true},
{"01", false},
{"-", false},
{"1.", false},
{"1e", false},
{"+1", false},
};
for (const auto& c : cases)
{
const std::string& number = c.first;
const bool expected = c.second;
CAPTURE(number)
CAPTURE(expected)
// accept() takes the fast path (skips conversion when possible)
CHECK(json::accept(number) == expected);
// parse() always performs the full conversion; it must agree
json j;
CHECK_NOTHROW(json::parser(nlohmann::detail::input_adapter(number), nullptr, false).parse(true, j));
CHECK(!j.is_discarded() == expected);
// wrap in an array so get_token() is exercised beyond the
// very first (constructor-time) scan as well
std::string wrapped = "[";
wrapped += number;
wrapped += ",";
wrapped += number;
wrapped += "]";
CHECK(json::accept(wrapped) == expected);
}
}
}
}
-31
View File
@@ -273,36 +273,5 @@ TEST_CASE("Regression tests for extended diagnostics")
CHECK(j1["numbers"]["two"] == 2);
CHECK(j1["string"] == "t");
}
SECTION("Regression test - swap(array_t&)/swap(object_t&) must update JSON_DIAGNOSTICS parent pointers")
{
// swap(array_t&)
{
json j = json::array();
json::array_t arr = {json::array({1})};
j.swap(arr);
// parent pointers of the moved-in elements must point into j, not
// into the now-defunct free-standing array_t
CHECK_THROWS_WITH_AS(j[0][0].get<std::string>(), "[json.exception.type_error.302] (/0/0) type must be string, but is number", json::type_error);
// must not trigger assert_invariant() in a debug/assert-enabled build
json const k = j;
CHECK(k == j);
}
// swap(object_t&)
{
json o = json::object();
json::object_t obj = {{"a", json::array({1})}};
o.swap(obj);
CHECK_THROWS_WITH_AS(o["a"][0].get<std::string>(), "[json.exception.type_error.302] (/a/0) type must be string, but is number", json::type_error);
// must not trigger assert_invariant() in a debug/assert-enabled build
json const p = o;
CHECK(p == o);
}
}
}
-81
View File
@@ -81,84 +81,3 @@ TEST_CASE("regression test for issue #3732 - iteration_proxy_value<iter_impl<ord
};
static_cast<void>(fn);
}
TEST_CASE("regression test - diff() must account for ordered_json member order")
{
SECTION("pure reorder, no value changes")
{
ordered_json a = {{"a", 1}, {"b", 2}};
ordered_json b = {{"b", 2}, {"a", 1}};
CHECK(a != b); // order-sensitive equality
CHECK(a.patch(ordered_json::diff(a, b)) == b);
}
SECTION("new key must land at the front")
{
ordered_json c = {{"b", 2}};
ordered_json e = {{"a", 1}, {"b", 2}};
CHECK(c.patch(ordered_json::diff(c, e)) == e);
}
SECTION("reorder plus a value change on one of the reordered keys")
{
ordered_json a = {{"a", 1}, {"b", 2}};
ordered_json b = {{"b", 20}, {"a", 1}};
CHECK(a != b);
CHECK(a.patch(ordered_json::diff(a, b)) == b);
}
SECTION("reorder plus a deleted key")
{
ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}};
ordered_json b = {{"b", 2}, {"a", 1}};
CHECK(a != b);
CHECK(a.patch(ordered_json::diff(a, b)) == b);
}
SECTION("reorder plus a nested value that itself needs a recursive diff")
{
ordered_json a = {{"a", {{"x", 1}, {"y", 2}}}, {"b", 2}};
ordered_json b = {{"b", 2}, {"a", {{"x", 1}, {"y", 99}}}};
CHECK(a != b);
CHECK(a.patch(ordered_json::diff(a, b)) == b);
}
SECTION("three or more keys shuffled into a different order")
{
ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}, {"d", 4}};
ordered_json b = {{"d", 4}, {"b", 2}, {"a", 1}, {"c", 3}};
CHECK(a != b);
CHECK(a.patch(ordered_json::diff(a, b)) == b);
}
SECTION("matching order still produces a minimal patch (fast path unaffected)")
{
ordered_json a = {{"a", 1}, {"b", 2}, {"c", 3}};
ordered_json b = {{"a", 1}, {"b", 20}, {"c", 3}};
auto p = ordered_json::diff(a, b);
// only the changed value should be touched, not a wholesale remove+add
CHECK(p.size() == 1);
CHECK(p[0]["op"] == "replace");
CHECK(p[0]["path"] == "/b");
CHECK(a.patch(p) == b);
}
SECTION("plain json (std::map-backed) is unaffected by same-key-different-insertion-order")
{
json a;
a["b"] = 2;
a["a"] = 1;
json b;
b["a"] = 1;
b["b"] = 2;
// std::map iteration is always sorted by key, so a == b regardless of
// insertion order, and diff() must still produce the same minimal
// (empty) result as before this fix
CHECK(a == b);
auto p = json::diff(a, b);
CHECK(p.empty());
CHECK(a.patch(p) == b);
}
}
-71
View File
@@ -1566,75 +1566,4 @@ TEST_CASE("issue #5402 - update(merge_objects=true) overwrites a primitive with
CHECK(mixed == json({{"keep", {{"a", 1}, {"b", 2}}}, {"replace", {{"x", 2}}}}));
}
TEST_CASE("regression test - parser callback must not lose a duplicate key's prior value")
{
// a callback that rejects only the scalar value 2
const json::parser_callback_t drop_value_2 = [](int /*depth*/, json::parse_event_t ev, json & v) noexcept
{
return !(ev == json::parse_event_t::value && v == 2);
};
SECTION("duplicate key, second (scalar) value rejected - prior value is restored")
{
const json j = json::parse(R"({"a":1,"a":2})", drop_value_2);
CHECK(j.dump() == "{\"a\":1}");
}
SECTION("duplicate key, second value is an object rejected at object_end - prior value is restored")
{
const json j = json::parse(R"({"a":1,"a":{"x":2}})",
[](int depth, json::parse_event_t ev, json& /*parsed*/) noexcept
{
return !(ev == json::parse_event_t::object_end && depth == 1);
});
CHECK(j.dump() == "{\"a\":1}");
}
SECTION("duplicate key, second value is an array rejected at array_end - prior value is restored")
{
const json j = json::parse(R"({"a":1,"a":[9,9]})",
[](int depth, json::parse_event_t ev, json& /*parsed*/) noexcept
{
return !(ev == json::parse_event_t::array_end && depth == 1);
});
CHECK(j.dump() == "{\"a\":1}");
}
SECTION("duplicate key, second value accepted (scalar) - last value wins")
{
const json j = json::parse(R"({"a":1,"a":2})", [](int, json::parse_event_t, json&) noexcept
{
return true;
});
CHECK(j.dump() == "{\"a\":2}");
}
SECTION("duplicate key, second value accepted (object) - last value wins")
{
const json j = json::parse(R"({"a":1,"a":{"x":2}})", [](int, json::parse_event_t, json&) noexcept
{
return true;
});
CHECK(j.dump() == "{\"a\":{\"x\":2}}");
}
SECTION("brand new (non-duplicate) key, value rejected - member is fully absent")
{
const json j = json::parse(R"({"a":1,"b":2})", drop_value_2);
CHECK(j.dump() == "{\"a\":1}");
}
SECTION("duplicate key nested two levels deep")
{
const json j = json::parse(R"({"outer":{"a":1,"a":2}})", drop_value_2);
CHECK(j.dump() == "{\"outer\":{\"a\":1}}");
}
SECTION("three occurrences of the same key - middle rejected, last accepted")
{
const json j = json::parse(R"({"k":1,"k":2,"k":3})", drop_value_2);
CHECK(j.dump() == "{\"k\":3}");
}
}
DOCTEST_CLANG_SUPPRESS_WARNING_POP