Reject a nested BJData ndarray dimension vector where it is read

get_ubjson_size_type() takes an inside_ndarray parameter saying whether it is
being called for an ndarray's dimension vector, where another ndarray is not
allowed. It then seeded the flag it passes down to get_ubjson_size_value()
with `false` rather than with that parameter, and only consulted
inside_ndarray afterwards, on the '$' branch.

So on the '#' branch nothing stopped the descent: every "#[" pair of an input
like "[" followed by "#[#[#[..." opened another dimension vector, several
native stack frames deeper each time, and the recursion was only reported on
the way back out. 100,000 pairs crash the process. This is #5104 again, in a
path that has nothing to do with containers.

Seed the flag with inside_ndarray, which is what get_ubjson_size_value()
documents it wants: "for input, `true` means already inside an ndarray vector
or ndarray dimension is not allowed". The nested '[' is then refused where it
is read, so the length of the chain no longer matters.

Both post-checks gain `&& !inside_ndarray`, because an ndarray was found
*here* only if the flag flipped -- get_ubjson_size_value() only ever returns
`true` when its initial value was `false`, as its documentation says. With
that, the "ndarray can not be recursive" branch is unreachable: a recursive
ndarray is now caught one level earlier, and reported as "ndarray dimensional
vector is not allowed" like every other nested dimension vector.

Three existing expectations move accordingly (vR2, vR4, vR6). All three now
fail earlier, and all three now report the same error that vR1, vR5 and vH
already reported for the same shape, which is the more consistent outcome.
Everything else is unchanged: valid 1D and 2D ndarrays, optimized containers
and plain arrays produce identical results, and unit-ubjson is untouched.

Signed-off-by: Niels Lohmann <mail@nlohmann.me>

.github/workflows/check_amalgamation.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 
@@ -34,7 +34,7 @@ jobs:
 
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 

.github/workflows/cifuzz.yml

@@ -9,7 +9,7 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
     - name: Harden Runner
-      uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+      uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
       with:
         egress-policy: audit
 

.github/workflows/codeql-analysis.yml

@@ -27,7 +27,7 @@ jobs:
 
     steps:
     - name: Harden Runner
-      uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+      uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
       with:
         egress-policy: audit
 

.github/workflows/comment_check_amalgamation.yml

@@ -19,7 +19,7 @@ jobs:
       pull-requests: write
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 

.github/workflows/dependency-review.yml

@@ -17,7 +17,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 

.github/workflows/flawfinder.yml

@@ -27,7 +27,7 @@ jobs:
       security-events: write
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 

.github/workflows/labeler.yml

@@ -17,7 +17,7 @@ jobs:
 
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 

.github/workflows/publish_documentation.yml

@@ -26,7 +26,7 @@ jobs:
     runs-on: ubuntu-22.04
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 

.github/workflows/scorecards.yml

@@ -36,7 +36,7 @@ jobs:
 
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 

.github/workflows/semgrep.yml

@@ -32,7 +32,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 

.github/workflows/stale.yml

@@ -16,7 +16,7 @@ jobs:
 
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 

.github/workflows/ubuntu.yml

@@ -35,7 +35,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 
@@ -60,7 +60,7 @@ jobs:
         target: [ci_test_amalgamation, ci_test_single_header, ci_cppcheck, ci_cpplint, ci_reproducible_tests, ci_non_git_tests, ci_offline_testdata, ci_reuse_compliance, ci_test_valgrind]
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 
@@ -118,7 +118,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 
@@ -369,7 +369,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 
@@ -392,7 +392,7 @@ jobs:
         target: [ci_test_examples, ci_test_build_documentation]
     steps:
       - name: Harden Runner
-        uses: step-security/harden-runner@05e31511f85b41b11d1cf0ef85d0992719546e2c # v2.21.0
+        uses: step-security/harden-runner@e14015d583714f6e62063499dc959a02595150a1 # v2.21.1
         with:
           egress-policy: audit
 

Makefile

@@ -1,4 +1,4 @@
-.PHONY: pretty clean ChangeLog.md release
+.PHONY: pretty clean ChangeLog.md release update_hedley update_hedley_undef
 
 ##########################################################################
 # configuration
@@ -41,6 +41,8 @@ all:
 	@echo "fuzz_testing_ubjson - prepare fuzz testing of the UBJSON parser"
 	@echo "pretty - beautify code with Artistic Style"
 	@echo "run_benchmarks - build and run benchmarks"
+	@echo "update_hedley - download Hedley and regenerate hedley.hpp / hedley_undef.hpp"
+	@echo "update_hedley_undef - rebuild hedley_undef.hpp from the JSON_HEDLEY_* #define names in hedley.hpp"
 
 
 ##########################################################################
@@ -241,11 +243,24 @@ update_hedley:
 	rm -f include/nlohmann/thirdparty/hedley/hedley.hpp include/nlohmann/thirdparty/hedley/hedley_undef.hpp
 	curl https://raw.githubusercontent.com/nemequ/hedley/master/hedley.h -o include/nlohmann/thirdparty/hedley/hedley.hpp
 	$(SED) -i 's/HEDLEY_/JSON_HEDLEY_/g' include/nlohmann/thirdparty/hedley/hedley.hpp
-	grep "[[:blank:]]*#[[:blank:]]*undef" include/nlohmann/thirdparty/hedley/hedley.hpp | grep -v "__" | sort | uniq | $(SED) 's/ //g' | $(SED) 's/undef/undef /g' > include/nlohmann/thirdparty/hedley/hedley_undef.hpp
 	$(SED) -i '1s/^/#pragma once\n\n/' include/nlohmann/thirdparty/hedley/hedley.hpp
-	$(SED) -i '1s/^/#pragma once\n\n/' include/nlohmann/thirdparty/hedley/hedley_undef.hpp
+	$(MAKE) update_hedley_undef
 	$(MAKE) amalgamate
 
+# Rebuild hedley_undef.hpp from every JSON_HEDLEY_* name that hedley.hpp
+# #defines. Hedley does not #undef all of its public macros internally (see
+# #5408), so grepping those #undef lines misses names such as
+# JSON_HEDLEY_PRAGMA. cmake/scripts/gen_hedley_undef_check.cmake is the
+# single source of truth for this extraction (tests/CMakeLists.txt uses the
+# same script, in MODE=checks, to generate the matching leak-check test), so
+# the vendored header, the generated #undef list, and the regression test
+# cannot drift apart.
+update_hedley_undef:
+	cmake -DHEDLEY_HPP=include/nlohmann/thirdparty/hedley/hedley.hpp \
+	      -DOUTPUT=include/nlohmann/thirdparty/hedley/hedley_undef.hpp \
+	      -DMODE=undef \
+	      -P cmake/scripts/gen_hedley_undef_check.cmake
+
 ##########################################################################
 # serve_header.py
 ##########################################################################

cmake/scripts/gen_hedley_undef_check.cmake

@@ -0,0 +1,112 @@
+# Shared extractor for the JSON_HEDLEY_* macro names defined in hedley.hpp.
+#
+# Every macro that hedley.hpp #defines must be #undef-ed again once json.hpp
+# has been fully processed (see include/nlohmann/detail/macro_unscope.hpp
+# and https://github.com/nlohmann/json/issues/5408). Deriving the macro list
+# straight from hedley.hpp here -- instead of hand-maintaining it in two
+# places -- means hedley_undef.hpp and the regression test that checks for
+# leaked macros can never drift apart, even after a future `make
+# update_hedley` pulls in new macros from upstream Hedley.
+#
+#   MODE=undef  (default): write hedley_undef.hpp (SPDX header, #pragma once,
+#               one #undef per macro name) -- used by `make update_hedley_undef`
+#   MODE=checks:            write one #ifdef/FAIL_CHECK/#endif per macro name,
+#               meant to be #include-d inside a TEST_CASE -- used by
+#               tests/CMakeLists.txt to (re)generate the include for
+#               tests/src/unit-no-macro-leak.cpp
+#
+# Required variables:
+#   HEDLEY_HPP  path to include/nlohmann/thirdparty/hedley/hedley.hpp
+#   OUTPUT      path of the file to (over)write
+# Optional:
+#   MODE        "undef" (default) or "checks"
+
+if(NOT DEFINED HEDLEY_HPP OR NOT DEFINED OUTPUT)
+    message(FATAL_ERROR "HEDLEY_HPP and OUTPUT must be set")
+endif()
+
+if(NOT EXISTS "${HEDLEY_HPP}")
+    message(FATAL_ERROR "Hedley header not found: ${HEDLEY_HPP}")
+endif()
+
+if(NOT DEFINED MODE)
+    set(MODE undef)
+endif()
+
+if(NOT MODE STREQUAL "undef" AND NOT MODE STREQUAL "checks")
+    message(FATAL_ERROR "MODE must be undef or checks, got: ${MODE}")
+endif()
+
+# Line-anchored, like `grep -oE "^[[:blank:]]*#[[:blank:]]*define[[:blank:]]+JSON_HEDLEY_[A-Za-z0-9_]+"`.
+# Unanchored matching would also pick up JSON_HEDLEY_* mentions inside
+# comments or string literals elsewhere in the file, which must not turn
+# into #undef lines.
+file(STRINGS "${HEDLEY_HPP}" hedley_lines)
+set(macro_names)
+foreach(line IN LISTS hedley_lines)
+    if("${line}" MATCHES "^[ \t]*#[ \t]*define[ \t]+(JSON_HEDLEY_[A-Za-z0-9_]+)")
+        list(APPEND macro_names "${CMAKE_MATCH_1}")
+    endif()
+endforeach()
+
+if(NOT macro_names)
+    message(FATAL_ERROR "No JSON_HEDLEY_* macros found in ${HEDLEY_HPP}")
+endif()
+
+list(REMOVE_DUPLICATES macro_names)
+# Lexicographic, locale-independent (ASCII-only names) -- matches `LC_ALL=C sort`.
+list(SORT macro_names COMPARE STRING)
+list(LENGTH macro_names macro_count)
+
+set(generated "")
+if(MODE STREQUAL "undef")
+    # Same banner `make update_hedley_undef` would stamp by hand, so the
+    # recipe is self-contained and its output is byte-stable across reruns.
+    # The embedded SPDX tags below are part of the *generated* file's
+    # content, not a REUSE header for this .cmake script itself (which is
+    # already covered by the blanket "Files: *" rule in .reuse/dep5) -- keep
+    # them wrapped in REUSE-IgnoreStart/End so `reuse lint` does not try to
+    # parse "MIT\n")" as this file's own SPDX-License-Identifier value.
+    # REUSE-IgnoreStart
+    string(APPEND generated "//     __ _____ _____ _____\n")
+    string(APPEND generated "//  __|  |   __|     |   | |  JSON for Modern C++\n")
+    string(APPEND generated "// |  |  |__   |  |  | | | |  version 3.12.0\n")
+    string(APPEND generated "// |_____|_____|_____|_|___|  https://github.com/nlohmann/json\n")
+    string(APPEND generated "//\n")
+    string(APPEND generated "// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>\n")
+    string(APPEND generated "// SPDX-License-Identifier: MIT\n")
+    # REUSE-IgnoreEnd
+    string(APPEND generated "\n")
+    string(APPEND generated "#pragma once\n")
+    string(APPEND generated "\n")
+    foreach(name IN LISTS macro_names)
+        string(APPEND generated "#undef ${name}\n")
+    endforeach()
+else()
+    string(APPEND generated "// This file is generated by cmake/scripts/gen_hedley_undef_check.cmake\n")
+    string(APPEND generated "// from include/nlohmann/thirdparty/hedley/hedley.hpp. Do not edit it by\n")
+    string(APPEND generated "// hand -- it is regenerated on every build. ${macro_count} macros checked.\n\n")
+    foreach(name IN LISTS macro_names)
+        string(APPEND generated "#ifdef ${name}\n")
+        string(APPEND generated "    FAIL_CHECK(\"${name} leaked after including nlohmann/json.hpp\");\n")
+        string(APPEND generated "#endif\n")
+    endforeach()
+endif()
+
+get_filename_component(output_dir "${OUTPUT}" DIRECTORY)
+if(output_dir)
+    file(MAKE_DIRECTORY "${output_dir}")
+endif()
+
+# Avoid rewriting the file (and busting downstream incremental rebuilds)
+# when the content has not actually changed.
+set(write_output TRUE)
+if(EXISTS "${OUTPUT}")
+    file(READ "${OUTPUT}" existing_content)
+    if(existing_content STREQUAL generated)
+        set(write_output FALSE)
+    endif()
+endif()
+if(write_output)
+    file(WRITE "${OUTPUT}" "${generated}")
+endif()

docs/mkdocs/docs/api/basic_json/insert.md

@@ -88,8 +88,6 @@ Strong exception safety: if an exception occurs, the original value stays intact
       do not belong to the same JSON value; example: `"iterators do not fit"`
     - Throws [`invalid_iterator.211`](../../home/exceptions.md#jsonexceptioninvalid_iterator211) if `first` or `last`
       are iterators into container for which insert is called; example: `"passed iterators may not belong to container"`
-    - Throws [`invalid_iterator.202`](../../home/exceptions.md#jsonexceptioninvalid_iterator202) if `first` or `last`
-      do not point to an array; example: `"iterators first and last must point to arrays"`
 4. The function can throw the following exceptions:
     - Throws [`type_error.309`](../../home/exceptions.md#jsonexceptiontype_error309) if called on JSON values other than
       arrays; example: `"cannot use insert() with string"`

docs/mkdocs/docs/api/basic_json/patch.md

@@ -34,6 +34,10 @@ Strong guarantee: if an exception is thrown, there are no changes in the JSON va
   ("add", "remove", "move")
 - Throws [`out_of_range.411`](../../home/exceptions.md#jsonexceptionout_of_range411) if an "add" operation's target
   location has a parent that is neither an object nor an array.
+- Throws [`out_of_range.413`](../../home/exceptions.md#jsonexceptionout_of_range413) if a "remove" operation's target
+  location has a parent that is neither an object nor an array.
+- Throws [`out_of_range.414`](../../home/exceptions.md#jsonexceptionout_of_range414) if a "move" operation's "from"
+  location is a proper prefix of its "path" location.
 - Throws [`other_error.501`](../../home/exceptions.md#jsonexceptionother_error501) if "test" operation was
   unsuccessful.
 
@@ -75,3 +79,7 @@ is thrown. In any case, the original value is not changed: the patch is applied
 - Added in version 2.0.0.
 - Added [`out_of_range.411`](../../home/exceptions.md#jsonexceptionout_of_range411) and stopped relying on an internal assertion when an "add" operation's
   target location has a non-object/non-array parent in version 3.13.0.
+- Added [`out_of_range.413`](../../home/exceptions.md#jsonexceptionout_of_range413) and stopped silently ignoring a "remove" operation whose target
+  location has a non-object/non-array parent in version 3.13.0.
+- Added [`out_of_range.414`](../../home/exceptions.md#jsonexceptionout_of_range414) and rejected a "move" operation whose "from" location is a proper
+  prefix of its "path" location instead of silently producing a corrupted result in version 3.13.0.

docs/mkdocs/docs/api/basic_json/patch_inplace.md

@@ -30,6 +30,10 @@ No guarantees, value may be corrupted by an unsuccessful patch operation.
   ("add", "remove", "move")
 - Throws [`out_of_range.411`](../../home/exceptions.md#jsonexceptionout_of_range411) if an "add" operation's target
   location has a parent that is neither an object nor an array.
+- Throws [`out_of_range.413`](../../home/exceptions.md#jsonexceptionout_of_range413) if a "remove" operation's target
+  location has a parent that is neither an object nor an array.
+- Throws [`out_of_range.414`](../../home/exceptions.md#jsonexceptionout_of_range414) if a "move" operation's "from"
+  location is a proper prefix of its "path" location.
 - Throws [`other_error.501`](../../home/exceptions.md#jsonexceptionother_error501) if "test" operation was
   unsuccessful.
 
@@ -72,3 +76,7 @@ function throws an exception.
 - Added in version 3.11.0.
 - Added [`out_of_range.411`](../../home/exceptions.md#jsonexceptionout_of_range411) and stopped relying on an internal assertion when an "add" operation's
   target location has a non-object/non-array parent in version 3.13.0.
+- Added [`out_of_range.413`](../../home/exceptions.md#jsonexceptionout_of_range413) and stopped silently ignoring a "remove" operation whose target
+  location has a non-object/non-array parent in version 3.13.0.
+- Added [`out_of_range.414`](../../home/exceptions.md#jsonexceptionout_of_range414) and rejected a "move" operation whose "from" location is a proper
+  prefix of its "path" location instead of silently producing a corrupted result in version 3.13.0.

docs/mkdocs/docs/examples/get__ValueType_const.output

@@ -4,8 +4,8 @@
 Hello, world!
 1 2 3 4 5 
 
-string: "Hello, world!"
 number: {"floating-point":17.23,"integer":42}
 null: null
+string: "Hello, world!"
 boolean: true
 array: [1,2,3,4,5]

docs/mkdocs/docs/examples/get_to.output

@@ -4,8 +4,8 @@
 Hello, world!
 1 2 3 4 5 
 
-string: "Hello, world!"
 number: {"floating-point":17.23,"integer":42}
 null: null
+string: "Hello, world!"
 boolean: true
 array: [1,2,3,4,5]

docs/mkdocs/docs/examples/operator__ValueType.output

@@ -4,9 +4,9 @@
 Hello, world!
 1 2 3 4 5 
 
-string: "Hello, world!"
 number: {"floating-point":17.23,"integer":42}
 null: null
+string: "Hello, world!"
 boolean: true
 array: [1,2,3,4,5]
 [json.exception.type_error.302] type must be boolean, but is string

docs/mkdocs/docs/home/exceptions.md

@@ -933,6 +933,34 @@ BSON stores the length of documents, arrays, strings, and binary values in a sig
     [`to_bson`](../api/basic_json/to_bson.md) produced documents with negative length prefixes that
     [`from_bson`](../api/basic_json/from_bson.md) rejected.
 
+### json.exception.out_of_range.413
+
+A JSON Patch `remove` operation cannot be applied because the target location's parent is neither an object nor an array. Per [RFC 6902](https://datatracker.ietf.org/doc/html/rfc6902), a `remove` target must reference a member of an existing object or an element of an existing array; a primitive value (string, number, boolean, etc.) or `null` has no members or elements to remove.
+
+!!! failure "Example message"
+
+    ```
+    cannot remove value: the JSON Patch 'remove' target's parent is of type number, but must be an object or array
+    ```
+
+!!! note
+
+    This exception was added in version 3.13.0. Before that, this situation was silently ignored (the `remove` operation had no effect).
+
+### json.exception.out_of_range.414
+
+A JSON Patch `move` operation's `"from"` location is a proper prefix of its `"path"` location. Per [RFC 6902](https://datatracker.ietf.org/doc/html/rfc6902) (section 4.4), a location cannot be moved into one of its own children.
+
+!!! failure "Example message"
+
+    ```
+    cannot move value: 'from' path '/0' is a proper prefix of 'path' '/0/0'
+    ```
+
+!!! note
+
+    This exception was added in version 3.13.0. Before that, this situation could succeed with a corrupted result: for an array target, removing the "from" element before the "add" step shifted subsequent indices, so "path" silently re-resolved to a different element than intended.
+
 ## Further exceptions
 
 This exception is thrown in case of errors that cannot be classified with the

include/nlohmann/detail/conversions/from_json.hpp

@@ -398,6 +398,17 @@ inline void from_json(const BasicJsonType& j, CompatibleArrayType& bin)
     }
 }
 
+template<typename ConstructibleObjectType>
+auto from_json_object_reserve(ConstructibleObjectType& obj, typename ConstructibleObjectType::size_type size, priority_tag<1> /*unused*/)
+-> decltype(obj.reserve(size), void())
+{
+    obj.reserve(size);
+}
+
+template<typename ConstructibleObjectType>
+inline void from_json_object_reserve(ConstructibleObjectType& /*obj*/, std::size_t /*size*/, priority_tag<0> /*unused*/)
+{}
+
 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)
@@ -409,6 +420,7 @@ inline void from_json(const BasicJsonType& j, ConstructibleObjectType& obj)
 
     ConstructibleObjectType ret;
     const auto* inner_object = j.template get_ptr<const typename BasicJsonType::object_t*>();
+    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>());

include/nlohmann/detail/conversions/to_chars.hpp

@@ -1075,8 +1075,8 @@ char* to_chars(char* first, const char* last, FloatType value)
     }
 
 #ifdef __GNUC__
-#pragma GCC diagnostic push
+    JSON_HEDLEY_DIAGNOSTIC_PUSH
-#pragma GCC diagnostic ignored "-Wfloat-equal"
+    JSON_HEDLEY_PRAGMA(GCC diagnostic ignored "-Wfloat-equal")
 #endif
     if (value == 0) // +-0
     {
@@ -1087,7 +1087,7 @@ char* to_chars(char* first, const char* last, FloatType value)
         return first;
     }
 #ifdef __GNUC__
-#pragma GCC diagnostic pop
+    JSON_HEDLEY_DIAGNOSTIC_POP
 #endif
 
     JSON_ASSERT(last - first >= std::numeric_limits<FloatType>::max_digits10);

include/nlohmann/detail/exceptions.hpp

@@ -33,8 +33,8 @@
 // code stumbling over this. See https://github.com/nlohmann/json/issues/4087
 // for a discussion.
 #if defined(__clang__)
-    #pragma clang diagnostic push
+    JSON_HEDLEY_DIAGNOSTIC_PUSH
-    #pragma clang diagnostic ignored "-Wweak-vtables"
+    JSON_HEDLEY_PRAGMA(clang diagnostic ignored "-Wweak-vtables")
 #endif
 
 NLOHMANN_JSON_NAMESPACE_BEGIN
@@ -287,5 +287,5 @@ class other_error : public exception
 NLOHMANN_JSON_NAMESPACE_END
 
 #if defined(__clang__)
-    #pragma clang diagnostic pop
+    JSON_HEDLEY_DIAGNOSTIC_POP
 #endif

include/nlohmann/detail/input/binary_reader.hpp

@@ -996,23 +996,21 @@ class binary_reader
     }
 
     /*!
-    @brief reads a CBOR string
+    @brief reads a definite-length CBOR string
 
-    This function first reads starting bytes to determine the expected
+    Reads everything @ref get_cbor_string accepts except the indefinite-length
-    string length and then copies this number of bytes into a string.
+    form, which that function handles itself. The bytes are appended to @a
-    Additionally, CBOR's strings with indefinite lengths are supported.
+    result, so consecutive chunks of an indefinite-length string can be read
+    into the same string.
 
-    @param[out] result  created string
+    @param[out] result  string the bytes are appended to
 
     @return whether string creation completed
-    */
-    bool get_cbor_string(string_t& result)
-    {
-        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
-        {
-            return false;
-        }
 
+    @pre @a current is not EOF
+    */
+    bool get_cbor_string_chunk(string_t& result)
+    {
         switch (current)
         {
             // UTF-8 string (0x00..0x17 bytes follow)
@@ -1068,20 +1066,6 @@ class binary_reader
                 return get_number(input_format_t::cbor, len) && get_string(input_format_t::cbor, len, result);
             }
 
-            case 0x7F: // UTF-8 string (indefinite length)
-            {
-                while (get() != 0xFF)
-                {
-                    string_t chunk;
-                    if (!get_cbor_string(chunk))
-                    {
-                        return false;
-                    }
-                    result.append(chunk);
-                }
-                return true;
-            }
-
             default:
             {
                 auto last_token = get_token_string();
@@ -1092,23 +1076,82 @@ class binary_reader
     }
 
     /*!
-    @brief reads a CBOR byte array
+    @brief reads a CBOR string
 
     This function first reads starting bytes to determine the expected
-    byte array length and then copies this number of bytes into the byte array.
+    string length and then copies this number of bytes into a string.
-    Additionally, CBOR's byte arrays with indefinite lengths are supported.
+    Additionally, CBOR's strings with indefinite lengths are supported.
 
-    @param[out] result  created byte array
+    @param[out] result  created string
 
-    @return whether byte array creation completed
+    @return whether string creation completed
     */
-    bool get_cbor_binary(binary_t& result)
+    bool get_cbor_string(string_t& result)
     {
-        if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
+        // number of indefinite-length strings that have been opened and not
+        // closed yet. RFC 8949, Section 3.2.3 does not permit nesting them,
+        // but this reader has always accepted it, so the open levels are
+        // counted instead of recursed through, which overflowed the stack for
+        // an input of repeated 0x7F bytes (see #5104). Every chunk is appended
+        // to the same result, so no per-level state is needed.
+        std::size_t open = 0;
+
+        while (true)
+        {
+            if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "string")))
             {
                 return false;
             }
 
+            if (current == 0x7F) // UTF-8 string (indefinite length)
+            {
+                ++open;
+                get();
+                continue;
+            }
+
+            // a break marker closes the innermost indefinite-length string;
+            // outside of one it is not a string and falls through to the error
+            if (open != 0 && current == 0xFF)
+            {
+                if (--open == 0)
+                {
+                    return true;
+                }
+                get();
+                continue;
+            }
+
+            if (JSON_HEDLEY_UNLIKELY(!get_cbor_string_chunk(result)))
+            {
+                return false;
+            }
+
+            if (open == 0)
+            {
+                return true;
+            }
+
+            get();
+        }
+    }
+
+    /*!
+    @brief reads a definite-length CBOR byte array
+
+    Reads everything @ref get_cbor_binary accepts except the indefinite-length
+    form, which that function handles itself. The bytes are appended to @a
+    result, so consecutive chunks of an indefinite-length byte array can be
+    read into the same byte array.
+
+    @param[out] result  byte array the bytes are appended to
+
+    @return whether byte array creation completed
+
+    @pre @a current is not EOF
+    */
+    bool get_cbor_binary_chunk(binary_t& result)
+    {
         switch (current)
         {
             // Binary data (0x00..0x17 bytes follow)
@@ -1168,20 +1211,6 @@ class binary_reader
                        get_binary(input_format_t::cbor, len, result);
             }
 
-            case 0x5F: // Binary data (indefinite length)
-            {
-                while (get() != 0xFF)
-                {
-                    binary_t chunk;
-                    if (!get_cbor_binary(chunk))
-                    {
-                        return false;
-                    }
-                    result.insert(result.end(), chunk.begin(), chunk.end());
-                }
-                return true;
-            }
-
             default:
             {
                 auto last_token = get_token_string();
@@ -1191,6 +1220,63 @@ class binary_reader
         }
     }
 
+    /*!
+    @brief reads a CBOR byte array
+
+    This function first reads starting bytes to determine the expected
+    byte array length and then copies this number of bytes into the byte array.
+    Additionally, CBOR's byte arrays with indefinite lengths are supported.
+
+    @param[out] result  created byte array
+
+    @return whether byte array creation completed
+    */
+    bool get_cbor_binary(binary_t& result)
+    {
+        // the open indefinite-length byte arrays are counted rather than
+        // recursed through, for the reason given in @ref get_cbor_string
+        std::size_t open = 0;
+
+        while (true)
+        {
+            if (JSON_HEDLEY_UNLIKELY(!unexpect_eof(input_format_t::cbor, "binary")))
+            {
+                return false;
+            }
+
+            if (current == 0x5F) // Binary data (indefinite length)
+            {
+                ++open;
+                get();
+                continue;
+            }
+
+            // a break marker closes the innermost indefinite-length byte
+            // array; outside of one it falls through to the error below
+            if (open != 0 && current == 0xFF)
+            {
+                if (--open == 0)
+                {
+                    return true;
+                }
+                get();
+                continue;
+            }
+
+            if (JSON_HEDLEY_UNLIKELY(!get_cbor_binary_chunk(result)))
+            {
+                return false;
+            }
+
+            if (open == 0)
+            {
+                return true;
+            }
+
+            get();
+        }
+    }
+
     /*!
     @brief narrow a definite CBOR array/map length to std::size_t
 
@@ -2391,7 +2477,12 @@ class binary_reader
     {
         result.first = npos; // size
         result.second = 0; // type
-        bool is_ndarray = false;
+        // seed the flag with the caller's context: inside an ndarray dimension
+        // vector another ndarray is not allowed, and get_ubjson_size_value()
+        // rejects it up front instead of reading it and reporting afterwards.
+        // Seeding it with `false` made every '#' of a "[#[#[..." chain descend
+        // another level, which overflowed the stack (see #5104).
+        bool is_ndarray = inside_ndarray;
 
         get_ignore_noop();
 
@@ -2424,13 +2515,11 @@ class binary_reader
             }
 
             const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
-            if (input_format == input_format_t::bjdata && is_ndarray)
+            // an ndarray was read here only if the flag flipped; when it was
+            // seeded true, get_ubjson_size_value() already rejected the nested
+            // dimension vector
+            if (input_format == input_format_t::bjdata && is_ndarray && !inside_ndarray)
             {
-                if (inside_ndarray)
-                {
-                    return sax->parse_error(chars_read, get_token_string(), parse_error::create(112, chars_read,
-                                            exception_message(input_format, "ndarray can not be recursive", "size"), nullptr));
-                }
                 result.second |= (1 << 8); // use bit 8 to indicate ndarray, all UBJSON and BJData markers should be ASCII letters
             }
             return is_error;
@@ -2439,7 +2528,7 @@ class binary_reader
         if (current == '#')
         {
             const bool is_error = get_ubjson_size_value(result.first, is_ndarray);
-            if (input_format == input_format_t::bjdata && 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(input_format, "ndarray requires both type and size", "size"), nullptr));

include/nlohmann/detail/input/json_sax.hpp

@@ -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>
@@ -250,7 +249,7 @@ class json_sax_dom_parser
 
         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()));
+            JSON_THROW(out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
         }
 
         return true;
@@ -299,7 +298,7 @@ class json_sax_dom_parser
 
         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 array size: ", std::to_string(len)), ref_stack.back()));
+            JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
         }
 
         return true;
@@ -569,7 +568,7 @@ class json_sax_dom_callback_parser
             // 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()));
+                JSON_THROW(out_of_range::create(408, concat("excessive object size: ", std::to_string(len)), ref_stack.back()));
             }
         }
         return true;
@@ -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;
+            object_element = &(ref_stack.back()->m_data.m_value.object->operator[](val) = discarded);
-            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);
         }
 
         return true;
@@ -608,11 +597,7 @@ 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
+                // discard object
-                // 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;
 
 #if JSON_DIAGNOSTIC_POSITIONS
@@ -620,7 +605,6 @@ class json_sax_dom_callback_parser
                 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);
             }
         }
 
@@ -679,7 +659,7 @@ class json_sax_dom_callback_parser
             // check array 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 array size: ", std::to_string(len)), ref_stack.back()));
+                JSON_THROW(out_of_range::create(408, concat("excessive array size: ", std::to_string(len)), ref_stack.back()));
             }
         }
 
@@ -706,18 +686,10 @@ 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
+                // discard array
-                // 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;
 
 #if JSON_DIAGNOSTIC_POSITIONS
@@ -726,7 +698,6 @@ class json_sax_dom_callback_parser
 #endif
             }
         }
-        }
 
         JSON_ASSERT(!ref_stack.empty());
         JSON_ASSERT(!keep_stack.empty());
@@ -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 the discarded value the callback rejected from its parent
-    /// remove it from the stash; if restore_value is true, the stashed
+    static void remove_discarded_value(BasicJsonType& parent)
-    /// 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)
     {
         for (auto it = parent.begin(); it != parent.end(); ++it)
         {
             if (it->is_discarded())
-            {
-                if (!resolve_duplicate_key_stash(&(*it), true))
             {
                 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

include/nlohmann/detail/input/lexer.hpp

@@ -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;
 
@@ -1393,8 +1446,7 @@ scan_number_done:
     */
     char_int_type get()
     {
-        ++position.chars_read_total;
+        advance_position();
-        ++position.chars_read_current_line;
 
         if (next_unget)
         {
@@ -1406,6 +1458,23 @@ scan_number_done:
             current = ia.get_character();
         }
 
+        return track_after_read();
+    }
+
+    /// shared head of get() / get_ignoring_pending_unget(): bump the
+    /// per-character position counters (line-count-on-'\n' bookkeeping is
+    /// handled afterwards, in track_after_read(), once `current` is known)
+    void advance_position() noexcept
+    {
+        ++position.chars_read_total;
+        ++position.chars_read_current_line;
+    }
+
+    /// shared tail of get() / get_ignoring_pending_unget(): capture the
+    /// character for error messages (if needed) and update line/column
+    /// bookkeeping for the character now in `current`
+    char_int_type track_after_read()
+    {
         // 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> {});
@@ -1419,6 +1488,29 @@ scan_number_done:
         return current;
     }
 
+    /*!
+    @brief like get(), but for call sites that can prove no unget() is pending
+
+    get() has to check the `next_unget` flag on every call, because a
+    previous token may have ended with unget() (e.g. scan_number() always
+    ungets the character that terminated the number, so the next call to
+    scan() can see it again). skip_whitespace() reads that first,
+    possibly-ungotten character via a plain get(), but every further
+    character it reads is guaranteed to be a fresh read: nothing between
+    those calls invokes unget(). This variant skips the (otherwise always
+    false) next_unget branch for those calls; it is not a general
+    replacement for get().
+    */
+    char_int_type get_ignoring_pending_unget()
+    {
+        JSON_ASSERT(!next_unget);
+
+        advance_position();
+        current = ia.get_character();
+
+        return track_after_read();
+    }
+
     /// seekable adapter: nothing to capture, the token is rebuilt on error
     void capture_char(std::true_type /*lazy*/) const noexcept {}
 
@@ -1612,13 +1704,37 @@ scan_number_done:
         return true;
     }
 
+    /// whether `current` is one of the four JSON whitespace characters
+    bool current_is_whitespace() const noexcept
+    {
+        return current == ' ' || current == '\t' || current == '\n' || current == '\r';
+    }
+
     void skip_whitespace()
     {
+        // the first character may be a pending unget() left over from the
+        // previous token (see get_ignoring_pending_unget()); every
+        // subsequent character read by this loop is guaranteed fresh, since
+        // nothing below calls unget()
+        get();
+
+        if (!current_is_whitespace())
+        {
+            return;
+        }
+
+        // this is written as an if-guarded do-while (rather than a plain
+        // while loop) because that shape is what lets both GCC and Clang
+        // keep the input adapter's read pointer in a register across
+        // iterations; the equivalent while-loop measurably defeated that
+        // optimization in testing, turning long whitespace runs (e.g. the
+        // indentation of pretty-printed JSON) from a register-only loop
+        // into one that reloads the pointer from memory every character
         do
         {
-            get();
+            get_ignoring_pending_unget();
         }
-        while (current == ' ' || current == '\t' || current == '\n' || current == '\r');
+        while (current_is_whitespace());
     }
 
     token_type scan()
@@ -1754,6 +1870,13 @@ 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

include/nlohmann/detail/input/parser.hpp

@@ -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_)
     {

include/nlohmann/detail/iterators/iteration_proxy.hpp

@@ -18,6 +18,7 @@
 #endif
 
 #include <nlohmann/detail/abi_macros.hpp>
+#include <nlohmann/detail/macro_scope.hpp>
 #include <nlohmann/detail/meta/type_traits.hpp>
 #include <nlohmann/detail/string_utils.hpp>
 #include <nlohmann/detail/value_t.hpp>
@@ -206,10 +207,10 @@ NLOHMANN_JSON_NAMESPACE_END
 namespace std
 {
 
-#if defined(__clang__)
 // Fix: https://github.com/nlohmann/json/issues/1401
-    #pragma clang diagnostic push
+#if defined(__clang__)
-    #pragma clang diagnostic ignored "-Wmismatched-tags"
+    JSON_HEDLEY_DIAGNOSTIC_PUSH
+    JSON_HEDLEY_PRAGMA(clang diagnostic ignored "-Wmismatched-tags")
 #endif
 template<typename IteratorType>
 class tuple_size<::nlohmann::detail::iteration_proxy_value<IteratorType>> // NOLINT(cert-dcl58-cpp)
@@ -224,7 +225,7 @@ class tuple_element<N, ::nlohmann::detail::iteration_proxy_value<IteratorType >>
                             ::nlohmann::detail::iteration_proxy_value<IteratorType >> ()));
 };
 #if defined(__clang__)
-    #pragma clang diagnostic pop
+    JSON_HEDLEY_DIAGNOSTIC_POP
 #endif
 
 }  // namespace std

include/nlohmann/detail/json_pointer.hpp

@@ -748,6 +748,20 @@ class json_pointer
                         }
                     }
 
+                    // the reference token consists only of digits at this point (cf. checks
+                    // above); however, its numeric value might not be representable, in which
+                    // case array_index() would throw out_of_range.404/410 -- contains() must
+                    // not throw (see #5395), so such a reference token is treated as "not found"
+                    errno = 0; // strtoull() does not reset errno on success
+                    char* p_end = nullptr; // NOLINT(misc-const-correctness)
+                    const unsigned long long magnitude = std::strtoull(reference_token.c_str(), &p_end, 10); // NOLINT(runtime/int)
+                    if (JSON_HEDLEY_UNLIKELY(errno == ERANGE // the value exceeds ULLONG_MAX
+                                             || magnitude >= static_cast<unsigned long long>((std::numeric_limits<typename BasicJsonType::size_type>::max)()))) // NOLINT(runtime/int)
+                    {
+                        // the array index cannot be represented as size_type
+                        return false;
+                    }
+
                     const auto idx = array_index<BasicJsonType>(reference_token);
                     if (idx >= ptr->size())
                     {

include/nlohmann/detail/output/binary_writer.hpp

@@ -1850,8 +1850,8 @@ class binary_writer
     void write_compact_float(const number_float_t n, detail::input_format_t format)
     {
 #ifdef __GNUC__
-#pragma GCC diagnostic push
+        JSON_HEDLEY_DIAGNOSTIC_PUSH
-#pragma GCC diagnostic ignored "-Wfloat-equal"
+        JSON_HEDLEY_PRAGMA(GCC diagnostic ignored "-Wfloat-equal")
 #endif
         if (!std::isfinite(n) || ((static_cast<double>(n) >= static_cast<double>(std::numeric_limits<float>::lowest()) &&
                                    static_cast<double>(n) <= static_cast<double>((std::numeric_limits<float>::max)()) &&
@@ -1870,7 +1870,7 @@ class binary_writer
             write_number(n);
         }
 #ifdef __GNUC__
-#pragma GCC diagnostic pop
+        JSON_HEDLEY_DIAGNOSTIC_POP
 #endif
     }
 

include/nlohmann/json.hpp

@@ -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:
@@ -1335,6 +1336,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief serialization
     /// @sa https://json.nlohmann.me/api/basic_json/dump/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     string_t dump(const int indent = -1,
                   const char indent_char = ' ',
                   const bool ensure_ascii = false,
@@ -1357,6 +1359,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return the type of the JSON value (explicit)
     /// @sa https://json.nlohmann.me/api/basic_json/type/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr value_t type() const noexcept
     {
         return m_data.m_type;
@@ -1364,6 +1367,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return whether type is primitive
     /// @sa https://json.nlohmann.me/api/basic_json/is_primitive/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr bool is_primitive() const noexcept
     {
         return is_null() || is_string() || is_boolean() || is_number() || is_binary();
@@ -1371,6 +1375,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return whether type is structured
     /// @sa https://json.nlohmann.me/api/basic_json/is_structured/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr bool is_structured() const noexcept
     {
         return is_array() || is_object();
@@ -1378,6 +1383,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return whether value is null
     /// @sa https://json.nlohmann.me/api/basic_json/is_null/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr bool is_null() const noexcept
     {
         return m_data.m_type == value_t::null;
@@ -1385,6 +1391,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return whether value is a boolean
     /// @sa https://json.nlohmann.me/api/basic_json/is_boolean/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr bool is_boolean() const noexcept
     {
         return m_data.m_type == value_t::boolean;
@@ -1392,6 +1399,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return whether value is a number
     /// @sa https://json.nlohmann.me/api/basic_json/is_number/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr bool is_number() const noexcept
     {
         return is_number_integer() || is_number_float();
@@ -1399,6 +1407,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return whether value is an integer number
     /// @sa https://json.nlohmann.me/api/basic_json/is_number_integer/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr bool is_number_integer() const noexcept
     {
         return m_data.m_type == value_t::number_integer || m_data.m_type == value_t::number_unsigned;
@@ -1406,6 +1415,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return whether value is an unsigned integer number
     /// @sa https://json.nlohmann.me/api/basic_json/is_number_unsigned/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr bool is_number_unsigned() const noexcept
     {
         return m_data.m_type == value_t::number_unsigned;
@@ -1413,6 +1423,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return whether value is a floating-point number
     /// @sa https://json.nlohmann.me/api/basic_json/is_number_float/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr bool is_number_float() const noexcept
     {
         return m_data.m_type == value_t::number_float;
@@ -1420,6 +1431,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return whether value is an object
     /// @sa https://json.nlohmann.me/api/basic_json/is_object/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr bool is_object() const noexcept
     {
         return m_data.m_type == value_t::object;
@@ -1427,6 +1439,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return whether value is an array
     /// @sa https://json.nlohmann.me/api/basic_json/is_array/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr bool is_array() const noexcept
     {
         return m_data.m_type == value_t::array;
@@ -1434,6 +1447,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return whether value is a string
     /// @sa https://json.nlohmann.me/api/basic_json/is_string/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr bool is_string() const noexcept
     {
         return m_data.m_type == value_t::string;
@@ -1441,6 +1455,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return whether value is a binary array
     /// @sa https://json.nlohmann.me/api/basic_json/is_binary/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr bool is_binary() const noexcept
     {
         return m_data.m_type == value_t::binary;
@@ -1448,6 +1463,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return whether value is discarded
     /// @sa https://json.nlohmann.me/api/basic_json/is_discarded/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     constexpr bool is_discarded() const noexcept
     {
         return m_data.m_type == value_t::discarded;
@@ -2779,6 +2795,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief returns the number of occurrences of a key in a JSON object
     /// @sa https://json.nlohmann.me/api/basic_json/count/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     size_type count(const typename object_t::key_type& key) const
     {
         // return 0 for all nonobject types
@@ -2789,6 +2806,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     /// @sa https://json.nlohmann.me/api/basic_json/count/
     template<class KeyType, detail::enable_if_t<
                  detail::is_usable_as_basic_json_key_type<basic_json_t, KeyType>::value, int> = 0>
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     size_type count(KeyType && key) const
     {
         // return 0 for all nonobject types
@@ -2797,6 +2815,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief check the existence of an element in a JSON object
     /// @sa https://json.nlohmann.me/api/basic_json/contains/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     bool contains(const typename object_t::key_type& key) const
     {
         return is_object() && m_data.m_value.object->find(key) != m_data.m_value.object->end();
@@ -2806,6 +2825,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     /// @sa https://json.nlohmann.me/api/basic_json/contains/
     template<class KeyType, detail::enable_if_t<
                  detail::is_usable_as_basic_json_key_type<basic_json_t, KeyType>::value, int> = 0>
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     bool contains(KeyType && key) const
     {
         return is_object() && m_data.m_value.object->find(std::forward<KeyType>(key)) != m_data.m_value.object->end();
@@ -2813,12 +2833,14 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief check the existence of an element in a JSON object given a JSON pointer
     /// @sa https://json.nlohmann.me/api/basic_json/contains/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     bool contains(const json_pointer& ptr) const
     {
         return ptr.contains(this);
     }
 
     template<typename BasicJsonType, detail::enable_if_t<detail::is_basic_json<BasicJsonType>::value, int> = 0>
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     JSON_HEDLEY_DEPRECATED_FOR(3.11.0, basic_json::json_pointer or nlohmann::json_pointer<basic_json::string_t>) // NOLINT(readability/alt_tokens)
     bool contains(const typename ::nlohmann::json_pointer<BasicJsonType>& ptr) const
     {
@@ -2974,6 +2996,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief checks whether the container is empty.
     /// @sa https://json.nlohmann.me/api/basic_json/empty/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     bool empty() const noexcept
     {
         switch (m_data.m_type)
@@ -3013,6 +3036,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief returns the number of elements
     /// @sa https://json.nlohmann.me/api/basic_json/size/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     size_type size() const noexcept
     {
         switch (m_data.m_type)
@@ -3052,6 +3076,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief returns the maximum possible number of elements
     /// @sa https://json.nlohmann.me/api/basic_json/max_size/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     size_type max_size() const noexcept
     {
         switch (m_data.m_type)
@@ -3425,12 +3450,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
             JSON_THROW(invalid_iterator::create(211, "passed iterators may not belong to container", this));
         }
 
-        // passed iterators must belong to arrays
-        if (JSON_HEDLEY_UNLIKELY(!first.m_object->is_array()))
-        {
-            JSON_THROW(invalid_iterator::create(202, "iterators first and last must point to arrays", this));
-        }
-
         // insert to array and return iterator
         return insert_iterator(pos, first.m_it.array_iterator, last.m_it.array_iterator);
     }
@@ -3579,7 +3598,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         {
             using std::swap;
             swap(*(m_data.m_value.array), other);
-            set_parents();
         }
         else
         {
@@ -3596,7 +3614,6 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         {
             using std::swap;
             swap(*(m_data.m_value.object), other);
-            set_parents();
         }
         else
         {
@@ -3778,13 +3795,13 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     bool operator==(const_reference rhs) const noexcept
     {
 #ifdef __GNUC__
-#pragma GCC diagnostic push
+        JSON_HEDLEY_DIAGNOSTIC_PUSH
-#pragma GCC diagnostic ignored "-Wfloat-equal"
+        JSON_HEDLEY_PRAGMA(GCC diagnostic ignored "-Wfloat-equal")
 #endif
         const_reference lhs = *this;
         JSON_IMPLEMENT_OPERATOR( ==, true, false, false)
 #ifdef __GNUC__
-#pragma GCC diagnostic pop
+        JSON_HEDLEY_DIAGNOSTIC_POP
 #endif
     }
 
@@ -3871,12 +3888,12 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     friend bool operator==(const_reference lhs, const_reference rhs) noexcept
     {
 #ifdef __GNUC__
-#pragma GCC diagnostic push
+        JSON_HEDLEY_DIAGNOSTIC_PUSH
-#pragma GCC diagnostic ignored "-Wfloat-equal"
+        JSON_HEDLEY_PRAGMA(GCC diagnostic ignored "-Wfloat-equal")
 #endif
         JSON_IMPLEMENT_OPERATOR( ==, true, false, false)
 #ifdef __GNUC__
-#pragma GCC diagnostic pop
+        JSON_HEDLEY_DIAGNOSTIC_POP
 #endif
     }
 
@@ -4137,22 +4154,24 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
     /// @brief check if the input is valid JSON
     /// @sa https://json.nlohmann.me/api/basic_json/accept/
     template<typename InputType>
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     static bool accept(InputType&& i,
                        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)
     /// @sa https://json.nlohmann.me/api/basic_json/accept/
     template<typename IteratorType, typename SentinelType = IteratorType,
              detail::enable_if_t<detail::can_compare_ne<IteratorType, SentinelType>::value, int> = 0>
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     static bool accept(IteratorType first, SentinelType last,
                        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
@@ -4161,7 +4180,7 @@ 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
@@ -4247,6 +4266,7 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
     /// @brief return the type as string
     /// @sa https://json.nlohmann.me/api/basic_json/type_name/
+    JSON_HEDLEY_WARN_UNUSED_RESULT
     JSON_HEDLEY_RETURNS_NON_NULL
     const char* type_name() const noexcept
     {
@@ -4481,8 +4501,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in CBOR format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4498,8 +4521,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     template<typename T>
@@ -4524,8 +4550,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::cbor).sax_parse(input_format_t::cbor, &sdp, strict, tag_handler)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in MessagePack format
@@ -4539,8 +4568,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in MessagePack format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4555,8 +4587,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     template<typename T>
@@ -4579,8 +4614,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::msgpack).sax_parse(input_format_t::msgpack, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in UBJSON format
@@ -4594,8 +4632,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in UBJSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4610,8 +4651,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     template<typename T>
@@ -4634,8 +4678,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::ubjson).sax_parse(input_format_t::ubjson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in BJData format
@@ -4649,8 +4696,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in BJData format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4665,8 +4715,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bjdata).sax_parse(input_format_t::bjdata, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in BSON format
@@ -4680,8 +4733,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::forward<InputType>(i));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     /// @brief create a JSON value from an input in BSON format (iterator pair, or iterator+sentinel pair for C++20 ranges support)
@@ -4696,8 +4752,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         basic_json result;
         auto ia = detail::input_adapter(std::move(first), std::move(last));
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
 
     template<typename T>
@@ -4720,8 +4779,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
         auto ia = i.get();
         detail::json_sax_dom_parser<basic_json, decltype(ia)> sdp(result, allow_exceptions);
         // NOLINTNEXTLINE(hicpp-move-const-arg,performance-move-const-arg)
-        const bool res = binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict); // cppcheck-suppress[accessMoved]
+        if (!binary_reader<decltype(ia)>(std::move(ia), input_format_t::bson).sax_parse(input_format_t::bson, &sdp, strict)) // cppcheck-suppress[accessMoved]
-        return res ? result : basic_json(value_t::discarded);
+        {
+            result = value_t::discarded;
+        }
+        return result;
     }
     /// @}
 
@@ -4947,6 +5009,36 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                 // note erase performs range check
                 parent.erase(json_pointer::template array_index<basic_json_t>(last_path));
             }
+            else
+            {
+                // the parent of a "remove" target must be an object or array
+                // (see #5396)
+                JSON_THROW(out_of_range::create(413, detail::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));
+            }
+        };
+
+        // RFC 6902 (section 4.4) forbids "from" from being a proper prefix
+        // of "path" for a "move" operation: a location cannot be moved into
+        // one of its own children. Compares reference tokens (already
+        // unescaped by json_pointer's parser) rather than the raw pointer
+        // strings, since a token may itself contain an escaped '/' or '~'
+        // that would defeat a naive string-prefix comparison. "from" equal
+        // to "path" is *not* a proper prefix and must return false.
+        const auto is_proper_prefix = [](const json_pointer & from, const json_pointer & to)
+        {
+            const auto from_size = from.reference_tokens.size();
+            if (from_size >= to.reference_tokens.size())
+            {
+                return false;
+            }
+            for (std::size_t i = 0; i < from_size; ++i)
+            {
+                if (!(from.reference_tokens[i] == to.reference_tokens[i]))
+                {
+                    return false;
+                }
+            }
+            return true;
         };
 
         // type check: top level value must be an array
@@ -5024,6 +5116,11 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
                     const auto from_path = get_value("move", "from", true).template get<string_t>();
                     json_pointer from_ptr(from_path);
 
+                    if (JSON_HEDLEY_UNLIKELY(is_proper_prefix(from_ptr, ptr)))
+                    {
+                        JSON_THROW(out_of_range::create(414, detail::concat("cannot move value: 'from' path '", from_path, "' is a proper prefix of 'path' '", path, "'"), &result));
+                    }
+
                     // the "from" location must exist - use at()
                     basic_json const v = result.at(from_ptr);
 
@@ -5165,139 +5262,34 @@ class basic_json // NOLINT(cppcoreguidelines-special-member-functions,hicpp-spec
 
             case value_t::object:
             {
-                // first pass: record, for every source key, whether it is
+                // first pass: traverse this object's elements
-                // 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;
                 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());
+                        // 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
+                    {
+                        // found a key that is not in o -> remove it
+                        result.push_back(object(
+                        {
+                            {"op", "remove"}, {"path", path_key}
+                        }));
                     }
                 }
 
-                // second pass: find keys that were added (i.e., in target but
+                // second pass: traverse other object's elements
-                // 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;
+                        // found a key that is not in this -> add it
-                        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()}
-                        });
-                    }
-                    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()));
-                        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)
-                    {
                         const auto path_key = detail::concat<string_t>(path, '/', detail::escape(it.key()));
                         result.push_back(
                         {

include/nlohmann/thirdparty/hedley/hedley_undef.hpp

@@ -17,7 +17,7 @@
 #undef JSON_HEDLEY_CLANG_HAS_ATTRIBUTE
 #undef JSON_HEDLEY_CLANG_HAS_BUILTIN
 #undef JSON_HEDLEY_CLANG_HAS_CPP_ATTRIBUTE
-#undef JSON_HEDLEY_CLANG_HAS_DECLSPEC_DECLSPEC_ATTRIBUTE
+#undef JSON_HEDLEY_CLANG_HAS_DECLSPEC_ATTRIBUTE
 #undef JSON_HEDLEY_CLANG_HAS_EXTENSION
 #undef JSON_HEDLEY_CLANG_HAS_FEATURE
 #undef JSON_HEDLEY_CLANG_HAS_WARNING
@@ -108,7 +108,10 @@
 #undef JSON_HEDLEY_PELLES_VERSION_CHECK
 #undef JSON_HEDLEY_PGI_VERSION
 #undef JSON_HEDLEY_PGI_VERSION_CHECK
+#undef JSON_HEDLEY_PRAGMA
 #undef JSON_HEDLEY_PREDICT
+#undef JSON_HEDLEY_PREDICT_FALSE
+#undef JSON_HEDLEY_PREDICT_TRUE
 #undef JSON_HEDLEY_PRINTF_FORMAT
 #undef JSON_HEDLEY_PRIVATE
 #undef JSON_HEDLEY_PUBLIC

tests/CMakeLists.txt

@@ -125,6 +125,51 @@ json_test_set_test_options(test-unicode4 TEST_PROPERTIES TIMEOUT 3000)
 # add unit tests
 #############################################################################
 
+# Generate the leak checks for every JSON_HEDLEY_* macro defined in
+# hedley.hpp; tests/src/unit-no-macro-leak.cpp #include-s the result after
+# nlohmann/json.hpp (see issue #5408). Using the shared
+# cmake/scripts/gen_hedley_undef_check.cmake script (also used by `make
+# update_hedley_undef`) instead of a hand-maintained list of macro names
+# means this test can never go stale after a future `make update_hedley`.
+set(hedley_hpp "${PROJECT_SOURCE_DIR}/include/nlohmann/thirdparty/hedley/hedley.hpp")
+set(hedley_undef_check_script "${PROJECT_SOURCE_DIR}/cmake/scripts/gen_hedley_undef_check.cmake")
+set(hedley_undef_checks "${PROJECT_BINARY_DIR}/include/hedley_undef_checks.inc")
+
+# Reconfigure whenever the vendored header or the generator script changes,
+# so a `cmake --build` after `make update_hedley` does not silently keep a
+# stale generated file around.
+set_property(DIRECTORY APPEND PROPERTY CMAKE_CONFIGURE_DEPENDS
+    "${hedley_hpp}"
+    "${hedley_undef_check_script}")
+
+# Generate once at configure time, so the very first build (before any
+# custom-command build step has run) already has an up-to-date file.
+execute_process(
+    COMMAND ${CMAKE_COMMAND}
+        "-DHEDLEY_HPP=${hedley_hpp}"
+        "-DOUTPUT=${hedley_undef_checks}"
+        -DMODE=checks
+        -P "${hedley_undef_check_script}"
+    RESULT_VARIABLE hedley_undef_check_result
+)
+if(NOT hedley_undef_check_result EQUAL 0)
+    message(FATAL_ERROR "Failed to generate ${hedley_undef_checks}")
+endif()
+
+# Also (re)generate as a build step, so an incremental build after editing
+# hedley.hpp without a full reconfigure still picks up the change.
+add_custom_command(
+    OUTPUT "${hedley_undef_checks}"
+    COMMAND ${CMAKE_COMMAND}
+        "-DHEDLEY_HPP=${hedley_hpp}"
+        "-DOUTPUT=${hedley_undef_checks}"
+        -DMODE=checks
+        -P "${hedley_undef_check_script}"
+    DEPENDS "${hedley_hpp}" "${hedley_undef_check_script}"
+    COMMENT "Generating Hedley undef leak checks"
+    VERBATIM)
+add_custom_target(generate_hedley_undef_checks DEPENDS "${hedley_undef_checks}")
+
 if("${JSON_TestStandards}" STREQUAL "")
     set(test_cxx_standards 11 14 17 20 23)
     unset(test_force)
@@ -163,6 +208,14 @@ foreach(file ${files})
     json_test_add_test_for(${file} MAIN test_main CXX_STANDARDS ${test_cxx_standards} ${test_force})
 endforeach()
 
+# tests/src/unit-no-macro-leak.cpp #include-s the generated leak-check file,
+# so its test targets must be built after generate_hedley_undef_checks.
+foreach(cxx_standard ${test_cxx_standards})
+    if(TARGET test-no-macro-leak_cpp${cxx_standard})
+        add_dependencies(test-no-macro-leak_cpp${cxx_standard} generate_hedley_undef_checks)
+    endif()
+endforeach()
+
 if(json_32bit_test_only)
     # Skip all other tests in this file
     return()

tests/src/test_utils.hpp

@@ -15,6 +15,15 @@
 namespace utils
 {
 
+// Some tests intentionally discard the [[nodiscard]]/JSON_HEDLEY_WARN_UNUSED_RESULT
+// return value of a call they only make to exercise its side effects (e.g. checking
+// that it does not throw). A plain (void) cast on the call expression does not
+// suppress GCC's warning for functions using the GNU __attribute__((warn_unused_result))
+// form (as opposed to the C++17 [[nodiscard]] attribute) -- passing the value into an
+// ordinary function call does.
+template<typename T>
+inline void ignore_return_value(T&& /*unused*/) noexcept {}
+
 inline std::vector<std::uint8_t> read_binary_file(const std::string& filename)
 {
     std::ifstream file(filename, std::ios::binary);

tests/src/unit-bjdata.cpp

@@ -3288,8 +3288,10 @@ TEST_CASE("BJData")
             CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR1), "[json.exception.parse_error.113] parse error at byte 6: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
             CHECK(json::from_bjdata(vR1, true, false).is_discarded());
 
+            // a dimension vector that opens another one is rejected where the
+            // nested '[' is read, rather than after it has been descended into
             std::vector<uint8_t> const vR2 = {'[', '$', 'i', '#', '[', '#', '[', 'i', 1, ']', ']', 1};
-            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR2), "[json.exception.parse_error.113] parse error at byte 11: syntax error while parsing BJData size: expected length type specification (U, i, u, I, m, l, M, L) after '#'; last byte: 0x5D", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR2), "[json.exception.parse_error.113] parse error at byte 7: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
             CHECK(json::from_bjdata(vR2, true, false).is_discarded());
 
             std::vector<uint8_t> const vR3 = {'[', '#', '[', 'i', '2', 'i', 2, ']'};
@@ -3297,7 +3299,7 @@ TEST_CASE("BJData")
             CHECK(json::from_bjdata(vR3, true, false).is_discarded());
 
             std::vector<uint8_t> const vR4 = {'[', '$', 'i', '#', '[', '$', 'i', '#', '[', 'i', 1, ']', 1};
-            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR4), "[json.exception.parse_error.110] parse error at byte 14: syntax error while parsing BJData number: unexpected end of input", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR4), "[json.exception.parse_error.113] parse error at byte 9: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
             CHECK(json::from_bjdata(vR4, true, false).is_discarded());
 
             std::vector<uint8_t> const vR5 = {'[', '$', 'i', '#', '[', '[', '[', ']', ']', ']'};
@@ -3305,12 +3307,25 @@ TEST_CASE("BJData")
             CHECK(json::from_bjdata(vR5, true, false).is_discarded());
 
             std::vector<uint8_t> const vR6 = {'[', '$', 'i', '#', '[', '$', 'i', '#', '[', 'i', '2', 'i', 2, ']'};
-            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR6), "[json.exception.parse_error.112] parse error at byte 14: syntax error while parsing BJData size: ndarray can not be recursive", json::parse_error&);
+            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vR6), "[json.exception.parse_error.113] parse error at byte 9: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
             CHECK(json::from_bjdata(vR6, true, false).is_discarded());
 
             std::vector<uint8_t> const vH = {'[', 'H', '[', '#', '[', '$', 'i', '#', '[', 'i', '2', 'i', 2, ']'};
             CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vH), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
             CHECK(json::from_bjdata(vH, true, false).is_discarded());
+
+            // Every "#[" of this chain used to open another dimension vector
+            // and cost several stack frames before anything was rejected, so a
+            // long enough chain crashed the process (see #5104). The nested
+            // vector is refused where it is read, so the length is irrelevant.
+            std::vector<uint8_t> vRdeep = {'['};
+            for (std::size_t i = 0; i < 100000; ++i)
+            {
+                vRdeep.push_back('#');
+                vRdeep.push_back('[');
+            }
+            CHECK_THROWS_WITH_AS(_ = json::from_bjdata(vRdeep), "[json.exception.parse_error.113] parse error at byte 5: syntax error while parsing BJData size: ndarray dimensional vector is not allowed", json::parse_error&);
+            CHECK(json::from_bjdata(vRdeep, true, false).is_discarded());
         }
 
         SECTION("objects")

tests/src/unit-bson.cpp

@@ -38,6 +38,54 @@ class huge_binary_t : public std::vector<std::uint8_t>
 using huge_binary_json = nlohmann::basic_json <
                          std::map, std::vector, std::string, bool, std::int64_t, std::uint64_t,
                          double, std::allocator, nlohmann::adl_serializer, huge_binary_t, void >;
+
+// a string type that can be made to report a size beyond INT32_MAX without
+// allocating that much memory, so BSON length overflow can be tested for
+// strings and (embedded) documents as well, following the same idea as
+// huge_binary_t.
+//
+// Unlike huge_binary_t (which is only ever used as the BSON *value* type),
+// this type doubles as basic_json's StringType and is therefore also used
+// for *object keys* (e.g. "s" or "nested" below). Only the designated test
+// value is meant to lie about its size - if every huge_string_t (including
+// keys) reported a huge size, the running totals computed while walking the
+// BSON document (see calc_bson_object_size & friends in binary_writer.hpp)
+// would need more than 32 bits, and on platforms where std::size_t is only
+// 32 bits wide that arithmetic would silently wrap around, producing wrong
+// (or even unguarded) lengths. The fake size is therefore opt-in via
+// as_huge(), and plain strings - in particular object keys - keep reporting
+// their real, small size.
+class huge_string_t : public std::string
+{
+  public:
+    using std::string::string;
+    huge_string_t(const std::string& s) : std::string(s) {} // NOLINT(google-explicit-constructor,hicpp-explicit-conversions)
+
+    // returns a copy of @a s whose size() pretends to be huge
+    static huge_string_t as_huge(const std::string& s)
+    {
+        huge_string_t result(s);
+        result.pretend_huge = true;
+        return result;
+    }
+
+    size_type size() const noexcept
+    {
+        if (pretend_huge)
+        {
+            // one byte more than the BSON length field can represent
+            return static_cast<size_type>((std::numeric_limits<std::int32_t>::max)()) + 1;
+        }
+        return std::string::size();
+    }
+
+  private:
+    bool pretend_huge = false;
+};
+
+using huge_string_json = nlohmann::basic_json <
+                         std::map, std::vector, huge_string_t, bool, std::int64_t, std::uint64_t,
+                         double, std::allocator, nlohmann::adl_serializer, std::vector<std::uint8_t>, void >;
 } // namespace
 
 TEST_CASE("BSON")
@@ -104,6 +152,11 @@ TEST_CASE("BSON")
     }
 
     SECTION("lengths exceeding INT32_MAX cannot be serialized to BSON")
+    {
+        // out_of_range.412 is thrown from a single shared helper
+        // (to_bson_length) that guards the BSON length fields of binary
+        // values, strings, and (embedded) documents alike
+        SECTION("binary")
         {
             huge_binary_json j;
             j["b"] = huge_binary_json::binary(huge_binary_t{});
@@ -111,6 +164,27 @@ TEST_CASE("BSON")
             CHECK_THROWS_WITH_AS(huge_binary_json::to_bson(j), "[json.exception.out_of_range.412] BSON length 2147483661 exceeds maximum of 2147483647", huge_binary_json::out_of_range&);
         }
 
+        SECTION("string")
+        {
+            huge_string_json j;
+            j["s"] = huge_string_t::as_huge("value");
+
+            CHECK_THROWS_WITH_AS(huge_string_json::to_bson(j), "[json.exception.out_of_range.412] BSON length 2147483661 exceeds maximum of 2147483647", huge_string_json::out_of_range&);
+        }
+
+        SECTION("document")
+        {
+            // an oversized string nested one level deep makes the
+            // *embedded* document's own length exceed INT32_MAX as well
+            huge_string_json nested;
+            nested["s"] = huge_string_t::as_huge("value");
+            huge_string_json j;
+            j["nested"] = nested;
+
+            CHECK_THROWS_WITH_AS(huge_string_json::to_bson(j), "[json.exception.out_of_range.412] BSON length 2147483674 exceeds maximum of 2147483647", huge_string_json::out_of_range&);
+        }
+    }
+
     SECTION("string length must be at least 1")
     {
         // from https://bugs.chromium.org/p/oss-fuzz/issues/detail?id=11175
@@ -193,6 +267,23 @@ TEST_CASE("BSON")
             CHECK(json::from_bson(result, true, false) == j);
         }
 
+        SECTION("non-empty object with bool from a non-0/1 byte (lenient parsing)")
+        {
+            // documented lenient behavior (see gh-5333): any non-zero byte
+            // is accepted as `true`, not just 0x01
+            std::vector<std::uint8_t> const input =
+            {
+                0x0D, 0x00, 0x00, 0x00, // size (little endian)
+                0x08,               // entry: boolean
+                'e', 'n', 't', 'r', 'y', '\x00',
+                0x02,           // value = 0x02 (neither 0x00 nor 0x01)
+                0x00                    // end marker
+            };
+
+            const json expected = { { "entry", true } };
+            CHECK(json::from_bson(input) == expected);
+        }
+
         SECTION("non-empty object with double")
         {
             json const j =
@@ -499,6 +590,29 @@ TEST_CASE("BSON")
             CHECK(json::from_bson(result, true, false) == j);
         }
 
+        SECTION("array elements with non-conforming keys (lenient parsing)")
+        {
+            // documented lenient behavior (see gh-5333): BSON array element
+            // keys are not checked against the required decimal sequence
+            // "0", "1", "2", ... - elements are taken in encoded order
+            std::vector<std::uint8_t> const input =
+            {
+                0x26, 0x00, 0x00, 0x00, // size (little endian)
+                0x04, 'e', 'n', 't', 'r', 'y', '\x00', // entry: embedded array
+
+                0x1A, 0x00, 0x00, 0x00, // size (little endian)
+                0x10, '5', 0x00, 0x0A, 0x00, 0x00, 0x00, // key "5" (bogus)      -> 10
+                0x10, 'x', 0x00, 0x14, 0x00, 0x00, 0x00, // key "x" (non-numeric) -> 20
+                0x10, '1', 0x00, 0x1E, 0x00, 0x00, 0x00, // key "1" (out of order) -> 30
+                0x00, // end marker (embedded array)
+
+                0x00 // end marker
+            };
+
+            const json expected = { { "entry", json::array({10, 20, 30}) } };
+            CHECK(json::from_bson(input) == expected);
+        }
+
         SECTION("non-empty object with binary member")
         {
             const size_t N = 10;
@@ -594,6 +708,31 @@ TEST_CASE("BSON")
             CHECK(json::from_bson(result, true, false) == j);
         }
 
+        SECTION("binary member with subtype 0x02 (old binary) keeps its inner length prefix (lenient parsing)")
+        {
+            // documented lenient behavior (see gh-5333): the payload for
+            // binary subtype 0x02 ("old binary") is returned as-is,
+            // including its own inner 4-byte length prefix; it is not
+            // stripped or reinterpreted
+            std::vector<std::uint8_t> const input =
+            {
+                0x17, 0x00, 0x00, 0x00, // size (little endian)
+                0x05, 'e', 'n', 't', 'r', 'y', '\x00', // entry: binary
+
+                0x06, 0x00, 0x00, 0x00, // size of binary (little endian)
+                0x02, // "old binary" subtype
+                0x02, 0x00, 0x00, 0x00, // inner length prefix (part of the old-binary payload)
+                0x68, 0x69, // payload ('h', 'i')
+
+                0x00 // end marker
+            };
+
+            // the inner length prefix is part of the (unmodified) payload
+            const std::vector<std::uint8_t> expected_payload = {0x02, 0x00, 0x00, 0x00, 0x68, 0x69};
+            const json expected = { { "entry", json::binary(expected_payload, 0x02) } };
+            CHECK(json::from_bson(input) == expected);
+        }
+
         SECTION("Some more complex document")
         {
             json const j =

tests/src/unit-cbor.cpp

@@ -2035,6 +2035,58 @@ TEST_CASE("CBOR definite length equal to the indefinite-length sentinel")
     }
 }
 
+TEST_CASE("CBOR indefinite-length strings do not recurse per chunk")
+{
+    // Reading an indefinite-length string or byte array used to call itself
+    // once per chunk, so a payload of repeated 0x7F (or 0x5F) bytes exhausted
+    // the call stack before any of the input was rejected. The open levels are
+    // counted now, and the levels below prove the reader still reads the same
+    // values and reports the same errors at the same byte offsets.
+    json _;
+
+    SECTION("many open levels are reported, not crashed on")
+    {
+        const std::vector<uint8_t> input(200000, 0x7F);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 200001: syntax error while parsing CBOR string: unexpected end of input", json::parse_error&);
+        CHECK(json::from_cbor(input, true, false).is_discarded());
+    }
+
+    SECTION("many open levels are reported, not crashed on (binary)")
+    {
+        const std::vector<uint8_t> input(200000, 0x5F);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(input), "[json.exception.parse_error.110] parse error at byte 200001: syntax error while parsing CBOR binary: unexpected end of input", json::parse_error&);
+        CHECK(json::from_cbor(input, true, false).is_discarded());
+    }
+
+    SECTION("chunks are still concatenated")
+    {
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0xFF})) == json(""));
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x61, 0x61, 0xFF})) == json("a"));
+        // nested indefinite-length strings are concatenated across levels
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x61, 0x61, 0xFF, 0x61, 0x62, 0xFF})) == json("ab"));
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x7F, 0x61, 0x7A, 0xFF, 0xFF, 0xFF})) == json("z"));
+        CHECK(json::from_cbor(std::vector<uint8_t>({0xA1, 0x7F, 0x61, 0x61, 0xFF, 0x01})) == json({{"a", 1}}));
+    }
+
+    SECTION("chunks are still concatenated (binary)")
+    {
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x41, 0x61, 0xFF})) == json::binary({0x61}));
+        CHECK(json::from_cbor(std::vector<uint8_t>({0x5F, 0x5F, 0x41, 0x61, 0xFF, 0x41, 0x62, 0xFF})) == json::binary({0x61, 0x62}));
+    }
+
+    SECTION("a chunk that is not a string is still rejected")
+    {
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x7F, 0x7F, 0x00})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0x00", json::parse_error&);
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0x5F, 0x5F, 0x00})), "[json.exception.parse_error.113] parse error at byte 3: syntax error while parsing CBOR binary: expected length specification (0x40-0x5B) or indefinite binary array type (0x5F); last byte: 0x00", json::parse_error&);
+    }
+
+    SECTION("a break marker outside an indefinite-length string is not a string")
+    {
+        // 0xFF only closes a string that was opened; on its own it is not one
+        CHECK_THROWS_WITH_AS(_ = json::from_cbor(std::vector<uint8_t>({0xA1, 0xFF, 0x01})), "[json.exception.parse_error.113] parse error at byte 2: syntax error while parsing CBOR string: expected length specification (0x60-0x7B) or indefinite string type (0x7F); last byte: 0xFF", json::parse_error&);
+    }
+}
+
 TEST_CASE("CBOR roundtrips" * doctest::skip())
 {
     SECTION("input from flynn")

tests/src/unit-class_parser.cpp

@@ -23,6 +23,8 @@ using nlohmann::json;
 #include <utility>
 #include <vector>
 
+#include "test_utils.hpp"
+
 namespace
 {
 class SaxEventLogger
@@ -624,7 +626,8 @@ TEST_CASE("parser class")
             SECTION("overflow")
             {
                 // overflows during parsing yield an exception
-                CHECK_THROWS_WITH_AS(parser_helper("1.18973e+4932").empty(), "[json.exception.out_of_range.406] number overflow parsing '1.18973e+4932'", json::out_of_range&);
+                // empty() is nodiscard; the exception is thrown by parser_helper() itself, before empty() would run
+                CHECK_THROWS_WITH_AS(utils::ignore_return_value(parser_helper("1.18973e+4932").empty()), "[json.exception.out_of_range.406] number overflow parsing '1.18973e+4932'", json::out_of_range&);
             }
 
             SECTION("invalid numbers")
@@ -930,6 +933,98 @@ 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);
+                }
+            }
         }
     }
 
@@ -1394,6 +1489,71 @@ TEST_CASE("parser class")
         CHECK(accept_helper("\"\\uD80C\\uFFFF\"") == false);
     }
 
+#if !defined(JSON_NOEXCEPTION)
+    SECTION("issue #5412 - whitespace skipping bookkeeping (compact vs. pretty-printed)")
+    {
+        // lexer::skip_whitespace() reads its first character with get() (to
+        // honor a possibly pending unget() from the previous token) and every
+        // further whitespace character with get_ignoring_pending_unget() (a
+        // get() variant that skips the then-always-false next_unget check).
+        // This must not change the reported byte offset, line, or column of
+        // a syntax error, even when a long run of whitespace containing
+        // multiple newlines is skipped beforehand (as with pretty-printed
+        // input). The expected values below were captured from the
+        // unmodified do-while(get()) loop, so any regression that miscounts
+        // characters or newlines while skipping whitespace changes them.
+        const auto check_error = [](const std::string & input, std::size_t expected_byte,
+                                    const std::string & expected_what)
+        {
+            CAPTURE(input)
+            try
+            {
+                json _ = json::parse(input);
+                FAIL_CHECK("expected a parse_error, but parsing succeeded");
+            }
+            catch (const json::parse_error& e)
+            {
+                CHECK(e.byte == expected_byte);
+                CHECK(std::string(e.what()) == expected_what);
+            }
+        };
+
+        // a nested document, serialized both compactly and pretty-printed
+        // (dump(4)), each truncated right before the final closing '}' so
+        // that the parser hits EOF after skipping all of the (in the
+        // pretty-printed case, substantial) indentation whitespace
+        const json doc =
+        {
+            {"a", 1},
+            {"b", json::array({true, false, nullptr, "x"})},
+            {"c", json::object({{"d", 3.14}, {"e", json::array({1, 2, 3})}})}
+        };
+
+        const std::string compact = doc.dump();
+        const std::string pretty = doc.dump(4);
+
+        check_error(compact.substr(0, compact.size() - 1), 60,
+                    "[json.exception.parse_error.101] parse error at line 1, column 60: syntax error while parsing object - unexpected end of input; expected '}'");
+        check_error(pretty.substr(0, pretty.size() - 1), 193,
+                    "[json.exception.parse_error.101] parse error at line 17, column 1: syntax error while parsing object - unexpected end of input; expected '}'");
+
+        // an invalid token appearing after several indented, multi-line
+        // whitespace runs vs. the same document without any of that
+        // whitespace
+        check_error(R"({
+    "a": 1,
+    "b": [
+        true,
+        false
+    ],
+    "c": @
+})", 70,
+                    "[json.exception.parse_error.101] parse error at line 7, column 10: syntax error while parsing value - invalid literal; last read: '\"c\": @'");
+        check_error(R"({"a":1,"b":[true,false],"c":@})", 29,
+                    "[json.exception.parse_error.101] parse error at line 1, column 29: syntax error while parsing value - invalid literal; last read: '\"c\":@'");
+    }
+#endif
+
     SECTION("tests found by mutate++")
     {
         // test case to make sure no comma precedes the first key

tests/src/unit-class_parser_diagnostic_positions.cpp

@@ -22,6 +22,8 @@ using nlohmann::json;
 
 #include <valarray>
 
+#include "test_utils.hpp"
+
 namespace
 {
 class SaxEventLogger
@@ -629,7 +631,8 @@ TEST_CASE("parser class")
             SECTION("overflow")
             {
                 // overflows during parsing yield an exception
-                CHECK_THROWS_WITH_AS(parser_helper("1.18973e+4932").empty(), "[json.exception.out_of_range.406] number overflow parsing '1.18973e+4932'", json::out_of_range&);
+                // empty() is nodiscard; the exception is thrown by parser_helper() itself, before empty() would run
+                CHECK_THROWS_WITH_AS(utils::ignore_return_value(parser_helper("1.18973e+4932").empty()), "[json.exception.out_of_range.406] number overflow parsing '1.18973e+4932'", json::out_of_range&);
             }
 
             SECTION("invalid numbers")

tests/src/unit-conversions.cpp

@@ -1389,6 +1389,37 @@ TEST_CASE("value conversion")
                 // CHECK(m5["one"] == "eins");
             }
 
+            SECTION("reserve is called on containers that support it (#5406)")
+            {
+                // build a larger object so that a missing/incorrect reserve()
+                // call would be more likely to corrupt or drop elements
+                json j_large;
+                for (int i = 0; i < 100; ++i)
+                {
+                    j_large[std::to_string(i)] = i;
+                }
+
+                SECTION("std::unordered_map (supports reserve)")
+                {
+                    const auto m = j_large.get<std::unordered_map<std::string, int>>();
+                    CHECK(m.size() == 100);
+                    for (int i = 0; i < 100; ++i)
+                    {
+                        CHECK(m.at(std::to_string(i)) == i);
+                    }
+                }
+
+                SECTION("std::map (no reserve, fallback path)")
+                {
+                    const auto m = j_large.get<std::map<std::string, int>>();
+                    CHECK(m.size() == 100);
+                    for (int i = 0; i < 100; ++i)
+                    {
+                        CHECK(m.at(std::to_string(i)) == i);
+                    }
+                }
+            }
+
             SECTION("std::multimap")
             {
                 j1.get<std::multimap<std::string, int>>();

tests/src/unit-diagnostics.cpp

@@ -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);
-        }
-    }
 }
 

tests/src/unit-items-cpp17.cpp

@@ -0,0 +1,42 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  JSON for Modern C++ (supporting code)
+// |  |  |__   |  |  | | | |  version 3.12.0
+// |_____|_____|_____|_|___|  https://github.com/nlohmann/json
+//
+// SPDX-FileCopyrightText: 2013-2026 Niels Lohmann <https://nlohmann.me>
+// SPDX-License-Identifier: MIT
+
+// This file contains the C++17-only part of unit-items.cpp (structured
+// bindings support for json::items()). It is kept in a separate
+// translation unit so the (much larger) unit-items.cpp does not need to
+// be compiled a second time just for this one SECTION.
+
+#include "doctest_compatibility.h"
+
+#include <nlohmann/json.hpp>
+using nlohmann::json;
+
+#ifdef JSON_HAS_CPP_17
+#include <map>
+#include <string>
+
+TEST_CASE("items()")
+{
+    SECTION("object")
+    {
+        SECTION("structured bindings")
+        {
+            json j = { {"A", 1}, {"B", 2} };
+
+            std::map<std::string, int> m;
+
+            for (auto const&[key, value] : j.items())
+            {
+                m.emplace(key, value);
+            }
+
+            CHECK(j.get<decltype(m)>() == m);
+        }
+    }
+}
+#endif

tests/src/unit-items.cpp

@@ -862,22 +862,6 @@ TEST_CASE("items()")
 
             CHECK(counter == 3);
         }
-
-#ifdef JSON_HAS_CPP_17
-        SECTION("structured bindings")
-        {
-            json j = { {"A", 1}, {"B", 2} };
-
-            std::map<std::string, int> m;
-
-            for (auto const&[key, value] : j.items())
-            {
-                m.emplace(key, value);
-            }
-
-            CHECK(j.get<decltype(m)>() == m);
-        }
-#endif
     }
 
     SECTION("const object")

tests/src/unit-json_patch.cpp

@@ -1389,6 +1389,192 @@ TEST_CASE("JSON patch - add to a primitive parent (regression #4292)")
     }
 }
 
+TEST_CASE("JSON patch - remove with primitive or null parent (regression #5396)")
+{
+    // Regression test for https://github.com/nlohmann/json/issues/5396
+    //
+    // RFC 6902 (§4.2) requires the target location of a "remove" operation
+    // to exist. When the target's parent resolves to a primitive value or
+    // null, the operation must fail. Previously operation_remove silently
+    // did nothing in this case (neither the "is_object" nor the "is_array"
+    // branch matched, and there was no final "else"), so the patch appeared
+    // to succeed without changing the document. It now throws
+    // out_of_range.413.
+
+    SECTION("parent is a primitive (number)")
+    {
+        json const doc = {{"a", 1}};
+        json const patch = {{{"op", "remove"}, {"path", "/a/b"}}};
+#if JSON_DIAGNOSTICS
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.413] (/a) cannot remove value: the JSON Patch 'remove' target's parent is of type number, but must be an object or array", json::out_of_range&);
+#else
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.413] cannot remove value: the JSON Patch 'remove' target's parent is of type number, but must be an object or array", json::out_of_range&);
+#endif
+    }
+
+    SECTION("parent is a primitive (string)")
+    {
+        json const doc = {{"foo", {{"bar", "a string"}}}};
+        json const patch = {{{"op", "remove"}, {"path", "/foo/bar/baz"}}};
+#if JSON_DIAGNOSTICS
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.413] (/foo/bar) cannot remove value: the JSON Patch 'remove' target's parent is of type string, but must be an object or array", json::out_of_range&);
+#else
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.413] cannot remove value: the JSON Patch 'remove' target's parent is of type string, but must be an object or array", json::out_of_range&);
+#endif
+    }
+
+    SECTION("top-level document is null")
+    {
+        json const doc = nullptr;
+        json const patch = {{{"op", "remove"}, {"path", "/a"}}};
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.413] cannot remove value: the JSON Patch 'remove' target's parent is of type null, but must be an object or array", json::out_of_range&);
+    }
+
+    SECTION("legitimate removes still work")
+    {
+        // object member
+        json const doc1 = {{"a", 1}, {"b", 2}};
+        json const patch1 = {{{"op", "remove"}, {"path", "/a"}}};
+        CHECK(doc1.patch(patch1) == json({{"b", 2}}));
+
+        // array element
+        json const doc2 = R"([1, 2, 3])"_json;
+        json const patch2 = {{{"op", "remove"}, {"path", "/1"}}};
+        CHECK(doc2.patch(patch2) == R"([1, 3])"_json);
+    }
+}
+
+TEST_CASE("JSON patch - move where 'from' is a proper prefix of 'path' (regression #5397)")
+{
+    // Regression test for https://github.com/nlohmann/json/issues/5397
+    //
+    // RFC 6902 (§4.4) forbids "from" from being a proper prefix of "path"
+    // for a "move" operation: "a location cannot be moved into one of its
+    // children." "move" is implemented as remove-then-add; for an object
+    // target this happened to throw anyway as a side effect of the "add"
+    // step re-resolving through the now-removed parent, but for an array
+    // target the removal shifted subsequent indices, so "path" silently
+    // re-resolved to a different element and the operation "succeeded"
+    // with a corrupted result. It now throws out_of_range.414 for both
+    // object and array targets.
+
+    SECTION("array target (from the issue)")
+    {
+        json const doc = R"([[1,2],[3]])"_json;
+        json const patch = {{{"op", "move"}, {"from", "/0"}, {"path", "/0/0"}}};
+#if JSON_DIAGNOSTIC_POSITIONS
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.414] (bytes 0-11) cannot move value: 'from' path '/0' is a proper prefix of 'path' '/0/0'", json::out_of_range&);
+#else
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.414] cannot move value: 'from' path '/0' is a proper prefix of 'path' '/0/0'", json::out_of_range&);
+#endif
+    }
+
+    SECTION("object target")
+    {
+        json const doc = R"({"a": {"b": 1}})"_json;
+        json const patch = {{{"op", "move"}, {"from", "/a"}, {"path", "/a/b"}}};
+#if JSON_DIAGNOSTIC_POSITIONS
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.414] (bytes 0-15) cannot move value: 'from' path '/a' is a proper prefix of 'path' '/a/b'", json::out_of_range&);
+#else
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.414] cannot move value: 'from' path '/a' is a proper prefix of 'path' '/a/b'", json::out_of_range&);
+#endif
+    }
+
+    SECTION("from == path is not a proper prefix and must not be rejected")
+    {
+        // "from" equal to "path" is a no-op move; it is not a *proper*
+        // prefix relationship, so this new check must not reject it.
+        json const doc = R"({"a": 1, "b": 2})"_json;
+        json const patch = {{{"op", "move"}, {"from", "/a"}, {"path", "/a"}}};
+        CHECK(doc.patch(patch) == doc);
+    }
+
+    SECTION("raw string prefix that is not a pointer-token prefix must be allowed")
+    {
+        // "/ab" is a string-prefix of "/abc/x" as raw text, but "ab" and
+        // "abc" are different reference tokens, so this is NOT a
+        // pointer-token prefix relationship and the move must succeed.
+        // This is the key case proving the check compares tokens, not
+        // raw pointer text (a naive std::string prefix/rfind check on
+        // the undecoded pointer would wrongly reject this).
+        json const doc = R"({"ab": 1, "abc": {"x": 2}})"_json;
+        json const patch = {{{"op", "move"}, {"from", "/ab"}, {"path", "/abc/x"}}};
+        json const result = R"({"abc": {"x": 1}})"_json;
+        CHECK(doc.patch(patch) == result);
+    }
+
+    SECTION("escaped reference tokens are compared unescaped")
+    {
+        // "from" is the single token "a/b" (escaped as "a~1b"); "path"
+        // addresses member "x" of that same value, so "from" is a
+        // proper (token-level) prefix of "path" and must be rejected.
+        json const doc = R"({"a/b": {"x": 1}})"_json;
+        json const patch = {{{"op", "move"}, {"from", "/a~1b"}, {"path", "/a~1b/x"}}};
+#if JSON_DIAGNOSTIC_POSITIONS
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.414] (bytes 0-17) cannot move value: 'from' path '/a~1b' is a proper prefix of 'path' '/a~1b/x'", json::out_of_range&);
+#else
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.414] cannot move value: 'from' path '/a~1b' is a proper prefix of 'path' '/a~1b/x'", json::out_of_range&);
+#endif
+    }
+
+    SECTION("ordinary valid moves still work")
+    {
+        // unrelated top-level members
+        json const doc1 = R"({"a": 1, "b": 2})"_json;
+        json const patch1 = {{{"op", "move"}, {"from", "/a"}, {"path", "/c"}}};
+        CHECK(doc1.patch(patch1) == R"({"b": 2, "c": 1})"_json);
+
+        // sibling paths that share a textual prefix but are unrelated
+        json const doc2 = R"({"a": {"x": 1}, "b": {"y": 2}})"_json;
+        json const patch2 = {{{"op", "move"}, {"from", "/a/x"}, {"path", "/b/z"}}};
+        CHECK(doc2.patch(patch2) == R"({"a": {}, "b": {"y": 2, "z": 1}})"_json);
+
+        // "path" is a proper prefix of "from" (the reverse relationship,
+        // which RFC 6902 does not forbid)
+        json const doc3 = R"({"a": {"b": 1}})"_json;
+        json const patch3 = {{{"op", "move"}, {"from", "/a/b"}, {"path", "/a"}}};
+        CHECK(doc3.patch(patch3) == R"({"a": 1})"_json);
+    }
+
+    SECTION("root 'from' is a proper prefix of every non-root 'path'")
+    {
+        // the whole document is a proper prefix of any location inside it
+        json const doc = R"({"a": 1})"_json;
+        json const patch = {{{"op", "move"}, {"from", ""}, {"path", "/a"}}};
+#if JSON_DIAGNOSTIC_POSITIONS
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.414] (bytes 0-8) cannot move value: 'from' path '' is a proper prefix of 'path' '/a'", json::out_of_range&);
+#else
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.414] cannot move value: 'from' path '' is a proper prefix of 'path' '/a'", json::out_of_range&);
+#endif
+    }
+
+    SECTION("root 'path' is never a proper prefix violation for a non-root 'from'")
+    {
+        // the reverse of the above: moving a non-root location to the root
+        // is the "path is a prefix of from" relationship, which RFC 6902
+        // permits (already covered generally above; this pins the root
+        // case specifically, since root is the one path with no reference
+        // tokens at all)
+        json const doc = R"({"a": {"b": 1}})"_json;
+        json const patch = {{{"op", "move"}, {"from", "/a"}, {"path", ""}}};
+        CHECK(doc.patch(patch) == R"({"b": 1})"_json);
+    }
+
+    SECTION("the array-append token '-' is an ordinary child token")
+    {
+        // "-" (append-to-array) addresses a location *inside* the array,
+        // so "from" pointing at the array is still a proper prefix of
+        // "path" ending in "-" and must be rejected like any other child.
+        json const doc = R"({"a": [1, 2]})"_json;
+        json const patch = {{{"op", "move"}, {"from", "/a"}, {"path", "/a/-"}}};
+#if JSON_DIAGNOSTIC_POSITIONS
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.414] (bytes 0-13) cannot move value: 'from' path '/a' is a proper prefix of 'path' '/a/-'", json::out_of_range&);
+#else
+        CHECK_THROWS_WITH_AS(doc.patch(patch), "[json.exception.out_of_range.414] cannot move value: 'from' path '/a' is a proper prefix of 'path' '/a/-'", json::out_of_range&);
+#endif
+    }
+}
+
 TEST_CASE("JSON patch - diff emits array removals in descending index order")
 {
     SECTION("array shrunk to empty")

tests/src/unit-json_pointer.cpp

@@ -319,6 +319,44 @@ TEST_CASE("JSON pointers")
 
                 CHECK_THROWS_WITH_AS(j[jp] = 1, throw_msg.c_str(), json::out_of_range&);
                 CHECK_THROWS_WITH_AS(j_const[jp] == 1, throw_msg.c_str(), json::out_of_range&);
+
+                // #5395: contains() must not throw for a reference token that is a
+                // syntactically valid array index but numerically exceeds ULLONG_MAX
+                // (causing strtoull() to set errno to ERANGE) -- it should just report
+                // that the pointer does not resolve to an element
+                CHECK(!j.contains(jp));
+                CHECK(!j_const.contains(jp));
+            }
+
+            {
+                // #5395: same as above, but using the exact reproduction from the issue
+                json::json_pointer const jp("/99999999999999999999");
+                std::string const throw_msg = "[json.exception.out_of_range.404] unresolved reference token '99999999999999999999'";
+
+                CHECK_THROWS_WITH_AS(j[jp] = 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j_const[jp] == 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j.at(jp) = 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j_const.at(jp) == 1, throw_msg.c_str(), json::out_of_range&);
+
+                CHECK(!j.contains(jp));
+                CHECK(!j_const.contains(jp));
+            }
+
+            {
+                // #5395: a reference token that is numerically representable in
+                // unsigned long long but exceeds size_type's max (e.g. ULLONG_MAX
+                // itself on typical 64-bit platforms, where size_type's max equals
+                // ULLONG_MAX) must not make contains() throw either
+                json::json_pointer const jp("/18446744073709551615");
+                std::string const throw_msg = "[json.exception.out_of_range.410] array index 18446744073709551615 exceeds size_type";
+
+                CHECK_THROWS_WITH_AS(j[jp] = 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j_const[jp] == 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j.at(jp) = 1, throw_msg.c_str(), json::out_of_range&);
+                CHECK_THROWS_WITH_AS(j_const.at(jp) == 1, throw_msg.c_str(), json::out_of_range&);
+
+                CHECK(!j.contains(jp));
+                CHECK(!j_const.contains(jp));
             }
 
             // on some machines, the check below is not constant
@@ -334,6 +372,10 @@ TEST_CASE("JSON pointers")
 
                 CHECK_THROWS_WITH_AS(j[jp] = 1, throw_msg.c_str(), json::out_of_range&);
                 CHECK_THROWS_WITH_AS(j_const[jp] == 1, throw_msg.c_str(), json::out_of_range&);
+
+                // #5395: contains() must not throw for a reference token exceeding size_type's max
+                CHECK(!j.contains(jp));
+                CHECK(!j_const.contains(jp));
             }
 
             DOCTEST_MSVC_SUPPRESS_WARNING_POP

tests/src/unit-modifiers.cpp

@@ -641,20 +641,6 @@ TEST_CASE("modifiers")
                 CHECK_THROWS_WITH_AS(j_array.insert(j_array.end(), j_other_array.begin(), j_other_array2.end()), "[json.exception.invalid_iterator.210] iterators do not fit",
                                      json::invalid_iterator&);
             }
-
-            SECTION("iterators not pointing into an array")
-            {
-                json j_object2 = {{"k", 1}, {"l", 2}};
-                json j_primitive = 5;
-                json j_null;
-
-                CHECK_THROWS_WITH_AS(j_array.insert(j_array.begin(), j_object2.begin(), j_object2.end()), "[json.exception.invalid_iterator.202] iterators first and last must point to arrays",
-                                     json::invalid_iterator&);
-                CHECK_THROWS_WITH_AS(j_array.insert(j_array.begin(), j_primitive.begin(), j_primitive.end()), "[json.exception.invalid_iterator.202] iterators first and last must point to arrays",
-                                     json::invalid_iterator&);
-                CHECK_THROWS_WITH_AS(j_array.insert(j_array.begin(), j_null.begin(), j_null.end()), "[json.exception.invalid_iterator.202] iterators first and last must point to arrays",
-                                     json::invalid_iterator&);
-            }
         }
 
         SECTION("range for object")

tests/src/unit-no-macro-leak.cpp

@@ -0,0 +1,34 @@
+//     __ _____ _____ _____
+//  __|  |   __|     |   | |  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
+
+// This file makes sure that none of the internal JSON_HEDLEY_* macros (vendored
+// from https://nemequ.github.io/hedley/, see
+// include/nlohmann/thirdparty/hedley/hedley.hpp) leak into the including
+// translation unit. include/nlohmann/detail/macro_unscope.hpp is supposed to
+// #undef every JSON_HEDLEY_* macro (via hedley_undef.hpp) once json.hpp has
+// been fully processed. See https://github.com/nlohmann/json/issues/5408,
+// where JSON_HEDLEY_PRAGMA, JSON_HEDLEY_PREDICT_TRUE, JSON_HEDLEY_PREDICT_FALSE,
+// and JSON_HEDLEY_CLANG_HAS_DECLSPEC_ATTRIBUTE escaped this cleanup because
+// hedley_undef.hpp had no matching #undef for them.
+//
+// hedley_undef_checks.inc (included below) is generated at CMake configure/
+// build time by cmake/scripts/gen_hedley_undef_check.cmake, which derives the
+// full list of JSON_HEDLEY_* macro names directly from hedley.hpp. That way
+// this test covers every macro Hedley actually defines -- not a hardcoded
+// snapshot that would silently go stale the next time `make update_hedley`
+// runs -- and can never drift from the vendored header.
+
+#include "doctest_compatibility.h"
+
+#include <nlohmann/json.hpp>
+
+TEST_CASE("JSON_HEDLEY macros do not leak after including json.hpp")
+{
+#include "hedley_undef_checks.inc"
+    CHECK(true); // keep an assertion when nothing leaked
+}

tests/src/unit-ordered_json.cpp

@@ -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);
-    }
-}

tests/src/unit-regression1.cpp

@@ -29,10 +29,7 @@ using nlohmann::json;
 #include <limits>
 #include <cstdio>
 #include "make_test_data_available.hpp"
-
+#include "test_utils.hpp"
-#ifdef JSON_HAS_CPP_17
-    #include <variant>
-#endif
 
 #include "fifo_map.hpp"
 
@@ -1373,7 +1370,8 @@ TEST_CASE("regression tests 1")
         std::array<uint8_t, 28> key1 = {{ 103, 92, 117, 48, 48, 48, 55, 92, 114, 215, 126, 214, 95, 92, 34, 174, 40, 71, 38, 174, 40, 71, 38, 223, 134, 247, 127, 0 }};
         std::string const key1_str(reinterpret_cast<char*>(key1.data()));
         json const j = key1_str;
-        CHECK_THROWS_WITH_AS(j.dump(), "[json.exception.type_error.316] invalid UTF-8 byte at index 10: 0x7E", json::type_error&);
+        // dump() is nodiscard; the exception is thrown by dump() itself before it would return
+        CHECK_THROWS_WITH_AS(utils::ignore_return_value(j.dump()), "[json.exception.type_error.316] invalid UTF-8 byte at index 10: 0x7E", json::type_error&);
     }
 
 #if JSON_USE_IMPLICIT_CONVERSIONS

tests/src/unit-regression2.cpp

@@ -31,6 +31,8 @@ using ordered_json = nlohmann::ordered_json;
 #include <type_traits>
 #include <utility>
 
+#include "test_utils.hpp"
+
 #ifdef JSON_HAS_CPP_17
     #include <any>
     #include <variant>
@@ -639,7 +641,8 @@ TEST_CASE("regression tests 2")
                 s += static_cast<char>(i);
             }
             dump_test["1"] = s;
-            dump_test.dump(-1, ' ', true, nlohmann::json::error_handler_t::replace);
+            // dump() is nodiscard; this only checks that dumping does not throw/crash
+            utils::ignore_return_value(dump_test.dump(-1, ' ', true, nlohmann::json::error_handler_t::replace));
         }
     }
 
@@ -731,12 +734,14 @@ TEST_CASE("regression tests 2")
     {
         const std::array<unsigned char, 23> data = {{0x81, 0xA4, 0x64, 0x61, 0x74, 0x61, 0xC4, 0x0F, 0x33, 0x30, 0x30, 0x32, 0x33, 0x34, 0x30, 0x31, 0x30, 0x37, 0x30, 0x35, 0x30, 0x31, 0x30}};
         const json j = json::from_msgpack(data.data(), data.size());
+        // dump() is nodiscard; this only checks that dumping does not throw
         CHECK_NOTHROW(
+            utils::ignore_return_value(
                 j.dump(4,                             // Indent
                        ' ',                           // Indent char
                        false,                         // Ensure ascii
                        json::error_handler_t::strict  // Error
-                  ));
+                      )));
     }
 
     SECTION("PR #2181 - regression bug with lvalue")
@@ -1566,106 +1571,4 @@ 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}");
-    }
-}
-
-TEST_CASE("regression test - excessive binary container size honors allow_exceptions=false")
-{
-    // CBOR array with declared length 2^63
-    const std::vector<std::uint8_t> cbor = {0x9b, 0x80, 0, 0, 0, 0, 0, 0, 0};
-    // CBOR map with declared length 2^63
-    const std::vector<std::uint8_t> cbor_m = {0xbb, 0x80, 0, 0, 0, 0, 0, 0, 0};
-    // UBJSON array with declared length 2^63-1
-    const std::vector<std::uint8_t> ubj = {'[', '#', 'L', 0x7f, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff};
-    // BJData array with declared length 2^63-1 (little endian)
-    const std::vector<std::uint8_t> bjd = {'[', '#', 'L', 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x7f};
-
-    // allow_exceptions=false must report failure instead of throwing/aborting
-    CHECK(json::from_cbor(cbor, true, false).is_discarded());
-    CHECK(json::from_cbor(cbor_m, true, false).is_discarded());
-    CHECK(json::from_ubjson(ubj, true, false).is_discarded());
-    CHECK(json::from_bjdata(bjd, true, false).is_discarded());
-
-    // allow_exceptions=true (the default) must still throw exactly as before.
-    // The exact message text is not checked here: on platforms where
-    // std::size_t is 32-bit, the CBOR reader's own length-narrowing check
-    // (get_cbor_container_size(), unrelated to this fix) intercepts a
-    // declared length of 2^63 before it ever reaches the check this test
-    // targets, with different (but equally valid, and already correct)
-    // wording -- see unit-cbor.cpp for coverage of that message.
-    json _;
-    CHECK_THROWS_AS(_ = json::from_cbor(cbor), json::out_of_range);
-
-    // regression guard: a genuinely truncated CBOR input must remain discarded
-    CHECK(json::from_cbor(std::vector<std::uint8_t> {0x9b, 0, 0, 0, 0, 0, 0, 0, 0x02}, true, false).is_discarded());
-}
-
 DOCTEST_CLANG_SUPPRESS_WARNING_POP

tests/src/unit-serialization.cpp

@@ -15,6 +15,8 @@ using nlohmann::json;
 #include <sstream>
 #include <iomanip>
 
+#include "test_utils.hpp"
+
 TEST_CASE("serialization")
 {
     SECTION("operator<<")
@@ -84,8 +86,9 @@ TEST_CASE("serialization")
         {
             const json j = "ä\xA9ü";
 
-            CHECK_THROWS_WITH_AS(j.dump(), "[json.exception.type_error.316] invalid UTF-8 byte at index 2: 0xA9", json::type_error&);
+            // dump() is nodiscard; the exception is thrown by dump() itself before it would return
-            CHECK_THROWS_WITH_AS(j.dump(1, ' ', false, json::error_handler_t::strict), "[json.exception.type_error.316] invalid UTF-8 byte at index 2: 0xA9", json::type_error&);
+            CHECK_THROWS_WITH_AS(utils::ignore_return_value(j.dump()), "[json.exception.type_error.316] invalid UTF-8 byte at index 2: 0xA9", json::type_error&);
+            CHECK_THROWS_WITH_AS(utils::ignore_return_value(j.dump(1, ' ', false, json::error_handler_t::strict)), "[json.exception.type_error.316] invalid UTF-8 byte at index 2: 0xA9", json::type_error&);
             CHECK(j.dump(-1, ' ', false, json::error_handler_t::ignore) == "\"äü\"");
             CHECK(j.dump(-1, ' ', false, json::error_handler_t::replace) == "\"ä\xEF\xBF\xBDü\"");
             CHECK(j.dump(-1, ' ', true, json::error_handler_t::replace) == "\"\\u00e4\\ufffd\\u00fc\"");
@@ -95,8 +98,9 @@ TEST_CASE("serialization")
         {
             const json j = "123\xC2";
 
-            CHECK_THROWS_WITH_AS(j.dump(), "[json.exception.type_error.316] incomplete UTF-8 string; last byte: 0xC2", json::type_error&);
+            // dump() is nodiscard; the exception is thrown by dump() itself before it would return
-            CHECK_THROWS_AS(j.dump(1, ' ', false, json::error_handler_t::strict), json::type_error&);
+            CHECK_THROWS_WITH_AS(utils::ignore_return_value(j.dump()), "[json.exception.type_error.316] incomplete UTF-8 string; last byte: 0xC2", json::type_error&);
+            CHECK_THROWS_AS(utils::ignore_return_value(j.dump(1, ' ', false, json::error_handler_t::strict)), json::type_error&);
             CHECK(j.dump(-1, ' ', false, json::error_handler_t::ignore) == "\"123\"");
             CHECK(j.dump(-1, ' ', false, json::error_handler_t::replace) == "\"123\xEF\xBF\xBD\"");
             CHECK(j.dump(-1, ' ', true, json::error_handler_t::replace) == "\"123\\ufffd\"");
@@ -106,8 +110,9 @@ TEST_CASE("serialization")
         {
             const json j = "123\xF1\xB0\x34\x35\x36";
 
-            CHECK_THROWS_WITH_AS(j.dump(), "[json.exception.type_error.316] invalid UTF-8 byte at index 5: 0x34", json::type_error&);
+            // dump() is nodiscard; the exception is thrown by dump() itself before it would return
-            CHECK_THROWS_AS(j.dump(1, ' ', false, json::error_handler_t::strict), json::type_error&);
+            CHECK_THROWS_WITH_AS(utils::ignore_return_value(j.dump()), "[json.exception.type_error.316] invalid UTF-8 byte at index 5: 0x34", json::type_error&);
+            CHECK_THROWS_AS(utils::ignore_return_value(j.dump(1, ' ', false, json::error_handler_t::strict)), json::type_error&);
             CHECK(j.dump(-1, ' ', false, json::error_handler_t::ignore) == "\"123456\"");
             CHECK(j.dump(-1, ' ', false, json::error_handler_t::replace) == "\"123\xEF\xBF\xBD\x34\x35\x36\"");
             CHECK(j.dump(-1, ' ', true, json::error_handler_t::replace) == "\"123\\ufffd456\"");

tests/src/unit-unicode1.cpp

@@ -17,6 +17,7 @@ using nlohmann::json;
 #include <sstream>
 #include <iomanip>
 #include "make_test_data_available.hpp"
+#include "test_utils.hpp"
 
 TEST_CASE("Unicode (1/5)" * doctest::skip())
 {
@@ -240,7 +241,8 @@ void roundtrip(bool success_expected, const std::string& s)
     if (success_expected)
     {
         // serialization succeeds
-        CHECK_NOTHROW(j.dump());
+        // dump() is nodiscard; this only checks that dumping does not throw
+        CHECK_NOTHROW(utils::ignore_return_value(j.dump()));
 
         // exclude parse test for U+0000
         if (s[0] != '\0')
@@ -259,7 +261,8 @@ void roundtrip(bool success_expected, const std::string& s)
     else
     {
         // serialization fails
-        CHECK_THROWS_AS(j.dump(), json::type_error&);
+        // dump() is nodiscard; the exception is thrown by dump() itself before it would return
+        CHECK_THROWS_AS(utils::ignore_return_value(j.dump()), json::type_error&);
 
         // parsing JSON text fails
         CHECK_THROWS_AS(_ = json::parse(ps), json::parse_error&);

tests/src/unit-unicode2.cpp

@@ -19,6 +19,7 @@ using nlohmann::json;
 #include <iostream>
 #include <iomanip>
 #include "make_test_data_available.hpp"
+#include "test_utils.hpp"
 
 // this test suite uses static variables with non-trivial destructors
 DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
@@ -97,7 +98,8 @@ void check_utf8dump(bool success_expected, int byte1, int byte2 = -1, int byte3
     else
     {
         // strict mode must throw if success is not expected
-        CHECK_THROWS_AS(j.dump(), json::type_error&);
+        // dump() is nodiscard; the exception is thrown by dump() itself before it would return
+        CHECK_THROWS_AS(utils::ignore_return_value(j.dump()), json::type_error&);
         // ignore and replace must create different dumps
         CHECK(s_ignored != s_replaced);
 

tests/src/unit-unicode3.cpp

@@ -19,6 +19,7 @@ using nlohmann::json;
 #include <iostream>
 #include <iomanip>
 #include "make_test_data_available.hpp"
+#include "test_utils.hpp"
 
 // this test suite uses static variables with non-trivial destructors
 DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
@@ -97,7 +98,8 @@ void check_utf8dump(bool success_expected, int byte1, int byte2 = -1, int byte3
     else
     {
         // strict mode must throw if success is not expected
-        CHECK_THROWS_AS(j.dump(), json::type_error&);
+        // dump() is nodiscard; the exception is thrown by dump() itself before it would return
+        CHECK_THROWS_AS(utils::ignore_return_value(j.dump()), json::type_error&);
         // ignore and replace must create different dumps
         CHECK(s_ignored != s_replaced);
 

tests/src/unit-unicode4.cpp

@@ -19,6 +19,7 @@ using nlohmann::json;
 #include <iostream>
 #include <iomanip>
 #include "make_test_data_available.hpp"
+#include "test_utils.hpp"
 
 // this test suite uses static variables with non-trivial destructors
 DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
@@ -97,7 +98,8 @@ void check_utf8dump(bool success_expected, int byte1, int byte2 = -1, int byte3
     else
     {
         // strict mode must throw if success is not expected
-        CHECK_THROWS_AS(j.dump(), json::type_error&);
+        // dump() is nodiscard; the exception is thrown by dump() itself before it would return
+        CHECK_THROWS_AS(utils::ignore_return_value(j.dump()), json::type_error&);
         // ignore and replace must create different dumps
         CHECK(s_ignored != s_replaced);
 

tests/src/unit-unicode5.cpp

@@ -19,6 +19,7 @@ using nlohmann::json;
 #include <iostream>
 #include <iomanip>
 #include "make_test_data_available.hpp"
+#include "test_utils.hpp"
 
 // this test suite uses static variables with non-trivial destructors
 DOCTEST_CLANG_SUPPRESS_WARNING_PUSH
@@ -97,7 +98,8 @@ void check_utf8dump(bool success_expected, int byte1, int byte2 = -1, int byte3
     else
     {
         // strict mode must throw if success is not expected
-        CHECK_THROWS_AS(j.dump(), json::type_error&);
+        // dump() is nodiscard; the exception is thrown by dump() itself before it would return
+        CHECK_THROWS_AS(utils::ignore_return_value(j.dump()), json::type_error&);
         // ignore and replace must create different dumps
         CHECK(s_ignored != s_replaced);